From f15f7a674b309eff00a66d16449f8d5abb1c6682 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 13 Jun 2018 14:46:00 +0100 Subject: [PATCH 001/558] [dailymotion] add support for password protected videos(closes #9789) --- youtube_dl/extractor/dailymotion.py | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index de27fffd4..0afb6a158 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -1,9 +1,14 @@ # coding: utf-8 from __future__ import unicode_literals -import re -import json +import base64 +import hashlib import itertools +import json +import random +import re +import string +import struct from .common import InfoExtractor @@ -64,7 +69,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor): 'uploader': 'Deadline', 'uploader_id': 'x1xm8ri', 'age_limit': 0, - 'view_count': int, }, }, { 'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames', @@ -167,6 +171,17 @@ class DailymotionIE(DailymotionBaseInfoExtractor): player = self._parse_json(player_v5, video_id) metadata = player['metadata'] + if metadata.get('error', {}).get('type') == 'password_protected': + password = self._downloader.params.get('videopassword') + if password: + r = int(metadata['id'][1:], 36) + us64e = lambda x: base64.urlsafe_b64encode(x).decode().strip('=') + t = ''.join(random.choice(string.ascii_letters) for i in range(10)) + n = us64e(struct.pack('I', r)) + i = us64e(hashlib.md5(('%s%d%s' % (password, r, t)).encode()).digest()) + metadata = self._download_json( + 'http://www.dailymotion.com/player/metadata/video/p' + i + t + n, video_id) + self._check_error(metadata) formats = [] @@ -302,8 +317,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor): def _check_error(self, info): error = info.get('error') - if info.get('error') is not None: - title = error['title'] + if error: + title = error.get('title') or error['message'] # See https://developer.dailymotion.com/api#access-error if error.get('code') == 'DM007': self.raise_geo_restricted(msg=title) From 18d66f04107b584c2d6ee6c175c44c7f2d81ecba Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 13 Jun 2018 15:12:42 +0100 Subject: [PATCH 002/558] [dailymotion] use compat_struct_pack --- youtube_dl/extractor/dailymotion.py | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 0afb6a158..9a74906cb 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -8,10 +8,9 @@ import json import random import re import string -import struct from .common import InfoExtractor - +from ..compat import compat_struct_pack from ..utils import ( determine_ext, error_to_compat_str, @@ -177,7 +176,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor): r = int(metadata['id'][1:], 36) us64e = lambda x: base64.urlsafe_b64encode(x).decode().strip('=') t = ''.join(random.choice(string.ascii_letters) for i in range(10)) - n = us64e(struct.pack('I', r)) + n = us64e(compat_struct_pack('I', r)) i = us64e(hashlib.md5(('%s%d%s' % (password, r, t)).encode()).digest()) metadata = self._download_json( 'http://www.dailymotion.com/player/metadata/video/p' + i + t + n, video_id) From aa56061627f9871b4793414b71a26976befd3a9c Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 13 Jun 2018 16:46:59 +0100 Subject: [PATCH 003/558] [discoverynetworks] Add support for disco-api videos(closes #16724) --- youtube_dl/extractor/discoverynetworks.py | 19 ++- youtube_dl/extractor/dplay.py | 137 +++++++++++----------- 2 files changed, 87 insertions(+), 69 deletions(-) diff --git a/youtube_dl/extractor/discoverynetworks.py b/youtube_dl/extractor/discoverynetworks.py index b6653784c..fba1ef221 100644 --- a/youtube_dl/extractor/discoverynetworks.py +++ b/youtube_dl/extractor/discoverynetworks.py @@ -3,8 +3,8 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor from .brightcove import BrightcoveLegacyIE +from .dplay import DPlayIE from ..compat import ( compat_parse_qs, compat_urlparse, @@ -12,8 +12,13 @@ from ..compat import ( from ..utils import smuggle_url -class DiscoveryNetworksDeIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:discovery|tlc|animalplanet|dmax)\.de/(?:.*#(?P\d+)|(?:[^/]+/)*videos/(?P[^/?#]+))' +class DiscoveryNetworksDeIE(DPlayIE): + _VALID_URL = r'''(?x)https?://(?:www\.)?(?P<site>discovery|tlc|animalplanet|dmax)\.de/ + (?: + .*\#(?P<id>\d+)| + (?:[^/]+/)*videos/(?P<display_id>[^/?#]+)| + programme/(?P<programme>[^/]+)/video/(?P<alternate_id>[^/]+) + )''' _TESTS = [{ 'url': 'http://www.tlc.de/sendungen/breaking-amish/videos/#3235167922001', @@ -40,6 +45,14 @@ class DiscoveryNetworksDeIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) + alternate_id = mobj.group('alternate_id') + if alternate_id: + self._initialize_geo_bypass({ + 'countries': ['DE'], + }) + return self._get_disco_api_info( + url, '%s/%s' % (mobj.group('programme'), alternate_id), + 'sonic-eu1-prod.disco-api.com', mobj.group('site') + 'de') brightcove_id = mobj.group('id') if not brightcove_id: title = mobj.group('title') diff --git a/youtube_dl/extractor/dplay.py b/youtube_dl/extractor/dplay.py index 8e0374320..fe47f6dce 100644 --- a/youtube_dl/extractor/dplay.py +++ b/youtube_dl/extractor/dplay.py @@ -97,6 +97,75 @@ class DPlayIE(InfoExtractor): 'only_matching': True, }] + def _get_disco_api_info(self, url, display_id, disco_host, realm): + disco_base = 'https://' + disco_host + token = self._download_json( + '%s/token' % disco_base, display_id, 'Downloading token', + query={ + 'realm': realm, + })['data']['attributes']['token'] + headers = { + 'Referer': url, + 'Authorization': 'Bearer ' + token, + } + video = self._download_json( + '%s/content/videos/%s' % (disco_base, display_id), display_id, + headers=headers, query={ + 'include': 'show' + }) + video_id = video['data']['id'] + info = video['data']['attributes'] + title = info['name'] + formats = [] + for format_id, format_dict in self._download_json( + '%s/playback/videoPlaybackInfo/%s' % (disco_base, video_id), + display_id, headers=headers)['data']['attributes']['streaming'].items(): + if not isinstance(format_dict, dict): + continue + format_url = format_dict.get('url') + if not format_url: + continue + ext = determine_ext(format_url) + if format_id == 'dash' or ext == 'mpd': + formats.extend(self._extract_mpd_formats( + format_url, display_id, mpd_id='dash', fatal=False)) + elif format_id == 'hls' or ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + format_url, display_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls', + fatal=False)) + else: + formats.append({ + 'url': format_url, + 'format_id': format_id, + }) + self._sort_formats(formats) + + series = None + try: + included = video.get('included') + if isinstance(included, list): + show = next(e for e in included if e.get('type') == 'show') + series = try_get( + show, lambda x: x['attributes']['name'], compat_str) + except StopIteration: + pass + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': info.get('description'), + 'duration': float_or_none( + info.get('videoDuration'), scale=1000), + 'timestamp': unified_timestamp(info.get('publishStart')), + 'series': series, + 'season_number': int_or_none(info.get('seasonNumber')), + 'episode_number': int_or_none(info.get('episodeNumber')), + 'age_limit': int_or_none(info.get('minimum_age')), + 'formats': formats, + } + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) display_id = mobj.group('id') @@ -113,72 +182,8 @@ class DPlayIE(InfoExtractor): if not video_id: host = mobj.group('host') - disco_base = 'https://disco-api.%s' % host - self._download_json( - '%s/token' % disco_base, display_id, 'Downloading token', - query={ - 'realm': host.replace('.', ''), - }) - video = self._download_json( - '%s/content/videos/%s' % (disco_base, display_id), display_id, - headers={ - 'Referer': url, - 'x-disco-client': 'WEB:UNKNOWN:dplay-client:0.0.1', - }, query={ - 'include': 'show' - }) - video_id = video['data']['id'] - info = video['data']['attributes'] - title = info['name'] - formats = [] - for format_id, format_dict in self._download_json( - '%s/playback/videoPlaybackInfo/%s' % (disco_base, video_id), - display_id)['data']['attributes']['streaming'].items(): - if not isinstance(format_dict, dict): - continue - format_url = format_dict.get('url') - if not format_url: - continue - ext = determine_ext(format_url) - if format_id == 'dash' or ext == 'mpd': - formats.extend(self._extract_mpd_formats( - format_url, display_id, mpd_id='dash', fatal=False)) - elif format_id == 'hls' or ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - format_url, display_id, 'mp4', - entry_protocol='m3u8_native', m3u8_id='hls', - fatal=False)) - else: - formats.append({ - 'url': format_url, - 'format_id': format_id, - }) - self._sort_formats(formats) - - series = None - try: - included = video.get('included') - if isinstance(included, list): - show = next(e for e in included if e.get('type') == 'show') - series = try_get( - show, lambda x: x['attributes']['name'], compat_str) - except StopIteration: - pass - - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, - 'description': info.get('description'), - 'duration': float_or_none( - info.get('videoDuration'), scale=1000), - 'timestamp': unified_timestamp(info.get('publishStart')), - 'series': series, - 'season_number': int_or_none(info.get('seasonNumber')), - 'episode_number': int_or_none(info.get('episodeNumber')), - 'age_limit': int_or_none(info.get('minimum_age')), - 'formats': formats, - } + return self._get_disco_api_info( + url, display_id, 'disco-api.' + host, host.replace('.', '')) info = self._download_json( 'http://%s/api/v2/ajax/videos?video_id=%s' % (domain, video_id), From 03eef0f03259bfcae284a56d00035950dd54f316 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 14 Jun 2018 01:22:42 +0700 Subject: [PATCH 004/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/ChangeLog b/ChangeLog index b808ad6ba..11812b195 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,19 @@ +version <unreleased> + +Core +* [downloader/http] Fix retry on error when streaming to stdout (#16699) + +Extractors ++ [discoverynetworks] Add support for disco-api videos (#16724) ++ [dailymotion] Add support for password protected videos (#9789) ++ [abc:iview] Add support for livestreams (#12354) +* [abc:iview] Fix extraction (#16704) ++ [crackle] Add support for sonycrackle.com (#16698) ++ [tvnet] Add support for tvnet.gov.vn (#15462) +* [nrk] Update API hosts and try all previously known ones (#16690) +* [wimp] Fix Youtube embeds extraction + + version 2018.06.11 Extractors From c797db4a2fb7c8e41485bac74fe7f78295bab556 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 14 Jun 2018 01:24:53 +0700 Subject: [PATCH 005/558] release 2018.06.14 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 1 + youtube_dl/version.py | 2 +- 4 files changed, 6 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index d5be8003b..1cfb54bfd 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.06.11*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.06.11** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.06.14*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.06.14** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.06.11 +[debug] youtube-dl version 2018.06.14 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 11812b195..062000594 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.06.14 Core * [downloader/http] Fix retry on error when streaming to stdout (#16699) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index e1a9f2236..705279ac1 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -893,6 +893,7 @@ - **tvigle**: Интернет-телевидение Tvigle.ru - **tvland.com** - **TVN24** + - **TVNet** - **TVNoe** - **TVNow** - **TVNowList** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index e72f42cf2..1533dceb4 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.06.11' +__version__ = '2018.06.14' From 61cb66830f5097b528aab381eb6b343a89f73cbc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 14 Jun 2018 22:40:30 +0700 Subject: [PATCH 006/558] [bilibili] Restrict cid regex (closes #16638, closes #16734) --- youtube_dl/extractor/bilibili.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py index 3e3348ef5..4d6b051fe 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -114,7 +114,7 @@ class BiliBiliIE(InfoExtractor): if 'anime/' not in url: cid = self._search_regex( - r'cid(?:["\']:|=)(\d+)', webpage, 'cid', + r'\bcid(?:["\']:|=)(\d+)', webpage, 'cid', default=None ) or compat_parse_qs(self._search_regex( [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)', From 9b0b62753432244fd062d99cc5dc604d6bad7877 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 15 Jun 2018 02:59:15 +0700 Subject: [PATCH 007/558] [downloader/rtmp] Fix downloading in verbose mode (closes #16736) --- youtube_dl/downloader/rtmp.py | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/youtube_dl/downloader/rtmp.py b/youtube_dl/downloader/rtmp.py index 9e0ddbb18..fbb7f51b0 100644 --- a/youtube_dl/downloader/rtmp.py +++ b/youtube_dl/downloader/rtmp.py @@ -24,13 +24,12 @@ class RtmpFD(FileDownloader): def real_download(self, filename, info_dict): def run_rtmpdump(args): start = time.time() + resume_percent = None + resume_downloaded_data_len = None proc = subprocess.Popen(args, stderr=subprocess.PIPE) cursor_in_new_line = True - - def dl(): - resume_percent = None - resume_downloaded_data_len = None - proc_stderr_closed = False + proc_stderr_closed = False + try: while not proc_stderr_closed: # read line from stderr line = '' @@ -90,12 +89,8 @@ class RtmpFD(FileDownloader): self.to_screen('') cursor_in_new_line = True self.to_screen('[rtmpdump] ' + line) - - try: - dl() finally: proc.wait() - if not cursor_in_new_line: self.to_screen('') return proc.returncode From 87f89dacddfa46399aea9252ca078f5f386dce38 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 16 Jun 2018 02:55:20 +0700 Subject: [PATCH 008/558] [pbs] Improve extraction (closes #16623, closes #16684) --- youtube_dl/extractor/pbs.py | 57 ++++++++++++++++++++++++++++++++----- 1 file changed, 50 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index 8d6f2dd3d..52ab2f158 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( ExtractorError, determine_ext, @@ -375,6 +376,35 @@ class PBSIE(InfoExtractor): }, 'expected_warnings': ['HTTP Error 403: Forbidden'], }, + { + 'url': 'https://www.pbs.org/wgbh/masterpiece/episodes/victoria-s2-e1/', + 'info_dict': { + 'id': '3007193718', + 'ext': 'mp4', + 'title': "Victoria - A Soldier's Daughter / The Green-Eyed Monster", + 'description': 'md5:37efbac85e0c09b009586523ec143652', + 'duration': 6292, + 'thumbnail': r're:^https?://.*\.(?:jpg|JPG)$', + }, + 'params': { + 'skip_download': True, + }, + 'expected_warnings': ['HTTP Error 403: Forbidden'], + }, + { + 'url': 'https://player.pbs.org/partnerplayer/tOz9tM5ljOXQqIIWke53UA==/', + 'info_dict': { + 'id': '3011407934', + 'ext': 'mp4', + 'title': 'Stories from the Stage - Road Trip', + 'duration': 1619, + 'thumbnail': r're:^https?://.*\.(?:jpg|JPG)$', + }, + 'params': { + 'skip_download': True, + }, + 'expected_warnings': ['HTTP Error 403: Forbidden'], + }, { 'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true', 'only_matching': True, @@ -438,6 +468,7 @@ class PBSIE(InfoExtractor): r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>', # jwplayer r"(?s)window\.PBS\.playerConfig\s*=\s*{.*?id\s*:\s*'([0-9]+)',", r'<div[^>]+\bdata-cove-id=["\'](\d+)"', # http://www.pbs.org/wgbh/roadshow/watch/episode/2105-indianapolis-hour-2/ + r'<iframe[^>]+\bsrc=["\'](?:https?:)?//video\.pbs\.org/widget/partnerplayer/(\d+)', # https://www.pbs.org/wgbh/masterpiece/episodes/victoria-s2-e1/ ] media_id = self._search_regex( @@ -472,7 +503,8 @@ class PBSIE(InfoExtractor): if not url: url = self._og_search_url(webpage) - mobj = re.match(self._VALID_URL, url) + mobj = re.match( + self._VALID_URL, self._proto_relative_url(url.strip())) player_id = mobj.group('player_id') if not display_id: @@ -482,13 +514,27 @@ class PBSIE(InfoExtractor): url, display_id, note='Downloading player page', errnote='Could not download player page') video_id = self._search_regex( - r'<div\s+id="video_([0-9]+)"', player_page, 'video ID') + r'<div\s+id=["\']video_(\d+)', player_page, 'video ID', + default=None) + if not video_id: + video_info = self._extract_video_data( + player_page, 'video data', display_id) + video_id = compat_str( + video_info.get('id') or video_info['contentID']) else: video_id = mobj.group('id') display_id = video_id return video_id, display_id, None, description + def _extract_video_data(self, string, name, video_id, fatal=True): + return self._parse_json( + self._search_regex( + [r'(?s)PBS\.videoData\s*=\s*({.+?});\n', + r'window\.videoBridge\s*=\s*({.+?});'], + string, name, default='{}'), + video_id, transform_source=js_to_json, fatal=fatal) + def _real_extract(self, url): video_id, display_id, upload_date, description = self._extract_webpage(url) @@ -519,11 +565,8 @@ class PBSIE(InfoExtractor): 'http://player.pbs.org/%s/%s' % (page, video_id), display_id, 'Downloading %s page' % page, fatal=False) if player: - video_info = self._parse_json( - self._search_regex( - [r'(?s)PBS\.videoData\s*=\s*({.+?});\n', r'window\.videoBridge\s*=\s*({.+?});'], - player, '%s video data' % page, default='{}'), - display_id, transform_source=js_to_json, fatal=False) + video_info = self._extract_video_data( + player, '%s video data' % page, display_id, fatal=False) if video_info: extract_redirect_urls(video_info) if not info: From 81c5df4f2ce33cff5d47b9ee29edf08b50998a53 Mon Sep 17 00:00:00 2001 From: Urgau <lolo.branstett@numericable.fr> Date: Sat, 16 Jun 2018 00:08:44 +0200 Subject: [PATCH 009/558] [vidzi] Fix extraction (closes #16678) --- youtube_dl/extractor/vidzi.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/vidzi.py b/youtube_dl/extractor/vidzi.py index 9026e778c..d70283479 100644 --- a/youtube_dl/extractor/vidzi.py +++ b/youtube_dl/extractor/vidzi.py @@ -54,7 +54,8 @@ class VidziIE(InfoExtractor): self._search_regex( r'setup\(([^)]+)\)', code, 'jwplayer data', default=NO_DEFAULT if num == len(codes) else '{}'), - video_id, transform_source=js_to_json) + video_id, transform_source=lambda s: js_to_json( + re.sub(r'\s*\+\s*window\[.+?\]', '', s))) if jwplayer_data: break From 734d461ca04a9f271dd463aa75d44ac82377057e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 16 Jun 2018 21:14:36 +0700 Subject: [PATCH 010/558] [expressen] Add extractor --- youtube_dl/extractor/expressen.py | 77 ++++++++++++++++++++++++++++++ youtube_dl/extractor/extractors.py | 1 + 2 files changed, 78 insertions(+) create mode 100644 youtube_dl/extractor/expressen.py diff --git a/youtube_dl/extractor/expressen.py b/youtube_dl/extractor/expressen.py new file mode 100644 index 000000000..f61178012 --- /dev/null +++ b/youtube_dl/extractor/expressen.py @@ -0,0 +1,77 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + int_or_none, + unescapeHTML, + unified_timestamp, +) + + +class ExpressenIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?expressen\.se/tv/(?:[^/]+/)*(?P<id>[^/?#&]+)' + _TESTS = [{ + 'url': 'https://www.expressen.se/tv/ledare/ledarsnack/ledarsnack-om-arbetslosheten-bland-kvinnor-i-speciellt-utsatta-omraden/', + 'md5': '2fbbe3ca14392a6b1b36941858d33a45', + 'info_dict': { + 'id': '8690962', + 'ext': 'mp4', + 'title': 'Ledarsnack: Om arbetslösheten bland kvinnor i speciellt utsatta områden', + 'description': 'md5:f38c81ff69f3de4d269bbda012fcbbba', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 788, + 'timestamp': 1526639109, + 'upload_date': '20180518', + }, + }, { + 'url': 'https://www.expressen.se/tv/kultur/kulturdebatt-med-expressens-karin-olsson/', + 'only_matching': True, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + def extract_data(name): + return self._parse_json( + self._search_regex( + r'data-%s=(["\'])(?P<value>(?:(?!\1).)+)\1' % name, + webpage, 'info', group='value'), + display_id, transform_source=unescapeHTML) + + info = extract_data('video-tracking-info') + video_id = info['videoId'] + + data = extract_data('article-data') + stream = data['stream'] + + if determine_ext(stream) == 'm3u8': + formats = self._extract_m3u8_formats( + stream, display_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + else: + formats = [{ + 'url': stream, + }] + self._sort_formats(formats) + + title = info.get('titleRaw') or data['title'] + description = info.get('descriptionRaw') + thumbnail = info.get('socialMediaImage') or data.get('image') + duration = int_or_none(info.get('videoTotalSecondsDuration') or + data.get('totalSecondsDuration')) + timestamp = unified_timestamp(info.get('publishDate')) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'timestamp': timestamp, + 'formats': formats, + } diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index d4583b8e4..c3e6daa24 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -335,6 +335,7 @@ from .esri import EsriVideoIE from .europa import EuropaIE from .everyonesmixtape import EveryonesMixtapeIE from .expotv import ExpoTVIE +from .expressen import ExpressenIE from .extremetube import ExtremeTubeIE from .eyedotv import EyedoTVIE from .facebook import ( From 764cd4e6f3450997eb0499b68b17b580a5e074f3 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 17 Jun 2018 02:43:24 +0100 Subject: [PATCH 011/558] [rtbf] improve extraction - add support for audio and live streams(closes #11923)(closes #9638) - extract HLS, DASH and all HTTP formats - extract subtitles - fixup specific http urls(fixes #16101) --- youtube_dl/extractor/rtbf.py | 127 ++++++++++++++++++++++++++--------- 1 file changed, 95 insertions(+), 32 deletions(-) diff --git a/youtube_dl/extractor/rtbf.py b/youtube_dl/extractor/rtbf.py index 28cc5522d..acff9766a 100644 --- a/youtube_dl/extractor/rtbf.py +++ b/youtube_dl/extractor/rtbf.py @@ -1,10 +1,14 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( - int_or_none, ExtractorError, + float_or_none, + int_or_none, + strip_or_none, ) @@ -14,20 +18,19 @@ class RTBFIE(InfoExtractor): (?: video/[^?]+\?.*\bid=| ouftivi/(?:[^/]+/)*[^?]+\?.*\bvideoId=| - auvio/[^/]+\?.*id= + auvio/[^/]+\?.*\b(?P<live>l)?id= )(?P<id>\d+)''' _TESTS = [{ 'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274', - 'md5': '799f334ddf2c0a582ba80c44655be570', + 'md5': '8c876a1cceeb6cf31b476461ade72384', 'info_dict': { 'id': '1921274', 'ext': 'mp4', 'title': 'Les Diables au coeur (épisode 2)', - 'description': 'Football - Diables Rouges', - 'duration': 3099, + 'description': '(du 25/04/2014)', + 'duration': 3099.54, 'upload_date': '20140425', - 'timestamp': 1398456336, - 'uploader': 'rtbfsport', + 'timestamp': 1398456300, } }, { # geo restricted @@ -39,6 +42,18 @@ class RTBFIE(InfoExtractor): }, { 'url': 'http://www.rtbf.be/auvio/detail_jeudi-en-prime-siegfried-bracke?id=2102996', 'only_matching': True, + }, { + # Live + 'url': 'https://www.rtbf.be/auvio/direct_pure-fm?lid=134775', + 'only_matching': True, + }, { + # Audio + 'url': 'https://www.rtbf.be/auvio/detail_cinq-heures-cinema?id=2360811', + 'only_matching': True, + }, { + # With Subtitle + 'url': 'https://www.rtbf.be/auvio/detail_les-carnets-du-bourlingueur?id=2361588', + 'only_matching': True, }] _IMAGE_HOST = 'http://ds1.ds.static.rtbf.be' _PROVIDERS = { @@ -53,46 +68,94 @@ class RTBFIE(InfoExtractor): ] def _real_extract(self, url): - video_id = self._match_id(url) - data = self._download_json( - 'http://www.rtbf.be/api/media/video?method=getVideoDetail&args[]=%s' % video_id, video_id) + live, media_id = re.match(self._VALID_URL, url).groups() + embed_page = self._download_webpage( + 'https://www.rtbf.be/auvio/embed/' + ('direct' if live else 'media'), + media_id, query={'id': media_id}) + data = self._parse_json(self._html_search_regex( + r'data-media="([^"]+)"', embed_page, 'media data'), media_id) error = data.get('error') if error: raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True) - data = data['data'] - provider = data.get('provider') if provider in self._PROVIDERS: return self.url_result(data['url'], self._PROVIDERS[provider]) + title = data['title'] + is_live = data.get('isLive') + if is_live: + title = self._live_title(title) + height_re = r'-(\d+)p\.' formats = [] - for key, format_id in self._QUALITIES: - format_url = data.get(key + 'Url') - if format_url: + + m3u8_url = data.get('urlHlsAes128') or data.get('urlHls') + if m3u8_url: + formats.extend(self._extract_m3u8_formats( + m3u8_url, media_id, 'mp4', m3u8_id='hls', fatal=False)) + + fix_url = lambda x: x.replace('//rtbf-vod.', '//rtbf.') if '/geo/drm/' in x else x + http_url = data.get('url') + if formats and http_url and re.search(height_re, http_url): + http_url = fix_url(http_url) + for m3u8_f in formats.copy(): + height = m3u8_f.get('height') + if not height: + continue + f = m3u8_f.copy() + del f['protocol'] + f.update({ + 'format_id': m3u8_f['format_id'].replace('hls-', 'http-'), + 'url': re.sub(height_re, '-%dp.' % height, http_url), + }) + formats.append(f) + else: + sources = data.get('sources') or {} + for key, format_id in self._QUALITIES: + format_url = sources.get(key) + if not format_url: + continue + height = int_or_none(self._search_regex( + height_re, format_url, 'height', default=None)) formats.append({ 'format_id': format_id, - 'url': format_url, + 'url': fix_url(format_url), + 'height': height, }) - thumbnails = [] - for thumbnail_id, thumbnail_url in data.get('thumbnail', {}).items(): - if thumbnail_id != 'default': - thumbnails.append({ - 'url': self._IMAGE_HOST + thumbnail_url, - 'id': thumbnail_id, - }) + mpd_url = data.get('urlDash') + if not data.get('drm') and mpd_url: + formats.extend(self._extract_mpd_formats( + mpd_url, media_id, mpd_id='dash', fatal=False)) + + audio_url = data.get('urlAudio') + if audio_url: + formats.append({ + 'format_id': 'audio', + 'url': audio_url, + 'vcodec': 'none', + }) + self._sort_formats(formats) + + subtitles = {} + for track in (data.get('tracks') or {}).values(): + sub_url = track.get('url') + if not sub_url: + continue + subtitles.setdefault(track.get('lang') or 'fr', []).append({ + 'url': sub_url, + }) return { - 'id': video_id, + 'id': media_id, 'formats': formats, - 'title': data['title'], - 'description': data.get('description') or data.get('subtitle'), - 'thumbnails': thumbnails, - 'duration': data.get('duration') or data.get('realDuration'), - 'timestamp': int_or_none(data.get('created')), - 'view_count': int_or_none(data.get('viewCount')), - 'uploader': data.get('channel'), - 'tags': data.get('tags'), + 'title': title, + 'description': strip_or_none(data.get('description')), + 'thumbnail': data.get('thumbnail'), + 'duration': float_or_none(data.get('realDuration')), + 'timestamp': int_or_none(data.get('liveFrom')), + 'series': data.get('programLabel'), + 'subtitles': subtitles, + 'is_live': is_live, } From 18825117545690499dc7064cd5ba207ca5ca3e23 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 17 Jun 2018 12:01:14 +0100 Subject: [PATCH 012/558] [6play] add support for rtlplay.be and extract hd usp formats --- youtube_dl/extractor/sixplay.py | 43 ++++++++++++++++++++------------- 1 file changed, 26 insertions(+), 17 deletions(-) diff --git a/youtube_dl/extractor/sixplay.py b/youtube_dl/extractor/sixplay.py index 69951e387..1f8469a90 100644 --- a/youtube_dl/extractor/sixplay.py +++ b/youtube_dl/extractor/sixplay.py @@ -19,29 +19,33 @@ from ..utils import ( class SixPlayIE(InfoExtractor): IE_NAME = '6play' - _VALID_URL = r'(?:6play:|https?://(?:www\.)?6play\.fr/.+?-c_)(?P<id>[0-9]+)' - _TEST = { - 'url': 'http://www.6play.fr/le-meilleur-patissier-p_1807/le-meilleur-patissier-special-fetes-mercredi-a-21-00-sur-m6-c_11638450', - 'md5': '42310bffe4ba3982db112b9cd3467328', + _VALID_URL = r'(?:6play:|https?://(?:www\.)?(?P<domain>6play\.fr|rtlplay.be)/.+?-c_)(?P<id>[0-9]+)' + _TESTS = [{ + 'url': 'https://www.6play.fr/minute-par-minute-p_9533/le-but-qui-a-marque-lhistoire-du-football-francais-c_12041051', + 'md5': '31fcd112637baa0c2ab92c4fcd8baf27', 'info_dict': { - 'id': '11638450', + 'id': '12041051', 'ext': 'mp4', - 'title': 'Le Meilleur Pâtissier, spécial fêtes mercredi à 21:00 sur M6', - 'description': 'md5:308853f6a5f9e2d55a30fc0654de415f', - 'duration': 39, - 'series': 'Le meilleur pâtissier', + 'title': 'Le but qui a marqué l\'histoire du football français !', + 'description': 'md5:b59e7e841d646ef1eb42a7868eb6a851', }, - 'params': { - 'skip_download': True, - }, - } + }, { + 'url': 'https://www.rtlplay.be/rtl-info-13h-p_8551/les-titres-du-rtlinfo-13h-c_12045869', + 'only_matching': True, + }] def _real_extract(self, url): - video_id = self._match_id(url) + domain, video_id = re.search(self._VALID_URL, url).groups() + service, consumer_name = { + '6play.fr': ('6play', 'm6web'), + 'rtlplay.be': ('rtlbe_rtl_play', 'rtlbe'), + }.get(domain, ('6play', 'm6web')) data = self._download_json( - 'https://pc.middleware.6play.fr/6play/v2/platforms/m6group_web/services/6play/videos/clip_%s' % video_id, - video_id, query={ + 'https://pc.middleware.6play.fr/6play/v2/platforms/m6group_web/services/%s/videos/clip_%s' % (service, video_id), + video_id, headers={ + 'x-customer-name': consumer_name + }, query={ 'csa': 5, 'with': 'clips', }) @@ -65,7 +69,12 @@ class SixPlayIE(InfoExtractor): subtitles.setdefault('fr', []).append({'url': asset_url}) continue if container == 'm3u8' or ext == 'm3u8': - if protocol == 'usp' and not compat_parse_qs(compat_urllib_parse_urlparse(asset_url).query).get('token', [None])[0]: + if protocol == 'usp': + if compat_parse_qs(compat_urllib_parse_urlparse(asset_url).query).get('token', [None])[0]: + urlh = self._request_webpage(asset_url, video_id, fatal=False) + if not urlh: + continue + asset_url = urlh.geturl() asset_url = re.sub(r'/([^/]+)\.ism/[^/]*\.m3u8', r'/\1.ism/\1.m3u8', asset_url) formats.extend(self._extract_m3u8_formats( asset_url, video_id, 'mp4', 'm3u8_native', From 8b183bd5f800792cfc37da8ef2383fb5ba88195c Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 17 Jun 2018 15:53:29 +0100 Subject: [PATCH 013/558] [tf1] try all supported adaptive urls --- youtube_dl/extractor/tf1.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py index e595c4a69..903f47380 100644 --- a/youtube_dl/extractor/tf1.py +++ b/youtube_dl/extractor/tf1.py @@ -19,6 +19,7 @@ class TF1IE(InfoExtractor): # Sometimes wat serves the whole file with the --test option 'skip_download': True, }, + 'expected_warnings': ['HTTP Error 404'], }, { 'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html', 'info_dict': { From 0adf213d8cce21e1a6ca6be7df532d67d184fbe2 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 17 Jun 2018 15:56:52 +0100 Subject: [PATCH 014/558] [wat] try all supported adaptive urls --- youtube_dl/extractor/wat.py | 41 +++++++++++++++---------------------- 1 file changed, 16 insertions(+), 25 deletions(-) diff --git a/youtube_dl/extractor/wat.py b/youtube_dl/extractor/wat.py index 20fef1f04..8ef3e0906 100644 --- a/youtube_dl/extractor/wat.py +++ b/youtube_dl/extractor/wat.py @@ -19,7 +19,6 @@ class WatIE(InfoExtractor): _TESTS = [ { 'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html', - 'md5': '83d882d9de5c9d97f0bb2c6273cde56a', 'info_dict': { 'id': '11713067', 'ext': 'mp4', @@ -28,10 +27,15 @@ class WatIE(InfoExtractor): 'upload_date': '20140819', 'duration': 120, }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + 'expected_warnings': ['HTTP Error 404'], }, { 'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html', - 'md5': '34bdfa5ca9fd3c7eb88601b635b0424c', + 'md5': 'b16574df2c3cd1a36ca0098f2a791925', 'info_dict': { 'id': '11713075', 'ext': 'mp4', @@ -98,38 +102,25 @@ class WatIE(InfoExtractor): formats = [] try: + alt_urls = lambda manifest_url: [re.sub(r'(?:wdv|ssm)?\.ism/', repl + '.ism/', manifest_url) for repl in ('', 'ssm')] manifest_urls = self._download_json( 'http://www.wat.tv/get/webhtml/' + video_id, video_id) m3u8_url = manifest_urls.get('hls') if m3u8_url: m3u8_url = remove_bitrate_limit(m3u8_url) - m3u8_formats = self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) - if m3u8_formats: - formats.extend(m3u8_formats) + for m3u8_alt_url in alt_urls(m3u8_url): + formats.extend(self._extract_m3u8_formats( + m3u8_alt_url, video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False)) formats.extend(self._extract_f4m_formats( - m3u8_url.replace('ios', 'web').replace('.m3u8', '.f4m'), + m3u8_alt_url.replace('ios', 'web').replace('.m3u8', '.f4m'), video_id, f4m_id='hds', fatal=False)) - http_url = extract_url('android5/%s.mp4', 'http') - if http_url: - for m3u8_format in m3u8_formats: - vbr, abr = m3u8_format.get('vbr'), m3u8_format.get('abr') - if not vbr or not abr: - continue - format_id = m3u8_format['format_id'].replace('hls', 'http') - fmt_url = re.sub(r'%s-\d+00-\d+' % video_id, '%s-%d00-%d' % (video_id, round(vbr / 100), round(abr)), http_url) - if self._is_valid_url(fmt_url, video_id, format_id): - f = m3u8_format.copy() - f.update({ - 'url': fmt_url, - 'format_id': format_id, - 'protocol': 'http', - }) - formats.append(f) mpd_url = manifest_urls.get('mpd') if mpd_url: - formats.extend(self._extract_mpd_formats(remove_bitrate_limit( - mpd_url), video_id, mpd_id='dash', fatal=False)) + mpd_url = remove_bitrate_limit(mpd_url) + for mpd_alt_url in alt_urls(mpd_url): + formats.extend(self._extract_mpd_formats( + mpd_alt_url, video_id, mpd_id='dash', fatal=False)) self._sort_formats(formats) except ExtractorError: abr = 64 From ce0edda0f9c0d8cf6250edfa7a43ddbccd101cd6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 18 Jun 2018 00:49:50 +0700 Subject: [PATCH 015/558] [markiza] Add extractors (closes #16750) --- youtube_dl/extractor/extractors.py | 4 + youtube_dl/extractor/markiza.py | 121 +++++++++++++++++++++++++++++ 2 files changed, 125 insertions(+) create mode 100644 youtube_dl/extractor/markiza.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index c3e6daa24..3b3964c01 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -590,6 +590,10 @@ from .mangomolo import ( MangomoloLiveIE, ) from .manyvids import ManyVidsIE +from .markiza import ( + MarkizaIE, + MarkizaPageIE, +) from .massengeschmacktv import MassengeschmackTVIE from .matchtv import MatchTVIE from .mdr import MDRIE diff --git a/youtube_dl/extractor/markiza.py b/youtube_dl/extractor/markiza.py new file mode 100644 index 000000000..e6bfab114 --- /dev/null +++ b/youtube_dl/extractor/markiza.py @@ -0,0 +1,121 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + orderedSet, + parse_duration, + try_get, +) + + +class MarkizaIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?videoarchiv\.markiza\.sk/(?:video/(?:[^/]+/)*|embed/)(?P<id>\d+)(?:[_/]|$)' + _TESTS = [{ + 'url': 'http://videoarchiv.markiza.sk/video/oteckovia/84723_oteckovia-109', + 'md5': 'ada4e9fad038abeed971843aa028c7b0', + 'info_dict': { + 'id': '139078', + 'ext': 'mp4', + 'title': 'Oteckovia 109', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 2760, + }, + }, { + 'url': 'http://videoarchiv.markiza.sk/video/televizne-noviny/televizne-noviny/85430_televizne-noviny', + 'info_dict': { + 'id': '85430', + 'title': 'Televízne noviny', + }, + 'playlist_count': 23, + }, { + 'url': 'http://videoarchiv.markiza.sk/video/oteckovia/84723', + 'only_matching': True, + }, { + 'url': 'http://videoarchiv.markiza.sk/video/84723', + 'only_matching': True, + }, { + 'url': 'http://videoarchiv.markiza.sk/video/filmy/85190_kamenak', + 'only_matching': True, + }, { + 'url': 'http://videoarchiv.markiza.sk/video/reflex/zo-zakulisia/84651_pribeh-alzbetky', + 'only_matching': True, + }, { + 'url': 'http://videoarchiv.markiza.sk/embed/85295', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + data = self._download_json( + 'http://videoarchiv.markiza.sk/json/video_jwplayer7.json', + video_id, query={'id': video_id}) + + info = self._parse_jwplayer_data(data, m3u8_id='hls', mpd_id='dash') + + if info.get('_type') == 'playlist': + info.update({ + 'id': video_id, + 'title': try_get( + data, lambda x: x['details']['name'], compat_str), + }) + else: + info['duration'] = parse_duration( + try_get(data, lambda x: x['details']['duration'], compat_str)) + return info + + +class MarkizaPageIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?(?:(?:[^/]+\.)?markiza|tvnoviny)\.sk/(?:[^/]+/)*(?P<id>\d+)_' + _TESTS = [{ + 'url': 'http://www.markiza.sk/soubiz/zahranicny/1923705_oteckovia-maju-svoj-den-ti-slavni-nie-su-o-nic-menej-rozkosni', + 'md5': 'ada4e9fad038abeed971843aa028c7b0', + 'info_dict': { + 'id': '139355', + 'ext': 'mp4', + 'title': 'Oteckovia 110', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 2604, + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'http://dajto.markiza.sk/filmy-a-serialy/1774695_frajeri-vo-vegas', + 'only_matching': True, + }, { + 'url': 'http://superstar.markiza.sk/aktualne/1923870_to-je-ale-telo-spevacka-ukazala-sexy-postavicku-v-bikinach', + 'only_matching': True, + }, { + 'url': 'http://hybsa.markiza.sk/aktualne/1923790_uzasna-atmosfera-na-hybsa-v-poprade-superstaristi-si-prve-koncerty-pred-davom-ludi-poriadne-uzili', + 'only_matching': True, + }, { + 'url': 'http://doma.markiza.sk/filmy/1885250_moja-vysnivana-svadba', + 'only_matching': True, + }, { + 'url': 'http://www.tvnoviny.sk/domace/1923887_po-smrti-manzela-ju-cakalo-poriadne-prekvapenie', + 'only_matching': True, + }] + + @classmethod + def suitable(cls, url): + return False if MarkizaIE.suitable(url) else super(MarkizaPageIE, cls).suitable(url) + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + entries = [ + self.url_result('http://videoarchiv.markiza.sk/video/%s' % video_id) + for video_id in orderedSet(re.findall( + r'(?:initPlayer_|data-entity=["\']|id=["\']player_)(\d+)', + webpage))] + + return self.playlist_result(entries, playlist_id) From 9e761fe6f555a3ad0b92bdc2c651a4c5b8aff887 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 18 Jun 2018 01:31:49 +0700 Subject: [PATCH 016/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/ChangeLog b/ChangeLog index 062000594..38cfcd8fd 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,22 @@ +version <unreleased> + +Core +* [downloader/rtmp] Fix downloading in verbose mode (#16736) + +Extractors ++ [markiza] Add support for markiza.sk (#16750) +* [wat] Try all supported adaptive URLs ++ [6play] Add support for rtlplay.be and extract hd usp formats ++ [rtbf] Add support for audio and live streams (#9638, #11923) ++ [rtbf] Extract HLS, DASH and all HTTP formats ++ [rtbf] Extract subtitles ++ [rtbf] Fixup specific HTTP URLs (#16101) ++ [expressen] Add support for expressen.se +* [vidzi] Fix extraction (#16678) +* [pbs] Improve extraction (#16623, #16684) +* [bilibili] Restrict cid regular expression (#16638, #16734) + + version 2018.06.14 Core From 858cf4dc2966d398d939cedffc160afad2484f8b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 18 Jun 2018 01:34:36 +0700 Subject: [PATCH 017/558] release 2018.06.18 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 3 +++ youtube_dl/version.py | 2 +- 4 files changed, 8 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 1cfb54bfd..de3888214 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.06.14*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.06.14** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.06.18*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.06.18** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.06.14 +[debug] youtube-dl version 2018.06.18 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 38cfcd8fd..fe5087097 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.06.18 Core * [downloader/rtmp] Fix downloading in verbose mode (#16736) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 705279ac1..432a7ba93 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -266,6 +266,7 @@ - **Europa** - **EveryonesMixtape** - **ExpoTV** + - **Expressen** - **ExtremeTube** - **EyedoTV** - **facebook** @@ -455,6 +456,8 @@ - **mangomolo:live** - **mangomolo:video** - **ManyVids** + - **Markiza** + - **MarkizaPage** - **massengeschmack.tv** - **MatchTV** - **MDR**: MDR.DE and KiKA diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 1533dceb4..49fef60ea 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.06.14' +__version__ = '2018.06.18' From 8ba84e4600229c9baec6410b0c0c9e500c0105b5 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 17 Jun 2018 20:40:35 +0100 Subject: [PATCH 018/558] [tvnow] try all clear manifest urls(closes #15361) --- youtube_dl/extractor/tvnow.py | 53 +++++++++++++++++++++++------------ 1 file changed, 35 insertions(+), 18 deletions(-) diff --git a/youtube_dl/extractor/tvnow.py b/youtube_dl/extractor/tvnow.py index 808571ece..60937616f 100644 --- a/youtube_dl/extractor/tvnow.py +++ b/youtube_dl/extractor/tvnow.py @@ -19,8 +19,8 @@ class TVNowBaseIE(InfoExtractor): _VIDEO_FIELDS = ( 'id', 'title', 'free', 'geoblocked', 'articleLong', 'articleShort', 'broadcastStartDate', 'isDrm', 'duration', 'season', 'episode', - 'manifest.dashclear', 'format.title', 'format.defaultImage169Format', - 'format.defaultImage169Logo') + 'manifest.dashclear', 'manifest.hlsclear', 'manifest.smoothclear', + 'format.title', 'format.defaultImage169Format', 'format.defaultImage169Logo') def _call_api(self, path, video_id, query): return self._download_json( @@ -31,27 +31,42 @@ class TVNowBaseIE(InfoExtractor): video_id = compat_str(info['id']) title = info['title'] - mpd_url = info['manifest']['dashclear'] - if not mpd_url: + paths = [] + for manifest_url in (info.get('manifest') or {}).values(): + if not manifest_url: + continue + manifest_url = update_url_query(manifest_url, {'filter': ''}) + path = self._search_regex(r'https?://[^/]+/(.+?)\.ism/', manifest_url, 'path') + if path in paths: + continue + paths.append(path) + + def url_repl(proto, suffix): + return re.sub( + r'(?:hls|dash|hss)([.-])', proto + r'\1', re.sub( + r'\.ism/(?:[^.]*\.(?:m3u8|mpd)|[Mm]anifest)', + '.ism/' + suffix, manifest_url)) + + formats = self._extract_mpd_formats( + url_repl('dash', '.mpd'), video_id, + mpd_id='dash', fatal=False) + formats.extend(self._extract_ism_formats( + url_repl('hss', 'Manifest'), + video_id, ism_id='mss', fatal=False)) + formats.extend(self._extract_m3u8_formats( + url_repl('hls', '.m3u8'), video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False)) + if formats: + break + else: if info.get('isDrm'): raise ExtractorError( 'Video %s is DRM protected' % video_id, expected=True) if info.get('geoblocked'): - raise ExtractorError( - 'Video %s is not available from your location due to geo restriction' % video_id, - expected=True) + raise self.raise_geo_restricted() if not info.get('free', True): raise ExtractorError( 'Video %s is not available for free' % video_id, expected=True) - - mpd_url = update_url_query(mpd_url, {'filter': ''}) - formats = self._extract_mpd_formats(mpd_url, video_id, mpd_id='dash', fatal=False) - formats.extend(self._extract_ism_formats( - mpd_url.replace('dash.', 'hss.').replace('/.mpd', '/Manifest'), - video_id, ism_id='mss', fatal=False)) - formats.extend(self._extract_m3u8_formats( - mpd_url.replace('dash.', 'hls.').replace('/.mpd', '/.m3u8'), - video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) self._sort_formats(formats) description = info.get('articleLong') or info.get('articleShort') @@ -88,7 +103,7 @@ class TVNowBaseIE(InfoExtractor): class TVNowIE(TVNowBaseIE): _VALID_URL = r'''(?x) https?:// - (?:www\.)?tvnow\.(?:de|at|ch)/[^/]+/ + (?:www\.)?tvnow\.(?:de|at|ch)/(?P<station>[^/]+)/ (?P<show_id>[^/]+)/ (?!(?:list|jahr)(?:/|$))(?P<id>[^/?\#&]+) ''' @@ -140,11 +155,13 @@ class TVNowIE(TVNowBaseIE): }] def _real_extract(self, url): - display_id = '%s/%s' % re.match(self._VALID_URL, url).groups() + mobj = re.match(self._VALID_URL, url) + display_id = '%s/%s' % mobj.group(2, 3) info = self._call_api( 'movies/' + display_id, display_id, query={ 'fields': ','.join(self._VIDEO_FIELDS), + 'station': mobj.group(1), }) return self._extract_video(info, display_id) From 075a13d3e9e860f0033ea5a37795bebba02690b1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 18 Jun 2018 03:22:08 +0700 Subject: [PATCH 019/558] [compat] Introduce compat_integer_types --- youtube_dl/compat.py | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index 4a611f183..7b770340f 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -2787,6 +2787,12 @@ except NameError: # Python 3 compat_numeric_types = (int, float, complex) +try: + compat_integer_types = (int, long) +except NameError: # Python 3 + compat_integer_types = (int, ) + + if sys.version_info < (2, 7): def compat_socket_create_connection(address, timeout, source_address=None): host, port = address @@ -2974,6 +2980,7 @@ __all__ = [ 'compat_http_client', 'compat_http_server', 'compat_input', + 'compat_integer_types', 'compat_itertools_count', 'compat_kwargs', 'compat_numeric_types', From d391b7e23d3d6c2af03c6329b4bf059ec095f33d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 18 Jun 2018 04:01:48 +0700 Subject: [PATCH 020/558] [extractor/common] Introduce expected_status for convenient accept of failed HTTP requests Useful when some non-success (2xx) HTTP status codes should be considered normal. Previously this required to manually catch corresponding exceptions and read the response. --- youtube_dl/extractor/common.py | 135 +++++++++++++++++++++++++++------ 1 file changed, 113 insertions(+), 22 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index a2548dba3..394f34372 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -19,6 +19,7 @@ from ..compat import ( compat_cookies, compat_etree_fromstring, compat_getpass, + compat_integer_types, compat_http_client, compat_os_name, compat_str, @@ -548,8 +549,26 @@ class InfoExtractor(object): def IE_NAME(self): return compat_str(type(self).__name__[:-2]) - def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers={}, query={}): - """ Returns the response handle """ + @staticmethod + def __can_accept_status_code(err, expected_status): + assert isinstance(err, compat_urllib_error.HTTPError) + if expected_status is None: + return False + if isinstance(expected_status, compat_integer_types): + return err.code == expected_status + elif isinstance(expected_status, (list, tuple)): + return err.code in expected_status + elif callable(expected_status): + return expected_status(err.code) is True + else: + assert False + + def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers={}, query={}, expected_status=None): + """ + Return the response handle. + + See _download_webpage docstring for arguments specification. + """ if note is None: self.report_download_webpage(video_id) elif note is not False: @@ -578,6 +597,10 @@ class InfoExtractor(object): try: return self._downloader.urlopen(url_or_request) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + if isinstance(err, compat_urllib_error.HTTPError): + if self.__can_accept_status_code(err, expected_status): + return err.fp + if errnote is False: return False if errnote is None: @@ -590,13 +613,17 @@ class InfoExtractor(object): self._downloader.report_warning(errmsg) return False - def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None, data=None, headers={}, query={}): - """ Returns a tuple (page content as string, URL handle) """ + def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None, data=None, headers={}, query={}, expected_status=None): + """ + Return a tuple (page content as string, URL handle). + + See _download_webpage docstring for arguments specification. + """ # Strip hashes from the URL (#1038) if isinstance(url_or_request, (compat_str, str)): url_or_request = url_or_request.partition('#')[0] - urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query) + urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query, expected_status=expected_status) if urlh is False: assert not fatal return False @@ -685,13 +712,52 @@ class InfoExtractor(object): return content - def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None, data=None, headers={}, query={}): - """ Returns the data of the page as a string """ + def _download_webpage( + self, url_or_request, video_id, note=None, errnote=None, + fatal=True, tries=1, timeout=5, encoding=None, data=None, + headers={}, query={}, expected_status=None): + """ + Return the data of the page as a string. + + Arguments: + url_or_request -- plain text URL as a string or + a compat_urllib_request.Requestobject + video_id -- Video/playlist/item identifier (string) + + Keyword arguments: + note -- note printed before downloading (string) + errnote -- note printed in case of an error (string) + fatal -- flag denoting whether error should be considered fatal, + i.e. whether it should cause ExtractionError to be raised, + otherwise a warning will be reported and extraction continued + tries -- number of tries + timeout -- sleep interval between tries + encoding -- encoding for a page content decoding, guessed automatically + when not explicitly specified + data -- POST data (bytes) + headers -- HTTP headers (dict) + query -- URL query (dict) + expected_status -- allows to accept failed HTTP requests (non 2xx + status code) by explicitly specifying a set of accepted status + codes. Can be any of the following entities: + - an integer type specifying an exact failed status code to + accept + - a list or a tuple of integer types specifying a list of + failed status codes to accept + - a callable accepting an actual failed status code and + returning True if it should be accepted + Note that this argument does not affect success status codes (2xx) + which are always accepted. + """ + success = False try_count = 0 while success is False: try: - res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding, data=data, headers=headers, query=query) + res = self._download_webpage_handle( + url_or_request, video_id, note, errnote, fatal, + encoding=encoding, data=data, headers=headers, query=query, + expected_status=expected_status) success = True except compat_http_client.IncompleteRead as e: try_count += 1 @@ -707,11 +773,17 @@ class InfoExtractor(object): def _download_xml_handle( self, url_or_request, video_id, note='Downloading XML', errnote='Unable to download XML', transform_source=None, - fatal=True, encoding=None, data=None, headers={}, query={}): - """Return a tuple (xml as an xml.etree.ElementTree.Element, URL handle)""" + fatal=True, encoding=None, data=None, headers={}, query={}, + expected_status=None): + """ + Return a tuple (xml as an xml.etree.ElementTree.Element, URL handle). + + See _download_webpage docstring for arguments specification. + """ res = self._download_webpage_handle( url_or_request, video_id, note, errnote, fatal=fatal, - encoding=encoding, data=data, headers=headers, query=query) + encoding=encoding, data=data, headers=headers, query=query, + expected_status=expected_status) if res is False: return res xml_string, urlh = res @@ -719,15 +791,21 @@ class InfoExtractor(object): xml_string, video_id, transform_source=transform_source, fatal=fatal), urlh - def _download_xml(self, url_or_request, video_id, - note='Downloading XML', errnote='Unable to download XML', - transform_source=None, fatal=True, encoding=None, - data=None, headers={}, query={}): - """Return the xml as an xml.etree.ElementTree.Element""" + def _download_xml( + self, url_or_request, video_id, + note='Downloading XML', errnote='Unable to download XML', + transform_source=None, fatal=True, encoding=None, + data=None, headers={}, query={}, expected_status=None): + """ + Return the xml as an xml.etree.ElementTree.Element. + + See _download_webpage docstring for arguments specification. + """ res = self._download_xml_handle( url_or_request, video_id, note=note, errnote=errnote, transform_source=transform_source, fatal=fatal, encoding=encoding, - data=data, headers=headers, query=query) + data=data, headers=headers, query=query, + expected_status=expected_status) return res if res is False else res[0] def _parse_xml(self, xml_string, video_id, transform_source=None, fatal=True): @@ -745,11 +823,17 @@ class InfoExtractor(object): def _download_json_handle( self, url_or_request, video_id, note='Downloading JSON metadata', errnote='Unable to download JSON metadata', transform_source=None, - fatal=True, encoding=None, data=None, headers={}, query={}): - """Return a tuple (JSON object, URL handle)""" + fatal=True, encoding=None, data=None, headers={}, query={}, + expected_status=None): + """ + Return a tuple (JSON object, URL handle). + + See _download_webpage docstring for arguments specification. + """ res = self._download_webpage_handle( url_or_request, video_id, note, errnote, fatal=fatal, - encoding=encoding, data=data, headers=headers, query=query) + encoding=encoding, data=data, headers=headers, query=query, + expected_status=expected_status) if res is False: return res json_string, urlh = res @@ -760,11 +844,18 @@ class InfoExtractor(object): def _download_json( self, url_or_request, video_id, note='Downloading JSON metadata', errnote='Unable to download JSON metadata', transform_source=None, - fatal=True, encoding=None, data=None, headers={}, query={}): + fatal=True, encoding=None, data=None, headers={}, query={}, + expected_status=None): + """ + Return the JSON object as a dict. + + See _download_webpage docstring for arguments specification. + """ res = self._download_json_handle( url_or_request, video_id, note=note, errnote=errnote, transform_source=transform_source, fatal=fatal, encoding=encoding, - data=data, headers=headers, query=query) + data=data, headers=headers, query=query, + expected_status=expected_status) return res if res is False else res[0] def _parse_json(self, json_string, video_id, transform_source=None, fatal=True): From 00a429bea3c2deacef5dbfb2b0b7e191b1dbaf62 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 18 Jun 2018 04:04:13 +0700 Subject: [PATCH 021/558] [markiza] Expect 500 status code --- youtube_dl/extractor/markiza.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/markiza.py b/youtube_dl/extractor/markiza.py index e6bfab114..def960a0c 100644 --- a/youtube_dl/extractor/markiza.py +++ b/youtube_dl/extractor/markiza.py @@ -110,7 +110,11 @@ class MarkizaPageIE(InfoExtractor): def _real_extract(self, url): playlist_id = self._match_id(url) - webpage = self._download_webpage(url, playlist_id) + webpage = self._download_webpage( + # Downloading for some hosts (e.g. dajto, doma) fails with 500 + # although everything seems to be OK, so considering 500 + # status code to be expected. + url, playlist_id, expected_status=500) entries = [ self.url_result('http://videoarchiv.markiza.sk/video/%s' % video_id) From 9283d4ea03f907f2b9e7954b0897075a165b4d4c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 18 Jun 2018 04:04:47 +0700 Subject: [PATCH 022/558] [bbccouk] Use expected_status --- youtube_dl/extractor/bbc.py | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 30a63a24e..293d82b0f 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -21,7 +21,6 @@ from ..utils import ( urljoin, ) from ..compat import ( - compat_etree_fromstring, compat_HTTPError, compat_urlparse, ) @@ -334,14 +333,9 @@ class BBCCoUkIE(InfoExtractor): self._raise_extractor_error(last_exception) def _download_media_selector_url(self, url, programme_id=None): - try: - media_selection = self._download_xml( - url, programme_id, 'Downloading media selection XML') - except ExtractorError as ee: - if isinstance(ee.cause, compat_HTTPError) and ee.cause.code in (403, 404): - media_selection = compat_etree_fromstring(ee.cause.read().decode('utf-8')) - else: - raise + media_selection = self._download_xml( + url, programme_id, 'Downloading media selection XML', + expected_status=(403, 404)) return self._process_media_selector(media_selection, programme_id) def _process_media_selector(self, media_selection, programme_id): From 721a877d2fb82de18e4aeec27d70f84f9b41f766 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 18 Jun 2018 23:08:35 +0700 Subject: [PATCH 023/558] [vgtv] Add support for www.aftonbladet.se/tv/ URLs --- youtube_dl/extractor/vgtv.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/vgtv.py b/youtube_dl/extractor/vgtv.py index c21a09c01..d430e2944 100644 --- a/youtube_dl/extractor/vgtv.py +++ b/youtube_dl/extractor/vgtv.py @@ -24,6 +24,7 @@ class VGTVIE(XstreamIE): 'aftenposten.no/webtv': 'aptv', 'ap.vgtv.no/webtv': 'aptv', 'tv.aftonbladet.se/abtv': 'abtv', + 'www.aftonbladet.se/tv': 'abtv', } _APP_NAME_TO_VENDOR = { @@ -44,7 +45,7 @@ class VGTVIE(XstreamIE): (?: (?:\#!/)?(?:video|live)/| embed?.*id=| - articles/ + a(?:rticles)?/ )| (?P<appname> %s @@ -143,6 +144,10 @@ class VGTVIE(XstreamIE): 'url': 'http://tv.aftonbladet.se/abtv/articles/36015', 'only_matching': True, }, + { + 'url': 'https://www.aftonbladet.se/tv/a/36015', + 'only_matching': True, + }, { 'url': 'abtv:140026', 'only_matching': True, From 713afa705c228c2caa6054fff19a7690ba19d64a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 18 Jun 2018 23:15:38 +0700 Subject: [PATCH 024/558] [vgtv] Improve HLS formats extraction --- youtube_dl/extractor/vgtv.py | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/vgtv.py b/youtube_dl/extractor/vgtv.py index d430e2944..fe7a26b62 100644 --- a/youtube_dl/extractor/vgtv.py +++ b/youtube_dl/extractor/vgtv.py @@ -183,13 +183,15 @@ class VGTVIE(XstreamIE): streams = data['streamUrls'] stream_type = data.get('streamType') - + is_live = stream_type == 'live' formats = [] hls_url = streams.get('hls') if hls_url: formats.extend(self._extract_m3u8_formats( - hls_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) + hls_url, video_id, 'mp4', + entry_protocol='m3u8' if is_live else 'm3u8_native', + m3u8_id='hls', fatal=False)) hds_url = streams.get('hds') if hds_url: @@ -234,13 +236,13 @@ class VGTVIE(XstreamIE): info.update({ 'id': video_id, - 'title': self._live_title(data['title']) if stream_type == 'live' else data['title'], + 'title': self._live_title(data['title']) if is_live else data['title'], 'description': data['description'], 'thumbnail': data['images']['main'] + '?t[]=900x506q80', 'timestamp': data['published'], 'duration': float_or_none(data['duration'], 1000), 'view_count': data['displays'], - 'is_live': True if stream_type == 'live' else False, + 'is_live': is_live, }) return info From 18806e3b6b95d03c773c89e465e1b28b2f12a618 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 18 Jun 2018 19:08:54 +0100 Subject: [PATCH 025/558] [rtbf] fix extraction for python 3.2 and older --- youtube_dl/extractor/rtbf.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/rtbf.py b/youtube_dl/extractor/rtbf.py index acff9766a..3b0f3080b 100644 --- a/youtube_dl/extractor/rtbf.py +++ b/youtube_dl/extractor/rtbf.py @@ -99,7 +99,7 @@ class RTBFIE(InfoExtractor): http_url = data.get('url') if formats and http_url and re.search(height_re, http_url): http_url = fix_url(http_url) - for m3u8_f in formats.copy(): + for m3u8_f in formats[:]: height = m3u8_f.get('height') if not height: continue From e12b4b8bccd364cb5cc68aab4888209965a82dc1 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 19 Jun 2018 10:35:42 +0100 Subject: [PATCH 026/558] [6play] use geo verfication headers --- youtube_dl/extractor/sixplay.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/sixplay.py b/youtube_dl/extractor/sixplay.py index 1f8469a90..a363221bc 100644 --- a/youtube_dl/extractor/sixplay.py +++ b/youtube_dl/extractor/sixplay.py @@ -71,7 +71,9 @@ class SixPlayIE(InfoExtractor): if container == 'm3u8' or ext == 'm3u8': if protocol == 'usp': if compat_parse_qs(compat_urllib_parse_urlparse(asset_url).query).get('token', [None])[0]: - urlh = self._request_webpage(asset_url, video_id, fatal=False) + urlh = self._request_webpage( + asset_url, video_id, fatal=False, + headers=self.geo_verification_headers()) if not urlh: continue asset_url = urlh.geturl() From 8b4b400aef83b233502ece7321ee84f6ab9e213e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 19 Jun 2018 23:00:36 +0700 Subject: [PATCH 027/558] [peertube] Improve generic support (closes #16733) --- youtube_dl/extractor/generic.py | 2 +- youtube_dl/extractor/peertube.py | 47 +++++++++++++++++++++++--------- 2 files changed, 35 insertions(+), 14 deletions(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index dad951b75..6c0f772ac 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -3076,7 +3076,7 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key()) - peertube_urls = PeerTubeIE._extract_urls(webpage) + peertube_urls = PeerTubeIE._extract_urls(webpage, url) if peertube_urls: return self.playlist_from_matches( peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key()) diff --git a/youtube_dl/extractor/peertube.py b/youtube_dl/extractor/peertube.py index a481b3151..d9849a2ba 100644 --- a/youtube_dl/extractor/peertube.py +++ b/youtube_dl/extractor/peertube.py @@ -116,12 +116,14 @@ class PeerTubeIE(InfoExtractor): videos\.tcit\.fr| peertube\.cpy\.re )''' + _UUID_RE = r'[\da-fA-F]{8}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{12}' _VALID_URL = r'''(?x) - https?:// - %s - /(?:videos/(?:watch|embed)|api/v\d/videos)/ - (?P<id>[^/?\#&]+) - ''' % _INSTANCES_RE + (?: + peertube:(?P<host>[^:]+):| + https?://(?P<host_2>%s)/(?:videos/(?:watch|embed)|api/v\d/videos)/ + ) + (?P<id>%s) + ''' % (_INSTANCES_RE, _UUID_RE) _TESTS = [{ 'url': 'https://peertube.moe/videos/watch/2790feb0-8120-4e63-9af3-c943c69f5e6c', 'md5': '80f24ff364cc9d333529506a263e7feb', @@ -157,21 +159,40 @@ class PeerTubeIE(InfoExtractor): }, { 'url': 'https://tube.openalgeria.org/api/v1/videos/c1875674-97d0-4c94-a058-3f7e64c962e8', 'only_matching': True, + }, { + 'url': 'peertube:video.blender.org:b37a5b9f-e6b5-415c-b700-04a5cd6ec205', + 'only_matching': True, }] @staticmethod - def _extract_urls(webpage): - return [ - mobj.group('url') - for mobj in re.finditer( - r'''(?x)<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//%s/videos/embed/[^/?\#&]+)\1''' - % PeerTubeIE._INSTANCES_RE, webpage)] + def _extract_peertube_url(webpage, source_url): + mobj = re.match( + r'https?://(?P<host>[^/]+)/videos/watch/(?P<id>%s)' + % PeerTubeIE._UUID_RE, source_url) + if mobj and any(p in webpage for p in ( + '<title>PeerTube<', + 'There will be other non JS-based clients to access PeerTube', + '>We are sorry but it seems that PeerTube is not compatible with your web browser.<')): + return 'peertube:%s:%s' % mobj.group('host', 'id') + + @staticmethod + def _extract_urls(webpage, source_url): + entries = re.findall( + r'''(?x)<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//%s/videos/embed/%s)''' + % (PeerTubeIE._INSTANCES_RE, PeerTubeIE._UUID_RE), webpage) + if not entries: + peertube_url = PeerTubeIE._extract_peertube_url(webpage, source_url) + if peertube_url: + entries = [peertube_url] + return entries def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') or mobj.group('host_2') + video_id = mobj.group('id') video = self._download_json( - urljoin(url, '/api/v1/videos/%s' % video_id), video_id) + 'https://%s/api/v1/videos/%s' % (host, video_id), video_id) title = video['name'] From e73050882763705ccb8e487edbc3983b5582b1a1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 19 Jun 2018 23:12:53 +0700 Subject: [PATCH 028/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/ChangeLog b/ChangeLog index fe5087097..1494081b8 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,21 @@ +version <unreleased> + +Core ++ [extractor/common] Introduce expected_status in _download_* methods + for convenient accept of HTTP requests failed with non 2xx status codes ++ [compat] Introduce compat_integer_types + +Extractors +* [peertube] Improve generic support (#16733) ++ [6play] Use geo verification headers +* [rtbf] Fix extraction for python 3.2 +* [vgtv] Improve HLS formats extraction ++ [vgtv] Add support for www.aftonbladet.se/tv URLs +* [bbccouk] Use expected_status +* [markiza] Expect 500 HTTP status code +* [tvnow] Try all clear manifest URLs (#15361) + + version 2018.06.18 Core From c9b983ff827aae25a0fe2116c98c26702c581b81 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 19 Jun 2018 23:16:04 +0700 Subject: [PATCH 029/558] release 2018.06.19 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index de3888214..d254678b5 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.06.18*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.06.18** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.06.19*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.06.19** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.06.18 +[debug] youtube-dl version 2018.06.19 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 1494081b8..93dc40d8c 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.06.19 Core + [extractor/common] Introduce expected_status in _download_* methods diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 49fef60ea..dd4795cd1 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.06.18' +__version__ = '2018.06.19' From f51f526b0acb5943332452d1958581cb1135bfe9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 20 Jun 2018 23:51:14 +0700 Subject: [PATCH 030/558] [foxnews] Add support for iframe embeds (closes #15810, closes #16711) --- youtube_dl/extractor/foxnews.py | 42 +++++++++++++++++++++++++++------ youtube_dl/extractor/generic.py | 6 +++++ 2 files changed, 41 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/foxnews.py b/youtube_dl/extractor/foxnews.py index dc0662f74..4c402806a 100644 --- a/youtube_dl/extractor/foxnews.py +++ b/youtube_dl/extractor/foxnews.py @@ -58,6 +58,14 @@ class FoxNewsIE(AMPIE): }, ] + @staticmethod + def _extract_urls(webpage): + return [ + mobj.group('url') + for mobj in re.finditer( + r'<(?:amp-)?iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//video\.foxnews\.com/v/video-embed\.html?.*?\bvideo_id=\d+.*?)\1', + webpage)] + def _real_extract(self, url): host, video_id = re.match(self._VALID_URL, url).groups() @@ -71,18 +79,35 @@ class FoxNewsArticleIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?foxnews\.com/(?!v)([^/]+/)+(?P<id>[a-z-]+)' IE_NAME = 'foxnews:article' - _TEST = { + _TESTS = [{ + # data-video-id 'url': 'http://www.foxnews.com/politics/2016/09/08/buzz-about-bud-clinton-camp-denies-claims-wore-earpiece-at-forum.html', - 'md5': '62aa5a781b308fdee212ebb6f33ae7ef', + 'md5': '83d44e1aff1433e7a29a7b537d1700b5', 'info_dict': { 'id': '5116295019001', 'ext': 'mp4', 'title': 'Trump and Clinton asked to defend positions on Iraq War', 'description': 'Veterans react on \'The Kelly File\'', - 'timestamp': 1473299755, + 'timestamp': 1473301045, 'upload_date': '20160908', }, - } + }, { + # iframe embed + 'url': 'http://www.foxnews.com/us/2018/03/09/parkland-survivor-kyle-kashuv-on-meeting-trump-his-app-to-prevent-another-school-shooting.amp.html?__twitter_impression=true', + 'info_dict': { + 'id': '5748266721001', + 'ext': 'flv', + 'title': 'Kyle Kashuv has a positive message for the Trump White House', + 'description': 'Marjory Stoneman Douglas student disagrees with classmates.', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 229, + 'timestamp': 1520594670, + 'upload_date': '20180309', + }, + 'params': { + 'skip_download': True, + }, + }] def _real_extract(self, url): display_id = self._match_id(url) @@ -90,10 +115,13 @@ class FoxNewsArticleIE(InfoExtractor): video_id = self._html_search_regex( r'data-video-id=([\'"])(?P<id>[^\'"]+)\1', - webpage, 'video ID', group='id') + webpage, 'video ID', group='id', default=None) + if video_id: + return self.url_result( + 'http://video.foxnews.com/v/' + video_id, FoxNewsIE.ie_key()) + return self.url_result( - 'http://video.foxnews.com/v/' + video_id, - FoxNewsIE.ie_key()) + FoxNewsIE._extract_urls(webpage)[0], FoxNewsIE.ie_key()) class FoxNewsInsiderIE(InfoExtractor): diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 6c0f772ac..d71cb9050 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -111,6 +111,7 @@ from .cloudflarestream import CloudflareStreamIE from .peertube import PeerTubeIE from .indavideo import IndavideoEmbedIE from .apa import APAIE +from .foxnews import FoxNewsIE class GenericIE(InfoExtractor): @@ -3091,6 +3092,11 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( apa_urls, video_id, video_title, ie=APAIE.ie_key()) + foxnews_urls = FoxNewsIE._extract_urls(webpage) + if foxnews_urls: + return self.playlist_from_matches( + foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key()) + sharevideos_urls = [mobj.group('url') for mobj in re.finditer( r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1', webpage)] From 91aa502d916fd3f103d34f927748767413f1d1a0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 20 Jun 2018 23:59:37 +0700 Subject: [PATCH 031/558] [foxnews:insider] Remove extractor (#15810) Now covered by foxnews:article --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/foxnews.py | 49 +++--------------------------- 2 files changed, 4 insertions(+), 46 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 3b3964c01..27ece3b53 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -373,7 +373,6 @@ from .foxgay import FoxgayIE from .foxnews import ( FoxNewsIE, FoxNewsArticleIE, - FoxNewsInsiderIE, ) from .foxsports import FoxSportsIE from .franceculture import FranceCultureIE diff --git a/youtube_dl/extractor/foxnews.py b/youtube_dl/extractor/foxnews.py index 4c402806a..63613cb85 100644 --- a/youtube_dl/extractor/foxnews.py +++ b/youtube_dl/extractor/foxnews.py @@ -76,7 +76,7 @@ class FoxNewsIE(AMPIE): class FoxNewsArticleIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?foxnews\.com/(?!v)([^/]+/)+(?P<id>[a-z-]+)' + _VALID_URL = r'https?://(?:www\.)?(?:insider\.)?foxnews\.com/(?!v)([^/]+/)+(?P<id>[a-z-]+)' IE_NAME = 'foxnews:article' _TESTS = [{ @@ -107,6 +107,9 @@ class FoxNewsArticleIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + 'url': 'http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words', + 'only_matching': True, }] def _real_extract(self, url): @@ -122,47 +125,3 @@ class FoxNewsArticleIE(InfoExtractor): return self.url_result( FoxNewsIE._extract_urls(webpage)[0], FoxNewsIE.ie_key()) - - -class FoxNewsInsiderIE(InfoExtractor): - _VALID_URL = r'https?://insider\.foxnews\.com/([^/]+/)+(?P<id>[a-z-]+)' - IE_NAME = 'foxnews:insider' - - _TEST = { - 'url': 'http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words', - 'md5': 'a10c755e582d28120c62749b4feb4c0c', - 'info_dict': { - 'id': '5099377331001', - 'display_id': 'univ-wisconsin-student-group-pushing-silence-certain-words', - 'ext': 'mp4', - 'title': 'Student Group: Saying \'Politically Correct,\' \'Trash\' and \'Lame\' Is Offensive', - 'description': 'Is campus censorship getting out of control?', - 'timestamp': 1472168725, - 'upload_date': '20160825', - 'thumbnail': r're:^https?://.*\.jpg$', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - 'add_ie': [FoxNewsIE.ie_key()], - } - - def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - - embed_url = self._html_search_meta('embedUrl', webpage, 'embed URL') - - title = self._og_search_title(webpage) - description = self._og_search_description(webpage) - - return { - '_type': 'url_transparent', - 'ie_key': FoxNewsIE.ie_key(), - 'url': embed_url, - 'display_id': display_id, - 'title': title, - 'description': description, - } From 30374f4d40d8c993bf92c5af9b9c073da49fe8b9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 21 Jun 2018 23:06:58 +0700 Subject: [PATCH 032/558] [itv] Make SOAP request non fatal and extract metadata from a webpage (closes #16780) --- youtube_dl/extractor/itv.py | 126 ++++++++++++++++++++---------------- 1 file changed, 69 insertions(+), 57 deletions(-) diff --git a/youtube_dl/extractor/itv.py b/youtube_dl/extractor/itv.py index 6a4f8a505..40cffed46 100644 --- a/youtube_dl/extractor/itv.py +++ b/youtube_dl/extractor/itv.py @@ -18,6 +18,7 @@ from ..utils import ( xpath_element, xpath_text, int_or_none, + merge_dicts, parse_duration, smuggle_url, ExtractorError, @@ -129,64 +130,65 @@ class ITVIE(InfoExtractor): resp_env = self._download_xml( params['data-playlist-url'], video_id, - headers=headers, data=etree.tostring(req_env)) - playlist = xpath_element(resp_env, './/Playlist') - if playlist is None: - fault_code = xpath_text(resp_env, './/faultcode') - fault_string = xpath_text(resp_env, './/faultstring') - if fault_code == 'InvalidGeoRegion': - self.raise_geo_restricted( - msg=fault_string, countries=self._GEO_COUNTRIES) - elif fault_code not in ( - 'InvalidEntity', 'InvalidVodcrid', 'ContentUnavailable'): - raise ExtractorError( - '%s said: %s' % (self.IE_NAME, fault_string), expected=True) - info.update({ - 'title': self._og_search_title(webpage), - 'episode_title': params.get('data-video-episode'), - 'series': params.get('data-video-title'), - }) - else: - title = xpath_text(playlist, 'EpisodeTitle', default=None) - info.update({ - 'title': title, - 'episode_title': title, - 'episode_number': int_or_none(xpath_text(playlist, 'EpisodeNumber')), - 'series': xpath_text(playlist, 'ProgrammeTitle'), - 'duration': parse_duration(xpath_text(playlist, 'Duration')), - }) - video_element = xpath_element(playlist, 'VideoEntries/Video', fatal=True) - media_files = xpath_element(video_element, 'MediaFiles', fatal=True) - rtmp_url = media_files.attrib['base'] + headers=headers, data=etree.tostring(req_env), fatal=False) + if resp_env: + playlist = xpath_element(resp_env, './/Playlist') + if playlist is None: + fault_code = xpath_text(resp_env, './/faultcode') + fault_string = xpath_text(resp_env, './/faultstring') + if fault_code == 'InvalidGeoRegion': + self.raise_geo_restricted( + msg=fault_string, countries=self._GEO_COUNTRIES) + elif fault_code not in ( + 'InvalidEntity', 'InvalidVodcrid', 'ContentUnavailable'): + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, fault_string), expected=True) + info.update({ + 'title': self._og_search_title(webpage), + 'episode_title': params.get('data-video-episode'), + 'series': params.get('data-video-title'), + }) + else: + title = xpath_text(playlist, 'EpisodeTitle', default=None) + info.update({ + 'title': title, + 'episode_title': title, + 'episode_number': int_or_none(xpath_text(playlist, 'EpisodeNumber')), + 'series': xpath_text(playlist, 'ProgrammeTitle'), + 'duration': parse_duration(xpath_text(playlist, 'Duration')), + }) + video_element = xpath_element(playlist, 'VideoEntries/Video', fatal=True) + media_files = xpath_element(video_element, 'MediaFiles', fatal=True) + rtmp_url = media_files.attrib['base'] - for media_file in media_files.findall('MediaFile'): - play_path = xpath_text(media_file, 'URL') - if not play_path: - continue - tbr = int_or_none(media_file.get('bitrate'), 1000) - f = { - 'format_id': 'rtmp' + ('-%d' % tbr if tbr else ''), - 'play_path': play_path, - # Providing this swfVfy allows to avoid truncated downloads - 'player_url': 'http://www.itv.com/mercury/Mercury_VideoPlayer.swf', - 'page_url': url, - 'tbr': tbr, - 'ext': 'flv', - } - app = self._search_regex( - 'rtmpe?://[^/]+/(.+)$', rtmp_url, 'app', default=None) - if app: - f.update({ - 'url': rtmp_url.split('?', 1)[0], - 'app': app, - }) - else: - f['url'] = rtmp_url - formats.append(f) + for media_file in media_files.findall('MediaFile'): + play_path = xpath_text(media_file, 'URL') + if not play_path: + continue + tbr = int_or_none(media_file.get('bitrate'), 1000) + f = { + 'format_id': 'rtmp' + ('-%d' % tbr if tbr else ''), + 'play_path': play_path, + # Providing this swfVfy allows to avoid truncated downloads + 'player_url': 'http://www.itv.com/mercury/Mercury_VideoPlayer.swf', + 'page_url': url, + 'tbr': tbr, + 'ext': 'flv', + } + app = self._search_regex( + 'rtmpe?://[^/]+/(.+)$', rtmp_url, 'app', default=None) + if app: + f.update({ + 'url': rtmp_url.split('?', 1)[0], + 'app': app, + }) + else: + f['url'] = rtmp_url + formats.append(f) - for caption_url in video_element.findall('ClosedCaptioningURIs/URL'): - if caption_url.text: - extract_subtitle(caption_url.text) + for caption_url in video_element.findall('ClosedCaptioningURIs/URL'): + if caption_url.text: + extract_subtitle(caption_url.text) ios_playlist_url = params.get('data-video-playlist') or params.get('data-video-id') hmac = params.get('data-video-hmac') @@ -261,7 +263,17 @@ class ITVIE(InfoExtractor): 'formats': formats, 'subtitles': subtitles, }) - return info + + webpage_info = self._search_json_ld(webpage, video_id, default={}) + if not webpage_info.get('title'): + webpage_info['title'] = self._html_search_regex( + r'(?s)<h\d+[^>]+\bclass=["\'][^>]*episode-title["\'][^>]*>([^<]+)<', + webpage, 'title', default=None) or self._og_search_title( + webpage, default=None) or self._html_search_meta( + 'twitter:title', webpage, 'title', + default=None) or webpage_info['episode'] + + return merge_dicts(info, webpage_info) class ITVBTCCIE(InfoExtractor): From a4ec45179e554e9b24e32c3c06908804b42a5a9c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 21 Jun 2018 23:12:40 +0700 Subject: [PATCH 033/558] [itv] Sort imports --- youtube_dl/extractor/itv.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/itv.py b/youtube_dl/extractor/itv.py index 40cffed46..d05a7b68d 100644 --- a/youtube_dl/extractor/itv.py +++ b/youtube_dl/extractor/itv.py @@ -13,16 +13,16 @@ from ..compat import ( compat_etree_register_namespace, ) from ..utils import ( + determine_ext, + ExtractorError, extract_attributes, - xpath_with_ns, - xpath_element, - xpath_text, int_or_none, merge_dicts, parse_duration, smuggle_url, - ExtractorError, - determine_ext, + xpath_with_ns, + xpath_element, + xpath_text, ) From b71cc719103c45365244334a4c481f88cd3534fc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 21 Jun 2018 23:38:32 +0700 Subject: [PATCH 034/558] [motherless] Fix extraction (closes #16786) --- youtube_dl/extractor/motherless.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/motherless.py b/youtube_dl/extractor/motherless.py index e24396e79..f191310e1 100644 --- a/youtube_dl/extractor/motherless.py +++ b/youtube_dl/extractor/motherless.py @@ -77,8 +77,11 @@ class MotherlessIE(InfoExtractor): title = self._html_search_regex( r'id="view-upload-title">\s+([^<]+)<', webpage, 'title') - video_url = self._html_search_regex( - r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video URL') + video_url = (self._html_search_regex( + (r'setup\(\{\s*["\']file["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', + r'fileurl\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1'), + webpage, 'video URL', default=None, group='url') or + 'http://cdn4.videos.motherlessmedia.com/videos/%s.mp4?fs=opencloud' % video_id) age_limit = self._rta_search(webpage) view_count = str_to_int(self._html_search_regex( r'<strong>Views</strong>\s+([^<]+)<', From 9fb62e35f6e7d865a73cc310f24ccfa0700e5e26 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 21 Jun 2018 23:39:13 +0700 Subject: [PATCH 035/558] [motherless:group] Fix _VALID_URL --- youtube_dl/extractor/motherless.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/motherless.py b/youtube_dl/extractor/motherless.py index f191310e1..bed5645f2 100644 --- a/youtube_dl/extractor/motherless.py +++ b/youtube_dl/extractor/motherless.py @@ -123,7 +123,7 @@ class MotherlessIE(InfoExtractor): class MotherlessGroupIE(InfoExtractor): - _VALID_URL = 'https?://(?:www\.)?motherless\.com/gv?/(?P<id>[a-z0-9_]+)' + _VALID_URL = r'https?://(?:www\.)?motherless\.com/gv?/(?P<id>[a-z0-9_]+)' _TESTS = [{ 'url': 'http://motherless.com/g/movie_scenes', 'info_dict': { From 74caf528bc822738dffe231df86ed399fc97a38a Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 24 Jun 2018 12:02:16 +0100 Subject: [PATCH 036/558] [brightcove] workaround sonyliv DRM protected videos(closes #16807) --- youtube_dl/extractor/brightcove.py | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index ab62e54d6..14f9a14ed 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -572,7 +572,8 @@ class BrightcoveNewIE(AdobePassIE): container = source.get('container') ext = mimetype2ext(source.get('type')) src = source.get('src') - if ext == 'ism' or container == 'WVM': + # https://support.brightcove.com/playback-api-video-fields-reference#key_systems_object + if ext == 'ism' or container == 'WVM' or source.get('key_systems'): continue elif ext == 'm3u8' or container == 'M2TS': if not src: @@ -629,6 +630,14 @@ class BrightcoveNewIE(AdobePassIE): 'format_id': build_format_id('rtmp'), }) formats.append(f) + if not formats: + # for sonyliv.com DRM protected videos + s3_source_url = json_data.get('custom_fields', {}).get('s3sourceurl') + if s3_source_url: + formats.append({ + 'url': s3_source_url, + 'format_id': 'source', + }) errors = json_data.get('errors') if not formats and errors: From a0949fec081d0badd6a584526cd66e8f170625c2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 24 Jun 2018 23:57:22 +0700 Subject: [PATCH 037/558] [joj] Relax _VALID_URL (closes #16771) --- youtube_dl/extractor/joj.py | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/joj.py b/youtube_dl/extractor/joj.py index a764023e9..d9f8dbfd2 100644 --- a/youtube_dl/extractor/joj.py +++ b/youtube_dl/extractor/joj.py @@ -18,7 +18,7 @@ class JojIE(InfoExtractor): joj:| https?://media\.joj\.sk/embed/ ) - (?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}) + (?P<id>[^/?#^]+) ''' _TESTS = [{ 'url': 'https://media.joj.sk/embed/a388ec4c-6019-4a4a-9312-b1bee194e932', @@ -29,16 +29,24 @@ class JojIE(InfoExtractor): 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 3118, } + }, { + 'url': 'https://media.joj.sk/embed/9i1cxv', + 'only_matching': True, }, { 'url': 'joj:a388ec4c-6019-4a4a-9312-b1bee194e932', 'only_matching': True, + }, { + 'url': 'joj:9i1cxv', + 'only_matching': True, }] @staticmethod def _extract_urls(webpage): - return re.findall( - r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//media\.joj\.sk/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})', - webpage) + return [ + mobj.group('url') + for mobj in re.finditer( + r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//media\.joj\.sk/embed/(?:(?!\1).)+)\1', + webpage)] def _real_extract(self, url): video_id = self._match_id(url) From c306f076ec81334b458f61b2a4ae683a9e732d06 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 25 Jun 2018 02:17:14 +0700 Subject: [PATCH 038/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/ChangeLog b/ChangeLog index 93dc40d8c..327580328 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,14 @@ +version <unreleased> + +Extractors +* [joj] Relax URL regular expression (#16771) +* [brightcove] Workaround sonyliv DRM protected videos (#16807) +* [motherless] Fix extraction (#16786) +* [itv] Make SOAP request non fatal and extract metadata from webpage (#16780) +- [foxnews:insider] Remove extractor (#15810) ++ [foxnews] Add support for iframe embeds (#15810, #16711) + + version 2018.06.19 Core From 1f6cc5807ec69584664388b8edfaf6b3ae442cea Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 25 Jun 2018 02:26:02 +0700 Subject: [PATCH 039/558] release 2018.06.25 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 1 - youtube_dl/version.py | 2 +- 4 files changed, 5 insertions(+), 6 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index d254678b5..128e6e681 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.06.19*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.06.19** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.06.25*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.06.25** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.06.19 +[debug] youtube-dl version 2018.06.25 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 327580328..8eb7469d4 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.06.25 Extractors * [joj] Relax URL regular expression (#16771) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 432a7ba93..a78fabb02 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -290,7 +290,6 @@ - **Foxgay** - **foxnews**: Fox News and Fox Business Video - **foxnews:article** - - **foxnews:insider** - **FoxSports** - **france2.fr:generation-what** - **FranceCulture** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index dd4795cd1..8fbafd6a1 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.06.19' +__version__ = '2018.06.25' From c3bcd206eb031de30179c88ac7acd806a477ceae Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 26 Jun 2018 00:01:06 +0700 Subject: [PATCH 040/558] [porncom] Fix extraction (closes #16808) --- youtube_dl/extractor/porncom.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/porncom.py b/youtube_dl/extractor/porncom.py index 60ade06da..5726cab3a 100644 --- a/youtube_dl/extractor/porncom.py +++ b/youtube_dl/extractor/porncom.py @@ -43,7 +43,8 @@ class PornComIE(InfoExtractor): config = self._parse_json( self._search_regex( - r'=\s*({.+?})\s*,\s*[\da-zA-Z_]+\s*=', + (r'=\s*({.+?})\s*;\s*v1ar\b', + r'=\s*({.+?})\s*,\s*[\da-zA-Z_]+\s*='), webpage, 'config', default='{}'), display_id, transform_source=js_to_json, fatal=False) @@ -69,7 +70,7 @@ class PornComIE(InfoExtractor): 'height': int(height), 'filesize_approx': parse_filesize(filesize), } for format_url, height, filesize in re.findall( - r'<a[^>]+href="(/download/[^"]+)">MPEG4 (\d+)p<span[^>]*>(\d+\s+[a-zA-Z]+)<', + r'<a[^>]+href="(/download/[^"]+)">[^<]*?(\d+)p<span[^>]*>(\d+\s*[a-zA-Z]+)<', webpage)] thumbnail = None duration = None From 7b393f9cc5dc4790bcb623c768fa4a3046ef80bf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 28 Jun 2018 04:29:11 +0700 Subject: [PATCH 041/558] [svt] Improve extraction and add support for pages (closes #16802) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/generic.py | 11 --- youtube_dl/extractor/svt.py | 117 ++++++++++++++++++++++++----- 3 files changed, 98 insertions(+), 31 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 27ece3b53..f2377521b 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1040,6 +1040,7 @@ from .stretchinternet import StretchInternetIE from .sunporno import SunPornoIE from .svt import ( SVTIE, + SVTPageIE, SVTPlayIE, SVTSeriesIE, ) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index d71cb9050..aa04905ed 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -1395,17 +1395,6 @@ class GenericIE(InfoExtractor): 'skip_download': True, }, }, - # SVT embed - { - 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun', - 'info_dict': { - 'id': '2900353', - 'ext': 'flv', - 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)', - 'duration': 27, - 'age_limit': 0, - }, - }, # Crooks and Liars embed { 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists', diff --git a/youtube_dl/extractor/svt.py b/youtube_dl/extractor/svt.py index f71eab8b2..0901c3163 100644 --- a/youtube_dl/extractor/svt.py +++ b/youtube_dl/extractor/svt.py @@ -12,6 +12,8 @@ from ..utils import ( determine_ext, dict_get, int_or_none, + orderedSet, + strip_or_none, try_get, urljoin, compat_str, @@ -137,7 +139,12 @@ class SVTPlayBaseIE(SVTBaseIE): class SVTPlayIE(SVTPlayBaseIE): IE_DESC = 'SVT Play and Öppet arkiv' - _VALID_URL = r'https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/(?:video|klipp|kanaler)/(?P<id>[^/?#&]+)' + _VALID_URL = r'''(?x) + (?: + svt:(?P<svt_id>[^/?#&]+)| + https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/(?:video|klipp|kanaler)/(?P<id>[^/?#&]+) + ) + ''' _TESTS = [{ 'url': 'http://www.svtplay.se/video/5996901/flygplan-till-haile-selassie/flygplan-till-haile-selassie-2', 'md5': '2b6704fe4a28801e1a098bbf3c5ac611', @@ -164,10 +171,40 @@ class SVTPlayIE(SVTPlayBaseIE): }, { 'url': 'https://www.svtplay.se/kanaler/svt1', 'only_matching': True, + }, { + 'url': 'svt:1376446-003A', + 'only_matching': True, + }, { + 'url': 'svt:14278044', + 'only_matching': True, }] + def _adjust_title(self, info): + if info['is_live']: + info['title'] = self._live_title(info['title']) + + def _extract_by_video_id(self, video_id, webpage=None): + data = self._download_json( + 'https://api.svt.se/videoplayer-api/video/%s' % video_id, + video_id, headers=self.geo_verification_headers()) + info_dict = self._extract_video(data, video_id) + if not info_dict.get('title'): + title = dict_get(info_dict, ('episode', 'series')) + if not title and webpage: + title = re.sub( + r'\s*\|\s*.+?$', '', self._og_search_title(webpage)) + if not title: + title = video_id + info_dict['title'] = title + self._adjust_title(info_dict) + return info_dict + def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + video_id, svt_id = mobj.group('id', 'svt_id') + + if svt_id: + return self._extract_by_video_id(svt_id) webpage = self._download_webpage(url, video_id) @@ -179,10 +216,6 @@ class SVTPlayIE(SVTPlayBaseIE): thumbnail = self._og_search_thumbnail(webpage) - def adjust_title(info): - if info['is_live']: - info['title'] = self._live_title(info['title']) - if data: video_info = try_get( data, lambda x: x['context']['dispatcher']['stores']['VideoTitlePageStore']['data']['video'], @@ -193,24 +226,14 @@ class SVTPlayIE(SVTPlayBaseIE): 'title': data['context']['dispatcher']['stores']['MetaStore']['title'], 'thumbnail': thumbnail, }) - adjust_title(info_dict) + self._adjust_title(info_dict) return info_dict - video_id = self._search_regex( + svt_id = self._search_regex( r'<video[^>]+data-video-id=["\']([\da-zA-Z-]+)', - webpage, 'video id', default=None) + webpage, 'video id') - if video_id: - data = self._download_json( - 'https://api.svt.se/videoplayer-api/video/%s' % video_id, - video_id, headers=self.geo_verification_headers()) - info_dict = self._extract_video(data, video_id) - if not info_dict.get('title'): - info_dict['title'] = re.sub( - r'\s*\|\s*.+?$', '', - info_dict.get('episode') or self._og_search_title(webpage)) - adjust_title(info_dict) - return info_dict + return self._extract_by_video_id(svt_id, webpage) class SVTSeriesIE(SVTPlayBaseIE): @@ -292,3 +315,57 @@ class SVTSeriesIE(SVTPlayBaseIE): return self.playlist_result( entries, series_id, title, metadata.get('description')) + + +class SVTPageIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?svt\.se/(?:[^/]+/)*(?P<id>[^/?&#]+)' + _TESTS = [{ + 'url': 'https://www.svt.se/sport/oseedat/guide-sommartraningen-du-kan-gora-var-och-nar-du-vill', + 'info_dict': { + 'id': 'guide-sommartraningen-du-kan-gora-var-och-nar-du-vill', + 'title': 'GUIDE: Sommarträning du kan göra var och när du vill', + }, + 'playlist_count': 7, + }, { + 'url': 'https://www.svt.se/nyheter/inrikes/ebba-busch-thor-kd-har-delvis-ratt-om-no-go-zoner', + 'info_dict': { + 'id': 'ebba-busch-thor-kd-har-delvis-ratt-om-no-go-zoner', + 'title': 'Ebba Busch Thor har bara delvis rätt om ”no-go-zoner”', + }, + 'playlist_count': 1, + }, { + # only programTitle + 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun', + 'info_dict': { + 'id': '2900353', + 'ext': 'mp4', + 'title': 'Stjärnorna skojar till det - under SVT-intervjun', + 'duration': 27, + 'age_limit': 0, + }, + }, { + 'url': 'https://www.svt.se/nyheter/lokalt/vast/svt-testar-tar-nagon-upp-skrapet-1', + 'only_matching': True, + }, { + 'url': 'https://www.svt.se/vader/manadskronikor/maj2018', + 'only_matching': True, + }] + + @classmethod + def suitable(cls, url): + return False if SVTIE.suitable(url) else super(SVTPageIE, cls).suitable(url) + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + entries = [ + self.url_result( + 'svt:%s' % video_id, ie=SVTPlayIE.ie_key(), video_id=video_id) + for video_id in orderedSet(re.findall( + r'data-video-id=["\'](\d+)', webpage))] + + title = strip_or_none(self._og_search_title(webpage, default=None)) + + return self.playlist_result(entries, playlist_id, title) From acbd0ff5df5ff9d69e6707ea4fa3e3b4f9cc6528 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 29 Jun 2018 00:35:05 +0700 Subject: [PATCH 042/558] [dctptv] Restore extraction based on REST API (closes #16850) --- youtube_dl/extractor/dctp.py | 82 ++++++++++++++++++++++++------------ 1 file changed, 55 insertions(+), 27 deletions(-) diff --git a/youtube_dl/extractor/dctp.py b/youtube_dl/extractor/dctp.py index 3a6d0560e..dc0c41b8a 100644 --- a/youtube_dl/extractor/dctp.py +++ b/youtube_dl/extractor/dctp.py @@ -5,13 +5,15 @@ from .common import InfoExtractor from ..compat import compat_str from ..utils import ( float_or_none, - unified_strdate, + int_or_none, + unified_timestamp, ) class DctpTvIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?dctp\.tv/(?:#/)?filme/(?P<id>[^/?#&]+)' - _TEST = { + _TESTS = [{ + # 4x3 'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/', 'info_dict': { 'id': '95eaa4f33dad413aa17b4ee613cccc6c', @@ -19,31 +21,49 @@ class DctpTvIE(InfoExtractor): 'ext': 'flv', 'title': 'Videoinstallation für eine Kaufhausfassade', 'description': 'Kurzfilm', - 'upload_date': '20110407', 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 71.24, + 'timestamp': 1302172322, + 'upload_date': '20110407', }, 'params': { # rtmp download 'skip_download': True, }, - } + }, { + # 16x9 + 'url': 'http://www.dctp.tv/filme/sind-youtuber-die-besseren-lehrer/', + 'only_matching': True, + }] + + _BASE_URL = 'http://dctp-ivms2-restapi.s3.amazonaws.com' def _real_extract(self, url): display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) + version = self._download_json( + '%s/version.json' % self._BASE_URL, display_id, + 'Downloading version JSON') - video_id = self._html_search_meta( - 'DC.identifier', webpage, 'video id', - default=None) or self._search_regex( - r'id=["\']uuid[^>]+>([^<]+)<', webpage, 'video id') + restapi_base = '%s/%s/restapi' % ( + self._BASE_URL, version['version_name']) - title = self._og_search_title(webpage) + info = self._download_json( + '%s/slugs/%s.json' % (restapi_base, display_id), display_id, + 'Downloading video info JSON') + + media = self._download_json( + '%s/media/%s.json' % (restapi_base, compat_str(info['object_id'])), + display_id, 'Downloading media JSON') + + uuid = media['uuid'] + title = media['title'] + ratio = '16x9' if media.get('is_wide') else '4x3' + play_path = 'mp4:%s_dctp_0500_%s.m4v' % (uuid, ratio) servers = self._download_json( 'http://www.dctp.tv/streaming_servers/', display_id, - note='Downloading server list', fatal=False) + note='Downloading server list JSON', fatal=False) if servers: endpoint = next( @@ -60,27 +80,35 @@ class DctpTvIE(InfoExtractor): formats = [{ 'url': endpoint, 'app': app, - 'play_path': 'mp4:%s_dctp_0500_4x3.m4v' % video_id, + 'play_path': play_path, 'page_url': url, - 'player_url': 'http://svm-prod-dctptv-static.s3.amazonaws.com/dctptv-relaunch2012-109.swf', + 'player_url': 'http://svm-prod-dctptv-static.s3.amazonaws.com/dctptv-relaunch2012-110.swf', 'ext': 'flv', }] - description = self._html_search_meta('DC.description', webpage) - upload_date = unified_strdate( - self._html_search_meta('DC.date.created', webpage)) - thumbnail = self._og_search_thumbnail(webpage) - duration = float_or_none(self._search_regex( - r'id=["\']duration_in_ms[^+]>(\d+)', webpage, 'duration', - default=None), scale=1000) + thumbnails = [] + images = media.get('images') + if isinstance(images, list): + for image in images: + if not isinstance(image, dict): + continue + image_url = image.get('url') + if not image_url or not isinstance(image_url, compat_str): + continue + thumbnails.append({ + 'url': image_url, + 'width': int_or_none(image.get('width')), + 'height': int_or_none(image.get('height')), + }) return { - 'id': video_id, - 'title': title, - 'formats': formats, + 'id': uuid, 'display_id': display_id, - 'description': description, - 'upload_date': upload_date, - 'thumbnail': thumbnail, - 'duration': duration, + 'title': title, + 'alt_title': media.get('subtitle'), + 'description': media.get('description') or media.get('teaser'), + 'timestamp': unified_timestamp(media.get('created')), + 'duration': float_or_none(media.get('duration_in_ms'), scale=1000), + 'thumbnails': thumbnails, + 'formats': formats, } From d4a24f4091a622b808ff621e78b5cfd0db3c8c11 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 29 Jun 2018 01:09:14 +0700 Subject: [PATCH 043/558] Prefer ffmpeg over avconv by default (closes #8622) --- youtube_dl/YoutubeDL.py | 4 ++-- youtube_dl/options.py | 4 ++-- youtube_dl/postprocessor/ffmpeg.py | 16 ++++++++-------- 3 files changed, 12 insertions(+), 12 deletions(-) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 2a405c5ca..38ba43a97 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -305,8 +305,8 @@ class YoutubeDL(object): http_chunk_size. The following options are used by the post processors: - prefer_ffmpeg: If True, use ffmpeg instead of avconv if both are available, - otherwise prefer avconv. + prefer_ffmpeg: If False, use avconv instead of ffmpeg if both are available, + otherwise prefer ffmpeg. postprocessor_args: A list of additional command-line arguments for the postprocessor. diff --git a/youtube_dl/options.py b/youtube_dl/options.py index e83d546a0..e7d8e8910 100644 --- a/youtube_dl/options.py +++ b/youtube_dl/options.py @@ -841,11 +841,11 @@ def parseOpts(overrideArguments=None): postproc.add_option( '--prefer-avconv', action='store_false', dest='prefer_ffmpeg', - help='Prefer avconv over ffmpeg for running the postprocessors (default)') + help='Prefer avconv over ffmpeg for running the postprocessors') postproc.add_option( '--prefer-ffmpeg', action='store_true', dest='prefer_ffmpeg', - help='Prefer ffmpeg over avconv for running the postprocessors') + help='Prefer ffmpeg over avconv for running the postprocessors (default)') postproc.add_option( '--ffmpeg-location', '--avconv-location', metavar='PATH', dest='ffmpeg_location', diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 3ea1afcf3..757b496a1 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -77,7 +77,7 @@ class FFmpegPostProcessor(PostProcessor): def _determine_executables(self): programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe'] - prefer_ffmpeg = False + prefer_ffmpeg = True self.basename = None self.probe_basename = None @@ -85,7 +85,7 @@ class FFmpegPostProcessor(PostProcessor): self._paths = None self._versions = None if self._downloader: - prefer_ffmpeg = self._downloader.params.get('prefer_ffmpeg', False) + prefer_ffmpeg = self._downloader.params.get('prefer_ffmpeg', True) location = self._downloader.params.get('ffmpeg_location') if location is not None: if not os.path.exists(location): @@ -117,19 +117,19 @@ class FFmpegPostProcessor(PostProcessor): (p, get_exe_version(p, args=['-version'])) for p in programs) self._paths = dict((p, p) for p in programs) - if prefer_ffmpeg: - prefs = ('ffmpeg', 'avconv') - else: + if prefer_ffmpeg is False: prefs = ('avconv', 'ffmpeg') + else: + prefs = ('ffmpeg', 'avconv') for p in prefs: if self._versions[p]: self.basename = p break - if prefer_ffmpeg: - prefs = ('ffprobe', 'avprobe') - else: + if prefer_ffmpeg is False: prefs = ('avprobe', 'ffprobe') + else: + prefs = ('ffprobe', 'avprobe') for p in prefs: if self._versions[p]: self.probe_basename = p From 5e8e2fa51f416e227367211ab937dfea17f89f57 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 29 Jun 2018 01:25:05 +0700 Subject: [PATCH 044/558] [extractor/common] Use source URL as Referer for HTML5 entries (closes #16849) --- youtube_dl/extractor/common.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 394f34372..f3fec160d 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -2437,6 +2437,8 @@ class InfoExtractor(object): media_info['subtitles'].setdefault(lang, []).append({ 'url': absolute_url(src), }) + for f in media_info['formats']: + f.setdefault('http_headers', {})['Referer'] = base_url if media_info['formats'] or media_info['subtitles']: entries.append(media_info) return entries From 9cf648c92bcc131db7d7fad673864bba06121482 Mon Sep 17 00:00:00 2001 From: Timendum <timedum@gmail.com> Date: Mon, 18 Jun 2018 11:50:06 +0200 Subject: [PATCH 045/558] [mediaset] Add support for new videos --- youtube_dl/extractor/mediaset.py | 60 ++++++++++++++++++++++---------- 1 file changed, 41 insertions(+), 19 deletions(-) diff --git a/youtube_dl/extractor/mediaset.py b/youtube_dl/extractor/mediaset.py index 9760eafd5..76a2ae125 100644 --- a/youtube_dl/extractor/mediaset.py +++ b/youtube_dl/extractor/mediaset.py @@ -10,6 +10,7 @@ from ..utils import ( parse_duration, try_get, unified_strdate, + ExtractorError ) @@ -42,6 +43,22 @@ class MediasetIE(InfoExtractor): 'categories': ['reality'], }, 'expected_warnings': ['is not a supported codec'], + }, { + 'url': 'http://www.video.mediaset.it/video/matrix/full_chiambretti/puntata-del-25-maggio_846685.html', + 'md5': '1276f966ac423d16ba255ce867de073e', + 'info_dict': { + 'id': '846685', + 'ext': 'mp4', + 'title': 'Puntata del 25 maggio', + 'description': 'md5:ee2e456e3eb1dba5e814596655bb5296', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 6565, + 'creator': 'mediaset', + 'upload_date': '20180525', + 'series': 'Matrix', + 'categories': ['infotainment'], + }, + 'expected_warnings': ['is not a supported codec'], }, { # clip 'url': 'http://www.video.mediaset.it/video/gogglebox/clip/un-grande-classico-della-commedia-sexy_661680.html', @@ -70,18 +87,29 @@ class MediasetIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) + media_info = self._download_json( + 'https://www.video.mediaset.it/html/metainfo.sjson', + video_id, 'Downloading media info', query={ + 'id': video_id + })['video'] + + media_id = try_get(media_info, lambda x: x['guid']) or video_id + video_list = self._download_json( - 'http://cdnsel01.mediaset.net/GetCdn.aspx', + 'http://cdnsel01.mediaset.net/GetCdn2018.aspx', video_id, 'Downloading video CDN JSON', query={ - 'streamid': video_id, + 'streamid': media_id, 'format': 'json', })['videoList'] formats = [] for format_url in video_list: if '.ism' in format_url: - formats.extend(self._extract_ism_formats( - format_url, video_id, ism_id='mss', fatal=False)) + try: + formats.extend(self._extract_ism_formats( + format_url, video_id, ism_id='mss', fatal=False)) + except ExtractorError: + pass else: formats.append({ 'url': format_url, @@ -89,30 +117,24 @@ class MediasetIE(InfoExtractor): }) self._sort_formats(formats) - mediainfo = self._download_json( - 'http://plr.video.mediaset.it/html/metainfo.sjson', - video_id, 'Downloading video info JSON', query={ - 'id': video_id, - })['video'] - - title = mediainfo['title'] + title = media_info['title'] creator = try_get( - mediainfo, lambda x: x['brand-info']['publisher'], compat_str) + media_info, lambda x: x['brand-info']['publisher'], compat_str) category = try_get( - mediainfo, lambda x: x['brand-info']['category'], compat_str) + media_info, lambda x: x['brand-info']['category'], compat_str) categories = [category] if category else None return { 'id': video_id, 'title': title, - 'description': mediainfo.get('short-description'), - 'thumbnail': mediainfo.get('thumbnail'), - 'duration': parse_duration(mediainfo.get('duration')), + 'description': media_info.get('short-description'), + 'thumbnail': media_info.get('thumbnail'), + 'duration': parse_duration(media_info.get('duration')), 'creator': creator, - 'upload_date': unified_strdate(mediainfo.get('production-date')), - 'webpage_url': mediainfo.get('url'), - 'series': mediainfo.get('brand-value'), + 'upload_date': unified_strdate(media_info.get('production-date')), + 'webpage_url': media_info.get('url'), + 'series': media_info.get('brand-value'), 'categories': categories, 'formats': formats, } From 267d81962a0709f15f82f96b7aadbb5473a06992 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 30 Jun 2018 02:16:44 +0700 Subject: [PATCH 046/558] [mediaset] Fix issues and extract all formats (closes #16568) --- youtube_dl/extractor/mediaset.py | 44 +++++++++++++++++--------------- 1 file changed, 24 insertions(+), 20 deletions(-) diff --git a/youtube_dl/extractor/mediaset.py b/youtube_dl/extractor/mediaset.py index 76a2ae125..9f2b60dcc 100644 --- a/youtube_dl/extractor/mediaset.py +++ b/youtube_dl/extractor/mediaset.py @@ -10,7 +10,6 @@ from ..utils import ( parse_duration, try_get, unified_strdate, - ExtractorError ) @@ -58,7 +57,7 @@ class MediasetIE(InfoExtractor): 'series': 'Matrix', 'categories': ['infotainment'], }, - 'expected_warnings': ['is not a supported codec'], + 'expected_warnings': ['HTTP Error 403: Forbidden'], }, { # clip 'url': 'http://www.video.mediaset.it/video/gogglebox/clip/un-grande-classico-della-commedia-sexy_661680.html', @@ -87,13 +86,14 @@ class MediasetIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - media_info = self._download_json( + video = self._download_json( 'https://www.video.mediaset.it/html/metainfo.sjson', video_id, 'Downloading media info', query={ 'id': video_id })['video'] - media_id = try_get(media_info, lambda x: x['guid']) or video_id + title = video['title'] + media_id = video.get('guid') or video_id video_list = self._download_json( 'http://cdnsel01.mediaset.net/GetCdn2018.aspx', @@ -104,12 +104,17 @@ class MediasetIE(InfoExtractor): formats = [] for format_url in video_list: - if '.ism' in format_url: - try: - formats.extend(self._extract_ism_formats( - format_url, video_id, ism_id='mss', fatal=False)) - except ExtractorError: - pass + ext = determine_ext(format_url) + if ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + elif ext == 'mpd': + formats.extend(self._extract_mpd_formats( + format_url, video_id, mpd_id='dash', fatal=False)) + elif ext == 'ism' or '.ism' in format_url: + formats.extend(self._extract_ism_formats( + format_url, video_id, ism_id='mss', fatal=False)) else: formats.append({ 'url': format_url, @@ -117,24 +122,23 @@ class MediasetIE(InfoExtractor): }) self._sort_formats(formats) - title = media_info['title'] - creator = try_get( - media_info, lambda x: x['brand-info']['publisher'], compat_str) + video, lambda x: x['brand-info']['publisher'], compat_str) category = try_get( - media_info, lambda x: x['brand-info']['category'], compat_str) + video, lambda x: x['brand-info']['category'], compat_str) categories = [category] if category else None return { 'id': video_id, 'title': title, - 'description': media_info.get('short-description'), - 'thumbnail': media_info.get('thumbnail'), - 'duration': parse_duration(media_info.get('duration')), + 'description': video.get('short-description'), + 'thumbnail': video.get('thumbnail'), + 'duration': parse_duration(video.get('duration')), 'creator': creator, - 'upload_date': unified_strdate(media_info.get('production-date')), - 'webpage_url': media_info.get('url'), - 'series': media_info.get('brand-value'), + 'upload_date': unified_strdate(video.get('production-date')), + 'webpage_url': video.get('url'), + 'series': video.get('brand-value'), + 'season': video.get('season'), 'categories': categories, 'formats': formats, } From 2160768a215849e82a167912cb8f0aa054e87d8c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 30 Jun 2018 23:39:56 +0700 Subject: [PATCH 047/558] [npo] Fix typo (closes #16872) --- youtube_dl/extractor/npo.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index cb8319f0d..c2cb85a73 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -282,7 +282,7 @@ class NPOIE(NPOBaseIE): video_url = stream_info.get('url') if not video_url or video_url in urls: continue - urls.add(item_url) + urls.add(video_url) if determine_ext(video_url) == 'm3u8': formats.extend(self._extract_m3u8_formats( video_url, video_id, ext='mp4', From eca1f0d115e6a2712ff0d5f6b25e3ded5e52db71 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 1 Jul 2018 02:00:16 +0700 Subject: [PATCH 048/558] [extractor/common] Properly escape % in MPD templates (closes #16867) --- youtube_dl/extractor/common.py | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index f3fec160d..78f053f18 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -2106,7 +2106,21 @@ class InfoExtractor(object): representation_ms_info = extract_multisegment_info(representation, adaption_set_ms_info) def prepare_template(template_name, identifiers): - t = representation_ms_info[template_name] + tmpl = representation_ms_info[template_name] + # First of, % characters outside $...$ templates + # must be escaped by doubling for proper processing + # by % operator string formatting used further (see + # https://github.com/rg3/youtube-dl/issues/16867). + t = '' + in_template = False + for c in tmpl: + t += c + if c == '$': + in_template = not in_template + elif c == '%' and not in_template: + t += c + # Next, $...$ templates are translated to their + # %(...) counterparts to be used with % operator t = t.replace('$RepresentationID$', representation_id) t = re.sub(r'\$(%s)\$' % '|'.join(identifiers), r'%(\1)d', t) t = re.sub(r'\$(%s)%%([^$]+)\$' % '|'.join(identifiers), r'%(\1)\2', t) From 973b6ceebbf0c79086cbf3203a8a8c79daf0b1ba Mon Sep 17 00:00:00 2001 From: coreynicholson <coreynicholson@users.noreply.github.com> Date: Sun, 1 Jul 2018 15:19:17 +0100 Subject: [PATCH 049/558] [vlive] Fix live streams extraction --- youtube_dl/extractor/vlive.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/vlive.py b/youtube_dl/extractor/vlive.py index 64d0224e6..0b5165fd0 100644 --- a/youtube_dl/extractor/vlive.py +++ b/youtube_dl/extractor/vlive.py @@ -57,7 +57,7 @@ class VLiveIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage( - 'http://www.vlive.tv/video/%s' % video_id, video_id) + 'https://www.vlive.tv/video/%s' % video_id, video_id) VIDEO_PARAMS_RE = r'\bvlive\.video\.init\(([^)]+)' VIDEO_PARAMS_FIELD = 'video params' @@ -108,11 +108,11 @@ class VLiveIE(InfoExtractor): def _live(self, video_id, webpage): init_page = self._download_webpage( - 'http://www.vlive.tv/video/init/view', + 'https://www.vlive.tv/video/init/view', video_id, note='Downloading live webpage', data=urlencode_postdata({'videoSeq': video_id}), headers={ - 'Referer': 'http://www.vlive.tv/video/%s' % video_id, + 'Referer': 'https://www.vlive.tv/video/%s' % video_id, 'Content-Type': 'application/x-www-form-urlencoded' }) From 8cee692b8b66322e4c1a0d37baceb9e4c49a3f8e Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 1 Jul 2018 22:32:59 +0100 Subject: [PATCH 050/558] [go90] detect geo restriction error and pass geo verification headers(closes #16874) --- youtube_dl/extractor/go90.py | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/go90.py b/youtube_dl/extractor/go90.py index 35dde42d0..6f8c56a93 100644 --- a/youtube_dl/extractor/go90.py +++ b/youtube_dl/extractor/go90.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_HTTPError from ..utils import ( determine_ext, ExtractorError, @@ -28,14 +29,27 @@ class Go90IE(InfoExtractor): 'age_limit': 14, } } + _GEO_BYPASS = False def _real_extract(self, url): video_id = self._match_id(url) - video_data = self._download_json( - 'https://www.go90.com/api/view/items/' + video_id, - video_id, headers={ + + try: + headers = self.geo_verification_headers() + headers.update({ 'Content-Type': 'application/json; charset=utf-8', - }, data=b'{"client":"web","device_type":"pc"}') + }) + video_data = self._download_json( + 'https://www.go90.com/api/view/items/' + video_id, video_id, + headers=headers, data=b'{"client":"web","device_type":"pc"}') + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: + message = self._parse_json(e.cause.read().decode(), None)['error']['message'] + if 'region unavailable' in message: + self.raise_geo_restricted(countries=['US']) + raise ExtractorError(message, expected=True) + raise + if video_data.get('requires_drm'): raise ExtractorError('This video is DRM protected.', expected=True) main_video_asset = video_data['main_video_asset'] From db5debf313bd2ab99016f2c5b389dbf9ffae3dfb Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 1 Jul 2018 22:41:11 +0100 Subject: [PATCH 051/558] [go90] add support for embed urls(closes #16873) --- youtube_dl/extractor/go90.py | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/go90.py b/youtube_dl/extractor/go90.py index 6f8c56a93..c3ea717bc 100644 --- a/youtube_dl/extractor/go90.py +++ b/youtube_dl/extractor/go90.py @@ -15,8 +15,8 @@ from ..utils import ( class Go90IE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?go90\.com/videos/(?P<id>[0-9a-zA-Z]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?go90\.com/(?:videos|embed)/(?P<id>[0-9a-zA-Z]+)' + _TESTS = [{ 'url': 'https://www.go90.com/videos/84BUqjLpf9D', 'md5': 'efa7670dbbbf21a7b07b360652b24a32', 'info_dict': { @@ -28,7 +28,10 @@ class Go90IE(InfoExtractor): 'upload_date': '20170411', 'age_limit': 14, } - } + }, { + 'url': 'https://www.go90.com/embed/261MflWkD3N', + 'only_matching': True, + }] _GEO_BYPASS = False def _real_extract(self, url): From 5621c3222eaab29d5ca705c8dac2d0bc1eb785d6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 3 Jul 2018 02:47:09 +0700 Subject: [PATCH 052/558] [lynda] Simplify login and improve error capturing (#16891) --- youtube_dl/extractor/lynda.py | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py index f5c7abc13..1316cddb6 100644 --- a/youtube_dl/extractor/lynda.py +++ b/youtube_dl/extractor/lynda.py @@ -44,21 +44,15 @@ class LyndaBaseIE(InfoExtractor): form_data = self._hidden_inputs(form_html) form_data.update(extra_form_data) - try: - response = self._download_json( - action_url, None, note, - data=urlencode_postdata(form_data), - headers={ - 'Referer': referrer_url, - 'X-Requested-With': 'XMLHttpRequest', - }) - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500: - response = self._parse_json(e.cause.read().decode('utf-8'), None) - self._check_error(response, ('email', 'password')) - raise + response = self._download_json( + action_url, None, note, + data=urlencode_postdata(form_data), + headers={ + 'Referer': referrer_url, + 'X-Requested-With': 'XMLHttpRequest', + }, expected_status=(418, 500, )) - self._check_error(response, 'ErrorMessage') + self._check_error(response, ('email', 'password', 'ErrorMessage')) return response, action_url From 836ef4840f00d7e07c826de23f3a09675dc532d5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 4 Jul 2018 04:48:40 +0700 Subject: [PATCH 053/558] [pluralsight] Switch to graphql (closes #16889, closes #16899) --- youtube_dl/extractor/pluralsight.py | 120 +++++++++++++++++++++++----- 1 file changed, 101 insertions(+), 19 deletions(-) diff --git a/youtube_dl/extractor/pluralsight.py b/youtube_dl/extractor/pluralsight.py index a207ca9cb..1257841e4 100644 --- a/youtube_dl/extractor/pluralsight.py +++ b/youtube_dl/extractor/pluralsight.py @@ -27,6 +27,60 @@ from ..utils import ( class PluralsightBaseIE(InfoExtractor): _API_BASE = 'https://app.pluralsight.com' + _GRAPHQL_EP = '%s/player/api/graphql' % _API_BASE + _GRAPHQL_HEADERS = { + 'Content-Type': 'application/json;charset=UTF-8', + } + _GRAPHQL_COURSE_TMPL = ''' +query BootstrapPlayer { + rpc { + bootstrapPlayer { + profile { + firstName + lastName + email + username + userHandle + authed + isAuthed + plan + } + course(courseId: "%s") { + name + title + courseHasCaptions + translationLanguages { + code + name + } + supportsWideScreenVideoFormats + timestamp + modules { + name + title + duration + formattedDuration + author + authorized + clips { + authorized + clipId + duration + formattedDuration + id + index + moduleIndex + moduleTitle + name + title + watched + } + } + } + } + } +}''' + def _download_course(self, course_id, url, display_id): try: return self._download_course_rpc(course_id, url, display_id) @@ -39,20 +93,14 @@ class PluralsightBaseIE(InfoExtractor): def _download_course_rpc(self, course_id, url, display_id): response = self._download_json( - '%s/player/functions/rpc' % self._API_BASE, display_id, - 'Downloading course JSON', - data=json.dumps({ - 'fn': 'bootstrapPlayer', - 'payload': { - 'courseId': course_id, - }, - }).encode('utf-8'), - headers={ - 'Content-Type': 'application/json;charset=utf-8', - 'Referer': url, - }) + self._GRAPHQL_EP, display_id, data=json.dumps({ + 'query': self._GRAPHQL_COURSE_TMPL % course_id, + 'variables': {} + }).encode('utf-8'), headers=self._GRAPHQL_HEADERS) - course = try_get(response, lambda x: x['payload']['course'], dict) + course = try_get( + response, lambda x: x['data']['rpc']['bootstrapPlayer']['course'], + dict) if course: return course @@ -90,6 +138,28 @@ class PluralsightIE(PluralsightBaseIE): 'only_matching': True, }] + GRAPHQL_VIEWCLIP_TMPL = ''' +query viewClip { + viewClip(input: { + author: "%(author)s", + clipIndex: %(clipIndex)d, + courseName: "%(courseName)s", + includeCaptions: %(includeCaptions)s, + locale: "%(locale)s", + mediaType: "%(mediaType)s", + moduleName: "%(moduleName)s", + quality: "%(quality)s" + }) { + urls { + url + cdn + rank + source + }, + status + } +}''' + def _real_initialize(self): self._login() @@ -277,7 +347,7 @@ class PluralsightIE(PluralsightBaseIE): f = QUALITIES[quality].copy() clip_post = { 'author': author, - 'includeCaptions': False, + 'includeCaptions': 'false', 'clipIndex': int(clip_idx), 'courseName': course_name, 'locale': 'en', @@ -286,11 +356,23 @@ class PluralsightIE(PluralsightBaseIE): 'quality': '%dx%d' % (f['width'], f['height']), } format_id = '%s-%s' % (ext, quality) - viewclip = self._download_json( - '%s/video/clips/viewclip' % self._API_BASE, display_id, - 'Downloading %s viewclip JSON' % format_id, fatal=False, - data=json.dumps(clip_post).encode('utf-8'), - headers={'Content-Type': 'application/json;charset=utf-8'}) + + try: + viewclip = self._download_json( + self._GRAPHQL_EP, display_id, + 'Downloading %s viewclip graphql' % format_id, + data=json.dumps({ + 'query': self.GRAPHQL_VIEWCLIP_TMPL % clip_post, + 'variables': {} + }).encode('utf-8'), + headers=self._GRAPHQL_HEADERS)['data']['viewClip'] + except ExtractorError: + # Still works but most likely will go soon + viewclip = self._download_json( + '%s/video/clips/viewclip' % self._API_BASE, display_id, + 'Downloading %s viewclip JSON' % format_id, fatal=False, + data=json.dumps(clip_post).encode('utf-8'), + headers={'Content-Type': 'application/json;charset=utf-8'}) # Pluralsight tracks multiple sequential calls to ViewClip API and start # to return 429 HTTP errors after some time (see From 24d26ab3808619b209e6a22c505a46eaa781c614 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 4 Jul 2018 04:49:03 +0700 Subject: [PATCH 054/558] [lynda] PEP 8 --- youtube_dl/extractor/lynda.py | 1 - 1 file changed, 1 deletion(-) diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py index 1316cddb6..4ba61cd8a 100644 --- a/youtube_dl/extractor/lynda.py +++ b/youtube_dl/extractor/lynda.py @@ -4,7 +4,6 @@ import re from .common import InfoExtractor from ..compat import ( - compat_HTTPError, compat_str, compat_urlparse, ) From d5de0f21b97bb26c8c558e33b40202a6e02f7b05 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 4 Jul 2018 04:57:17 +0700 Subject: [PATCH 055/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/ChangeLog b/ChangeLog index 8eb7469d4..b1045d7d4 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,24 @@ +version <unreleased> + +Core +* [extractor/common] Properly escape % in MPD templates (#16867) +* [extractor/common] Use source URL as Referer for HTML5 entries (16849) +* Prefer ffmpeg over avconv by default (#8622) + +Extractors +* [pluralsight] Switch to graphql (#16889, #16895, #16896, #16899) +* [lynda] Simplify login and improve error capturing (#16891) ++ [go90] Add support for embed URLs (#16873) +* [go90] Detect geo restriction error and pass geo verification headers + (#16874) +* [vlive] Fix live streams extraction (#16871) +* [npo] Fix typo (#16872) ++ [mediaset] Add support for new videos and extract all formats (#16568) +* [dctptv] Restore extraction based on REST API (#16850) +* [svt] Improve extraction and add support for pages (#16802) +* [porncom] Fix extraction (#16808) + + version 2018.06.25 Extractors From 689af4960e16c63c1f26933095d2f8c8b76f119f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 4 Jul 2018 04:59:21 +0700 Subject: [PATCH 056/558] release 2018.07.04 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- README.md | 4 ++-- docs/supportedsites.md | 1 + youtube_dl/version.py | 2 +- 5 files changed, 8 insertions(+), 7 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 128e6e681..453983f84 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.06.25*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.06.25** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.07.04*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.07.04** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.06.25 +[debug] youtube-dl version 2018.07.04 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index b1045d7d4..c33bf7777 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.07.04 Core * [extractor/common] Properly escape % in MPD templates (#16867) diff --git a/README.md b/README.md index 499a0c206..09e62899a 100644 --- a/README.md +++ b/README.md @@ -427,9 +427,9 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo default; fix file if we can, warn otherwise) --prefer-avconv Prefer avconv over ffmpeg for running the - postprocessors (default) - --prefer-ffmpeg Prefer ffmpeg over avconv for running the postprocessors + --prefer-ffmpeg Prefer ffmpeg over avconv for running the + postprocessors (default) --ffmpeg-location PATH Location of the ffmpeg/avconv binary; either the path to the binary or its containing directory. diff --git a/docs/supportedsites.md b/docs/supportedsites.md index a78fabb02..19dc984dc 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -813,6 +813,7 @@ - **StretchInternet** - **SunPorno** - **SVT** + - **SVTPage** - **SVTPlay**: SVT Play and Öppet arkiv - **SVTSeries** - **SWRMediathek** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 8fbafd6a1..4cf97291b 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.06.25' +__version__ = '2018.07.04' From 9a6628aaf918afdcdf4c661f474e318207155780 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 5 Jul 2018 00:36:35 +0700 Subject: [PATCH 057/558] [youtube] Improve login error handling (closes #13822) --- youtube_dl/extractor/youtube.py | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 89c8b7f8d..117a57911 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -178,13 +178,13 @@ class YoutubeBaseInfoExtractor(InfoExtractor): warn('Unable to extract result entry') return False - tfa = try_get(res, lambda x: x[0][0], list) - if tfa: - tfa_str = try_get(tfa, lambda x: x[2], compat_str) - if tfa_str == 'TWO_STEP_VERIFICATION': + login_challenge = try_get(res, lambda x: x[0][0], list) + if login_challenge: + challenge_str = try_get(login_challenge, lambda x: x[2], compat_str) + if challenge_str == 'TWO_STEP_VERIFICATION': # SEND_SUCCESS - TFA code has been successfully sent to phone # QUOTA_EXCEEDED - reached the limit of TFA codes - status = try_get(tfa, lambda x: x[5], compat_str) + status = try_get(login_challenge, lambda x: x[5], compat_str) if status == 'QUOTA_EXCEEDED': warn('Exceeded the limit of TFA codes, try later') return False @@ -228,6 +228,17 @@ class YoutubeBaseInfoExtractor(InfoExtractor): check_cookie_url = try_get( tfa_results, lambda x: x[0][-1][2], compat_str) + else: + CHALLENGES = { + 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.", + 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.', + 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.", + } + challenge = CHALLENGES.get( + challenge_str, + '%s returned error %s.' % (self.IE_NAME, challenge_str)) + warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge) + return False else: check_cookie_url = try_get(res, lambda x: x[2], compat_str) From 94fef94d9c8571db255b0f3694617f5cd56825b8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 5 Jul 2018 02:14:06 +0700 Subject: [PATCH 058/558] [dplayit] Fix extraction (closes #16901) --- youtube_dl/extractor/dplay.py | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/dplay.py b/youtube_dl/extractor/dplay.py index fe47f6dce..a95e3213c 100644 --- a/youtube_dl/extractor/dplay.py +++ b/youtube_dl/extractor/dplay.py @@ -21,6 +21,7 @@ from ..utils import ( unified_strdate, unified_timestamp, update_url_query, + urljoin, USER_AGENTS, ) @@ -310,9 +311,11 @@ class DPlayItIE(InfoExtractor): if not info: info_url = self._search_regex( - r'url\s*[:=]\s*["\']((?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)', - webpage, 'info url') + (r'playback_json_url\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', + r'url\s*[:=]\s*["\'](?P<url>(?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)'), + webpage, 'info url', group='url') + info_url = urljoin(url, info_url) video_id = info_url.rpartition('/')[-1] try: @@ -322,6 +325,8 @@ class DPlayItIE(InfoExtractor): 'dplayit_token').value, 'Referer': url, }) + if isinstance(info, compat_str): + info = self._parse_json(info, display_id) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 403): info = self._parse_json(e.cause.read().decode('utf-8'), display_id) From e15141adaee67d1e9b9e97c17b73fe4c052c3449 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 5 Jul 2018 02:14:50 +0700 Subject: [PATCH 059/558] [dplayit] Sort formats --- youtube_dl/extractor/dplay.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/dplay.py b/youtube_dl/extractor/dplay.py index a95e3213c..ebf59512c 100644 --- a/youtube_dl/extractor/dplay.py +++ b/youtube_dl/extractor/dplay.py @@ -342,6 +342,7 @@ class DPlayItIE(InfoExtractor): formats = self._extract_m3u8_formats( hls_url, display_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls') + self._sort_formats(formats) series = self._html_search_regex( r'(?s)<h1[^>]+class=["\'].*?\bshow_title\b.*?["\'][^>]*>(.+?)</h1>', From 1ed0b2f74d8337b9625716f9069233a341edd22e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 5 Jul 2018 02:22:15 +0700 Subject: [PATCH 060/558] [watchbox] Fix extraction (closes #16904) --- youtube_dl/extractor/watchbox.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/watchbox.py b/youtube_dl/extractor/watchbox.py index be0bcba15..d99313080 100644 --- a/youtube_dl/extractor/watchbox.py +++ b/youtube_dl/extractor/watchbox.py @@ -67,11 +67,12 @@ class WatchBoxIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - source = self._parse_json( + source = (self._parse_json( self._search_regex( - r'(?s)source["\']?\s*:\s*({.+?})\s*[,}]', webpage, 'source', + r'playerConf\s*=\s*({.+?})\s*;', webpage, 'player config', default='{}'), - video_id, transform_source=js_to_json, fatal=False) or {} + video_id, transform_source=js_to_json, + fatal=False) or {}).get('source') or {} video_id = compat_str(source.get('videoId') or video_id) From 4e71dfd819ccef91a056edc5bf6ca8cec9f2ad4f Mon Sep 17 00:00:00 2001 From: Aaron Brager <getaaron@gmail.com> Date: Thu, 5 Jul 2018 10:17:18 -0500 Subject: [PATCH 061/558] [README.md] Rename OS X to macOS --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 09e62899a..6d49d6a4f 100644 --- a/README.md +++ b/README.md @@ -17,7 +17,7 @@ youtube-dl - download videos from youtube.com or other video platforms # INSTALLATION -To install it right away for all UNIX users (Linux, OS X, etc.), type: +To install it right away for all UNIX users (Linux, macOS, etc.), type: sudo curl -L https://yt-dl.org/downloads/latest/youtube-dl -o /usr/local/bin/youtube-dl sudo chmod a+rx /usr/local/bin/youtube-dl @@ -35,7 +35,7 @@ You can also use pip: This command will update youtube-dl if you have already installed it. See the [pypi page](https://pypi.python.org/pypi/youtube_dl) for more information. -OS X users can install youtube-dl with [Homebrew](https://brew.sh/): +macOS users can install youtube-dl with [Homebrew](https://brew.sh/): brew install youtube-dl @@ -442,7 +442,7 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo # CONFIGURATION -You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux and OS X, the system wide configuration file is located at `/etc/youtube-dl.conf` and the user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. Note that by default configuration file may not exist so you may need to create it yourself. +You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux and macOS, the system wide configuration file is located at `/etc/youtube-dl.conf` and the user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. Note that by default configuration file may not exist so you may need to create it yourself. For example, with the following configuration file youtube-dl will always extract the audio, not copy the mtime, use a proxy and save all videos under `Movies` directory in your home directory: ``` From 47421507883850dc679dc23eb44a615f18282bed Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 6 Jul 2018 23:49:36 +0700 Subject: [PATCH 062/558] [funk] Fix extraction (closes #16918) --- youtube_dl/extractor/funk.py | 64 ++++++++++++++++++++++++++---------- 1 file changed, 46 insertions(+), 18 deletions(-) diff --git a/youtube_dl/extractor/funk.py b/youtube_dl/extractor/funk.py index 0ff058619..76c20ffac 100644 --- a/youtube_dl/extractor/funk.py +++ b/youtube_dl/extractor/funk.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from .nexx import NexxIE +from ..compat import compat_str from ..utils import ( int_or_none, try_get, @@ -12,6 +13,19 @@ from ..utils import ( class FunkBaseIE(InfoExtractor): + _HEADERS = { + 'Accept': '*/*', + 'Accept-Language': 'en-US,en;q=0.9,ru;q=0.8', + 'authorization': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnROYW1lIjoid2ViYXBwLXYzMSIsInNjb3BlIjoic3RhdGljLWNvbnRlbnQtYXBpLGN1cmF0aW9uLWFwaSxuZXh4LWNvbnRlbnQtYXBpLXYzMSx3ZWJhcHAtYXBpIn0.mbuG9wS9Yf5q6PqgR4fiaRFIagiHk9JhwoKES7ksVX4', + } + _AUTH = 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnROYW1lIjoid2ViYXBwLXYzMSIsInNjb3BlIjoic3RhdGljLWNvbnRlbnQtYXBpLGN1cmF0aW9uLWFwaSxuZXh4LWNvbnRlbnQtYXBpLXYzMSx3ZWJhcHAtYXBpIn0.mbuG9wS9Yf5q6PqgR4fiaRFIagiHk9JhwoKES7ksVX4' + + @staticmethod + def _make_headers(referer): + headers = FunkBaseIE._HEADERS.copy() + headers['Referer'] = referer + return headers + def _make_url_result(self, video): return { '_type': 'url_transparent', @@ -48,19 +62,19 @@ class FunkMixIE(FunkBaseIE): lists = self._download_json( 'https://www.funk.net/api/v3.1/curation/curatedLists/', - mix_id, headers={ - 'authorization': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnROYW1lIjoiY3VyYXRpb24tdG9vbC12Mi4wIiwic2NvcGUiOiJzdGF0aWMtY29udGVudC1hcGksY3VyYXRpb24tc2VydmljZSxzZWFyY2gtYXBpIn0.SGCC1IXHLtZYoo8PvRKlU2gXH1su8YSu47sB3S4iXBI', - 'Referer': url, - }, query={ + mix_id, headers=self._make_headers(url), query={ 'size': 100, - })['result']['lists'] + })['_embedded']['curatedListList'] metas = next( l for l in lists if mix_id in (l.get('entityId'), l.get('alias')))['videoMetas'] video = next( meta['videoDataDelegate'] - for meta in metas if meta.get('alias') == alias) + for meta in metas + if try_get( + meta, lambda x: x['videoDataDelegate']['alias'], + compat_str) == alias) return self._make_url_result(video) @@ -104,25 +118,39 @@ class FunkChannelIE(FunkBaseIE): channel_id = mobj.group('id') alias = mobj.group('alias') - headers = { - 'authorization': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnROYW1lIjoiY3VyYXRpb24tdG9vbCIsInNjb3BlIjoic3RhdGljLWNvbnRlbnQtYXBpLGN1cmF0aW9uLWFwaSxzZWFyY2gtYXBpIn0.q4Y2xZG8PFHai24-4Pjx2gym9RmJejtmK6lMXP5wAgc', - 'Referer': url, - } + headers = self._make_headers(url) video = None - by_id_list = self._download_json( - 'https://www.funk.net/api/v3.0/content/videos/byIdList', channel_id, - headers=headers, query={ - 'ids': alias, + # Id-based channels are currently broken on their side: webplayer + # tries to process them via byChannelAlias endpoint and fails + # predictably. + by_channel_alias = self._download_json( + 'https://www.funk.net/api/v3.1/webapp/videos/byChannelAlias/%s' + % channel_id, + 'Downloading byChannelAlias JSON', headers=headers, query={ + 'size': 100, }, fatal=False) - if by_id_list: - video = try_get(by_id_list, lambda x: x['result'][0], dict) + if by_channel_alias: + video_list = try_get( + by_channel_alias, lambda x: x['_embedded']['videoList'], list) + if video_list: + video = next(r for r in video_list if r.get('alias') == alias) + + if not video: + by_id_list = self._download_json( + 'https://www.funk.net/api/v3.0/content/videos/byIdList', + channel_id, 'Downloading byIdList JSON', headers=headers, + query={ + 'ids': alias, + }, fatal=False) + if by_id_list: + video = try_get(by_id_list, lambda x: x['result'][0], dict) if not video: results = self._download_json( - 'https://www.funk.net/api/v3.0/content/videos/filter', channel_id, - headers=headers, query={ + 'https://www.funk.net/api/v3.0/content/videos/filter', + channel_id, 'Downloading filter JSON', headers=headers, query={ 'channelId': channel_id, 'size': 100, })['result'] From 6868d272e5c4a85ba4143bacbb7269dac099c55d Mon Sep 17 00:00:00 2001 From: Luca Cherubin <luca.cherubin@gmail.com> Date: Thu, 26 Apr 2018 20:33:09 +0100 Subject: [PATCH 063/558] [frontendmasters] Add extractor --- youtube_dl/extractor/extractors.py | 4 + youtube_dl/extractor/frontendmaster.py | 271 +++++++++++++++++++++++++ 2 files changed, 275 insertions(+) create mode 100644 youtube_dl/extractor/frontendmaster.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index f2377521b..265b4aa9d 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -390,6 +390,10 @@ from .francetv import ( from .freesound import FreesoundIE from .freespeech import FreespeechIE from .freshlive import FreshLiveIE +from .frontendmaster import ( + FrontEndMasterIE, + FrontEndMasterCourseIE +) from .funimation import FunimationIE from .funk import ( FunkMixIE, diff --git a/youtube_dl/extractor/frontendmaster.py b/youtube_dl/extractor/frontendmaster.py new file mode 100644 index 000000000..21e382da9 --- /dev/null +++ b/youtube_dl/extractor/frontendmaster.py @@ -0,0 +1,271 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import collections +import re + +from .common import InfoExtractor +from ..compat import ( + compat_urlparse) +from ..utils import ( + ExtractorError, + urlencode_postdata, + qualities, unescapeHTML) + + +class FrontEndMasterBaseIE(InfoExtractor): + _API_BASE = 'https://api.frontendmasters.com/v1/kabuki/courses' + _VIDEO_BASE = 'http://www.frontendmasters.com/courses' + _CAPTIONS_BASE = 'https://api.frontendmasters.com/v1/kabuki/transcripts' + _COOKIES_BASE = 'https://api.frontendmasters.com' + _LOGIN_URL = 'https://frontendmasters.com/login/' + + _QUALITIES_PREFERENCE = ('low', 'medium', 'high') + _QUALITIES = { + 'low': {'width': 480, 'height': 360}, + 'medium': {'width': 1280, 'height': 720}, + 'high': {'width': 1920, 'height': 1080} + } + + AllowedQuality = collections.namedtuple('AllowedQuality', + ['ext', 'qualities']) + _ALLOWED_QUALITIES = [ + AllowedQuality('webm', ['low', 'medium', 'high']), + AllowedQuality('mp4', ['low', 'medium', 'high']) + ] + + def _real_initialize(self): + self._login() + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + + login_page = self._download_webpage( + self._LOGIN_URL, None, 'Downloading login page') + + login_form = self._hidden_inputs(login_page) + + login_form.update({ + 'username': username, + 'password': password + }) + + post_url = self._search_regex( + r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page, + 'post_url', default=self._LOGIN_URL, group='url') + + if not post_url.startswith('http'): + post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url) + + response = self._download_webpage( + post_url, None, 'Logging in', + data=urlencode_postdata(login_form), + headers={'Content-Type': 'application/x-www-form-urlencoded'} + ) + + error = self._search_regex( + r'<div[^>]+class=["\']Message MessageAlert["\'][^>]*>' + r'([^<]+)' + r'</div>', + response, 'error message', default=None) + + if error: + raise ExtractorError('Unable to login: %s' % unescapeHTML(error), + expected=True) + + def _download_course(self, course_id, url): + response = self._download_json( + '%s/%s' % (self._API_BASE, course_id), course_id, + 'Downloading course JSON', + headers={ + 'Content-Type': 'application/json;charset=utf-8', + 'Referer': url, + }) + return response + + @staticmethod + def _pair_section_video_element(lesson_elements): + sections = {} + current_section = None + current_section_number = 0 + for elem in lesson_elements: + if not isinstance(elem, int): + elem_name = elem + if not isinstance(elem_name, str): + # convert unicode to str + elem_name = elem.encode('utf-8') + (current_section, current_section_number) = \ + (elem_name, current_section_number + 1) + else: + if current_section: + sections[elem] = (current_section, current_section_number) + + return sections + + +class FrontEndMasterIE(FrontEndMasterBaseIE): + IE_NAME = 'frontend-masters' + _VALID_URL = r'https?://(?:www\.)?frontendmasters\.com/courses/' \ + r'(?P<courseid>[a-z\-]+)/' \ + r'(?P<id>[a-z\-]+)' + + _NETRC_MACHINE = 'frontendmasters' + + _TEST = { + 'url': 'https://frontendmasters.com/courses/web-development/tools', + 'md5': '7f161159710d6b7016a4f4af6fcb05e2', + 'info_dict': { + 'id': 'tools', + 'title': 'Tools', + 'display_id': 'tools', + 'description': 'md5:82c1ea6472e88ed5acd1829fe992e4f7', + 'ext': 'mp4' + }, + 'skip': 'Requires FrontendMasters account credentials', + } + + def _get_subtitles(self, video_hash, video_id): + captions = self._download_webpage( + '%s/%s.vtt' % (self._CAPTIONS_BASE, video_hash), video_id, + fatal=False) + if captions: + return { + 'en': [{ + 'ext': 'vtt', + 'data': captions + }] + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + course_id = mobj.group('courseid') + + course_json_content = self._download_course(course_id=course_id, + url=url) + + # Necessary to get mandatory informations like title and video_url + lesson_index = course_json_content.get('lessonSlugs').index(video_id) + lesson_hash = course_json_content.get('lessonHashes')[lesson_index] + lesson_data = course_json_content.get('lessonData')[lesson_hash] + # This is necessary to get the link for the video + lesson_source_base = lesson_data['sourceBase'] + + lesson_title = lesson_data['title'] + + # Some optional fields + lesson_description = lesson_data.get('description') + lesson_index = lesson_data.get('index') + lesson_slug = lesson_data.get('slug') + lesson_thumbnail_url = lesson_data.get('thumbnail') + lesson_section_elements = course_json_content.get('lessonElements') + + try: + course_sections_pairing = self._pair_section_video_element( + lesson_section_elements) + + lesson_section = \ + course_sections_pairing.get(lesson_index)[0] + + lesson_section_number = \ + course_sections_pairing.get(lesson_index)[1] + except Exception: + lesson_section = None + lesson_section_number = None + + video_request_url = '%s/source' + video_request_headers = { + 'origin': 'https://frontendmasters.com', + 'referer': lesson_source_base, + } + + quality_key = qualities(self._QUALITIES_PREFERENCE) + + formats = [] + for ext, qualities_ in self._ALLOWED_QUALITIES: + for quality in qualities_: + f = self._QUALITIES[quality].copy() + video_request_params = { + 'r': f['height'], + 'f': ext + } + video_response = self._download_json( + video_request_url % lesson_source_base, video_id, + query=video_request_params, headers=video_request_headers) + + video_url = video_response.get('url') + clip_f = f.copy() + clip_f.update({ + 'url': video_url, + 'ext': ext, + 'format_id': '%s-%s' % (ext, quality), + 'quality': quality_key(quality), + 'height': f['height'] + }) + formats.append(clip_f) + + self._sort_formats(formats) + + subtitles = self.extract_subtitles(lesson_hash, video_id) + + return { + 'id': video_id, + 'display_id': lesson_slug, + 'title': lesson_title, + 'description': lesson_description, + 'chapter': lesson_section, + 'chapter_number': lesson_section_number, + 'thumbnail': lesson_thumbnail_url, + 'formats': formats, + 'subtitles': subtitles + } + + +class FrontEndMasterCourseIE(FrontEndMasterBaseIE): + IE_NAME = 'frontend-masters:course' + _VALID_URL = r'https?://(?:www\.)?frontendmasters\.com/courses/(?P<courseid>[a-z\-]+)/?$' + + _NETRC_MACHINE = 'frontendmasters' + + _TEST = { + 'url': 'https://frontendmasters.com/courses/javascript-basics/', + 'info_dict': { + 'id': 'javascript-basics', + 'title': 'Introduction to JavaScript Programming', + 'description': 'md5:269412fbb76d86954761599ad8e4cbc9' + }, + 'playlist_count': 19, + 'skip': 'Requires FrontendMasters account credentials' + } + + @classmethod + def suitable(cls, url): + return False if FrontEndMasterIE.suitable(url) else super(FrontEndMasterBaseIE, cls).suitable(url) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + course_id = mobj.group('courseid') + course_json_content = self._download_course(course_id=course_id, + url=url) + + title = course_json_content.get('title') + description = course_json_content.get('description') + course_display_id = course_json_content.get('slug') + + videos_data = course_json_content.get('lessonData').values() + videos_data = sorted(videos_data, key=lambda video: video.get('index')) + + entries = [] + for video in videos_data: + video_slug = video.get('slug') + clip_url = '%s/%s/%s' % ( + self._VIDEO_BASE, course_display_id, video_slug) + entries.append({ + '_type': 'url_transparent', + 'url': clip_url, + 'ie_key': FrontEndMasterIE.ie_key() + }) + + return self.playlist_result(entries, course_id, title, description) From 69fcdb845b9744125161f514cb4166becbae2959 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 8 Jul 2018 00:48:23 +0700 Subject: [PATCH 064/558] [frontendmasters] Fix issues and improve extraction (closes #3661, closes #16328) --- youtube_dl/extractor/extractors.py | 7 +- youtube_dl/extractor/frontendmaster.py | 271 ------------------------ youtube_dl/extractor/frontendmasters.py | 262 +++++++++++++++++++++++ 3 files changed, 266 insertions(+), 274 deletions(-) delete mode 100644 youtube_dl/extractor/frontendmaster.py create mode 100644 youtube_dl/extractor/frontendmasters.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 265b4aa9d..ed532d77f 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -390,9 +390,10 @@ from .francetv import ( from .freesound import FreesoundIE from .freespeech import FreespeechIE from .freshlive import FreshLiveIE -from .frontendmaster import ( - FrontEndMasterIE, - FrontEndMasterCourseIE +from .frontendmasters import ( + FrontendMastersIE, + FrontendMastersLessonIE, + FrontendMastersCourseIE ) from .funimation import FunimationIE from .funk import ( diff --git a/youtube_dl/extractor/frontendmaster.py b/youtube_dl/extractor/frontendmaster.py deleted file mode 100644 index 21e382da9..000000000 --- a/youtube_dl/extractor/frontendmaster.py +++ /dev/null @@ -1,271 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import collections -import re - -from .common import InfoExtractor -from ..compat import ( - compat_urlparse) -from ..utils import ( - ExtractorError, - urlencode_postdata, - qualities, unescapeHTML) - - -class FrontEndMasterBaseIE(InfoExtractor): - _API_BASE = 'https://api.frontendmasters.com/v1/kabuki/courses' - _VIDEO_BASE = 'http://www.frontendmasters.com/courses' - _CAPTIONS_BASE = 'https://api.frontendmasters.com/v1/kabuki/transcripts' - _COOKIES_BASE = 'https://api.frontendmasters.com' - _LOGIN_URL = 'https://frontendmasters.com/login/' - - _QUALITIES_PREFERENCE = ('low', 'medium', 'high') - _QUALITIES = { - 'low': {'width': 480, 'height': 360}, - 'medium': {'width': 1280, 'height': 720}, - 'high': {'width': 1920, 'height': 1080} - } - - AllowedQuality = collections.namedtuple('AllowedQuality', - ['ext', 'qualities']) - _ALLOWED_QUALITIES = [ - AllowedQuality('webm', ['low', 'medium', 'high']), - AllowedQuality('mp4', ['low', 'medium', 'high']) - ] - - def _real_initialize(self): - self._login() - - def _login(self): - (username, password) = self._get_login_info() - if username is None: - return - - login_page = self._download_webpage( - self._LOGIN_URL, None, 'Downloading login page') - - login_form = self._hidden_inputs(login_page) - - login_form.update({ - 'username': username, - 'password': password - }) - - post_url = self._search_regex( - r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page, - 'post_url', default=self._LOGIN_URL, group='url') - - if not post_url.startswith('http'): - post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url) - - response = self._download_webpage( - post_url, None, 'Logging in', - data=urlencode_postdata(login_form), - headers={'Content-Type': 'application/x-www-form-urlencoded'} - ) - - error = self._search_regex( - r'<div[^>]+class=["\']Message MessageAlert["\'][^>]*>' - r'([^<]+)' - r'</div>', - response, 'error message', default=None) - - if error: - raise ExtractorError('Unable to login: %s' % unescapeHTML(error), - expected=True) - - def _download_course(self, course_id, url): - response = self._download_json( - '%s/%s' % (self._API_BASE, course_id), course_id, - 'Downloading course JSON', - headers={ - 'Content-Type': 'application/json;charset=utf-8', - 'Referer': url, - }) - return response - - @staticmethod - def _pair_section_video_element(lesson_elements): - sections = {} - current_section = None - current_section_number = 0 - for elem in lesson_elements: - if not isinstance(elem, int): - elem_name = elem - if not isinstance(elem_name, str): - # convert unicode to str - elem_name = elem.encode('utf-8') - (current_section, current_section_number) = \ - (elem_name, current_section_number + 1) - else: - if current_section: - sections[elem] = (current_section, current_section_number) - - return sections - - -class FrontEndMasterIE(FrontEndMasterBaseIE): - IE_NAME = 'frontend-masters' - _VALID_URL = r'https?://(?:www\.)?frontendmasters\.com/courses/' \ - r'(?P<courseid>[a-z\-]+)/' \ - r'(?P<id>[a-z\-]+)' - - _NETRC_MACHINE = 'frontendmasters' - - _TEST = { - 'url': 'https://frontendmasters.com/courses/web-development/tools', - 'md5': '7f161159710d6b7016a4f4af6fcb05e2', - 'info_dict': { - 'id': 'tools', - 'title': 'Tools', - 'display_id': 'tools', - 'description': 'md5:82c1ea6472e88ed5acd1829fe992e4f7', - 'ext': 'mp4' - }, - 'skip': 'Requires FrontendMasters account credentials', - } - - def _get_subtitles(self, video_hash, video_id): - captions = self._download_webpage( - '%s/%s.vtt' % (self._CAPTIONS_BASE, video_hash), video_id, - fatal=False) - if captions: - return { - 'en': [{ - 'ext': 'vtt', - 'data': captions - }] - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - course_id = mobj.group('courseid') - - course_json_content = self._download_course(course_id=course_id, - url=url) - - # Necessary to get mandatory informations like title and video_url - lesson_index = course_json_content.get('lessonSlugs').index(video_id) - lesson_hash = course_json_content.get('lessonHashes')[lesson_index] - lesson_data = course_json_content.get('lessonData')[lesson_hash] - # This is necessary to get the link for the video - lesson_source_base = lesson_data['sourceBase'] - - lesson_title = lesson_data['title'] - - # Some optional fields - lesson_description = lesson_data.get('description') - lesson_index = lesson_data.get('index') - lesson_slug = lesson_data.get('slug') - lesson_thumbnail_url = lesson_data.get('thumbnail') - lesson_section_elements = course_json_content.get('lessonElements') - - try: - course_sections_pairing = self._pair_section_video_element( - lesson_section_elements) - - lesson_section = \ - course_sections_pairing.get(lesson_index)[0] - - lesson_section_number = \ - course_sections_pairing.get(lesson_index)[1] - except Exception: - lesson_section = None - lesson_section_number = None - - video_request_url = '%s/source' - video_request_headers = { - 'origin': 'https://frontendmasters.com', - 'referer': lesson_source_base, - } - - quality_key = qualities(self._QUALITIES_PREFERENCE) - - formats = [] - for ext, qualities_ in self._ALLOWED_QUALITIES: - for quality in qualities_: - f = self._QUALITIES[quality].copy() - video_request_params = { - 'r': f['height'], - 'f': ext - } - video_response = self._download_json( - video_request_url % lesson_source_base, video_id, - query=video_request_params, headers=video_request_headers) - - video_url = video_response.get('url') - clip_f = f.copy() - clip_f.update({ - 'url': video_url, - 'ext': ext, - 'format_id': '%s-%s' % (ext, quality), - 'quality': quality_key(quality), - 'height': f['height'] - }) - formats.append(clip_f) - - self._sort_formats(formats) - - subtitles = self.extract_subtitles(lesson_hash, video_id) - - return { - 'id': video_id, - 'display_id': lesson_slug, - 'title': lesson_title, - 'description': lesson_description, - 'chapter': lesson_section, - 'chapter_number': lesson_section_number, - 'thumbnail': lesson_thumbnail_url, - 'formats': formats, - 'subtitles': subtitles - } - - -class FrontEndMasterCourseIE(FrontEndMasterBaseIE): - IE_NAME = 'frontend-masters:course' - _VALID_URL = r'https?://(?:www\.)?frontendmasters\.com/courses/(?P<courseid>[a-z\-]+)/?$' - - _NETRC_MACHINE = 'frontendmasters' - - _TEST = { - 'url': 'https://frontendmasters.com/courses/javascript-basics/', - 'info_dict': { - 'id': 'javascript-basics', - 'title': 'Introduction to JavaScript Programming', - 'description': 'md5:269412fbb76d86954761599ad8e4cbc9' - }, - 'playlist_count': 19, - 'skip': 'Requires FrontendMasters account credentials' - } - - @classmethod - def suitable(cls, url): - return False if FrontEndMasterIE.suitable(url) else super(FrontEndMasterBaseIE, cls).suitable(url) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - course_id = mobj.group('courseid') - course_json_content = self._download_course(course_id=course_id, - url=url) - - title = course_json_content.get('title') - description = course_json_content.get('description') - course_display_id = course_json_content.get('slug') - - videos_data = course_json_content.get('lessonData').values() - videos_data = sorted(videos_data, key=lambda video: video.get('index')) - - entries = [] - for video in videos_data: - video_slug = video.get('slug') - clip_url = '%s/%s/%s' % ( - self._VIDEO_BASE, course_display_id, video_slug) - entries.append({ - '_type': 'url_transparent', - 'url': clip_url, - 'ie_key': FrontEndMasterIE.ie_key() - }) - - return self.playlist_result(entries, course_id, title, description) diff --git a/youtube_dl/extractor/frontendmasters.py b/youtube_dl/extractor/frontendmasters.py new file mode 100644 index 000000000..770db46d0 --- /dev/null +++ b/youtube_dl/extractor/frontendmasters.py @@ -0,0 +1,262 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_str, + compat_urlparse, +) +from ..utils import ( + ExtractorError, + parse_duration, + urlencode_postdata, +) + + +class FrontendMastersBaseIE(InfoExtractor): + _API_BASE = 'https://api.frontendmasters.com/v1/kabuki' + _LOGIN_URL = 'https://frontendmasters.com/login/' + + _NETRC_MACHINE = 'frontendmasters' + + _QUALITIES = { + 'low': {'width': 480, 'height': 360}, + 'mid': {'width': 1280, 'height': 720}, + 'high': {'width': 1920, 'height': 1080} + } + + def _real_initialize(self): + self._login() + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + + login_page = self._download_webpage( + self._LOGIN_URL, None, 'Downloading login page') + + login_form = self._hidden_inputs(login_page) + + login_form.update({ + 'username': username, + 'password': password + }) + + post_url = self._search_regex( + r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page, + 'post_url', default=self._LOGIN_URL, group='url') + + if not post_url.startswith('http'): + post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url) + + response = self._download_webpage( + post_url, None, 'Logging in', data=urlencode_postdata(login_form), + headers={'Content-Type': 'application/x-www-form-urlencoded'}) + + # Successful login + if any(p in response for p in ( + 'wp-login.php?action=logout', '>Logout')): + return + + error = self._html_search_regex( + r'class=(["\'])(?:(?!\1).)*\bMessageAlert\b(?:(?!\1).)*\1[^>]*>(?P<error>[^<]+)<', + response, 'error message', default=None, group='error') + if error: + raise ExtractorError('Unable to login: %s' % error, expected=True) + raise ExtractorError('Unable to log in') + + +class FrontendMastersPageBaseIE(FrontendMastersBaseIE): + def _download_course(self, course_name, url): + return self._download_json( + '%s/courses/%s' % (self._API_BASE, course_name), course_name, + 'Downloading course JSON', headers={'Referer': url}) + + @staticmethod + def _extract_chapters(course): + chapters = [] + lesson_elements = course.get('lessonElements') + if isinstance(lesson_elements, list): + chapters = [e for e in lesson_elements if isinstance(e, compat_str)] + return chapters + + @staticmethod + def _extract_lesson(chapters, lesson_id, lesson): + title = lesson.get('title') or lesson_id + display_id = lesson.get('slug') + description = lesson.get('description') + thumbnail = lesson.get('thumbnail') + + chapter_number = None + index = lesson.get('index') + element_index = lesson.get('elementIndex') + if (isinstance(index, int) and isinstance(element_index, int) and + index < element_index): + chapter_number = element_index - index + chapter = (chapters[chapter_number - 1] + if chapter_number - 1 < len(chapters) else None) + + duration = None + timestamp = lesson.get('timestamp') + if isinstance(timestamp, compat_str): + mobj = re.search( + r'(?P<start>\d{1,2}:\d{1,2}:\d{1,2})\s*-(?P<end>\s*\d{1,2}:\d{1,2}:\d{1,2})', + timestamp) + if mobj: + duration = parse_duration(mobj.group('end')) - parse_duration( + mobj.group('start')) + + return { + '_type': 'url_transparent', + 'url': 'frontendmasters:%s' % lesson_id, + 'ie_key': FrontendMastersIE.ie_key(), + 'id': lesson_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'chapter': chapter, + 'chapter_number': chapter_number, + } + + +class FrontendMastersIE(FrontendMastersBaseIE): + _VALID_URL = r'(?:frontendmasters:|https?://api\.frontendmasters\.com/v\d+/kabuki/video/)(?P<id>[^/]+)' + _TESTS = [{ + 'url': 'https://api.frontendmasters.com/v1/kabuki/video/a2qogef6ba', + 'md5': '7f161159710d6b7016a4f4af6fcb05e2', + 'info_dict': { + 'id': 'a2qogef6ba', + 'ext': 'mp4', + 'title': 'a2qogef6ba', + }, + 'skip': 'Requires FrontendMasters account credentials', + }, { + 'url': 'frontendmasters:a2qogef6ba', + 'only_matching': True, + }] + + def _real_extract(self, url): + lesson_id = self._match_id(url) + + source_url = '%s/video/%s/source' % (self._API_BASE, lesson_id) + + formats = [] + for ext in ('webm', 'mp4'): + for quality in ('low', 'mid', 'high'): + resolution = self._QUALITIES[quality].copy() + format_id = '%s-%s' % (ext, quality) + format_url = self._download_json( + source_url, lesson_id, + 'Downloading %s source JSON' % format_id, query={ + 'f': ext, + 'r': resolution['height'], + }, headers={ + 'Referer': url, + }, fatal=False)['url'] + + if not format_url: + continue + + f = resolution.copy() + f.update({ + 'url': format_url, + 'ext': ext, + 'format_id': format_id, + }) + formats.append(f) + self._sort_formats(formats) + + subtitles = { + 'en': [{ + 'url': '%s/transcripts/%s.vtt' % (self._API_BASE, lesson_id), + }] + } + + return { + 'id': lesson_id, + 'title': lesson_id, + 'formats': formats, + 'subtitles': subtitles + } + + +class FrontendMastersLessonIE(FrontendMastersPageBaseIE): + _VALID_URL = r'https?://(?:www\.)?frontendmasters\.com/courses/(?P<course_name>[^/]+)/(?P<lesson_name>[^/]+)' + _TEST = { + 'url': 'https://frontendmasters.com/courses/web-development/tools', + 'info_dict': { + 'id': 'a2qogef6ba', + 'display_id': 'tools', + 'ext': 'mp4', + 'title': 'Tools', + 'description': 'md5:82c1ea6472e88ed5acd1829fe992e4f7', + 'thumbnail': r're:^https?://.*\.jpg$', + 'chapter': 'Introduction', + 'chapter_number': 1, + }, + 'params': { + 'skip_download': True, + }, + 'skip': 'Requires FrontendMasters account credentials', + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + course_name, lesson_name = mobj.group('course_name', 'lesson_name') + + course = self._download_course(course_name, url) + + lesson_id, lesson = next( + (video_id, data) + for video_id, data in course['lessonData'].items() + if data.get('slug') == lesson_name) + + chapters = self._extract_chapters(course) + return self._extract_lesson(chapters, lesson_id, lesson) + + +class FrontendMastersCourseIE(FrontendMastersPageBaseIE): + _VALID_URL = r'https?://(?:www\.)?frontendmasters\.com/courses/(?P<id>[^/]+)' + _TEST = { + 'url': 'https://frontendmasters.com/courses/web-development/', + 'info_dict': { + 'id': 'web-development', + 'title': 'Introduction to Web Development', + 'description': 'md5:9317e6e842098bf725d62360e52d49a6', + }, + 'playlist_count': 81, + 'skip': 'Requires FrontendMasters account credentials', + } + + @classmethod + def suitable(cls, url): + return False if FrontendMastersLessonIE.suitable(url) else super( + FrontendMastersBaseIE, cls).suitable(url) + + def _real_extract(self, url): + course_name = self._match_id(url) + + course = self._download_course(course_name, url) + + chapters = self._extract_chapters(course) + + lessons = sorted( + course['lessonData'].values(), key=lambda data: data['index']) + + entries = [] + for lesson in lessons: + lesson_name = lesson.get('slug') + if not lesson_name: + continue + lesson_id = lesson.get('hash') or lesson.get('statsId') + entries.append(self._extract_lesson(chapters, lesson_id, lesson)) + + title = course.get('title') + description = course.get('description') + + return self.playlist_result(entries, course_name, title, description) From e06632e3fe25036b804a62469bb18fa4c37e3368 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 8 Jul 2018 08:22:56 +0700 Subject: [PATCH 065/558] [downloader/dash] Improve error handling (#16927) --- youtube_dl/downloader/dash.py | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/youtube_dl/downloader/dash.py b/youtube_dl/downloader/dash.py index 576ece6db..eaa7adf7c 100644 --- a/youtube_dl/downloader/dash.py +++ b/youtube_dl/downloader/dash.py @@ -2,7 +2,10 @@ from __future__ import unicode_literals from .fragment import FragmentFD from ..compat import compat_urllib_error -from ..utils import urljoin +from ..utils import ( + DownloadError, + urljoin, +) class DashSegmentsFD(FragmentFD): @@ -57,6 +60,14 @@ class DashSegmentsFD(FragmentFD): count += 1 if count <= fragment_retries: self.report_retry_fragment(err, frag_index, count, fragment_retries) + except DownloadError: + # Don't retry fragment if error occurred during HTTP downloading + # itself since it has own retry settings + if not fatal: + self.report_skip_fragment(frag_index) + break + raise + if count > fragment_retries: if not fatal: self.report_skip_fragment(frag_index) From 0685d9727b9657fc8a31c96cb52c4155de29fcfc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 9 Jul 2018 23:43:05 +0700 Subject: [PATCH 066/558] [utils] Share JSON-LD regex --- youtube_dl/extractor/common.py | 4 ++-- youtube_dl/utils.py | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 78f053f18..5d4db54d5 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -52,6 +52,7 @@ from ..utils import ( GeoUtils, int_or_none, js_to_json, + JSON_LD_RE, mimetype2ext, orderedSet, parse_codecs, @@ -1149,8 +1150,7 @@ class InfoExtractor(object): def _search_json_ld(self, html, video_id, expected_type=None, **kwargs): json_ld = self._search_regex( - r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>', - html, 'JSON-LD', group='json_ld', **kwargs) + JSON_LD_RE, html, 'JSON-LD', group='json_ld', **kwargs) default = kwargs.get('default', NO_DEFAULT) if not json_ld: return default if default is not NO_DEFAULT else {} diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 6a3199fb9..8c45166d7 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -184,6 +184,7 @@ DATE_FORMATS_MONTH_FIRST.extend([ ]) PACKED_CODES_RE = r"}\('(.+)',(\d+),(\d+),'([^']+)'\.split\('\|'\)" +JSON_LD_RE = r'(?is)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>' def preferredencoding(): From 79fd7320e24596b39d81c2a364fb5b41c2f57b41 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 9 Jul 2018 23:44:05 +0700 Subject: [PATCH 067/558] [nrktv] Add support for new episode URL schema (closes #16909) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/nrk.py | 38 +++++++++++++++++++++++++++++- 2 files changed, 38 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index ed532d77f..a20712d34 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -768,6 +768,7 @@ from .nrk import ( NRKSkoleIE, NRKTVIE, NRKTVDirekteIE, + NRKTVEpisodeIE, NRKTVEpisodesIE, NRKTVSeriesIE, ) diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index 7157e2390..50dd07d11 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -8,6 +8,7 @@ from ..compat import compat_urllib_parse_unquote from ..utils import ( ExtractorError, int_or_none, + JSON_LD_RE, parse_age_limit, parse_duration, ) @@ -359,6 +360,40 @@ class NRKTVIE(NRKBaseIE): }] +class NRKTVEpisodeIE(InfoExtractor): + _VALID_URL = r'https?://tv\.nrk\.no/serie/(?P<id>[^/]+/sesong/\d+/episode/\d+)' + _TEST = { + 'url': 'https://tv.nrk.no/serie/backstage/sesong/1/episode/8', + 'info_dict': { + 'id': 'MSUI14000816AA', + 'ext': 'mp4', + 'title': 'Backstage 8:30', + 'description': 'md5:de6ca5d5a2d56849e4021f2bf2850df4', + 'duration': 1320, + 'series': 'Backstage', + 'season_number': 1, + 'episode_number': 8, + 'episode': '8:30', + }, + 'params': { + 'skip_download': True, + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + nrk_id = self._parse_json( + self._search_regex(JSON_LD_RE, webpage, 'JSON-LD', group='json_ld'), + display_id)['@id'] + + assert re.match(NRKTVIE._EPISODE_RE, nrk_id) + return self.url_result( + 'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id) + + class NRKTVDirekteIE(NRKTVIE): IE_DESC = 'NRK TV Direkte and NRK Radio Direkte' _VALID_URL = r'https?://(?:tv|radio)\.nrk\.no/direkte/(?P<id>[^/?#&]+)' @@ -470,7 +505,8 @@ class NRKTVSeriesIE(InfoExtractor): @classmethod def suitable(cls, url): - return False if NRKTVIE.suitable(url) else super(NRKTVSeriesIE, cls).suitable(url) + return (False if NRKTVIE.suitable(url) or NRKTVEpisodeIE.suitable(url) + else super(NRKTVSeriesIE, cls).suitable(url)) def _real_extract(self, url): series_id = self._match_id(url) From 4b3ee09886d1f2a096004013e6a8a13a1f564ba8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 10 Jul 2018 00:21:14 +0700 Subject: [PATCH 068/558] [nrktv] Add support for new season and serie URL schema --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/nrk.py | 208 ++++++++++++++++++++--------- 2 files changed, 149 insertions(+), 60 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index a20712d34..c6f8a785a 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -770,6 +770,7 @@ from .nrk import ( NRKTVDirekteIE, NRKTVEpisodeIE, NRKTVEpisodesIE, + NRKTVSeasonIE, NRKTVSeriesIE, ) from .ntvde import NTVDeIE diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index 50dd07d11..a231735fb 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -4,13 +4,18 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_urllib_parse_unquote +from ..compat import ( + compat_str, + compat_urllib_parse_unquote, +) from ..utils import ( ExtractorError, int_or_none, JSON_LD_RE, + NO_DEFAULT, parse_age_limit, parse_duration, + try_get, ) @@ -394,6 +399,148 @@ class NRKTVEpisodeIE(InfoExtractor): 'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id) +class NRKTVSerieBaseIE(InfoExtractor): + def _extract_series(self, webpage, display_id, fatal=True): + config = self._parse_json( + self._search_regex( + r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>', webpage, 'config', + default='{}' if not fatal else NO_DEFAULT), + display_id, fatal=False) + if not config: + return + return try_get(config, lambda x: x['series'], dict) + + def _extract_episodes(self, season): + entries = [] + if not isinstance(season, dict): + return entries + episodes = season.get('episodes') + if not isinstance(episodes, list): + return entries + for episode in episodes: + nrk_id = episode.get('prfId') + if not nrk_id or not isinstance(nrk_id, compat_str): + continue + entries.append(self.url_result( + 'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id)) + return entries + + +class NRKTVSeasonIE(NRKTVSerieBaseIE): + _VALID_URL = r'https?://tv\.nrk\.no/serie/[^/]+/sesong/(?P<id>\d+)' + _TEST = { + 'url': 'https://tv.nrk.no/serie/backstage/sesong/1', + 'info_dict': { + 'id': '1', + 'title': 'Sesong 1', + }, + 'playlist_mincount': 30, + } + + @classmethod + def suitable(cls, url): + return (False if NRKTVIE.suitable(url) or NRKTVEpisodeIE.suitable(url) + else super(NRKTVSeasonIE, cls).suitable(url)) + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + series = self._extract_series(webpage, display_id) + + season = next( + s for s in series['seasons'] + if int(display_id) == s.get('seasonNumber')) + + title = try_get(season, lambda x: x['titles']['title'], compat_str) + return self.playlist_result( + self._extract_episodes(season), display_id, title) + + +class NRKTVSeriesIE(NRKTVSerieBaseIE): + _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)' + _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)' + _TESTS = [{ + # new layout + 'url': 'https://tv.nrk.no/serie/backstage', + 'info_dict': { + 'id': 'backstage', + 'title': 'Backstage', + 'description': 'md5:c3ec3a35736fca0f9e1207b5511143d3', + }, + 'playlist_mincount': 60, + }, { + # old layout + 'url': 'https://tv.nrk.no/serie/groenn-glede', + 'info_dict': { + 'id': 'groenn-glede', + 'title': 'Grønn glede', + 'description': 'md5:7576e92ae7f65da6993cf90ee29e4608', + }, + 'playlist_mincount': 9, + }, { + 'url': 'http://tv.nrksuper.no/serie/labyrint', + 'info_dict': { + 'id': 'labyrint', + 'title': 'Labyrint', + 'description': 'md5:58afd450974c89e27d5a19212eee7115', + }, + 'playlist_mincount': 3, + }, { + 'url': 'https://tv.nrk.no/serie/broedrene-dal-og-spektralsteinene', + 'only_matching': True, + }, { + 'url': 'https://tv.nrk.no/serie/saving-the-human-race', + 'only_matching': True, + }, { + 'url': 'https://tv.nrk.no/serie/postmann-pat', + 'only_matching': True, + }] + + @classmethod + def suitable(cls, url): + return ( + False if any(ie.suitable(url) + for ie in (NRKTVIE, NRKTVEpisodeIE, NRKTVSeasonIE)) + else super(NRKTVSeriesIE, cls).suitable(url)) + + def _real_extract(self, url): + series_id = self._match_id(url) + + webpage = self._download_webpage(url, series_id) + + # New layout (e.g. https://tv.nrk.no/serie/backstage) + series = self._extract_series(webpage, series_id, fatal=False) + if series: + title = try_get(series, lambda x: x['titles']['title'], compat_str) + description = try_get( + series, lambda x: x['titles']['subtitle'], compat_str) + entries = [] + for season in series['seasons']: + entries.extend(self._extract_episodes(season)) + return self.playlist_result(entries, series_id, title, description) + + # Old layout (e.g. https://tv.nrk.no/serie/groenn-glede) + entries = [ + self.url_result( + 'https://tv.nrk.no/program/Episodes/{series}/{season}'.format( + series=series_id, season=season_id)) + for season_id in re.findall(self._ITEM_RE, webpage) + ] + + title = self._html_search_meta( + 'seriestitle', webpage, + 'title', default=None) or self._og_search_title( + webpage, fatal=False) + + description = self._html_search_meta( + 'series_description', webpage, + 'description', default=None) or self._og_search_description(webpage) + + return self.playlist_result(entries, series_id, title, description) + + class NRKTVDirekteIE(NRKTVIE): IE_DESC = 'NRK TV Direkte and NRK Radio Direkte' _VALID_URL = r'https?://(?:tv|radio)\.nrk\.no/direkte/(?P<id>[^/?#&]+)' @@ -473,65 +620,6 @@ class NRKTVEpisodesIE(NRKPlaylistBaseIE): r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False) -class NRKTVSeriesIE(InfoExtractor): - _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)' - _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)' - _TESTS = [{ - 'url': 'https://tv.nrk.no/serie/groenn-glede', - 'info_dict': { - 'id': 'groenn-glede', - 'title': 'Grønn glede', - 'description': 'md5:7576e92ae7f65da6993cf90ee29e4608', - }, - 'playlist_mincount': 9, - }, { - 'url': 'http://tv.nrksuper.no/serie/labyrint', - 'info_dict': { - 'id': 'labyrint', - 'title': 'Labyrint', - 'description': 'md5:58afd450974c89e27d5a19212eee7115', - }, - 'playlist_mincount': 3, - }, { - 'url': 'https://tv.nrk.no/serie/broedrene-dal-og-spektralsteinene', - 'only_matching': True, - }, { - 'url': 'https://tv.nrk.no/serie/saving-the-human-race', - 'only_matching': True, - }, { - 'url': 'https://tv.nrk.no/serie/postmann-pat', - 'only_matching': True, - }] - - @classmethod - def suitable(cls, url): - return (False if NRKTVIE.suitable(url) or NRKTVEpisodeIE.suitable(url) - else super(NRKTVSeriesIE, cls).suitable(url)) - - def _real_extract(self, url): - series_id = self._match_id(url) - - webpage = self._download_webpage(url, series_id) - - entries = [ - self.url_result( - 'https://tv.nrk.no/program/Episodes/{series}/{season}'.format( - series=series_id, season=season_id)) - for season_id in re.findall(self._ITEM_RE, webpage) - ] - - title = self._html_search_meta( - 'seriestitle', webpage, - 'title', default=None) or self._og_search_title( - webpage, fatal=False) - - description = self._html_search_meta( - 'series_description', webpage, - 'description', default=None) or self._og_search_description(webpage) - - return self.playlist_result(entries, series_id, title, description) - - class NRKSkoleIE(InfoExtractor): IE_DESC = 'NRK Skole' _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)' From 7e8e948cf7eb17de57e95f20d1b3cb963f46f121 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 10 Jul 2018 02:08:15 +0700 Subject: [PATCH 069/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/ChangeLog b/ChangeLog index c33bf7777..978a316bc 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,20 @@ +version <unreleased> + +Core +* [utils] Share JSON-LD regular expression +* [downloader/dash] Improve error handling (#16927) + +Extractors ++ [nrktv] Add support for new season and serie URL schema ++ [nrktv] Add support for new episode URL schema (#16909) ++ [frontendmasters] Add support for frontendmasters.com (#3661, #16328) +* [funk] Fix extraction (#16918) +* [watchbox] Fix extraction (#16904) +* [dplayit] Sort formats +* [dplayit] Fix extraction (#16901) +* [youtube] Improve login error handling (#13822) + + version 2018.07.04 Core From 40a051fa9f48000f311f243c40e3cae588420738 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 10 Jul 2018 02:09:51 +0700 Subject: [PATCH 070/558] release 2018.07.10 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 5 +++++ youtube_dl/version.py | 2 +- 4 files changed, 10 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 453983f84..f192c6633 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.07.04*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.07.04** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.07.10*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.07.10** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.07.04 +[debug] youtube-dl version 2018.07.10 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 978a316bc..1d602079e 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.07.10 Core * [utils] Share JSON-LD regular expression diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 19dc984dc..6cbe81802 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -302,6 +302,9 @@ - **Freesound** - **freespeech.org** - **FreshLive** + - **FrontendMasters** + - **FrontendMastersCourse** + - **FrontendMastersLesson** - **Funimation** - **FunkChannel** - **FunkMix** @@ -589,7 +592,9 @@ - **NRKSkole**: NRK Skole - **NRKTV**: NRK TV and NRK Radio - **NRKTVDirekte**: NRK TV Direkte and NRK Radio Direkte + - **NRKTVEpisode** - **NRKTVEpisodes** + - **NRKTVSeason** - **NRKTVSeries** - **ntv.ru** - **Nuvid** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 4cf97291b..c7083cf47 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.07.04' +__version__ = '2018.07.10' From 79367a98208fbf01d6e04b6747a6e01d0b1f8b9a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 14 Jul 2018 18:05:06 +0700 Subject: [PATCH 071/558] [pornhub] Improve extraction and extract all formats (closes #12166, closes #15891, closes #16262, closes #16959) --- youtube_dl/extractor/pornhub.py | 125 ++++++++++++++++++++------------ 1 file changed, 79 insertions(+), 46 deletions(-) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 23e24d216..97f988da4 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -4,28 +4,21 @@ from __future__ import unicode_literals import functools import itertools import operator -# import os import re from .common import InfoExtractor from ..compat import ( compat_HTTPError, - # compat_urllib_parse_unquote, - # compat_urllib_parse_unquote_plus, - # compat_urllib_parse_urlparse, + compat_str, ) from ..utils import ( ExtractorError, int_or_none, js_to_json, orderedSet, - # sanitized_Request, remove_quotes, str_to_int, ) -# from ..aes import ( -# aes_decrypt_text -# ) class PornHubIE(InfoExtractor): @@ -62,7 +55,7 @@ class PornHubIE(InfoExtractor): 'id': '1331683002', 'ext': 'mp4', 'title': '重庆婷婷女王足交', - 'uploader': 'cj397186295', + 'uploader': 'Unknown', 'duration': 1753, 'view_count': int, 'like_count': int, @@ -121,7 +114,7 @@ class PornHubIE(InfoExtractor): self._set_cookie('pornhub.com', 'platform', platform) return self._download_webpage( 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id, - video_id) + video_id, 'Downloading %s webpage' % platform) webpage = dl_webpage('pc') @@ -134,48 +127,19 @@ class PornHubIE(InfoExtractor): 'PornHub said: %s' % error_msg, expected=True, video_id=video_id) - tv_webpage = dl_webpage('tv') - - assignments = self._search_regex( - r'(var.+?mediastring.+?)</script>', tv_webpage, - 'encoded url').split(';') - - js_vars = {} - - def parse_js_value(inp): - inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp) - if '+' in inp: - inps = inp.split('+') - return functools.reduce( - operator.concat, map(parse_js_value, inps)) - inp = inp.strip() - if inp in js_vars: - return js_vars[inp] - return remove_quotes(inp) - - for assn in assignments: - assn = assn.strip() - if not assn: - continue - assn = re.sub(r'var\s+', '', assn) - vname, value = assn.split('=', 1) - js_vars[vname] = parse_js_value(value) - - video_url = js_vars['mediastring'] - - title = self._search_regex( - r'<h1>([^>]+)</h1>', tv_webpage, 'title', default=None) - # video_title from flashvars contains whitespace instead of non-ASCII (see # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying # on that anymore. - title = title or self._html_search_meta( + title = self._html_search_meta( 'twitter:title', webpage, default=None) or self._search_regex( (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)', r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1', r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'), webpage, 'title', group='title') + video_urls = [] + video_urls_set = set() + flashvars = self._parse_json( self._search_regex( r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'), @@ -183,8 +147,78 @@ class PornHubIE(InfoExtractor): if flashvars: thumbnail = flashvars.get('image_url') duration = int_or_none(flashvars.get('video_duration')) + media_definitions = flashvars.get('mediaDefinitions') + if isinstance(media_definitions, list): + for definition in media_definitions: + if not isinstance(definition, dict): + continue + video_url = definition.get('videoUrl') + if not video_url or not isinstance(video_url, compat_str): + continue + if video_url in video_urls_set: + continue + video_urls_set.add(video_url) + video_urls.append( + (video_url, int_or_none(definition.get('quality')))) else: - title, thumbnail, duration = [None] * 3 + thumbnail, duration = [None] * 2 + + if not video_urls: + tv_webpage = dl_webpage('tv') + + assignments = self._search_regex( + r'(var.+?mediastring.+?)</script>', tv_webpage, + 'encoded url').split(';') + + js_vars = {} + + def parse_js_value(inp): + inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp) + if '+' in inp: + inps = inp.split('+') + return functools.reduce( + operator.concat, map(parse_js_value, inps)) + inp = inp.strip() + if inp in js_vars: + return js_vars[inp] + return remove_quotes(inp) + + for assn in assignments: + assn = assn.strip() + if not assn: + continue + assn = re.sub(r'var\s+', '', assn) + vname, value = assn.split('=', 1) + js_vars[vname] = parse_js_value(value) + + video_url = js_vars['mediastring'] + if video_url not in video_urls_set: + video_urls.append((video_url, None)) + video_urls_set.add(video_url) + + for mobj in re.finditer( + r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1', + webpage): + video_url = mobj.group('url') + if video_url not in video_urls_set: + video_urls.append((video_url, None)) + video_urls_set.add(video_url) + + formats = [] + for video_url, height in video_urls: + tbr = None + mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url) + if mobj: + if not height: + height = int(mobj.group('height')) + tbr = int(mobj.group('tbr')) + formats.append({ + 'url': video_url, + 'format_id': '%dp' % height if height else None, + 'height': height, + 'tbr': tbr, + }) + self._sort_formats(formats) video_uploader = self._html_search_regex( r'(?s)From: .+?<(?:a\b[^>]+\bhref=["\']/(?:user|channel)s/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<', @@ -210,7 +244,6 @@ class PornHubIE(InfoExtractor): return { 'id': video_id, - 'url': video_url, 'uploader': video_uploader, 'title': title, 'thumbnail': thumbnail, @@ -219,7 +252,7 @@ class PornHubIE(InfoExtractor): 'like_count': like_count, 'dislike_count': dislike_count, 'comment_count': comment_count, - # 'formats': formats, + 'formats': formats, 'age_limit': 18, 'tags': tags, 'categories': categories, From 905eef2b06f1e890b1dfd228aa4fa1fa2308d687 Mon Sep 17 00:00:00 2001 From: Jakub Wilk <jwilk@jwilk.net> Date: Wed, 18 Jul 2018 18:47:26 +0200 Subject: [PATCH 072/558] [imgur] Allow digits in filename extension --- youtube_dl/extractor/imgur.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/imgur.py b/youtube_dl/extractor/imgur.py index 2901960a5..ecc958a17 100644 --- a/youtube_dl/extractor/imgur.py +++ b/youtube_dl/extractor/imgur.py @@ -12,7 +12,7 @@ from ..utils import ( class ImgurIE(InfoExtractor): - _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:gallery|(?:topic|r)/[^/]+)/)?(?P<id>[a-zA-Z0-9]{6,})(?:[/?#&]+|\.[a-z]+)?$' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:gallery|(?:topic|r)/[^/]+)/)?(?P<id>[a-zA-Z0-9]{6,})(?:[/?#&]+|\.[a-z0-9]+)?$' _TESTS = [{ 'url': 'https://i.imgur.com/A61SaA1.gifv', @@ -43,6 +43,9 @@ class ImgurIE(InfoExtractor): }, { 'url': 'http://imgur.com/r/aww/VQcQPhM', 'only_matching': True, + }, { + 'url': 'https://i.imgur.com/crGpqCV.mp4', + 'only_matching': True, }] def _real_extract(self, url): From bd21ead2a20ff16ec8cb10da72526103471069d6 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 18 Jul 2018 18:29:18 +0100 Subject: [PATCH 073/558] [extractor/common] add support for DASH and MSS formats extraction in SMIL manifests --- youtube_dl/extractor/common.py | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 5d4db54d5..b8bbaf81a 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1859,9 +1859,7 @@ class InfoExtractor(object): 'height': height, }) formats.extend(m3u8_formats) - continue - - if src_ext == 'f4m': + elif src_ext == 'f4m': f4m_url = src_url if not f4m_params: f4m_params = { @@ -1871,9 +1869,13 @@ class InfoExtractor(object): f4m_url += '&' if '?' in f4m_url else '?' f4m_url += compat_urllib_parse_urlencode(f4m_params) formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False)) - continue - - if src_url.startswith('http') and self._is_valid_url(src, video_id): + elif src_ext == 'mpd': + formats.extend(self._extract_mpd_formats( + src_url, video_id, mpd_id='dash', fatal=False)) + elif re.search(r'\.ism/[Mm]anifest', src_url): + formats.extend(self._extract_ism_formats( + src_url, video_id, ism_id='mss', fatal=False)) + elif src_url.startswith('http') and self._is_valid_url(src, video_id): http_count += 1 formats.append({ 'url': src_url, @@ -1884,7 +1886,6 @@ class InfoExtractor(object): 'width': width, 'height': height, }) - continue return formats From 371dcc1dd4b29001910005c1d3e416db204cc262 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 18 Jul 2018 18:31:40 +0100 Subject: [PATCH 074/558] [theplatform] add support for theplatform Top-level domain customization(#16977) --- youtube_dl/extractor/theplatform.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index b1a985ff6..e7dc6071c 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -32,13 +32,14 @@ _x = lambda p: xpath_with_ns(p, {'smil': default_ns}) class ThePlatformBaseIE(OnceIE): + _TP_TLD = 'com' def _extract_theplatform_smil(self, smil_url, video_id, note='Downloading SMIL data'): meta = self._download_xml( smil_url, video_id, note=note, query={'format': 'SMIL'}, headers=self.geo_verification_headers()) error_element = find_xpath_attr(meta, _x('.//smil:ref'), 'src') if error_element is not None and error_element.attrib['src'].startswith( - 'http://link.theplatform.com/s/errorFiles/Unavailable.'): + 'http://link.theplatform.%s/s/errorFiles/Unavailable.' % self._TP_TLD): raise ExtractorError(error_element.attrib['abstract'], expected=True) smil_formats = self._parse_smil_formats( @@ -66,7 +67,7 @@ class ThePlatformBaseIE(OnceIE): return formats, subtitles def _download_theplatform_metadata(self, path, video_id): - info_url = 'http://link.theplatform.com/s/%s?format=preview' % path + info_url = 'http://link.theplatform.%s/s/%s?format=preview' % (self._TP_TLD, path) return self._download_json(info_url, video_id) def _parse_theplatform_metadata(self, info): From 38f1eb0ac3be5d3b61e7722db0024e61cf98eb69 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 18 Jul 2018 18:33:33 +0100 Subject: [PATCH 075/558] [mediaset] fix extraction(closes #16977) --- youtube_dl/extractor/mediaset.py | 155 +++++++++++++++---------------- 1 file changed, 74 insertions(+), 81 deletions(-) diff --git a/youtube_dl/extractor/mediaset.py b/youtube_dl/extractor/mediaset.py index 9f2b60dcc..57f97409d 100644 --- a/youtube_dl/extractor/mediaset.py +++ b/youtube_dl/extractor/mediaset.py @@ -3,75 +3,75 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor -from ..compat import compat_str +from .theplatform import ThePlatformBaseIE from ..utils import ( - determine_ext, - parse_duration, - try_get, - unified_strdate, + ExtractorError, + int_or_none, + update_url_query, ) -class MediasetIE(InfoExtractor): +class MediasetIE(ThePlatformBaseIE): + _TP_TLD = 'eu' _VALID_URL = r'''(?x) (?: mediaset:| https?:// - (?:www\.)?video\.mediaset\.it/ + (?:(?:www|static3)\.)?mediasetplay\.mediaset\.it/ (?: (?:video|on-demand)/(?:[^/]+/)+[^/]+_| - player/playerIFrame(?:Twitter)?\.shtml\?.*?\bid= + player/index\.html\?.*?\bprogramGuid= ) - )(?P<id>[0-9]+) + )(?P<id>[0-9A-Z]{16}) ''' _TESTS = [{ # full episode - 'url': 'http://www.video.mediaset.it/video/hello_goodbye/full/quarta-puntata_661824.html', + 'url': 'https://www.mediasetplay.mediaset.it/video/hellogoodbye/quarta-puntata_FAFU000000661824', 'md5': '9b75534d42c44ecef7bf1ffeacb7f85d', 'info_dict': { - 'id': '661824', + 'id': 'FAFU000000661824', 'ext': 'mp4', 'title': 'Quarta puntata', - 'description': 'md5:7183696d6df570e3412a5ef74b27c5e2', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', 'thumbnail': r're:^https?://.*\.jpg$', - 'duration': 1414, - 'creator': 'mediaset', + 'duration': 1414.26, 'upload_date': '20161107', 'series': 'Hello Goodbye', - 'categories': ['reality'], + 'timestamp': 1478532900, + 'uploader': 'Rete 4', + 'uploader_id': 'R4', }, - 'expected_warnings': ['is not a supported codec'], }, { - 'url': 'http://www.video.mediaset.it/video/matrix/full_chiambretti/puntata-del-25-maggio_846685.html', - 'md5': '1276f966ac423d16ba255ce867de073e', + 'url': 'https://www.mediasetplay.mediaset.it/video/matrix/puntata-del-25-maggio_F309013801000501', + 'md5': '288532f0ad18307705b01e581304cd7b', 'info_dict': { - 'id': '846685', + 'id': 'F309013801000501', 'ext': 'mp4', 'title': 'Puntata del 25 maggio', - 'description': 'md5:ee2e456e3eb1dba5e814596655bb5296', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', 'thumbnail': r're:^https?://.*\.jpg$', - 'duration': 6565, - 'creator': 'mediaset', - 'upload_date': '20180525', + 'duration': 6565.007, + 'upload_date': '20180526', 'series': 'Matrix', - 'categories': ['infotainment'], + 'timestamp': 1527326245, + 'uploader': 'Canale 5', + 'uploader_id': 'C5', }, 'expected_warnings': ['HTTP Error 403: Forbidden'], }, { # clip - 'url': 'http://www.video.mediaset.it/video/gogglebox/clip/un-grande-classico-della-commedia-sexy_661680.html', + 'url': 'https://www.mediasetplay.mediaset.it/video/gogglebox/un-grande-classico-della-commedia-sexy_FAFU000000661680', 'only_matching': True, }, { # iframe simple - 'url': 'http://www.video.mediaset.it/player/playerIFrame.shtml?id=665924&autoplay=true', + 'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665924&id=665924', 'only_matching': True, }, { # iframe twitter (from http://www.wittytv.it/se-prima-mi-fidavo-zero/) - 'url': 'https://www.video.mediaset.it/player/playerIFrameTwitter.shtml?id=665104&playrelated=false&autoplay=false&related=true&hidesocial=true', + 'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665104&id=665104', 'only_matching': True, }, { - 'url': 'mediaset:661824', + 'url': 'mediaset:FAFU000000665924', 'only_matching': True, }] @@ -84,61 +84,54 @@ class MediasetIE(InfoExtractor): webpage)] def _real_extract(self, url): - video_id = self._match_id(url) - - video = self._download_json( - 'https://www.video.mediaset.it/html/metainfo.sjson', - video_id, 'Downloading media info', query={ - 'id': video_id - })['video'] - - title = video['title'] - media_id = video.get('guid') or video_id - - video_list = self._download_json( - 'http://cdnsel01.mediaset.net/GetCdn2018.aspx', - video_id, 'Downloading video CDN JSON', query={ - 'streamid': media_id, - 'format': 'json', - })['videoList'] + guid = self._match_id(url) + tp_path = 'PR1GhC/media/guid/2702976343/' + guid + info = self._extract_theplatform_metadata(tp_path, guid) formats = [] - for format_url in video_list: - ext = determine_ext(format_url) - if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - format_url, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False)) - elif ext == 'mpd': - formats.extend(self._extract_mpd_formats( - format_url, video_id, mpd_id='dash', fatal=False)) - elif ext == 'ism' or '.ism' in format_url: - formats.extend(self._extract_ism_formats( - format_url, video_id, ism_id='mss', fatal=False)) - else: - formats.append({ - 'url': format_url, - 'format_id': determine_ext(format_url), - }) + subtitles = {} + first_e = None + for asset_type in ('SD', 'HD'): + for f in ('MPEG4', 'MPEG-DASH', 'M3U', 'ISM'): + try: + tp_formats, tp_subtitles = self._extract_theplatform_smil( + update_url_query('http://link.theplatform.%s/s/%s' % (self._TP_TLD, tp_path), { + 'mbr': 'true', + 'formats': f, + 'assetTypes': asset_type, + }), guid, 'Downloading %s %s SMIL data' % (f, asset_type)) + except ExtractorError as e: + if not first_e: + first_e = e + break + for tp_f in tp_formats: + tp_f['quality'] = 1 if asset_type == 'HD' else 0 + formats.extend(tp_formats) + subtitles = self._merge_subtitles(subtitles, tp_subtitles) + if first_e and not formats: + raise first_e self._sort_formats(formats) - creator = try_get( - video, lambda x: x['brand-info']['publisher'], compat_str) - category = try_get( - video, lambda x: x['brand-info']['category'], compat_str) - categories = [category] if category else None + fields = [] + for templ, repls in (('tvSeason%sNumber', ('', 'Episode')), ('mediasetprogram$%s', ('brandTitle', 'numberOfViews', 'publishInfo'))): + fields.extend(templ % repl for repl in repls) + feed_data = self._download_json( + 'https://feed.entertainment.tv.theplatform.eu/f/PR1GhC/mediaset-prod-all-programs/guid/-/' + guid, + guid, fatal=False, query={'fields': ','.join(fields)}) + if feed_data: + publish_info = feed_data.get('mediasetprogram$publishInfo') or {} + info.update({ + 'episode_number': int_or_none(feed_data.get('tvSeasonEpisodeNumber')), + 'season_number': int_or_none(feed_data.get('tvSeasonNumber')), + 'series': feed_data.get('mediasetprogram$brandTitle'), + 'uploader': publish_info.get('description'), + 'uploader_id': publish_info.get('channel'), + 'view_count': int_or_none(feed_data.get('mediasetprogram$numberOfViews')), + }) - return { - 'id': video_id, - 'title': title, - 'description': video.get('short-description'), - 'thumbnail': video.get('thumbnail'), - 'duration': parse_duration(video.get('duration')), - 'creator': creator, - 'upload_date': unified_strdate(video.get('production-date')), - 'webpage_url': video.get('url'), - 'series': video.get('brand-value'), - 'season': video.get('season'), - 'categories': categories, + info.update({ + 'id': guid, 'formats': formats, - } + 'subtitles': subtitles, + }) + return info From c63f5fb8633dda1b0a673c90d537e93497a8d62d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 19 Jul 2018 01:59:00 +0700 Subject: [PATCH 076/558] [slutload] Fix and improve extraction (closes #17001) --- youtube_dl/extractor/slutload.py | 57 +++++++++++++++++++++----------- 1 file changed, 37 insertions(+), 20 deletions(-) diff --git a/youtube_dl/extractor/slutload.py b/youtube_dl/extractor/slutload.py index 6fc2ff60d..661f9e59d 100644 --- a/youtube_dl/extractor/slutload.py +++ b/youtube_dl/extractor/slutload.py @@ -1,12 +1,10 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor class SlutloadIE(InfoExtractor): - _VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$' + _VALID_URL = r'https?://(?:\w+\.)?slutload\.com/(?:video/[^/]+|embed_player|watch)/(?P<id>[^/]+)' _TESTS = [{ 'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/', 'md5': '868309628ba00fd488cf516a113fd717', @@ -16,33 +14,52 @@ class SlutloadIE(InfoExtractor): 'title': 'virginie baisee en cam', 'age_limit': 18, 'thumbnail': r're:https?://.*?\.jpg' - } + }, }, { # mobile site 'url': 'http://mobile.slutload.com/video/masturbation-solo/fviFLmc6kzJ/', 'only_matching': True, + }, { + 'url': 'http://www.slutload.com/embed_player/TD73btpBqSxc/', + 'only_matching': True, + }, { + 'url': 'http://www.slutload.com/watch/TD73btpBqSxc/Virginie-Baisee-En-Cam.html', + 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) - desktop_url = re.sub(r'^(https?://)mobile\.', r'\1', url) - webpage = self._download_webpage(desktop_url, video_id) + embed_page = self._download_webpage( + 'http://www.slutload.com/embed_player/%s' % video_id, video_id, + 'Downloading embed page', fatal=False) - video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>', - webpage, 'title').strip() + if embed_page: + def extract(what): + return self._html_search_regex( + r'data-video-%s=(["\'])(?P<url>(?:(?!\1).)+)\1' % what, + embed_page, 'video %s' % what, default=None, group='url') - video_url = self._html_search_regex( - r'(?s)<div id="vidPlayer"\s+data-url="([^"]+)"', - webpage, 'video URL') - thumbnail = self._html_search_regex( - r'(?s)<div id="vidPlayer"\s+.*?previewer-file="([^"]+)"', - webpage, 'thumbnail', fatal=False) + video_url = extract('url') + if video_url: + title = self._html_search_regex( + r'<title>([^<]+)', embed_page, 'title', default=video_id) + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'thumbnail': extract('preview'), + 'age_limit': 18 + } - return { + webpage = self._download_webpage( + 'http://www.slutload.com/video/_/%s/' % video_id, video_id) + title = self._html_search_regex( + r'<h1><strong>([^<]+)</strong>', webpage, 'title').strip() + info = self._parse_html5_media_entries(url, webpage, video_id)[0] + info.update({ 'id': video_id, - 'url': video_url, - 'title': video_title, - 'thumbnail': thumbnail, - 'age_limit': 18 - } + 'title': title, + 'age_limit': 18, + }) + return info From 8da17f96803faa35ab19352bdcd2777011d8812a Mon Sep 17 00:00:00 2001 From: bato3 <bato3@bandyci.org> Date: Wed, 18 Jul 2018 21:04:05 +0200 Subject: [PATCH 077/558] [dailymotion] Improve description extraction (closes #16984) --- youtube_dl/extractor/dailymotion.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 9a74906cb..8f5f57b98 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -144,7 +144,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor): age_limit = self._rta_search(webpage) - description = self._og_search_description(webpage) or self._html_search_meta( + description = self._og_search_description( + webpage, default=None) or self._html_search_meta( 'description', webpage, 'description') view_count_str = self._search_regex( From 11330f5121732f80e3d6ba1c34102955427eb04b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 19 Jul 2018 02:25:19 +0700 Subject: [PATCH 078/558] [facebook] Extract view count and update tests (closes #16942) --- youtube_dl/extractor/facebook.py | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 8a9ed96c2..f78479b92 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -20,6 +20,7 @@ from ..utils import ( int_or_none, js_to_json, limit_length, + parse_count, sanitized_Request, try_get, urlencode_postdata, @@ -75,7 +76,7 @@ class FacebookIE(InfoExtractor): 'info_dict': { 'id': '274175099429670', 'ext': 'mp4', - 'title': 'Asif Nawab Butt posted a video to his Timeline.', + 'title': 're:^Asif Nawab Butt posted a video', 'uploader': 'Asif Nawab Butt', 'upload_date': '20140506', 'timestamp': 1399398998, @@ -133,7 +134,7 @@ class FacebookIE(InfoExtractor): }, { # have 1080P, but only up to 720p in swf params 'url': 'https://www.facebook.com/cnn/videos/10155529876156509/', - 'md5': '0d9813160b146b3bc8744e006027fcc6', + 'md5': '9571fae53d4165bbbadb17a94651dcdc', 'info_dict': { 'id': '10155529876156509', 'ext': 'mp4', @@ -142,6 +143,7 @@ class FacebookIE(InfoExtractor): 'upload_date': '20161030', 'uploader': 'CNN', 'thumbnail': r're:^https?://.*', + 'view_count': int, }, }, { # bigPipe.onPageletArrive ... onPageletArrive pagelet_group_mall @@ -149,7 +151,7 @@ class FacebookIE(InfoExtractor): 'info_dict': { 'id': '1417995061575415', 'ext': 'mp4', - 'title': 'md5:a7b86ca673f51800cd54687b7f4012fe', + 'title': 'md5:1db063d6a8c13faa8da727817339c857', 'timestamp': 1486648217, 'upload_date': '20170209', 'uploader': 'Yaroslav Korpan', @@ -176,7 +178,7 @@ class FacebookIE(InfoExtractor): 'info_dict': { 'id': '1396382447100162', 'ext': 'mp4', - 'title': 'md5:e2d2700afdf84e121f5d0f999bad13a3', + 'title': 'md5:19a428bbde91364e3de815383b54a235', 'timestamp': 1486035494, 'upload_date': '20170202', 'uploader': 'Elisabeth Ahtn', @@ -426,6 +428,10 @@ class FacebookIE(InfoExtractor): 'timestamp', default=None)) thumbnail = self._og_search_thumbnail(webpage) + view_count = parse_count(self._search_regex( + r'\bviewCount\s*:\s*["\']([\d,.]+)', webpage, 'view count', + default=None)) + info_dict = { 'id': video_id, 'title': video_title, @@ -433,6 +439,7 @@ class FacebookIE(InfoExtractor): 'uploader': uploader, 'timestamp': timestamp, 'thumbnail': thumbnail, + 'view_count': view_count, } return webpage, info_dict From 6fc09f0155bae1fd0d3edf31111b37012875b6f2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 19 Jul 2018 23:14:20 +0700 Subject: [PATCH 079/558] [vimeo] Add another config regex (closes #17013) --- youtube_dl/extractor/vimeo.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 3baa2d075..e49b233f2 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -539,9 +539,10 @@ class VimeoIE(VimeoBaseInfoExtractor): # We try to find out to which variable is assigned the config dic m_variable_name = re.search(r'(\w)\.video\.id', webpage) if m_variable_name is not None: - config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1)) + config_re = [r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))] else: config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});'] + config_re.append(r'\bvar\s+r\s*=\s*({.+?})\s*;') config = self._search_regex(config_re, webpage, 'info section', flags=re.DOTALL) config = json.loads(config) From c258570eddeafdef23221326e1961c81934f5297 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 20 Jul 2018 00:01:43 +0700 Subject: [PATCH 080/558] [viu] Pass Referer and Origin headers (closes #16992) --- youtube_dl/extractor/viu.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/youtube_dl/extractor/viu.py b/youtube_dl/extractor/viu.py index 5cf93591c..e268f9409 100644 --- a/youtube_dl/extractor/viu.py +++ b/youtube_dl/extractor/viu.py @@ -214,6 +214,9 @@ class ViuOTTIE(InfoExtractor): 'https://d1k2us671qcoau.cloudfront.net/distribute_web_%s.php' % country_code, video_id, 'Downloading stream info', query={ 'ccs_product_id': video_data['ccs_product_id'], + }, headers={ + 'Referer': url, + 'Origin': re.search(r'https?://[^/]+', url).group(0), })['data']['stream'] stream_sizes = stream_data.get('size', {}) From ecb6b6ae2df15cb777fbffdfb8058affa8918f54 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 20 Jul 2018 00:46:50 +0700 Subject: [PATCH 081/558] [viu] Pass area id --- youtube_dl/extractor/viu.py | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/viu.py b/youtube_dl/extractor/viu.py index e268f9409..3bd37525b 100644 --- a/youtube_dl/extractor/viu.py +++ b/youtube_dl/extractor/viu.py @@ -195,16 +195,29 @@ class ViuOTTIE(InfoExtractor): 'skip': 'Geo-restricted to Hong Kong', }] + _AREA_ID = { + 'HK': 1, + 'SG': 2, + 'TH': 4, + 'PH': 5, + } + def _real_extract(self, url): country_code, video_id = re.match(self._VALID_URL, url).groups() + query = { + 'r': 'vod/ajax-detail', + 'platform_flag_label': 'web', + 'product_id': video_id, + } + + area_id = self._AREA_ID.get(country_code.upper()) + if area_id: + query['area_id'] = area_id + product_data = self._download_json( 'http://www.viu.com/ott/%s/index.php' % country_code, video_id, - 'Downloading video info', query={ - 'r': 'vod/ajax-detail', - 'platform_flag_label': 'web', - 'product_id': video_id, - })['data'] + 'Downloading video info', query=query)['data'] video_data = product_data.get('current_product') if not video_data: From 25586c601c46768271070c61af76e7fa1d196890 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 20 Jul 2018 00:48:50 +0700 Subject: [PATCH 082/558] [theplatform] PEP 8 [ci skip] --- youtube_dl/extractor/theplatform.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index e7dc6071c..411b1f874 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -33,6 +33,7 @@ _x = lambda p: xpath_with_ns(p, {'smil': default_ns}) class ThePlatformBaseIE(OnceIE): _TP_TLD = 'com' + def _extract_theplatform_smil(self, smil_url, video_id, note='Downloading SMIL data'): meta = self._download_xml( smil_url, video_id, note=note, query={'format': 'SMIL'}, From fd62b36680ff7d7bea789ac0031a33fc2d9270ad Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 20 Jul 2018 02:39:20 +0700 Subject: [PATCH 083/558] [vrtnu] Relax title extraction and extract JSON-LD (closes #17018) --- youtube_dl/extractor/canvas.py | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/canvas.py b/youtube_dl/extractor/canvas.py index 8ac62c1a6..174fd9e2b 100644 --- a/youtube_dl/extractor/canvas.py +++ b/youtube_dl/extractor/canvas.py @@ -11,6 +11,7 @@ from ..utils import ( strip_or_none, float_or_none, int_or_none, + merge_dicts, parse_iso8601, ) @@ -248,9 +249,13 @@ class VrtNUIE(GigyaBaseIE): webpage, urlh = self._download_webpage_handle(url, display_id) - title = self._html_search_regex( + info = self._search_json_ld(webpage, display_id, default={}) + + # title is optional here since it may be extracted by extractor + # that is delegated from here + title = strip_or_none(self._html_search_regex( r'(?ms)<h1 class="content__heading">(.+?)</h1>', - webpage, 'title').strip() + webpage, 'title', default=None)) description = self._html_search_regex( r'(?ms)<div class="content__description">(.+?)</div>', @@ -295,7 +300,7 @@ class VrtNUIE(GigyaBaseIE): # the first one video_id = list(video.values())[0].get('videoid') - return { + return merge_dicts(info, { '_type': 'url_transparent', 'url': 'https://mediazone.vrt.be/api/v1/vrtvideo/assets/%s' % video_id, 'ie_key': CanvasIE.ie_key(), @@ -307,4 +312,4 @@ class VrtNUIE(GigyaBaseIE): 'season_number': season_number, 'episode_number': episode_number, 'release_date': release_date, - } + }) From e9c671d5e86e43785382ae9cb20c8e7676c7c9bf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 21 Jul 2018 12:30:18 +0700 Subject: [PATCH 084/558] [utils] Allow JSONP with empty func name (closes #17028) --- test/test_utils.py | 4 ++++ youtube_dl/utils.py | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/test/test_utils.py b/test/test_utils.py index e63af0166..de841b1a0 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -717,6 +717,10 @@ class TestUtil(unittest.TestCase): d = json.loads(stripped) self.assertEqual(d, {'status': 'success'}) + stripped = strip_jsonp('({"status": "success"});') + d = json.loads(stripped) + self.assertEqual(d, {'status': 'success'}) + def test_uppercase_escape(self): self.assertEqual(uppercase_escape('aä'), 'aä') self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐') diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 8c45166d7..b8700efcb 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -2282,7 +2282,7 @@ def parse_age_limit(s): def strip_jsonp(code): return re.sub( r'''(?sx)^ - (?:window\.)?(?P<func_name>[a-zA-Z0-9_.$]+) + (?:window\.)?(?P<func_name>[a-zA-Z0-9_.$]*) (?:\s*&&\s*(?P=func_name))? \s*\(\s*(?P<callback_data>.*)\);? \s*?(?://[^\n]*)*$''', From edb0e17188a1197afae1a0d594e4aab7d27bbcf2 Mon Sep 17 00:00:00 2001 From: Kazuma Takahara <4269kzm@gmail.com> Date: Sat, 21 Jul 2018 19:41:33 +0900 Subject: [PATCH 085/558] [iwara] Fix download URLs (closes #17026) --- youtube_dl/extractor/iwara.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/iwara.py b/youtube_dl/extractor/iwara.py index a7514fc80..250140d91 100644 --- a/youtube_dl/extractor/iwara.py +++ b/youtube_dl/extractor/iwara.py @@ -77,7 +77,7 @@ class IwaraIE(InfoExtractor): height = int_or_none(self._search_regex( r'(\d+)p', format_id, 'height', default=None)) formats.append({ - 'url': a_format['uri'], + 'url': self._proto_relative_url(a_format['uri'], 'https:'), 'format_id': format_id, 'ext': mimetype2ext(a_format.get('mime')) or 'mp4', 'height': height, From b96b4be4619b1e090650212380a92fb068f2fd21 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 21 Jul 2018 11:49:55 +0100 Subject: [PATCH 086/558] [bbc] add support for BBC Radio Play pages(closes #17022) --- youtube_dl/extractor/bbc.py | 41 +++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 293d82b0f..641bf6073 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -778,6 +778,17 @@ class BBCIE(BBCCoUkIE): 'params': { 'skip_download': True, } + }, { + # window.__PRELOADED_STATE__ + 'url': 'https://www.bbc.co.uk/radio/play/b0b9z4yl', + 'info_dict': { + 'id': 'b0b9z4vz', + 'ext': 'mp4', + 'title': 'Prom 6: An American in Paris and Turangalila', + 'description': 'md5:51cf7d6f5c8553f197e58203bc78dff8', + 'uploader': 'Radio 3', + 'uploader_id': 'bbc_radio_three', + }, }] @classmethod @@ -1000,6 +1011,36 @@ class BBCIE(BBCCoUkIE): 'subtitles': subtitles, } + preload_state = self._parse_json(self._search_regex( + r'window\.__PRELOADED_STATE__\s*=\s*({.+?});', webpage, + 'preload state', default='{}'), playlist_id, fatal=False) + if preload_state: + current_programme = preload_state.get('programmes', {}).get('current') or {} + programme_id = current_programme.get('id') + if current_programme and programme_id and current_programme.get('type') == 'playable_item': + title = current_programme.get('titles', {}).get('tertiary') or playlist_title + formats, subtitles = self._download_media_selector(programme_id) + self._sort_formats(formats) + synopses = current_programme.get('synopses') or {} + network = current_programme.get('network') or {} + duration = int_or_none( + current_programme.get('duration', {}).get('value')) + thumbnail = None + image_url = current_programme.get('image_url') + if image_url: + thumbnail = image_url.replace('{recipe}', '1920x1920') + return { + 'id': programme_id, + 'title': title, + 'description': dict_get(synopses, ('long', 'medium', 'short')), + 'thumbnail': thumbnail, + 'duration': duration, + 'uploader': network.get('short_title'), + 'uploader_id': network.get('id'), + 'formats': formats, + 'subtitles': subtitles, + } + bbc3_config = self._parse_json( self._search_regex( r'(?s)bbcthreeConfig\s*=\s*({.+?})\s*;\s*<', webpage, From af03000ad5a445f03fbacb63ce626f8dcfe785c7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 21 Jul 2018 18:01:06 +0700 Subject: [PATCH 087/558] [utils] Introduce url_or_none --- test/test_utils.py | 11 +++++++++++ youtube_dl/utils.py | 7 +++++++ 2 files changed, 18 insertions(+) diff --git a/test/test_utils.py b/test/test_utils.py index de841b1a0..8da5ccc56 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -78,6 +78,7 @@ from youtube_dl.utils import ( uppercase_escape, lowercase_escape, url_basename, + url_or_none, base_url, urljoin, urlencode_postdata, @@ -507,6 +508,16 @@ class TestUtil(unittest.TestCase): self.assertEqual(urljoin('http://foo.de/', ['foobar']), None) self.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt') + def test_url_or_none(self): + self.assertEqual(url_or_none(None), None) + self.assertEqual(url_or_none(''), None) + self.assertEqual(url_or_none('foo'), None) + self.assertEqual(url_or_none('http://foo.de'), 'http://foo.de') + self.assertEqual(url_or_none('https://foo.de'), 'https://foo.de') + self.assertEqual(url_or_none('http$://foo.de'), None) + self.assertEqual(url_or_none('http://foo.de'), 'http://foo.de') + self.assertEqual(url_or_none('//foo.de'), '//foo.de') + def test_parse_age_limit(self): self.assertEqual(parse_age_limit(None), None) self.assertEqual(parse_age_limit(False), None) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index b8700efcb..b84436ed6 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1866,6 +1866,13 @@ def strip_or_none(v): return None if v is None else v.strip() +def url_or_none(url): + if not url or not isinstance(url, compat_str): + return None + url = url.strip() + return url if re.match(r'^(?:[a-zA-Z][\da-zA-Z.+-]*:)?//', url) else None + + def parse_duration(s): if not isinstance(s, compat_basestring): return None From 4ecf300d13a6503ae80b76e01047b41d86ab4d92 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 21 Jul 2018 18:02:41 +0700 Subject: [PATCH 088/558] [iwara] Improve extraction --- youtube_dl/extractor/iwara.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/iwara.py b/youtube_dl/extractor/iwara.py index 250140d91..907d5fc8b 100644 --- a/youtube_dl/extractor/iwara.py +++ b/youtube_dl/extractor/iwara.py @@ -7,6 +7,7 @@ from ..utils import ( int_or_none, mimetype2ext, remove_end, + url_or_none, ) @@ -73,11 +74,14 @@ class IwaraIE(InfoExtractor): formats = [] for a_format in video_data: + format_uri = url_or_none(a_format.get('uri')) + if not format_uri: + continue format_id = a_format.get('resolution') height = int_or_none(self._search_regex( r'(\d+)p', format_id, 'height', default=None)) formats.append({ - 'url': self._proto_relative_url(a_format['uri'], 'https:'), + 'url': self._proto_relative_url(format_uri, 'https:'), 'format_id': format_id, 'ext': mimetype2ext(a_format.get('mime')) or 'mp4', 'height': height, From 3052a30d4259b182904e5d2430077039461745bb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 21 Jul 2018 19:08:28 +0700 Subject: [PATCH 089/558] Improve URL extraction --- youtube_dl/extractor/adultswim.py | 3 ++- youtube_dl/extractor/afreecatv.py | 3 ++- youtube_dl/extractor/amp.py | 15 ++++++++------- youtube_dl/extractor/animeondemand.py | 3 ++- youtube_dl/extractor/aol.py | 3 ++- youtube_dl/extractor/apa.py | 6 +++--- youtube_dl/extractor/aparat.py | 3 ++- youtube_dl/extractor/ard.py | 4 ++-- youtube_dl/extractor/bandcamp.py | 7 ++++--- youtube_dl/extractor/breakcom.py | 10 ++++++---- youtube_dl/extractor/cammodels.py | 6 +++--- youtube_dl/extractor/ccma.py | 6 +++--- youtube_dl/extractor/crackle.py | 14 ++++++-------- youtube_dl/extractor/dctp.py | 7 ++++--- youtube_dl/extractor/discoverygo.py | 7 +++---- youtube_dl/extractor/dramafever.py | 10 +++++----- youtube_dl/extractor/eagleplatform.py | 8 +++----- youtube_dl/extractor/egghead.py | 8 +++++--- youtube_dl/extractor/eporner.py | 5 +++-- youtube_dl/extractor/firsttv.py | 5 +++-- youtube_dl/extractor/francetv.py | 8 ++++---- youtube_dl/extractor/frontendmasters.py | 3 ++- youtube_dl/extractor/generic.py | 5 +++-- youtube_dl/extractor/hidive.py | 10 +++++----- youtube_dl/extractor/imdb.py | 6 +++--- youtube_dl/extractor/instagram.py | 3 ++- youtube_dl/extractor/itv.py | 5 +++-- youtube_dl/extractor/keezmovies.py | 9 ++++----- youtube_dl/extractor/konserthusetplay.py | 5 +++-- youtube_dl/extractor/mediasite.py | 5 +++-- youtube_dl/extractor/peertube.py | 5 +++-- youtube_dl/extractor/redtube.py | 6 +++--- youtube_dl/extractor/rentv.py | 5 +++-- youtube_dl/extractor/rutube.py | 5 +++-- youtube_dl/extractor/turner.py | 5 +++-- youtube_dl/extractor/tvnet.py | 7 +++---- youtube_dl/extractor/tvplay.py | 4 +++- youtube_dl/extractor/twitch.py | 5 +++-- youtube_dl/extractor/udemy.py | 13 +++++++------ youtube_dl/extractor/vidme.py | 10 ++++------ youtube_dl/extractor/vk.py | 4 +++- youtube_dl/extractor/xhamster.py | 7 +++++-- youtube_dl/extractor/yapfiles.py | 8 ++++---- youtube_dl/extractor/youjizz.py | 6 +++--- youtube_dl/extractor/youporn.py | 6 +++--- youtube_dl/extractor/zattoo.py | 5 +++-- youtube_dl/extractor/zdf.py | 12 +++++++----- 47 files changed, 166 insertions(+), 139 deletions(-) diff --git a/youtube_dl/extractor/adultswim.py b/youtube_dl/extractor/adultswim.py index acc4ce38d..88c96a950 100644 --- a/youtube_dl/extractor/adultswim.py +++ b/youtube_dl/extractor/adultswim.py @@ -7,6 +7,7 @@ from .turner import TurnerBaseIE from ..utils import ( int_or_none, strip_or_none, + url_or_none, ) @@ -98,7 +99,7 @@ class AdultSwimIE(TurnerBaseIE): if not video_id: entries = [] for episode in video_data.get('archiveEpisodes', []): - episode_url = episode.get('url') + episode_url = url_or_none(episode.get('url')) if not episode_url: continue entries.append(self.url_result( diff --git a/youtube_dl/extractor/afreecatv.py b/youtube_dl/extractor/afreecatv.py index 4b3d97136..6275e5209 100644 --- a/youtube_dl/extractor/afreecatv.py +++ b/youtube_dl/extractor/afreecatv.py @@ -9,6 +9,7 @@ from ..utils import ( determine_ext, ExtractorError, int_or_none, + url_or_none, urlencode_postdata, xpath_text, ) @@ -304,7 +305,7 @@ class AfreecaTVIE(InfoExtractor): file_elements = video_element.findall(compat_xpath('./file')) one = len(file_elements) == 1 for file_num, file_element in enumerate(file_elements, start=1): - file_url = file_element.text + file_url = url_or_none(file_element.text) if not file_url: continue key = file_element.get('key', '') diff --git a/youtube_dl/extractor/amp.py b/youtube_dl/extractor/amp.py index fde1a8ff7..7ff098cfa 100644 --- a/youtube_dl/extractor/amp.py +++ b/youtube_dl/extractor/amp.py @@ -3,11 +3,12 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( - int_or_none, - parse_iso8601, - mimetype2ext, determine_ext, ExtractorError, + int_or_none, + mimetype2ext, + parse_iso8601, + url_or_none, ) @@ -35,7 +36,7 @@ class AMPIE(InfoExtractor): media_thumbnail = [media_thumbnail] for thumbnail_data in media_thumbnail: thumbnail = thumbnail_data.get('@attributes', {}) - thumbnail_url = thumbnail.get('url') + thumbnail_url = url_or_none(thumbnail.get('url')) if not thumbnail_url: continue thumbnails.append({ @@ -51,7 +52,7 @@ class AMPIE(InfoExtractor): media_subtitle = [media_subtitle] for subtitle_data in media_subtitle: subtitle = subtitle_data.get('@attributes', {}) - subtitle_href = subtitle.get('href') + subtitle_href = url_or_none(subtitle.get('href')) if not subtitle_href: continue subtitles.setdefault(subtitle.get('lang') or 'en', []).append({ @@ -65,7 +66,7 @@ class AMPIE(InfoExtractor): media_content = [media_content] for media_data in media_content: media = media_data.get('@attributes', {}) - media_url = media.get('url') + media_url = url_or_none(media.get('url')) if not media_url: continue ext = mimetype2ext(media.get('type')) or determine_ext(media_url) @@ -79,7 +80,7 @@ class AMPIE(InfoExtractor): else: formats.append({ 'format_id': media_data.get('media-category', {}).get('@attributes', {}).get('label'), - 'url': media['url'], + 'url': media_url, 'tbr': int_or_none(media.get('bitrate')), 'filesize': int_or_none(media.get('fileSize')), 'ext': ext, diff --git a/youtube_dl/extractor/animeondemand.py b/youtube_dl/extractor/animeondemand.py index 1fe5d5e56..00ce684d1 100644 --- a/youtube_dl/extractor/animeondemand.py +++ b/youtube_dl/extractor/animeondemand.py @@ -8,6 +8,7 @@ from ..utils import ( determine_ext, extract_attributes, ExtractorError, + url_or_none, urlencode_postdata, urljoin, ) @@ -165,7 +166,7 @@ class AnimeOnDemandIE(InfoExtractor): }, fatal=False) if not playlist: continue - stream_url = playlist.get('streamurl') + stream_url = url_or_none(playlist.get('streamurl')) if stream_url: rtmp = re.search( r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+/))(?P<playpath>mp[34]:.+)', diff --git a/youtube_dl/extractor/aol.py b/youtube_dl/extractor/aol.py index b50f454ee..cb9279193 100644 --- a/youtube_dl/extractor/aol.py +++ b/youtube_dl/extractor/aol.py @@ -7,6 +7,7 @@ from .common import InfoExtractor from ..utils import ( ExtractorError, int_or_none, + url_or_none, ) @@ -77,7 +78,7 @@ class AolIE(InfoExtractor): formats.extend(self._extract_m3u8_formats( m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) for rendition in video_data.get('renditions', []): - video_url = rendition.get('url') + video_url = url_or_none(rendition.get('url')) if not video_url: continue ext = rendition.get('format') diff --git a/youtube_dl/extractor/apa.py b/youtube_dl/extractor/apa.py index a30a935aa..98ccdaa4a 100644 --- a/youtube_dl/extractor/apa.py +++ b/youtube_dl/extractor/apa.py @@ -4,10 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( determine_ext, js_to_json, + url_or_none, ) @@ -68,8 +68,8 @@ class APAIE(InfoExtractor): for source in sources: if not isinstance(source, dict): continue - source_url = source.get('file') - if not source_url or not isinstance(source_url, compat_str): + source_url = url_or_none(source.get('file')) + if not source_url: continue ext = determine_ext(source_url) if ext == 'm3u8': diff --git a/youtube_dl/extractor/aparat.py b/youtube_dl/extractor/aparat.py index e394cb661..6eb8bbb6e 100644 --- a/youtube_dl/extractor/aparat.py +++ b/youtube_dl/extractor/aparat.py @@ -5,6 +5,7 @@ from .common import InfoExtractor from ..utils import ( int_or_none, mimetype2ext, + url_or_none, ) @@ -43,7 +44,7 @@ class AparatIE(InfoExtractor): formats = [] for item in file_list[0]: - file_url = item.get('file') + file_url = url_or_none(item.get('file')) if not file_url: continue ext = mimetype2ext(item.get('type')) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 86951d975..23f574d36 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -5,7 +5,6 @@ import re from .common import InfoExtractor from .generic import GenericIE -from ..compat import compat_str from ..utils import ( determine_ext, ExtractorError, @@ -15,6 +14,7 @@ from ..utils import ( unified_strdate, xpath_text, update_url_query, + url_or_none, ) from ..compat import compat_etree_fromstring @@ -100,7 +100,7 @@ class ARDMediathekIE(InfoExtractor): quality = stream.get('_quality') server = stream.get('_server') for stream_url in stream_urls: - if not isinstance(stream_url, compat_str) or '//' not in stream_url: + if not url_or_none(stream_url): continue ext = determine_ext(stream_url) if quality != 'auto' and ext in ('f4m', 'm3u8'): diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py index be41bd5a2..b8514734d 100644 --- a/youtube_dl/extractor/bandcamp.py +++ b/youtube_dl/extractor/bandcamp.py @@ -19,6 +19,7 @@ from ..utils import ( unescapeHTML, update_url_query, unified_strdate, + url_or_none, ) @@ -131,8 +132,8 @@ class BandcampIE(InfoExtractor): fatal=False) if not stat: continue - retry_url = stat.get('retry_url') - if not isinstance(retry_url, compat_str): + retry_url = url_or_none(stat.get('retry_url')) + if not retry_url: continue formats.append({ 'url': self._proto_relative_url(retry_url, 'http:'), @@ -306,7 +307,7 @@ class BandcampWeeklyIE(InfoExtractor): formats = [] for format_id, format_url in show['audio_stream'].items(): - if not isinstance(format_url, compat_str): + if not url_or_none(format_url): continue for known_ext in KNOWN_EXTENSIONS: if known_ext in format_id: diff --git a/youtube_dl/extractor/breakcom.py b/youtube_dl/extractor/breakcom.py index 70d16767f..68c7cf2bb 100644 --- a/youtube_dl/extractor/breakcom.py +++ b/youtube_dl/extractor/breakcom.py @@ -4,8 +4,10 @@ import re from .common import InfoExtractor from .youtube import YoutubeIE -from ..compat import compat_str -from ..utils import int_or_none +from ..utils import ( + int_or_none, + url_or_none, +) class BreakIE(InfoExtractor): @@ -55,8 +57,8 @@ class BreakIE(InfoExtractor): formats = [] for video in content: - video_url = video.get('url') - if not video_url or not isinstance(video_url, compat_str): + video_url = url_or_none(video.get('url')) + if not video_url: continue bitrate = int_or_none(self._search_regex( r'(\d+)_kbps', video_url, 'tbr', default=None)) diff --git a/youtube_dl/extractor/cammodels.py b/youtube_dl/extractor/cammodels.py index ee0165dba..79350817f 100644 --- a/youtube_dl/extractor/cammodels.py +++ b/youtube_dl/extractor/cammodels.py @@ -2,10 +2,10 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( ExtractorError, int_or_none, + url_or_none, ) @@ -56,8 +56,8 @@ class CamModelsIE(InfoExtractor): for media in encodings: if not isinstance(media, dict): continue - media_url = media.get('location') - if not media_url or not isinstance(media_url, compat_str): + media_url = url_or_none(media.get('location')) + if not media_url: continue format_id_list = [format_id] diff --git a/youtube_dl/extractor/ccma.py b/youtube_dl/extractor/ccma.py index 07f5206c1..544647f92 100644 --- a/youtube_dl/extractor/ccma.py +++ b/youtube_dl/extractor/ccma.py @@ -4,13 +4,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( clean_html, int_or_none, parse_duration, parse_iso8601, parse_resolution, + url_or_none, ) @@ -53,8 +53,8 @@ class CCMAIE(InfoExtractor): media_url = media['media']['url'] if isinstance(media_url, list): for format_ in media_url: - format_url = format_.get('file') - if not format_url or not isinstance(format_url, compat_str): + format_url = url_or_none(format_.get('file')) + if not format_url: continue label = format_.get('label') f = parse_resolution(label) diff --git a/youtube_dl/extractor/crackle.py b/youtube_dl/extractor/crackle.py index f4a616455..8dd9d6687 100644 --- a/youtube_dl/extractor/crackle.py +++ b/youtube_dl/extractor/crackle.py @@ -4,16 +4,14 @@ from __future__ import unicode_literals, division import re from .common import InfoExtractor -from ..compat import ( - compat_str, - compat_HTTPError, -) +from ..compat import compat_HTTPError from ..utils import ( determine_ext, float_or_none, int_or_none, parse_age_limit, parse_duration, + url_or_none, ExtractorError ) @@ -86,8 +84,8 @@ class CrackleIE(InfoExtractor): for e in media['MediaURLs']: if e.get('UseDRM') is True: continue - format_url = e.get('Path') - if not format_url or not isinstance(format_url, compat_str): + format_url = url_or_none(e.get('Path')) + if not format_url: continue ext = determine_ext(format_url) if ext == 'm3u8': @@ -124,8 +122,8 @@ class CrackleIE(InfoExtractor): for cc_file in cc_files: if not isinstance(cc_file, dict): continue - cc_url = cc_file.get('Path') - if not cc_url or not isinstance(cc_url, compat_str): + cc_url = url_or_none(cc_file.get('Path')) + if not cc_url: continue lang = cc_file.get('Locale') or 'en' subtitles.setdefault(lang, []).append({'url': cc_url}) diff --git a/youtube_dl/extractor/dctp.py b/youtube_dl/extractor/dctp.py index dc0c41b8a..769a219df 100644 --- a/youtube_dl/extractor/dctp.py +++ b/youtube_dl/extractor/dctp.py @@ -7,6 +7,7 @@ from ..utils import ( float_or_none, int_or_none, unified_timestamp, + url_or_none, ) @@ -69,7 +70,7 @@ class DctpTvIE(InfoExtractor): endpoint = next( server['endpoint'] for server in servers - if isinstance(server.get('endpoint'), compat_str) and + if url_or_none(server.get('endpoint')) and 'cloudfront' in server['endpoint']) else: endpoint = 'rtmpe://s2pqqn4u96e4j8.cloudfront.net/cfx/st/' @@ -92,8 +93,8 @@ class DctpTvIE(InfoExtractor): for image in images: if not isinstance(image, dict): continue - image_url = image.get('url') - if not image_url or not isinstance(image_url, compat_str): + image_url = url_or_none(image.get('url')) + if not image_url: continue thumbnails.append({ 'url': image_url, diff --git a/youtube_dl/extractor/discoverygo.py b/youtube_dl/extractor/discoverygo.py index 3368c4c07..9e7b14a7d 100644 --- a/youtube_dl/extractor/discoverygo.py +++ b/youtube_dl/extractor/discoverygo.py @@ -3,7 +3,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( determine_ext, extract_attributes, @@ -12,6 +11,7 @@ from ..utils import ( parse_age_limit, remove_end, unescapeHTML, + url_or_none, ) @@ -69,9 +69,8 @@ class DiscoveryGoBaseIE(InfoExtractor): captions = stream.get('captions') if isinstance(captions, list): for caption in captions: - subtitle_url = caption.get('fileUrl') - if (not subtitle_url or not isinstance(subtitle_url, compat_str) or - not subtitle_url.startswith('http')): + subtitle_url = url_or_none(caption.get('fileUrl')) + if not subtitle_url or not subtitle_url.startswith('http'): continue lang = caption.get('fileLang', 'en') ext = determine_ext(subtitle_url) diff --git a/youtube_dl/extractor/dramafever.py b/youtube_dl/extractor/dramafever.py index ab32ba4ff..db1de699f 100644 --- a/youtube_dl/extractor/dramafever.py +++ b/youtube_dl/extractor/dramafever.py @@ -7,7 +7,6 @@ import json from .common import InfoExtractor from ..compat import ( compat_HTTPError, - compat_str, compat_urlparse, ) from ..utils import ( @@ -17,6 +16,7 @@ from ..utils import ( parse_age_limit, parse_duration, unified_timestamp, + url_or_none, ) @@ -139,8 +139,8 @@ class DramaFeverIE(DramaFeverBaseIE): for sub in subs: if not isinstance(sub, dict): continue - sub_url = sub.get('url') - if not sub_url or not isinstance(sub_url, compat_str): + sub_url = url_or_none(sub.get('url')) + if not sub_url: continue subtitles.setdefault( sub.get('code') or sub.get('language') or 'en', []).append({ @@ -163,8 +163,8 @@ class DramaFeverIE(DramaFeverBaseIE): for format_id, format_dict in download_assets.items(): if not isinstance(format_dict, dict): continue - format_url = format_dict.get('url') - if not format_url or not isinstance(format_url, compat_str): + format_url = url_or_none(format_dict.get('url')) + if not format_url: continue formats.append({ 'url': format_url, diff --git a/youtube_dl/extractor/eagleplatform.py b/youtube_dl/extractor/eagleplatform.py index 42789278e..36fef07b7 100644 --- a/youtube_dl/extractor/eagleplatform.py +++ b/youtube_dl/extractor/eagleplatform.py @@ -4,14 +4,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_HTTPError, - compat_str, -) +from ..compat import compat_HTTPError from ..utils import ( ExtractorError, int_or_none, unsmuggle_url, + url_or_none, ) @@ -177,7 +175,7 @@ class EaglePlatformIE(InfoExtractor): video_id, 'Downloading mp4 JSON', fatal=False) if mp4_data: for format_id, format_url in mp4_data.get('data', {}).items(): - if not isinstance(format_url, compat_str): + if not url_or_none(format_url): continue height = int_or_none(format_id) if height is not None and m3u8_formats_dict.get(height): diff --git a/youtube_dl/extractor/egghead.py b/youtube_dl/extractor/egghead.py index edabaafe6..df11dc206 100644 --- a/youtube_dl/extractor/egghead.py +++ b/youtube_dl/extractor/egghead.py @@ -8,6 +8,7 @@ from ..utils import ( int_or_none, try_get, unified_timestamp, + url_or_none, ) @@ -34,8 +35,8 @@ class EggheadCourseIE(InfoExtractor): entries = [] for lesson in lessons: - lesson_url = lesson.get('http_url') - if not lesson_url or not isinstance(lesson_url, compat_str): + lesson_url = url_or_none(lesson.get('http_url')) + if not lesson_url: continue lesson_id = lesson.get('id') if lesson_id: @@ -95,7 +96,8 @@ class EggheadLessonIE(InfoExtractor): formats = [] for _, format_url in lesson['media_urls'].items(): - if not format_url or not isinstance(format_url, compat_str): + format_url = url_or_none(format_url) + if not format_url: continue ext = determine_ext(format_url) if ext == 'm3u8': diff --git a/youtube_dl/extractor/eporner.py b/youtube_dl/extractor/eporner.py index 81f2e2ee1..6d03d7095 100644 --- a/youtube_dl/extractor/eporner.py +++ b/youtube_dl/extractor/eporner.py @@ -11,6 +11,7 @@ from ..utils import ( int_or_none, parse_duration, str_to_int, + url_or_none, ) @@ -82,8 +83,8 @@ class EpornerIE(InfoExtractor): for format_id, format_dict in formats_dict.items(): if not isinstance(format_dict, dict): continue - src = format_dict.get('src') - if not isinstance(src, compat_str) or not src.startswith('http'): + src = url_or_none(format_dict.get('src')) + if not src or not src.startswith('http'): continue if kind == 'hls': formats.extend(self._extract_m3u8_formats( diff --git a/youtube_dl/extractor/firsttv.py b/youtube_dl/extractor/firsttv.py index 4803a22c8..28617d83c 100644 --- a/youtube_dl/extractor/firsttv.py +++ b/youtube_dl/extractor/firsttv.py @@ -10,6 +10,7 @@ from ..utils import ( int_or_none, qualities, unified_strdate, + url_or_none, ) @@ -88,8 +89,8 @@ class FirstTVIE(InfoExtractor): formats = [] path = None for f in item.get('mbr', []): - src = f.get('src') - if not src or not isinstance(src, compat_str): + src = url_or_none(f.get('src')) + if not src: continue tbr = int_or_none(self._search_regex( r'_(\d{3,})\.mp4', src, 'tbr', default=None)) diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 6fc6b0da0..2ffe83a78 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -16,6 +16,7 @@ from ..utils import ( int_or_none, parse_duration, try_get, + url_or_none, ) from .dailymotion import DailymotionIE @@ -115,14 +116,13 @@ class FranceTVIE(InfoExtractor): def sign(manifest_url, manifest_id): for host in ('hdfauthftv-a.akamaihd.net', 'hdfauth.francetv.fr'): - signed_url = self._download_webpage( + signed_url = url_or_none(self._download_webpage( 'https://%s/esi/TA' % host, video_id, 'Downloading signed %s manifest URL' % manifest_id, fatal=False, query={ 'url': manifest_url, - }) - if (signed_url and isinstance(signed_url, compat_str) and - re.search(r'^(?:https?:)?//', signed_url)): + })) + if signed_url: return signed_url return manifest_url diff --git a/youtube_dl/extractor/frontendmasters.py b/youtube_dl/extractor/frontendmasters.py index 770db46d0..cb57ba007 100644 --- a/youtube_dl/extractor/frontendmasters.py +++ b/youtube_dl/extractor/frontendmasters.py @@ -11,6 +11,7 @@ from ..compat import ( from ..utils import ( ExtractorError, parse_duration, + url_or_none, urlencode_postdata, ) @@ -80,7 +81,7 @@ class FrontendMastersPageBaseIE(FrontendMastersBaseIE): chapters = [] lesson_elements = course.get('lessonElements') if isinstance(lesson_elements, list): - chapters = [e for e in lesson_elements if isinstance(e, compat_str)] + chapters = [url_or_none(e) for e in lesson_elements if url_or_none(e)] return chapters @staticmethod diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index aa04905ed..e5a8ffbe8 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -32,6 +32,7 @@ from ..utils import ( unified_strdate, unsmuggle_url, UnsupportedError, + url_or_none, xpath_text, ) from .commonprotocols import RtmpIE @@ -3130,8 +3131,8 @@ class GenericIE(InfoExtractor): sources = [sources] formats = [] for source in sources: - src = source.get('src') - if not src or not isinstance(src, compat_str): + src = url_or_none(source.get('src')) + if not src: continue src = compat_urlparse.urljoin(url, src) src_type = source.get('type') diff --git a/youtube_dl/extractor/hidive.py b/youtube_dl/extractor/hidive.py index 39fabe8a5..f26f80265 100644 --- a/youtube_dl/extractor/hidive.py +++ b/youtube_dl/extractor/hidive.py @@ -8,6 +8,7 @@ from ..compat import compat_str from ..utils import ( ExtractorError, int_or_none, + url_or_none, urlencode_postdata, ) @@ -80,8 +81,8 @@ class HiDiveIE(InfoExtractor): bitrates = rendition.get('bitrates') if not isinstance(bitrates, dict): continue - m3u8_url = bitrates.get('hls') - if not isinstance(m3u8_url, compat_str): + m3u8_url = url_or_none(bitrates.get('hls')) + if not m3u8_url: continue formats.extend(self._extract_m3u8_formats( m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', @@ -93,9 +94,8 @@ class HiDiveIE(InfoExtractor): if not isinstance(cc_file, list) or len(cc_file) < 3: continue cc_lang = cc_file[0] - cc_url = cc_file[2] - if not isinstance(cc_lang, compat_str) or not isinstance( - cc_url, compat_str): + cc_url = url_or_none(cc_file[2]) + if not isinstance(cc_lang, compat_str) or not cc_url: continue subtitles.setdefault(cc_lang, []).append({ 'url': cc_url, diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 4bafa54a2..fba01ef49 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -3,12 +3,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( determine_ext, mimetype2ext, parse_duration, qualities, + url_or_none, ) @@ -61,8 +61,8 @@ class ImdbIE(InfoExtractor): for encoding in video_metadata.get('encodings', []): if not encoding or not isinstance(encoding, dict): continue - video_url = encoding.get('videoUrl') - if not video_url or not isinstance(video_url, compat_str): + video_url = url_or_none(encoding.get('videoUrl')) + if not video_url: continue ext = determine_ext(video_url, mimetype2ext(encoding.get('mimeType'))) if ext == 'm3u8': diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index 0c13f54ee..7e0e838f0 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -17,6 +17,7 @@ from ..utils import ( lowercase_escape, std_headers, try_get, + url_or_none, ) @@ -170,7 +171,7 @@ class InstagramIE(InfoExtractor): node = try_get(edge, lambda x: x['node'], dict) if not node: continue - node_video_url = try_get(node, lambda x: x['video_url'], compat_str) + node_video_url = url_or_none(node.get('video_url')) if not node_video_url: continue entries.append({ diff --git a/youtube_dl/extractor/itv.py b/youtube_dl/extractor/itv.py index d05a7b68d..de65b6bb4 100644 --- a/youtube_dl/extractor/itv.py +++ b/youtube_dl/extractor/itv.py @@ -20,6 +20,7 @@ from ..utils import ( merge_dicts, parse_duration, smuggle_url, + url_or_none, xpath_with_ns, xpath_element, xpath_text, @@ -250,8 +251,8 @@ class ITVIE(InfoExtractor): for sub in subs: if not isinstance(sub, dict): continue - href = sub.get('Href') - if isinstance(href, compat_str): + href = url_or_none(sub.get('Href')) + if href: extract_subtitle(href) if not info.get('duration'): info['duration'] = parse_duration(video_data.get('Duration')) diff --git a/youtube_dl/extractor/keezmovies.py b/youtube_dl/extractor/keezmovies.py index d4e6f7ac1..c3eb74c17 100644 --- a/youtube_dl/extractor/keezmovies.py +++ b/youtube_dl/extractor/keezmovies.py @@ -4,16 +4,14 @@ import re from .common import InfoExtractor from ..aes import aes_decrypt_text -from ..compat import ( - compat_str, - compat_urllib_parse_unquote, -) +from ..compat import compat_urllib_parse_unquote from ..utils import ( determine_ext, ExtractorError, int_or_none, str_to_int, strip_or_none, + url_or_none, ) @@ -55,7 +53,8 @@ class KeezMoviesIE(InfoExtractor): encrypted = False def extract_format(format_url, height=None): - if not isinstance(format_url, compat_str) or not format_url.startswith(('http', '//')): + format_url = url_or_none(format_url) + if not format_url or not format_url.startswith(('http', '//')): return if format_url in format_urls: return diff --git a/youtube_dl/extractor/konserthusetplay.py b/youtube_dl/extractor/konserthusetplay.py index c11cbcf47..dd42bb2f2 100644 --- a/youtube_dl/extractor/konserthusetplay.py +++ b/youtube_dl/extractor/konserthusetplay.py @@ -2,11 +2,11 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( determine_ext, float_or_none, int_or_none, + url_or_none, ) @@ -109,7 +109,8 @@ class KonserthusetPlayIE(InfoExtractor): captions = source.get('captionsAvailableLanguages') if isinstance(captions, dict): for lang, subtitle_url in captions.items(): - if lang != 'none' and isinstance(subtitle_url, compat_str): + subtitle_url = url_or_none(subtitle_url) + if lang != 'none' and subtitle_url: subtitles.setdefault(lang, []).append({'url': subtitle_url}) return { diff --git a/youtube_dl/extractor/mediasite.py b/youtube_dl/extractor/mediasite.py index 0e2645c55..84876b883 100644 --- a/youtube_dl/extractor/mediasite.py +++ b/youtube_dl/extractor/mediasite.py @@ -15,6 +15,7 @@ from ..utils import ( mimetype2ext, unescapeHTML, unsmuggle_url, + url_or_none, urljoin, ) @@ -156,8 +157,8 @@ class MediasiteIE(InfoExtractor): stream_formats = [] for unum, VideoUrl in enumerate(video_urls): - video_url = VideoUrl.get('Location') - if not video_url or not isinstance(video_url, compat_str): + video_url = url_or_none(VideoUrl.get('Location')) + if not video_url: continue # XXX: if Stream.get('CanChangeScheme', False), switch scheme to HTTP/HTTPS diff --git a/youtube_dl/extractor/peertube.py b/youtube_dl/extractor/peertube.py index d9849a2ba..e03c3d1d3 100644 --- a/youtube_dl/extractor/peertube.py +++ b/youtube_dl/extractor/peertube.py @@ -10,6 +10,7 @@ from ..utils import ( parse_resolution, try_get, unified_timestamp, + url_or_none, urljoin, ) @@ -200,8 +201,8 @@ class PeerTubeIE(InfoExtractor): for file_ in video['files']: if not isinstance(file_, dict): continue - file_url = file_.get('fileUrl') - if not file_url or not isinstance(file_url, compat_str): + file_url = url_or_none(file_.get('fileUrl')) + if not file_url: continue file_size = int_or_none(file_.get('size')) format_id = try_get( diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py index 879bcf81d..10311a81a 100644 --- a/youtube_dl/extractor/redtube.py +++ b/youtube_dl/extractor/redtube.py @@ -3,12 +3,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( ExtractorError, int_or_none, str_to_int, unified_strdate, + url_or_none, ) @@ -71,8 +71,8 @@ class RedTubeIE(InfoExtractor): video_id, fatal=False) if medias and isinstance(medias, list): for media in medias: - format_url = media.get('videoUrl') - if not format_url or not isinstance(format_url, compat_str): + format_url = url_or_none(media.get('videoUrl')) + if not format_url: continue format_id = media.get('quality') formats.append({ diff --git a/youtube_dl/extractor/rentv.py b/youtube_dl/extractor/rentv.py index 8bcf87126..7c8909d95 100644 --- a/youtube_dl/extractor/rentv.py +++ b/youtube_dl/extractor/rentv.py @@ -6,6 +6,7 @@ from ..compat import compat_str from ..utils import ( determine_ext, int_or_none, + url_or_none, ) @@ -37,8 +38,8 @@ class RENTVIE(InfoExtractor): title = config['title'] formats = [] for video in config['src']: - src = video.get('src') - if not src or not isinstance(src, compat_str): + src = url_or_none(video.get('src')) + if not src: continue ext = determine_ext(src) if ext == 'm3u8': diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index 89d89b65a..261bcbb83 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -16,6 +16,7 @@ from ..utils import ( int_or_none, try_get, unified_timestamp, + url_or_none, ) @@ -176,8 +177,8 @@ class RutubePlaylistBaseIE(RutubeBaseIE): break for result in results: - video_url = result.get('video_url') - if not video_url or not isinstance(video_url, compat_str): + video_url = url_or_none(result.get('video_url')) + if not video_url: continue entry = self._extract_video(result, require_title=False) entry.update({ diff --git a/youtube_dl/extractor/turner.py b/youtube_dl/extractor/turner.py index 2b7b0d6e1..4a6cbfbb8 100644 --- a/youtube_dl/extractor/turner.py +++ b/youtube_dl/extractor/turner.py @@ -15,6 +15,7 @@ from ..utils import ( update_url_query, ExtractorError, strip_or_none, + url_or_none, ) @@ -154,8 +155,8 @@ class TurnerBaseIE(AdobePassIE): subtitles = {} for source in video_data.findall('closedCaptions/source'): for track in source.findall('track'): - track_url = track.get('url') - if not isinstance(track_url, compat_str) or track_url.endswith('/big'): + track_url = url_or_none(track.get('url')) + if not track_url or track_url.endswith('/big'): continue lang = track.get('lang') or track.get('label') or 'en' subtitles.setdefault(lang, []).append({ diff --git a/youtube_dl/extractor/tvnet.py b/youtube_dl/extractor/tvnet.py index 2b2630b91..4222ff9ee 100644 --- a/youtube_dl/extractor/tvnet.py +++ b/youtube_dl/extractor/tvnet.py @@ -4,10 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( int_or_none, unescapeHTML, + url_or_none, ) @@ -106,9 +106,8 @@ class TVNetIE(InfoExtractor): for stream in self._download_json(data_file, video_id): if not isinstance(stream, dict): continue - stream_url = stream.get('url') - if (stream_url in stream_urls or not stream_url or - not isinstance(stream_url, compat_str)): + stream_url = url_or_none(stream.get('url')) + if stream_url in stream_urls or not stream_url: continue stream_urls.add(stream_url) formats.extend(self._extract_m3u8_formats( diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py index e09b5f804..d3adab457 100644 --- a/youtube_dl/extractor/tvplay.py +++ b/youtube_dl/extractor/tvplay.py @@ -19,6 +19,7 @@ from ..utils import ( try_get, unsmuggle_url, update_url_query, + url_or_none, ) @@ -255,7 +256,8 @@ class TVPlayIE(InfoExtractor): quality = qualities(['hls', 'medium', 'high']) formats = [] for format_id, video_url in streams.get('streams', {}).items(): - if not video_url or not isinstance(video_url, compat_str): + video_url = url_or_none(video_url) + if not video_url: continue ext = determine_ext(video_url) if ext == 'f4m': diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index e01f11331..89ee44224 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -27,6 +27,7 @@ from ..utils import ( unified_timestamp, update_url_query, urlencode_postdata, + url_or_none, urljoin, ) @@ -663,8 +664,8 @@ class TwitchClipsIE(TwitchBaseIE): for option in status['quality_options']: if not isinstance(option, dict): continue - source = option.get('source') - if not source or not isinstance(source, compat_str): + source = url_or_none(option.get('source')) + if not source: continue formats.append({ 'url': source, diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py index a7196997e..79c45f80e 100644 --- a/youtube_dl/extractor/udemy.py +++ b/youtube_dl/extractor/udemy.py @@ -20,6 +20,7 @@ from ..utils import ( sanitized_Request, try_get, unescapeHTML, + url_or_none, urlencode_postdata, ) @@ -265,8 +266,8 @@ class UdemyIE(InfoExtractor): if not isinstance(source_list, list): return for source in source_list: - video_url = source.get('file') or source.get('src') - if not video_url or not isinstance(video_url, compat_str): + video_url = url_or_none(source.get('file') or source.get('src')) + if not video_url: continue if source.get('type') == 'application/x-mpegURL' or determine_ext(video_url) == 'm3u8': formats.extend(self._extract_m3u8_formats( @@ -293,8 +294,8 @@ class UdemyIE(InfoExtractor): continue if track.get('kind') != 'captions': continue - src = track.get('src') - if not src or not isinstance(src, compat_str): + src = url_or_none(track.get('src')) + if not src: continue lang = track.get('language') or track.get( 'srclang') or track.get('label') @@ -314,8 +315,8 @@ class UdemyIE(InfoExtractor): for cc in captions: if not isinstance(cc, dict): continue - cc_url = cc.get('url') - if not cc_url or not isinstance(cc_url, compat_str): + cc_url = url_or_none(cc.get('url')) + if not cc_url: continue lang = try_get(cc, lambda x: x['locale']['locale'], compat_str) sub_dict = (automatic_captions if cc.get('source') == 'auto' diff --git a/youtube_dl/extractor/vidme.py b/youtube_dl/extractor/vidme.py index 59adb2377..174e69cd6 100644 --- a/youtube_dl/extractor/vidme.py +++ b/youtube_dl/extractor/vidme.py @@ -3,15 +3,13 @@ from __future__ import unicode_literals import itertools from .common import InfoExtractor -from ..compat import ( - compat_HTTPError, - compat_str, -) +from ..compat import compat_HTTPError from ..utils import ( ExtractorError, int_or_none, float_or_none, parse_iso8601, + url_or_none, ) @@ -166,8 +164,8 @@ class VidmeIE(InfoExtractor): formats = [] for f in video.get('formats', []): - format_url = f.get('uri') - if not format_url or not isinstance(format_url, compat_str): + format_url = url_or_none(f.get('uri')) + if not format_url: continue format_type = f.get('type') if format_type == 'dash': diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 29002b35f..48b5987c2 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -20,6 +20,7 @@ from ..utils import ( str_to_int, unescapeHTML, unified_timestamp, + url_or_none, urlencode_postdata, ) from .dailymotion import DailymotionIE @@ -423,7 +424,8 @@ class VKIE(VKBaseIE): formats = [] for format_id, format_url in data.items(): - if not isinstance(format_url, compat_str) or not format_url.startswith(('http', '//', 'rtmp')): + format_url = url_or_none(format_url) + if not format_url or not format_url.startswith(('http', '//', 'rtmp')): continue if (format_id.startswith(('url', 'cache')) or format_id in ('extra_data', 'live_mp4', 'postlive_mp4')): diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index d1bc992fd..68a48034e 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -13,6 +13,7 @@ from ..utils import ( parse_duration, try_get, unified_strdate, + url_or_none, ) @@ -137,7 +138,8 @@ class XHamsterIE(InfoExtractor): else: format_url = format_item filesize = None - if not isinstance(format_url, compat_str): + format_url = url_or_none(format_url) + if not format_url: continue formats.append({ 'format_id': '%s-%s' % (format_id, quality), @@ -198,7 +200,8 @@ class XHamsterIE(InfoExtractor): default='{}'), video_id, fatal=False) for format_id, format_url in sources.items(): - if not isinstance(format_url, compat_str): + format_url = url_or_none(format_url) + if not format_url: continue if format_url in format_urls: continue diff --git a/youtube_dl/extractor/yapfiles.py b/youtube_dl/extractor/yapfiles.py index 7fafbf596..cfb368de9 100644 --- a/youtube_dl/extractor/yapfiles.py +++ b/youtube_dl/extractor/yapfiles.py @@ -4,12 +4,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( ExtractorError, int_or_none, qualities, unescapeHTML, + url_or_none, ) @@ -80,9 +80,9 @@ class YapFilesIE(InfoExtractor): formats = [] for format_id in QUALITIES: is_hd = format_id == 'hd' - format_url = playlist.get( - 'file%s' % ('_hd' if is_hd else '')) - if not format_url or not isinstance(format_url, compat_str): + format_url = url_or_none(playlist.get( + 'file%s' % ('_hd' if is_hd else ''))) + if not format_url: continue formats.append({ 'url': format_url, diff --git a/youtube_dl/extractor/youjizz.py b/youtube_dl/extractor/youjizz.py index f33fabe19..dff69fcb7 100644 --- a/youtube_dl/extractor/youjizz.py +++ b/youtube_dl/extractor/youjizz.py @@ -3,11 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( determine_ext, int_or_none, parse_duration, + url_or_none, ) @@ -50,8 +50,8 @@ class YouJizzIE(InfoExtractor): for encoding in encodings: if not isinstance(encoding, dict): continue - format_url = encoding.get('filename') - if not isinstance(format_url, compat_str): + format_url = url_or_none(encoding.get('filename')) + if not format_url: continue if determine_ext(format_url) == 'm3u8': formats.extend(self._extract_m3u8_formats( diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index 547adefeb..ea0bce784 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -3,13 +3,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( int_or_none, sanitized_Request, str_to_int, unescapeHTML, unified_strdate, + url_or_none, ) from ..aes import aes_decrypt_text @@ -88,8 +88,8 @@ class YouPornIE(InfoExtractor): for definition in definitions: if not isinstance(definition, dict): continue - video_url = definition.get('videoUrl') - if isinstance(video_url, compat_str) and video_url: + video_url = url_or_none(definition.get('videoUrl')) + if video_url: links.append(video_url) # Fallback #1, this also contains extra low quality 180p format diff --git a/youtube_dl/extractor/zattoo.py b/youtube_dl/extractor/zattoo.py index b5a3a0716..fb167c198 100644 --- a/youtube_dl/extractor/zattoo.py +++ b/youtube_dl/extractor/zattoo.py @@ -13,6 +13,7 @@ from ..utils import ( ExtractorError, int_or_none, try_get, + url_or_none, urlencode_postdata, ) @@ -150,8 +151,8 @@ class ZattooBaseIE(InfoExtractor): for watch in watch_urls: if not isinstance(watch, dict): continue - watch_url = watch.get('url') - if not watch_url or not isinstance(watch_url, compat_str): + watch_url = url_or_none(watch.get('url')) + if not watch_url: continue format_id_list = [stream_type] maxrate = watch.get('maxrate') diff --git a/youtube_dl/extractor/zdf.py b/youtube_dl/extractor/zdf.py index bb9020c91..afa3f6c47 100644 --- a/youtube_dl/extractor/zdf.py +++ b/youtube_dl/extractor/zdf.py @@ -15,6 +15,7 @@ from ..utils import ( try_get, unified_timestamp, update_url_query, + url_or_none, urljoin, ) @@ -67,8 +68,8 @@ class ZDFIE(ZDFBaseIE): def _extract_subtitles(src): subtitles = {} for caption in try_get(src, lambda x: x['captions'], list) or []: - subtitle_url = caption.get('uri') - if subtitle_url and isinstance(subtitle_url, compat_str): + subtitle_url = url_or_none(caption.get('uri')) + if subtitle_url: lang = caption.get('language', 'deu') subtitles.setdefault(lang, []).append({ 'url': subtitle_url, @@ -76,8 +77,8 @@ class ZDFIE(ZDFBaseIE): return subtitles def _extract_format(self, video_id, formats, format_urls, meta): - format_url = meta.get('url') - if not format_url or not isinstance(format_url, compat_str): + format_url = url_or_none(meta.get('url')) + if not format_url: return if format_url in format_urls: return @@ -152,7 +153,8 @@ class ZDFIE(ZDFBaseIE): content, lambda x: x['teaserImageRef']['layouts'], dict) if layouts: for layout_key, layout_url in layouts.items(): - if not isinstance(layout_url, compat_str): + layout_url = url_or_none(layout_url) + if not layout_url: continue thumbnail = { 'url': layout_url, From 6f27998e750d8409f03cce2754ea3e9066b3b794 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 21 Jul 2018 20:58:30 +0700 Subject: [PATCH 090/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/ChangeLog b/ChangeLog index 1d602079e..bda7be4a9 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,26 @@ +version <unreleased> + +Core ++ [utils] Introduce url_or_none +* [utils] Allow JSONP without function name (#17028) ++ [extractor/common] Extract DASH and MSS formats from SMIL manifests + +Extractors ++ [bbc] Add support for BBC Radio Play pages (#17022) +* [iwara] Fix download URLs (#17026) +* [vrtnu] Relax title extraction and extract JSON-LD (#17018) ++ [viu] Pass Referer and Origin headers and area id (#16992) ++ [vimeo] Add another config regular expression (#17013) ++ [facebook] Extract view count (#16942) +* [dailymotion] Improve description extraction (#16984) +* [slutload] Fix and improve extraction (#17001) +* [mediaset] Fix extraction (#16977) ++ [theplatform] Add support for theplatform TLD customization (#16977) +* [imgur] Relax URL regular expression (#16987) +* [pornhub] Improve extraction and extract all formats (#12166, #15891, #16262, + #16959) + + version 2018.07.10 Core From 8e66ffc3b7df8ad78e7f9e2e77d026c84027a814 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 21 Jul 2018 21:00:18 +0700 Subject: [PATCH 091/558] release 2018.07.21 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index f192c6633..24827ba8f 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.07.10*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.07.10** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.07.21*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.07.21** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.07.10 +[debug] youtube-dl version 2018.07.21 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index bda7be4a9..94ecaae8e 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.07.21 Core + [utils] Introduce url_or_none diff --git a/youtube_dl/version.py b/youtube_dl/version.py index c7083cf47..9bf0ea30d 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.07.10' +__version__ = '2018.07.21' From 6de82b44768624b888fd141e009540ff3bed9e6a Mon Sep 17 00:00:00 2001 From: Enes <enessolak99@gmail.com> Date: Tue, 24 Apr 2018 19:02:38 +0300 Subject: [PATCH 092/558] [puhutv] Add extractor (closes #16010) --- youtube_dl/extractor/extractors.py | 4 + youtube_dl/extractor/puhutv.py | 232 +++++++++++++++++++++++++++++ 2 files changed, 236 insertions(+) create mode 100644 youtube_dl/extractor/puhutv.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index c6f8a785a..29fab5b9a 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -860,6 +860,10 @@ from .pornhub import ( from .pornotube import PornotubeIE from .pornovoisines import PornoVoisinesIE from .pornoxo import PornoXOIE +from .puhutv import ( + PuhuTVIE, + PuhuTVSerieIE, +) from .presstv import PressTVIE from .primesharetv import PrimeShareTVIE from .promptfile import PromptFileIE diff --git a/youtube_dl/extractor/puhutv.py b/youtube_dl/extractor/puhutv.py new file mode 100644 index 000000000..8abdab52a --- /dev/null +++ b/youtube_dl/extractor/puhutv.py @@ -0,0 +1,232 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + int_or_none, + float_or_none, + determine_ext, + str_or_none, + url_or_none, + unified_strdate, + unified_timestamp, + try_get, + url_basename, + remove_end +) + + +class PuhuTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?puhutv\.com/(?P<id>[a-z0-9-]+)-izle' + IE_NAME = 'puhutv' + _TESTS = [ + { + # A Film + 'url': 'https://puhutv.com/sut-kardesler-izle', + 'md5': 'a347470371d56e1585d1b2c8dab01c96', + 'info_dict': { + 'id': 'sut-kardesler', + 'display_id': '5085', + 'ext': 'mp4', + 'title': 'Süt Kardeşler', + 'thumbnail': r're:^https?://.*\.jpg$', + 'uploader': 'Arzu Film', + 'description': 'md5:405fd024df916ca16731114eb18e511a', + 'uploader_id': '43', + 'upload_date': '20160729', + 'timestamp': int, + }, + }, + { + # An Episode and geo restricted + 'url': 'https://puhutv.com/jet-sosyete-1-bolum-izle', + 'only_matching': True, + }, + { + # Has subtitle + 'url': 'https://puhutv.com/dip-1-bolum-izle', + 'only_matching': True, + } + ] + _SUBTITLE_LANGS = { + 'English': 'en', + 'Deutsch': 'de', + 'عربى': 'ar' + } + + def _real_extract(self, url): + video_id = self._match_id(url) + info = self._download_json( + 'https://puhutv.com/api/slug/%s-izle' % video_id, video_id)['data'] + + display_id = compat_str(info['id']) + title = info['title']['name'] + if info.get('display_name'): + title = '%s %s' % (title, info.get('display_name')) + + description = try_get(info, lambda x: x['title']['description'], compat_str) or info.get('description') + timestamp = unified_timestamp(info.get('created_at')) + upload_date = unified_strdate(info.get('created_at')) + uploader = try_get(info, lambda x: x['title']['producer']['name'], compat_str) + uploader_id = str_or_none(try_get(info, lambda x: x['title']['producer']['id'])) + view_count = int_or_none(try_get(info, lambda x: x['content']['watch_count'])) + duration = float_or_none(try_get(info, lambda x: x['content']['duration_in_ms']), scale=1000) + thumbnail = try_get(info, lambda x: x['content']['images']['wide']['main'], compat_str) + release_year = int_or_none(try_get(info, lambda x: x['title']['released_at'])) + webpage_url = info.get('web_url') + + season_number = int_or_none(info.get('season_number')) + season_id = int_or_none(info.get('season_id')) + episode_number = int_or_none(info.get('episode_number')) + + tags = [] + for tag in try_get(info, lambda x: x['title']['genres'], list) or []: + if isinstance(tag.get('name'), compat_str): + tags.append(tag.get('name')) + + thumbnails = [] + thumbs_dict = try_get(info, lambda x: x['content']['images']['wide'], dict) or {} + for id, url in thumbs_dict.items(): + if not url_or_none(url): + continue + thumbnails.append({ + 'url': 'https://%s' % url, + 'id': id + }) + + subtitles = {} + for subtitle in try_get(info, lambda x: x['content']['subtitles'], list) or []: + if not isinstance(subtitle, dict): + continue + lang = subtitle.get('language') + sub_url = url_or_none(subtitle.get('url')) + if not lang or not isinstance(lang, compat_str) or not sub_url: + continue + subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = [{ + 'url': sub_url + }] + + # Some of videos are geo restricted upon request copyright owner and returns 403 + req_formats = self._download_json( + 'https://puhutv.com/api/assets/%s/videos' % display_id, + video_id, 'Downloading video JSON') + + formats = [] + for format in req_formats['data']['videos']: + media_url = url_or_none(format.get('url')) + if not media_url: + continue + ext = format.get('video_format') or determine_ext(media_url) + quality = format.get('quality') + if format.get('stream_type') == 'hls' and format.get('is_playlist') is True: + m3u8_id = remove_end(url_basename(media_url), '.m3u8') + formats.append(self._m3u8_meta_format(media_url, ext, m3u8_id=m3u8_id)) + elif ext == 'mp4' and format.get('is_playlist', False) is False: + formats.append({ + 'url': media_url, + 'format_id': 'http-%s' % quality, + 'ext': ext, + 'height': quality + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'season_id': season_id, + 'season_number': season_number, + 'episode_number': episode_number, + 'release_year': release_year, + 'upload_date': upload_date, + 'timestamp': timestamp, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'view_count': view_count, + 'duration': duration, + 'tags': tags, + 'subtitles': subtitles, + 'webpage_url': webpage_url, + 'thumbnail': thumbnail, + 'thumbnails': thumbnails, + 'formats': formats + } + + +class PuhuTVSerieIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?puhutv\.com/(?P<id>[a-z0-9-]+)-detay' + IE_NAME = 'puhutv:serie' + _TESTS = [ + { + 'url': 'https://puhutv.com/deniz-yildizi-detay', + 'info_dict': { + 'title': 'Deniz Yıldızı', + 'id': 'deniz-yildizi', + 'uploader': 'Focus Film', + 'uploader_id': 61, + }, + 'playlist_mincount': 234, + }, + { + # a film detail page which is using same url with serie page + 'url': 'https://puhutv.com/kaybedenler-kulubu-detay', + 'info_dict': { + 'title': 'Kaybedenler Kulübü', + 'id': 'kaybedenler-kulubu', + 'uploader': 'Tolga Örnek, Murat Dörtbudak, Neslihan Dörtbudak, Kemal Kaplanoğlu', + 'uploader_id': 248, + }, + 'playlist_mincount': 1, + }, + ] + + def _extract_entries(self, playlist_id, seasons): + for season in seasons: + season_id = season['id'] + season_number = season.get('position') + pagenum = 1 + has_more = True + while has_more is True: + season_info = self._download_json( + 'https://galadriel.puhutv.com/seasons/%s' % season_id, + playlist_id, 'Downloading season %s page %s' % (season_number, pagenum), query={ + 'page': pagenum, + 'per': 40, + }) + for episode in season_info.get('episodes'): + video_id = episode['slugPath'].replace('-izle', '') + yield self.url_result( + 'https://puhutv.com/%s-izle' % video_id, + PuhuTVIE.ie_key(), video_id) + pagenum = pagenum + 1 + has_more = season_info.get('hasMore', False) + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + info = self._download_json( + 'https://puhutv.com/api/slug/%s-detay' % playlist_id, playlist_id)['data'] + + title = info.get('name') + uploader = try_get(info, lambda x: x['producer']['name'], compat_str) + uploader_id = try_get(info, lambda x: x['producer']['id']) + seasons = info.get('seasons') + if seasons: + entries = self._extract_entries(playlist_id, seasons) + else: + # For films, these are using same url with series + video_id = info['assets'][0]['slug'] + return self.url_result( + 'https://puhutv.com/%s-izle' % video_id, + PuhuTVIE.ie_key(), video_id) + + return { + '_type': 'playlist', + 'id': playlist_id, + 'title': title, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'entries': entries, + } From 8fd2a7be373a29b9bea491f952f14315a90c2f3a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 22 Jul 2018 20:25:46 +0700 Subject: [PATCH 093/558] [puhutv] Improve extraction (closes #16269) --- youtube_dl/extractor/puhutv.py | 313 +++++++++++++++++---------------- 1 file changed, 164 insertions(+), 149 deletions(-) diff --git a/youtube_dl/extractor/puhutv.py b/youtube_dl/extractor/puhutv.py index 8abdab52a..5465e8ab7 100644 --- a/youtube_dl/extractor/puhutv.py +++ b/youtube_dl/extractor/puhutv.py @@ -2,53 +2,54 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_str +from ..compat import ( + compat_HTTPError, + compat_str, +) from ..utils import ( + ExtractorError, int_or_none, float_or_none, - determine_ext, + parse_resolution, str_or_none, - url_or_none, - unified_strdate, - unified_timestamp, try_get, - url_basename, - remove_end + unified_timestamp, + url_or_none, + urljoin, ) class PuhuTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?puhutv\.com/(?P<id>[a-z0-9-]+)-izle' + _VALID_URL = r'https?://(?:www\.)?puhutv\.com/(?P<id>[^/?#&]+)-izle' IE_NAME = 'puhutv' - _TESTS = [ - { - # A Film - 'url': 'https://puhutv.com/sut-kardesler-izle', - 'md5': 'a347470371d56e1585d1b2c8dab01c96', - 'info_dict': { - 'id': 'sut-kardesler', - 'display_id': '5085', - 'ext': 'mp4', - 'title': 'Süt Kardeşler', - 'thumbnail': r're:^https?://.*\.jpg$', - 'uploader': 'Arzu Film', - 'description': 'md5:405fd024df916ca16731114eb18e511a', - 'uploader_id': '43', - 'upload_date': '20160729', - 'timestamp': int, - }, + _TESTS = [{ + # film + 'url': 'https://puhutv.com/sut-kardesler-izle', + 'md5': 'fbd8f2d8e7681f8bcd51b592475a6ae7', + 'info_dict': { + 'id': '5085', + 'display_id': 'sut-kardesler', + 'ext': 'mp4', + 'title': 'Süt Kardeşler', + 'description': 'md5:405fd024df916ca16731114eb18e511a', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 4832.44, + 'creator': 'Arzu Film', + 'timestamp': 1469778212, + 'upload_date': '20160729', + 'release_year': 1976, + 'view_count': int, + 'tags': ['Aile', 'Komedi', 'Klasikler'], }, - { - # An Episode and geo restricted - 'url': 'https://puhutv.com/jet-sosyete-1-bolum-izle', - 'only_matching': True, - }, - { - # Has subtitle - 'url': 'https://puhutv.com/dip-1-bolum-izle', - 'only_matching': True, - } - ] + }, { + # episode, geo restricted, bypassable with --geo-verification-proxy + 'url': 'https://puhutv.com/jet-sosyete-1-bolum-izle', + 'only_matching': True, + }, { + # 4k, with subtitles + 'url': 'https://puhutv.com/dip-1-bolum-izle', + 'only_matching': True, + }] _SUBTITLE_LANGS = { 'English': 'en', 'Deutsch': 'de', @@ -56,47 +57,103 @@ class PuhuTVIE(InfoExtractor): } def _real_extract(self, url): - video_id = self._match_id(url) - info = self._download_json( - 'https://puhutv.com/api/slug/%s-izle' % video_id, video_id)['data'] + display_id = self._match_id(url) - display_id = compat_str(info['id']) - title = info['title']['name'] + info = self._download_json( + urljoin(url, '/api/slug/%s-izle' % display_id), + display_id)['data'] + + video_id = compat_str(info['id']) + title = info.get('name') or info['title']['name'] if info.get('display_name'): title = '%s %s' % (title, info.get('display_name')) - description = try_get(info, lambda x: x['title']['description'], compat_str) or info.get('description') + try: + videos = self._download_json( + 'https://puhutv.com/api/assets/%s/videos' % video_id, + display_id, 'Downloading video JSON', + headers=self.geo_verification_headers()) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + self.raise_geo_restricted() + raise + + formats = [] + for video in videos['data']['videos']: + media_url = url_or_none(video.get('url')) + if not media_url: + continue + playlist = video.get('is_playlist') + if video.get('stream_type') == 'hls' and playlist is True: + formats.extend(self._extract_m3u8_formats( + media_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + continue + quality = int_or_none(video.get('quality')) + f = { + 'url': media_url, + 'ext': 'mp4', + 'height': quality + } + video_format = video.get('video_format') + if video_format == 'hls' and playlist is False: + format_id = 'hls' + f['protocol'] = 'm3u8_native' + elif video_format == 'mp4': + format_id = 'http' + + else: + continue + if quality: + format_id += '-%sp' % quality + f['format_id'] = format_id + formats.append(f) + self._sort_formats(formats) + + description = try_get( + info, lambda x: x['title']['description'], + compat_str) or info.get('description') timestamp = unified_timestamp(info.get('created_at')) - upload_date = unified_strdate(info.get('created_at')) - uploader = try_get(info, lambda x: x['title']['producer']['name'], compat_str) - uploader_id = str_or_none(try_get(info, lambda x: x['title']['producer']['id'])) - view_count = int_or_none(try_get(info, lambda x: x['content']['watch_count'])) - duration = float_or_none(try_get(info, lambda x: x['content']['duration_in_ms']), scale=1000) - thumbnail = try_get(info, lambda x: x['content']['images']['wide']['main'], compat_str) - release_year = int_or_none(try_get(info, lambda x: x['title']['released_at'])) - webpage_url = info.get('web_url') + creator = try_get( + info, lambda x: x['title']['producer']['name'], compat_str) + + duration = float_or_none( + try_get(info, lambda x: x['content']['duration_in_ms'], int), + scale=1000) + view_count = try_get(info, lambda x: x['content']['watch_count'], int) + + images = try_get( + info, lambda x: x['content']['images']['wide'], dict) or {} + thumbnails = [] + for image_id, image_url in images.items(): + if not isinstance(image_url, compat_str): + continue + if not image_url.startswith(('http', '//')): + image_url = 'https://%s' % image_url + t = parse_resolution(image_id) + t.update({ + 'id': image_id, + 'url': image_url + }) + thumbnails.append(t) + + release_year = try_get(info, lambda x: x['title']['released_at'], int) season_number = int_or_none(info.get('season_number')) - season_id = int_or_none(info.get('season_id')) + season_id = str_or_none(info.get('season_id')) episode_number = int_or_none(info.get('episode_number')) tags = [] - for tag in try_get(info, lambda x: x['title']['genres'], list) or []: - if isinstance(tag.get('name'), compat_str): - tags.append(tag.get('name')) - - thumbnails = [] - thumbs_dict = try_get(info, lambda x: x['content']['images']['wide'], dict) or {} - for id, url in thumbs_dict.items(): - if not url_or_none(url): + for genre in try_get(info, lambda x: x['title']['genres'], list) or []: + if not isinstance(genre, dict): continue - thumbnails.append({ - 'url': 'https://%s' % url, - 'id': id - }) + genre_name = genre.get('name') + if genre_name and isinstance(genre_name, compat_str): + tags.append(genre_name) subtitles = {} - for subtitle in try_get(info, lambda x: x['content']['subtitles'], list) or []: + for subtitle in try_get( + info, lambda x: x['content']['subtitles'], list) or []: if not isinstance(subtitle, dict): continue lang = subtitle.get('language') @@ -107,30 +164,6 @@ class PuhuTVIE(InfoExtractor): 'url': sub_url }] - # Some of videos are geo restricted upon request copyright owner and returns 403 - req_formats = self._download_json( - 'https://puhutv.com/api/assets/%s/videos' % display_id, - video_id, 'Downloading video JSON') - - formats = [] - for format in req_formats['data']['videos']: - media_url = url_or_none(format.get('url')) - if not media_url: - continue - ext = format.get('video_format') or determine_ext(media_url) - quality = format.get('quality') - if format.get('stream_type') == 'hls' and format.get('is_playlist') is True: - m3u8_id = remove_end(url_basename(media_url), '.m3u8') - formats.append(self._m3u8_meta_format(media_url, ext, m3u8_id=m3u8_id)) - elif ext == 'mp4' and format.get('is_playlist', False) is False: - formats.append({ - 'url': media_url, - 'format_id': 'http-%s' % quality, - 'ext': ext, - 'height': quality - }) - self._sort_formats(formats) - return { 'id': video_id, 'display_id': display_id, @@ -140,93 +173,75 @@ class PuhuTVIE(InfoExtractor): 'season_number': season_number, 'episode_number': episode_number, 'release_year': release_year, - 'upload_date': upload_date, 'timestamp': timestamp, - 'uploader': uploader, - 'uploader_id': uploader_id, + 'creator': creator, 'view_count': view_count, 'duration': duration, 'tags': tags, 'subtitles': subtitles, - 'webpage_url': webpage_url, - 'thumbnail': thumbnail, 'thumbnails': thumbnails, 'formats': formats } class PuhuTVSerieIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?puhutv\.com/(?P<id>[a-z0-9-]+)-detay' + _VALID_URL = r'https?://(?:www\.)?puhutv\.com/(?P<id>[^/?#&]+)-detay' IE_NAME = 'puhutv:serie' - _TESTS = [ - { - 'url': 'https://puhutv.com/deniz-yildizi-detay', - 'info_dict': { - 'title': 'Deniz Yıldızı', - 'id': 'deniz-yildizi', - 'uploader': 'Focus Film', - 'uploader_id': 61, - }, - 'playlist_mincount': 234, + _TESTS = [{ + 'url': 'https://puhutv.com/deniz-yildizi-detay', + 'info_dict': { + 'title': 'Deniz Yıldızı', + 'id': 'deniz-yildizi', }, - { - # a film detail page which is using same url with serie page - 'url': 'https://puhutv.com/kaybedenler-kulubu-detay', - 'info_dict': { - 'title': 'Kaybedenler Kulübü', - 'id': 'kaybedenler-kulubu', - 'uploader': 'Tolga Örnek, Murat Dörtbudak, Neslihan Dörtbudak, Kemal Kaplanoğlu', - 'uploader_id': 248, - }, - 'playlist_mincount': 1, - }, - ] + 'playlist_mincount': 205, + }, { + # a film detail page which is using same url with serie page + 'url': 'https://puhutv.com/kaybedenler-kulubu-detay', + 'only_matching': True, + }] - def _extract_entries(self, playlist_id, seasons): + def _extract_entries(self, seasons): for season in seasons: - season_id = season['id'] - season_number = season.get('position') - pagenum = 1 + season_id = season.get('id') + if not season_id: + continue + page = 1 has_more = True while has_more is True: - season_info = self._download_json( + season = self._download_json( 'https://galadriel.puhutv.com/seasons/%s' % season_id, - playlist_id, 'Downloading season %s page %s' % (season_number, pagenum), query={ - 'page': pagenum, + season_id, 'Downloading page %s' % page, query={ + 'page': page, 'per': 40, }) - for episode in season_info.get('episodes'): - video_id = episode['slugPath'].replace('-izle', '') - yield self.url_result( - 'https://puhutv.com/%s-izle' % video_id, - PuhuTVIE.ie_key(), video_id) - pagenum = pagenum + 1 - has_more = season_info.get('hasMore', False) + episodes = season.get('episodes') + if isinstance(episodes, list): + for ep in episodes: + slug_path = str_or_none(ep.get('slugPath')) + if not slug_path: + continue + video_id = str_or_none(int_or_none(ep.get('id'))) + yield self.url_result( + 'https://puhutv.com/%s' % slug_path, + ie=PuhuTVIE.ie_key(), video_id=video_id, + video_title=ep.get('name') or ep.get('eventLabel')) + page += 1 + has_more = season.get('hasMore') def _real_extract(self, url): playlist_id = self._match_id(url) info = self._download_json( - 'https://puhutv.com/api/slug/%s-detay' % playlist_id, playlist_id)['data'] + urljoin(url, '/api/slug/%s-detay' % playlist_id), + playlist_id)['data'] - title = info.get('name') - uploader = try_get(info, lambda x: x['producer']['name'], compat_str) - uploader_id = try_get(info, lambda x: x['producer']['id']) seasons = info.get('seasons') if seasons: - entries = self._extract_entries(playlist_id, seasons) - else: - # For films, these are using same url with series - video_id = info['assets'][0]['slug'] - return self.url_result( - 'https://puhutv.com/%s-izle' % video_id, - PuhuTVIE.ie_key(), video_id) + return self.playlist_result( + self._extract_entries(seasons), playlist_id, info.get('name')) - return { - '_type': 'playlist', - 'id': playlist_id, - 'title': title, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'entries': entries, - } + # For films, these are using same url with series + video_id = info.get('slug') or info['assets'][0]['slug'] + return self.url_result( + 'https://puhutv.com/%s-izle' % video_id, + PuhuTVIE.ie_key(), video_id) From a702056fbe0e4dc615ebc73d6891c505cd7d818f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 22 Jul 2018 21:26:12 +0700 Subject: [PATCH 094/558] Credit @bastiandg for #16189 --- AUTHORS | 1 + 1 file changed, 1 insertion(+) diff --git a/AUTHORS b/AUTHORS index eaf96d79d..c9f7189ac 100644 --- a/AUTHORS +++ b/AUTHORS @@ -239,3 +239,4 @@ Martin Weinelt Surya Oktafendri TingPing Alexandre Macabies +Bastian de Groot From 7930f914949cbf28aa522463a22f0eea396875bf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 22 Jul 2018 21:27:28 +0700 Subject: [PATCH 095/558] Credit @haasn for #16326 --- AUTHORS | 1 + 1 file changed, 1 insertion(+) diff --git a/AUTHORS b/AUTHORS index c9f7189ac..9b9fff3c3 100644 --- a/AUTHORS +++ b/AUTHORS @@ -240,3 +240,4 @@ Surya Oktafendri TingPing Alexandre Macabies Bastian de Groot +Niklas Haas From d94fb1225edc546f81f4b01b2eebcc9e4cd89313 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 22 Jul 2018 21:29:25 +0700 Subject: [PATCH 096/558] Credit @dnet for #16174 --- AUTHORS | 1 + 1 file changed, 1 insertion(+) diff --git a/AUTHORS b/AUTHORS index 9b9fff3c3..0b23f4066 100644 --- a/AUTHORS +++ b/AUTHORS @@ -241,3 +241,4 @@ TingPing Alexandre Macabies Bastian de Groot Niklas Haas +András Veres-Szentkirályi From 694079dff754e72e8b3b6c1395f1e9b8e9a66db7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 22 Jul 2018 21:31:46 +0700 Subject: [PATCH 097/558] Credit @mrfade for #16269 and #16271 --- AUTHORS | 1 + 1 file changed, 1 insertion(+) diff --git a/AUTHORS b/AUTHORS index 0b23f4066..af8accb51 100644 --- a/AUTHORS +++ b/AUTHORS @@ -242,3 +242,4 @@ Alexandre Macabies Bastian de Groot Niklas Haas András Veres-Szentkirályi +Enes Solak From a789d1cc90055aeefa4a2dafb4a81fcf43b65bb5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 22 Jul 2018 21:34:34 +0700 Subject: [PATCH 098/558] Credit @nathanrossi for #16554 --- AUTHORS | 1 + 1 file changed, 1 insertion(+) diff --git a/AUTHORS b/AUTHORS index af8accb51..c2f48668b 100644 --- a/AUTHORS +++ b/AUTHORS @@ -243,3 +243,4 @@ Bastian de Groot Niklas Haas András Veres-Szentkirályi Enes Solak +Nathan Rossi From 234a85858cd50d6c88848c2e0ceffeabe26306e4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 22 Jul 2018 21:35:38 +0700 Subject: [PATCH 099/558] Credit @tmsbrg for #15462 --- AUTHORS | 1 + 1 file changed, 1 insertion(+) diff --git a/AUTHORS b/AUTHORS index c2f48668b..58b695784 100644 --- a/AUTHORS +++ b/AUTHORS @@ -244,3 +244,4 @@ Niklas Haas András Veres-Szentkirályi Enes Solak Nathan Rossi +Thomas van der Berg From d4e7065111b1c18bc47795b102a4e5c6757e9bad Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 22 Jul 2018 21:36:58 +0700 Subject: [PATCH 100/558] Credit @Kerruba for #16328 --- AUTHORS | 1 + 1 file changed, 1 insertion(+) diff --git a/AUTHORS b/AUTHORS index 58b695784..b507cb8df 100644 --- a/AUTHORS +++ b/AUTHORS @@ -245,3 +245,4 @@ András Veres-Szentkirályi Enes Solak Nathan Rossi Thomas van der Berg +Luca Cherubin From 631f93ee2d5dfe5a90da38d293159670ada4d95e Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 23 Jul 2018 06:20:00 +0100 Subject: [PATCH 101/558] [facebook] fix tahoe request for authenticated users(closes #16655) --- youtube_dl/extractor/facebook.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index f78479b92..97cfe0fc3 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -355,7 +355,6 @@ class FacebookIE(InfoExtractor): tahoe_data = self._download_webpage( self._VIDEO_PAGE_TAHOE_TEMPLATE % video_id, video_id, data=urlencode_postdata({ - '__user': 0, '__a': 1, '__pc': self._search_regex( r'pkg_cohort["\']\s*:\s*["\'](.+?)["\']', webpage, @@ -363,6 +362,9 @@ class FacebookIE(InfoExtractor): '__rev': self._search_regex( r'client_revision["\']\s*:\s*(\d+),', webpage, 'client revision', default='3944515'), + 'fb_dtsg': self._search_regex( + r'"DTSGInitialData"\s*,\s*\[\]\s*,\s*{\s*"token"\s*:\s*"([^"]+)"', + webpage, 'dtsg token', default=''), }), headers={ 'Content-Type': 'application/x-www-form-urlencoded', From b5dec62ca688f35feac1f56415355e9a8e850edb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 25 Jul 2018 23:07:12 +0700 Subject: [PATCH 102/558] [streamcloud] Fix extraction (closes #17054) --- youtube_dl/extractor/streamcloud.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/youtube_dl/extractor/streamcloud.py b/youtube_dl/extractor/streamcloud.py index 6a6bb90c4..4a410611d 100644 --- a/youtube_dl/extractor/streamcloud.py +++ b/youtube_dl/extractor/streamcloud.py @@ -72,4 +72,7 @@ class StreamcloudIE(InfoExtractor): 'title': title, 'url': video_url, 'thumbnail': thumbnail, + 'http_headers': { + 'Referer': url, + }, } From ad1bc71a8a448583734b313bc77a2097200ad97b Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 26 Jul 2018 07:24:46 +0100 Subject: [PATCH 103/558] [vk] fix extraction for inline only videos(fixes #16923) --- youtube_dl/extractor/vk.py | 40 +++++++++++++++++++++++++------------- 1 file changed, 26 insertions(+), 14 deletions(-) diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 48b5987c2..ef8b9bcb7 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -17,6 +17,7 @@ from ..utils import ( int_or_none, orderedSet, remove_start, + str_or_none, str_to_int, unescapeHTML, unified_timestamp, @@ -106,10 +107,10 @@ class VKIE(VKBaseIE): 'ext': 'mp4', 'title': 'ProtivoGunz - Хуёвая песня', 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*', + 'uploader_id': '-77521', 'duration': 195, - 'timestamp': 1329060660, + 'timestamp': 1329049880, 'upload_date': '20120212', - 'view_count': int, }, }, { @@ -118,12 +119,12 @@ class VKIE(VKBaseIE): 'info_dict': { 'id': '165548505', 'ext': 'mp4', - 'uploader': 'Tom Cruise', 'title': 'No name', + 'uploader': 'Tom Cruise', + 'uploader_id': '205387401', 'duration': 9, - 'timestamp': 1374374880, - 'upload_date': '20130721', - 'view_count': int, + 'timestamp': 1374364108, + 'upload_date': '20130720', } }, { @@ -207,10 +208,10 @@ class VKIE(VKBaseIE): 'id': 'V3K4mi0SYkc', 'ext': 'webm', 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate", - 'description': 'md5:d9903938abdc74c738af77f527ca0596', - 'duration': 178, + 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a', + 'duration': 179, 'upload_date': '20130116', - 'uploader': "Children's Joy Foundation", + 'uploader': "Children's Joy Foundation Inc.", 'uploader_id': 'thecjf', 'view_count': int, }, @@ -222,6 +223,7 @@ class VKIE(VKBaseIE): 'id': 'k3lz2cmXyRuJQSjGHUv', 'ext': 'mp4', 'title': 'md5:d52606645c20b0ddbb21655adaa4f56f', + # TODO: fix test by fixing dailymotion description extraction 'description': 'md5:c651358f03c56f1150b555c26d90a0fd', 'uploader': 'AniLibria.Tv', 'upload_date': '20160914', @@ -241,9 +243,12 @@ class VKIE(VKBaseIE): 'ext': 'mp4', 'title': 'S-Dance, репетиции к The way show', 'uploader': 'THE WAY SHOW | 17 апреля', - 'timestamp': 1454870100, + 'uploader_id': '-110305615', + 'timestamp': 1454859345, 'upload_date': '20160207', - 'view_count': int, + }, + 'params': { + 'skip_download': True, }, }, { @@ -296,7 +301,7 @@ class VKIE(VKBaseIE): video_id = mobj.group('videoid') if video_id: - info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id + info_url = 'https://vk.com/al_video.php?act=show_inline&al=1&video=' + video_id # Some videos (removed?) can only be downloaded with list id specified list_id = mobj.group('list_id') if list_id: @@ -346,6 +351,9 @@ class VKIE(VKBaseIE): r'<!>This video is no longer available, because its author has been blocked.': 'Video %s is no longer available, because its author has been blocked.', + + r'<!>This video is no longer available, because it has been deleted.': + 'Video %s is no longer available, because it has been deleted.', } for error_re, error_msg in ERRORS.items(): @@ -394,7 +402,8 @@ class VKIE(VKBaseIE): if not data: data = self._parse_json( self._search_regex( - r'<!json>\s*({.+?})\s*<!>', info_page, 'json', default='{}'), + [r'<!json>\s*({.+?})\s*<!>', r'<!json>\s*({.+})'], + info_page, 'json', default='{}'), video_id) if data: data = data['player']['params'][0] @@ -416,7 +425,7 @@ class VKIE(VKBaseIE): timestamp = unified_timestamp(self._html_search_regex( r'class=["\']mv_info_date[^>]+>([^<]+)(?:<|from)', info_page, - 'upload date', fatal=False)) + 'upload date', default=None)) or int_or_none(data.get('date')) view_count = str_to_int(self._search_regex( r'class=["\']mv_views_count[^>]+>\s*([\d,.]+)', @@ -454,9 +463,12 @@ class VKIE(VKBaseIE): 'title': title, 'thumbnail': data.get('jpg'), 'uploader': data.get('md_author'), + 'uploader_id': str_or_none(data.get('author_id')), 'duration': data.get('duration'), 'timestamp': timestamp, 'view_count': view_count, + 'like_count': int_or_none(data.get('liked')), + 'dislike_count': int_or_none(data.get('nolikes')), 'is_live': is_live, } From 0c7b4f49eb07bb68918da3dd7ff277565273033f Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 26 Jul 2018 08:11:06 +0100 Subject: [PATCH 104/558] [rai] return non http relinker URL intact(closes #17055) --- youtube_dl/extractor/rai.py | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py index d22311031..f916b2619 100644 --- a/youtube_dl/extractor/rai.py +++ b/youtube_dl/extractor/rai.py @@ -32,6 +32,9 @@ class RaiBaseIE(InfoExtractor): _GEO_BYPASS = False def _extract_relinker_info(self, relinker_url, video_id): + if not re.match(r'https?://', relinker_url): + return {'formats': [{'url': relinker_url}]} + formats = [] geoprotection = None is_live = None @@ -369,6 +372,10 @@ class RaiIE(RaiBaseIE): 'params': { 'skip_download': True, }, + }, { + # Direct MMS URL + 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-b63a4089-ac28-48cf-bca5-9f5b5bc46df5.html', + 'only_matching': True, }] def _extract_from_content_id(self, content_id, url): From 722f1a0f8f82617b3abf646b2d0df2c624e98912 Mon Sep 17 00:00:00 2001 From: Sidney de Koning <sidney.dekoning@gmail.com> Date: Fri, 27 Jul 2018 19:18:41 +0200 Subject: [PATCH 105/558] [README.md] Actualize Firefox cookie export add-on Previous one does not work with newer Firefox versions --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 6d49d6a4f..dd068a462 100644 --- a/README.md +++ b/README.md @@ -870,7 +870,7 @@ Either prepend `https://www.youtube.com/watch?v=` or separate the ID from the op Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`. -In order to extract cookies from browser use any conforming browser extension for exporting cookies. For example, [cookies.txt](https://chrome.google.com/webstore/detail/cookiestxt/njabckikapfpffapmjgojcnbfjonfjfg) (for Chrome) or [Export Cookies](https://addons.mozilla.org/en-US/firefox/addon/export-cookies/) (for Firefox). +In order to extract cookies from browser use any conforming browser extension for exporting cookies. For example, [cookies.txt](https://chrome.google.com/webstore/detail/cookiestxt/njabckikapfpffapmjgojcnbfjonfjfg) (for Chrome) or [cookies.txt](https://addons.mozilla.org/en-US/firefox/addon/cookies-txt/) (for Firefox). Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows and `LF` (`\n`) for Unix and Unix-like systems (Linux, macOS, etc.). `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format. From 8e37a7e4cce7555c12b8d9f7a1d331476aba357c Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 28 Jul 2018 06:52:36 +0100 Subject: [PATCH 106/558] [mitele] reduce number of requests and update tests --- youtube_dl/extractor/mitele.py | 109 +++------------------------------ 1 file changed, 10 insertions(+), 99 deletions(-) diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py index 42759eae8..40f214a87 100644 --- a/youtube_dl/extractor/mitele.py +++ b/youtube_dl/extractor/mitele.py @@ -1,84 +1,14 @@ # coding: utf-8 from __future__ import unicode_literals -import json -import uuid - from .common import InfoExtractor -from .ooyala import OoyalaIE -from ..compat import ( - compat_str, - compat_urlparse, -) from ..utils import ( int_or_none, - extract_attributes, - determine_ext, smuggle_url, parse_duration, ) -class MiTeleBaseIE(InfoExtractor): - def _get_player_info(self, url, webpage): - player_data = extract_attributes(self._search_regex( - r'(?s)(<ms-video-player.+?</ms-video-player>)', - webpage, 'ms video player')) - video_id = player_data['data-media-id'] - if player_data.get('data-cms-id') == 'ooyala': - return self.url_result( - 'ooyala:%s' % video_id, ie=OoyalaIE.ie_key(), video_id=video_id) - config_url = compat_urlparse.urljoin(url, player_data['data-config']) - config = self._download_json( - config_url, video_id, 'Downloading config JSON') - mmc_url = config['services']['mmc'] - - duration = None - formats = [] - for m_url in (mmc_url, mmc_url.replace('/flash.json', '/html5.json')): - mmc = self._download_json( - m_url, video_id, 'Downloading mmc JSON') - if not duration: - duration = int_or_none(mmc.get('duration')) - for location in mmc['locations']: - gat = self._proto_relative_url(location.get('gat'), 'http:') - gcp = location.get('gcp') - ogn = location.get('ogn') - if None in (gat, gcp, ogn): - continue - token_data = { - 'gcp': gcp, - 'ogn': ogn, - 'sta': 0, - } - media = self._download_json( - gat, video_id, data=json.dumps(token_data).encode('utf-8'), - headers={ - 'Content-Type': 'application/json;charset=utf-8', - 'Referer': url, - }) - stream = media.get('stream') or media.get('file') - if not stream: - continue - ext = determine_ext(stream) - if ext == 'f4m': - formats.extend(self._extract_f4m_formats( - stream + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18', - video_id, f4m_id='hds', fatal=False)) - elif ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - stream, video_id, 'mp4', 'm3u8_native', - m3u8_id='hls', fatal=False)) - self._sort_formats(formats) - - return { - 'id': video_id, - 'formats': formats, - 'thumbnail': player_data.get('data-poster') or config.get('poster', {}).get('imageUrl'), - 'duration': duration, - } - - class MiTeleIE(InfoExtractor): IE_DESC = 'mitele.es' _VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/)+(?P<id>[^/]+)/player' @@ -86,7 +16,7 @@ class MiTeleIE(InfoExtractor): _TESTS = [{ 'url': 'http://www.mitele.es/programas-tv/diario-de/57b0dfb9c715da65618b4afa/player', 'info_dict': { - 'id': '57b0dfb9c715da65618b4afa', + 'id': 'FhYW1iNTE6J6H7NkQRIEzfne6t2quqPg', 'ext': 'mp4', 'title': 'Tor, la web invisible', 'description': 'md5:3b6fce7eaa41b2d97358726378d9369f', @@ -104,7 +34,7 @@ class MiTeleIE(InfoExtractor): # no explicit title 'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/57b0de3dc915da14058b4876/player', 'info_dict': { - 'id': '57b0de3dc915da14058b4876', + 'id': 'oyNG1iNTE6TAPP-JmCjbwfwJqqMMX3Vq', 'ext': 'mp4', 'title': 'Cuarto Milenio Temporada 6 Programa 226', 'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f', @@ -128,40 +58,21 @@ class MiTeleIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - gigya_url = self._search_regex( - r'<gigya-api>[^>]*</gigya-api>[^>]*<script\s+src="([^"]*)">[^>]*</script>', - webpage, 'gigya', default=None) - gigya_sc = self._download_webpage( - compat_urlparse.urljoin('http://www.mitele.es/', gigya_url), - video_id, 'Downloading gigya script') - - # Get a appKey/uuid for getting the session key - appKey = self._search_regex( - r'constant\s*\(\s*["\']_appGridApplicationKey["\']\s*,\s*["\']([0-9a-f]+)', - gigya_sc, 'appKey') - - session_json = self._download_json( - 'https://appgrid-api.cloud.accedo.tv/session', - video_id, 'Downloading session keys', query={ - 'appKey': appKey, - 'uuid': compat_str(uuid.uuid4()), - }) paths = self._download_json( - 'https://appgrid-api.cloud.accedo.tv/metadata/general_configuration,%20web_configuration', - video_id, 'Downloading paths JSON', - query={'sessionKey': compat_str(session_json['sessionKey'])}) + 'https://www.mitele.es/amd/agp/web/metadata/general_configuration', + video_id, 'Downloading paths JSON') ooyala_s = paths['general_configuration']['api_configuration']['ooyala_search'] + base_url = ooyala_s.get('base_url', 'cdn-search-mediaset.carbyne.ps.ooyala.com') + full_path = ooyala_s.get('full_path', '/search/v1/full/providers/') source = self._download_json( - 'http://%s%s%s/docs/%s' % ( - ooyala_s['base_url'], ooyala_s['full_path'], - ooyala_s['provider_id'], video_id), + '%s://%s%s%s/docs/%s' % ( + ooyala_s.get('protocol', 'https'), base_url, full_path, + ooyala_s.get('provider_id', '104951'), video_id), video_id, 'Downloading data JSON', query={ 'include_titles': 'Series,Season', - 'product_name': 'test', + 'product_name': ooyala_s.get('product_name', 'test'), 'format': 'full', })['hits']['hits'][0]['_source'] From a098c99f0d0deb4ad0d5c9b67496582d89970368 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 28 Jul 2018 06:55:18 +0100 Subject: [PATCH 107/558] [telecinco] fix extraction(closes #17080) --- youtube_dl/extractor/telecinco.py | 122 ++++++++++++++++++++++++++---- 1 file changed, 106 insertions(+), 16 deletions(-) diff --git a/youtube_dl/extractor/telecinco.py b/youtube_dl/extractor/telecinco.py index fdcc7d573..d37e1b055 100644 --- a/youtube_dl/extractor/telecinco.py +++ b/youtube_dl/extractor/telecinco.py @@ -1,26 +1,43 @@ # coding: utf-8 from __future__ import unicode_literals -from .mitele import MiTeleBaseIE +import json +import re + +from .common import InfoExtractor +from .ooyala import OoyalaIE +from ..utils import ( + clean_html, + determine_ext, + int_or_none, + str_or_none, + urljoin, +) -class TelecincoIE(MiTeleBaseIE): +class TelecincoIE(InfoExtractor): IE_DESC = 'telecinco.es, cuatro.com and mediaset.es' _VALID_URL = r'https?://(?:www\.)?(?:telecinco\.es|cuatro\.com|mediaset\.es)/(?:[^/]+/)+(?P<id>.+?)\.html' _TESTS = [{ 'url': 'http://www.telecinco.es/robinfood/temporada-01/t01xp14/Bacalao-cocochas-pil-pil_0_1876350223.html', - 'md5': '8d7b2d5f699ee2709d992a63d5cd1712', 'info_dict': { - 'id': 'JEA5ijCnF6p5W08A1rNKn7', - 'ext': 'mp4', + 'id': '1876350223', 'title': 'Bacalao con kokotxas al pil-pil', 'description': 'md5:1382dacd32dd4592d478cbdca458e5bb', - 'duration': 662, }, + 'playlist': [{ + 'md5': 'adb28c37238b675dad0f042292f209a7', + 'info_dict': { + 'id': 'JEA5ijCnF6p5W08A1rNKn7', + 'ext': 'mp4', + 'title': 'Con Martín Berasategui, hacer un bacalao al pil-pil es fácil y divertido', + 'duration': 662, + }, + }] }, { 'url': 'http://www.cuatro.com/deportes/futbol/barcelona/Leo_Messi-Champions-Roma_2_2052780128.html', - 'md5': '284393e5387b3b947b77c613ef04749a', + 'md5': '9468140ebc300fbb8b9d65dc6e5c4b43', 'info_dict': { 'id': 'jn24Od1zGLG4XUZcnUnZB6', 'ext': 'mp4', @@ -30,7 +47,7 @@ class TelecincoIE(MiTeleBaseIE): }, }, { 'url': 'http://www.mediaset.es/12meses/campanas/doylacara/conlatratanohaytrato/Ayudame-dar-cara-trata-trato_2_1986630220.html', - 'md5': '749afab6ea5a136a8806855166ae46a2', + 'md5': 'ae2dc6b7b50b2392076a51c0f70e01f6', 'info_dict': { 'id': 'aywerkD2Sv1vGNqq9b85Q2', 'ext': 'mp4', @@ -50,17 +67,90 @@ class TelecincoIE(MiTeleBaseIE): 'only_matching': True, }] + def _parse_content(self, content, url): + video_id = content['dataMediaId'] + if content.get('dataCmsId') == 'ooyala': + return self.url_result( + 'ooyala:%s' % video_id, OoyalaIE.ie_key(), video_id) + config_url = urljoin(url, content['dataConfig']) + config = self._download_json( + config_url, video_id, 'Downloading config JSON') + title = config['info']['title'] + + def mmc_url(mmc_type): + return re.sub( + r'/(?:flash|html5)\.json', '/%s.json' % mmc_type, + config['services']['mmc']) + + duration = None + formats = [] + for mmc_type in ('flash', 'html5'): + mmc = self._download_json( + mmc_url(mmc_type), video_id, + 'Downloading %s mmc JSON' % mmc_type, fatal=False) + if not mmc: + continue + if not duration: + duration = int_or_none(mmc.get('duration')) + for location in mmc['locations']: + gat = self._proto_relative_url(location.get('gat'), 'http:') + gcp = location.get('gcp') + ogn = location.get('ogn') + if None in (gat, gcp, ogn): + continue + token_data = { + 'gcp': gcp, + 'ogn': ogn, + 'sta': 0, + } + media = self._download_json( + gat, video_id, data=json.dumps(token_data).encode('utf-8'), + headers={ + 'Content-Type': 'application/json;charset=utf-8', + 'Referer': url, + }, fatal=False) or {} + stream = media.get('stream') or media.get('file') + if not stream: + continue + ext = determine_ext(stream) + if ext == 'f4m': + formats.extend(self._extract_f4m_formats( + stream + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18', + video_id, f4m_id='hds', fatal=False)) + elif ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + stream, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': content.get('dataPoster') or config.get('poster', {}).get('imageUrl'), + 'duration': duration, + } + def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - title = self._html_search_meta( - ['og:title', 'twitter:title'], webpage, 'title') - info = self._get_player_info(url, webpage) + article = self._parse_json(self._search_regex( + r'window\.\$REACTBASE_STATE\.article\s*=\s*({.+})', + webpage, 'article'), display_id)['article'] + title = article.get('title') + description = clean_html(article.get('leadParagraph')) + if article.get('editorialType') != 'VID': + entries = [] + for p in article.get('body', []): + content = p.get('content') + if p.get('type') != 'video' or not content: + continue + entries.append(self._parse_content(content, url)) + return self.playlist_result( + entries, str_or_none(article.get('id')), title, description) + content = article['opening']['content'] + info = self._parse_content(content, url) info.update({ - 'display_id': display_id, - 'title': title, - 'description': self._html_search_meta( - ['og:description', 'twitter:description'], - webpage, 'title', fatal=False), + 'description': description, }) return info From 9a984265b90eb0e8a7c26a1edf479fbfcebce0a5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 28 Jul 2018 21:26:23 +0700 Subject: [PATCH 108/558] [ted] Fix extraction for videos without nativeDownloads (closes #16756, closes #17085) --- youtube_dl/extractor/ted.py | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index 06a27fd04..dc9c5ce8e 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -107,6 +107,19 @@ class TEDIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + # no nativeDownloads + 'url': 'https://www.ted.com/talks/tom_thum_the_orchestra_in_my_mouth', + 'info_dict': { + 'id': '1792', + 'ext': 'mp4', + 'title': 'The orchestra in my mouth', + 'description': 'md5:5d1d78650e2f8dfcbb8ebee2951ac29a', + 'uploader': 'Tom Thum', + }, + 'params': { + 'skip_download': True, + }, }] _NATIVE_FORMATS = { @@ -180,8 +193,10 @@ class TEDIE(InfoExtractor): } native_downloads = try_get( - talk_info, lambda x: x['downloads']['nativeDownloads'], - dict) or talk_info['nativeDownloads'] + talk_info, + (lambda x: x['downloads']['nativeDownloads'], + lambda x: x['nativeDownloads']), + dict) or {} formats = [{ 'url': format_url, From cd3a3ff93bd5d6866d3822cb438b0e172ffe4e39 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 28 Jul 2018 22:09:53 +0700 Subject: [PATCH 109/558] [ted] Improve extraction and update tests --- youtube_dl/extractor/ted.py | 111 ++++++++++++++++++++---------------- 1 file changed, 61 insertions(+), 50 deletions(-) diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index dc9c5ce8e..212ac80ab 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -7,8 +7,10 @@ from .common import InfoExtractor from ..compat import compat_str from ..utils import ( + float_or_none, int_or_none, try_get, + url_or_none, ) @@ -30,7 +32,7 @@ class TEDIE(InfoExtractor): ''' _TESTS = [{ 'url': 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html', - 'md5': '0de43ac406aa3e4ea74b66c9c7789b13', + 'md5': 'b0ce2b05ca215042124fbc9e3886493a', 'info_dict': { 'id': '102', 'ext': 'mp4', @@ -42,24 +44,30 @@ class TEDIE(InfoExtractor): 'uploader': 'Dan Dennett', 'width': 853, 'duration': 1308, - } - }, { - 'url': 'http://www.ted.com/watch/ted-institute/ted-bcg/vishal-sikka-the-beauty-and-power-of-algorithms', - 'md5': 'b899ac15e345fb39534d913f7606082b', - 'info_dict': { - 'id': 'tSVI8ta_P4w', - 'ext': 'mp4', - 'title': 'Vishal Sikka: The beauty and power of algorithms', - 'thumbnail': r're:^https?://.+\.jpg', - 'description': 'md5:6261fdfe3e02f4f579cbbfc00aff73f4', - 'upload_date': '20140122', - 'uploader_id': 'TEDInstitute', - 'uploader': 'TED Institute', + 'view_count': int, + 'comment_count': int, + 'tags': list, + }, + 'params': { + 'skip_download': True, + }, + }, { + # missing HTTP bitrates + 'url': 'https://www.ted.com/talks/vishal_sikka_the_beauty_and_power_of_algorithms', + 'info_dict': { + 'id': '6069', + 'ext': 'mp4', + 'title': 'The beauty and power of algorithms', + 'thumbnail': r're:^https?://.+\.jpg', + 'description': 'md5:734e352710fb00d840ab87ae31aaf688', + 'uploader': 'Vishal Sikka', + }, + 'params': { + 'skip_download': True, }, - 'add_ie': ['Youtube'], }, { 'url': 'http://www.ted.com/talks/gabby_giffords_and_mark_kelly_be_passionate_be_courageous_be_your_best', - 'md5': '71b3ab2f4233012dce09d515c9c39ce2', + 'md5': 'e6b9617c01a7970ceac8bb2c92c346c0', 'info_dict': { 'id': '1972', 'ext': 'mp4', @@ -68,6 +76,9 @@ class TEDIE(InfoExtractor): 'description': 'md5:5174aed4d0f16021b704120360f72b92', 'duration': 1128, }, + 'params': { + 'skip_download': True, + }, }, { 'url': 'http://www.ted.com/playlists/who_are_the_hackers', 'info_dict': { @@ -91,22 +102,6 @@ class TEDIE(InfoExtractor): 'params': { 'skip_download': True, }, - }, { - # YouTube video - 'url': 'http://www.ted.com/talks/jeffrey_kluger_the_sibling_bond', - 'add_ie': ['Youtube'], - 'info_dict': { - 'id': 'aFBIPO-P7LM', - 'ext': 'mp4', - 'title': 'The hidden power of siblings: Jeff Kluger at TEDxAsheville', - 'description': 'md5:3d7a4f50d95ca5dd67104e2a20f43fe1', - 'uploader': 'TEDx Talks', - 'uploader_id': 'TEDxTalks', - 'upload_date': '20111216', - }, - 'params': { - 'skip_download': True, - }, }, { # no nativeDownloads 'url': 'https://www.ted.com/talks/tom_thum_the_orchestra_in_my_mouth', @@ -116,6 +111,9 @@ class TEDIE(InfoExtractor): 'title': 'The orchestra in my mouth', 'description': 'md5:5d1d78650e2f8dfcbb8ebee2951ac29a', 'uploader': 'Tom Thum', + 'view_count': int, + 'comment_count': int, + 'tags': list, }, 'params': { 'skip_download': True, @@ -174,24 +172,11 @@ class TEDIE(InfoExtractor): info = self._extract_info(webpage) - talk_info = try_get( - info, lambda x: x['__INITIAL_DATA__']['talks'][0], - dict) or info['talks'][0] + data = try_get(info, lambda x: x['__INITIAL_DATA__'], dict) or info + talk_info = data['talks'][0] title = talk_info['title'].strip() - external = talk_info.get('external') - if external: - service = external['service'] - self.to_screen('Found video from %s' % service) - ext_url = None - if service.lower() == 'youtube': - ext_url = external.get('code') - return { - '_type': 'url', - 'url': ext_url or external['uri'], - } - native_downloads = try_get( talk_info, (lambda x: x['downloads']['nativeDownloads'], @@ -211,10 +196,24 @@ class TEDIE(InfoExtractor): player_talk = talk_info['player_talks'][0] + external = player_talk.get('external') + if isinstance(external, dict): + service = external.get('service') + if isinstance(service, compat_str): + ext_url = None + if service.lower() == 'youtube': + ext_url = external.get('code') + return { + '_type': 'url', + 'url': ext_url or external['uri'], + } + resources_ = player_talk.get('resources') or talk_info.get('resources') http_url = None for format_id, resources in resources_.items(): + if not isinstance(resources, dict): + continue if format_id == 'h264': for resource in resources: h264_url = resource.get('file') @@ -243,8 +242,12 @@ class TEDIE(InfoExtractor): 'tbr': int_or_none(resource.get('bitrate')), }) elif format_id == 'hls': + stream_url = url_or_none(resources.get('stream')) + if not stream_url: + continue formats.extend(self._extract_m3u8_formats( - resources.get('stream'), video_name, 'mp4', m3u8_id=format_id, fatal=False)) + stream_url, video_name, 'mp4', m3u8_id=format_id, + fatal=False)) m3u8_formats = list(filter( lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none', @@ -254,9 +257,13 @@ class TEDIE(InfoExtractor): bitrate = self._search_regex(r'(\d+k)', m3u8_format['url'], 'bitrate', default=None) if not bitrate: continue + bitrate_url = re.sub(r'\d+k', bitrate, http_url) + if not self._is_valid_url( + bitrate_url, video_name, '%s bitrate' % bitrate): + continue f = m3u8_format.copy() f.update({ - 'url': re.sub(r'\d+k', bitrate, http_url), + 'url': bitrate_url, 'format_id': m3u8_format['format_id'].replace('hls', 'http'), 'protocol': 'http', }) @@ -282,7 +289,11 @@ class TEDIE(InfoExtractor): 'description': self._og_search_description(webpage), 'subtitles': self._get_subtitles(video_id, talk_info), 'formats': formats, - 'duration': talk_info.get('duration'), + 'duration': float_or_none(talk_info.get('duration')), + 'view_count': int_or_none(data.get('viewed_count')), + 'comment_count': int_or_none( + try_get(data, lambda x: x['comments']['count'])), + 'tags': try_get(talk_info, lambda x: x['tags'], list), } def _get_subtitles(self, video_id, talk_info): From ec240a43696478e43abb15e7c91f067b2bd5fe08 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 28 Jul 2018 20:29:56 +0100 Subject: [PATCH 110/558] [dailymotion:playlist] fix extraction(closes #16894) --- youtube_dl/extractor/dailymotion.py | 126 ++++++++++++++++++---------- 1 file changed, 84 insertions(+), 42 deletions(-) diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 8f5f57b98..040f0bd02 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals import base64 +import functools import hashlib import itertools import json @@ -16,11 +17,13 @@ from ..utils import ( error_to_compat_str, ExtractorError, int_or_none, + mimetype2ext, + OnDemandPagedList, parse_iso8601, sanitized_Request, str_to_int, unescapeHTML, - mimetype2ext, + urlencode_postdata, ) @@ -343,17 +346,93 @@ class DailymotionIE(DailymotionBaseInfoExtractor): class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): IE_NAME = 'dailymotion:playlist' - _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>[^/?#&]+)' - _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"' - _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s' + _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>x[0-9a-z]+)' _TESTS = [{ 'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q', 'info_dict': { 'title': 'SPORT', - 'id': 'xv4bw_nqtv_sport', + 'id': 'xv4bw', }, 'playlist_mincount': 20, }] + _PAGE_SIZE = 100 + + def _fetch_page(self, playlist_id, authorizaion, page): + page += 1 + videos = self._download_json( + 'https://graphql.api.dailymotion.com', + playlist_id, 'Downloading page %d' % page, + data=json.dumps({ + 'query': '''{ + collection(xid: "%s") { + videos(first: %d, page: %d) { + pageInfo { + hasNextPage + nextPage + } + edges { + node { + xid + url + } + } + } + } +}''' % (playlist_id, self._PAGE_SIZE, page) + }).encode(), headers={ + 'Authorization': authorizaion, + 'Origin': 'https://www.dailymotion.com', + })['data']['collection']['videos'] + for edge in videos['edges']: + node = edge['node'] + yield self.url_result( + node['url'], DailymotionIE.ie_key(), node['xid']) + + def _real_extract(self, url): + playlist_id = self._match_id(url) + webpage = self._download_webpage(url, playlist_id) + api = self._parse_json(self._search_regex( + r'__PLAYER_CONFIG__\s*=\s*({.+?});', + webpage, 'player config'), playlist_id)['context']['api'] + auth = self._download_json( + api.get('auth_url', 'https://graphql.api.dailymotion.com/oauth/token'), + playlist_id, data=urlencode_postdata({ + 'client_id': api.get('client_id', 'f1a362d288c1b98099c7'), + 'client_secret': api.get('client_secret', 'eea605b96e01c796ff369935357eca920c5da4c5'), + 'grant_type': 'client_credentials', + })) + authorizaion = '%s %s' % (auth.get('token_type', 'Bearer'), auth['access_token']) + entries = OnDemandPagedList(functools.partial( + self._fetch_page, playlist_id, authorizaion), self._PAGE_SIZE) + return self.playlist_result( + entries, playlist_id, + self._og_search_title(webpage)) + + +class DailymotionUserIE(DailymotionBaseInfoExtractor): + IE_NAME = 'dailymotion:user' + _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist)/)(?:(?:old/)?user/)?(?P<user>[^/]+)' + _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"' + _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s' + _TESTS = [{ + 'url': 'https://www.dailymotion.com/user/nqtv', + 'info_dict': { + 'id': 'nqtv', + 'title': 'Rémi Gaillard', + }, + 'playlist_mincount': 100, + }, { + 'url': 'http://www.dailymotion.com/user/UnderProject', + 'info_dict': { + 'id': 'UnderProject', + 'title': 'UnderProject', + }, + 'playlist_mincount': 1800, + 'expected_warnings': [ + 'Stopped at duplicated page', + ], + 'skip': 'Takes too long time', + }] def _extract_entries(self, id): video_ids = set() @@ -379,43 +458,6 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): if re.search(self._MORE_PAGES_INDICATOR, webpage) is None: break - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - playlist_id = mobj.group('id') - webpage = self._download_webpage(url, playlist_id) - - return { - '_type': 'playlist', - 'id': playlist_id, - 'title': self._og_search_title(webpage), - 'entries': self._extract_entries(playlist_id), - } - - -class DailymotionUserIE(DailymotionPlaylistIE): - IE_NAME = 'dailymotion:user' - _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist)/)(?:(?:old/)?user/)?(?P<user>[^/]+)' - _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s' - _TESTS = [{ - 'url': 'https://www.dailymotion.com/user/nqtv', - 'info_dict': { - 'id': 'nqtv', - 'title': 'Rémi Gaillard', - }, - 'playlist_mincount': 100, - }, { - 'url': 'http://www.dailymotion.com/user/UnderProject', - 'info_dict': { - 'id': 'UnderProject', - 'title': 'UnderProject', - }, - 'playlist_mincount': 1800, - 'expected_warnings': [ - 'Stopped at duplicated page', - ], - 'skip': 'Takes too long time', - }] - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) user = mobj.group('user') From 38e87f6c2ae2cdc04dd6f526213c83a0259db335 Mon Sep 17 00:00:00 2001 From: Huyuumi <zx.you.funy@gmail.com> Date: Sun, 29 Jul 2018 07:52:42 +0900 Subject: [PATCH 111/558] [utils] Remove return from __init__ --- youtube_dl/utils.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index b84436ed6..29cafd8f0 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -3569,7 +3569,7 @@ class PerRequestProxyHandler(compat_urllib_request.ProxyHandler): setattr(self, '%s_open' % type, lambda r, proxy='__noproxy__', type=type, meth=self.proxy_open: meth(r, proxy, type)) - return compat_urllib_request.ProxyHandler.__init__(self, proxies) + compat_urllib_request.ProxyHandler.__init__(self, proxies) def proxy_open(self, req, proxy, type): req_proxy = req.headers.get('Ytdl-request-proxy') From 1a88fc5a69249a6c36ce5dbb6e5d251792ab6f39 Mon Sep 17 00:00:00 2001 From: bato3 <bato3@bandyci.org> Date: Sun, 29 Jul 2018 01:04:59 +0200 Subject: [PATCH 112/558] [ceskatelevize] Use https for API call (refs #16997) --- youtube_dl/extractor/ceskatelevize.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index 6bad90859..46380430f 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -108,7 +108,7 @@ class CeskaTelevizeIE(InfoExtractor): for user_agent in (None, USER_AGENTS['Safari']): req = sanitized_Request( - 'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist', + 'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist', data=urlencode_postdata(data)) req.add_header('Content-type', 'application/x-www-form-urlencoded') From 4938c8d5730fd0db9eee977f94052c0058e407f0 Mon Sep 17 00:00:00 2001 From: Giuseppe Fabiano <gfabiano40@gmail.com> Date: Sun, 29 Jul 2018 01:24:10 +0200 Subject: [PATCH 113/558] [pornhub] Add support for subtitles (closes #16924) --- youtube_dl/extractor/pornhub.py | 34 +++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 97f988da4..ffc4405a8 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -18,6 +18,7 @@ from ..utils import ( orderedSet, remove_quotes, str_to_int, + url_or_none, ) @@ -68,6 +69,31 @@ class PornHubIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + # subtitles + 'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7', + 'info_dict': { + 'id': 'ph5af5fef7c2aa7', + 'ext': 'mp4', + 'title': 'BFFS - Cute Teen Girls Share Cock On the Floor', + 'uploader': 'BFFs', + 'duration': 622, + 'view_count': int, + 'like_count': int, + 'dislike_count': int, + 'comment_count': int, + 'age_limit': 18, + 'tags': list, + 'categories': list, + 'subtitles': { + 'en': [{ + "ext": 'srt' + }] + }, + }, + 'params': { + 'skip_download': True, + }, }, { 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d', 'only_matching': True, @@ -139,12 +165,19 @@ class PornHubIE(InfoExtractor): video_urls = [] video_urls_set = set() + subtitles = {} flashvars = self._parse_json( self._search_regex( r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'), video_id) if flashvars: + subtitle_url = url_or_none(flashvars.get('closedCaptionsFile')) + if subtitle_url: + subtitles.setdefault('en', []).append({ + 'url': subtitle_url, + 'ext': 'srt', + }) thumbnail = flashvars.get('image_url') duration = int_or_none(flashvars.get('video_duration')) media_definitions = flashvars.get('mediaDefinitions') @@ -256,6 +289,7 @@ class PornHubIE(InfoExtractor): 'age_limit': 18, 'tags': tags, 'categories': categories, + 'subtitles': subtitles, } From b2286f8fb29a7be8eefe53e074df8ab1092a12d8 Mon Sep 17 00:00:00 2001 From: bato3 <bato3@bandyci.org> Date: Sun, 29 Jul 2018 01:56:52 +0200 Subject: [PATCH 114/558] [crunchyroll:playlist] Restrict _VALID_URL (closes #17069) --- youtube_dl/extractor/crunchyroll.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 311da515d..463f995c7 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -262,6 +262,9 @@ class CrunchyrollIE(CrunchyrollBaseIE): # Just test metadata extraction 'skip_download': True, }, + }, { + 'url': 'http://www.crunchyroll.com/media-723735', + 'only_matching': True, }] _FORMAT_IDS = { @@ -580,7 +583,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE): IE_NAME = 'crunchyroll:playlist' - _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?(?:\?|$)' + _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login|media-\d+))(?P<id>[\w\-]+))/?(?:\?|$)' _TESTS = [{ 'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi', From 4eecef84f32869c25d56a4297a09b1b0b14a403e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 29 Jul 2018 06:58:37 +0700 Subject: [PATCH 115/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/ChangeLog b/ChangeLog index 94ecaae8e..f9dd0a89f 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,21 @@ +version <unreleased> + +Extractors +* [crunchyroll:playlist] Restrict URL regular expression (#17069, #17076) ++ [pornhub] Add support for subtitles (#16924, #17088) +* [ceskatelevize] Use https for API call (#16997, #16999) +* [dailymotion:playlist] Fix extraction (#16894) +* [ted] Improve extraction +* [ted] Fix extraction for videos without nativeDownloads (#16756, #17085) +* [telecinco] Fix extraction (#17080) +* [mitele] Reduce number of requests +* [rai] Return non HTTP relinker URL intact (#17055) +* [vk] Fix extraction for inline only videos (#16923) +* [streamcloud] Fix extraction (#17054) +* [facebook] Fix tahoe player extraction with authentication (#16655) ++ [puhutv] Add support for puhutv.com (#12712, #16010, #16269) + + version 2018.07.21 Core From 548482841867a16d3f68e18f78091e59f768a880 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 29 Jul 2018 07:02:18 +0700 Subject: [PATCH 116/558] release 2018.07.29 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 2 ++ youtube_dl/version.py | 2 +- 4 files changed, 7 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 24827ba8f..cae5fd749 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.07.21*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.07.21** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.07.29*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.07.29** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.07.21 +[debug] youtube-dl version 2018.07.29 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index f9dd0a89f..dfa27d3be 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.07.29 Extractors * [crunchyroll:playlist] Restrict URL regular expression (#17069, #17076) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 6cbe81802..f464d89db 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -672,6 +672,8 @@ - **PrimeShareTV** - **PromptFile** - **prosiebensat1**: ProSiebenSat.1 Digital + - **puhutv** + - **puhutv:serie** - **Puls4** - **Pyvideo** - **qqmusic**: QQ音乐 diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 9bf0ea30d..2048b69d2 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.07.21' +__version__ = '2018.07.29' From 9d1b213845f35af4de40dd057754f8f285091bfa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 30 Jul 2018 03:05:36 +0700 Subject: [PATCH 117/558] [viqeo] Add extractor (closes #17066) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/generic.py | 15 +++++ youtube_dl/extractor/viqeo.py | 99 ++++++++++++++++++++++++++++++ 3 files changed, 115 insertions(+) create mode 100644 youtube_dl/extractor/viqeo.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 29fab5b9a..c7a91a986 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1291,6 +1291,7 @@ from .viki import ( VikiIE, VikiChannelIE, ) +from .viqeo import ViqeoIE from .viu import ( ViuIE, ViuPlaylistIE, diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index e5a8ffbe8..43218c3a4 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -113,6 +113,7 @@ from .peertube import PeerTubeIE from .indavideo import IndavideoEmbedIE from .apa import APAIE from .foxnews import FoxNewsIE +from .viqeo import ViqeoIE class GenericIE(InfoExtractor): @@ -2060,6 +2061,15 @@ class GenericIE(InfoExtractor): }, 'skip': 'TODO: fix nested playlists processing in tests', }, + { + # Viqeo embeds + 'url': 'https://viqeo.tv/', + 'info_dict': { + 'id': 'viqeo', + 'title': 'All-new video platform', + }, + 'playlist_count': 6, + }, # { # # TODO: find another test # # http://schema.org/VideoObject @@ -3094,6 +3104,11 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( sharevideos_urls, video_id, video_title) + viqeo_urls = ViqeoIE._extract_urls(webpage) + if viqeo_urls: + return self.playlist_from_matches( + viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key()) + # Look for HTML5 media entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls') if entries: diff --git a/youtube_dl/extractor/viqeo.py b/youtube_dl/extractor/viqeo.py new file mode 100644 index 000000000..be7dfa814 --- /dev/null +++ b/youtube_dl/extractor/viqeo.py @@ -0,0 +1,99 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + str_or_none, + url_or_none, +) + + +class ViqeoIE(InfoExtractor): + _VALID_URL = r'''(?x) + (?: + viqeo:| + https?://cdn\.viqeo\.tv/embed/*\?.*?\bvid=| + https?://api\.viqeo\.tv/v\d+/data/startup?.*?\bvideo(?:%5B%5D|\[\])= + ) + (?P<id>[\da-f]+) + ''' + _TESTS = [{ + 'url': 'https://cdn.viqeo.tv/embed/?vid=cde96f09d25f39bee837', + 'md5': 'a169dd1a6426b350dca4296226f21e76', + 'info_dict': { + 'id': 'cde96f09d25f39bee837', + 'ext': 'mp4', + 'title': 'cde96f09d25f39bee837', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 76, + }, + }, { + 'url': 'viqeo:cde96f09d25f39bee837', + 'only_matching': True, + }, { + 'url': 'https://api.viqeo.tv/v1/data/startup?video%5B%5D=71bbec412ade45c3216c&profile=112', + 'only_matching': True, + }] + + @staticmethod + def _extract_urls(webpage): + return [ + mobj.group('url') + for mobj in re.finditer( + r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//cdn\.viqeo\.tv/embed/*\?.*?\bvid=[\da-f]+.*?)\1', + webpage)] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage( + 'https://cdn.viqeo.tv/embed/?vid=%s' % video_id, video_id) + + data = self._parse_json( + self._search_regex( + r'SLOT_DATA\s*=\s*({.+?})\s*;', webpage, 'slot data'), + video_id) + + formats = [] + thumbnails = [] + for media_file in data['mediaFiles']: + if not isinstance(media_file, dict): + continue + media_url = url_or_none(media_file.get('url')) + if not media_url or not media_url.startswith(('http', '//')): + continue + media_type = str_or_none(media_file.get('type')) + if not media_type: + continue + media_kind = media_type.split('/')[0].lower() + f = { + 'url': media_url, + 'width': int_or_none(media_file.get('width')), + 'height': int_or_none(media_file.get('height')), + } + format_id = str_or_none(media_file.get('quality')) + if media_kind == 'image': + f['id'] = format_id + thumbnails.append(f) + elif media_kind in ('video', 'audio'): + is_audio = media_kind == 'audio' + f.update({ + 'format_id': 'audio' if is_audio else format_id, + 'fps': int_or_none(media_file.get('fps')), + 'vcodec': 'none' if is_audio else None, + }) + formats.append(f) + self._sort_formats(formats) + + duration = int_or_none(data.get('duration')) + + return { + 'id': video_id, + 'title': video_id, + 'duration': duration, + 'thumbnails': thumbnails, + 'formats': formats, + } From 7ff129d3ea6ec010493a3b98d960e943eda05595 Mon Sep 17 00:00:00 2001 From: Giuseppe Fabiano <gfabiano40@gmail.com> Date: Sun, 29 Jul 2018 22:15:06 +0200 Subject: [PATCH 118/558] [theplatform] Relax _VALID_URL (closes #16181) --- youtube_dl/extractor/theplatform.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index 411b1f874..ffef5bf06 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -310,7 +310,7 @@ class ThePlatformIE(ThePlatformBaseIE, AdobePassIE): class ThePlatformFeedIE(ThePlatformBaseIE): _URL_TEMPLATE = '%s//feed.theplatform.com/f/%s/%s?form=json&%s' - _VALID_URL = r'https?://feed\.theplatform\.com/f/(?P<provider_id>[^/]+)/(?P<feed_id>[^?/]+)\?(?:[^&]+&)*(?P<filter>by(?:Gui|I)d=(?P<id>[\w-]+))' + _VALID_URL = r'https?://feed\.theplatform\.com/f/(?P<provider_id>[^/]+)/(?P<feed_id>[^?/]+)\?(?:[^&]+&)*(?P<filter>by(?:Gui|I)d=(?P<id>[^&]+))' _TESTS = [{ # From http://player.theplatform.com/p/7wvmTC/MSNBCEmbeddedOffSite?guid=n_hardball_5biden_140207 'url': 'http://feed.theplatform.com/f/7wvmTC/msnbc_video-p-test?form=json&pretty=true&range=-40&byGuid=n_hardball_5biden_140207', @@ -327,6 +327,9 @@ class ThePlatformFeedIE(ThePlatformBaseIE): 'categories': ['MSNBC/Issues/Democrats', 'MSNBC/Issues/Elections/Election 2016'], 'uploader': 'NBCU-NEWS', }, + }, { + 'url': 'http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews?byGuid=nn_netcast_180306.Copy.01', + 'only_matching': True, }] def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}, account_id=None): From 6f2d82a5a0fd020ac36bdfe4faa0ee8a9f4945ac Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 30 Jul 2018 23:10:40 +0700 Subject: [PATCH 119/558] [pbs] Fix extraction (closes #17109) --- youtube_dl/extractor/pbs.py | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index 52ab2f158..80340f595 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -15,6 +15,7 @@ from ..utils import ( strip_jsonp, strip_or_none, unified_strdate, + url_or_none, US_RATINGS, ) @@ -557,6 +558,13 @@ class PBSIE(InfoExtractor): if redirect_url and redirect_url not in redirect_urls: redirects.append(redirect) redirect_urls.add(redirect_url) + encodings = info.get('encodings') + if isinstance(encodings, list): + for encoding in encodings: + encoding_url = url_or_none(encoding) + if encoding_url and encoding_url not in redirect_urls: + redirects.append({'url': encoding_url}) + redirect_urls.add(encoding_url) chapters = [] # Player pages may also serve different qualities From 19b9de13c4e83416f09708dddecba6edc69b4525 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 30 Jul 2018 23:28:44 +0700 Subject: [PATCH 120/558] [watchbox] Fix extraction (closes #17107) --- youtube_dl/extractor/watchbox.py | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/watchbox.py b/youtube_dl/extractor/watchbox.py index d99313080..5a4e46e73 100644 --- a/youtube_dl/extractor/watchbox.py +++ b/youtube_dl/extractor/watchbox.py @@ -10,6 +10,7 @@ from ..utils import ( js_to_json, strip_or_none, try_get, + unescapeHTML, unified_timestamp, ) @@ -67,12 +68,20 @@ class WatchBoxIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - source = (self._parse_json( + player_config = self._parse_json( self._search_regex( - r'playerConf\s*=\s*({.+?})\s*;', webpage, 'player config', - default='{}'), - video_id, transform_source=js_to_json, - fatal=False) or {}).get('source') or {} + r'data-player-conf=(["\'])(?P<data>{.+?})\1', webpage, + 'player config', default='{}', group='data'), + video_id, transform_source=unescapeHTML, fatal=False) + + if not player_config: + player_config = self._parse_json( + self._search_regex( + r'playerConf\s*=\s*({.+?})\s*;', webpage, 'player config', + default='{}'), + video_id, transform_source=js_to_json, fatal=False) or {} + + source = player_config.get('source') or {} video_id = compat_str(source.get('videoId') or video_id) From 644921b3722093720216ba62f09db5a75a0b43e9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 2 Aug 2018 23:16:15 +0700 Subject: [PATCH 121/558] [twitch:vod] Improve _VALID_URL (closes #17135) --- youtube_dl/extractor/twitch.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index 89ee44224..2c9363ffb 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -240,7 +240,7 @@ class TwitchVodIE(TwitchItemBaseIE): _VALID_URL = r'''(?x) https?:// (?: - (?:(?:www|go|m)\.)?twitch\.tv/(?:[^/]+/v|videos)/| + (?:(?:www|go|m)\.)?twitch\.tv/(?:[^/]+/v(?:ideo)?|videos)/| player\.twitch\.tv/\?.*?\bvideo=v ) (?P<id>\d+) @@ -296,6 +296,9 @@ class TwitchVodIE(TwitchItemBaseIE): }, { 'url': 'https://m.twitch.tv/beagsandjam/v/247478721', 'only_matching': True, + }, { + 'url': 'https://www.twitch.tv/northernlion/video/291940395', + 'only_matching': True, }] def _real_extract(self, url): From 48afc6ca3ea8b666b0af24b0d9f424917d134d1b Mon Sep 17 00:00:00 2001 From: Tim Broder <tim@kidfund.us> Date: Tue, 31 Jul 2018 16:49:30 -0400 Subject: [PATCH 122/558] [twitch] Fix authentication (closes #17024) --- youtube_dl/extractor/twitch.py | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index 2c9363ffb..cbb735403 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals import itertools import re import random +import json from .common import InfoExtractor from ..compat import ( @@ -26,7 +27,6 @@ from ..utils import ( try_get, unified_timestamp, update_url_query, - urlencode_postdata, url_or_none, urljoin, ) @@ -37,7 +37,8 @@ class TwitchBaseIE(InfoExtractor): _API_BASE = 'https://api.twitch.tv' _USHER_BASE = 'https://usher.ttvnw.net' - _LOGIN_URL = 'https://www.twitch.tv/login' + _LOGIN_FORM_URL = 'https://www.twitch.tv/login' + _LOGIN_POST_URL = 'https://passport.twitch.tv/login' _CLIENT_ID = 'jzkbprff40iqj646a697cyrvl0zt2m6' _NETRC_MACHINE = 'twitch' @@ -77,21 +78,25 @@ class TwitchBaseIE(InfoExtractor): page_url = urlh.geturl() post_url = self._search_regex( r'<form[^>]+action=(["\'])(?P<url>.+?)\1', page, - 'post url', default=page_url, group='url') + 'post url', default=self._LOGIN_POST_URL, group='url') post_url = urljoin(page_url, post_url) - headers = {'Referer': page_url} + headers = { + 'Referer': page_url, + 'Origin': page_url, + 'Content-Type': 'text/plain;charset=UTF-8' + } try: response = self._download_json( post_url, None, note, - data=urlencode_postdata(form), + data=json.dumps(form).encode(), headers=headers) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: response = self._parse_json( e.cause.read().decode('utf-8'), None) - fail(response.get('message') or response['errors'][0]) + fail(response.get('error_description') or response.get('error_code')) raise if 'Authenticated successfully' in response.get('message', ''): @@ -105,7 +110,7 @@ class TwitchBaseIE(InfoExtractor): headers=headers) login_page, handle = self._download_webpage_handle( - self._LOGIN_URL, None, 'Downloading login page') + self._LOGIN_FORM_URL, None, 'Downloading login page') # Some TOR nodes and public proxies are blocked completely if 'blacklist_message' in login_page: @@ -115,6 +120,7 @@ class TwitchBaseIE(InfoExtractor): login_page, handle, 'Logging in', { 'username': username, 'password': password, + 'client_id': self._CLIENT_ID, }) # Successful login From cb1c3a3c07b2afe854ecd8c97f77d8f62720d7a4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 3 Aug 2018 22:43:06 +0700 Subject: [PATCH 123/558] [twitch] Update cliend id and modernize (closes #17126) --- youtube_dl/extractor/twitch.py | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index cbb735403..b39972b1e 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -8,7 +8,6 @@ import json from .common import InfoExtractor from ..compat import ( - compat_HTTPError, compat_kwargs, compat_parse_qs, compat_str, @@ -39,7 +38,7 @@ class TwitchBaseIE(InfoExtractor): _USHER_BASE = 'https://usher.ttvnw.net' _LOGIN_FORM_URL = 'https://www.twitch.tv/login' _LOGIN_POST_URL = 'https://passport.twitch.tv/login' - _CLIENT_ID = 'jzkbprff40iqj646a697cyrvl0zt2m6' + _CLIENT_ID = 'kimne78kx3ncx6brgo4mv6wki5h1ko' _NETRC_MACHINE = 'twitch' def _handle_error(self, response): @@ -84,20 +83,15 @@ class TwitchBaseIE(InfoExtractor): headers = { 'Referer': page_url, 'Origin': page_url, - 'Content-Type': 'text/plain;charset=UTF-8' + 'Content-Type': 'text/plain;charset=UTF-8', } - try: - response = self._download_json( - post_url, None, note, - data=json.dumps(form).encode(), - headers=headers) - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: - response = self._parse_json( - e.cause.read().decode('utf-8'), None) - fail(response.get('error_description') or response.get('error_code')) - raise + response = self._download_json( + post_url, None, note, data=json.dumps(form).encode(), + headers=headers, expected_status=400) + error = response.get('error_description') or response.get('error_code') + if error: + fail(error) if 'Authenticated successfully' in response.get('message', ''): return None, None From af322eb830525edaf39a202b7ecaface2bfc1bad Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 4 Aug 2018 00:26:58 +0700 Subject: [PATCH 124/558] [funk:channel] Improve byChannelAlias extraction (closes #17142) --- youtube_dl/extractor/funk.py | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/funk.py b/youtube_dl/extractor/funk.py index 76c20ffac..7e1af95e0 100644 --- a/youtube_dl/extractor/funk.py +++ b/youtube_dl/extractor/funk.py @@ -1,6 +1,7 @@ # coding: utf-8 from __future__ import unicode_literals +import itertools import re from .common import InfoExtractor @@ -125,17 +126,31 @@ class FunkChannelIE(FunkBaseIE): # Id-based channels are currently broken on their side: webplayer # tries to process them via byChannelAlias endpoint and fails # predictably. - by_channel_alias = self._download_json( - 'https://www.funk.net/api/v3.1/webapp/videos/byChannelAlias/%s' - % channel_id, - 'Downloading byChannelAlias JSON', headers=headers, query={ - 'size': 100, - }, fatal=False) - if by_channel_alias: + for page_num in itertools.count(): + by_channel_alias = self._download_json( + 'https://www.funk.net/api/v3.1/webapp/videos/byChannelAlias/%s' + % channel_id, + 'Downloading byChannelAlias JSON page %d' % (page_num + 1), + headers=headers, query={ + 'filterFsk': 'false', + 'sort': 'creationDate,desc', + 'size': 100, + 'page': page_num, + }, fatal=False) + if not by_channel_alias: + break video_list = try_get( by_channel_alias, lambda x: x['_embedded']['videoList'], list) - if video_list: + if not video_list: + break + try: video = next(r for r in video_list if r.get('alias') == alias) + break + except StopIteration: + pass + if not try_get( + by_channel_alias, lambda x: x['_links']['next']): + break if not video: by_id_list = self._download_json( From 20f96f64bd1c5825604995800fde741c5581fd83 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 4 Aug 2018 01:20:55 +0700 Subject: [PATCH 125/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/ChangeLog b/ChangeLog index dfa27d3be..ca18e2a7d 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,15 @@ +version <unreleased> + +Extractors +* [funk:channel] Improve byChannelAlias extraction (#17142) +* [twitch] Fix authentication (#17024, #17126) +* [twitch:vod] Improve URL regular expression (#17135) +* [watchbox] Fix extraction (#17107) +* [pbs] Fix extraction (#17109) +* [theplatform] Relax URL regular expression (#16181, #17097) ++ [viqeo] Add support for viqeo.tv (#17066) + + version 2018.07.29 Extractors From 81cc22bab66e27e64039263fe2cdbc4b8dfb41e5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 4 Aug 2018 01:23:24 +0700 Subject: [PATCH 126/558] release 2018.08.04 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 1 + youtube_dl/version.py | 2 +- 4 files changed, 6 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index cae5fd749..20433e915 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.07.29*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.07.29** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.08.04*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.08.04** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.07.29 +[debug] youtube-dl version 2018.08.04 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index ca18e2a7d..665503827 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.08.04 Extractors * [funk:channel] Improve byChannelAlias extraction (#17142) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index f464d89db..4bf2ec81b 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -1001,6 +1001,7 @@ - **Vimple**: Vimple - one-click video hosting - **Vine** - **vine:user** + - **Viqeo** - **Viu** - **viu:ott** - **viu:playlist** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 2048b69d2..67394fa01 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.07.29' +__version__ = '2018.08.04' From d588d4a5a69a1dee1a52ceb60e963687176d0493 Mon Sep 17 00:00:00 2001 From: Stanny Nuytkens <stannynuytkens@users.noreply.github.com> Date: Sun, 5 Aug 2018 17:10:01 +0200 Subject: [PATCH 127/558] [.gitignore] Add .vscode --- .gitignore | 3 +++ 1 file changed, 3 insertions(+) diff --git a/.gitignore b/.gitignore index f064a0d9e..c4870a6ba 100644 --- a/.gitignore +++ b/.gitignore @@ -48,3 +48,6 @@ youtube-dl.zsh tmp/ venv/ + +# VS Code related files +.vscode From a62460aa213c628874a4e6aee9d835433c705b94 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 6 Aug 2018 04:37:03 +0700 Subject: [PATCH 128/558] [imdb] Fix extension extraction (closes #17167) --- youtube_dl/extractor/imdb.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index fba01ef49..436759da5 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -64,7 +64,8 @@ class ImdbIE(InfoExtractor): video_url = url_or_none(encoding.get('videoUrl')) if not video_url: continue - ext = determine_ext(video_url, mimetype2ext(encoding.get('mimeType'))) + ext = mimetype2ext(encoding.get( + 'mimeType')) or determine_ext(video_url) if ext == 'm3u8': formats.extend(self._extract_m3u8_formats( video_url, video_id, 'mp4', entry_protocol='m3u8_native', From d37dc6e1c956ce0f390a4b832f8388cb94254f90 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 7 Aug 2018 23:27:08 +0700 Subject: [PATCH 129/558] [clyp] Add support for token protected media (closes #17184) --- youtube_dl/extractor/clyp.py | 35 ++++++++++++++++++++++++++++++----- 1 file changed, 30 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/clyp.py b/youtube_dl/extractor/clyp.py index 57e643799..06d04de13 100644 --- a/youtube_dl/extractor/clyp.py +++ b/youtube_dl/extractor/clyp.py @@ -1,15 +1,19 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import ( + compat_parse_qs, + compat_urllib_parse_urlparse, +) from ..utils import ( float_or_none, - parse_iso8601, + unified_timestamp, ) class ClypIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?clyp\.it/(?P<id>[a-z0-9]+)' - _TEST = { + _TESTS = [{ 'url': 'https://clyp.it/ojz2wfah', 'md5': '1d4961036c41247ecfdcc439c0cddcbb', 'info_dict': { @@ -21,13 +25,34 @@ class ClypIE(InfoExtractor): 'timestamp': 1443515251, 'upload_date': '20150929', }, - } + }, { + 'url': 'https://clyp.it/b04p1odi?token=b0078e077e15835845c528a44417719d', + 'info_dict': { + 'id': 'b04p1odi', + 'ext': 'mp3', + 'title': 'GJ! (Reward Edit)', + 'description': 'Metal Resistance (THE ONE edition)', + 'duration': 177.789, + 'timestamp': 1528241278, + 'upload_date': '20180605', + }, + 'params': { + 'skip_download': True, + }, + }] def _real_extract(self, url): audio_id = self._match_id(url) + qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query) + token = qs.get('token', [None])[0] + + query = {} + if token: + query['token'] = token + metadata = self._download_json( - 'https://api.clyp.it/%s' % audio_id, audio_id) + 'https://api.clyp.it/%s' % audio_id, audio_id, query=query) formats = [] for secure in ('', 'Secure'): @@ -45,7 +70,7 @@ class ClypIE(InfoExtractor): title = metadata['Title'] description = metadata.get('Description') duration = float_or_none(metadata.get('Duration')) - timestamp = parse_iso8601(metadata.get('DateCreated')) + timestamp = unified_timestamp(metadata.get('DateCreated')) return { 'id': audio_id, From b65e3b0636c4b992f3187bff7d5268c6891023a6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 12 Aug 2018 01:47:10 +0700 Subject: [PATCH 130/558] [bitchute] Add extractor (closes #14052) --- youtube_dl/extractor/bitchute.py | 116 +++++++++++++++++++++++++++++ youtube_dl/extractor/extractors.py | 4 + 2 files changed, 120 insertions(+) create mode 100644 youtube_dl/extractor/bitchute.py diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py new file mode 100644 index 000000000..28016f18b --- /dev/null +++ b/youtube_dl/extractor/bitchute.py @@ -0,0 +1,116 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import itertools +import re + +from .common import InfoExtractor +from ..utils import urlencode_postdata + + +class BitChuteIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)' + _TESTS = [{ + 'url': 'https://www.bitchute.com/video/szoMrox2JEI/', + 'md5': '66c4a70e6bfc40dcb6be3eb1d74939eb', + 'info_dict': { + 'id': 'szoMrox2JEI', + 'ext': 'mp4', + 'title': 'Fuck bitches get money', + 'description': 'md5:3f21f6fb5b1d17c3dee9cf6b5fe60b3a', + 'thumbnail': r're:^https?://.*\.jpg$', + 'uploader': 'Victoria X Rave', + }, + }, { + 'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/', + 'only_matching': True, + }, { + 'url': 'https://www.bitchute.com/torrent/Zee5BE49045h/szoMrox2JEI.webtorrent', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage( + 'https://www.bitchute.com/video/%s' % video_id, video_id) + + title = self._search_regex( + (r'<[^>]+\bid=["\']video-title[^>]+>([^<]+)', r'<title>([^<]+)'), + webpage, 'title', default=None) or self._html_search_meta( + 'description', webpage, 'title', + default=None) or self._og_search_description(webpage) + + formats = [ + {'url': mobj.group('url')} + for mobj in re.finditer( + r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage)] + self._sort_formats(formats) + + description = self._html_search_regex( + r'(?s)<div\b[^>]+\bclass=["\']full hidden[^>]+>(.+?)</div>', + webpage, 'description', fatal=False) + thumbnail = self._og_search_thumbnail( + webpage, default=None) or self._html_search_meta( + 'twitter:image:src', webpage, 'thumbnail') + uploader = self._html_search_regex( + r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>', webpage, + 'uploader', fatal=False) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'formats': formats, + } + + +class BitChuteChannelIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)' + _TEST = { + 'url': 'https://www.bitchute.com/channel/victoriaxrave/', + 'playlist_mincount': 185, + 'info_dict': { + 'id': 'victoriaxrave', + }, + } + + _TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7' + + def _entries(self, channel_id): + channel_url = 'https://www.bitchute.com/channel/%s/' % channel_id + for page_num in itertools.count(0): + data = self._download_json( + '%sextend/' % channel_url, channel_id, + 'Downloading channel page %d' % (page_num + 1), + data=urlencode_postdata({ + 'csrfmiddlewaretoken': self._TOKEN, + 'name': '', + 'offset': page_num * 25 + }), headers={ + 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', + 'Referer': channel_url, + 'X-Requested-With': 'XMLHttpRequest', + 'Cookie': 'csrftoken=%s' % self._TOKEN, + }) + if data.get('success') is False: + break + html = data.get('html') + if not html: + break + video_ids = re.findall( + r'class=["\']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref=["\']/video/([^"\'/]+)', + html) + if not video_ids: + break + for video_id in video_ids: + yield self.url_result( + 'https://www.bitchute.com/video/%s' % video_id, + ie=BitChuteIE.ie_key(), video_id=video_id) + + def _real_extract(self, url): + channel_id = self._match_id(url) + return self.playlist_result( + self._entries(channel_id), playlist_id=channel_id) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index c7a91a986..eb22d0999 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -118,6 +118,10 @@ from .bilibili import ( BiliBiliBangumiIE, ) from .biobiochiletv import BioBioChileTVIE +from .bitchute import ( + BitChuteIE, + BitChuteChannelIE, +) from .biqle import BIQLEIE from .bleacherreport import ( BleacherReportIE, From de4c41b437c7a0126074d75ddeeccbf4470d0684 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 12 Aug 2018 01:52:50 +0700 Subject: [PATCH 131/558] [bitchute] Improve page offset --- youtube_dl/extractor/bitchute.py | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py index 28016f18b..da263714a 100644 --- a/youtube_dl/extractor/bitchute.py +++ b/youtube_dl/extractor/bitchute.py @@ -81,14 +81,15 @@ class BitChuteChannelIE(InfoExtractor): def _entries(self, channel_id): channel_url = 'https://www.bitchute.com/channel/%s/' % channel_id - for page_num in itertools.count(0): + offset = 0 + for page_num in itertools.count(1): data = self._download_json( '%sextend/' % channel_url, channel_id, - 'Downloading channel page %d' % (page_num + 1), + 'Downloading channel page %d' % page_num, data=urlencode_postdata({ 'csrfmiddlewaretoken': self._TOKEN, 'name': '', - 'offset': page_num * 25 + 'offset': offset, }), headers={ 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', 'Referer': channel_url, @@ -105,6 +106,7 @@ class BitChuteChannelIE(InfoExtractor): html) if not video_ids: break + offset += len(video_ids) for video_id in video_ids: yield self.url_result( 'https://www.bitchute.com/video/%s' % video_id, From 4779420ce8e13d0df33189907e477146a2a0cefe Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 12 Aug 2018 05:31:18 +0100 Subject: [PATCH 132/558] [redbulltv] add support redbull.com tv URLs(closes #17218) --- youtube_dl/extractor/redbulltv.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/redbulltv.py b/youtube_dl/extractor/redbulltv.py index 243603676..7e8d58f38 100644 --- a/youtube_dl/extractor/redbulltv.py +++ b/youtube_dl/extractor/redbulltv.py @@ -10,7 +10,7 @@ from ..utils import ( class RedBullTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?redbull\.tv/video/(?P<id>AP-\w+)' + _VALID_URL = r'https?://(?:www\.)?redbull(?:\.tv|\.com/(?:[^/]+/)?tv)/video/(?P<id>AP-\w+)' _TESTS = [{ # film 'url': 'https://www.redbull.tv/video/AP-1Q6XCDTAN1W11', @@ -35,6 +35,9 @@ class RedBullTVIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + 'url': 'https://www.redbull.com/int-en/tv/video/AP-1UWHCAR9S1W11/rob-meets-sam-gaze?playlist=playlists::3f81040a-2f31-4832-8e2e-545b1d39d173', + 'only_matching': True, }] def _real_extract(self, url): From 24e0cd709fae13d9192361dae27ecd292c6b1fd6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 13 Aug 2018 00:15:59 +0700 Subject: [PATCH 133/558] [raywenderlich] Adapt to site redesign (closes #17225) --- youtube_dl/extractor/extractors.py | 5 +- youtube_dl/extractor/raywenderlich.py | 189 ++++++++++++++++++-------- 2 files changed, 137 insertions(+), 57 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index eb22d0999..23ad42da9 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -899,7 +899,10 @@ from .rai import ( RaiPlayPlaylistIE, RaiIE, ) -from .raywenderlich import RayWenderlichIE +from .raywenderlich import ( + RayWenderlichIE, + RayWenderlichCourseIE, +) from .rbmaradio import RBMARadioIE from .rds import RDSIE from .redbulltv import RedBullTVIE diff --git a/youtube_dl/extractor/raywenderlich.py b/youtube_dl/extractor/raywenderlich.py index 640c3ee23..5411ece21 100644 --- a/youtube_dl/extractor/raywenderlich.py +++ b/youtube_dl/extractor/raywenderlich.py @@ -4,24 +4,37 @@ import re from .common import InfoExtractor from .vimeo import VimeoIE +from ..compat import compat_str from ..utils import ( - extract_attributes, ExtractorError, - smuggle_url, - unsmuggle_url, + int_or_none, + merge_dicts, + try_get, + unescapeHTML, + unified_timestamp, urljoin, ) class RayWenderlichIE(InfoExtractor): - _VALID_URL = r'https?://videos\.raywenderlich\.com/courses/(?P<course_id>[^/]+)/lessons/(?P<id>\d+)' + _VALID_URL = r'''(?x) + https?:// + (?: + videos\.raywenderlich\.com/courses| + (?:www\.)?raywenderlich\.com + )/ + (?P<course_id>[^/]+)/lessons/(?P<id>\d+) + ''' _TESTS = [{ - 'url': 'https://videos.raywenderlich.com/courses/105-testing-in-ios/lessons/1', + 'url': 'https://www.raywenderlich.com/3530-testing-in-ios/lessons/1', 'info_dict': { 'id': '248377018', 'ext': 'mp4', - 'title': 'Testing In iOS Episode 1: Introduction', + 'title': 'Introduction', + 'description': 'md5:804d031b3efa9fcb49777d512d74f722', + 'timestamp': 1513906277, + 'upload_date': '20171222', 'duration': 133, 'uploader': 'Ray Wenderlich', 'uploader_id': 'user3304672', @@ -34,69 +47,133 @@ class RayWenderlichIE(InfoExtractor): 'expected_warnings': ['HTTP Error 403: Forbidden'], }, { 'url': 'https://videos.raywenderlich.com/courses/105-testing-in-ios/lessons/1', + 'only_matching': True, + }] + + @staticmethod + def _extract_video_id(data, lesson_id): + if not data: + return + groups = try_get(data, lambda x: x['groups'], list) or [] + if not groups: + return + for group in groups: + if not isinstance(group, dict): + continue + contents = try_get(data, lambda x: x['contents'], list) or [] + for content in contents: + if not isinstance(content, dict): + continue + ordinal = int_or_none(content.get('ordinal')) + if ordinal != lesson_id: + continue + video_id = content.get('identifier') + if video_id: + return compat_str(video_id) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + course_id, lesson_id = mobj.group('course_id', 'id') + display_id = '%s/%s' % (course_id, lesson_id) + + webpage = self._download_webpage(url, display_id) + + thumbnail = self._og_search_thumbnail( + webpage, default=None) or self._html_search_meta( + 'twitter:image', webpage, 'thumbnail') + + if '>Subscribe to unlock' in webpage: + raise ExtractorError( + 'This content is only available for subscribers', + expected=True) + + info = { + 'thumbnail': thumbnail, + } + + vimeo_id = self._search_regex( + r'data-vimeo-id=["\'](\d+)', webpage, 'vimeo id', default=None) + + if not vimeo_id: + data = self._parse_json( + self._search_regex( + r'data-collection=(["\'])(?P<data>{.+?})\1', webpage, + 'data collection', default='{}', group='data'), + display_id, transform_source=unescapeHTML, fatal=False) + video_id = self._extract_video_id( + data, lesson_id) or self._search_regex( + r'/videos/(\d+)/', thumbnail, 'video id') + headers = { + 'Referer': url, + 'X-Requested-With': 'XMLHttpRequest', + } + csrf_token = self._html_search_meta( + 'csrf-token', webpage, 'csrf token', default=None) + if csrf_token: + headers['X-CSRF-Token'] = csrf_token + video = self._download_json( + 'https://videos.raywenderlich.com/api/v1/videos/%s.json' + % video_id, display_id, headers=headers)['video'] + vimeo_id = video['clips'][0]['provider_id'] + info.update({ + '_type': 'url_transparent', + 'title': video.get('name'), + 'description': video.get('description') or video.get( + 'meta_description'), + 'duration': int_or_none(video.get('duration')), + 'timestamp': unified_timestamp(video.get('created_at')), + }) + + return merge_dicts(info, self.url_result( + VimeoIE._smuggle_referrer( + 'https://player.vimeo.com/video/%s' % vimeo_id, url), + ie=VimeoIE.ie_key(), video_id=vimeo_id)) + + +class RayWenderlichCourseIE(InfoExtractor): + _VALID_URL = r'''(?x) + https?:// + (?: + videos\.raywenderlich\.com/courses| + (?:www\.)?raywenderlich\.com + )/ + (?P<id>[^/]+) + ''' + + _TEST = { + 'url': 'https://www.raywenderlich.com/3530-testing-in-ios', 'info_dict': { 'title': 'Testing in iOS', - 'id': '105-testing-in-ios', + 'id': '3530-testing-in-ios', }, 'params': { 'noplaylist': False, }, 'playlist_count': 29, - }] + } + + @classmethod + def suitable(cls, url): + return False if RayWenderlichIE.suitable(url) else super( + RayWenderlichCourseIE, cls).suitable(url) def _real_extract(self, url): - url, smuggled_data = unsmuggle_url(url, {}) + course_id = self._match_id(url) - mobj = re.match(self._VALID_URL, url) - course_id, lesson_id = mobj.group('course_id', 'id') - video_id = '%s/%s' % (course_id, lesson_id) - - webpage = self._download_webpage(url, video_id) - - no_playlist = self._downloader.params.get('noplaylist') - if no_playlist or smuggled_data.get('force_video', False): - if no_playlist: - self.to_screen( - 'Downloading just video %s because of --no-playlist' - % video_id) - if '>Subscribe to unlock' in webpage: - raise ExtractorError( - 'This content is only available for subscribers', - expected=True) - vimeo_id = self._search_regex( - r'data-vimeo-id=["\'](\d+)', webpage, 'video id') - return self.url_result( - VimeoIE._smuggle_referrer( - 'https://player.vimeo.com/video/%s' % vimeo_id, url), - ie=VimeoIE.ie_key(), video_id=vimeo_id) - - self.to_screen( - 'Downloading playlist %s - add --no-playlist to just download video' - % course_id) - - lesson_ids = set((lesson_id, )) - for lesson in re.findall( - r'(<a[^>]+\bclass=["\']lesson-link[^>]+>)', webpage): - attrs = extract_attributes(lesson) - if not attrs: - continue - lesson_url = attrs.get('href') - if not lesson_url: - continue - lesson_id = self._search_regex( - r'/lessons/(\d+)', lesson_url, 'lesson id', default=None) - if not lesson_id: - continue - lesson_ids.add(lesson_id) + webpage = self._download_webpage(url, course_id) entries = [] - for lesson_id in sorted(lesson_ids): + lesson_urls = set() + for lesson_url in re.findall( + r'<a[^>]+\bhref=["\'](/%s/lessons/\d+)' % course_id, webpage): + if lesson_url in lesson_urls: + continue + lesson_urls.add(lesson_url) entries.append(self.url_result( - smuggle_url(urljoin(url, lesson_id), {'force_video': True}), - ie=RayWenderlichIE.ie_key())) + urljoin(url, lesson_url), ie=RayWenderlichIE.ie_key())) - title = self._search_regex( - r'class=["\']course-title[^>]+>([^<]+)', webpage, 'course title', - default=None) + title = self._og_search_title( + webpage, default=None) or self._html_search_meta( + 'twitter:title', webpage, 'title', default=None) return self.playlist_result(entries, course_id, title) From 57c68ec4c303f471b2519db21b9b56c080d88338 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 14 Aug 2018 22:51:44 +0700 Subject: [PATCH 134/558] [generic] Add support for expressen embeds --- youtube_dl/extractor/expressen.py | 23 ++++++++++++++++++++++- youtube_dl/extractor/generic.py | 6 ++++++ 2 files changed, 28 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/expressen.py b/youtube_dl/extractor/expressen.py index f61178012..934571472 100644 --- a/youtube_dl/extractor/expressen.py +++ b/youtube_dl/extractor/expressen.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( determine_ext, @@ -11,7 +13,13 @@ from ..utils import ( class ExpressenIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?expressen\.se/tv/(?:[^/]+/)*(?P<id>[^/?#&]+)' + _VALID_URL = r'''(?x) + https?:// + (?:www\.)?expressen\.se/ + (?:(?:tvspelare/video|videoplayer/embed)/)? + tv/(?:[^/]+/)* + (?P<id>[^/?#&]+) + ''' _TESTS = [{ 'url': 'https://www.expressen.se/tv/ledare/ledarsnack/ledarsnack-om-arbetslosheten-bland-kvinnor-i-speciellt-utsatta-omraden/', 'md5': '2fbbe3ca14392a6b1b36941858d33a45', @@ -28,8 +36,21 @@ class ExpressenIE(InfoExtractor): }, { 'url': 'https://www.expressen.se/tv/kultur/kulturdebatt-med-expressens-karin-olsson/', 'only_matching': True, + }, { + 'url': 'https://www.expressen.se/tvspelare/video/tv/ditv/ekonomistudion/experterna-har-ar-fragorna-som-avgor-valet/?embed=true&external=true&autoplay=true&startVolume=0&partnerId=di', + 'only_matching': True, + }, { + 'url': 'https://www.expressen.se/videoplayer/embed/tv/ditv/ekonomistudion/experterna-har-ar-fragorna-som-avgor-valet/?embed=true&external=true&autoplay=true&startVolume=0&partnerId=di', + 'only_matching': True, }] + @staticmethod + def _extract_urls(webpage): + return [ + mobj.group('url') for mobj in re.finditer( + r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?expressen\.se/(?:tvspelare/video|videoplayer/embed)/tv/.+?)\1', + webpage)] + def _real_extract(self, url): display_id = self._match_id(url) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 43218c3a4..83a31f3d3 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -114,6 +114,7 @@ from .indavideo import IndavideoEmbedIE from .apa import APAIE from .foxnews import FoxNewsIE from .viqeo import ViqeoIE +from .expressen import ExpressenIE class GenericIE(InfoExtractor): @@ -3109,6 +3110,11 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key()) + expressen_urls = ExpressenIE._extract_urls(webpage) + if expressen_urls: + return self.playlist_from_matches( + expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key()) + # Look for HTML5 media entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls') if entries: From 60c0856223391864135694197db2d17125fe4e8e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 14 Aug 2018 23:27:12 +0700 Subject: [PATCH 135/558] [utils] Use pure browser header for User-Agent (closes #17236) --- youtube_dl/utils.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 29cafd8f0..0c830ba71 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -82,7 +82,7 @@ def register_socks_protocols(): compiled_regex_type = type(re.compile('')) std_headers = { - 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:59.0) Gecko/20100101 Firefox/59.0 (Chrome)', + 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:59.0) Gecko/20100101 Firefox/59.0', 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 'Accept-Encoding': 'gzip, deflate', From d6ef8b4dd4230233b8ada6b1f8d7083df86a7cd7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 16 Aug 2018 00:11:41 +0700 Subject: [PATCH 136/558] [nova] Fix extraction (closes #17241) --- youtube_dl/extractor/nova.py | 31 ++++++++++++++++++++++++++----- 1 file changed, 26 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/nova.py b/youtube_dl/extractor/nova.py index 06cb8cb3f..edf8b82c6 100644 --- a/youtube_dl/extractor/nova.py +++ b/youtube_dl/extractor/nova.py @@ -6,7 +6,9 @@ import re from .common import InfoExtractor from ..utils import ( clean_html, + js_to_json, unified_strdate, + url_or_none, ) @@ -111,8 +113,21 @@ class NovaIE(InfoExtractor): webpage, 'video id') config_url = self._search_regex( - r'src="(http://tn\.nova\.cz/bin/player/videojs/config\.php\?[^"]+)"', + r'src="(https?://(?:tn|api)\.nova\.cz/bin/player/videojs/config\.php\?[^"]+)"', webpage, 'config url', default=None) + config_params = {} + + if not config_url: + player = self._parse_json( + self._search_regex( + r'(?s)Player\s*\(.+?\s*,\s*({.+?\bmedia\b["\']?\s*:\s*["\']?\d+.+?})\s*\)', webpage, + 'player', default='{}'), + video_id, transform_source=js_to_json, fatal=False) + if player: + config_url = url_or_none(player.get('configUrl')) + params = player.get('configParams') + if isinstance(params, dict): + config_params = params if not config_url: DEFAULT_SITE_ID = '23000' @@ -127,14 +142,20 @@ class NovaIE(InfoExtractor): } site_id = self._search_regex( - r'site=(\d+)', webpage, 'site id', default=None) or SITES.get(site, DEFAULT_SITE_ID) + r'site=(\d+)', webpage, 'site id', default=None) or SITES.get( + site, DEFAULT_SITE_ID) - config_url = ('http://tn.nova.cz/bin/player/videojs/config.php?site=%s&media=%s&jsVar=vjsconfig' - % (site_id, video_id)) + config_url = 'https://api.nova.cz/bin/player/videojs/config.php' + config_params = { + 'site': site_id, + 'media': video_id, + 'quality': 3, + 'version': 1, + } config = self._download_json( config_url, display_id, - 'Downloading config JSON', + 'Downloading config JSON', query=config_params, transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1]) mediafile = config['mediafile'] From 0a74b4519147aec45dc39756dc55b5755beefbc2 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 17 Aug 2018 11:59:22 +0100 Subject: [PATCH 137/558] [cwtv] fix extraction(closes #17256) --- youtube_dl/extractor/cwtv.py | 82 +++++++++++++----------------------- 1 file changed, 29 insertions(+), 53 deletions(-) diff --git a/youtube_dl/extractor/cwtv.py b/youtube_dl/extractor/cwtv.py index f4cf0f1c5..224a1fb5d 100644 --- a/youtube_dl/extractor/cwtv.py +++ b/youtube_dl/extractor/cwtv.py @@ -4,7 +4,10 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( int_or_none, + parse_age_limit, parse_iso8601, + smuggle_url, + str_or_none, ) @@ -40,10 +43,15 @@ class CWTVIE(InfoExtractor): 'duration': 1263, 'series': 'Whose Line Is It Anyway?', 'season_number': 11, - 'season': '11', 'episode_number': 20, 'upload_date': '20151006', 'timestamp': 1444107300, + 'age_limit': 14, + 'uploader': 'CWTV', + }, + 'params': { + # m3u8 download + 'skip_download': True, }, }, { 'url': 'http://cwtv.com/thecw/chroniclesofcisco/?play=8adebe35-f447-465f-ab52-e863506ff6d6', @@ -58,60 +66,28 @@ class CWTVIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - video_data = None - formats = [] - for partner in (154, 213): - vdata = self._download_json( - 'http://metaframe.digitalsmiths.tv/v2/CWtv/assets/%s/partner/%d?format=json' % (video_id, partner), video_id, fatal=False) - if not vdata: - continue - video_data = vdata - for quality, quality_data in vdata.get('videos', {}).items(): - quality_url = quality_data.get('uri') - if not quality_url: - continue - if quality == 'variantplaylist': - formats.extend(self._extract_m3u8_formats( - quality_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) - else: - tbr = int_or_none(quality_data.get('bitrate')) - format_id = 'http' + ('-%d' % tbr if tbr else '') - if self._is_valid_url(quality_url, video_id, format_id): - formats.append({ - 'format_id': format_id, - 'url': quality_url, - 'tbr': tbr, - }) - video_metadata = video_data['assetFields'] - ism_url = video_metadata.get('smoothStreamingUrl') - if ism_url: - formats.extend(self._extract_ism_formats( - ism_url, video_id, ism_id='mss', fatal=False)) - self._sort_formats(formats) + video_data = self._download_json( + 'http://images.cwtv.com/feed/mobileapp/video-meta/apiversion_8/guid_' + video_id, + video_id)['video'] + title = video_data['title'] + mpx_url = video_data.get('mpx_url') or 'http://link.theplatform.com/s/cwtv/media/guid/2703454149/%s?formats=M3U' % video_id - thumbnails = [{ - 'url': image['uri'], - 'width': image.get('width'), - 'height': image.get('height'), - } for image_id, image in video_data['images'].items() if image.get('uri')] if video_data.get('images') else None - - subtitles = { - 'en': [{ - 'url': video_metadata['UnicornCcUrl'], - }], - } if video_metadata.get('UnicornCcUrl') else None + season = str_or_none(video_data.get('season')) + episode = str_or_none(video_data.get('episode')) + if episode and season: + episode = episode.lstrip(season) return { + '_type': 'url_transparent', 'id': video_id, - 'title': video_metadata['title'], - 'description': video_metadata.get('description'), - 'duration': int_or_none(video_metadata.get('duration')), - 'series': video_metadata.get('seriesName'), - 'season_number': int_or_none(video_metadata.get('seasonNumber')), - 'season': video_metadata.get('seasonName'), - 'episode_number': int_or_none(video_metadata.get('episodeNumber')), - 'timestamp': parse_iso8601(video_data.get('startTime')), - 'thumbnails': thumbnails, - 'formats': formats, - 'subtitles': subtitles, + 'title': title, + 'url': smuggle_url(mpx_url, {'force_smil_url': True}), + 'description': video_data.get('description_long'), + 'duration': int_or_none(video_data.get('duration_secs')), + 'series': video_data.get('series_name'), + 'season_number': int_or_none(season), + 'episode_number': int_or_none(episode), + 'timestamp': parse_iso8601(video_data.get('start_time')), + 'age_limit': parse_age_limit(video_data.get('rating')), + 'ie_key': 'ThePlatform', } From 6f356cbbcf0bb3e3e3abce912d451d1852999b67 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 20 Aug 2018 02:05:07 +0700 Subject: [PATCH 138/558] [bbccouk] Extend _ID_REGEX (closes #17270) --- youtube_dl/extractor/bbc.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 641bf6073..abcfa301d 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -29,7 +29,7 @@ from ..compat import ( class BBCCoUkIE(InfoExtractor): IE_NAME = 'bbc.co.uk' IE_DESC = 'BBC iPlayer' - _ID_REGEX = r'[pbw][\da-z]{7}' + _ID_REGEX = r'(?:[pbm][\da-z]{7}|w[\da-z]{7,14})' _VALID_URL = r'''(?x) https?:// (?:www\.)?bbc\.co\.uk/ @@ -236,6 +236,12 @@ class BBCCoUkIE(InfoExtractor): }, { 'url': 'http://www.bbc.co.uk/programmes/w3csv1y9', 'only_matching': True, + }, { + 'url': 'https://www.bbc.co.uk/programmes/m00005xn', + 'only_matching': True, + }, { + 'url': 'https://www.bbc.co.uk/programmes/w172w4dww1jqt5s', + 'only_matching': True, }] _USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8' From bf1245d236f4199497a8cbc42ff0baa5f92f9edc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 20 Aug 2018 02:15:48 +0700 Subject: [PATCH 139/558] [lci] Fix extraction (closes #17274) --- youtube_dl/extractor/lci.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/lci.py b/youtube_dl/extractor/lci.py index af34829e7..920872f5c 100644 --- a/youtube_dl/extractor/lci.py +++ b/youtube_dl/extractor/lci.py @@ -20,5 +20,7 @@ class LCIIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - wat_id = self._search_regex(r'data-watid=[\'"](\d+)', webpage, 'wat id') + wat_id = self._search_regex( + (r'data-watid=[\'"](\d+)', r'idwat["\']?\s*:\s*["\']?(\d+)'), + webpage, 'wat id') return self.url_result('wat:' + wat_id, 'Wat', wat_id) From eda86b4335a464c2744adb537f1296eff24f5bde Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 21 Aug 2018 23:45:18 +0700 Subject: [PATCH 140/558] [anvato] Fallback to generic API key for access key to API key lookup (closes #16788, closes #17254) --- youtube_dl/extractor/anvato.py | 30 ++++++++++++++++++++++++++++-- 1 file changed, 28 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/anvato.py b/youtube_dl/extractor/anvato.py index f6a78eb5d..84e841035 100644 --- a/youtube_dl/extractor/anvato.py +++ b/youtube_dl/extractor/anvato.py @@ -134,9 +134,33 @@ class AnvatoIE(InfoExtractor): 'telemundo': 'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582' } + _API_KEY = '3hwbSuqqT690uxjNYBktSQpa5ZrpYYR0Iofx7NcJHyA' + _ANVP_RE = r'<script[^>]+\bdata-anvp\s*=\s*(["\'])(?P<anvp>(?:(?!\1).)+)\1' _AUTH_KEY = b'\x31\xc2\x42\x84\x9e\x73\xa0\xce' + _TESTS = [{ + # from https://www.boston25news.com/news/watch-humpback-whale-breaches-right-next-to-fishing-boat-near-nh/817484874 + 'url': 'anvato:8v9BEynrwx8EFLYpgfOWcG1qJqyXKlRM:4465496', + 'info_dict': { + 'id': '4465496', + 'ext': 'mp4', + 'title': 'VIDEO: Humpback whale breaches right next to NH boat', + 'description': 'VIDEO: Humpback whale breaches right next to NH boat. Footage courtesy: Zach Fahey.', + 'duration': 22, + 'timestamp': 1534855680, + 'upload_date': '20180821', + 'uploader': 'ANV', + }, + 'params': { + 'skip_download': True, + }, + }, { + # from https://sanfrancisco.cbslocal.com/2016/06/17/source-oakland-cop-on-leave-for-having-girlfriend-help-with-police-reports/ + 'url': 'anvato:DVzl9QRzox3ZZsP9bNu5Li3X7obQOnqP:3417601', + 'only_matching': True, + }] + def __init__(self, *args, **kwargs): super(AnvatoIE, self).__init__(*args, **kwargs) self.__server_time = None @@ -169,7 +193,8 @@ class AnvatoIE(InfoExtractor): 'api': { 'anvrid': anvrid, 'anvstk': md5_text('%s|%s|%d|%s' % ( - access_key, anvrid, server_time, self._ANVACK_TABLE[access_key])), + access_key, anvrid, server_time, + self._ANVACK_TABLE.get(access_key, self._API_KEY))), 'anvts': server_time, }, } @@ -284,5 +309,6 @@ class AnvatoIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) access_key, video_id = mobj.group('access_key_or_mcp', 'id') if access_key not in self._ANVACK_TABLE: - access_key = self._MCP_TO_ACCESS_KEY_TABLE[access_key] + access_key = self._MCP_TO_ACCESS_KEY_TABLE.get( + access_key) or access_key return self._get_anvato_videos(access_key, video_id) From 28f96cf407cecbac21fe2c7d3417928dae3ab3b5 Mon Sep 17 00:00:00 2001 From: hmlinaric <mlinaric.hrvoje@gmail.com> Date: Tue, 21 Aug 2018 19:06:27 +0200 Subject: [PATCH 141/558] [6play] Add support for play.rtl.hr --- youtube_dl/extractor/sixplay.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/sixplay.py b/youtube_dl/extractor/sixplay.py index a363221bc..207ab4477 100644 --- a/youtube_dl/extractor/sixplay.py +++ b/youtube_dl/extractor/sixplay.py @@ -19,7 +19,7 @@ from ..utils import ( class SixPlayIE(InfoExtractor): IE_NAME = '6play' - _VALID_URL = r'(?:6play:|https?://(?:www\.)?(?P<domain>6play\.fr|rtlplay.be)/.+?-c_)(?P<id>[0-9]+)' + _VALID_URL = r'(?:6play:|https?://(?:www\.)?(?P<domain>6play\.fr|rtlplay\.be|play\.rtl\.hr)/.+?-c_)(?P<id>[0-9]+)' _TESTS = [{ 'url': 'https://www.6play.fr/minute-par-minute-p_9533/le-but-qui-a-marque-lhistoire-du-football-francais-c_12041051', 'md5': '31fcd112637baa0c2ab92c4fcd8baf27', @@ -32,6 +32,9 @@ class SixPlayIE(InfoExtractor): }, { 'url': 'https://www.rtlplay.be/rtl-info-13h-p_8551/les-titres-du-rtlinfo-13h-c_12045869', 'only_matching': True, + }, { + 'url': 'https://play.rtl.hr/pj-masks-p_9455/epizoda-34-sezona-1-catboyevo-cudo-na-dva-kotaca-c_11984989', + 'only_matching': True, }] def _real_extract(self, url): @@ -39,6 +42,7 @@ class SixPlayIE(InfoExtractor): service, consumer_name = { '6play.fr': ('6play', 'm6web'), 'rtlplay.be': ('rtlbe_rtl_play', 'rtlbe'), + 'play.rtl.hr': ('rtlhr_rtl_play', 'rtlhr'), }.get(domain, ('6play', 'm6web')) data = self._download_json( From 52007de8ca6fcc2b72cbfb3fe026ea63cda88f25 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 22 Aug 2018 01:14:47 +0700 Subject: [PATCH 142/558] [go] Add support for disneynow.go.com (closes #16299, closes #17264) --- youtube_dl/extractor/go.py | 30 ++++++++++++++++++++++++------ 1 file changed, 24 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/go.py b/youtube_dl/extractor/go.py index e781405f2..ec9dd6e3a 100644 --- a/youtube_dl/extractor/go.py +++ b/youtube_dl/extractor/go.py @@ -36,7 +36,8 @@ class GoIE(AdobePassIE): 'requestor_id': 'DisneyXD', } } - _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))' % '|'.join(_SITE_INFO.keys()) + _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))'\ + % '|'.join(list(_SITE_INFO.keys()) + ['disneynow']) _TESTS = [{ 'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643', 'info_dict': { @@ -62,6 +63,14 @@ class GoIE(AdobePassIE): }, { 'url': 'http://abc.go.com/shows/world-news-tonight/episode-guide/2017-02/17-021717-intense-stand-off-between-man-with-rifle-and-police-in-oakland', 'only_matching': True, + }, { + # brand 004 + 'url': 'http://disneynow.go.com/shows/big-hero-6-the-series/season-01/episode-10-mr-sparkles-loses-his-sparkle/vdka4637915', + 'only_matching': True, + }, { + # brand 008 + 'url': 'http://disneynow.go.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013', + 'only_matching': True, }] def _extract_videos(self, brand, video_id='-1', show_id='-1'): @@ -72,14 +81,23 @@ class GoIE(AdobePassIE): def _real_extract(self, url): sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups() - site_info = self._SITE_INFO[sub_domain] - brand = site_info['brand'] - if not video_id: - webpage = self._download_webpage(url, display_id) + site_info = self._SITE_INFO.get(sub_domain, {}) + brand = site_info.get('brand') + if not video_id or not site_info: + webpage = self._download_webpage(url, display_id or video_id) video_id = self._search_regex( # There may be inner quotes, e.g. data-video-id="'VDKA3609139'" # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood - r'data-video-id=["\']*(VDKA\w+)', webpage, 'video id', default=None) + r'data-video-id=["\']*(VDKA\w+)', webpage, 'video id', + default=None) + if not site_info: + brand = self._search_regex( + (r'data-brand=\s*["\']\s*(\d+)', + r'data-page-brand=\s*["\']\s*(\d+)'), webpage, 'brand', + default='004') + site_info = next( + si for _, si in self._SITE_INFO.items() + if si.get('brand') == brand) if not video_id: # show extraction works for Disney, DisneyJunior and DisneyXD # ABC and Freeform has different layout From db192b29329696547b422d904819321077efddfe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 22 Aug 2018 01:44:22 +0700 Subject: [PATCH 143/558] [yourporn] Add extractor (closes #17298) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/yourporn.py | 41 ++++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+) create mode 100644 youtube_dl/extractor/yourporn.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 23ad42da9..d8e86c277 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1424,6 +1424,7 @@ from .younow import ( YouNowMomentIE, ) from .youporn import YouPornIE +from .yourporn import YourPornIE from .yourupload import YourUploadIE from .youtube import ( YoutubeIE, diff --git a/youtube_dl/extractor/yourporn.py b/youtube_dl/extractor/yourporn.py new file mode 100644 index 000000000..6602f7c03 --- /dev/null +++ b/youtube_dl/extractor/yourporn.py @@ -0,0 +1,41 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import urljoin + + +class YourPornIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?yourporn\.sexy/post/(?P<id>[^/?#&.]+)' + _TEST = { + 'url': 'https://yourporn.sexy/post/57ffcb2e1179b.html', + 'md5': '6f8682b6464033d87acaa7a8ff0c092e', + 'info_dict': { + 'id': '57ffcb2e1179b', + 'ext': 'mp4', + 'title': 'md5:c9f43630bd968267672651ba905a7d35', + 'thumbnail': r're:^https?://.*\.jpg$', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + video_url = urljoin(url, self._parse_json( + self._search_regex( + r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info', + group='data'), + video_id)[video_id]) + + title = (self._search_regex( + r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title', + default=None) or self._og_search_description(webpage)).strip() + thumbnail = self._og_search_thumbnail(webpage) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + } From df4d817bc3802e776c5056c3288953aa0ff817b1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 22 Aug 2018 02:19:30 +0700 Subject: [PATCH 144/558] [kinopoisk] Add extractor (closes #17283) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/kinopoisk.py | 70 ++++++++++++++++++++++++++++++ 2 files changed, 71 insertions(+) create mode 100644 youtube_dl/extractor/kinopoisk.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index d8e86c277..9fc1cfa70 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -520,6 +520,7 @@ from .keezmovies import KeezMoviesIE from .ketnet import KetnetIE from .khanacademy import KhanAcademyIE from .kickstarter import KickStarterIE +from .kinopoisk import KinoPoiskIE from .keek import KeekIE from .konserthusetplay import KonserthusetPlayIE from .kontrtube import KontrTubeIE diff --git a/youtube_dl/extractor/kinopoisk.py b/youtube_dl/extractor/kinopoisk.py new file mode 100644 index 000000000..9e8d01f53 --- /dev/null +++ b/youtube_dl/extractor/kinopoisk.py @@ -0,0 +1,70 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + dict_get, + int_or_none, +) + + +class KinoPoiskIE(InfoExtractor): + _GEO_COUNTRIES = ['RU'] + _VALID_URL = r'https?://(?:www\.)?kinopoisk\.ru/film/(?P<id>\d+)' + _TESTS = [{ + 'url': 'https://www.kinopoisk.ru/film/81041/watch/', + 'md5': '4f71c80baea10dfa54a837a46111d326', + 'info_dict': { + 'id': '81041', + 'ext': 'mp4', + 'title': 'Алеша попович и тугарин змей', + 'description': 'md5:43787e673d68b805d0aa1df5a5aea701', + 'thumbnail': r're:^https?://.*', + 'duration': 4533, + 'age_limit': 12, + }, + 'params': { + 'format': 'bestvideo', + }, + }, { + 'url': 'https://www.kinopoisk.ru/film/81041', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage( + 'https://ott-widget.kinopoisk.ru/v1/kp/', video_id, + query={'kpId': video_id}) + + data = self._parse_json( + self._search_regex( + r'(?s)<script[^>]+\btype=["\']application/json[^>]+>(.+?)<', + webpage, 'data'), + video_id)['models'] + + film = data['filmStatus'] + title = film.get('title') or film['originalTitle'] + + formats = self._extract_m3u8_formats( + data['playlistEntity']['uri'], video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls') + self._sort_formats(formats) + + description = dict_get( + film, ('descriptscription', 'description', + 'shortDescriptscription', 'shortDescription')) + thumbnail = film.get('coverUrl') or film.get('posterUrl') + duration = int_or_none(film.get('duration')) + age_limit = int_or_none(film.get('restrictionAge')) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'age_limit': age_limit, + 'formats': formats, + } From b662273989ec18e9905b67467b5feded30f19d4b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 22 Aug 2018 02:28:25 +0700 Subject: [PATCH 145/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/ChangeLog b/ChangeLog index 665503827..a4cc6e4ac 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,27 @@ +version <unreleased> + +Core +* [utils] Use pure browser header for User-Agent (#17236) + +Extractors ++ [kinopoisk] Add support for kinopoisk.ru (#17283) ++ [yourporn] Add support for yourporn.sexy (#17298) ++ [go] Add support for disneynow.go.com (#16299, #17264) ++ [6play] Add support for play.rtl.hr (#17249) +* [anvato] Fallback to generic API key for access-key-to-API-key lookup + (#16788, #17254) +* [lci] Fix extraction (#17274) +* [bbccouk] Extend id URL regular expression (#17270) +* [cwtv] Fix extraction (#17256) +* [nova] Fix extraction (#17241) ++ [generic] Add support for expressen embeds +* [raywenderlich] Adapt to site redesign (#17225) ++ [redbulltv] Add support redbull.com tv URLs (#17218) ++ [bitchute] Add support for bitchute.com (#14052) ++ [clyp] Add support for token protected media (#17184) +* [imdb] Fix extension extraction (#17167) + + version 2018.08.04 Extractors From 4c86163b60ee3acc7f4b02c59c80d9027f378288 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 22 Aug 2018 02:32:18 +0700 Subject: [PATCH 146/558] release 2018.08.22 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 5 +++++ youtube_dl/version.py | 2 +- 4 files changed, 10 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 20433e915..6d54efbc3 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.08.04*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.08.04** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.08.22*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.08.22** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.08.04 +[debug] youtube-dl version 2018.08.22 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index a4cc6e4ac..c34e9682a 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.08.22 Core * [utils] Use pure browser header for User-Agent (#17236) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 4bf2ec81b..5d2a355ff 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -108,6 +108,8 @@ - **BiliBili** - **BioBioChileTV** - **BIQLE** + - **BitChute** + - **BitChuteChannel** - **BleacherReport** - **BleacherReportCMS** - **blinkx** @@ -405,6 +407,7 @@ - **Ketnet** - **KhanAcademy** - **KickStarter** + - **KinoPoisk** - **KonserthusetPlay** - **kontrtube**: KontrTube.ru - Труба зовёт - **KrasView**: Красвью @@ -696,6 +699,7 @@ - **RaiPlayLive** - **RaiPlayPlaylist** - **RayWenderlich** + - **RayWenderlichCourse** - **RBMARadio** - **RDS**: RDS.ca - **RedBullTV** @@ -1093,6 +1097,7 @@ - **YouNowLive** - **YouNowMoment** - **YouPorn** + - **YourPorn** - **YourUpload** - **youtube**: YouTube.com - **youtube:channel**: YouTube.com channels diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 67394fa01..f68848389 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.08.04' +__version__ = '2018.08.22' From c707d2067d649f23f03cf11995d1eeb665d51838 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 22 Aug 2018 23:18:07 +0700 Subject: [PATCH 147/558] [nova:embed] Add extractor (closes #17282) --- youtube_dl/extractor/extractors.py | 5 +- youtube_dl/extractor/nova.py | 138 ++++++++++++++++++++--------- 2 files changed, 101 insertions(+), 42 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 9fc1cfa70..a8b89bcde 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -741,7 +741,10 @@ from .nonktube import NonkTubeIE from .noovo import NoovoIE from .normalboots import NormalbootsIE from .nosvideo import NosVideoIE -from .nova import NovaIE +from .nova import ( + NovaEmbedIE, + NovaIE, +) from .novamov import ( AuroraVidIE, CloudTimeIE, diff --git a/youtube_dl/extractor/nova.py b/youtube_dl/extractor/nova.py index edf8b82c6..80186ec50 100644 --- a/youtube_dl/extractor/nova.py +++ b/youtube_dl/extractor/nova.py @@ -6,30 +6,90 @@ import re from .common import InfoExtractor from ..utils import ( clean_html, + int_or_none, js_to_json, + qualities, unified_strdate, url_or_none, ) +class NovaEmbedIE(InfoExtractor): + _VALID_URL = r'https?://media\.cms\.nova\.cz/embed/(?P<id>[^/?#&]+)' + _TEST = { + 'url': 'https://media.cms.nova.cz/embed/8o0n0r?autoplay=1', + 'md5': 'b3834f6de5401baabf31ed57456463f7', + 'info_dict': { + 'id': '8o0n0r', + 'ext': 'mp4', + 'title': '2180. díl', + 'thumbnail': r're:^https?://.*\.jpg', + 'duration': 2578, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + bitrates = self._parse_json( + self._search_regex( + r'(?s)bitrates\s*=\s*({.+?})\s*;', webpage, 'formats'), + video_id, transform_source=js_to_json) + + QUALITIES = ('lq', 'mq', 'hq', 'hd') + quality_key = qualities(QUALITIES) + + formats = [] + for format_id, format_list in bitrates.items(): + if not isinstance(format_list, list): + continue + for format_url in format_list: + format_url = url_or_none(format_url) + if not format_url: + continue + f = { + 'url': format_url, + } + f_id = format_id + for quality in QUALITIES: + if '%s.mp4' % quality in format_url: + f_id += '-%s' % quality + f.update({ + 'quality': quality_key(quality), + 'format_note': quality.upper(), + }) + break + f['format_id'] = f_id + formats.append(f) + self._sort_formats(formats) + + title = self._og_search_title( + webpage, default=None) or self._search_regex( + (r'<value>(?P<title>[^<]+)', + r'videoTitle\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage, + 'title', group='value') + thumbnail = self._og_search_thumbnail( + webpage, default=None) or self._search_regex( + r'poster\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, + 'thumbnail', fatal=False, group='value') + duration = int_or_none(self._search_regex( + r'videoDuration\s*:\s*(\d+)', webpage, 'duration', fatal=False)) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, + } + + class NovaIE(InfoExtractor): IE_DESC = 'TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz' _VALID_URL = r'https?://(?:[^.]+\.)?(?P<site>tv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P<id>[^/]+?)(?:\.html|/|$)' _TESTS = [{ - 'url': 'http://tvnoviny.nova.cz/clanek/novinky/co-na-sebe-sportaci-praskli-vime-jestli-pujde-hrdlicka-na-materskou.html?utm_source=tvnoviny&utm_medium=cpfooter&utm_campaign=novaplus', - 'info_dict': { - 'id': '1608920', - 'display_id': 'co-na-sebe-sportaci-praskli-vime-jestli-pujde-hrdlicka-na-materskou', - 'ext': 'flv', - 'title': 'Duel: Michal Hrdlička a Petr Suchoň', - 'description': 'md5:d0cc509858eee1b1374111c588c6f5d5', - 'thumbnail': r're:^https?://.*\.(?:jpg)', - }, - 'params': { - # rtmp download - 'skip_download': True, - } - }, { 'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html#player_13260', 'md5': '1dd7b9d5ea27bc361f110cd855a19bd3', 'info_dict': { @@ -40,33 +100,6 @@ class NovaIE(InfoExtractor): 'description': 'md5:f0a42dd239c26f61c28f19e62d20ef53', 'thumbnail': r're:^https?://.*\.(?:jpg)', } - }, { - 'url': 'http://novaplus.nova.cz/porad/policie-modrava/video/5591-policie-modrava-15-dil-blondynka-na-hrbitove', - 'info_dict': { - 'id': '1756825', - 'display_id': '5591-policie-modrava-15-dil-blondynka-na-hrbitove', - 'ext': 'flv', - 'title': 'Policie Modrava - 15. díl - Blondýnka na hřbitově', - 'description': 'md5:dc24e50be5908df83348e50d1431295e', # Make sure this description is clean of html tags - 'thumbnail': r're:^https?://.*\.(?:jpg)', - }, - 'params': { - # rtmp download - 'skip_download': True, - } - }, { - 'url': 'http://novaplus.nova.cz/porad/televizni-noviny/video/5585-televizni-noviny-30-5-2015/', - 'info_dict': { - 'id': '1756858', - 'ext': 'flv', - 'title': 'Televizní noviny - 30. 5. 2015', - 'thumbnail': r're:^https?://.*\.(?:jpg)', - 'upload_date': '20150530', - }, - 'params': { - # rtmp download - 'skip_download': True, - } }, { 'url': 'http://fanda.nova.cz/clanek/fun-and-games/krvavy-epos-zaklinac-3-divoky-hon-vychazi-vyhrajte-ho-pro-sebe.html', 'info_dict': { @@ -81,6 +114,20 @@ class NovaIE(InfoExtractor): # rtmp download 'skip_download': True, } + }, { + # media.cms.nova.cz embed + 'url': 'https://novaplus.nova.cz/porad/ulice/epizoda/18760-2180-dil', + 'info_dict': { + 'id': '8o0n0r', + 'ext': 'mp4', + 'title': '2180. díl', + 'thumbnail': r're:^https?://.*\.jpg', + 'duration': 2578, + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': [NovaEmbedIE.ie_key()], }, { 'url': 'http://sport.tn.nova.cz/clanek/sport/hokej/nhl/zivot-jde-dal-hodnotil-po-vyrazeni-z-playoff-jiri-sekac.html', 'only_matching': True, @@ -105,6 +152,15 @@ class NovaIE(InfoExtractor): webpage = self._download_webpage(url, display_id) + # novaplus + embed_id = self._search_regex( + r'<iframe[^>]+\bsrc=["\'](?:https?:)?//media\.cms\.nova\.cz/embed/([^/?#&]+)', + webpage, 'embed url', default=None) + if embed_id: + return self.url_result( + 'https://media.cms.nova.cz/embed/%s' % embed_id, + ie=NovaEmbedIE.ie_key(), video_id=embed_id) + video_id = self._search_regex( [r"(?:media|video_id)\s*:\s*'(\d+)'", r'media=(\d+)', From 135e6a1c107f49e7968013a57c33eea615406b96 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 24 Aug 2018 02:36:56 +0700 Subject: [PATCH 148/558] [vidzi] Add support for vidzi.nu (closes #17316) --- youtube_dl/extractor/vidzi.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/vidzi.py b/youtube_dl/extractor/vidzi.py index d70283479..42ea4952c 100644 --- a/youtube_dl/extractor/vidzi.py +++ b/youtube_dl/extractor/vidzi.py @@ -13,7 +13,7 @@ from ..utils import ( class VidziIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?vidzi\.(?:tv|cc|si)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)' + _VALID_URL = r'https?://(?:www\.)?vidzi\.(?:tv|cc|si|nu)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)' _TESTS = [{ 'url': 'http://vidzi.tv/cghql9yq6emu.html', 'md5': '4f16c71ca0c8c8635ab6932b5f3f1660', @@ -35,6 +35,9 @@ class VidziIE(InfoExtractor): }, { 'url': 'https://vidzi.si/rph9gztxj1et.html', 'only_matching': True, + }, { + 'url': 'http://vidzi.nu/cghql9yq6emu.html', + 'only_matching': True, }] def _real_extract(self, url): From beff09505cc4a7a980901c6e48adc1620aa417aa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 24 Aug 2018 04:00:35 +0700 Subject: [PATCH 149/558] [xfileshare] Add support for vidto.se (closes #17317) --- youtube_dl/extractor/xfileshare.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/xfileshare.py b/youtube_dl/extractor/xfileshare.py index bc3239f68..b38c7a7b3 100644 --- a/youtube_dl/extractor/xfileshare.py +++ b/youtube_dl/extractor/xfileshare.py @@ -23,7 +23,7 @@ class XFileShareIE(InfoExtractor): (r'powerwatch\.pw', 'PowerWatch'), (r'rapidvideo\.ws', 'Rapidvideo.ws'), (r'thevideobee\.to', 'TheVideoBee'), - (r'vidto\.me', 'Vidto'), + (r'vidto\.(?:me|se)', 'Vidto'), (r'streamin\.to', 'Streamin.To'), (r'xvidstage\.com', 'XVIDSTAGE'), (r'vidabc\.com', 'Vid ABC'), @@ -115,7 +115,10 @@ class XFileShareIE(InfoExtractor): 'only_matching': True, }, { 'url': 'http://www.fastvideo.me/k8604r8nk8sn/FAST_FURIOUS_8_-_Trailer_italiano_ufficiale.mp4.html', - 'only_matching': True + 'only_matching': True, + }, { + 'url': 'http://vidto.se/1tx1pf6t12cg.html', + 'only_matching': True, }] @staticmethod From e0b6e988710037791057cd0b65f795d44e2f534c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 24 Aug 2018 23:12:53 +0700 Subject: [PATCH 150/558] [generic] Allow relative src for videojs embeds (closes #17324) --- youtube_dl/extractor/generic.py | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 83a31f3d3..096348513 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2071,6 +2071,21 @@ class GenericIE(InfoExtractor): }, 'playlist_count': 6, }, + { + # videojs embed + 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904', + 'info_dict': { + 'id': 'shell', + 'ext': 'mp4', + 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано', + 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1', + 'thumbnail': r're:^https?://.*\.jpg$', + }, + 'params': { + 'skip_download': True, + }, + 'expected_warnings': ['Failed to download MPD manifest'], + }, # { # # TODO: find another test # # http://schema.org/VideoObject @@ -3152,8 +3167,8 @@ class GenericIE(InfoExtractor): sources = [sources] formats = [] for source in sources: - src = url_or_none(source.get('src')) - if not src: + src = source.get('src') + if not src or not isinstance(src, compat_str): continue src = compat_urlparse.urljoin(url, src) src_type = source.get('type') From dac6f7654a577533ebcb825f34f0d7735274b205 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 26 Aug 2018 20:07:52 +0700 Subject: [PATCH 151/558] [tvplayhome] Add extractor (closes #17344) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/tvplay.py | 114 ++++++++++++++++++++++++++++- 2 files changed, 112 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index a8b89bcde..6012d0f5f 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1181,6 +1181,7 @@ from .tvp import ( from .tvplay import ( TVPlayIE, ViafreeIE, + TVPlayHomeIE, ) from .tvplayer import TVPlayerIE from .tweakers import TweakersIE diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py index d3adab457..8f1ff3b76 100644 --- a/youtube_dl/extractor/tvplay.py +++ b/youtube_dl/extractor/tvplay.py @@ -32,12 +32,12 @@ class TVPlayIE(InfoExtractor): https?:// (?:www\.)? (?: - tvplay(?:\.skaties)?\.lv/parraides| - (?:tv3play|play\.tv3)\.lt/programos| + tvplay(?:\.skaties)?\.lv(?:/parraides)?| + (?:tv3play|play\.tv3)\.lt(?:/programos)?| tv3play(?:\.tv3)?\.ee/sisu| (?:tv(?:3|6|8|10)play|viafree)\.se/program| (?:(?:tv3play|viasat4play|tv6play|viafree)\.no|(?:tv3play|viafree)\.dk)/programmer| - play\.novatv\.bg/programi + play\.nova(?:tv)?\.bg/programi ) /(?:[^/]+/)+ ) @@ -203,10 +203,18 @@ class TVPlayIE(InfoExtractor): 'skip_download': True, }, }, + { + 'url': 'https://play.nova.bg/programi/zdravei-bulgariya/764300?autostart=true', + 'only_matching': True, + }, { 'url': 'http://tvplay.skaties.lv/parraides/vinas-melo-labak/418113?autostart=true', 'only_matching': True, }, + { + 'url': 'https://tvplay.skaties.lv/vinas-melo-labak/418113/?autostart=true', + 'only_matching': True, + }, { # views is null 'url': 'http://tvplay.skaties.lv/parraides/tv3-zinas/760183', @@ -288,6 +296,7 @@ class TVPlayIE(InfoExtractor): 'url': m.group('url'), 'app': m.group('app'), 'play_path': m.group('playpath'), + 'preference': -1, }) else: fmt.update({ @@ -447,3 +456,102 @@ class ViafreeIE(InfoExtractor): 'skip_rtmp': True, }), ie=TVPlayIE.ie_key(), video_id=video_id) + + +class TVPlayHomeIE(InfoExtractor): + _VALID_URL = r'https?://tvplay\.(?:tv3\.lt|skaties\.lv|tv3\.ee)/[^/]+/[^/?#&]+-(?P<id>\d+)' + _TESTS = [{ + 'url': 'https://tvplay.tv3.lt/aferistai-n-7/aferistai-10047125/', + 'info_dict': { + 'id': '366367', + 'ext': 'mp4', + 'title': 'Aferistai', + 'description': 'Aferistai. Kalėdinė pasaka.', + 'series': 'Aferistai [N-7]', + 'season': '1 sezonas', + 'season_number': 1, + 'duration': 464, + 'timestamp': 1394209658, + 'upload_date': '20140307', + 'age_limit': 18, + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': [TVPlayIE.ie_key()], + }, { + 'url': 'https://tvplay.skaties.lv/vinas-melo-labak/vinas-melo-labak-10280317/', + 'only_matching': True, + }, { + 'url': 'https://tvplay.tv3.ee/cool-d-ga-mehhikosse/cool-d-ga-mehhikosse-10044354/', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + video_id = self._search_regex( + r'data-asset-id\s*=\s*["\'](\d{5,7})\b', webpage, 'video id', + default=None) + + if video_id: + return self.url_result( + 'mtg:%s' % video_id, ie=TVPlayIE.ie_key(), video_id=video_id) + + m3u8_url = self._search_regex( + r'data-file\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, + 'm3u8 url', group='url') + + formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + self._sort_formats(formats) + + title = self._search_regex( + r'data-title\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, + 'title', default=None, group='value') or self._html_search_meta( + 'title', webpage, default=None) or self._og_search_title( + webpage) + + description = self._html_search_meta( + 'description', webpage, + default=None) or self._og_search_description(webpage) + + thumbnail = self._search_regex( + r'data-image\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, + 'thumbnail', default=None, group='url') or self._html_search_meta( + 'thumbnail', webpage, default=None) or self._og_search_thumbnail( + webpage) + + duration = int_or_none(self._search_regex( + r'data-duration\s*=\s*["\'](\d+)', webpage, 'duration', + fatal=False)) + + season = self._search_regex( + (r'data-series-title\s*=\s*(["\'])[^/]+/(?P<value>(?:(?!\1).)+)\1', + r'\bseason\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage, + 'season', default=None, group='value') + season_number = int_or_none(self._search_regex( + r'(\d+)(?:[.\s]+sezona|\s+HOOAEG)', season or '', 'season number', + default=None)) + episode = self._search_regex( + r'(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, 'episode', + default=None, group='value') + episode_number = int_or_none(self._search_regex( + r'(?:S[eē]rija|Osa)\s+(\d+)', episode or '', 'episode number', + default=None)) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'season': season, + 'season_number': season_number, + 'episode': episode, + 'episode_number': episode_number, + 'formats': formats, + } From 287cf7e443814b405caac87449ee34fb055cc6b7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 26 Aug 2018 20:08:31 +0700 Subject: [PATCH 152/558] [generic] Remove unused import --- youtube_dl/extractor/generic.py | 1 - 1 file changed, 1 deletion(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 096348513..229dfda1b 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -32,7 +32,6 @@ from ..utils import ( unified_strdate, unsmuggle_url, UnsupportedError, - url_or_none, xpath_text, ) from .commonprotocols import RtmpIE From dd88fd65a5eda12694104afa3fa891c640de71c6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 26 Aug 2018 21:41:55 +0700 Subject: [PATCH 153/558] [webofstories:playlist] Fix extraction (closes #16914) --- youtube_dl/extractor/webofstories.py | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/webofstories.py b/youtube_dl/extractor/webofstories.py index 1eb1f6702..f2b8d19b4 100644 --- a/youtube_dl/extractor/webofstories.py +++ b/youtube_dl/extractor/webofstories.py @@ -4,7 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + orderedSet, +) class WebOfStoriesIE(InfoExtractor): @@ -133,8 +136,10 @@ class WebOfStoriesPlaylistIE(InfoExtractor): webpage = self._download_webpage(url, playlist_id) entries = [ - self.url_result('http://www.webofstories.com/play/%s' % video_number, 'WebOfStories') - for video_number in set(re.findall(r'href="/playAll/%s\?sId=(\d+)"' % playlist_id, webpage)) + self.url_result( + 'http://www.webofstories.com/play/%s' % video_id, + 'WebOfStories', video_id=video_id) + for video_id in orderedSet(re.findall(r'\bid=["\']td_(\d+)', webpage)) ] title = self._search_regex( From 02df41354cfae04555b3f78b2fcca3e66ec7faba Mon Sep 17 00:00:00 2001 From: Andrew Udvare <Tatsh@users.noreply.github.com> Date: Mon, 27 Aug 2018 11:04:56 -0400 Subject: [PATCH 154/558] [bitchute] Fix extraction by pass custom User-Agent --- youtube_dl/extractor/bitchute.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py index da263714a..446a1ab19 100644 --- a/youtube_dl/extractor/bitchute.py +++ b/youtube_dl/extractor/bitchute.py @@ -33,7 +33,9 @@ class BitChuteIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage( - 'https://www.bitchute.com/video/%s' % video_id, video_id) + 'https://www.bitchute.com/video/%s' % video_id, video_id, headers={ + 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.57 Safari/537.36', + }) title = self._search_regex( (r'<[^>]+\bid=["\']video-title[^>]+>([^<]+)', r'<title>([^<]+)'), From 409b9324da3ead199b26081b228b042b0b494f8d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 28 Aug 2018 02:14:47 +0700 Subject: [PATCH 155/558] [youtube:playlist] Add support for music album playlists (OLAK5uy_ prefix) (closes #17361) --- youtube_dl/extractor/youtube.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 117a57911..0442906df 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -64,7 +64,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor): # If True it will raise an error if no login info is provided _LOGIN_REQUIRED = False - _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL)[0-9A-Za-z-_]{10,}' + _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)[0-9A-Za-z-_]{10,}' def _set_language(self): self._set_cookie( @@ -2123,7 +2123,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist= ) ( - (?:PL|LL|EC|UU|FL|RD|UL|TL)?[0-9A-Za-z-_]{10,} + (?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)?[0-9A-Za-z-_]{10,} # Top tracks, they can also include dots |(?:MC)[\w\.]* ) @@ -2261,6 +2261,10 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): }, { 'url': 'TLGGrESM50VT6acwMjAyMjAxNw', 'only_matching': True, + }, { + # music album playlist + 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', + 'only_matching': True, }] def _real_initialize(self): From 56213aff1d8bd8f06a940fcbd65a96a3baad9d1e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 28 Aug 2018 03:07:18 +0700 Subject: [PATCH 156/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/ChangeLog b/ChangeLog index c34e9682a..71174bbe6 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,17 @@ +version <unreleased> + +Extractors ++ [youtube:playlist] Add support for music album playlists (OLAK5uy_ prefix) + (#17361) +* [bitchute] Fix extraction by pass custom User-Agent (#17360) +* [webofstories:playlist] Fix extraction (#16914) ++ [tvplayhome] Add support for new tvplay URLs (#17344) ++ [generic] Allow relative src for videojs embeds (#17324) ++ [xfileshare] Add support for vidto.se (#17317) ++ [vidzi] Add support for vidzi.nu (#17316) ++ [nova:embed] Add support for media.cms.nova.cz (#17282) + + version 2018.08.22 Core From eebbce5656fd7d626594aa54d2d1ec545d9ae53a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 28 Aug 2018 03:10:09 +0700 Subject: [PATCH 157/558] release 2018.08.28 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 2 ++ youtube_dl/version.py | 2 +- 4 files changed, 7 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 6d54efbc3..0816c4f5f 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.08.22*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.08.22** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.08.28*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.08.28** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.08.22 +[debug] youtube-dl version 2018.08.28 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 71174bbe6..49f44a6e6 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.08.28 Extractors + [youtube:playlist] Add support for music album playlists (OLAK5uy_ prefix) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 5d2a355ff..5beb9bc17 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -580,6 +580,7 @@ - **Normalboots** - **NosVideo** - **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz + - **NovaEmbed** - **nowness** - **nowness:playlist** - **nowness:series** @@ -916,6 +917,7 @@ - **tvp:embed**: Telewizja Polska - **tvp:series** - **TVPlayer** + - **TVPlayHome** - **Tweakers** - **twitch:chapter** - **twitch:clips** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index f68848389..3e3fe1375 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.08.22' +__version__ = '2018.08.28' From 8959018a5f3efc02f7402c44f4d3950c0811b97a Mon Sep 17 00:00:00 2001 From: Andrew Udvare <audvare@gmail.com> Date: Fri, 16 Mar 2018 20:11:47 -0400 Subject: [PATCH 158/558] [utils] Skip remote IP addresses non matching to source address' IP version (closes #13422) --- youtube_dl/utils.py | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 0c830ba71..2be8c95cd 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -882,7 +882,40 @@ def _create_http_connection(ydl_handler, http_class, is_https, *args, **kwargs): kwargs['strict'] = True hc = http_class(*args, **compat_kwargs(kwargs)) source_address = ydl_handler._params.get('source_address') + if source_address is not None: + filter_for = socket.AF_INET if '.' in source_address else socket.AF_INET6 + # This is to workaround _create_connection() from socket where it will try all + # address data from getaddrinfo() including IPv6. This filters the result from + # getaddrinfo() based on the source_address value. + # This is based on the cpython socket.create_connection() function. + # https://github.com/python/cpython/blob/master/Lib/socket.py#L691 + def _create_connection(address, timeout=socket._GLOBAL_DEFAULT_TIMEOUT, source_address=None): + host, port = address + err = None + addrs = socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM) + ip_addrs = [addr for addr in addrs if addr[0] == filter_for] + for res in ip_addrs: + af, socktype, proto, canonname, sa = res + sock = None + try: + sock = socket.socket(af, socktype, proto) + if timeout is not socket._GLOBAL_DEFAULT_TIMEOUT: + sock.settimeout(timeout) + sock.bind(source_address) + sock.connect(sa) + err = None # Explicitly break reference cycle + return sock + except socket.error as _: + err = _ + if sock is not None: + sock.close() + if err is not None: + raise err + else: + raise socket.error('Unknown error occurred') + hc._create_connection = _create_connection + sa = (source_address, 0) if hasattr(hc, 'source_address'): # Python 2.7+ hc.source_address = sa From 9e21e6d96bed929ba57b8ce775e2a0e29e54dd60 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 29 Aug 2018 01:17:21 +0700 Subject: [PATCH 159/558] [utils] Improve remote address skipping and add support for python 2.6 (closes #17362) --- youtube_dl/utils.py | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 2be8c95cd..bcfb72d43 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -49,7 +49,6 @@ from .compat import ( compat_os_name, compat_parse_qs, compat_shlex_quote, - compat_socket_create_connection, compat_str, compat_struct_pack, compat_struct_unpack, @@ -884,7 +883,6 @@ def _create_http_connection(ydl_handler, http_class, is_https, *args, **kwargs): source_address = ydl_handler._params.get('source_address') if source_address is not None: - filter_for = socket.AF_INET if '.' in source_address else socket.AF_INET6 # This is to workaround _create_connection() from socket where it will try all # address data from getaddrinfo() including IPv6. This filters the result from # getaddrinfo() based on the source_address value. @@ -894,7 +892,13 @@ def _create_http_connection(ydl_handler, http_class, is_https, *args, **kwargs): host, port = address err = None addrs = socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM) - ip_addrs = [addr for addr in addrs if addr[0] == filter_for] + af = socket.AF_INET if '.' in source_address[0] else socket.AF_INET6 + ip_addrs = [addr for addr in addrs if addr[0] == af] + if addrs and not ip_addrs: + ip_version = 'v4' if af == socket.AF_INET else 'v6' + raise socket.error( + "No remote IP%s addresses available for connect, can't use '%s' as source address" + % (ip_version, source_address[0])) for res in ip_addrs: af, socktype, proto, canonname, sa = res sock = None @@ -913,15 +917,15 @@ def _create_http_connection(ydl_handler, http_class, is_https, *args, **kwargs): if err is not None: raise err else: - raise socket.error('Unknown error occurred') - hc._create_connection = _create_connection - + raise socket.error('getaddrinfo returns an empty list') + if hasattr(hc, '_create_connection'): + hc._create_connection = _create_connection sa = (source_address, 0) if hasattr(hc, 'source_address'): # Python 2.7+ hc.source_address = sa else: # Python 2.6 def _hc_connect(self, *args, **kwargs): - sock = compat_socket_create_connection( + sock = _create_connection( (self.host, self.port), self.timeout, sa) if is_https: self.sock = ssl.wrap_socket( From 73f3bdbeb4b62a1286bcd74fdd1d5741740ea845 Mon Sep 17 00:00:00 2001 From: Leonardo Taccari <iamleot@gmail.com> Date: Thu, 30 Aug 2018 21:15:46 +0200 Subject: [PATCH 160/558] [internazionale] Fix extraction of non-available-abroad videos --- youtube_dl/extractor/internazionale.py | 27 +++++++++++++++++++++++--- 1 file changed, 24 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/internazionale.py b/youtube_dl/extractor/internazionale.py index 10ba1f6cf..676e8e269 100644 --- a/youtube_dl/extractor/internazionale.py +++ b/youtube_dl/extractor/internazionale.py @@ -7,7 +7,7 @@ from ..utils import unified_timestamp class InternazionaleIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?internazionale\.it/video/(?:[^/]+/)*(?P<id>[^/?#&]+)' - _TEST = { + _TESTS = [{ 'url': 'https://www.internazionale.it/video/2015/02/19/richard-linklater-racconta-una-scena-di-boyhood', 'md5': '3e39d32b66882c1218e305acbf8348ca', 'info_dict': { @@ -23,7 +23,23 @@ class InternazionaleIE(InfoExtractor): 'params': { 'format': 'bestvideo', }, - } + }, { + 'url': 'https://www.internazionale.it/video/2018/08/29/telefono-stare-con-noi-stessi', + 'md5': '9db8663704cab73eb972d1cee0082c79', + 'info_dict': { + 'id': '761344', + 'display_id': 'telefono-stare-con-noi-stessi', + 'ext': 'mp4', + 'title': 'Usiamo il telefono per evitare di stare con noi stessi', + 'description': 'md5:75ccfb0d6bcefc6e7428c68b4aa1fe44', + 'timestamp': 1535528954, + 'upload_date': '20180829', + 'thumbnail': r're:^https?://.*\.jpg$', + }, + 'params': { + 'format': 'bestvideo', + }, + }] def _real_extract(self, url): display_id = self._match_id(url) @@ -40,8 +56,13 @@ class InternazionaleIE(InfoExtractor): DATA_RE % 'job-id', webpage, 'video id', group='value') video_path = self._search_regex( DATA_RE % 'video-path', webpage, 'video path', group='value') + video_available_abroad = self._search_regex( + DATA_RE % 'video-available_abroad', webpage, + 'video available aboard', default='1', group='value') + video_available_abroad = video_available_abroad == '1' - video_base = 'https://video.internazionale.it/%s/%s.' % (video_path, video_id) + video_base = 'https://video%s.internazionale.it/%s/%s.' % \ + ('' if video_available_abroad else '-ita', video_path, video_id) formats = self._extract_m3u8_formats( video_base + 'm3u8', display_id, 'mp4', From 14b7a24c19d70ec172eaedf799bcf81445ac9403 Mon Sep 17 00:00:00 2001 From: Parmjit Virk <pvirk@mts.net> Date: Thu, 30 Aug 2018 14:32:35 -0500 Subject: [PATCH 161/558] [bandcamp] Extract track_number (closes #17266) --- youtube_dl/extractor/bandcamp.py | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py index b8514734d..bc4c5165a 100644 --- a/youtube_dl/extractor/bandcamp.py +++ b/youtube_dl/extractor/bandcamp.py @@ -44,6 +44,17 @@ class BandcampIE(InfoExtractor): 'title': 'Ben Prunty - Lanius (Battle)', 'uploader': 'Ben Prunty', }, + }, { + 'url': 'https://relapsealumni.bandcamp.com/track/hail-to-fire', + 'info_dict': { + 'id': '2584466013', + 'ext': 'mp3', + 'title': 'Hail to Fire', + 'track_number': 5, + }, + 'params': { + 'skip_download': True, + }, }] def _real_extract(self, url): @@ -82,6 +93,7 @@ class BandcampIE(InfoExtractor): 'thumbnail': thumbnail, 'formats': formats, 'duration': float_or_none(data.get('duration')), + 'track_number': int_or_none(data.get('track_num')), } else: raise ExtractorError('No free songs found') From 4991e16c2a62ecd1a81cbb9ff6563885c1bf6210 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 31 Aug 2018 03:35:55 +0700 Subject: [PATCH 162/558] [bandcamp] Extract more metadata (closes #13197) --- youtube_dl/extractor/bandcamp.py | 218 +++++++++++++++++++------------ 1 file changed, 134 insertions(+), 84 deletions(-) diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py index bc4c5165a..f14b407dc 100644 --- a/youtube_dl/extractor/bandcamp.py +++ b/youtube_dl/extractor/bandcamp.py @@ -1,6 +1,5 @@ from __future__ import unicode_literals -import json import random import re import time @@ -16,15 +15,18 @@ from ..utils import ( int_or_none, KNOWN_EXTENSIONS, parse_filesize, + str_or_none, + try_get, unescapeHTML, update_url_query, unified_strdate, + unified_timestamp, url_or_none, ) class BandcampIE(InfoExtractor): - _VALID_URL = r'https?://.*?\.bandcamp\.com/track/(?P<title>[^/?#&]+)' + _VALID_URL = r'https?://[^/]+\.bandcamp\.com/track/(?P<title>[^/?#&]+)' _TESTS = [{ 'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song', 'md5': 'c557841d5e50261777a6585648adf439', @@ -36,24 +38,44 @@ class BandcampIE(InfoExtractor): }, '_skip': 'There is a limit of 200 free downloads / month for the test song' }, { + # free download 'url': 'http://benprunty.bandcamp.com/track/lanius-battle', - 'md5': '0369ace6b939f0927e62c67a1a8d9fa7', + 'md5': '853e35bf34aa1d6fe2615ae612564b36', 'info_dict': { 'id': '2650410135', 'ext': 'aiff', 'title': 'Ben Prunty - Lanius (Battle)', + 'thumbnail': r're:^https?://.*\.jpg$', 'uploader': 'Ben Prunty', + 'timestamp': 1396508491, + 'upload_date': '20140403', + 'release_date': '20140403', + 'duration': 260.877, + 'track': 'Lanius (Battle)', + 'track_number': 1, + 'track_id': '2650410135', + 'artist': 'Ben Prunty', + 'album': 'FTL: Advanced Edition Soundtrack', }, }, { + # no free download, mp3 128 'url': 'https://relapsealumni.bandcamp.com/track/hail-to-fire', + 'md5': 'fec12ff55e804bb7f7ebeb77a800c8b7', 'info_dict': { 'id': '2584466013', 'ext': 'mp3', - 'title': 'Hail to Fire', + 'title': 'Mastodon - Hail to Fire', + 'thumbnail': r're:^https?://.*\.jpg$', + 'uploader': 'Mastodon', + 'timestamp': 1322005399, + 'upload_date': '20111122', + 'release_date': '20040207', + 'duration': 120.79, + 'track': 'Hail to Fire', 'track_number': 5, - }, - 'params': { - 'skip_download': True, + 'track_id': '2584466013', + 'artist': 'Mastodon', + 'album': 'Call of the Mastodon', }, }] @@ -62,19 +84,23 @@ class BandcampIE(InfoExtractor): title = mobj.group('title') webpage = self._download_webpage(url, title) thumbnail = self._html_search_meta('og:image', webpage, default=None) - m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage) - if not m_download: - m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage) - if m_trackinfo: - json_code = m_trackinfo.group(1) - data = json.loads(json_code)[0] - track_id = compat_str(data['id']) - if not data.get('file'): - raise ExtractorError('Not streamable', video_id=track_id, expected=True) + track_id = None + track = None + track_number = None + duration = None - formats = [] - for format_id, format_url in data['file'].items(): + formats = [] + track_info = self._parse_json( + self._search_regex( + r'trackinfo\s*:\s*\[\s*({.+?})\s*\]\s*,\s*?\n', + webpage, 'track info', default='{}'), title) + if track_info: + file_ = track_info.get('file') + if isinstance(file_, dict): + for format_id, format_url in file_.items(): + if not url_or_none(format_url): + continue ext, abr_str = format_id.split('-', 1) formats.append({ 'format_id': format_id, @@ -84,86 +110,110 @@ class BandcampIE(InfoExtractor): 'acodec': ext, 'abr': int_or_none(abr_str), }) + track = track_info.get('title') + track_id = str_or_none(track_info.get('track_id') or track_info.get('id')) + track_number = int_or_none(track_info.get('track_num')) + duration = float_or_none(track_info.get('duration')) - self._sort_formats(formats) + def extract(key): + return self._search_regex( + r'\b%s\s*["\']?\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % key, + webpage, key, default=None, group='value') - return { - 'id': track_id, - 'title': data['title'], - 'thumbnail': thumbnail, - 'formats': formats, - 'duration': float_or_none(data.get('duration')), - 'track_number': int_or_none(data.get('track_num')), - } - else: - raise ExtractorError('No free songs found') + artist = extract('artist') + album = extract('album_title') + timestamp = unified_timestamp( + extract('publish_date') or extract('album_publish_date')) + release_date = unified_strdate(extract('album_release_date')) - download_link = m_download.group(1) - video_id = self._search_regex( - r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$', - webpage, 'video id') + download_link = self._search_regex( + r'freeDownloadPage\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, + 'download link', default=None, group='url') + if download_link: + track_id = self._search_regex( + r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$', + webpage, 'track id') - download_webpage = self._download_webpage( - download_link, video_id, 'Downloading free downloads page') + download_webpage = self._download_webpage( + download_link, track_id, 'Downloading free downloads page') - blob = self._parse_json( - self._search_regex( - r'data-blob=(["\'])(?P<blob>{.+?})\1', download_webpage, - 'blob', group='blob'), - video_id, transform_source=unescapeHTML) + blob = self._parse_json( + self._search_regex( + r'data-blob=(["\'])(?P<blob>{.+?})\1', download_webpage, + 'blob', group='blob'), + track_id, transform_source=unescapeHTML) - info = blob['digital_items'][0] + info = try_get( + blob, (lambda x: x['digital_items'][0], + lambda x: x['download_items'][0]), dict) + if info: + downloads = info.get('downloads') + if isinstance(downloads, dict): + if not track: + track = info.get('title') + if not artist: + artist = info.get('artist') + if not thumbnail: + thumbnail = info.get('thumb_url') - downloads = info['downloads'] - track = info['title'] + download_formats = {} + download_formats_list = blob.get('download_formats') + if isinstance(download_formats_list, list): + for f in blob['download_formats']: + name, ext = f.get('name'), f.get('file_extension') + if all(isinstance(x, compat_str) for x in (name, ext)): + download_formats[name] = ext.strip('.') - artist = info.get('artist') - title = '%s - %s' % (artist, track) if artist else track + for format_id, f in downloads.items(): + format_url = f.get('url') + if not format_url: + continue + # Stat URL generation algorithm is reverse engineered from + # download_*_bundle_*.js + stat_url = update_url_query( + format_url.replace('/download/', '/statdownload/'), { + '.rand': int(time.time() * 1000 * random.random()), + }) + format_id = f.get('encoding_name') or format_id + stat = self._download_json( + stat_url, track_id, 'Downloading %s JSON' % format_id, + transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1], + fatal=False) + if not stat: + continue + retry_url = url_or_none(stat.get('retry_url')) + if not retry_url: + continue + formats.append({ + 'url': self._proto_relative_url(retry_url, 'http:'), + 'ext': download_formats.get(format_id), + 'format_id': format_id, + 'format_note': f.get('description'), + 'filesize': parse_filesize(f.get('size_mb')), + 'vcodec': 'none', + }) - download_formats = {} - for f in blob['download_formats']: - name, ext = f.get('name'), f.get('file_extension') - if all(isinstance(x, compat_str) for x in (name, ext)): - download_formats[name] = ext.strip('.') - - formats = [] - for format_id, f in downloads.items(): - format_url = f.get('url') - if not format_url: - continue - # Stat URL generation algorithm is reverse engineered from - # download_*_bundle_*.js - stat_url = update_url_query( - format_url.replace('/download/', '/statdownload/'), { - '.rand': int(time.time() * 1000 * random.random()), - }) - format_id = f.get('encoding_name') or format_id - stat = self._download_json( - stat_url, video_id, 'Downloading %s JSON' % format_id, - transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1], - fatal=False) - if not stat: - continue - retry_url = url_or_none(stat.get('retry_url')) - if not retry_url: - continue - formats.append({ - 'url': self._proto_relative_url(retry_url, 'http:'), - 'ext': download_formats.get(format_id), - 'format_id': format_id, - 'format_note': f.get('description'), - 'filesize': parse_filesize(f.get('size_mb')), - 'vcodec': 'none', - }) self._sort_formats(formats) + title = '%s - %s' % (artist, track) if artist else track + + if not duration: + duration = float_or_none(self._html_search_meta( + 'duration', webpage, default=None)) + return { - 'id': video_id, + 'id': track_id, 'title': title, - 'thumbnail': info.get('thumb_url') or thumbnail, - 'uploader': info.get('artist'), - 'artist': artist, + 'thumbnail': thumbnail, + 'uploader': artist, + 'timestamp': timestamp, + 'release_date': release_date, + 'duration': duration, 'track': track, + 'track_number': track_number, + 'track_id': track_id, + 'artist': artist, + 'album': album, 'formats': formats, } From c1a37eb24a78fe07a3ad41fc151389e444b7962b Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister <phihag@phihag.de> Date: Sat, 1 Sep 2018 00:18:17 +0200 Subject: [PATCH 163/558] [ard] Add support for Beta ARD Mediathek Thanks to https://blog.fefe.de/?ts=a577685d for pointing out support is missing. --- youtube_dl/extractor/ard.py | 62 ++++++++++++++++++++++++++++++ youtube_dl/extractor/extractors.py | 1 + 2 files changed, 63 insertions(+) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 23f574d36..9c6be2dd9 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -282,3 +282,65 @@ class ARDIE(InfoExtractor): 'upload_date': upload_date, 'thumbnail': thumbnail, } + + +class ARDBetaMediathekIE(InfoExtractor): + _VALID_URL = r'https://beta\.ardmediathek\.de/[a-z]+/player/(?P<video_id>[a-zA-Z0-9]+)/(?P<display_id>[^/?#]+)' + _TESTS = [{ + 'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita', + 'md5': '2d02d996156ea3c397cfc5036b5d7f8f', + 'info_dict': { + 'display_id': 'die-robuste-roswita', + 'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE', + 'title': 'Tatort: Die robuste Roswita', + 'description': r're:^Der Mord.*trüber ist als die Ilm.', + 'duration': 5316, + 'thumbnail': 'https://img.ardmediathek.de/standard/00/55/43/59/34/-1774185891/16x9/960?mandant=ard', + 'upload_date': '20180826', + 'ext': 'mp4', + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('video_id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + data_json = self._search_regex(r'window\.__APOLLO_STATE__\s*=\s*(\{.*);', webpage, 'json') + data = self._parse_json(data_json, display_id) + + res = { + 'id': video_id, + 'display_id': display_id, + } + formats = [] + for widget in data.values(): + if widget.get('_geoblocked'): + raise ExtractorError('This video is not available due to geoblocking', expected=True) + + if '_duration' in widget: + res['duration'] = widget['_duration'] + if 'clipTitle' in widget: + res['title'] = widget['clipTitle'] + if '_previewImage' in widget: + res['thumbnail'] = widget['_previewImage'] + if 'broadcastedOn' in widget: + res['upload_date'] = unified_strdate(widget['broadcastedOn']) + if 'synopsis' in widget: + res['description'] = widget['synopsis'] + if '_subtitleUrl' in widget: + res['subtitles'] = {'de': [{ + 'ext': 'ttml', + 'url': widget['_subtitleUrl'], + }]} + if '_quality' in widget: + formats.append({ + 'format_id': widget['_quality'], + 'url': widget['_stream']['json'][0], + }) + + self._sort_formats(formats) + res['formats'] = formats + + return res diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 6012d0f5f..995af9988 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -54,6 +54,7 @@ from .appletrailers import ( from .archiveorg import ArchiveOrgIE from .arkena import ArkenaIE from .ard import ( + ARDBetaMediathekIE, ARDIE, ARDMediathekIE, ) From 2b83da246375e6b37884aad9fe22ea8e461e20b3 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister <phihag@phihag.de> Date: Sat, 1 Sep 2018 00:45:36 +0200 Subject: [PATCH 164/558] [ard] Better format handling Skip f4m, doesn't work (yet); correctly extract m3u8, and prefer plain HTTP files. --- youtube_dl/extractor/ard.py | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 9c6be2dd9..cff8ca4a5 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -335,10 +335,24 @@ class ARDBetaMediathekIE(InfoExtractor): 'url': widget['_subtitleUrl'], }]} if '_quality' in widget: - formats.append({ - 'format_id': widget['_quality'], - 'url': widget['_stream']['json'][0], - }) + format_url = widget['_stream']['json'][0] + + if format_url.endswith('.f4m'): + # Skip f4m - these URLs just return a 403 + formats.append({ + 'format_id': 'f4m-' + widget['_quality'], + 'url': format_url, + 'preference': -1001, + }) + elif format_url.endswith('m3u8'): + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) + else: + formats.append({ + 'format_id': 'http-' + widget['_quality'], + 'url': format_url, + 'preference': 10, # Plain HTTP, that's nice + }) self._sort_formats(formats) res['formats'] = formats From ed6919e7371b3da66c10e4c5768816e81f4c5db3 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister <phihag@phihag.de> Date: Sat, 1 Sep 2018 01:59:13 +0200 Subject: [PATCH 165/558] [ard] beta mediathek: make regexp for JSON more robust --- youtube_dl/extractor/ard.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index cff8ca4a5..dcb347849 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -307,7 +307,7 @@ class ARDBetaMediathekIE(InfoExtractor): display_id = mobj.group('display_id') webpage = self._download_webpage(url, display_id) - data_json = self._search_regex(r'window\.__APOLLO_STATE__\s*=\s*(\{.*);', webpage, 'json') + data_json = self._search_regex(r'window\.__APOLLO_STATE__\s*=\s*(\{.*);\n', webpage, 'json') data = self._parse_json(data_json, display_id) res = { From 54a5be4dba3560ff51f98865b5598d361a878e82 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 1 Sep 2018 08:16:28 +0100 Subject: [PATCH 166/558] [crunchyroll] parse vilos media data(closes #17343) --- youtube_dl/extractor/crunchyroll.py | 205 ++++++++++++++++------------ youtube_dl/extractor/vrv.py | 48 ++++--- 2 files changed, 141 insertions(+), 112 deletions(-) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 463f995c7..4ed458372 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -7,7 +7,7 @@ import zlib from hashlib import sha1 from math import pow, sqrt, floor -from .common import InfoExtractor +from .vrv import VRVIE from ..compat import ( compat_b64decode, compat_etree_fromstring, @@ -18,6 +18,8 @@ from ..compat import ( from ..utils import ( ExtractorError, bytes_to_intlist, + extract_attributes, + float_or_none, intlist_to_bytes, int_or_none, lowercase_escape, @@ -26,14 +28,13 @@ from ..utils import ( unified_strdate, urlencode_postdata, xpath_text, - extract_attributes, ) from ..aes import ( aes_cbc_decrypt, ) -class CrunchyrollBaseIE(InfoExtractor): +class CrunchyrollBaseIE(VRVIE): _LOGIN_URL = 'https://www.crunchyroll.com/login' _LOGIN_FORM = 'login_form' _NETRC_MACHINE = 'crunchyroll' @@ -148,7 +149,7 @@ class CrunchyrollIE(CrunchyrollBaseIE): 'ext': 'mp4', 'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!', 'description': 'md5:2d17137920c64f2f49981a7797d275ef', - 'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg', + 'thumbnail': r're:^https?://.*\.jpg$', 'uploader': 'Yomiuri Telecasting Corporation (YTV)', 'upload_date': '20131013', 'url': 're:(?!.*&)', @@ -221,7 +222,7 @@ class CrunchyrollIE(CrunchyrollBaseIE): 'info_dict': { 'id': '535080', 'ext': 'mp4', - 'title': '11eyes Episode 1 – Piros éjszaka - Red Night', + 'title': '11eyes Episode 1 – Red Night ~ Piros éjszaka', 'description': 'Kakeru and Yuka are thrown into an alternate nightmarish world they call "Red Night".', 'uploader': 'Marvelous AQL Inc.', 'upload_date': '20091021', @@ -437,13 +438,18 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text if 'To view this, please log in to verify you are 18 or older.' in webpage: self.raise_login_required() + media = self._parse_json(self._search_regex( + r'vilos\.config\.media\s*=\s*({.+?});', + webpage, 'vilos media', default='{}'), video_id) + media_metadata = media.get('metadata') or {} + video_title = self._html_search_regex( r'(?s)<h1[^>]*>((?:(?!<h1).)*?<span[^>]+itemprop=["\']title["\'][^>]*>(?:(?!<h1).)+?)</h1>', webpage, 'video_title') video_title = re.sub(r' {2,}', ' ', video_title) - video_description = self._parse_json(self._html_search_regex( + video_description = (self._parse_json(self._html_search_regex( r'<script[^>]*>\s*.+?\[media_id=%s\].+?({.+?"description"\s*:.+?})\);' % video_id, - webpage, 'description', default='{}'), video_id).get('description') + webpage, 'description', default='{}'), video_id) or media_metadata).get('description') if video_description: video_description = lowercase_escape(video_description.replace(r'\r\n', '\n')) video_upload_date = self._html_search_regex( @@ -456,91 +462,99 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text [r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', r'<div>\s*Publisher:\s*<span>\s*(.+?)\s*</span>\s*</div>'], webpage, 'video_uploader', fatal=False) - available_fmts = [] - for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage): - attrs = extract_attributes(a) - href = attrs.get('href') - if href and '/freetrial' in href: - continue - available_fmts.append(fmt) - if not available_fmts: - for p in (r'token=["\']showmedia\.([0-9]{3,4})p"', r'showmedia\.([0-9]{3,4})p'): - available_fmts = re.findall(p, webpage) - if available_fmts: - break - video_encode_ids = [] formats = [] - for fmt in available_fmts: - stream_quality, stream_format = self._FORMAT_IDS[fmt] - video_format = fmt + 'p' - stream_infos = [] - streamdata = self._call_rpc_api( - 'VideoPlayer_GetStandardConfig', video_id, - 'Downloading media info for %s' % video_format, data={ - 'media_id': video_id, - 'video_format': stream_format, - 'video_quality': stream_quality, - 'current_page': url, - }) - if streamdata is not None: - stream_info = streamdata.find('./{default}preload/stream_info') + for stream in media.get('streams', []): + formats.extend(self._extract_vrv_formats( + stream.get('url'), video_id, stream.get('format'), + stream.get('audio_lang'), stream.get('hardsub_lang'))) + if not formats: + available_fmts = [] + for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage): + attrs = extract_attributes(a) + href = attrs.get('href') + if href and '/freetrial' in href: + continue + available_fmts.append(fmt) + if not available_fmts: + for p in (r'token=["\']showmedia\.([0-9]{3,4})p"', r'showmedia\.([0-9]{3,4})p'): + available_fmts = re.findall(p, webpage) + if available_fmts: + break + if not available_fmts: + available_fmts = self._FORMAT_IDS.keys() + video_encode_ids = [] + + for fmt in available_fmts: + stream_quality, stream_format = self._FORMAT_IDS[fmt] + video_format = fmt + 'p' + stream_infos = [] + streamdata = self._call_rpc_api( + 'VideoPlayer_GetStandardConfig', video_id, + 'Downloading media info for %s' % video_format, data={ + 'media_id': video_id, + 'video_format': stream_format, + 'video_quality': stream_quality, + 'current_page': url, + }) + if streamdata is not None: + stream_info = streamdata.find('./{default}preload/stream_info') + if stream_info is not None: + stream_infos.append(stream_info) + stream_info = self._call_rpc_api( + 'VideoEncode_GetStreamInfo', video_id, + 'Downloading stream info for %s' % video_format, data={ + 'media_id': video_id, + 'video_format': stream_format, + 'video_encode_quality': stream_quality, + }) if stream_info is not None: stream_infos.append(stream_info) - stream_info = self._call_rpc_api( - 'VideoEncode_GetStreamInfo', video_id, - 'Downloading stream info for %s' % video_format, data={ - 'media_id': video_id, - 'video_format': stream_format, - 'video_encode_quality': stream_quality, - }) - if stream_info is not None: - stream_infos.append(stream_info) - for stream_info in stream_infos: - video_encode_id = xpath_text(stream_info, './video_encode_id') - if video_encode_id in video_encode_ids: - continue - video_encode_ids.append(video_encode_id) + for stream_info in stream_infos: + video_encode_id = xpath_text(stream_info, './video_encode_id') + if video_encode_id in video_encode_ids: + continue + video_encode_ids.append(video_encode_id) - video_file = xpath_text(stream_info, './file') - if not video_file: - continue - if video_file.startswith('http'): - formats.extend(self._extract_m3u8_formats( - video_file, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False)) - continue - - video_url = xpath_text(stream_info, './host') - if not video_url: - continue - metadata = stream_info.find('./metadata') - format_info = { - 'format': video_format, - 'height': int_or_none(xpath_text(metadata, './height')), - 'width': int_or_none(xpath_text(metadata, './width')), - } - - if '.fplive.net/' in video_url: - video_url = re.sub(r'^rtmpe?://', 'http://', video_url.strip()) - parsed_video_url = compat_urlparse.urlparse(video_url) - direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace( - netloc='v.lvlt.crcdn.net', - path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_file.split(':')[-1]))) - if self._is_valid_url(direct_video_url, video_id, video_format): - format_info.update({ - 'format_id': 'http-' + video_format, - 'url': direct_video_url, - }) - formats.append(format_info) + video_file = xpath_text(stream_info, './file') + if not video_file: + continue + if video_file.startswith('http'): + formats.extend(self._extract_m3u8_formats( + video_file, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) continue - format_info.update({ - 'format_id': 'rtmp-' + video_format, - 'url': video_url, - 'play_path': video_file, - 'ext': 'flv', - }) - formats.append(format_info) + video_url = xpath_text(stream_info, './host') + if not video_url: + continue + metadata = stream_info.find('./metadata') + format_info = { + 'format': video_format, + 'height': int_or_none(xpath_text(metadata, './height')), + 'width': int_or_none(xpath_text(metadata, './width')), + } + + if '.fplive.net/' in video_url: + video_url = re.sub(r'^rtmpe?://', 'http://', video_url.strip()) + parsed_video_url = compat_urlparse.urlparse(video_url) + direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace( + netloc='v.lvlt.crcdn.net', + path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_file.split(':')[-1]))) + if self._is_valid_url(direct_video_url, video_id, video_format): + format_info.update({ + 'format_id': 'http-' + video_format, + 'url': direct_video_url, + }) + formats.append(format_info) + continue + + format_info.update({ + 'format_id': 'rtmp-' + video_format, + 'url': video_url, + 'play_path': video_file, + 'ext': 'flv', + }) + formats.append(format_info) self._sort_formats(formats, ('height', 'width', 'tbr', 'fps')) metadata = self._call_rpc_api( @@ -549,7 +563,17 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'media_id': video_id, }) - subtitles = self.extract_subtitles(video_id, webpage) + subtitles = {} + for subtitle in media.get('subtitles', []): + subtitle_url = subtitle.get('url') + if not subtitle_url: + continue + subtitles.setdefault(subtitle.get('language', 'enUS'), []).append({ + 'url': subtitle_url, + 'ext': subtitle.get('format', 'ass'), + }) + if not subtitles: + subtitles = self.extract_subtitles(video_id, webpage) # webpage provide more accurate data than series_title from XML series = self._html_search_regex( @@ -557,8 +581,8 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text webpage, 'series', fatal=False) season = xpath_text(metadata, 'series_title') - episode = xpath_text(metadata, 'episode_title') - episode_number = int_or_none(xpath_text(metadata, 'episode_number')) + episode = xpath_text(metadata, 'episode_title') or media_metadata.get('title') + episode_number = int_or_none(xpath_text(metadata, 'episode_number') or media_metadata.get('episode_number')) season_number = int_or_none(self._search_regex( r'(?s)<h\d[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h\d>\s*<h4>\s*Season (\d+)', @@ -568,7 +592,8 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'id': video_id, 'title': video_title, 'description': video_description, - 'thumbnail': xpath_text(metadata, 'episode_image_url'), + 'duration': float_or_none(media_metadata.get('duration'), 1000), + 'thumbnail': xpath_text(metadata, 'episode_image_url') or media_metadata.get('thumbnail', {}).get('url'), 'uploader': video_uploader, 'upload_date': video_upload_date, 'series': series, diff --git a/youtube_dl/extractor/vrv.py b/youtube_dl/extractor/vrv.py index 64b13f0ed..921e9e172 100644 --- a/youtube_dl/extractor/vrv.py +++ b/youtube_dl/extractor/vrv.py @@ -72,7 +72,7 @@ class VRVBaseIE(InfoExtractor): class VRVIE(VRVBaseIE): IE_NAME = 'vrv' _VALID_URL = r'https?://(?:www\.)?vrv\.co/watch/(?P<id>[A-Z0-9]+)' - _TEST = { + _TESTS = [{ 'url': 'https://vrv.co/watch/GR9PNZ396/Hidden-America-with-Jonah-Ray:BOSTON-WHERE-THE-PAST-IS-THE-PRESENT', 'info_dict': { 'id': 'GR9PNZ396', @@ -85,7 +85,28 @@ class VRVIE(VRVBaseIE): # m3u8 download 'skip_download': True, }, - } + }] + + def _extract_vrv_formats(self, url, video_id, stream_format, audio_lang, hardsub_lang): + if not url or stream_format not in ('hls', 'dash'): + return [] + stream_id = hardsub_lang or audio_lang + format_id = '%s-%s' % (stream_format, stream_id) + if stream_format == 'hls': + adaptive_formats = self._extract_m3u8_formats( + url, video_id, 'mp4', m3u8_id=format_id, + note='Downloading %s m3u8 information' % stream_id, + fatal=False) + elif stream_format == 'dash': + adaptive_formats = self._extract_mpd_formats( + url, video_id, mpd_id=format_id, + note='Downloading %s MPD information' % stream_id, + fatal=False) + if audio_lang: + for f in adaptive_formats: + if f.get('acodec') != 'none': + f['language'] = audio_lang + return adaptive_formats def _real_extract(self, url): video_id = self._match_id(url) @@ -115,26 +136,9 @@ class VRVIE(VRVBaseIE): for stream_type, streams in streams_json.get('streams', {}).items(): if stream_type in ('adaptive_hls', 'adaptive_dash'): for stream in streams.values(): - stream_url = stream.get('url') - if not stream_url: - continue - stream_id = stream.get('hardsub_locale') or audio_locale - format_id = '%s-%s' % (stream_type.split('_')[1], stream_id) - if stream_type == 'adaptive_hls': - adaptive_formats = self._extract_m3u8_formats( - stream_url, video_id, 'mp4', m3u8_id=format_id, - note='Downloading %s m3u8 information' % stream_id, - fatal=False) - else: - adaptive_formats = self._extract_mpd_formats( - stream_url, video_id, mpd_id=format_id, - note='Downloading %s MPD information' % stream_id, - fatal=False) - if audio_locale: - for f in adaptive_formats: - if f.get('acodec') != 'none': - f['language'] = audio_locale - formats.extend(adaptive_formats) + formats.extend(self._extract_vrv_formats( + stream.get('url'), video_id, stream_type.split('_')[1], + audio_locale, stream.get('hardsub_locale'))) self._sort_formats(formats) subtitles = {} From 7f2611cb5b086fbdb6281779a96fcb75a594e68c Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 1 Sep 2018 08:40:38 +0100 Subject: [PATCH 167/558] [ard] extract f4m formats --- youtube_dl/extractor/ard.py | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index dcb347849..194a369c0 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -338,12 +338,9 @@ class ARDBetaMediathekIE(InfoExtractor): format_url = widget['_stream']['json'][0] if format_url.endswith('.f4m'): - # Skip f4m - these URLs just return a 403 - formats.append({ - 'format_id': 'f4m-' + widget['_quality'], - 'url': format_url, - 'preference': -1001, - }) + formats.extend(self._extract_f4m_formats( + format_url + '?hdcore=3.11.0', + video_id, f4m_id='hds', fatal=False)) elif format_url.endswith('m3u8'): formats.extend(self._extract_m3u8_formats( format_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) From 462799588288b9ac8280dc361a9efcced8cb29e1 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 1 Sep 2018 10:04:10 +0100 Subject: [PATCH 168/558] [crunchyroll] limit VRVIE inheritance to CrunchyrollIE --- youtube_dl/extractor/crunchyroll.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 4ed458372..ba8b9fa7e 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -7,6 +7,7 @@ import zlib from hashlib import sha1 from math import pow, sqrt, floor +from .common import InfoExtractor from .vrv import VRVIE from ..compat import ( compat_b64decode, @@ -34,7 +35,7 @@ from ..aes import ( ) -class CrunchyrollBaseIE(VRVIE): +class CrunchyrollBaseIE(InfoExtractor): _LOGIN_URL = 'https://www.crunchyroll.com/login' _LOGIN_FORM = 'login_form' _NETRC_MACHINE = 'crunchyroll' @@ -140,7 +141,8 @@ class CrunchyrollBaseIE(VRVIE): parsed_url._replace(query=compat_urllib_parse_urlencode(qs, True))) -class CrunchyrollIE(CrunchyrollBaseIE): +class CrunchyrollIE(CrunchyrollBaseIE, VRVIE): + IE_NAME = 'crunchyroll' _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)' _TESTS = [{ 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', From 4d59db5b900fa8f1416cb33328f2f12daf9946c5 Mon Sep 17 00:00:00 2001 From: Gorfiend <Gorfiend@users.noreply.github.com> Date: Sat, 1 Sep 2018 05:04:45 -0400 Subject: [PATCH 169/558] [niconico] Fix extraction on python3 (closes #17393) --- youtube_dl/extractor/niconico.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/niconico.py b/youtube_dl/extractor/niconico.py index dbe871f16..76b412ff1 100644 --- a/youtube_dl/extractor/niconico.py +++ b/youtube_dl/extractor/niconico.py @@ -252,7 +252,7 @@ class NiconicoIE(InfoExtractor): }, 'timing_constraint': 'unlimited' } - })) + }).encode()) resolution = video_quality.get('resolution', {}) From 0b87e8845328fd93a6f0fd873f5394f63c9ce64f Mon Sep 17 00:00:00 2001 From: LangerJan <LangerJan@users.noreply.github.com> Date: Sat, 1 Sep 2018 11:42:30 +0200 Subject: [PATCH 170/558] [ard] Add support for one.ard.de --- youtube_dl/extractor/ard.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 194a369c0..6bf8f61eb 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -21,7 +21,7 @@ from ..compat import compat_etree_fromstring class ARDMediathekIE(InfoExtractor): IE_NAME = 'ARD:mediathek' - _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' + _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' _TESTS = [{ # available till 26.07.2022 @@ -37,6 +37,9 @@ class ARDMediathekIE(InfoExtractor): # m3u8 download 'skip_download': True, } + }, { + 'url': 'https://one.ard.de/tv/Mord-mit-Aussicht/Mord-mit-Aussicht-6-39-T%C3%B6dliche-Nach/ONE/Video?bcastId=46384294&documentId=55586872', + 'only_matching': True, }, { # audio 'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086', From 7bbc1b189aa7b0cea5336964a2acdca4001c1566 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 1 Sep 2018 18:36:18 +0700 Subject: [PATCH 171/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/ChangeLog b/ChangeLog index 49f44a6e6..7585f06e9 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,19 @@ +version <unreleased> + +Core +* [utils] Skip remote IP addresses non matching to source address' IP version + when creating a connection (#13422, #17362) + +Extractors ++ [ard] Add support for one.ard.de (#17397) +* [niconico] Fix extraction on python3 (#17393, #17407) +* [ard] Extract f4m formats +* [crunchyroll] Parse vilos media data (#17343) ++ [ard] Add support for Beta ARD Mediathek ++ [bandcamp] Extract more metadata (#13197) +* [internazionale] Fix extraction of non-available-abroad videos (#17386) + + version 2018.08.28 Extractors From 27d8e089a21561480f5261f77665604bba2f5901 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 1 Sep 2018 18:40:23 +0700 Subject: [PATCH 172/558] release 2018.09.01 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 3 ++- youtube_dl/version.py | 2 +- 4 files changed, 7 insertions(+), 6 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 0816c4f5f..16d8f36d7 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.08.28*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.08.28** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.09.01*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.09.01** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.08.28 +[debug] youtube-dl version 2018.09.01 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 7585f06e9..4632133a3 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.09.01 Core * [utils] Skip remote IP addresses non matching to source address' IP version diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 5beb9bc17..f0d6be901 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -56,6 +56,7 @@ - **archive.org**: archive.org videos - **ARD** - **ARD:mediathek** + - **ARDBetaMediathek** - **Arkena** - **arte.tv** - **arte.tv:+7** @@ -191,7 +192,7 @@ - **Crackle** - **Criterion** - **CrooksAndLiars** - - **Crunchyroll** + - **crunchyroll** - **crunchyroll:playlist** - **CSNNE** - **CSpan**: C-SPAN diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 3e3fe1375..e655e0050 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.08.28' +__version__ = '2018.09.01' From 3d08f63dc57f000384703f26b7dcb4b683e18c05 Mon Sep 17 00:00:00 2001 From: Mohammed Yaseen Mowzer <yaseen@mowzer.co.za> Date: Thu, 14 Jun 2018 17:12:33 +0200 Subject: [PATCH 173/558] [generic] Skip unsuccessful jwplayer extraction (closes #16735) --- youtube_dl/extractor/generic.py | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 229dfda1b..1db154c4f 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -3150,9 +3150,13 @@ class GenericIE(InfoExtractor): jwplayer_data = self._find_jwplayer_data( webpage, video_id, transform_source=js_to_json) if jwplayer_data: - info = self._parse_jwplayer_data( - jwplayer_data, video_id, require_title=False, base_url=url) - return merge_dicts(info, info_dict) + try: + info = self._parse_jwplayer_data( + jwplayer_data, video_id, require_title=False, base_url=url) + return merge_dicts(info, info_dict) + except ExtractorError: + # See https://github.com/rg3/youtube-dl/pull/16735 + pass # Video.js embed mobj = re.search( From 0a9a8118ce834c206434df04c18187934acbf608 Mon Sep 17 00:00:00 2001 From: Hormoz K <hkheradm@gmail.com> Date: Sat, 4 Aug 2018 09:47:58 -0400 Subject: [PATCH 174/558] [radiojavan] Fix extraction --- youtube_dl/extractor/radiojavan.py | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/radiojavan.py b/youtube_dl/extractor/radiojavan.py index a53ad97a5..4124bcd45 100644 --- a/youtube_dl/extractor/radiojavan.py +++ b/youtube_dl/extractor/radiojavan.py @@ -6,11 +6,13 @@ from .common import InfoExtractor from ..utils import ( unified_strdate, str_to_int, + urlencode_postdata, ) class RadioJavanIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?' + _HOST_TRACKER_URL = 'https://www.radiojavan.com/videos/video_host' _TEST = { 'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam', 'md5': 'e85208ffa3ca8b83534fca9fe19af95b', @@ -31,8 +33,18 @@ class RadioJavanIE(InfoExtractor): webpage = self._download_webpage(url, video_id) + download_host = self._download_json( + self._HOST_TRACKER_URL, + video_id, + data=urlencode_postdata({'id': video_id}), + headers={ + 'Content-Type': 'application/x-www-form-urlencoded', + 'Referer': url, + } + )['host'] + formats = [{ - 'url': 'https://media.rdjavan.com/media/music_video/%s' % video_path, + 'url': '%s/%s' % (download_host, video_path), 'format_id': '%sp' % height, 'height': int(height), } for height, video_path in re.findall(r"RJ\.video(\d+)p\s*=\s*'/?([^']+)'", webpage)] From 93284ff2ea4eb84c25b8d496012398a056ba89ac Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 3 Sep 2018 02:53:26 +0700 Subject: [PATCH 175/558] [radiojavan] Improve extraction (closes #17151) --- youtube_dl/extractor/radiojavan.py | 30 +++++++++++++++++------------- 1 file changed, 17 insertions(+), 13 deletions(-) diff --git a/youtube_dl/extractor/radiojavan.py b/youtube_dl/extractor/radiojavan.py index 4124bcd45..3f74f0c01 100644 --- a/youtube_dl/extractor/radiojavan.py +++ b/youtube_dl/extractor/radiojavan.py @@ -4,15 +4,16 @@ import re from .common import InfoExtractor from ..utils import ( - unified_strdate, + parse_resolution, str_to_int, + unified_strdate, urlencode_postdata, + urljoin, ) class RadioJavanIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?' - _HOST_TRACKER_URL = 'https://www.radiojavan.com/videos/video_host' _TEST = { 'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam', 'md5': 'e85208ffa3ca8b83534fca9fe19af95b', @@ -31,23 +32,26 @@ class RadioJavanIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - download_host = self._download_json( - self._HOST_TRACKER_URL, - video_id, + 'https://www.radiojavan.com/videos/video_host', video_id, data=urlencode_postdata({'id': video_id}), headers={ 'Content-Type': 'application/x-www-form-urlencoded', 'Referer': url, - } - )['host'] + }).get('host', 'https://host1.rjmusicmedia.com') - formats = [{ - 'url': '%s/%s' % (download_host, video_path), - 'format_id': '%sp' % height, - 'height': int(height), - } for height, video_path in re.findall(r"RJ\.video(\d+)p\s*=\s*'/?([^']+)'", webpage)] + webpage = self._download_webpage(url, video_id) + + formats = [] + for format_id, _, video_path in re.findall( + r'RJ\.video(?P<format_id>\d+[pPkK])\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2', + webpage): + f = parse_resolution(format_id) + f.update({ + 'url': urljoin(download_host, video_path), + 'format_id': format_id, + }) + formats.append(f) self._sort_formats(formats) title = self._og_search_title(webpage) From aa1d5eb9053b4c39661415ef411fb3746ee11f41 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 4 Sep 2018 10:37:11 +0100 Subject: [PATCH 176/558] [slideslive] make the check for video_service_name case-insensitive(closes #17429) --- youtube_dl/extractor/slideslive.py | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/slideslive.py b/youtube_dl/extractor/slideslive.py index 104576033..ed84322c5 100644 --- a/youtube_dl/extractor/slideslive.py +++ b/youtube_dl/extractor/slideslive.py @@ -8,6 +8,7 @@ from ..utils import ExtractorError class SlidesLiveIE(InfoExtractor): _VALID_URL = r'https?://slideslive\.com/(?P<id>[0-9]+)' _TESTS = [{ + # video_service_name = YOUTUBE 'url': 'https://slideslive.com/38902413/gcc-ia16-backend', 'md5': 'b29fcd6c6952d0c79c5079b0e7a07e6f', 'info_dict': { @@ -19,14 +20,18 @@ class SlidesLiveIE(InfoExtractor): 'uploader_id': 'UC62SdArr41t_-_fX40QCLRw', 'upload_date': '20170925', } + }, { + # video_service_name = youtube + 'url': 'https://slideslive.com/38903721/magic-a-scientific-resurrection-of-an-esoteric-legend', + 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) video_data = self._download_json( url, video_id, headers={'Accept': 'application/json'}) - service_name = video_data['video_service_name'] - if service_name == 'YOUTUBE': + service_name = video_data['video_service_name'].lower() + if service_name == 'youtube': yt_video_id = video_data['video_service_id'] return self.url_result(yt_video_id, 'Youtube', video_id=yt_video_id) else: From 09322cccdb655954c63724459556bd3ebb585d48 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 6 Sep 2018 00:22:30 +0700 Subject: [PATCH 177/558] [iprima] Confirm adult check (closes #17437) --- youtube_dl/extractor/iprima.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py index a29e6a5ba..3c4b7e48b 100644 --- a/youtube_dl/extractor/iprima.py +++ b/youtube_dl/extractor/iprima.py @@ -38,6 +38,8 @@ class IPrimaIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) + self._set_cookie('play.iprima.cz', 'ott_adult_confirmed', '1') + webpage = self._download_webpage(url, video_id) video_id = self._search_regex(r'data-product="([^"]+)">', webpage, 'real id') From 2d4fe594c64249c263d739c8094b445c67fa09f5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 6 Sep 2018 00:51:20 +0700 Subject: [PATCH 178/558] [pornhub:uservideos] Add support for new URLs (closes #17388) --- youtube_dl/extractor/pornhub.py | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index ffc4405a8..6782848d9 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -254,7 +254,7 @@ class PornHubIE(InfoExtractor): self._sort_formats(formats) video_uploader = self._html_search_regex( - r'(?s)From: .+?<(?:a\b[^>]+\bhref=["\']/(?:user|channel)s/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<', + r'(?s)From: .+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<', webpage, 'uploader', fatal=False) view_count = self._extract_count( @@ -346,7 +346,7 @@ class PornHubPlaylistIE(PornHubPlaylistBaseIE): class PornHubUserVideosIE(PornHubPlaylistBaseIE): - _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/(?:user|channel)s/(?P<id>[^/]+)/videos' + _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos' _TESTS = [{ 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public', 'info_dict': { @@ -378,6 +378,12 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE): }, { 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public', 'only_matching': True, + }, { + 'url': 'https://www.pornhub.com/model/jayndrea/videos/upload', + 'only_matching': True, + }, { + 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload', + 'only_matching': True, }] def _real_extract(self, url): From 9a47fa35dd9dd2d53f4d3f088811ea29295991e5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 8 Sep 2018 03:36:10 +0700 Subject: [PATCH 179/558] [youtube] Fix extraction (closes #17457, closes #17464) --- youtube_dl/extractor/youtube.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 0442906df..27047425d 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1178,7 +1178,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def _parse_sig_js(self, jscode): funcname = self._search_regex( (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', - r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\('), + r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(', + r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', + r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\('), jscode, 'Initial JS player signature function name', group='sig') jsi = JSInterpreter(jscode) From a41a506077936b2574cbb34afa83f8215accc3a3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 8 Sep 2018 03:40:06 +0700 Subject: [PATCH 180/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/ChangeLog b/ChangeLog index 4632133a3..b378f0a0e 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,14 @@ +version <unreleased> + +Extractors +* [youtube] Fix extraction (#17457, #17464) ++ [pornhub:uservideos] Add support for new URLs (#17388) +* [iprima] Confirm adult check (#17437) +* [slideslive] Make check for video service name case-insensitive (#17429) +* [radiojavan] Fix extraction (#17151) +* [generic] Skip unsuccessful jwplayer extraction (#16735) + + version 2018.09.01 Core From ad98d2eb748b593dc044296493904607c3058e8b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 8 Sep 2018 03:42:28 +0700 Subject: [PATCH 181/558] release 2018.09.08 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 16d8f36d7..2d67247e6 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.09.01*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.09.01** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.09.08*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.09.08** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.09.01 +[debug] youtube-dl version 2018.09.08 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index b378f0a0e..ac95c9b71 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.09.08 Extractors * [youtube] Fix extraction (#17457, #17464) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index e655e0050..716d9ffe0 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.09.01' +__version__ = '2018.09.08' From d0c5fabc1215fddd354fd91cd65082e45df1165e Mon Sep 17 00:00:00 2001 From: Timendum <timedum@gmail.com> Date: Sat, 8 Sep 2018 09:44:06 +0200 Subject: [PATCH 182/558] [nbc] Fix extraction of percent encoded URLs (closes #17374) --- youtube_dl/extractor/nbc.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index c843f8649..765c46fd2 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -7,6 +7,7 @@ import re from .common import InfoExtractor from .theplatform import ThePlatformIE from .adobepass import AdobePassIE +from ..compat import compat_urllib_parse_unquote from ..utils import ( find_xpath_attr, smuggle_url, @@ -75,11 +76,16 @@ class NBCIE(AdobePassIE): 'url': 'https://www.nbc.com/classic-tv/charles-in-charge/video/charles-in-charge-pilot/n3310', 'only_matching': True, }, + { + # Percent escaped url + 'url': 'https://www.nbc.com/up-all-night/video/day-after-valentine%27s-day/n2189', + 'only_matching': True, + } ] def _real_extract(self, url): permalink, video_id = re.match(self._VALID_URL, url).groups() - permalink = 'http' + permalink + permalink = 'http' + compat_urllib_parse_unquote(permalink) response = self._download_json( 'https://api.nbc.com/v3/videos', video_id, query={ 'filter[permalink]': permalink, From d0de6a287ac64b52630e5b21c3db52a4312675fd Mon Sep 17 00:00:00 2001 From: Jens Rutschmann <N/A> Date: Sat, 1 Sep 2018 19:43:34 +0200 Subject: [PATCH 183/558] [tele5] Add extractor --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/tele5.py | 39 ++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+) create mode 100644 youtube_dl/extractor/tele5.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 995af9988..7dc569724 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1086,6 +1086,7 @@ from .teachingchannel import TeachingChannelIE from .teamcoco import TeamcocoIE from .techtalks import TechTalksIE from .ted import TEDIE +from .tele5 import Tele5IE from .tele13 import Tele13IE from .telebruxelles import TeleBruxellesIE from .telecinco import TelecincoIE diff --git a/youtube_dl/extractor/tele5.py b/youtube_dl/extractor/tele5.py new file mode 100644 index 000000000..cfa8d2475 --- /dev/null +++ b/youtube_dl/extractor/tele5.py @@ -0,0 +1,39 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from .nexx import NexxIE + + +class Tele5IE(InfoExtractor): + _VALID_URL = r'https://www\.tele5\.de/(?:mediathek/filme-online/videos\?vid=|tv/)(?P<display_id>[\w-]+)' + + _TESTS = [{ + 'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1550589', + 'info_dict': { + 'id': '1550589', + 'ext': 'mp4', + 'upload_date': '20180822', + 'timestamp': 1534927316, + 'title': 'SchleFaZ: Atomic Shark', + } + }, { + 'url': 'https://www.tele5.de/tv/dark-matter/videos', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + video_id = self._html_search_regex( + r'id\s*=\s*["\']video-player["\']\s*data-id\s*=\s*["\']([0-9]+)["\']', + webpage, 'video_id') + + return self.url_result( + 'https://api.nexx.cloud/v3/759/videos/byid/%s' % video_id, + ie=NexxIE.ie_key(), video_id=video_id) From ae2384ff5f9d6a18209139a4b2e2cd33921be63a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 8 Sep 2018 16:04:39 +0700 Subject: [PATCH 184/558] [tele5] Improve extraction (closes #7805, closes #7922, closes #17331, closes #17414) --- youtube_dl/extractor/tele5.py | 39 ++++++++++++++++++++--------------- 1 file changed, 22 insertions(+), 17 deletions(-) diff --git a/youtube_dl/extractor/tele5.py b/youtube_dl/extractor/tele5.py index cfa8d2475..25573e49f 100644 --- a/youtube_dl/extractor/tele5.py +++ b/youtube_dl/extractor/tele5.py @@ -1,38 +1,43 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from .nexx import NexxIE +from ..compat import compat_urlparse class Tele5IE(InfoExtractor): - _VALID_URL = r'https://www\.tele5\.de/(?:mediathek/filme-online/videos\?vid=|tv/)(?P<display_id>[\w-]+)' - + _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:mediathek|tv)/(?P<id>[^?#&]+)' _TESTS = [{ - 'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1550589', + 'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1549416', 'info_dict': { - 'id': '1550589', + 'id': '1549416', 'ext': 'mp4', - 'upload_date': '20180822', - 'timestamp': 1534927316, - 'title': 'SchleFaZ: Atomic Shark', - } + 'upload_date': '20180814', + 'timestamp': 1534290623, + 'title': 'Pandorum', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://www.tele5.de/tv/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191', + 'only_matching': True, }, { 'url': 'https://www.tele5.de/tv/dark-matter/videos', 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('display_id') + qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) + video_id = (qs.get('vid') or qs.get('ve_id') or [None])[0] - webpage = self._download_webpage(url, display_id) - - video_id = self._html_search_regex( - r'id\s*=\s*["\']video-player["\']\s*data-id\s*=\s*["\']([0-9]+)["\']', - webpage, 'video_id') + if not video_id: + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + video_id = self._html_search_regex( + r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](\d+)', + webpage, 'video id') return self.url_result( 'https://api.nexx.cloud/v3/759/videos/byid/%s' % video_id, From 6f9f3340bb4c837d86067856e12232fc9695e698 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 8 Sep 2018 17:24:09 +0700 Subject: [PATCH 185/558] [dtube] PEP 8 (#17455) --- youtube_dl/extractor/dtube.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/dtube.py b/youtube_dl/extractor/dtube.py index 4ca97f860..5887887e1 100644 --- a/youtube_dl/extractor/dtube.py +++ b/youtube_dl/extractor/dtube.py @@ -59,7 +59,7 @@ class DTubeIE(InfoExtractor): try: self.to_screen('%s: Checking %s video format URL' % (video_id, format_id)) self._downloader._opener.open(video_url, timeout=5).close() - except timeout as e: + except timeout: self.to_screen( '%s: %s URL is invalid, skipping' % (video_id, format_id)) continue From 13ef64fd9340794e214ba64c258fa0999fbd0a17 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 8 Sep 2018 17:24:34 +0700 Subject: [PATCH 186/558] [motherless] PEP 8 (#17455) --- youtube_dl/extractor/motherless.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/motherless.py b/youtube_dl/extractor/motherless.py index bed5645f2..d4bd273b6 100644 --- a/youtube_dl/extractor/motherless.py +++ b/youtube_dl/extractor/motherless.py @@ -167,9 +167,9 @@ class MotherlessGroupIE(InfoExtractor): if not entries: entries = [ self.url_result( - compat_urlparse.urljoin(base, '/' + video_id), - ie=MotherlessIE.ie_key(), video_id=video_id) - for video_id in orderedSet(re.findall( + compat_urlparse.urljoin(base, '/' + entry_id), + ie=MotherlessIE.ie_key(), video_id=entry_id) + for entry_id in orderedSet(re.findall( r'data-codename=["\']([A-Z0-9]+)', webpage))] return entries From 2c9d3b9962e28b61615e382bfcaf6db6d6987c09 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 8 Sep 2018 17:24:48 +0700 Subject: [PATCH 187/558] [seznamzpravy] PEP 8 (#17455) --- youtube_dl/extractor/seznamzpravy.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/seznamzpravy.py b/youtube_dl/extractor/seznamzpravy.py index 6d4e3b76d..7a1c7e38b 100644 --- a/youtube_dl/extractor/seznamzpravy.py +++ b/youtube_dl/extractor/seznamzpravy.py @@ -164,6 +164,6 @@ class SeznamZpravyArticleIE(InfoExtractor): description = info.get('description') or self._og_search_description(webpage) return self.playlist_result([ - self.url_result(url, ie=SeznamZpravyIE.ie_key()) - for url in SeznamZpravyIE._extract_urls(webpage)], + self.url_result(entry_url, ie=SeznamZpravyIE.ie_key()) + for entry_url in SeznamZpravyIE._extract_urls(webpage)], article_id, title, description) From 2e4350eec6981ffb12617abda7623e4fb565ce8a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 8 Sep 2018 17:24:59 +0700 Subject: [PATCH 188/558] [generic] PEP 8 (#17455) --- youtube_dl/extractor/generic.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 1db154c4f..76ef01332 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -3112,7 +3112,7 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key()) - sharevideos_urls = [mobj.group('url') for mobj in re.finditer( + sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer( r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1', webpage)] if sharevideos_urls: From a2637a2dda5e90b83bd2f403d06ad1ce21fc8c5f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 10 Sep 2018 01:34:49 +0700 Subject: [PATCH 189/558] [iprima] Add support for prima.iprima.cz (closes #17514) --- youtube_dl/extractor/iprima.py | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py index 3c4b7e48b..1d58d6e85 100644 --- a/youtube_dl/extractor/iprima.py +++ b/youtube_dl/extractor/iprima.py @@ -12,7 +12,7 @@ from ..utils import ( class IPrimaIE(InfoExtractor): - _VALID_URL = r'https?://play\.iprima\.cz/(?:.+/)?(?P<id>[^?#]+)' + _VALID_URL = r'https?://(?:play|prima)\.iprima\.cz/(?:.+/)?(?P<id>[^?#]+)' _GEO_BYPASS = False _TESTS = [{ @@ -33,6 +33,14 @@ class IPrimaIE(InfoExtractor): # geo restricted 'url': 'http://play.iprima.cz/closer-nove-pripady/closer-nove-pripady-iv-1', 'only_matching': True, + }, { + # iframe api.play-backend.iprima.cz + 'url': 'https://prima.iprima.cz/my-little-pony/mapa-znameni-2-2', + 'only_matching': True, + }, { + # iframe prima.iprima.cz + 'url': 'https://prima.iprima.cz/porady/jak-se-stavi-sen/rodina-rathousova-praha', + 'only_matching': True, }] def _real_extract(self, url): @@ -42,7 +50,10 @@ class IPrimaIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - video_id = self._search_regex(r'data-product="([^"]+)">', webpage, 'real id') + video_id = self._search_regex( + (r'<iframe[^>]+\bsrc=["\'](?:https?:)?//(?:api\.play-backend\.iprima\.cz/prehravac/embedded|prima\.iprima\.cz/[^/]+/[^/]+)\?.*?\bid=(p\d+)', + r'data-product="([^"]+)">'), + webpage, 'real id') playerpage = self._download_webpage( 'http://play.iprima.cz/prehravac/init', From 25d110be30b92f785617140b0617a73d8eec5f7b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 10 Sep 2018 02:37:22 +0700 Subject: [PATCH 190/558] [utils] Properly recognize AV1 codec (closes #17506) --- test/test_utils.py | 4 ++++ youtube_dl/utils.py | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/test/test_utils.py b/test/test_utils.py index 8da5ccc56..9e28e008f 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -785,6 +785,10 @@ class TestUtil(unittest.TestCase): 'vcodec': 'h264', 'acodec': 'aac', }) + self.assertEqual(parse_codecs('av01.0.05M.08'), { + 'vcodec': 'av01.0.05M.08', + 'acodec': 'none', + }) def test_escape_rfc3986(self): reserved = "!*'();:@&=+$,/?#[]" diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index bcfb72d43..e84d35d4d 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -2477,7 +2477,7 @@ def parse_codecs(codecs_str): vcodec, acodec = None, None for full_codec in splited_codecs: codec = full_codec.split('.')[0] - if codec in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2', 'h263', 'h264', 'mp4v', 'hvc1'): + if codec in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2', 'h263', 'h264', 'mp4v', 'hvc1', 'av01'): if not vcodec: vcodec = full_codec elif codec in ('mp4a', 'opus', 'vorbis', 'mp3', 'aac', 'ac-3', 'ec-3', 'eac3', 'dtsc', 'dtse', 'dtsh', 'dtsl'): From 14f577e31c3d11e84bda5048d11bc7c31a830e2d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 10 Sep 2018 02:45:44 +0700 Subject: [PATCH 191/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/ChangeLog b/ChangeLog index ac95c9b71..c02450bf4 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,14 @@ +version <unreleased> + +Core ++ [utils] Properly recognize AV1 codec (#17506) + +Extractors ++ [iprima] Add support for prima.iprima.cz (#17514) ++ [tele5] Add support for tele5.de (#7805, #7922, #17331, #17414) +* [nbc] Fix extraction of percent encoded URLs (#17374) + + version 2018.09.08 Extractors From 8476b4fd91ce71c052a3bdea9e010e5196331606 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 10 Sep 2018 02:48:37 +0700 Subject: [PATCH 192/558] release 2018.09.10 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 1 + youtube_dl/version.py | 2 +- 4 files changed, 6 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 2d67247e6..f41266f32 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.09.08*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.09.08** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.09.10*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.09.10** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.09.08 +[debug] youtube-dl version 2018.09.10 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index c02450bf4..d184f69ee 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.09.10 Core + [utils] Properly recognize AV1 codec (#17506) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index f0d6be901..9b8601751 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -847,6 +847,7 @@ - **techtv.mit.edu** - **ted** - **Tele13** + - **Tele5** - **TeleBruxelles** - **Telecinco**: telecinco.es, cuatro.com and mediaset.es - **Telegraaf** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 716d9ffe0..b078c4993 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.09.08' +__version__ = '2018.09.10' From 96dbf70de63c08fc27e9bd7bec97670325225758 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 11 Sep 2018 02:24:32 +0700 Subject: [PATCH 193/558] [eporner] Extract JSON-LD (closes #17519) --- youtube_dl/extractor/eporner.py | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/eporner.py b/youtube_dl/extractor/eporner.py index 6d03d7095..c050bf9df 100644 --- a/youtube_dl/extractor/eporner.py +++ b/youtube_dl/extractor/eporner.py @@ -9,6 +9,7 @@ from ..utils import ( encode_base_n, ExtractorError, int_or_none, + merge_dicts, parse_duration, str_to_int, url_or_none, @@ -25,10 +26,16 @@ class EpornerIE(InfoExtractor): 'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video', 'ext': 'mp4', 'title': 'Infamous Tiffany Teen Strip Tease Video', + 'description': 'md5:764f39abf932daafa37485eb46efa152', + 'timestamp': 1232520922, + 'upload_date': '20090121', 'duration': 1838, 'view_count': int, 'age_limit': 18, }, + 'params': { + 'proxy': '127.0.0.1:8118' + } }, { # New (May 2016) URL layout 'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/', @@ -104,12 +111,15 @@ class EpornerIE(InfoExtractor): }) self._sort_formats(formats) - duration = parse_duration(self._html_search_meta('duration', webpage)) + json_ld = self._search_json_ld(webpage, display_id, default={}) + + duration = parse_duration(self._html_search_meta( + 'duration', webpage, default=None)) view_count = str_to_int(self._search_regex( r'id="cinemaviews">\s*([0-9,]+)\s*<small>views', webpage, 'view count', fatal=False)) - return { + return merge_dicts(json_ld, { 'id': video_id, 'display_id': display_id, 'title': title, @@ -117,4 +127,4 @@ class EpornerIE(InfoExtractor): 'view_count': view_count, 'formats': formats, 'age_limit': 18, - } + }) From 79facb27735baf27d65baf050121d68e26654a02 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 11 Sep 2018 02:29:45 +0700 Subject: [PATCH 194/558] [tube8] Fix metadata extraction (closes #17520) --- youtube_dl/extractor/tube8.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py index 368c45729..db93b0182 100644 --- a/youtube_dl/extractor/tube8.py +++ b/youtube_dl/extractor/tube8.py @@ -45,7 +45,7 @@ class Tube8IE(KeezMoviesIE): r'videoTitle\s*=\s*"([^"]+)', webpage, 'title') description = self._html_search_regex( - r'>Description:</strong>\s*(.+?)\s*<', webpage, 'description', fatal=False) + r'(?s)Description:</dt>\s*<dd>(.+?)</dd>', webpage, 'description', fatal=False) uploader = self._html_search_regex( r'<span class="username">\s*(.+?)\s*<', webpage, 'uploader', fatal=False) @@ -55,19 +55,19 @@ class Tube8IE(KeezMoviesIE): dislike_count = int_or_none(self._search_regex( r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False)) view_count = str_to_int(self._search_regex( - r'<strong>Views: </strong>([\d,\.]+)\s*</li>', + r'Views:\s*</dt>\s*<dd>([\d,\.]+)', webpage, 'view count', fatal=False)) comment_count = str_to_int(self._search_regex( r'<span id="allCommentsCount">(\d+)</span>', webpage, 'comment count', fatal=False)) category = self._search_regex( - r'Category:\s*</strong>\s*<a[^>]+href=[^>]+>([^<]+)', + r'Category:\s*</dt>\s*<dd>\s*<a[^>]+href=[^>]+>([^<]+)', webpage, 'category', fatal=False) categories = [category] if category else None tags_str = self._search_regex( - r'(?s)Tags:\s*</strong>(.+?)</(?!a)', + r'(?s)Tags:\s*</dt>\s*<dd>(.+?)</(?!a)', webpage, 'tags', fatal=False) tags = [t for t in re.findall( r'<a[^>]+href=[^>]+>([^<]+)', tags_str)] if tags_str else None From f5b0175349aa85a1b366d12a487ebd66aec5e1b0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 11 Sep 2018 02:41:05 +0700 Subject: [PATCH 195/558] [vzaar] Add support for HLS --- youtube_dl/extractor/vzaar.py | 60 +++++++++++++++++++++++++---------- 1 file changed, 44 insertions(+), 16 deletions(-) diff --git a/youtube_dl/extractor/vzaar.py b/youtube_dl/extractor/vzaar.py index 02fcd52c7..6000671c3 100644 --- a/youtube_dl/extractor/vzaar.py +++ b/youtube_dl/extractor/vzaar.py @@ -4,15 +4,19 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( int_or_none, float_or_none, + unified_timestamp, + url_or_none, ) class VzaarIE(InfoExtractor): _VALID_URL = r'https?://(?:(?:www|view)\.)?vzaar\.com/(?:videos/)?(?P<id>\d+)' _TESTS = [{ + # HTTP and HLS 'url': 'https://vzaar.com/videos/1152805', 'md5': 'bde5ddfeb104a6c56a93a06b04901dbf', 'info_dict': { @@ -40,24 +44,48 @@ class VzaarIE(InfoExtractor): video_id = self._match_id(url) video_data = self._download_json( 'http://view.vzaar.com/v2/%s/video' % video_id, video_id) - source_url = video_data['sourceUrl'] - info = { + title = video_data['videoTitle'] + + formats = [] + + source_url = url_or_none(video_data.get('sourceUrl')) + if source_url: + f = { + 'url': source_url, + 'format_id': 'http', + } + if 'audio' in source_url: + f.update({ + 'vcodec': 'none', + 'ext': 'mp3', + }) + else: + f.update({ + 'width': int_or_none(video_data.get('width')), + 'height': int_or_none(video_data.get('height')), + 'ext': 'mp4', + 'fps': float_or_none(video_data.get('fps')), + }) + formats.append(f) + + video_guid = video_data.get('guid') + usp = video_data.get('usp') + if isinstance(video_guid, compat_str) and isinstance(usp, dict): + m3u8_url = ('http://fable.vzaar.com/v4/usp/%s/%s.ism/.m3u8?' + % (video_guid, video_id)) + '&'.join( + '%s=%s' % (k, v) for k, v in usp.items()) + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + + self._sort_formats(formats) + + return { 'id': video_id, - 'title': video_data['videoTitle'], - 'url': source_url, + 'title': title, 'thumbnail': self._proto_relative_url(video_data.get('poster')), 'duration': float_or_none(video_data.get('videoDuration')), + 'timestamp': unified_timestamp(video_data.get('ts')), + 'formats': formats, } - if 'audio' in source_url: - info.update({ - 'vcodec': 'none', - 'ext': 'mp3', - }) - else: - info.update({ - 'width': int_or_none(video_data.get('width')), - 'height': int_or_none(video_data.get('height')), - 'ext': 'mp4', - }) - return info From db348e88495bd87adcf058bb6c0a26c1fc591f4f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 14 Sep 2018 23:26:38 +0700 Subject: [PATCH 196/558] [twitch:clips] Extend _VALID_URL (closes #17559) --- youtube_dl/extractor/twitch.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index b39972b1e..26661fdf6 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -559,7 +559,8 @@ class TwitchStreamIE(TwitchBaseIE): TwitchAllVideosIE, TwitchUploadsIE, TwitchPastBroadcastsIE, - TwitchHighlightsIE)) + TwitchHighlightsIE, + TwitchClipsIE)) else super(TwitchStreamIE, cls).suitable(url)) def _real_extract(self, url): @@ -633,7 +634,7 @@ class TwitchStreamIE(TwitchBaseIE): class TwitchClipsIE(TwitchBaseIE): IE_NAME = 'twitch:clips' - _VALID_URL = r'https?://clips\.twitch\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)' + _VALID_URL = r'https?://(?:clips\.twitch\.tv/(?:[^/]+/)*|(?:www\.)?twitch\.tv/[^/]+/clip/)(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'https://clips.twitch.tv/FaintLightGullWholeWheat', @@ -653,6 +654,9 @@ class TwitchClipsIE(TwitchBaseIE): # multiple formats 'url': 'https://clips.twitch.tv/rflegendary/UninterestedBeeDAESuppy', 'only_matching': True, + }, { + 'url': 'https://www.twitch.tv/sergeynixon/clip/StormyThankfulSproutFutureMan', + 'only_matching': True, }] def _real_extract(self, url): From 0f2aa0dcaa5ebffbca781f8ecd15c4d52a80f011 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 14 Sep 2018 23:56:03 +0700 Subject: [PATCH 197/558] [asiancrush] Fix extraction (closes #15630) --- youtube_dl/extractor/asiancrush.py | 42 ++++++++++++++++++++++-------- 1 file changed, 31 insertions(+), 11 deletions(-) diff --git a/youtube_dl/extractor/asiancrush.py b/youtube_dl/extractor/asiancrush.py index 594c88c9c..6d71c5ad5 100644 --- a/youtube_dl/extractor/asiancrush.py +++ b/youtube_dl/extractor/asiancrush.py @@ -8,7 +8,6 @@ from .kaltura import KalturaIE from ..utils import ( extract_attributes, remove_end, - urlencode_postdata, ) @@ -34,19 +33,40 @@ class AsianCrushIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - data = self._download_json( - 'https://www.asiancrush.com/wp-admin/admin-ajax.php', video_id, - data=urlencode_postdata({ - 'postid': video_id, - 'action': 'get_channel_kaltura_vars', - })) + webpage = self._download_webpage(url, video_id) - entry_id = data['entry_id'] + entry_id, partner_id, title = [None] * 3 + + vars = self._parse_json( + self._search_regex( + r'iEmbedVars\s*=\s*({.+?})', webpage, 'embed vars', + default='{}'), video_id, fatal=False) + if vars: + entry_id = vars.get('entry_id') + partner_id = vars.get('partner_id') + title = vars.get('vid_label') + + if not entry_id: + entry_id = self._search_regex( + r'\bentry_id["\']\s*:\s*["\'](\d+)', webpage, 'entry id') + + player = self._download_webpage( + 'https://api.asiancrush.com/embeddedVideoPlayer', video_id, + query={'id': entry_id}) + + kaltura_id = self._search_regex( + r'entry_id["\']\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1', player, + 'kaltura id', group='id') + + if not partner_id: + partner_id = self._search_regex( + r'/p(?:artner_id)?/(\d+)', player, 'partner id', + default='513551') return self.url_result( - 'kaltura:%s:%s' % (data['partner_id'], entry_id), - ie=KalturaIE.ie_key(), video_id=entry_id, - video_title=data.get('vid_label')) + 'kaltura:%s:%s' % (partner_id, kaltura_id), + ie=KalturaIE.ie_key(), video_id=kaltura_id, + video_title=title) class AsianCrushPlaylistIE(InfoExtractor): From 15bf2ca0da0ae94dbc6c3b76c89910ceaea88bd9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 15 Sep 2018 00:42:27 +0700 Subject: [PATCH 198/558] [porntube] Fix extraction (closes #17541) --- youtube_dl/extractor/fourtube.py | 94 ++++++++++++++++++++++++++------ 1 file changed, 76 insertions(+), 18 deletions(-) diff --git a/youtube_dl/extractor/fourtube.py b/youtube_dl/extractor/fourtube.py index ad273a0e7..20391b2bb 100644 --- a/youtube_dl/extractor/fourtube.py +++ b/youtube_dl/extractor/fourtube.py @@ -3,15 +3,44 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_urlparse +from ..compat import ( + compat_b64decode, + compat_str, + compat_urllib_parse_unquote, + compat_urlparse, +) from ..utils import ( + int_or_none, parse_duration, parse_iso8601, str_to_int, + try_get, + unified_timestamp, + url_or_none, ) class FourTubeBaseIE(InfoExtractor): + _TKN_HOST = 'tkn.kodicdn.com' + + def _extract_formats(self, url, video_id, media_id, sources): + token_url = 'https://%s/%s/desktop/%s' % ( + self._TKN_HOST, media_id, '+'.join(sources)) + + parsed_url = compat_urlparse.urlparse(url) + tokens = self._download_json(token_url, video_id, data=b'', headers={ + 'Origin': '%s://%s' % (parsed_url.scheme, parsed_url.hostname), + 'Referer': url, + }) + formats = [{ + 'url': tokens[format]['token'], + 'format_id': format + 'p', + 'resolution': format + 'p', + 'quality': int(format), + } for format in sources] + self._sort_formats(formats) + return formats + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) kind, video_id, display_id = mobj.group('kind', 'id', 'display_id') @@ -68,21 +97,7 @@ class FourTubeBaseIE(InfoExtractor): media_id = params[0] sources = ['%s' % p for p in params[2]] - token_url = 'https://tkn.kodicdn.com/{0}/desktop/{1}'.format( - media_id, '+'.join(sources)) - - parsed_url = compat_urlparse.urlparse(url) - tokens = self._download_json(token_url, video_id, data=b'', headers={ - 'Origin': '%s://%s' % (parsed_url.scheme, parsed_url.hostname), - 'Referer': url, - }) - formats = [{ - 'url': tokens[format]['token'], - 'format_id': format + 'p', - 'resolution': format + 'p', - 'quality': int(format), - } for format in sources] - self._sort_formats(formats) + formats = self._extract_formats(url, video_id, media_id, sources) return { 'id': video_id, @@ -164,6 +179,7 @@ class FuxIE(FourTubeBaseIE): class PornTubeIE(FourTubeBaseIE): _VALID_URL = r'https?://(?:(?P<kind>www|m)\.)?porntube\.com/(?:videos/(?P<display_id>[^/]+)_|embed/)(?P<id>\d+)' _URL_TEMPLATE = 'https://www.porntube.com/videos/video_%s' + _TKN_HOST = 'tkn.porntube.com' _TESTS = [{ 'url': 'https://www.porntube.com/videos/teen-couple-doing-anal_7089759', 'info_dict': { @@ -171,13 +187,12 @@ class PornTubeIE(FourTubeBaseIE): 'ext': 'mp4', 'title': 'Teen couple doing anal', 'uploader': 'Alexy', - 'uploader_id': 'Alexy', + 'uploader_id': '91488', 'upload_date': '20150606', 'timestamp': 1433595647, 'duration': 5052, 'view_count': int, 'like_count': int, - 'categories': list, 'age_limit': 18, }, 'params': { @@ -191,6 +206,49 @@ class PornTubeIE(FourTubeBaseIE): 'only_matching': True, }] + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id, display_id = mobj.group('id', 'display_id') + + webpage = self._download_webpage(url, display_id) + + video = self._parse_json( + self._search_regex( + r'INITIALSTATE\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', + webpage, 'data', group='value'), video_id, + transform_source=lambda x: compat_urllib_parse_unquote( + compat_b64decode(x).decode('utf-8')))['page']['video'] + + title = video['title'] + media_id = video['mediaId'] + sources = [compat_str(e['height']) + for e in video['encodings'] if e.get('height')] + formats = self._extract_formats(url, video_id, media_id, sources) + + thumbnail = url_or_none(video.get('masterThumb')) + uploader = try_get(video, lambda x: x['user']['username'], compat_str) + uploader_id = compat_str(try_get(video, lambda x: x['user']['id'], int)) + like_count = int_or_none(video.get('likes')) + dislike_count = int_or_none(video.get('dislikes')) + view_count = int_or_none(video.get('playsQty')) + duration = int_or_none(video.get('durationInSeconds')) + timestamp = unified_timestamp(video.get('publishedAt')) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'timestamp': timestamp, + 'like_count': like_count, + 'dislike_count': dislike_count, + 'view_count': view_count, + 'duration': duration, + 'age_limit': 18, + } + class PornerBrosIE(FourTubeBaseIE): _VALID_URL = r'https?://(?:(?P<kind>www|m)\.)?pornerbros\.com/(?:videos/(?P<display_id>[^/]+)_|embed/)(?P<id>\d+)' From 6f1f59f39cf934d5ccae3ca2e6fd4eaab726137f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 15 Sep 2018 01:23:36 +0700 Subject: [PATCH 199/558] [extractor/common] Introduce channel meta fields --- youtube_dl/extractor/common.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index b8bbaf81a..8eab5947f 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -211,6 +211,11 @@ class InfoExtractor(object): If not explicitly set, calculated from timestamp. uploader_id: Nickname or id of the video uploader. uploader_url: Full URL to a personal webpage of the video uploader. + channel: Full name of the channel the video is uploaded on. + Note that channel fields may or may noy repeat uploader + fields. This depends on a particular extractor. + channel_id: Id of the channel. + channel_url: Full URL to a channel webpage. location: Physical location where the video was filmed. subtitles: The available subtitles as a dictionary in the format {tag: subformats}. "tag" is usually a language code, and From dd4c449219976ad6e80fef74a3431c5553cf5031 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 15 Sep 2018 01:24:26 +0700 Subject: [PATCH 200/558] [youtube] Extract channel meta fields (closes #9676, closes #12939) --- youtube_dl/extractor/youtube.py | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 27047425d..2fe074cb4 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -490,6 +490,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': 'Philipp Hagemeister', 'uploader_id': 'phihag', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', + 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', + 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', 'upload_date': '20121002', 'license': 'Standard YouTube License', 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .', @@ -1907,6 +1909,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): else: self._downloader.report_warning('unable to extract uploader nickname') + channel_id = self._html_search_meta( + 'channelId', video_webpage, 'channel id') + channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None + # thumbnail image # We try first to get a high quality image: m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">', @@ -2078,6 +2084,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': video_uploader, 'uploader_id': video_uploader_id, 'uploader_url': video_uploader_url, + 'channel_id': channel_id, + 'channel_url': channel_url, 'upload_date': upload_date, 'license': video_license, 'creator': video_creator or artist, From d03beddf0f0b460d1b58c98173e2d4620d1d11b0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 15 Sep 2018 01:24:48 +0700 Subject: [PATCH 201/558] [vimeo] Extract channel meta fields --- youtube_dl/extractor/vimeo.py | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index e49b233f2..95d368cc1 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -299,10 +299,13 @@ class VimeoIE(VimeoBaseInfoExtractor): 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio', 'uploader_id': 'atencio', 'uploader': 'Peter Atencio', + 'channel_id': 'keypeele', + 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele', 'timestamp': 1380339469, 'upload_date': '20130928', 'duration': 187, }, + 'expected_warnings': ['Unable to download JSON metadata'], }, { 'url': 'http://vimeo.com/76979871', @@ -355,11 +358,13 @@ class VimeoIE(VimeoBaseInfoExtractor): 'url': 'https://vimeo.com/channels/tributes/6213729', 'info_dict': { 'id': '6213729', - 'ext': 'mov', + 'ext': 'mp4', 'title': 'Vimeo Tribute: The Shining', 'uploader': 'Casey Donahue', 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue', 'uploader_id': 'caseydonahue', + 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes', + 'channel_id': 'tributes', 'timestamp': 1250886430, 'upload_date': '20090821', 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6', @@ -465,6 +470,9 @@ class VimeoIE(VimeoBaseInfoExtractor): if 'Referer' not in headers: headers['Referer'] = url + channel_id = self._search_regex( + r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None) + # Extract ID from URL mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') @@ -652,6 +660,8 @@ class VimeoIE(VimeoBaseInfoExtractor): r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1', webpage, 'license', default=None, group='license') + channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None + info_dict = { 'id': video_id, 'formats': formats, @@ -662,6 +672,8 @@ class VimeoIE(VimeoBaseInfoExtractor): 'like_count': like_count, 'comment_count': comment_count, 'license': cc_license, + 'channel_id': channel_id, + 'channel_url': channel_url, } info_dict = merge_dicts(info_dict, info_dict_config, json_ld) From 127103b643c5105bd361c5e3be267ac40843ccdc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 15 Sep 2018 01:25:32 +0700 Subject: [PATCH 202/558] [porntube] Extract channel meta fields --- youtube_dl/extractor/fourtube.py | 33 +++++++++++++++++++++++++++++--- 1 file changed, 30 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/fourtube.py b/youtube_dl/extractor/fourtube.py index 20391b2bb..a9a1f911e 100644 --- a/youtube_dl/extractor/fourtube.py +++ b/youtube_dl/extractor/fourtube.py @@ -13,6 +13,7 @@ from ..utils import ( int_or_none, parse_duration, parse_iso8601, + str_or_none, str_to_int, try_get, unified_timestamp, @@ -198,6 +199,26 @@ class PornTubeIE(FourTubeBaseIE): 'params': { 'skip_download': True, }, + }, { + 'url': 'https://www.porntube.com/videos/squirting-teen-ballerina-ecg_1331406', + 'info_dict': { + 'id': '1331406', + 'ext': 'mp4', + 'title': 'Squirting Teen Ballerina on ECG', + 'uploader': 'Exploited College Girls', + 'uploader_id': '665', + 'channel': 'Exploited College Girls', + 'channel_id': '665', + 'upload_date': '20130920', + 'timestamp': 1379685485, + 'duration': 851, + 'view_count': int, + 'like_count': int, + 'age_limit': 18, + }, + 'params': { + 'skip_download': True, + }, }, { 'url': 'https://www.porntube.com/embed/7089759', 'only_matching': True, @@ -227,7 +248,11 @@ class PornTubeIE(FourTubeBaseIE): thumbnail = url_or_none(video.get('masterThumb')) uploader = try_get(video, lambda x: x['user']['username'], compat_str) - uploader_id = compat_str(try_get(video, lambda x: x['user']['id'], int)) + uploader_id = str_or_none(try_get( + video, lambda x: x['user']['id'], int)) + channel = try_get(video, lambda x: x['channel']['name'], compat_str) + channel_id = str_or_none(try_get( + video, lambda x: x['channel']['id'], int)) like_count = int_or_none(video.get('likes')) dislike_count = int_or_none(video.get('dislikes')) view_count = int_or_none(video.get('playsQty')) @@ -239,8 +264,10 @@ class PornTubeIE(FourTubeBaseIE): 'title': title, 'formats': formats, 'thumbnail': thumbnail, - 'uploader': uploader, - 'uploader_id': uploader_id, + 'uploader': uploader or channel, + 'uploader_id': uploader_id or channel_id, + 'channel': channel, + 'channel_id': channel_id, 'timestamp': timestamp, 'like_count': like_count, 'dislike_count': dislike_count, From 0e7b8d3eaca710fbae8aa5531e28a6b6f05b387a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 15 Sep 2018 01:53:01 +0700 Subject: [PATCH 203/558] [extractor/common] Fix typos --- youtube_dl/extractor/common.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 8eab5947f..2dbf81e6e 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -212,7 +212,7 @@ class InfoExtractor(object): uploader_id: Nickname or id of the video uploader. uploader_url: Full URL to a personal webpage of the video uploader. channel: Full name of the channel the video is uploaded on. - Note that channel fields may or may noy repeat uploader + Note that channel fields may or may not repeat uploader fields. This depends on a particular extractor. channel_id: Id of the channel. channel_url: Full URL to a channel webpage. @@ -1706,9 +1706,9 @@ class InfoExtractor(object): # However, this is not always respected, for example, [2] # contains EXT-X-STREAM-INF tag which references AUDIO # rendition group but does not have CODECS and despite - # referencing audio group an audio group, it represents - # a complete (with audio and video) format. So, for such cases - # we will ignore references to rendition groups and treat them + # referencing an audio group it represents a complete + # (with audio and video) format. So, for such cases we will + # ignore references to rendition groups and treat them # as complete formats. if audio_group_id and codecs and f.get('vcodec') != 'none': audio_group = groups.get(audio_group_id) From 3661ebf2b6e0cb951dca5b4498a1d6885cbf7b56 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 15 Sep 2018 02:04:43 +0700 Subject: [PATCH 204/558] [pornhub] Extract upload date (closes #17574) --- youtube_dl/extractor/pornhub.py | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 6782848d9..19eaf389f 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -40,6 +40,7 @@ class PornHubIE(InfoExtractor): 'ext': 'mp4', 'title': 'Seductive Indian beauty strips down and fingers her pink pussy', 'uploader': 'Babes', + 'upload_date': '20130628', 'duration': 361, 'view_count': int, 'like_count': int, @@ -57,6 +58,7 @@ class PornHubIE(InfoExtractor): 'ext': 'mp4', 'title': '重庆婷婷女王足交', 'uploader': 'Unknown', + 'upload_date': '20150213', 'duration': 1753, 'view_count': int, 'like_count': int, @@ -237,8 +239,14 @@ class PornHubIE(InfoExtractor): video_urls.append((video_url, None)) video_urls_set.add(video_url) + upload_date = None formats = [] for video_url, height in video_urls: + if not upload_date: + upload_date = self._search_regex( + r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None) + if upload_date: + upload_date = upload_date.replace('/', '') tbr = None mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url) if mobj: @@ -278,6 +286,7 @@ class PornHubIE(InfoExtractor): return { 'id': video_id, 'uploader': video_uploader, + 'upload_date': upload_date, 'title': title, 'thumbnail': thumbnail, 'duration': duration, From 8b40c92724453995701b75559b190075d6dbfd7d Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 15 Sep 2018 06:30:57 +0100 Subject: [PATCH 205/558] [vimeo] redirect to feature url only in the case of a trailer(closes #14591) --- youtube_dl/extractor/vimeo.py | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 95d368cc1..0a9239b62 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -571,19 +571,23 @@ class VimeoIE(VimeoBaseInfoExtractor): if config.get('view') == 4: config = self._verify_player_video_password(redirect_url, video_id) + vod = config.get('video', {}).get('vod', {}) + def is_rented(): if '>You rented this title.<' in webpage: return True if config.get('user', {}).get('purchased'): return True - label = try_get( - config, lambda x: x['video']['vod']['purchase_options'][0]['label_string'], compat_str) - if label and label.startswith('You rented this'): - return True + for purchase_option in vod.get('purchase_options', []): + if purchase_option.get('purchased'): + return True + label = purchase_option.get('label_string') + if label and (label.startswith('You rented this') or label.endswith(' remaining')): + return True return False - if is_rented(): - feature_id = config.get('video', {}).get('vod', {}).get('feature_id') + if is_rented() and vod.get('is_trailer'): + feature_id = vod.get('feature_id') if feature_id and not data.get('force_feature_id', False): return self.url_result(smuggle_url( 'https://player.vimeo.com/player/%s' % feature_id, From d9b0d118adfa365e8ed67de277f5e83e29c4635c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 16 Sep 2018 23:52:27 +0700 Subject: [PATCH 206/558] [vrv] Make format ids deterministic --- youtube_dl/extractor/vrv.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/vrv.py b/youtube_dl/extractor/vrv.py index 921e9e172..ac0819c7c 100644 --- a/youtube_dl/extractor/vrv.py +++ b/youtube_dl/extractor/vrv.py @@ -90,7 +90,13 @@ class VRVIE(VRVBaseIE): def _extract_vrv_formats(self, url, video_id, stream_format, audio_lang, hardsub_lang): if not url or stream_format not in ('hls', 'dash'): return [] - stream_id = hardsub_lang or audio_lang + assert audio_lang or hardsub_lang + stream_id_list = [] + if audio_lang: + stream_id_list.append('audio-%s' % audio_lang) + if hardsub_lang: + stream_id_list.append('hardsub-%s' % hardsub_lang) + stream_id = '-'.join(stream_id_list) format_id = '%s-%s' % (stream_format, stream_id) if stream_format == 'hls': adaptive_formats = self._extract_m3u8_formats( From 1084563eaab3a039ea8ccb65f2507e919d8e11f0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 16 Sep 2018 23:54:25 +0700 Subject: [PATCH 207/558] [crunchyroll] Prefer hardsubless formats and formats in locale language --- youtube_dl/extractor/crunchyroll.py | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index ba8b9fa7e..af786d096 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -445,6 +445,10 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text webpage, 'vilos media', default='{}'), video_id) media_metadata = media.get('metadata') or {} + language = self._search_regex( + r'(?:vilos\.config\.player\.language|LOCALE)\s*=\s*(["\'])(?P<lang>(?:(?!\1).)+)\1', + webpage, 'language', default=None, group='lang') + video_title = self._html_search_regex( r'(?s)<h1[^>]*>((?:(?!<h1).)*?<span[^>]+itemprop=["\']title["\'][^>]*>(?:(?!<h1).)+?)</h1>', webpage, 'video_title') @@ -466,9 +470,22 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text formats = [] for stream in media.get('streams', []): - formats.extend(self._extract_vrv_formats( + audio_lang = stream.get('audio_lang') + hardsub_lang = stream.get('hardsub_lang') + vrv_formats = self._extract_vrv_formats( stream.get('url'), video_id, stream.get('format'), - stream.get('audio_lang'), stream.get('hardsub_lang'))) + audio_lang, hardsub_lang) + for f in vrv_formats: + if not hardsub_lang: + f['preference'] = 1 + language_preference = 0 + if audio_lang == language: + language_preference += 1 + if hardsub_lang == language: + language_preference += 1 + if language_preference: + f['language_preference'] = language_preference + formats.extend(vrv_formats) if not formats: available_fmts = [] for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage): @@ -557,7 +574,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'ext': 'flv', }) formats.append(format_info) - self._sort_formats(formats, ('height', 'width', 'tbr', 'fps')) + self._sort_formats(formats, ('preference', 'language_preference', 'height', 'width', 'tbr', 'fps')) metadata = self._call_rpc_api( 'VideoPlayer_GetMediaMetadata', video_id, From c11485162bcbf6f517fd9225850a048fc5f7cec1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 17 Sep 2018 22:13:39 +0700 Subject: [PATCH 208/558] [youtube] Don't pollute default query dict (closes #17593) --- youtube_dl/extractor/youtube.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 2fe074cb4..e80e36f98 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -259,7 +259,9 @@ class YoutubeBaseInfoExtractor(InfoExtractor): return True def _download_webpage_handle(self, *args, **kwargs): - kwargs.setdefault('query', {})['disable_polymer'] = 'true' + query = kwargs.get('query', {}).copy() + query['disable_polymer'] = 'true' + kwargs['query'] = query return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle( *args, **compat_kwargs(kwargs)) From e2f61598be49b75f16b501f7a4d24f4c8c230c49 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 17 Sep 2018 22:14:28 +0700 Subject: [PATCH 209/558] [twitch] Don't pollute default headers dict --- youtube_dl/extractor/twitch.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index 26661fdf6..401615683 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -51,7 +51,9 @@ class TwitchBaseIE(InfoExtractor): expected=True) def _call_api(self, path, item_id, *args, **kwargs): - kwargs.setdefault('headers', {})['Client-ID'] = self._CLIENT_ID + headers = kwargs.get('headers', {}).copy() + headers['Client-ID'] = self._CLIENT_ID + kwargs['headers'] = headers response = self._download_json( '%s/%s' % (self._API_BASE, path), item_id, *args, **compat_kwargs(kwargs)) From c8f6ab8c38f8397b06028cdea2839d6e25e2c809 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 17 Sep 2018 22:14:53 +0700 Subject: [PATCH 210/558] [udemy] Don't pollute default headers dict --- youtube_dl/extractor/udemy.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py index 79c45f80e..105826e9b 100644 --- a/youtube_dl/extractor/udemy.py +++ b/youtube_dl/extractor/udemy.py @@ -122,7 +122,9 @@ class UdemyIE(InfoExtractor): raise ExtractorError(error_str, expected=True) def _download_webpage_handle(self, *args, **kwargs): - kwargs.setdefault('headers', {})['User-Agent'] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/603.2.4 (KHTML, like Gecko) Version/10.1.1 Safari/603.2.4' + headers = kwargs.get('headers', {}).copy() + headers['User-Agent'] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/603.2.4 (KHTML, like Gecko) Version/10.1.1 Safari/603.2.4' + kwargs['headers'] = headers return super(UdemyIE, self)._download_webpage_handle( *args, **compat_kwargs(kwargs)) From e504b0907082512d5252643d7fd8c5ca67225e3d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 17 Sep 2018 22:15:27 +0700 Subject: [PATCH 211/558] [adobepass] Don't pollute default headers dict --- youtube_dl/extractor/adobepass.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/adobepass.py b/youtube_dl/extractor/adobepass.py index b83b51efb..1cf2dcbf3 100644 --- a/youtube_dl/extractor/adobepass.py +++ b/youtube_dl/extractor/adobepass.py @@ -1325,8 +1325,8 @@ class AdobePassIE(InfoExtractor): _DOWNLOADING_LOGIN_PAGE = 'Downloading Provider Login Page' def _download_webpage_handle(self, *args, **kwargs): - headers = kwargs.get('headers', {}) - headers.update(self.geo_verification_headers()) + headers = self.geo_verification_headers() + headers.update(kwargs.get('headers', {})) kwargs['headers'] = headers return super(AdobePassIE, self)._download_webpage_handle( *args, **compat_kwargs(kwargs)) From d9b1cec1712c39d7e98a4ca44051643eebef8b30 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 18 Sep 2018 01:44:55 +0700 Subject: [PATCH 212/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/ChangeLog b/ChangeLog index d184f69ee..b2b2d90a1 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,28 @@ +version <unreleased> + +Core ++ [extractor/common] Introduce channel meta fields + +Extractors +* [adobepass] Don't pollute default headers dict +* [udemy] Don't pollute default headers dict +* [twitch] Don't pollute default headers dict +* [youtube] Don't pollute default query dict (#17593) +* [crunchyroll] Prefer hardsubless formats and formats in locale language +* [vrv] Make format ids deterministic +* [vimeo] Fix ondemand playlist extraction (#14591) ++ [pornhub] Extract upload date (#17574) ++ [porntube] Extract channel meta fields ++ [vimeo] Extract channel meta fields ++ [youtube] Extract channel meta fields (#9676, #12939) +* [porntube] Fix extraction (#17541) +* [asiancrush] Fix extraction (#15630) ++ [twitch:clips] Extend URL regular expression (closes #17559) ++ [vzaar] Add support for HLS +* [tube8] Fix metadata extraction (#17520) +* [eporner] Extract JSON-LD (#17519) + + version 2018.09.10 Core From 3a9c928426258e51c74515b09f7c6f565d60efe8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 18 Sep 2018 01:46:36 +0700 Subject: [PATCH 213/558] release 2018.09.18 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index f41266f32..a4602287a 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.09.10*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.09.10** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.09.18*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.09.18** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.09.10 +[debug] youtube-dl version 2018.09.18 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index b2b2d90a1..800ece790 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.09.18 Core + [extractor/common] Introduce channel meta fields diff --git a/youtube_dl/version.py b/youtube_dl/version.py index b078c4993..2b3b584a4 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.09.10' +__version__ = '2018.09.18' From 28fcb7b06178cebfc361f0d1c491ea9507b0d75e Mon Sep 17 00:00:00 2001 From: Leonardo Taccari <iamleot@gmail.com> Date: Wed, 19 Sep 2018 04:48:39 +0200 Subject: [PATCH 214/558] [raiplay:playlist] Remove a debug leftover print() --- youtube_dl/extractor/rai.py | 1 - 1 file changed, 1 deletion(-) diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py index f916b2619..548a6553b 100644 --- a/youtube_dl/extractor/rai.py +++ b/youtube_dl/extractor/rai.py @@ -274,7 +274,6 @@ class RaiPlayPlaylistIE(InfoExtractor): ('programma', 'nomeProgramma'), webpage, 'title') description = unescapeHTML(self._html_search_meta( ('description', 'og:description'), webpage, 'description')) - print(description) entries = [] for mobj in re.finditer( From 4ac73fc170f41ccb2d468a0b8563b2ec39d9e9b9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 19 Sep 2018 22:16:43 +0700 Subject: [PATCH 215/558] [popcorntv] Remove debug output --- youtube_dl/extractor/popcorntv.py | 2 -- 1 file changed, 2 deletions(-) diff --git a/youtube_dl/extractor/popcorntv.py b/youtube_dl/extractor/popcorntv.py index ac901f426..9f834fb6c 100644 --- a/youtube_dl/extractor/popcorntv.py +++ b/youtube_dl/extractor/popcorntv.py @@ -58,8 +58,6 @@ class PopcornTVIE(InfoExtractor): thumbnail = self._og_search_thumbnail(webpage) timestamp = unified_timestamp(self._html_search_meta( 'uploadDate', webpage, 'timestamp')) - print(self._html_search_meta( - 'duration', webpage)) duration = int_or_none(self._html_search_meta( 'duration', webpage), invscale=60) view_count = int_or_none(self._html_search_meta( From 21160a179256cfbb859948138905ffe67cb970a8 Mon Sep 17 00:00:00 2001 From: Alexander Seiler <seileralex@gmail.com> Date: Sun, 23 Sep 2018 16:34:47 +0200 Subject: [PATCH 216/558] [zattoo] Fix extraction (closes #17175) --- youtube_dl/extractor/zattoo.py | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/youtube_dl/extractor/zattoo.py b/youtube_dl/extractor/zattoo.py index fb167c198..9c9024799 100644 --- a/youtube_dl/extractor/zattoo.py +++ b/youtube_dl/extractor/zattoo.py @@ -93,28 +93,30 @@ class ZattooBaseIE(InfoExtractor): def _extract_cid_and_video_info(self, video_id): data = self._download_json( - '%s/zapi/program/details' % self._HOST_URL, + '%s/zapi/v2/cached/program/power_details/%s' % ( + self._HOST_URL, self._power_guide_hash), video_id, 'Downloading video information', query={ - 'program_id': video_id, - 'complete': True + 'program_ids': video_id, + 'complete': True, }) - p = data['program'] + p = data['programs'][0] cid = p['cid'] info_dict = { 'id': video_id, - 'title': p.get('title') or p['episode_title'], - 'description': p.get('description'), - 'thumbnail': p.get('image_url'), + 'title': p.get('t') or p['et'], + 'description': p.get('d'), + 'thumbnail': p.get('i_url'), 'creator': p.get('channel_name'), - 'episode': p.get('episode_title'), - 'episode_number': int_or_none(p.get('episode_number')), - 'season_number': int_or_none(p.get('season_number')), + 'episode': p.get('et'), + 'episode_number': int_or_none(p.get('e_no')), + 'season_number': int_or_none(p.get('s_no')), 'release_year': int_or_none(p.get('year')), - 'categories': try_get(p, lambda x: x['categories'], list), + 'categories': try_get(p, lambda x: x['c'], list), + 'tags': try_get(p, lambda x: x['g'], list) } return cid, info_dict From f6d7f7b474075955afb02c373b8d2a442faaa0a3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 23 Sep 2018 23:30:18 +0700 Subject: [PATCH 217/558] [zattoo] Add support for more zattoo platform sites --- youtube_dl/extractor/extractors.py | 12 ++ youtube_dl/extractor/zattoo.py | 178 ++++++++++++++++++++++++++--- 2 files changed, 172 insertions(+), 18 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 7dc569724..464c8d690 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1455,8 +1455,20 @@ from .youtube import ( from .zapiks import ZapiksIE from .zaq1 import Zaq1IE from .zattoo import ( + BBVTVIE, + EinsUndEinsTVIE, + EWETVIE, + GlattvisionTVIE, + MNetTVIE, + MyVisionTVIE, + NetPlusIE, + OsnatelTVIE, + QuantumTVIE, QuicklineIE, QuicklineLiveIE, + SAKTVIE, + VTXTVIE, + WalyTVIE, ZattooIE, ZattooLiveIE, ) diff --git a/youtube_dl/extractor/zattoo.py b/youtube_dl/extractor/zattoo.py index 9c9024799..bbe0aecb6 100644 --- a/youtube_dl/extractor/zattoo.py +++ b/youtube_dl/extractor/zattoo.py @@ -18,12 +18,12 @@ from ..utils import ( ) -class ZattooBaseIE(InfoExtractor): - _NETRC_MACHINE = 'zattoo' - _HOST_URL = 'https://zattoo.com' - +class ZattooPlatformBaseIE(InfoExtractor): _power_guide_hash = None + def _host_url(self): + return 'https://%s' % self._HOST + def _login(self): username, password = self._get_login_info() if not username or not password: @@ -33,13 +33,13 @@ class ZattooBaseIE(InfoExtractor): try: data = self._download_json( - '%s/zapi/v2/account/login' % self._HOST_URL, None, 'Logging in', + '%s/zapi/v2/account/login' % self._host_url(), None, 'Logging in', data=urlencode_postdata({ 'login': username, 'password': password, 'remember': 'true', }), headers={ - 'Referer': '%s/login' % self._HOST_URL, + 'Referer': '%s/login' % self._host_url(), 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', }) except ExtractorError as e: @@ -53,7 +53,7 @@ class ZattooBaseIE(InfoExtractor): def _real_initialize(self): webpage = self._download_webpage( - self._HOST_URL, None, 'Downloading app token') + self._host_url(), None, 'Downloading app token') app_token = self._html_search_regex( r'appToken\s*=\s*(["\'])(?P<token>(?:(?!\1).)+?)\1', webpage, 'app token', group='token') @@ -62,7 +62,7 @@ class ZattooBaseIE(InfoExtractor): # Will setup appropriate cookies self._request_webpage( - '%s/zapi/v2/session/hello' % self._HOST_URL, None, + '%s/zapi/v2/session/hello' % self._host_url(), None, 'Opening session', data=urlencode_postdata({ 'client_app_token': app_token, 'uuid': compat_str(uuid4()), @@ -75,7 +75,7 @@ class ZattooBaseIE(InfoExtractor): def _extract_cid(self, video_id, channel_name): channel_groups = self._download_json( - '%s/zapi/v2/cached/channels/%s' % (self._HOST_URL, + '%s/zapi/v2/cached/channels/%s' % (self._host_url(), self._power_guide_hash), video_id, 'Downloading channel list', query={'details': False})['channel_groups'] @@ -94,7 +94,7 @@ class ZattooBaseIE(InfoExtractor): def _extract_cid_and_video_info(self, video_id): data = self._download_json( '%s/zapi/v2/cached/program/power_details/%s' % ( - self._HOST_URL, self._power_guide_hash), + self._host_url(), self._power_guide_hash), video_id, 'Downloading video information', query={ @@ -128,11 +128,11 @@ class ZattooBaseIE(InfoExtractor): if is_live: postdata_common.update({'timeshift': 10800}) - url = '%s/zapi/watch/live/%s' % (self._HOST_URL, cid) + url = '%s/zapi/watch/live/%s' % (self._host_url(), cid) elif record_id: - url = '%s/zapi/watch/recording/%s' % (self._HOST_URL, record_id) + url = '%s/zapi/watch/recording/%s' % (self._host_url(), record_id) else: - url = '%s/zapi/watch/recall/%s/%s' % (self._HOST_URL, cid, video_id) + url = '%s/zapi/watch/recall/%s/%s' % (self._host_url(), cid, video_id) formats = [] for stream_type in ('dash', 'hls', 'hls5', 'hds'): @@ -203,13 +203,13 @@ class ZattooBaseIE(InfoExtractor): return info_dict -class QuicklineBaseIE(ZattooBaseIE): +class QuicklineBaseIE(ZattooPlatformBaseIE): _NETRC_MACHINE = 'quickline' - _HOST_URL = 'https://mobiltv.quickline.com' + _HOST = 'mobiltv.quickline.com' class QuicklineIE(QuicklineBaseIE): - _VALID_URL = r'https?://(?:www\.)?mobiltv\.quickline\.com/watch/(?P<channel>[^/]+)/(?P<id>[0-9]+)' + _VALID_URL = r'https?://(?:www\.)?%s/watch/(?P<channel>[^/]+)/(?P<id>[0-9]+)' % re.escape(QuicklineBaseIE._HOST) _TEST = { 'url': 'https://mobiltv.quickline.com/watch/prosieben/130671867-maze-runner-die-auserwaehlten-in-der-brandwueste', @@ -222,7 +222,7 @@ class QuicklineIE(QuicklineBaseIE): class QuicklineLiveIE(QuicklineBaseIE): - _VALID_URL = r'https?://(?:www\.)?mobiltv\.quickline\.com/watch/(?P<id>[^/]+)' + _VALID_URL = r'https?://(?:www\.)?%s/watch/(?P<id>[^/]+)' % re.escape(QuicklineBaseIE._HOST) _TEST = { 'url': 'https://mobiltv.quickline.com/watch/srf1', @@ -238,8 +238,18 @@ class QuicklineLiveIE(QuicklineBaseIE): return self._extract_video(channel_name, video_id, is_live=True) +class ZattooBaseIE(ZattooPlatformBaseIE): + _NETRC_MACHINE = 'zattoo' + _HOST = 'zattoo.com' + + +def _make_valid_url(tmpl, host): + return tmpl % re.escape(host) + + class ZattooIE(ZattooBaseIE): - _VALID_URL = r'https?://(?:www\.)?zattoo\.com/watch/(?P<channel>[^/]+?)/(?P<id>[0-9]+)[^/]+(?:/(?P<recid>[0-9]+))?' + _VALID_URL_TEMPLATE = r'https?://(?:www\.)?%s/watch/(?P<channel>[^/]+?)/(?P<id>[0-9]+)[^/]+(?:/(?P<recid>[0-9]+))?' + _VALID_URL = _make_valid_url(_VALID_URL_TEMPLATE, ZattooBaseIE._HOST) # Since regular videos are only available for 7 days and recorded videos # are only available for a specific user, we cannot have detailed tests. @@ -271,3 +281,135 @@ class ZattooLiveIE(ZattooBaseIE): def _real_extract(self, url): channel_name = video_id = self._match_id(url) return self._extract_video(channel_name, video_id, is_live=True) + + +class NetPlusIE(ZattooIE): + _NETRC_MACHINE = 'netplus' + _HOST = 'netplus.tv' + _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) + + _TESTS = [{ + 'url': 'https://www.netplus.tv/watch/abc/123-abc', + 'only_matching': True, + }] + + +class MNetTVIE(ZattooIE): + _NETRC_MACHINE = 'mnettv' + _HOST = 'tvplus.m-net.de' + _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) + + _TESTS = [{ + 'url': 'https://www.tvplus.m-net.de/watch/abc/123-abc', + 'only_matching': True, + }] + + +class WalyTVIE(ZattooIE): + _NETRC_MACHINE = 'walytv' + _HOST = 'player.waly.tv' + _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) + + _TESTS = [{ + 'url': 'https://www.player.waly.tv/watch/abc/123-abc', + 'only_matching': True, + }] + + +class BBVTVIE(ZattooIE): + _NETRC_MACHINE = 'bbvtv' + _HOST = 'bbv-tv.net' + _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) + + _TESTS = [{ + 'url': 'https://www.bbv-tv.net/watch/abc/123-abc', + 'only_matching': True, + }] + + +class VTXTVIE(ZattooIE): + _NETRC_MACHINE = 'vtxtv' + _HOST = 'vtxtv.ch' + _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) + + _TESTS = [{ + 'url': 'https://www.vtxtv.ch/watch/abc/123-abc', + 'only_matching': True, + }] + + +class MyVisionTVIE(ZattooIE): + _NETRC_MACHINE = 'myvisiontv' + _HOST = 'myvisiontv.ch' + _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) + + _TESTS = [{ + 'url': 'https://www.myvisiontv.ch/watch/abc/123-abc', + 'only_matching': True, + }] + + +class GlattvisionTVIE(ZattooIE): + _NETRC_MACHINE = 'glattvisiontv' + _HOST = 'iptv.glattvision.ch' + _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) + + _TESTS = [{ + 'url': 'https://www.iptv.glattvision.ch/watch/abc/123-abc', + 'only_matching': True, + }] + + +class SAKTVIE(ZattooIE): + _NETRC_MACHINE = 'saktv' + _HOST = 'saktv.ch' + _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) + + _TESTS = [{ + 'url': 'https://www.saktv.ch/watch/abc/123-abc', + 'only_matching': True, + }] + + +class EWETVIE(ZattooIE): + _NETRC_MACHINE = 'ewetv' + _HOST = 'tvonline.ewe.de' + _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) + + _TESTS = [{ + 'url': 'https://www.tvonline.ewe.de/watch/abc/123-abc', + 'only_matching': True, + }] + + +class QuantumTVIE(ZattooIE): + _NETRC_MACHINE = 'quantumtv' + _HOST = 'quantum-tv.com' + _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) + + _TESTS = [{ + 'url': 'https://www.quantum-tv.com/watch/abc/123-abc', + 'only_matching': True, + }] + + +class OsnatelTVIE(ZattooIE): + _NETRC_MACHINE = 'osnateltv' + _HOST = 'onlinetv.osnatel.de' + _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) + + _TESTS = [{ + 'url': 'https://www.onlinetv.osnatel.de/watch/abc/123-abc', + 'only_matching': True, + }] + + +class EinsUndEinsTVIE(ZattooIE): + _NETRC_MACHINE = '1und1tv' + _HOST = '1und1.tv' + _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) + + _TESTS = [{ + 'url': 'https://www.1und1.tv/watch/abc/123-abc', + 'only_matching': True, + }] From cd5a74a28e7102e877d00b1e3cffba82d28b2f2b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 24 Sep 2018 00:14:49 +0700 Subject: [PATCH 218/558] [youtube] Add support for invidio.us (closes #17613) --- youtube_dl/extractor/youtube.py | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index e80e36f98..78203ef84 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -349,6 +349,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): (?:www\.)?hooktube\.com/| (?:www\.)?yourepeat\.com/| tube\.majestyc\.net/| + (?:www\.)?invidio\.us/| youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains (?:.*?\#/)? # handle anchor (#/) redirect urls (?: # the various things that can precede the ID: @@ -1068,6 +1069,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM', 'only_matching': True, }, + { + 'url': 'https://invidio.us/watch?v=BaW_jenozKc', + 'only_matching': True, + }, ] def __init__(self, *args, **kwargs): @@ -2419,7 +2424,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor): IE_DESC = 'YouTube.com channels' - _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)' + _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)' _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos' _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?' IE_NAME = 'youtube:channel' @@ -2440,6 +2445,9 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor): 'id': 'UUs0ifCMCm1icqRbqhUINa0w', 'title': 'Uploads from Deus Ex', }, + }, { + 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA', + 'only_matching': True, }] @classmethod From 60ce0c67fd1ef71463af2c036bbabf06ec26bd98 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 25 Sep 2018 23:43:41 +0700 Subject: [PATCH 219/558] [README.md] Document channel meta fields for output template --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index dd068a462..fdd115c9b 100644 --- a/README.md +++ b/README.md @@ -511,6 +511,8 @@ The basic usage is not to set any template arguments when downloading a single f - `timestamp` (numeric): UNIX timestamp of the moment the video became available - `upload_date` (string): Video upload date (YYYYMMDD) - `uploader_id` (string): Nickname or id of the video uploader + - `channel` (string): Full name of the channel the video is uploaded on + - `channel_id` (string): Id of the channel - `location` (string): Physical location where the video was filmed - `duration` (numeric): Length of the video in seconds - `view_count` (numeric): How many users have watched the video on the platform From 8fd12a083131550476fb771c180a0734794d0b9d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 26 Sep 2018 05:38:41 +0700 Subject: [PATCH 220/558] [mediaset] Improve embed support (closes #17668) --- youtube_dl/extractor/generic.py | 2 +- youtube_dl/extractor/mediaset.py | 38 +++++++++++++++++++++++++++----- 2 files changed, 33 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 76ef01332..2a48667f0 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -3023,7 +3023,7 @@ class GenericIE(InfoExtractor): wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key()) # Look for Mediaset embeds - mediaset_urls = MediasetIE._extract_urls(webpage) + mediaset_urls = MediasetIE._extract_urls(self, webpage) if mediaset_urls: return self.playlist_from_matches( mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key()) diff --git a/youtube_dl/extractor/mediaset.py b/youtube_dl/extractor/mediaset.py index 57f97409d..df3748798 100644 --- a/youtube_dl/extractor/mediaset.py +++ b/youtube_dl/extractor/mediaset.py @@ -4,6 +4,11 @@ from __future__ import unicode_literals import re from .theplatform import ThePlatformBaseIE +from ..compat import ( + compat_parse_qs, + compat_str, + compat_urllib_parse_urlparse, +) from ..utils import ( ExtractorError, int_or_none, @@ -76,12 +81,33 @@ class MediasetIE(ThePlatformBaseIE): }] @staticmethod - def _extract_urls(webpage): - return [ - mobj.group('url') - for mobj in re.finditer( - r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>https?://(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml\?.*?\bid=\d+.*?)\1', - webpage)] + def _extract_urls(ie, webpage): + def _qs(url): + return compat_parse_qs(compat_urllib_parse_urlparse(url).query) + + def _program_guid(qs): + return qs.get('programGuid', [None])[0] + + entries = [] + for mobj in re.finditer( + r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml.*?)\1', + webpage): + embed_url = mobj.group('url') + embed_qs = _qs(embed_url) + program_guid = _program_guid(embed_qs) + if program_guid: + entries.append(embed_url) + continue + video_id = embed_qs.get('id', [None])[0] + if not video_id: + continue + urlh = ie._request_webpage( + embed_url, video_id, note='Following embed URL redirect') + embed_url = compat_str(urlh.geturl()) + program_guid = _program_guid(_qs(embed_url)) + if program_guid: + entries.append(embed_url) + return entries def _real_extract(self, url): guid = self._match_id(url) From c17e100b96e3a1c1d2115226c9a2f166c8338031 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 26 Sep 2018 09:27:40 +0700 Subject: [PATCH 221/558] [pluralsight] Fix subtitles extraction (closes #17671) --- youtube_dl/extractor/pluralsight.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/pluralsight.py b/youtube_dl/extractor/pluralsight.py index 1257841e4..ec67381bb 100644 --- a/youtube_dl/extractor/pluralsight.py +++ b/youtube_dl/extractor/pluralsight.py @@ -213,7 +213,7 @@ query viewClip { def _get_subtitles(self, author, clip_idx, lang, name, duration, video_id): captions_post = { 'a': author, - 'cn': clip_idx, + 'cn': int(clip_idx), 'lc': lang, 'm': name, } From 3d3499742c88ce89de5b49dff4e96483b089fcaf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 26 Sep 2018 11:56:15 +0700 Subject: [PATCH 222/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/ChangeLog b/ChangeLog index 800ece790..15b875297 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,13 @@ +version <unreleased> + +Extractors +* [pluralsight] Fix subtitles extraction (#17671) +* [mediaset] Improve embed support (#17668) ++ [youtube] Add support for invidio.us (#17613) ++ [zattoo] Add support for more zattoo platform sites +* [zattoo] Fix extraction (#17175, #17542) + + version 2018.09.18 Core From 4c89a675dd50429a1a5f5903e624db0204d2435a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 26 Sep 2018 11:58:25 +0700 Subject: [PATCH 223/558] release 2018.09.26 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 12 ++++++++++++ youtube_dl/version.py | 2 +- 4 files changed, 17 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index a4602287a..ed3e0a157 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.09.18*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.09.18** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.09.26*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.09.26** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.09.18 +[debug] youtube-dl version 2018.09.26 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 15b875297..241712037 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.09.26 Extractors * [pluralsight] Fix subtitles extraction (#17671) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 9b8601751..736ab6da7 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -98,6 +98,7 @@ - **bbc.co.uk:article**: BBC articles - **bbc.co.uk:iplayer:playlist** - **bbc.co.uk:playlist** + - **BBVTV** - **Beatport** - **Beeg** - **BehindKink** @@ -251,6 +252,7 @@ - **egghead:course**: egghead.io course - **egghead:lesson**: egghead.io lesson - **eHow** + - **EinsUndEinsTV** - **Einthusan** - **eitb.tv** - **EllenTube** @@ -268,6 +270,7 @@ - **EsriVideo** - **Europa** - **EveryonesMixtape** + - **EWETV** - **ExpoTV** - **Expressen** - **ExtremeTube** @@ -327,6 +330,7 @@ - **Gfycat** - **GiantBomb** - **Giga** + - **GlattvisionTV** - **Glide**: Glide mobile video messages (glide.me) - **Globo** - **GloboArticle** @@ -494,6 +498,7 @@ - **Mixer:vod** - **MLB** - **Mnet** + - **MNetTV** - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net - **Mofosex** - **Mojvideo** @@ -525,6 +530,7 @@ - **Myvi** - **MyVidster** - **MyviEmbed** + - **MyVisionTV** - **n-tv.de** - **natgeo** - **natgeo:episodeguide** @@ -550,6 +556,7 @@ - **netease:program**: 网易云音乐 - 电台节目 - **netease:singer**: 网易云音乐 - 歌手 - **netease:song**: 网易云音乐 + - **NetPlus** - **Netzkino** - **Newgrounds** - **NewgroundsPlaylist** @@ -626,6 +633,7 @@ - **orf:iptv**: iptv.ORF.at - **orf:oe1**: Radio Österreich 1 - **orf:tvthek**: ORF TVthek + - **OsnatelTV** - **PacktPub** - **PacktPubCourse** - **PandaTV**: 熊猫TV @@ -686,6 +694,7 @@ - **qqmusic:playlist**: QQ音乐 - 歌单 - **qqmusic:singer**: QQ音乐 - 歌手 - **qqmusic:toplist**: QQ音乐 - 排行榜 + - **QuantumTV** - **Quickline** - **QuicklineLive** - **R7** @@ -753,6 +762,7 @@ - **safari**: safaribooksonline.com online video - **safari:api** - **safari:course**: safaribooksonline.com online courses + - **SAKTV** - **Sapo**: SAPO Vídeos - **savefrom.net** - **SBS**: sbs.com.au @@ -1035,12 +1045,14 @@ - **vrv** - **vrv:series** - **VShare** + - **VTXTV** - **vube**: Vube.com - **VuClip** - **VVVVID** - **VyboryMos** - **Vzaar** - **Walla** + - **WalyTV** - **washingtonpost** - **washingtonpost:article** - **wat.tv** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 2b3b584a4..6f2cc31df 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.09.18' +__version__ = '2018.09.26' From 85cd69adcb41454f30d4db85eeb4d5cc26b6bb5d Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 26 Sep 2018 08:13:16 +0100 Subject: [PATCH 224/558] [hotstar] fix extraction(closes #14694)(closes #14931)(closes #17637) --- youtube_dl/extractor/hotstar.py | 159 +++++++++++++++----------------- 1 file changed, 73 insertions(+), 86 deletions(-) diff --git a/youtube_dl/extractor/hotstar.py b/youtube_dl/extractor/hotstar.py index d28af36ec..354ac00dc 100644 --- a/youtube_dl/extractor/hotstar.py +++ b/youtube_dl/extractor/hotstar.py @@ -1,10 +1,12 @@ # coding: utf-8 from __future__ import unicode_literals -import re +import hashlib +import hmac +import time from .common import InfoExtractor -from ..compat import compat_str +from ..compat import compat_HTTPError from ..utils import ( determine_ext, ExtractorError, @@ -13,37 +15,40 @@ from ..utils import ( class HotStarBaseIE(InfoExtractor): - _GEO_COUNTRIES = ['IN'] + _AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee' - def _download_json(self, *args, **kwargs): - response = super(HotStarBaseIE, self)._download_json(*args, **kwargs) - if response['resultCode'] != 'OK': - if kwargs.get('fatal'): - raise ExtractorError( - response['errorDescription'], expected=True) - return None - return response['resultObj'] - - def _download_content_info(self, content_id): - return self._download_json( - 'https://account.hotstar.com/AVS/besc', content_id, query={ - 'action': 'GetAggregatedContentDetails', - 'appVersion': '5.0.40', - 'channel': 'PCTV', - 'contentId': content_id, - })['contentInfo'][0] + def _call_api(self, path, video_id, query_name='contentId'): + st = int(time.time()) + exp = st + 6000 + auth = 'st=%d~exp=%d~acl=/*' % (st, exp) + auth += '~hmac=' + hmac.new(self._AKAMAI_ENCRYPTION_KEY, auth.encode(), hashlib.sha256).hexdigest() + response = self._download_json( + 'https://api.hotstar.com/' + path, + video_id, headers={ + 'hotstarauth': auth, + 'x-country-code': 'IN', + 'x-platform-code': 'JIO', + }, query={ + query_name: video_id, + 'tas': 10000, + }) + if response['statusCode'] != 'OK': + raise ExtractorError( + response['body']['message'], expected=True) + return response['body']['results'] class HotStarIE(HotStarBaseIE): + IE_NAME = 'hotstar' _VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+?[/-])?(?P<id>\d{10})' _TESTS = [{ - 'url': 'http://www.hotstar.com/on-air-with-aib--english-1000076273', + 'url': 'https://www.hotstar.com/can-you-not-spread-rumours/1000076273', 'info_dict': { 'id': '1000076273', 'ext': 'mp4', - 'title': 'On Air With AIB', + 'title': 'Can You Not Spread Rumours?', 'description': 'md5:c957d8868e9bc793ccb813691cc4c434', - 'timestamp': 1447227000, + 'timestamp': 1447248600, 'upload_date': '20151111', 'duration': 381, }, @@ -58,47 +63,43 @@ class HotStarIE(HotStarBaseIE): 'url': 'http://www.hotstar.com/1000000515', 'only_matching': True, }] + _GEO_BYPASS = False def _real_extract(self, url): video_id = self._match_id(url) - video_data = self._download_content_info(video_id) + webpage = self._download_webpage(url, video_id) + app_state = self._parse_json(self._search_regex( + r'<script>window\.APP_STATE\s*=\s*({.+?})</script>', + webpage, 'app state'), video_id) + video_data = list(app_state.values())[0]['initialState']['contentData']['content'] - title = video_data['episodeTitle'] + title = video_data['title'] - if video_data.get('encrypted') == 'Y': + if video_data.get('drmProtected'): raise ExtractorError('This video is DRM protected.', expected=True) formats = [] - for f in ('JIO',): - format_data = self._download_json( - 'http://getcdn.hotstar.com/AVS/besc', - video_id, 'Downloading %s JSON metadata' % f, - fatal=False, query={ - 'action': 'GetCDN', - 'asJson': 'Y', - 'channel': f, - 'id': video_id, - 'type': 'VOD', - }) - if format_data: - format_url = format_data.get('src') - if not format_url: - continue - ext = determine_ext(format_url) - if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - format_url, video_id, 'mp4', - m3u8_id='hls', fatal=False)) - elif ext == 'f4m': - # produce broken files - continue - else: - formats.append({ - 'url': format_url, - 'width': int_or_none(format_data.get('width')), - 'height': int_or_none(format_data.get('height')), - }) + format_data = self._call_api('h/v1/play', video_id)['item'] + format_url = format_data['playbackUrl'] + ext = determine_ext(format_url) + if ext == 'm3u8': + try: + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', m3u8_id='hls')) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + self.raise_geo_restricted(countries=['IN']) + raise + elif ext == 'f4m': + # produce broken files + pass + else: + formats.append({ + 'url': format_url, + 'width': int_or_none(format_data.get('width')), + 'height': int_or_none(format_data.get('height')), + }) self._sort_formats(formats) return { @@ -106,57 +107,43 @@ class HotStarIE(HotStarBaseIE): 'title': title, 'description': video_data.get('description'), 'duration': int_or_none(video_data.get('duration')), - 'timestamp': int_or_none(video_data.get('broadcastDate')), + 'timestamp': int_or_none(video_data.get('broadcastDate') or video_data.get('startDate')), 'formats': formats, + 'channel': video_data.get('channelName'), + 'channel_id': video_data.get('channelId'), + 'series': video_data.get('showName'), + 'season': video_data.get('seasonName'), + 'season_number': int_or_none(video_data.get('seasonNo')), + 'season_id': video_data.get('seasonId'), 'episode': title, - 'episode_number': int_or_none(video_data.get('episodeNumber')), - 'series': video_data.get('contentTitle'), + 'episode_number': int_or_none(video_data.get('episodeNo')), } class HotStarPlaylistIE(HotStarBaseIE): IE_NAME = 'hotstar:playlist' - _VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com/tv/[^/]+/(?P<content_id>\d+))/(?P<type>[^/]+)/(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?hotstar\.com/tv/[^/]+/s-\w+/list/[^/]+/t-(?P<id>\w+)' _TESTS = [{ - 'url': 'http://www.hotstar.com/tv/pratidaan/14982/episodes/14812/9993', + 'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/popular-clips/t-3_2_26', 'info_dict': { - 'id': '14812', + 'id': '3_2_26', }, - 'playlist_mincount': 75, + 'playlist_mincount': 20, }, { - 'url': 'http://www.hotstar.com/tv/pratidaan/14982/popular-clips/9998/9998', + 'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/extras/t-2480', 'only_matching': True, }] - _ITEM_TYPES = { - 'episodes': 'EPISODE', - 'popular-clips': 'CLIPS', - } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - base_url = mobj.group('url') - content_id = mobj.group('content_id') - playlist_type = mobj.group('type') + playlist_id = self._match_id(url) - content_info = self._download_content_info(content_id) - playlist_id = compat_str(content_info['categoryId']) - - collection = self._download_json( - 'https://search.hotstar.com/AVS/besc', playlist_id, query={ - 'action': 'SearchContents', - 'appVersion': '5.0.40', - 'channel': 'PCTV', - 'moreFilters': 'series:%s;' % playlist_id, - 'query': '*', - 'searchOrder': 'last_broadcast_date desc,year desc,title asc', - 'type': self._ITEM_TYPES.get(playlist_type, 'EPISODE'), - }) + collection = self._call_api('o/v1/tray/find', playlist_id, 'uqId') entries = [ self.url_result( - '%s/_/%s' % (base_url, video['contentId']), + 'https://www.hotstar.com/%s' % video['contentId'], ie=HotStarIE.ie_key(), video_id=video['contentId']) - for video in collection['response']['docs'] + for video in collection['assets']['items'] if video.get('contentId')] return self.playlist_result(entries, playlist_id) From 245cbb33bcb7d519c897277e65acdcbc45335233 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 28 Sep 2018 15:13:25 +0100 Subject: [PATCH 225/558] [spike] fix Paramount Network extraction(closes #17677) --- youtube_dl/extractor/spike.py | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/youtube_dl/extractor/spike.py b/youtube_dl/extractor/spike.py index e76522b45..6090e0066 100644 --- a/youtube_dl/extractor/spike.py +++ b/youtube_dl/extractor/spike.py @@ -44,3 +44,10 @@ class ParamountNetworkIE(MTVServicesInfoExtractor): _FEED_URL = 'http://www.paramountnetwork.com/feeds/mrss/' _GEO_COUNTRIES = ['US'] + + def _extract_mgid(self, webpage): + cs = self._parse_json(self._search_regex( + r'window\.__DATA__\s*=\s*({.+})', + webpage, 'data'), None)['children'] + c = next(c for c in cs if c.get('type') == 'VideoPlayer') + return c['props']['media']['video']['config']['uri'] From 85fa80d5f9d867bab706b92d15a6c9ad5b862b47 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 1 Oct 2018 21:13:43 +0700 Subject: [PATCH 226/558] [vimeo] Add another config regex (closes #17690) --- youtube_dl/extractor/vimeo.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 0a9239b62..88f4d9979 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -551,6 +551,7 @@ class VimeoIE(VimeoBaseInfoExtractor): else: config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});'] config_re.append(r'\bvar\s+r\s*=\s*({.+?})\s*;') + config_re.append(r'\bconfig\s*=\s*({.+?})\s*;') config = self._search_regex(config_re, webpage, 'info section', flags=re.DOTALL) config = json.loads(config) From 365343131d752bece96d2279a3e0bcd7e9f0000f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 1 Oct 2018 21:45:24 +0700 Subject: [PATCH 227/558] [pluralsight] Fix subtitles extraction (closes #17726, closes #17728) --- youtube_dl/extractor/pluralsight.py | 34 ++++++++++++++++++----------- 1 file changed, 21 insertions(+), 13 deletions(-) diff --git a/youtube_dl/extractor/pluralsight.py b/youtube_dl/extractor/pluralsight.py index ec67381bb..daf172570 100644 --- a/youtube_dl/extractor/pluralsight.py +++ b/youtube_dl/extractor/pluralsight.py @@ -210,18 +210,26 @@ query viewClip { raise ExtractorError('Unable to log in') - def _get_subtitles(self, author, clip_idx, lang, name, duration, video_id): - captions_post = { - 'a': author, - 'cn': int(clip_idx), - 'lc': lang, - 'm': name, - } - captions = self._download_json( - '%s/player/retrieve-captions' % self._API_BASE, video_id, - 'Downloading captions JSON', 'Unable to download captions JSON', - fatal=False, data=json.dumps(captions_post).encode('utf-8'), - headers={'Content-Type': 'application/json;charset=utf-8'}) + def _get_subtitles(self, author, clip_idx, clip_id, lang, name, duration, video_id): + captions = None + if clip_id: + captions = self._download_json( + '%s/transcript/api/v1/caption/json/%s/%s' + % (self._API_BASE, clip_id, lang), video_id, + 'Downloading captions JSON', 'Unable to download captions JSON', + fatal=False) + if not captions: + captions_post = { + 'a': author, + 'cn': int(clip_idx), + 'lc': lang, + 'm': name, + } + captions = self._download_json( + '%s/player/retrieve-captions' % self._API_BASE, video_id, + 'Downloading captions JSON', 'Unable to download captions JSON', + fatal=False, data=json.dumps(captions_post).encode('utf-8'), + headers={'Content-Type': 'application/json;charset=utf-8'}) if captions: return { lang: [{ @@ -413,7 +421,7 @@ query viewClip { # TODO: other languages? subtitles = self.extract_subtitles( - author, clip_idx, 'en', name, duration, display_id) + author, clip_idx, clip.get('clipId'), 'en', name, duration, display_id) return { 'id': clip_id, From 9795d93316cb63e0e2a73ee840600be7f13e19f5 Mon Sep 17 00:00:00 2001 From: Enes <enessolak99@gmail.com> Date: Mon, 1 Oct 2018 17:48:59 +0300 Subject: [PATCH 228/558] [openload] Add support for oload.cloud (closes #17710) --- youtube_dl/extractor/openload.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index d264fe206..dc01b6346 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -243,7 +243,7 @@ class PhantomJSwrapper(object): class OpenloadIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream|site|xyz|win|download))/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)' + _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream|site|xyz|win|download|cloud))/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)' _TESTS = [{ 'url': 'https://openload.co/f/kUEfGclsU9o', @@ -307,6 +307,9 @@ class OpenloadIE(InfoExtractor): }, { 'url': 'https://oload.download/f/kUEfGclsU9o', 'only_matching': True, + }, { + 'url': 'https://oload.cloud/f/4ZDnBXRWiB8', + 'only_matching': True, }, { # Its title has not got its extension but url has it 'url': 'https://oload.download/f/N4Otkw39VCw/Tomb.Raider.2018.HDRip.XviD.AC3-EVO.avi.mp4', From 3c7da54c92b7560c3ceeb8b58a67d4759ed843d0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 1 Oct 2018 22:05:18 +0700 Subject: [PATCH 229/558] [jamendo] Add support for licensing.jamendo.com (closes #17724) --- youtube_dl/extractor/jamendo.py | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/jamendo.py b/youtube_dl/extractor/jamendo.py index 595d7a5b7..c21827618 100644 --- a/youtube_dl/extractor/jamendo.py +++ b/youtube_dl/extractor/jamendo.py @@ -26,8 +26,15 @@ class JamendoBaseIE(InfoExtractor): class JamendoIE(JamendoBaseIE): - _VALID_URL = r'https?://(?:www\.)?jamendo\.com/track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+)' - _TEST = { + _VALID_URL = r'''(?x) + https?:// + (?: + licensing\.jamendo\.com/[^/]+| + (?:www\.)?jamendo\.com + ) + /track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+) + ''' + _TESTS = [{ 'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i', 'md5': '6e9e82ed6db98678f171c25a8ed09ffd', 'info_dict': { @@ -40,14 +47,19 @@ class JamendoIE(JamendoBaseIE): 'duration': 210, 'thumbnail': r're:^https?://.*\.jpg' } - } + }, { + 'url': 'https://licensing.jamendo.com/en/track/1496667/energetic-rock', + 'only_matching': True, + }] def _real_extract(self, url): mobj = self._VALID_URL_RE.match(url) track_id = mobj.group('id') display_id = mobj.group('display_id') - webpage = self._download_webpage(url, display_id) + webpage = self._download_webpage( + 'https://www.jamendo.com/track/%s/%s' % (track_id, display_id), + display_id) title, artist, track = self._extract_meta(webpage) From 66d106f2705d565675b6a94fb0e7e0bdfe132065 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 1 Oct 2018 23:29:24 +0700 Subject: [PATCH 230/558] [philharmoniedeparis] Fix extraction and add support for pad.philharmoniedeparis.fr (closes #17705) --- youtube_dl/extractor/philharmoniedeparis.py | 118 ++++++++++++-------- 1 file changed, 70 insertions(+), 48 deletions(-) diff --git a/youtube_dl/extractor/philharmoniedeparis.py b/youtube_dl/extractor/philharmoniedeparis.py index f1008ae51..f723a2b3b 100644 --- a/youtube_dl/extractor/philharmoniedeparis.py +++ b/youtube_dl/extractor/philharmoniedeparis.py @@ -2,31 +2,38 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( - float_or_none, - int_or_none, - parse_iso8601, - xpath_text, + try_get, + urljoin, ) class PhilharmonieDeParisIE(InfoExtractor): IE_DESC = 'Philharmonie de Paris' - _VALID_URL = r'https?://live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)(?P<id>\d+)' + _VALID_URL = r'''(?x) + https?:// + (?: + live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)| + pad\.philharmoniedeparis\.fr/doc/CIMU/ + ) + (?P<id>\d+) + ''' _TESTS = [{ + 'url': 'http://pad.philharmoniedeparis.fr/doc/CIMU/1086697/jazz-a-la-villette-knower', + 'md5': 'a0a4b195f544645073631cbec166a2c2', + 'info_dict': { + 'id': '1086697', + 'ext': 'mp4', + 'title': 'Jazz à la Villette : Knower', + }, + }, { 'url': 'http://live.philharmoniedeparis.fr/concert/1032066.html', 'info_dict': { 'id': '1032066', - 'ext': 'flv', - 'title': 'md5:d1f5585d87d041d07ce9434804bc8425', - 'timestamp': 1428179400, - 'upload_date': '20150404', - 'duration': 6592.278, + 'title': 'md5:0a031b81807b3593cffa3c9a87a167a0', }, - 'params': { - # rtmp download - 'skip_download': True, - } + 'playlist_mincount': 2, }, { 'url': 'http://live.philharmoniedeparis.fr/Concert/1030324.html', 'only_matching': True, @@ -34,45 +41,60 @@ class PhilharmonieDeParisIE(InfoExtractor): 'url': 'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=1030324&track=&lang=fr', 'only_matching': True, }] + _LIVE_URL = 'https://live.philharmoniedeparis.fr' def _real_extract(self, url): video_id = self._match_id(url) - concert = self._download_xml( - 'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=%s' % video_id, - video_id).find('./concert') + config = self._download_json( + '%s/otoPlayer/config.ashx' % self._LIVE_URL, video_id, query={ + 'id': video_id, + 'lang': 'fr-FR', + }) - formats = [] - info_dict = { - 'id': video_id, - 'title': xpath_text(concert, './titre', 'title', fatal=True), - 'formats': formats, - } - - fichiers = concert.find('./fichiers') - stream = fichiers.attrib['serveurstream'] - for fichier in fichiers.findall('./fichier'): - info_dict['duration'] = float_or_none(fichier.get('timecodefin')) - for quality, (format_id, suffix) in enumerate([('lq', ''), ('hq', '_hd')]): - format_url = fichier.get('url%s' % suffix) - if not format_url: + def extract_entry(source): + if not isinstance(source, dict): + return + title = source.get('title') + if not title: + return + files = source.get('files') + if not isinstance(files, dict): + return + format_urls = set() + formats = [] + for format_id in ('mobile', 'desktop'): + format_url = try_get( + files, lambda x: x[format_id]['file'], compat_str) + if not format_url or format_url in format_urls: continue - formats.append({ - 'url': stream, - 'play_path': format_url, - 'ext': 'flv', - 'format_id': format_id, - 'width': int_or_none(concert.get('largeur%s' % suffix)), - 'height': int_or_none(concert.get('hauteur%s' % suffix)), - 'quality': quality, - }) - self._sort_formats(formats) + format_urls.add(format_url) + m3u8_url = urljoin(self._LIVE_URL, format_url) + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + if not formats: + return + self._sort_formats(formats) + return { + 'title': title, + 'formats': formats, + } - date, hour = concert.get('date'), concert.get('heure') - if date and hour: - info_dict['timestamp'] = parse_iso8601( - '%s-%s-%sT%s:00' % (date[0:4], date[4:6], date[6:8], hour)) - elif date: - info_dict['upload_date'] = date + thumbnail = urljoin(self._LIVE_URL, config.get('image')) - return info_dict + info = extract_entry(config) + if info: + info.update({ + 'id': video_id, + 'thumbnail': thumbnail, + }) + return info + + entries = [] + for num, chapter in enumerate(config['chapters'], start=1): + entry = extract_entry(chapter) + entry['id'] = '%s-%d' % (video_id, num) + entries.append(entry) + + return self.playlist_result(entries, video_id, config.get('title')) From 05e7c184da85f83b254bc3d138f89b11da802bdb Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 2 Oct 2018 06:07:06 +0100 Subject: [PATCH 231/558] [hotstar] fix extraction in python 2(closes #17696) --- youtube_dl/extractor/hotstar.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/hotstar.py b/youtube_dl/extractor/hotstar.py index 354ac00dc..bf5717f1b 100644 --- a/youtube_dl/extractor/hotstar.py +++ b/youtube_dl/extractor/hotstar.py @@ -11,6 +11,7 @@ from ..utils import ( determine_ext, ExtractorError, int_or_none, + try_get, ) @@ -72,7 +73,11 @@ class HotStarIE(HotStarBaseIE): app_state = self._parse_json(self._search_regex( r'<script>window\.APP_STATE\s*=\s*({.+?})</script>', webpage, 'app state'), video_id) - video_data = list(app_state.values())[0]['initialState']['contentData']['content'] + video_data = {} + for v in app_state.values(): + content = try_get(v, lambda x: x['initialState']['contentData']['content'], dict) + if content and content.get('contentId') == video_id: + video_data = content title = video_data['title'] From d98cb62e552ee74079fda2e4173a40b14faac3fe Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 2 Oct 2018 19:43:06 +0100 Subject: [PATCH 232/558] [crunchyroll] switch to HTTPS for RpcApi(closes #17749) --- youtube_dl/extractor/crunchyroll.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index af786d096..045be0ab5 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -45,7 +45,7 @@ class CrunchyrollBaseIE(InfoExtractor): data['req'] = 'RpcApi' + method data = compat_urllib_parse_urlencode(data).encode('utf-8') return self._download_xml( - 'http://www.crunchyroll.com/xml/', + 'https://www.crunchyroll.com/xml/', video_id, note, fatal=False, data=data, headers={ 'Content-Type': 'application/x-www-form-urlencoded', }) From f60b9803a473da8e324313d01af91e5676792c77 Mon Sep 17 00:00:00 2001 From: Enes <enessolak99@gmail.com> Date: Sat, 29 Sep 2018 13:28:56 +0300 Subject: [PATCH 233/558] [dailymotion] Fix extraction (closes #17699) --- youtube_dl/extractor/dailymotion.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 040f0bd02..842d9a259 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -24,6 +24,7 @@ from ..utils import ( str_to_int, unescapeHTML, urlencode_postdata, + try_get, ) @@ -172,7 +173,12 @@ class DailymotionIE(DailymotionBaseInfoExtractor): webpage, 'player v5', default=None) if player_v5: player = self._parse_json(player_v5, video_id) - metadata = player['metadata'] + metadata = try_get( + player, lambda x: x['metadata'], dict) or self._download_json( + 'http://www.dailymotion.com/player/metadata/video/%s' % video_id, video_id, query={ + 'integration': 'inline', + 'GK_PV5_NEON': '1', + }) if metadata.get('error', {}).get('type') == 'password_protected': password = self._downloader.params.get('videopassword') From 0082f44a08e33712fcd33ceabab15215c962eaac Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 5 Oct 2018 02:02:58 +0700 Subject: [PATCH 234/558] [dailymotion] Improve metadata extraction (closes #17706) --- youtube_dl/extractor/dailymotion.py | 32 ++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 10 deletions(-) diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 842d9a259..1816c559e 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -22,9 +22,11 @@ from ..utils import ( parse_iso8601, sanitized_Request, str_to_int, - unescapeHTML, - urlencode_postdata, try_get, + unescapeHTML, + update_url_query, + url_or_none, + urlencode_postdata, ) @@ -172,15 +174,25 @@ class DailymotionIE(DailymotionBaseInfoExtractor): r'__PLAYER_CONFIG__\s*=\s*({.+?});'], webpage, 'player v5', default=None) if player_v5: - player = self._parse_json(player_v5, video_id) - metadata = try_get( - player, lambda x: x['metadata'], dict) or self._download_json( - 'http://www.dailymotion.com/player/metadata/video/%s' % video_id, video_id, query={ - 'integration': 'inline', - 'GK_PV5_NEON': '1', - }) + player = self._parse_json(player_v5, video_id, fatal=False) or {} + metadata = try_get(player, lambda x: x['metadata'], dict) + if not metadata: + metadata_url = url_or_none(try_get( + player, lambda x: x['context']['metadata_template_url1'])) + if metadata_url: + metadata_url = metadata_url.replace(':videoId', video_id) + else: + metadata_url = update_url_query( + 'https://www.dailymotion.com/player/metadata/video/%s' + % video_id, { + 'embedder': url, + 'integration': 'inline', + 'GK_PV5_NEON': '1', + }) + metadata = self._download_json( + metadata_url, video_id, 'Downloading metadata JSON') - if metadata.get('error', {}).get('type') == 'password_protected': + if try_get(metadata, lambda x: x['error']['type']) == 'password_protected': password = self._downloader.params.get('videopassword') if password: r = int(metadata['id'][1:], 36) From 21c1a00dd7dbb9f7551ca9809a194f6380dee7a5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 5 Oct 2018 02:27:14 +0700 Subject: [PATCH 235/558] [pluralsight] Improve authentication (closes #17762) --- youtube_dl/extractor/pluralsight.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/pluralsight.py b/youtube_dl/extractor/pluralsight.py index daf172570..eafe56897 100644 --- a/youtube_dl/extractor/pluralsight.py +++ b/youtube_dl/extractor/pluralsight.py @@ -4,6 +4,7 @@ import collections import json import os import random +import re from .common import InfoExtractor from ..compat import ( @@ -196,7 +197,10 @@ query viewClip { if error: raise ExtractorError('Unable to login: %s' % error, expected=True) - if all(p not in response for p in ('__INITIAL_STATE__', '"currentUser"')): + if all(not re.search(p, response) for p in ( + r'__INITIAL_STATE__', r'["\']currentUser["\']', + # new layout? + r'>\s*Sign out\s*<')): BLOCKED = 'Your account has been blocked due to suspicious activity' if BLOCKED in response: raise ExtractorError( From 2e7ed29e3429c20e735f3f7dfceb1b13cf757037 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 5 Oct 2018 02:29:52 +0700 Subject: [PATCH 236/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/ChangeLog b/ChangeLog index 241712037..e2757f891 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,19 @@ +version <unreleased> + +Extractors +* [pluralsight] Improve authentication (#17762) +* [dailymotion] Fix extraction (#17699) +* [crunchyroll] Switch to HTTPS for RpcApi (#17749) ++ [philharmoniedeparis] Add support for pad.philharmoniedeparis.fr (#17705) +* [philharmoniedeparis] Fix extraction (#17705) ++ [jamendo] Add support for licensing.jamendo.com (#17724) ++ [openload] Add support for oload.cloud (#17710) +* [pluralsight] Fix subtitles extraction (#17726, #17728) ++ [vimeo] Add another config regular expression (#17690) +* [spike] Fix Paramount Network extraction (#17677) +* [hotstar] Fix extraction (#14694, #14931, #17637) + + version 2018.09.26 Extractors From d96f976b0c36f65894380d3d831b0520d6260c20 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 5 Oct 2018 02:31:30 +0700 Subject: [PATCH 237/558] release 2018.10.05 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 2 +- youtube_dl/version.py | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index ed3e0a157..058eb4321 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.09.26*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.09.26** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.10.05*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.10.05** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.09.26 +[debug] youtube-dl version 2018.10.05 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index e2757f891..86cf489b1 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.10.05 Extractors * [pluralsight] Improve authentication (#17762) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 736ab6da7..f167a6ddc 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -360,7 +360,7 @@ - **HitRecord** - **HornBunny** - **HotNewHipHop** - - **HotStar** + - **hotstar** - **hotstar:playlist** - **Howcast** - **HowStuffWorks** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 6f2cc31df..7d3f25019 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.09.26' +__version__ = '2018.10.05' From c9d891f19a923f53132b49a1f5b97f344d92503c Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 5 Oct 2018 20:11:01 +0100 Subject: [PATCH 238/558] [patreon] fix extraction(closes #14502)(closes #10471) --- youtube_dl/extractor/patreon.py | 160 ++++++++++++++++++-------------- 1 file changed, 88 insertions(+), 72 deletions(-) diff --git a/youtube_dl/extractor/patreon.py b/youtube_dl/extractor/patreon.py index 9eb027679..6f73ed68d 100644 --- a/youtube_dl/extractor/patreon.py +++ b/youtube_dl/extractor/patreon.py @@ -2,52 +2,63 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import js_to_json +from ..utils import ( + clean_html, + determine_ext, + int_or_none, + parse_iso8601, +) class PatreonIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?patreon\.com/creation\?hid=(?P<id>[^&#]+)' - _TESTS = [ - { - 'url': 'http://www.patreon.com/creation?hid=743933', - 'md5': 'e25505eec1053a6e6813b8ed369875cc', - 'info_dict': { - 'id': '743933', - 'ext': 'mp3', - 'title': 'Episode 166: David Smalley of Dogma Debate', - 'uploader': 'Cognitive Dissonance Podcast', - 'thumbnail': 're:^https?://.*$', - }, + _VALID_URL = r'https?://(?:www\.)?patreon\.com/(?:creation\?hid=|posts/(?:[\w-]+-)?)(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://www.patreon.com/creation?hid=743933', + 'md5': 'e25505eec1053a6e6813b8ed369875cc', + 'info_dict': { + 'id': '743933', + 'ext': 'mp3', + 'title': 'Episode 166: David Smalley of Dogma Debate', + 'description': 'md5:713b08b772cd6271b9f3906683cfacdf', + 'uploader': 'Cognitive Dissonance Podcast', + 'thumbnail': 're:^https?://.*$', + 'timestamp': 1406473987, + 'upload_date': '20140727', }, - { - 'url': 'http://www.patreon.com/creation?hid=754133', - 'md5': '3eb09345bf44bf60451b8b0b81759d0a', - 'info_dict': { - 'id': '754133', - 'ext': 'mp3', - 'title': 'CD 167 Extra', - 'uploader': 'Cognitive Dissonance Podcast', - 'thumbnail': 're:^https?://.*$', - }, + }, { + 'url': 'http://www.patreon.com/creation?hid=754133', + 'md5': '3eb09345bf44bf60451b8b0b81759d0a', + 'info_dict': { + 'id': '754133', + 'ext': 'mp3', + 'title': 'CD 167 Extra', + 'uploader': 'Cognitive Dissonance Podcast', + 'thumbnail': 're:^https?://.*$', }, - { - 'url': 'https://www.patreon.com/creation?hid=1682498', - 'info_dict': { - 'id': 'SU4fj_aEMVw', - 'ext': 'mp4', - 'title': 'I\'m on Patreon!', - 'uploader': 'TraciJHines', - 'thumbnail': 're:^https?://.*$', - 'upload_date': '20150211', - 'description': 'md5:c5a706b1f687817a3de09db1eb93acd4', - 'uploader_id': 'TraciJHines', - }, - 'params': { - 'noplaylist': True, - 'skip_download': True, - } + 'skip': 'Patron-only content', + }, { + 'url': 'https://www.patreon.com/creation?hid=1682498', + 'info_dict': { + 'id': 'SU4fj_aEMVw', + 'ext': 'mp4', + 'title': 'I\'m on Patreon!', + 'uploader': 'TraciJHines', + 'thumbnail': 're:^https?://.*$', + 'upload_date': '20150211', + 'description': 'md5:c5a706b1f687817a3de09db1eb93acd4', + 'uploader_id': 'TraciJHines', + }, + 'params': { + 'noplaylist': True, + 'skip_download': True, } - ] + }, { + 'url': 'https://www.patreon.com/posts/episode-166-of-743933', + 'only_matching': True, + }, { + 'url': 'https://www.patreon.com/posts/743933', + 'only_matching': True, + }] # Currently Patreon exposes download URL via hidden CSS, so login is not # needed. Keeping this commented for when this inevitably changes. @@ -78,38 +89,43 @@ class PatreonIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - title = self._og_search_title(webpage).strip() - - attach_fn = self._html_search_regex( - r'<div class="attach"><a target="_blank" href="([^"]+)">', - webpage, 'attachment URL', default=None) - embed = self._html_search_regex( - r'<div[^>]+id="watchCreation"[^>]*>\s*<iframe[^>]+src="([^"]+)"', - webpage, 'embedded URL', default=None) - - if attach_fn is not None: - video_url = 'http://www.patreon.com' + attach_fn - thumbnail = self._og_search_thumbnail(webpage) - uploader = self._html_search_regex( - r'<strong>(.*?)</strong> is creating', webpage, 'uploader') - elif embed is not None: - return self.url_result(embed) - else: - playlist = self._parse_json(self._search_regex( - r'(?s)new\s+jPlayerPlaylist\(\s*\{\s*[^}]*},\s*(\[.*?,?\s*\])', - webpage, 'playlist JSON'), - video_id, transform_source=js_to_json) - data = playlist[0] - video_url = self._proto_relative_url(data['mp3']) - thumbnail = self._proto_relative_url(data.get('cover')) - uploader = data.get('artist') - - return { + post = self._download_json( + 'https://www.patreon.com/api/posts/' + video_id, video_id) + attributes = post['data']['attributes'] + title = attributes['title'].strip() + image = attributes.get('image') or {} + info = { 'id': video_id, - 'url': video_url, - 'ext': 'mp3', 'title': title, - 'uploader': uploader, - 'thumbnail': thumbnail, + 'description': clean_html(attributes.get('content')), + 'thumbnail': image.get('large_url') or image.get('url'), + 'timestamp': parse_iso8601(attributes.get('published_at')), + 'like_count': int_or_none(attributes.get('like_count')), + 'comment_count': int_or_none(attributes.get('comment_count')), } + + for i in post.get('included', []): + i_type = i.get('type') + if i_type == 'attachment': + attachment_attributes = i.get('attributes') or {} + attachment_url = attachment_attributes.get('url') + if attachment_url: + info.update({ + 'url': attachment_url, + 'ext': determine_ext(attachment_attributes.get('name'), 'mp3'), + }) + elif i_type == 'user': + user_attributes = i.get('attributes') + if user_attributes: + info.update({ + 'uploader': user_attributes.get('full_name'), + 'uploader_url': user_attributes.get('url'), + }) + + if not info.get('url'): + info.update({ + '_type': 'url', + 'url': attributes['embed']['url'], + }) + + return info From 19a352854f5143b7cd120e990433d0fd40f617b0 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 5 Oct 2018 22:45:04 +0100 Subject: [PATCH 239/558] [patreon] extract post_file url(#17792) --- youtube_dl/extractor/patreon.py | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/patreon.py b/youtube_dl/extractor/patreon.py index 6f73ed68d..426dd8121 100644 --- a/youtube_dl/extractor/patreon.py +++ b/youtube_dl/extractor/patreon.py @@ -104,16 +104,18 @@ class PatreonIE(InfoExtractor): 'comment_count': int_or_none(attributes.get('comment_count')), } + def add_file(file_data): + file_url = file_data.get('url') + if file_url: + info.update({ + 'url': file_url, + 'ext': determine_ext(file_data.get('name'), 'mp3'), + }) + for i in post.get('included', []): i_type = i.get('type') if i_type == 'attachment': - attachment_attributes = i.get('attributes') or {} - attachment_url = attachment_attributes.get('url') - if attachment_url: - info.update({ - 'url': attachment_url, - 'ext': determine_ext(attachment_attributes.get('name'), 'mp3'), - }) + add_file(i.get('attributes') or {}) elif i_type == 'user': user_attributes = i.get('attributes') if user_attributes: @@ -122,6 +124,9 @@ class PatreonIE(InfoExtractor): 'uploader_url': user_attributes.get('url'), }) + if not info.get('url'): + add_file(attributes.get('post_file') or {}) + if not info.get('url'): info.update({ '_type': 'url', From 5d90a8a5f3fef73bb4ccbecd8c61583522b88d79 Mon Sep 17 00:00:00 2001 From: yonaikerlol <39972049+yonaikerlol@users.noreply.github.com> Date: Sun, 7 Oct 2018 09:05:45 -0400 Subject: [PATCH 240/558] [openload] Add support for oload.cc --- youtube_dl/extractor/openload.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index dc01b6346..c652603a5 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -243,7 +243,7 @@ class PhantomJSwrapper(object): class OpenloadIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream|site|xyz|win|download|cloud))/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)' + _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc))/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)' _TESTS = [{ 'url': 'https://openload.co/f/kUEfGclsU9o', @@ -314,6 +314,9 @@ class OpenloadIE(InfoExtractor): # Its title has not got its extension but url has it 'url': 'https://oload.download/f/N4Otkw39VCw/Tomb.Raider.2018.HDRip.XviD.AC3-EVO.avi.mp4', 'only_matching': True, + }, { + 'url': 'https://oload.cc/embed/5NEAbI2BDSk', + 'only_matching': True, }] _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36' From a94e7c195e261137461b546c6446033b371dfbbe Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 15 Oct 2018 11:51:40 +0100 Subject: [PATCH 241/558] [ted] fix extraction for http and rtmp formats(closes #5941)(closes #17572)(closes #17894) --- youtube_dl/extractor/ted.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index 212ac80ab..f9b6aa48f 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -212,8 +212,6 @@ class TEDIE(InfoExtractor): http_url = None for format_id, resources in resources_.items(): - if not isinstance(resources, dict): - continue if format_id == 'h264': for resource in resources: h264_url = resource.get('file') @@ -242,6 +240,8 @@ class TEDIE(InfoExtractor): 'tbr': int_or_none(resource.get('bitrate')), }) elif format_id == 'hls': + if not isinstance(resources, dict): + continue stream_url = url_or_none(resources.get('stream')) if not stream_url: continue From f0ee386851bb0d53801a27dafbe4e8fee5b43d88 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 15 Oct 2018 16:26:29 +0100 Subject: [PATCH 242/558] [tv3] remove extractor(closes #10461)(closes #15339) --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/tv3.py | 34 ------------------------------ 2 files changed, 35 deletions(-) delete mode 100644 youtube_dl/extractor/tv3.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 464c8d690..17b576df3 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1153,7 +1153,6 @@ from .tv2 import ( TV2ArticleIE, ) from .tv2hu import TV2HuIE -from .tv3 import TV3IE from .tv4 import TV4IE from .tv5mondeplus import TV5MondePlusIE from .tva import TVAIE diff --git a/youtube_dl/extractor/tv3.py b/youtube_dl/extractor/tv3.py deleted file mode 100644 index 3867ec90d..000000000 --- a/youtube_dl/extractor/tv3.py +++ /dev/null @@ -1,34 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor - - -class TV3IE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tv3\.co\.nz/(?P<id>[^/]+)/tabid/\d+/articleID/\d+/MCat/\d+/Default\.aspx' - _TEST = { - 'url': 'http://www.tv3.co.nz/MOTORSPORT-SRS-SsangYong-Hampton-Downs-Round-3/tabid/3692/articleID/121615/MCat/2915/Default.aspx', - 'info_dict': { - 'id': '4659127992001', - 'ext': 'mp4', - 'title': 'CRC Motorsport: SRS SsangYong Hampton Downs Round 3 - S2015 Ep3', - 'description': 'SsangYong Racing Series returns for Round 3 with drivers from New Zealand and Australia taking to the grid at Hampton Downs raceway.', - 'uploader_id': '3812193411001', - 'upload_date': '20151213', - 'timestamp': 1449975272, - }, - 'expected_warnings': [ - 'Failed to download MPD manifest' - ], - 'params': { - # m3u8 download - 'skip_download': True, - }, - } - BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/3812193411001/default_default/index.html?videoId=%s' - - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - brightcove_id = self._search_regex(r'<param\s*name="@videoPlayer"\s*value="(\d+)"', webpage, 'brightcove id') - return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id) From ee5fe42e442f04e1c9a388a46e0b4552be4a56d7 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 15 Oct 2018 17:54:38 +0100 Subject: [PATCH 243/558] [brightcove:legacy] fall back to brightcove:new(#13912) --- youtube_dl/extractor/brightcove.py | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 14f9a14ed..5dbd71e12 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -356,7 +356,9 @@ class BrightcoveLegacyIE(InfoExtractor): def _extract_video_info(self, video_info): video_id = compat_str(video_info['id']) + publisher_id = video_info.get('publisherId') + info = { 'id': video_id, 'title': video_info['displayName'].strip(), @@ -444,8 +446,16 @@ class BrightcoveLegacyIE(InfoExtractor): else: return ad_info - if 'url' not in info and not info.get('formats'): - raise ExtractorError('Unable to extract video url for %s' % video_id) + if not info.get('url') and not info.get('formats'): + uploader_id = info.get('uploader_id') + if uploader_id: + info.update({ + '_type': 'url', + 'url': 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' % (uploader_id, video_id), + 'ie_key': BrightcoveNewIE.ie_key(), + }) + else: + raise ExtractorError('Unable to extract video url for %s' % video_id) return info From 160c2773f63c72686635533bc2553634b22e7e2e Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 15 Oct 2018 18:41:57 +0100 Subject: [PATCH 244/558] [brightcove:legacy] add another fall back to brightcove:new --- youtube_dl/extractor/brightcove.py | 39 ++++++++++++++++++++++++------ 1 file changed, 31 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 5dbd71e12..40c3959fd 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -1,8 +1,10 @@ # coding: utf-8 from __future__ import unicode_literals -import re +import base64 import json +import re +import struct from .common import InfoExtractor from .adobepass import AdobePassIE @@ -310,6 +312,10 @@ class BrightcoveLegacyIE(InfoExtractor): 'Cannot find playerKey= variable. Did you forget quotes in a shell invocation?', expected=True) + def _brightcove_new_url_result(self, publisher_id, video_id): + brightcove_new_url = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' % (publisher_id, video_id) + return self.url_result(brightcove_new_url, BrightcoveNewIE.ie_key(), video_id) + def _get_video_info(self, video_id, query, referer=None): headers = {} linkBase = query.get('linkBaseURL') @@ -323,6 +329,29 @@ class BrightcoveLegacyIE(InfoExtractor): r"<h1>We're sorry.</h1>([\s\n]*<p>.*?</p>)+", webpage, 'error message', default=None) if error_msg is not None: + publisher_id = query.get('publisherId') + if publisher_id and publisher_id[0].isdigit(): + publisher_id = publisher_id[0] + if not publisher_id: + valid_key = lambda key: key and ',' in key + player_key = query.get('playerKey') + if player_key and ',' in player_key[0]: + player_key = player_key[0] + else: + player_id = query.get('playerID') + if player_id and player_id[0].isdigit(): + player_page = self._download_webpage( + 'http://link.brightcove.com/services/player/bcpid' + player_id[0], + video_id, headers=headers, fatal=False) + if player_page: + player_key = self._search_regex( + r'<param\s+name="playerKey"\s+value="([\w~,-]+)"', + player_page, 'player key', fatal=False) + if player_key: + enc_pub_id = player_key.split(',')[1].replace('~', '=') + publisher_id = struct.unpack('>Q', base64.urlsafe_b64decode(enc_pub_id))[0] + if publisher_id: + return self._brightcove_new_url_result(publisher_id, video_id) raise ExtractorError( 'brightcove said: %s' % error_msg, expected=True) @@ -356,9 +385,7 @@ class BrightcoveLegacyIE(InfoExtractor): def _extract_video_info(self, video_info): video_id = compat_str(video_info['id']) - publisher_id = video_info.get('publisherId') - info = { 'id': video_id, 'title': video_info['displayName'].strip(), @@ -449,11 +476,7 @@ class BrightcoveLegacyIE(InfoExtractor): if not info.get('url') and not info.get('formats'): uploader_id = info.get('uploader_id') if uploader_id: - info.update({ - '_type': 'url', - 'url': 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' % (uploader_id, video_id), - 'ie_key': BrightcoveNewIE.ie_key(), - }) + info.update(self._brightcove_new_url_result(uploader_id, video_id)) else: raise ExtractorError('Unable to extract video url for %s' % video_id) return info From 582797d780b6f4857a5b8b6ca8c63915242c0ab9 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 15 Oct 2018 20:47:12 +0100 Subject: [PATCH 245/558] [brightcove] remove unused variable --- youtube_dl/extractor/brightcove.py | 1 - 1 file changed, 1 deletion(-) diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 40c3959fd..465ae396e 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -333,7 +333,6 @@ class BrightcoveLegacyIE(InfoExtractor): if publisher_id and publisher_id[0].isdigit(): publisher_id = publisher_id[0] if not publisher_id: - valid_key = lambda key: key and ',' in key player_key = query.get('playerKey') if player_key and ',' in player_key[0]: player_key = player_key[0] From baeabf77428ad1a6bd5a910e7be07100fcb1eadd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 16 Oct 2018 23:19:44 +0700 Subject: [PATCH 246/558] [rutube] Use geo verification headers (closes #17897) --- youtube_dl/extractor/rutube.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index 261bcbb83..10ac8ed1f 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -103,7 +103,8 @@ class RutubeIE(RutubeBaseIE): options = self._download_json( 'http://rutube.ru/api/play/options/%s/?format=json' % video_id, - video_id, 'Downloading options JSON') + video_id, 'Downloading options JSON', + headers=self.geo_verification_headers()) formats = [] for format_id, format_url in options['video_balancer'].items(): From b99b0bcfa079a15a988cf931a3ce44bb480dfbdb Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 17 Oct 2018 06:22:07 +0100 Subject: [PATCH 247/558] [cwtv] handle api errors(closes #17905) --- youtube_dl/extractor/cwtv.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/cwtv.py b/youtube_dl/extractor/cwtv.py index 224a1fb5d..f9bd535f6 100644 --- a/youtube_dl/extractor/cwtv.py +++ b/youtube_dl/extractor/cwtv.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( + ExtractorError, int_or_none, parse_age_limit, parse_iso8601, @@ -66,9 +67,12 @@ class CWTVIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - video_data = self._download_json( + data = self._download_json( 'http://images.cwtv.com/feed/mobileapp/video-meta/apiversion_8/guid_' + video_id, - video_id)['video'] + video_id) + if data.get('result') != 'ok': + raise ExtractorError(data['msg'], expected=True) + video_data = data['video'] title = video_data['title'] mpx_url = video_data.get('mpx_url') or 'http://link.theplatform.com/s/cwtv/media/guid/2703454149/%s?formats=M3U' % video_id From 7d9e858132cd28b975d2174f5836d3de03f741d1 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 26 Oct 2018 05:40:49 +0100 Subject: [PATCH 248/558] [viewster] reduce format requests --- youtube_dl/extractor/viewster.py | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/youtube_dl/extractor/viewster.py b/youtube_dl/extractor/viewster.py index d5d5b4c69..6e318479c 100644 --- a/youtube_dl/extractor/viewster.py +++ b/youtube_dl/extractor/viewster.py @@ -130,16 +130,16 @@ class ViewsterIE(InfoExtractor): def concat(suffix, sep='-'): return (base_format_id + '%s%s' % (sep, suffix)) if base_format_id else suffix - for media_type in ('application/f4m+xml', 'application/x-mpegURL', 'video/mp4'): - media = self._download_json( - 'https://public-api.viewster.com/movies/%s/video' % entry_id, - video_id, 'Downloading %s JSON' % concat(media_type, ' '), fatal=False, query={ - 'mediaType': media_type, - 'language': audio, - 'subtitle': subtitle, - }) - if not media: - continue + medias = self._download_json( + 'https://public-api.viewster.com/movies/%s/videos' % entry_id, + video_id, fatal=False, query={ + 'mediaTypes': ['application/f4m+xml', 'application/x-mpegURL', 'video/mp4'], + 'language': audio, + 'subtitle': subtitle, + }) + if not medias: + continue + for media in medias: video_url = media.get('Uri') if not video_url: continue From 5e733b066a5fca7fe91ad5800a3e83f0a49c8fbd Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 26 Oct 2018 05:41:57 +0100 Subject: [PATCH 249/558] [dailymail] fix format extraction(closes #17976) --- youtube_dl/extractor/dailymail.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/youtube_dl/extractor/dailymail.py b/youtube_dl/extractor/dailymail.py index af3978035..4f75a2a30 100644 --- a/youtube_dl/extractor/dailymail.py +++ b/youtube_dl/extractor/dailymail.py @@ -49,6 +49,9 @@ class DailyMailIE(InfoExtractor): 'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id) video_sources = self._download_json(sources_url, video_id) + body = video_sources.get('body') + if body: + video_sources = body formats = [] for rendition in video_sources['renditions']: From 08c7d3dadec053ff5535ab2dc91f550ef4788297 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 28 Oct 2018 22:12:54 +0700 Subject: [PATCH 250/558] [crunchyroll] Improve extraction failsafeness (closes #17991) --- youtube_dl/extractor/crunchyroll.py | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 045be0ab5..4a68d092b 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals import re import json +import xml.etree.ElementTree as etree import zlib from hashlib import sha1 @@ -398,7 +399,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'Downloading subtitles for ' + sub_name, data={ 'subtitle_script_id': sub_id, }) - if sub_doc is None: + if not isinstance(sub_doc, etree.Element): continue sid = sub_doc.get('id') iv = xpath_text(sub_doc, 'iv', 'subtitle iv') @@ -515,7 +516,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'video_quality': stream_quality, 'current_page': url, }) - if streamdata is not None: + if isinstance(streamdata, etree.Element): stream_info = streamdata.find('./{default}preload/stream_info') if stream_info is not None: stream_infos.append(stream_info) @@ -526,7 +527,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'video_format': stream_format, 'video_encode_quality': stream_quality, }) - if stream_info is not None: + if isinstance(stream_info, etree.Element): stream_infos.append(stream_info) for stream_info in stream_infos: video_encode_id = xpath_text(stream_info, './video_encode_id') @@ -598,10 +599,22 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text series = self._html_search_regex( r'(?s)<h\d[^>]+\bid=["\']showmedia_about_episode_num[^>]+>(.+?)</h\d', webpage, 'series', fatal=False) - season = xpath_text(metadata, 'series_title') - episode = xpath_text(metadata, 'episode_title') or media_metadata.get('title') - episode_number = int_or_none(xpath_text(metadata, 'episode_number') or media_metadata.get('episode_number')) + season = episode = episode_number = duration = thumbnail = None + + if isinstance(metadata, etree.Element): + season = xpath_text(metadata, 'series_title') + episode = xpath_text(metadata, 'episode_title') + episode_number = int_or_none(xpath_text(metadata, 'episode_number')) + duration = float_or_none(media_metadata.get('duration'), 1000) + thumbnail = xpath_text(metadata, 'episode_image_url') + + if not episode: + episode = media_metadata.get('title') + if not episode_number: + episode_number = int_or_none(media_metadata.get('episode_number')) + if not thumbnail: + thumbnail = media_metadata.get('thumbnail', {}).get('url') season_number = int_or_none(self._search_regex( r'(?s)<h\d[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h\d>\s*<h4>\s*Season (\d+)', @@ -611,8 +624,8 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'id': video_id, 'title': video_title, 'description': video_description, - 'duration': float_or_none(media_metadata.get('duration'), 1000), - 'thumbnail': xpath_text(metadata, 'episode_image_url') or media_metadata.get('thumbnail', {}).get('url'), + 'duration': duration, + 'thumbnail': thumbnail, 'uploader': video_uploader, 'upload_date': video_upload_date, 'series': series, From 022218f2f0dce112c0e2b15923c3a368bdfe4d6a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 28 Oct 2018 22:49:10 +0700 Subject: [PATCH 251/558] [ivi] Add support for ivi.tv --- youtube_dl/extractor/ivi.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index cb51cef2d..86c014b07 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -15,7 +15,7 @@ from ..utils import ( class IviIE(InfoExtractor): IE_DESC = 'ivi.ru' IE_NAME = 'ivi' - _VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?ivi\.(?:ru|tv)/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)' _GEO_BYPASS = False _GEO_COUNTRIES = ['RU'] @@ -65,7 +65,11 @@ class IviIE(InfoExtractor): 'thumbnail': r're:^https?://.*\.jpg$', }, 'skip': 'Only works from Russia', - } + }, + { + 'url': 'https://www.ivi.tv/watch/33560/', + 'only_matching': True, + }, ] # Sorted by quality From c901cc38e50a47c9659db534e637ac4f6a54c450 Mon Sep 17 00:00:00 2001 From: yonaikerlol <lawlietrs7@gmail.com> Date: Sun, 28 Oct 2018 11:51:29 -0400 Subject: [PATCH 252/558] [openload] Add support for oload.icu --- youtube_dl/extractor/openload.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index c652603a5..a91f29f5c 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -243,7 +243,7 @@ class PhantomJSwrapper(object): class OpenloadIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc))/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)' + _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu))/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)' _TESTS = [{ 'url': 'https://openload.co/f/kUEfGclsU9o', @@ -317,6 +317,9 @@ class OpenloadIE(InfoExtractor): }, { 'url': 'https://oload.cc/embed/5NEAbI2BDSk', 'only_matching': True, + }, { + 'url': 'https://oload.icu/f/-_i4y_F_Hs8', + 'only_matching': True }] _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36' From 1fafb329849e3f07e6a6e4141bcd4547e141745c Mon Sep 17 00:00:00 2001 From: sichuan-pepper <huajiao.sichuan.pepper@gmail.com> Date: Sun, 28 Oct 2018 01:46:32 +0900 Subject: [PATCH 253/558] [screencast] Fix extraction (closes #14590) --- youtube_dl/extractor/screencast.py | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/youtube_dl/extractor/screencast.py b/youtube_dl/extractor/screencast.py index 62a6a8337..c6554c905 100644 --- a/youtube_dl/extractor/screencast.py +++ b/youtube_dl/extractor/screencast.py @@ -90,6 +90,14 @@ class ScreencastIE(InfoExtractor): r'src=(.*?)(?:$|&)', video_meta, 'meta tag video URL', default=None) + if video_url is None: + video_url = self._html_search_regex( + r'"MediaContentUrl":"([^"]+)"', webpage, 'media content url', default=None) + + if video_url is None: + video_url = self._html_search_meta( + 'og:video', webpage, default=None) + if video_url is None: raise ExtractorError('Cannot find video') From a1d1c63678dcb075a8e741947c41abfee6c790a0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 28 Oct 2018 23:23:32 +0700 Subject: [PATCH 254/558] [screencast] Improve extraction (closes #14617, closes #17990) --- youtube_dl/extractor/screencast.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/screencast.py b/youtube_dl/extractor/screencast.py index c6554c905..69a0d01f3 100644 --- a/youtube_dl/extractor/screencast.py +++ b/youtube_dl/extractor/screencast.py @@ -92,7 +92,8 @@ class ScreencastIE(InfoExtractor): if video_url is None: video_url = self._html_search_regex( - r'"MediaContentUrl":"([^"]+)"', webpage, 'media content url', default=None) + r'MediaContentUrl["\']\s*:(["\'])(?P<url>(?:(?!\1).)+)\1', + webpage, 'video url', default=None, group='url') if video_url is None: video_url = self._html_search_meta( From 4c237ab78768972e4d61d0b97fe9078d95dc4433 Mon Sep 17 00:00:00 2001 From: Alexey Trofimov <dmzkrsk@gmail.com> Date: Fri, 26 Oct 2018 15:00:55 +0700 Subject: [PATCH 255/558] [sportbox] Fix extraction --- youtube_dl/extractor/sportbox.py | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/sportbox.py b/youtube_dl/extractor/sportbox.py index 54497c880..9413cf27a 100644 --- a/youtube_dl/extractor/sportbox.py +++ b/youtube_dl/extractor/sportbox.py @@ -18,7 +18,7 @@ class SportBoxEmbedIE(InfoExtractor): 'info_dict': { 'id': '211355', 'ext': 'mp4', - 'title': '211355', + 'title': 'В Новороссийске прошел детский турнир «Поле славы боевой»', 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 292, 'view_count': int, @@ -48,9 +48,18 @@ class SportBoxEmbedIE(InfoExtractor): wjplayer_data = self._parse_json( self._search_regex( - r'(?s)wjplayer\(({.+?})\);', webpage, 'wjplayer settings'), + r'(?s)var\s+playerOptions\s*=\s*({.+?});', webpage, 'wjplayer settings'), video_id, transform_source=js_to_json) + wjplayer_data['sources'] = self._parse_json( + self._search_regex( + r'(?s)playerOptions\.sources\s*=\s*(\[.+?\]);', webpage, 'wjplayer sources'), + video_id, transform_source=js_to_json) + + title = self._html_search_meta( + ['og:title', 'twitter:title'], webpage) or self._html_search_regex( + r'<title>(.+?)', webpage, 'title', fatal=False) or video_id + formats = [] for source in wjplayer_data['sources']: src = source.get('src') @@ -71,7 +80,7 @@ class SportBoxEmbedIE(InfoExtractor): return { 'id': video_id, - 'title': video_id, + 'title': title, 'thumbnail': wjplayer_data.get('poster'), 'duration': int_or_none(wjplayer_data.get('duration')), 'view_count': view_count, From bebef109092ba2ad1b08619661aa1b51e65be1bf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 29 Oct 2018 00:19:08 +0700 Subject: [PATCH 256/558] [extractor/common] Add validation for JSON-LD URLs --- youtube_dl/extractor/common.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 2dbf81e6e..8452125c8 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -69,6 +69,7 @@ from ..utils import ( update_url_query, urljoin, url_basename, + url_or_none, xpath_element, xpath_text, xpath_with_ns, @@ -1213,10 +1214,10 @@ class InfoExtractor(object): def extract_video_object(e): assert e['@type'] == 'VideoObject' info.update({ - 'url': e.get('contentUrl'), + 'url': url_or_none(e.get('contentUrl')), 'title': unescapeHTML(e.get('name')), 'description': unescapeHTML(e.get('description')), - 'thumbnail': e.get('thumbnailUrl') or e.get('thumbnailURL'), + 'thumbnail': url_or_none(e.get('thumbnailUrl') or e.get('thumbnailURL')), 'duration': parse_duration(e.get('duration')), 'timestamp': unified_timestamp(e.get('uploadDate')), 'filesize': float_or_none(e.get('contentSize')), From 476cf548e1c6aa83686150db7abf625c6237a67f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 29 Oct 2018 00:20:29 +0700 Subject: [PATCH 257/558] [sportbox] Improve extraction, add support for matchtv.ru and fix video id (closes #17978) --- youtube_dl/extractor/extractors.py | 2 +- youtube_dl/extractor/generic.py | 6 ++-- youtube_dl/extractor/sportbox.py | 55 ++++++++++++++++++------------ 3 files changed, 37 insertions(+), 26 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 17b576df3..f013d13c3 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1043,7 +1043,7 @@ from .spike import ( ) from .stitcher import StitcherIE from .sport5 import Sport5IE -from .sportbox import SportBoxEmbedIE +from .sportbox import SportBoxIE from .sportdeutschland import SportDeutschlandIE from .springboardplatform import SpringboardPlatformIE from .sprout import SproutIE diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 2a48667f0..545e03371 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -47,7 +47,7 @@ from .nbc import NBCSportsVPlayerIE from .ooyala import OoyalaIE from .rutv import RUTVIE from .tvc import TVCIE -from .sportbox import SportBoxEmbedIE +from .sportbox import SportBoxIE from .smotri import SmotriIE from .myvi import MyviIE from .condenast import CondeNastIE @@ -2636,9 +2636,9 @@ class GenericIE(InfoExtractor): return self.url_result(tvc_url, 'TVC') # Look for embedded SportBox player - sportbox_urls = SportBoxEmbedIE._extract_urls(webpage) + sportbox_urls = SportBoxIE._extract_urls(webpage) if sportbox_urls: - return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed') + return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key()) # Look for embedded XHamster player xhamster_urls = XHamsterEmbedIE._extract_urls(webpage) diff --git a/youtube_dl/extractor/sportbox.py b/youtube_dl/extractor/sportbox.py index 9413cf27a..b9017fd2a 100644 --- a/youtube_dl/extractor/sportbox.py +++ b/youtube_dl/extractor/sportbox.py @@ -8,20 +8,24 @@ from ..utils import ( determine_ext, int_or_none, js_to_json, + merge_dicts, ) -class SportBoxEmbedIE(InfoExtractor): - _VALID_URL = r'https?://news\.sportbox\.ru/vdl/player(?:/[^/]+/|\?.*?\bn?id=)(?P\d+)' +class SportBoxIE(InfoExtractor): + _VALID_URL = r'https?://(?:news\.sportbox|matchtv)\.ru/vdl/player(?:/[^/]+/|\?.*?\bn?id=)(?P\d+)' _TESTS = [{ 'url': 'http://news.sportbox.ru/vdl/player/ci/211355', 'info_dict': { - 'id': '211355', + 'id': '109158', 'ext': 'mp4', 'title': 'В Новороссийске прошел детский турнир «Поле славы боевой»', + 'description': 'В Новороссийске прошел детский турнир «Поле славы боевой»', 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 292, 'view_count': int, + 'timestamp': 1426237001, + 'upload_date': '20150313', }, 'params': { # m3u8 download @@ -33,12 +37,18 @@ class SportBoxEmbedIE(InfoExtractor): }, { 'url': 'https://news.sportbox.ru/vdl/player/media/193095', 'only_matching': True, + }, { + 'url': 'https://news.sportbox.ru/vdl/player/media/109158', + 'only_matching': True, + }, { + 'url': 'https://matchtv.ru/vdl/player/media/109158', + 'only_matching': True, }] @staticmethod def _extract_urls(webpage): return re.findall( - r']+src="(https?://news\.sportbox\.ru/vdl/player[^"]+)"', + r']+src="(https?://(?:news\.sportbox|matchtv)\.ru/vdl/player[^"]+)"', webpage) def _real_extract(self, url): @@ -46,22 +56,14 @@ class SportBoxEmbedIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - wjplayer_data = self._parse_json( + sources = self._parse_json( self._search_regex( - r'(?s)var\s+playerOptions\s*=\s*({.+?});', webpage, 'wjplayer settings'), + r'(?s)playerOptions\.sources(?:WithRes)?\s*=\s*(\[.+?\])\s*;\s*\n', + webpage, 'sources'), video_id, transform_source=js_to_json) - wjplayer_data['sources'] = self._parse_json( - self._search_regex( - r'(?s)playerOptions\.sources\s*=\s*(\[.+?\]);', webpage, 'wjplayer sources'), - video_id, transform_source=js_to_json) - - title = self._html_search_meta( - ['og:title', 'twitter:title'], webpage) or self._html_search_regex( - r'(.+?)', webpage, 'title', fatal=False) or video_id - formats = [] - for source in wjplayer_data['sources']: + for source in sources: src = source.get('src') if not src: continue @@ -75,14 +77,23 @@ class SportBoxEmbedIE(InfoExtractor): }) self._sort_formats(formats) + player = self._parse_json( + self._search_regex( + r'(?s)playerOptions\s*=\s*({.+?})\s*;\s*\n', webpage, + 'player options', default='{}'), + video_id, transform_source=js_to_json) + media_id = player['mediaId'] + + info = self._search_json_ld(webpage, media_id, default={}) + view_count = int_or_none(self._search_regex( r'Просмотров\s*:\s*(\d+)', webpage, 'view count', default=None)) - return { - 'id': video_id, - 'title': title, - 'thumbnail': wjplayer_data.get('poster'), - 'duration': int_or_none(wjplayer_data.get('duration')), + return merge_dicts(info, { + 'id': media_id, + 'title': self._og_search_title(webpage, default=None) or media_id, + 'thumbnail': player.get('poster'), + 'duration': int_or_none(player.get('duration')), 'view_count': view_count, 'formats': formats, - } + }) From c2fe21efaaf5be47da9d88bb2a490c688bc920f0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 29 Oct 2018 00:38:06 +0700 Subject: [PATCH 258/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/ChangeLog b/ChangeLog index 86cf489b1..a21177dac 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,27 @@ +version + +Core ++ [extractor/common] Add validation for JSON-LD URLs + +Extractors ++ [sportbox] Add support for matchtv.ru +* [sportbox] Fix extraction (#17978) +* [screencast] Fix extraction (#14590, #14617, #17990) ++ [openload] Add support for oload.icu ++ [ivi] Add support for ivi.tv +* [crunchyroll] Improve extraction failsafeness (#17991) +* [dailymail] Fix formats extraction (#17976) +* [viewster] Reduce format requests +* [cwtv] Handle API errors (#17905) ++ [rutube] Use geo verification headers (#17897) ++ [brightcove:legacy] Add fallbacks to brightcove:new (#13912) +- [tv3] Remove extractor (#10461, #15339) +* [ted] Fix extraction for HTTP and RTMP formats (#5941, #17572, #17894) ++ [openload] Add support for oload.cc (#17823) ++ [patreon] Extract post_file URL (#17792) +* [patreon] Fix extraction (#14502, #10471) + + version 2018.10.05 Extractors From 9ff558f67f2285a17d2a4214b5f74aeb6ce4d9b6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 29 Oct 2018 00:39:29 +0700 Subject: [PATCH 259/558] release 2018.10.29 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 3 +-- youtube_dl/version.py | 2 +- 4 files changed, 6 insertions(+), 7 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 058eb4321..aefed163a 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.10.05*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.10.05** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.10.29*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.10.29** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.10.05 +[debug] youtube-dl version 2018.10.29 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index a21177dac..57dbde12d 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2018.10.29 Core + [extractor/common] Add validation for JSON-LD URLs diff --git a/docs/supportedsites.md b/docs/supportedsites.md index f167a6ddc..e5a6879bc 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -818,7 +818,7 @@ - **Spiegeltv** - **sport.francetvinfo.fr** - **Sport5** - - **SportBoxEmbed** + - **SportBox** - **SportDeutschland** - **SpringboardPlatform** - **Sprout** @@ -909,7 +909,6 @@ - **TV2** - **tv2.hu** - **TV2Article** - - **TV3** - **TV4**: tv4.se and tv4play.se - **TV5MondePlus**: TV5MONDE+ - **TVA** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 7d3f25019..ae9a77966 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.10.05' +__version__ = '2018.10.29' From 9c4a83a1bec9d7abd066a89be40e62dd36ffa67d Mon Sep 17 00:00:00 2001 From: Ali Irani Date: Thu, 6 Sep 2018 02:08:38 +0430 Subject: [PATCH 260/558] [aparat] Fix extraction --- youtube_dl/extractor/aparat.py | 36 +++++++++++++++++----------------- 1 file changed, 18 insertions(+), 18 deletions(-) diff --git a/youtube_dl/extractor/aparat.py b/youtube_dl/extractor/aparat.py index 6eb8bbb6e..780439e17 100644 --- a/youtube_dl/extractor/aparat.py +++ b/youtube_dl/extractor/aparat.py @@ -34,32 +34,32 @@ class AparatIE(InfoExtractor): 'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id, video_id) - title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, 'title') - file_list = self._parse_json( self._search_regex( - r'fileList\s*=\s*JSON\.parse\(\'([^\']+)\'\)', webpage, + r'var options\s*=\s*JSON\.parse\(\'([^\']+)\'\)', webpage, 'file list'), video_id) + title = file_list['plugins']['sabaPlayerPlugin']['title'] + formats = [] - for item in file_list[0]: - file_url = url_or_none(item.get('file')) - if not file_url: - continue - ext = mimetype2ext(item.get('type')) - label = item.get('label') - formats.append({ - 'url': file_url, - 'ext': ext, - 'format_id': label or ext, - 'height': int_or_none(self._search_regex( - r'(\d+)[pP]', label or '', 'height', default=None)), - }) + for list in file_list['plugins']['sabaPlayerPlugin']['multiSRC']: + for item in list: + file_url = url_or_none(item.get('src')) + if not file_url: + continue + ext = mimetype2ext(item.get('type')) + label = item.get('label') + formats.append({ + 'url': file_url, + 'ext': ext, + 'format_id': label or ext, + 'height': int_or_none(self._search_regex( + r'(\d+)[pP]', label or '', 'height', default=None)), + }) self._sort_formats(formats) - thumbnail = self._search_regex( - r'image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False) + thumbnail = file_list['poster'] return { 'id': video_id, From 2943397e8701d3dcd28433e485e50459fdbda62a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 29 Oct 2018 23:29:05 +0700 Subject: [PATCH 261/558] [aparat] Improve extraction and extract more metadata (closes #17445, closes #18008) --- youtube_dl/extractor/aparat.py | 89 ++++++++++++++++++++++------------ 1 file changed, 57 insertions(+), 32 deletions(-) diff --git a/youtube_dl/extractor/aparat.py b/youtube_dl/extractor/aparat.py index 780439e17..883dcee7a 100644 --- a/youtube_dl/extractor/aparat.py +++ b/youtube_dl/extractor/aparat.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( int_or_none, + merge_dicts, mimetype2ext, url_or_none, ) @@ -12,59 +13,83 @@ from ..utils import ( class AparatIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P[a-zA-Z0-9]+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.aparat.com/v/wP8On', 'md5': '131aca2e14fe7c4dcb3c4877ba300c89', 'info_dict': { 'id': 'wP8On', 'ext': 'mp4', 'title': 'تیم گلکسی 11 - زومیت', - 'age_limit': 0, + 'description': 'md5:096bdabcdcc4569f2b8a5e903a3b3028', + 'duration': 231, + 'timestamp': 1387394859, + 'upload_date': '20131218', + 'view_count': int, }, - # 'skip': 'Extremely unreliable', - } + }, { + # multiple formats + 'url': 'https://www.aparat.com/v/8dflw/', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) - # Note: There is an easier-to-parse configuration at - # http://www.aparat.com/video/video/config/videohash/%video_id - # but the URL in there does not work - webpage = self._download_webpage( - 'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id, - video_id) + # Provides more metadata + webpage = self._download_webpage(url, video_id, fatal=False) - file_list = self._parse_json( + if not webpage: + # Note: There is an easier-to-parse configuration at + # http://www.aparat.com/video/video/config/videohash/%video_id + # but the URL in there does not work + webpage = self._download_webpage( + 'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id, + video_id) + + options = self._parse_json( self._search_regex( - r'var options\s*=\s*JSON\.parse\(\'([^\']+)\'\)', webpage, - 'file list'), + r'options\s*=\s*JSON\.parse\(\s*(["\'])(?P(?:(?!\1).)+)\1\s*\)', + webpage, 'options', group='value'), video_id) - title = file_list['plugins']['sabaPlayerPlugin']['title'] + player = options['plugins']['sabaPlayerPlugin'] formats = [] - for list in file_list['plugins']['sabaPlayerPlugin']['multiSRC']: - for item in list: + for sources in player['multiSRC']: + for item in sources: + if not isinstance(item, dict): + continue file_url = url_or_none(item.get('src')) if not file_url: continue - ext = mimetype2ext(item.get('type')) - label = item.get('label') - formats.append({ - 'url': file_url, - 'ext': ext, - 'format_id': label or ext, - 'height': int_or_none(self._search_regex( - r'(\d+)[pP]', label or '', 'height', default=None)), - }) - self._sort_formats(formats) + item_type = item.get('type') + if item_type == 'application/vnd.apple.mpegurl': + formats.extend(self._extract_m3u8_formats( + file_url, video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls', + fatal=False)) + else: + ext = mimetype2ext(item.get('type')) + label = item.get('label') + formats.append({ + 'url': file_url, + 'ext': ext, + 'format_id': 'http-%s' % (label or ext), + 'height': int_or_none(self._search_regex( + r'(\d+)[pP]', label or '', 'height', + default=None)), + }) + self._sort_formats( + formats, field_preference=('height', 'width', 'tbr', 'format_id')) - thumbnail = file_list['poster'] + info = self._search_json_ld(webpage, video_id, default={}) - return { + if not info.get('title'): + info['title'] = player['title'] + + return merge_dicts(info, { 'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - 'age_limit': self._family_friendly_search(webpage), + 'thumbnail': url_or_none(options.get('poster')), + 'duration': int_or_none(player.get('duration')), 'formats': formats, - } + }) From ffa7b2bfee7b94191ffc20ef00c22f708c97cddf Mon Sep 17 00:00:00 2001 From: gfabiano Date: Mon, 30 Jul 2018 18:15:20 +0200 Subject: [PATCH 262/558] [cbnc] Add support for new URL schema (closes #14193) --- youtube_dl/extractor/cnbc.py | 41 +++++++++++++++++++++++++++++- youtube_dl/extractor/extractors.py | 5 +++- 2 files changed, 44 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/cnbc.py b/youtube_dl/extractor/cnbc.py index d354d9f95..35c0b6124 100644 --- a/youtube_dl/extractor/cnbc.py +++ b/youtube_dl/extractor/cnbc.py @@ -1,8 +1,12 @@ # coding: utf-8 from __future__ import unicode_literals + from .common import InfoExtractor -from ..utils import smuggle_url +from ..utils import ( + js_to_json, + smuggle_url, +) class CNBCIE(InfoExtractor): @@ -34,3 +38,38 @@ class CNBCIE(InfoExtractor): {'force_smil_url': True}), 'id': video_id, } + + +class CNBCNewIE(InfoExtractor): + IE_NAME = 'CNBC:new' + _VALID_URL = r'https?://(?:www)?\.cnbc\.com/video.*/(?P[^.]+)' + _TEST = { + 'url': 'https://www.cnbc.com/video/2018/07/19/trump-i-dont-necessarily-agree-with-raising-rates.html', + 'info_dict': { + 'id': '7000031301', + 'ext': 'mp4', + 'title': 'Trump: I don\'t necessarily agree with raising rates', + 'description': 'md5:878d8f0b4ebb5bb1dda3514b91b49de3', + 'timestamp': 1531958400, + 'upload_date': '20180719', + 'uploader': 'NBCU-CNBC', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + } + + CNBC_URL_TEMPLATE = 'http://video.cnbc.com/gallery/?video=%s' + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + video_id = self._parse_json( + self._search_regex( + r'(?s).*]*>.*?({.+?content_id.+?}).*?', + webpage, display_id), + display_id, transform_source=js_to_json + )['content_id'] + + return self.url_result(self.CNBC_URL_TEMPLATE % video_id, 'CNBC') diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index f013d13c3..93574907b 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -209,7 +209,10 @@ from .cloudy import CloudyIE from .clubic import ClubicIE from .clyp import ClypIE from .cmt import CMTIE -from .cnbc import CNBCIE +from .cnbc import ( + CNBCIE, + CNBCNewIE, +) from .cnn import ( CNNIE, CNNBlogsIE, From 94db1f7f3b7269d5843b815ef2aa5b71d0361e6f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 29 Oct 2018 23:53:39 +0700 Subject: [PATCH 263/558] [cnbc] Simplify extraction (closes #14280, closes #17110) --- youtube_dl/extractor/cnbc.py | 29 ++++++++++------------------- youtube_dl/extractor/extractors.py | 2 +- 2 files changed, 11 insertions(+), 20 deletions(-) diff --git a/youtube_dl/extractor/cnbc.py b/youtube_dl/extractor/cnbc.py index 35c0b6124..81b0c9fc4 100644 --- a/youtube_dl/extractor/cnbc.py +++ b/youtube_dl/extractor/cnbc.py @@ -3,10 +3,7 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import ( - js_to_json, - smuggle_url, -) +from ..utils import smuggle_url class CNBCIE(InfoExtractor): @@ -40,36 +37,30 @@ class CNBCIE(InfoExtractor): } -class CNBCNewIE(InfoExtractor): - IE_NAME = 'CNBC:new' - _VALID_URL = r'https?://(?:www)?\.cnbc\.com/video.*/(?P[^.]+)' +class CNBCVideoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www)?\.cnbc\.com/video/(?:[^/]+/)+(?P[^./?#&]+)' _TEST = { 'url': 'https://www.cnbc.com/video/2018/07/19/trump-i-dont-necessarily-agree-with-raising-rates.html', 'info_dict': { 'id': '7000031301', 'ext': 'mp4', - 'title': 'Trump: I don\'t necessarily agree with raising rates', + 'title': "Trump: I don't necessarily agree with raising rates", 'description': 'md5:878d8f0b4ebb5bb1dda3514b91b49de3', 'timestamp': 1531958400, 'upload_date': '20180719', 'uploader': 'NBCU-CNBC', }, 'params': { - # m3u8 download 'skip_download': True, }, } - CNBC_URL_TEMPLATE = 'http://video.cnbc.com/gallery/?video=%s' - def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - video_id = self._parse_json( - self._search_regex( - r'(?s).*]*>.*?({.+?content_id.+?}).*?', - webpage, display_id), - display_id, transform_source=js_to_json - )['content_id'] - - return self.url_result(self.CNBC_URL_TEMPLATE % video_id, 'CNBC') + video_id = self._search_regex( + r'content_id["\']\s*:\s*["\'](\d+)', webpage, display_id, + 'video id') + return self.url_result( + 'http://video.cnbc.com/gallery/?video=%s' % video_id, + CNBCIE.ie_key()) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 93574907b..d96e23905 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -211,7 +211,7 @@ from .clyp import ClypIE from .cmt import CMTIE from .cnbc import ( CNBCIE, - CNBCNewIE, + CNBCVideoIE, ) from .cnn import ( CNNIE, From 9aac22c195cf41ff46a644bd027481629d0e6d06 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 30 Oct 2018 00:22:18 +0700 Subject: [PATCH 264/558] [theplatform] Improve error detection (#13222) --- youtube_dl/extractor/theplatform.py | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index ffef5bf06..181620615 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -39,9 +39,17 @@ class ThePlatformBaseIE(OnceIE): smil_url, video_id, note=note, query={'format': 'SMIL'}, headers=self.geo_verification_headers()) error_element = find_xpath_attr(meta, _x('.//smil:ref'), 'src') - if error_element is not None and error_element.attrib['src'].startswith( - 'http://link.theplatform.%s/s/errorFiles/Unavailable.' % self._TP_TLD): - raise ExtractorError(error_element.attrib['abstract'], expected=True) + if error_element is not None: + exception = find_xpath_attr( + error_element, _x('.//smil:param'), 'name', 'exception') + if exception is not None: + if exception.get('value') == 'GeoLocationBlocked': + self.raise_geo_restricted(error_element.attrib['abstract']) + elif error_element.attrib['src'].startswith( + 'http://link.theplatform.%s/s/errorFiles/Unavailable.' + % self._TP_TLD): + raise ExtractorError( + error_element.attrib['abstract'], expected=True) smil_formats = self._parse_smil_formats( meta, smil_url, video_id, namespace=default_ns, From aa7e974a2a61a20e017b52a3a9ab1fb43cf8cd13 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 29 Oct 2018 19:28:09 +0100 Subject: [PATCH 265/558] [linkedin:learning] Add new extractor(closes #13545) --- youtube_dl/extractor/extractors.py | 4 + youtube_dl/extractor/linkedin.py | 175 +++++++++++++++++++++++++++++ 2 files changed, 179 insertions(+) create mode 100644 youtube_dl/extractor/linkedin.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index d96e23905..8879f5d90 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -572,6 +572,10 @@ from .limelight import ( LimelightChannelListIE, ) from .line import LineTVIE +from .linkedin import ( + LinkedInLearningIE, + LinkedInLearningCourseIE, +) from .litv import LiTVIE from .liveleak import ( LiveLeakIE, diff --git a/youtube_dl/extractor/linkedin.py b/youtube_dl/extractor/linkedin.py new file mode 100644 index 000000000..6333a8fd3 --- /dev/null +++ b/youtube_dl/extractor/linkedin.py @@ -0,0 +1,175 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + float_or_none, + int_or_none, + urlencode_postdata, +) + + +class LinkedInLearningBaseIE(InfoExtractor): + _NETRC_MACHINE = 'linkedin' + + def _call_api(self, course_slug, fields, video_slug=None, resolution=None): + query = { + 'courseSlug': course_slug, + 'fields': fields, + 'q': 'slugs', + } + sub = '' + if video_slug: + query.update({ + 'videoSlug': video_slug, + 'resolution': '_%s' % resolution, + }) + sub = ' %dp' % resolution + api_url = 'https://www.linkedin.com/learning-api/detailedCourses' + return self._download_json( + api_url, video_slug, 'Downloading%s JSON metadata' % sub, headers={ + 'Csrf-Token': self._get_cookies(api_url)['JSESSIONID'].value, + }, query=query)['elements'][0] + + def _get_video_id(self, urn, course_slug, video_slug): + if urn: + mobj = re.search(r'urn:li:lyndaCourse:\d+,(\d+)', urn) + if mobj: + return mobj.group(1) + return '%s/%s' % (course_slug, video_slug) + + def _real_initialize(self): + email, password = self._get_login_info() + if email is None: + return + + login_page = self._download_webpage( + 'https://www.linkedin.com/uas/login?trk=learning', + None, 'Downloading login page') + action_url = self._search_regex( + r']+action=(["\'])(?P.+?)\1', login_page, 'post url', + default='https://www.linkedin.com/uas/login-submit', group='url') + data = self._hidden_inputs(login_page) + data.update({ + 'session_key': email, + 'session_password': password, + }) + login_submit_page = self._download_webpage( + action_url, None, 'Logging in', + data=urlencode_postdata(data)) + error = self._search_regex( + r']+class="error"[^>]*>\s*(.+?)\s*', + login_submit_page, 'error', default=None) + if error: + raise ExtractorError(error, expected=True) + + +class LinkedInLearningIE(LinkedInLearningBaseIE): + IE_NAME = 'linkedin:learning' + _VALID_URL = r'https?://(?:www\.)?linkedin\.com/learning/(?P[^/]+)/(?P[^/?#]+)' + _TEST = { + 'url': 'https://www.linkedin.com/learning/programming-foundations-fundamentals/welcome?autoplay=true', + 'md5': 'a1d74422ff0d5e66a792deb996693167', + 'info_dict': { + 'id': '90426', + 'ext': 'mp4', + 'title': 'Welcome', + 'timestamp': 1430396150.82, + 'upload_date': '20150430', + }, + } + + def _real_extract(self, url): + course_slug, video_slug = re.match(self._VALID_URL, url).groups() + + video_data = None + formats = [] + for width, height in ((640, 360), (960, 540), (1280, 720)): + video_data = self._call_api( + course_slug, 'selectedVideo', video_slug, height)['selectedVideo'] + + video_url_data = video_data.get('url') or {} + progressive_url = video_url_data.get('progressiveUrl') + if progressive_url: + formats.append({ + 'format_id': 'progressive-%dp' % height, + 'url': progressive_url, + 'height': height, + 'width': width, + 'source_preference': 1, + }) + + title = video_data['title'] + + audio_url = video_data.get('audio', {}).get('progressiveUrl') + if audio_url: + formats.append({ + 'abr': 64, + 'ext': 'm4a', + 'format_id': 'audio', + 'url': audio_url, + 'vcodec': 'none', + }) + + streaming_url = video_url_data.get('streamingUrl') + if streaming_url: + formats.extend(self._extract_m3u8_formats( + streaming_url, video_slug, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False)) + + self._sort_formats(formats, ('width', 'height', 'source_preference', 'tbr', 'abr')) + + return { + 'id': self._get_video_id(video_data.get('urn'), course_slug, video_slug), + 'title': title, + 'formats': formats, + 'thumbnail': video_data.get('defaultThumbnail'), + 'timestamp': float_or_none(video_data.get('publishedOn'), 1000), + 'duration': int_or_none(video_data.get('durationInSeconds')), + } + + +class LinkedInLearningCourseIE(LinkedInLearningBaseIE): + IE_NAME = 'linkedin:learning:course' + _VALID_URL = r'https?://(?:www\.)?linkedin\.com/learning/(?P[^/?#]+)' + _TEST = { + 'url': 'https://www.linkedin.com/learning/programming-foundations-fundamentals', + 'info_dict': { + 'id': 'programming-foundations-fundamentals', + 'title': 'Programming Foundations: Fundamentals', + 'description': 'md5:76e580b017694eb89dc8e8923fff5c86', + }, + 'playlist_mincount': 61, + } + + @classmethod + def suitable(cls, url): + return False if LinkedInLearningIE.suitable(url) else super(LinkedInLearningCourseIE, cls).suitable(url) + + def _real_extract(self, url): + course_slug = self._match_id(url) + course_data = self._call_api(course_slug, 'chapters,description,title') + + entries = [] + for chapter in course_data.get('chapters', []): + chapter_title = chapter.get('title') + for video in chapter.get('videos', []): + video_slug = video.get('slug') + if not video_slug: + continue + entries.append({ + '_type': 'url', + 'id': self._get_video_id(video.get('urn'), course_slug, video_slug), + 'title': video.get('title'), + 'url': 'https://www.linkedin.com/learning/%s/%s' % (course_slug, video_slug), + 'chapter': chapter_title, + 'ie_key': LinkedInLearningIE.ie_key(), + }) + + return self.playlist_result( + entries, course_slug, + course_data.get('title'), + course_data.get('description')) From b14475724b78bf3b4f2f448bb2953dfd52d3d425 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 29 Oct 2018 21:49:12 +0100 Subject: [PATCH 266/558] [linkedin:learning:course] use url_transparent type for playlist entries --- youtube_dl/extractor/linkedin.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/linkedin.py b/youtube_dl/extractor/linkedin.py index 6333a8fd3..259fc4c5e 100644 --- a/youtube_dl/extractor/linkedin.py +++ b/youtube_dl/extractor/linkedin.py @@ -161,7 +161,7 @@ class LinkedInLearningCourseIE(LinkedInLearningBaseIE): if not video_slug: continue entries.append({ - '_type': 'url', + '_type': 'url_transparent', 'id': self._get_video_id(video.get('urn'), course_slug, video_slug), 'title': video.get('title'), 'url': 'https://www.linkedin.com/learning/%s/%s' % (course_slug, video_slug), From f16679e8436fb0e9d01aca2343ce22a01802667f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 30 Oct 2018 04:57:28 +0700 Subject: [PATCH 267/558] [cnbc:video] Fix _VALID_URL (#17110) --- youtube_dl/extractor/cnbc.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/cnbc.py b/youtube_dl/extractor/cnbc.py index 81b0c9fc4..6889b0f40 100644 --- a/youtube_dl/extractor/cnbc.py +++ b/youtube_dl/extractor/cnbc.py @@ -38,7 +38,7 @@ class CNBCIE(InfoExtractor): class CNBCVideoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www)?\.cnbc\.com/video/(?:[^/]+/)+(?P[^./?#&]+)' + _VALID_URL = r'https?://(?:www\.)?cnbc\.com/video/(?:[^/]+/)+(?P[^./?#&]+)' _TEST = { 'url': 'https://www.cnbc.com/video/2018/07/19/trump-i-dont-necessarily-agree-with-raising-rates.html', 'info_dict': { From c70ba664f19f0323d74e4e8ea76249f4c97def06 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 1 Nov 2018 01:35:32 +0700 Subject: [PATCH 268/558] [njpwworld] Fix authentication (closes #17427) --- youtube_dl/extractor/njpwworld.py | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/njpwworld.py b/youtube_dl/extractor/njpwworld.py index febef097a..025c5d249 100644 --- a/youtube_dl/extractor/njpwworld.py +++ b/youtube_dl/extractor/njpwworld.py @@ -31,6 +31,8 @@ class NJPWWorldIE(InfoExtractor): 'skip': 'Requires login', } + _LOGIN_URL = 'https://front.njpwworld.com/auth/login' + def _real_initialize(self): self._login() @@ -40,13 +42,17 @@ class NJPWWorldIE(InfoExtractor): if not username: return True + # Setup session (will set necessary cookies) + self._request_webpage( + 'https://njpwworld.com/', None, note='Setting up session') + webpage, urlh = self._download_webpage_handle( - 'https://njpwworld.com/auth/login', None, + self._LOGIN_URL, None, note='Logging in', errnote='Unable to login', data=urlencode_postdata({'login_id': username, 'pw': password}), - headers={'Referer': 'https://njpwworld.com/auth'}) + headers={'Referer': 'https://front.njpwworld.com/auth'}) # /auth/login will return 302 for successful logins - if urlh.geturl() == 'https://njpwworld.com/auth/login': + if urlh.geturl() == self._LOGIN_URL: self.report_warning('unable to login') return False From 061ea3a776830f15dbce899bad8b48232f32aaf0 Mon Sep 17 00:00:00 2001 From: yonaikerlol Date: Fri, 2 Nov 2018 12:08:41 -0400 Subject: [PATCH 269/558] [openload] Add support for oload.fun --- youtube_dl/extractor/openload.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index a91f29f5c..2473536fd 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -243,7 +243,7 @@ class PhantomJSwrapper(object): class OpenloadIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu))/(?:f|embed)/(?P[a-zA-Z0-9-_]+)' + _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun))/(?:f|embed)/(?P[a-zA-Z0-9-_]+)' _TESTS = [{ 'url': 'https://openload.co/f/kUEfGclsU9o', @@ -319,7 +319,10 @@ class OpenloadIE(InfoExtractor): 'only_matching': True, }, { 'url': 'https://oload.icu/f/-_i4y_F_Hs8', - 'only_matching': True + 'only_matching': True, + }, { + 'url': 'https://oload.fun/f/gb6G1H4sHXY', + 'only_matching': True, }] _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36' From c620694c97151396055108cd10d2a393036eb334 Mon Sep 17 00:00:00 2001 From: Sebastian Haas Date: Tue, 30 Oct 2018 23:44:50 +0100 Subject: [PATCH 270/558] [orf:tvthek] Fix extraction (closes #17737) use _extract_m3u8_formats and _extract_f4m_formats helper functions closes #17737 --- youtube_dl/extractor/orf.py | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index c1fb580ca..da8031ad2 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -80,14 +80,16 @@ class ORFTVthekIE(InfoExtractor): if not video_id or not title: continue video_id = compat_str(video_id) - formats = [{ - 'preference': -10 if fd['delivery'] == 'hls' else None, - 'format_id': '%s-%s-%s' % ( - fd['delivery'], fd['quality'], fd['quality_string']), - 'url': fd['src'], - 'protocol': fd['protocol'], - 'quality': quality_to_int(fd['quality']), - } for fd in sd['sources']] + formats = [] + for fd in sd['sources']: + format_id = '%s-%s-%s' % ( + fd['delivery'], fd['quality'], fd['quality_string']) + if determine_ext(fd['src']) == 'm3u8': + formats.extend(self._extract_m3u8_formats( + fd['src'], video_id, 'mp4', m3u8_id=format_id)) + elif determine_ext(fd['src']) == 'f4m': + formats.extend(self._extract_f4m_formats( + fd['src'], video_id, f4m_id=format_id)) # Check for geoblocking. # There is a property is_geoprotection, but that's always false From 4b6aca17cc7d4df22e78501b4c00a9281c189ab3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 2 Nov 2018 23:46:56 +0700 Subject: [PATCH 271/558] [orf:tvthek] Improve extraction and remove unused code (closes #17956, closes #18024) --- youtube_dl/extractor/orf.py | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index da8031ad2..d432e3449 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -15,6 +15,7 @@ from ..utils import ( strip_jsonp, unescapeHTML, unified_strdate, + url_or_none, ) @@ -68,12 +69,6 @@ class ORFTVthekIE(InfoExtractor): webpage, 'playlist', group='json'), playlist_id, transform_source=unescapeHTML)['playlist']['videos'] - def quality_to_int(s): - m = re.search('([0-9]+)', s) - if m is None: - return -1 - return int(m.group(1)) - entries = [] for sd in data_jsb: video_id, title = sd.get('id'), sd.get('title') @@ -82,14 +77,27 @@ class ORFTVthekIE(InfoExtractor): video_id = compat_str(video_id) formats = [] for fd in sd['sources']: - format_id = '%s-%s-%s' % ( - fd['delivery'], fd['quality'], fd['quality_string']) + src = url_or_none(fd.get('src')) + if not src: + continue + format_id_list = [] + for key in ('delivery', 'quality', 'quality_string'): + value = fd.get(key) + if value: + format_id_list.append(value) + format_id = '-'.join(format_id_list) if determine_ext(fd['src']) == 'm3u8': formats.extend(self._extract_m3u8_formats( fd['src'], video_id, 'mp4', m3u8_id=format_id)) elif determine_ext(fd['src']) == 'f4m': formats.extend(self._extract_f4m_formats( fd['src'], video_id, f4m_id=format_id)) + else: + formats.append({ + 'format_id': format_id, + 'url': src, + 'protocol': fd.get('protocol'), + }) # Check for geoblocking. # There is a property is_geoprotection, but that's always false From 036f905161b104ef90e75ad42d472b45eeb102ba Mon Sep 17 00:00:00 2001 From: sichuan-pepper Date: Sat, 27 Oct 2018 03:40:44 +0900 Subject: [PATCH 272/558] [twitcasting] Add extractor --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/twitcasting.py | 44 +++++++++++++++++++++++++++++ 2 files changed, 45 insertions(+) create mode 100644 youtube_dl/extractor/twitcasting.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 8879f5d90..27452d73e 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1196,6 +1196,7 @@ from .tweakers import TweakersIE from .twentyfourvideo import TwentyFourVideoIE from .twentymin import TwentyMinutenIE from .twentythreevideo import TwentyThreeVideoIE +from .twitcasting import TwitcastingIE from .twitch import ( TwitchVideoIE, TwitchChapterIE, diff --git a/youtube_dl/extractor/twitcasting.py b/youtube_dl/extractor/twitcasting.py new file mode 100644 index 000000000..856df5c0b --- /dev/null +++ b/youtube_dl/extractor/twitcasting.py @@ -0,0 +1,44 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + +import re + + +class TwitcastingIE(InfoExtractor): + _VALID_URL = r'https?://(?:(?:www|ssl|en|pt|es|ja|ko)\.)?twitcasting\.tv/(?P[^\/]+)/movie/(?P[0-9]+)' + _TEST = { + 'url': 'https://twitcasting.tv/ivetesangalo/movie/2357609', + 'md5': '745243cad58c4681dc752490f7540d7f', + 'info_dict': { + 'id': '2357609', + 'ext': 'mp4', + 'title': 'Recorded Live #2357609', + 'uploader_id': 'ivetesangalo', + 'description': "Moi! I'm live on TwitCasting from my iPhone.", + 'thumbnail': r're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('video_id') + uploader_id = mobj.group('uploader_id') + + webpage = self._download_webpage(url, video_id) + + playlist_url = self._html_search_regex(r'(["\'])(?Phttp.+?\.m3u8.*?)\1', webpage, name='playlist url', group='url') + formats = self._extract_m3u8_formats(playlist_url, video_id, ext='mp4') + thumbnail = self._og_search_thumbnail(webpage) + title = self._html_search_meta('twitter:title', webpage) + description = self._og_search_description(webpage) or self._html_search_meta('twitter:description', webpage) + return{ + 'id': video_id, + 'url': url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader_id': uploader_id, + 'formats': formats, + } From cf0db4d99785532d767d0ca1cc029c73d16bb045 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 3 Nov 2018 00:27:36 +0700 Subject: [PATCH 273/558] [twitcasting] Improve extraction and fix issues (closes #17981) --- youtube_dl/extractor/extractors.py | 2 +- youtube_dl/extractor/twitcasting.py | 36 +++++++++++++++++++++-------- 2 files changed, 27 insertions(+), 11 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 27452d73e..b41cd65d7 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1196,7 +1196,7 @@ from .tweakers import TweakersIE from .twentyfourvideo import TwentyFourVideoIE from .twentymin import TwentyMinutenIE from .twentythreevideo import TwentyThreeVideoIE -from .twitcasting import TwitcastingIE +from .twitcasting import TwitCastingIE from .twitch import ( TwitchVideoIE, TwitchChapterIE, diff --git a/youtube_dl/extractor/twitcasting.py b/youtube_dl/extractor/twitcasting.py index 856df5c0b..05f8aa9ce 100644 --- a/youtube_dl/extractor/twitcasting.py +++ b/youtube_dl/extractor/twitcasting.py @@ -6,8 +6,8 @@ from .common import InfoExtractor import re -class TwitcastingIE(InfoExtractor): - _VALID_URL = r'https?://(?:(?:www|ssl|en|pt|es|ja|ko)\.)?twitcasting\.tv/(?P[^\/]+)/movie/(?P[0-9]+)' +class TwitCastingIE(InfoExtractor): + _VALID_URL = r'https?://(?:[^/]+\.)?twitcasting\.tv/(?P[^/]+)/movie/(?P\d+)' _TEST = { 'url': 'https://twitcasting.tv/ivetesangalo/movie/2357609', 'md5': '745243cad58c4681dc752490f7540d7f', @@ -18,24 +18,40 @@ class TwitcastingIE(InfoExtractor): 'uploader_id': 'ivetesangalo', 'description': "Moi! I'm live on TwitCasting from my iPhone.", 'thumbnail': r're:^https?://.*\.jpg$', - } + }, + 'params': { + 'skip_download': True, + }, } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('video_id') + video_id = mobj.group('id') uploader_id = mobj.group('uploader_id') webpage = self._download_webpage(url, video_id) - playlist_url = self._html_search_regex(r'(["\'])(?Phttp.+?\.m3u8.*?)\1', webpage, name='playlist url', group='url') - formats = self._extract_m3u8_formats(playlist_url, video_id, ext='mp4') + title = self._html_search_regex( + r'(?s)<[^>]+id=["\']movietitle[^>]+>(.+?)(?:(?!\1).)+)\1', + r'(["\'])(?Phttp.+?\.m3u8.*?)\1'), + webpage, 'm3u8 url', group='url') + + formats = self._extract_m3u8_formats( + m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + thumbnail = self._og_search_thumbnail(webpage) - title = self._html_search_meta('twitter:title', webpage) - description = self._og_search_description(webpage) or self._html_search_meta('twitter:description', webpage) - return{ + description = self._og_search_description( + webpage, default=None) or self._html_search_meta( + 'twitter:description', webpage) + + return { 'id': video_id, - 'url': url, 'title': title, 'description': description, 'thumbnail': thumbnail, From 95e42d7336d01f505d6551a21df52f3ae234e96b Mon Sep 17 00:00:00 2001 From: Xiao Di Guan Date: Sat, 3 Nov 2018 05:18:20 +1100 Subject: [PATCH 274/558] [extractor/common] Ensure response handle is not prematurely closed before it can be read if it matches expected_status (resolves #17195, closes #17846, resolves #17447) --- test/helper.py | 10 ++++++++ test/test_InfoExtractor.py | 42 ++++++++++++++++++++++++++++++++-- test/test_downloader_http.py | 12 +--------- test/test_http.py | 10 +------- youtube_dl/extractor/common.py | 5 ++++ 5 files changed, 57 insertions(+), 22 deletions(-) diff --git a/test/helper.py b/test/helper.py index dfee217a9..aa9a1c9b2 100644 --- a/test/helper.py +++ b/test/helper.py @@ -7,6 +7,7 @@ import json import os.path import re import types +import ssl import sys import youtube_dl.extractor @@ -244,3 +245,12 @@ def expect_warnings(ydl, warnings_re): real_warning(w) ydl.report_warning = _report_warning + + +def http_server_port(httpd): + if os.name == 'java' and isinstance(httpd.socket, ssl.SSLSocket): + # In Jython SSLSocket is not a subclass of socket.socket + sock = httpd.socket.sock + else: + sock = httpd.socket + return sock.getsockname()[1] diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py index 4833396a5..06be72616 100644 --- a/test/test_InfoExtractor.py +++ b/test/test_InfoExtractor.py @@ -9,11 +9,30 @@ import sys import unittest sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -from test.helper import FakeYDL, expect_dict, expect_value -from youtube_dl.compat import compat_etree_fromstring +from test.helper import FakeYDL, expect_dict, expect_value, http_server_port +from youtube_dl.compat import compat_etree_fromstring, compat_http_server from youtube_dl.extractor.common import InfoExtractor from youtube_dl.extractor import YoutubeIE, get_info_extractor from youtube_dl.utils import encode_data_uri, strip_jsonp, ExtractorError, RegexNotFoundError +import threading + + +TEAPOT_RESPONSE_STATUS = 418 +TEAPOT_RESPONSE_BODY = "

418 I'm a teapot

" + + +class InfoExtractorTestRequestHandler(compat_http_server.BaseHTTPRequestHandler): + def log_message(self, format, *args): + pass + + def do_GET(self): + if self.path == '/teapot': + self.send_response(TEAPOT_RESPONSE_STATUS) + self.send_header('Content-Type', 'text/html; charset=utf-8') + self.end_headers() + self.wfile.write(TEAPOT_RESPONSE_BODY.encode()) + else: + assert False class TestIE(InfoExtractor): @@ -743,6 +762,25 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/ for i in range(len(entries)): expect_dict(self, entries[i], expected_entries[i]) + def test_response_with_expected_status_returns_content(self): + # Checks for mitigations against the effects of + # that affect Python 3.4.1+, which + # manifest as `_download_webpage`, `_download_xml`, `_download_json`, + # or the underlying `_download_webpage_handle` returning no content + # when a response matches `expected_status`. + + httpd = compat_http_server.HTTPServer( + ('127.0.0.1', 0), InfoExtractorTestRequestHandler) + port = http_server_port(httpd) + server_thread = threading.Thread(target=httpd.serve_forever) + server_thread.daemon = True + server_thread.start() + + (content, urlh) = self.ie._download_webpage_handle( + 'http://127.0.0.1:%d/teapot' % port, None, + expected_status=TEAPOT_RESPONSE_STATUS) + self.assertEqual(content, TEAPOT_RESPONSE_BODY) + if __name__ == '__main__': unittest.main() diff --git a/test/test_downloader_http.py b/test/test_downloader_http.py index 5cf2bf1a5..750472281 100644 --- a/test/test_downloader_http.py +++ b/test/test_downloader_http.py @@ -9,26 +9,16 @@ import sys import unittest sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -from test.helper import try_rm +from test.helper import http_server_port, try_rm from youtube_dl import YoutubeDL from youtube_dl.compat import compat_http_server from youtube_dl.downloader.http import HttpFD from youtube_dl.utils import encodeFilename -import ssl import threading TEST_DIR = os.path.dirname(os.path.abspath(__file__)) -def http_server_port(httpd): - if os.name == 'java' and isinstance(httpd.socket, ssl.SSLSocket): - # In Jython SSLSocket is not a subclass of socket.socket - sock = httpd.socket.sock - else: - sock = httpd.socket - return sock.getsockname()[1] - - TEST_SIZE = 10 * 1024 diff --git a/test/test_http.py b/test/test_http.py index 409fec9c8..3ee0a5dda 100644 --- a/test/test_http.py +++ b/test/test_http.py @@ -8,6 +8,7 @@ import sys import unittest sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) +from test.helper import http_server_port from youtube_dl import YoutubeDL from youtube_dl.compat import compat_http_server, compat_urllib_request import ssl @@ -16,15 +17,6 @@ import threading TEST_DIR = os.path.dirname(os.path.abspath(__file__)) -def http_server_port(httpd): - if os.name == 'java' and isinstance(httpd.socket, ssl.SSLSocket): - # In Jython SSLSocket is not a subclass of socket.socket - sock = httpd.socket.sock - else: - sock = httpd.socket - return sock.getsockname()[1] - - class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler): def log_message(self, format, *args): pass diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 8452125c8..e5f8136fc 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -606,6 +606,11 @@ class InfoExtractor(object): except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: if isinstance(err, compat_urllib_error.HTTPError): if self.__can_accept_status_code(err, expected_status): + # Retain reference to error to prevent file object from + # being closed before it can be read. Works around the + # effects of + # introduced in Python 3.4.1. + err.fp._error = err return err.fp if errnote is False: From da56fb631fb6389849f2f021bdd047aa1c55dc0a Mon Sep 17 00:00:00 2001 From: Alexander Seiler Date: Tue, 2 Oct 2018 14:49:01 +0200 Subject: [PATCH 275/558] [azmedien] Adopt to major site redesign (closes #17745) --- youtube_dl/extractor/azmedien.py | 222 +++++++---------------------- youtube_dl/extractor/extractors.py | 6 +- 2 files changed, 53 insertions(+), 175 deletions(-) diff --git a/youtube_dl/extractor/azmedien.py b/youtube_dl/extractor/azmedien.py index 68f26e2ca..9d606ee67 100644 --- a/youtube_dl/extractor/azmedien.py +++ b/youtube_dl/extractor/azmedien.py @@ -1,19 +1,16 @@ # coding: utf-8 from __future__ import unicode_literals +import json import re from .common import InfoExtractor from .kaltura import KalturaIE -from ..utils import ( - get_element_by_class, - get_element_by_id, - strip_or_none, - urljoin, -) class AZMedienBaseIE(InfoExtractor): + _PARTNER_ID = '1719221' + def _kaltura_video(self, partner_id, entry_id): return self.url_result( 'kaltura:%s:%s' % (partner_id, entry_id), ie=KalturaIE.ie_key(), @@ -25,189 +22,74 @@ class AZMedienIE(AZMedienBaseIE): _VALID_URL = r'''(?x) https?:// (?:www\.)? - (?: + (?P telezueri\.ch| telebaern\.tv| telem1\.ch )/ - [0-9]+-show-[^/\#]+ - (?: - /[0-9]+-episode-[^/\#]+ - (?: - /[0-9]+-segment-(?:[^/\#]+\#)?| - \# - )| - \# + [^/]+/ + (?P + [^/]+-(?P\d+) ) - (?P[^\#]+) + (?: + \#video= + (?P + [_0-9a-z]+ + ) + )? ''' _TESTS = [{ - # URL with 'segment' - 'url': 'http://www.telezueri.ch/62-show-zuerinews/13772-episode-sonntag-18-dezember-2016/32419-segment-massenabweisungen-beim-hiltl-club-wegen-pelzboom', + 'url': 'https://www.telezueri.ch/sonntalk/bundesrats-vakanzen-eu-rahmenabkommen-133214569', 'info_dict': { - 'id': '1_2444peh4', + 'id': '1_anruz3wy', 'ext': 'mp4', - 'title': 'Massenabweisungen beim Hiltl Club wegen Pelzboom', - 'description': 'md5:9ea9dd1b159ad65b36ddcf7f0d7c76a8', - 'uploader_id': 'TeleZ?ri', - 'upload_date': '20161218', - 'timestamp': 1482084490, + 'title': 'Bundesrats-Vakanzen / EU-Rahmenabkommen', + 'description': 'md5:dd9f96751ec9c35e409a698a328402f3', + 'uploader_id': 'TVOnline', + 'upload_date': '20180930', + 'timestamp': 1538328802, }, 'params': { 'skip_download': True, }, }, { - # URL with 'segment' and fragment: - 'url': 'http://www.telebaern.tv/118-show-news/14240-episode-dienstag-17-januar-2017/33666-segment-achtung-gefahr#zu-wenig-pflegerinnen-und-pfleger', - 'only_matching': True - }, { - # URL with 'episode' and fragment: - 'url': 'http://www.telem1.ch/47-show-sonntalk/13986-episode-soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz#soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz', - 'only_matching': True - }, { - # URL with 'show' and fragment: - 'url': 'http://www.telezueri.ch/66-show-sonntalk#burka-plakate-trump-putin-china-besuch', + 'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1', 'only_matching': True }] def _real_extract(self, url): video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + entry_id = mobj.group('kaltura_id') - webpage = self._download_webpage(url, video_id) + if not entry_id: + webpage = self._download_webpage(url, video_id) + api_path = self._search_regex( + r'["\']apiPath["\']\s*:\s*["\']([^"^\']+)["\']', + webpage, 'api path') + api_url = 'https://www.%s%s' % (mobj.group('host'), api_path) + payload = { + 'query': '''query VideoContext($articleId: ID!) { + article: node(id: $articleId) { + ... on Article { + mainAssetRelation { + asset { + ... on VideoAsset { + kalturaId + } + } + } + } + } + }''', + 'variables': {'articleId': 'Article:%s' % mobj.group('article_id')}, + } + json_data = self._download_json( + api_url, video_id, headers={ + 'Content-Type': 'application/json', + }, + data=json.dumps(payload).encode()) + entry_id = json_data['data']['article']['mainAssetRelation']['asset']['kalturaId'] - partner_id = self._search_regex( - r']+src=["\'](?:https?:)?//(?:[^/]+\.)?kaltura\.com(?:/[^/]+)*/(?:p|partner_id)/([0-9]+)', - webpage, 'kaltura partner id') - entry_id = self._html_search_regex( - r']+data-id=(["\'])(?P(?:(?!\1).)+)\1[^>]+data-slug=["\']%s' - % re.escape(video_id), webpage, 'kaltura entry id', group='id') - - return self._kaltura_video(partner_id, entry_id) - - -class AZMedienPlaylistIE(AZMedienBaseIE): - IE_DESC = 'AZ Medien playlists' - _VALID_URL = r'''(?x) - https?:// - (?:www\.)? - (?: - telezueri\.ch| - telebaern\.tv| - telem1\.ch - )/ - (?P[0-9]+- - (?: - show| - topic| - themen - )-[^/\#]+ - (?: - /[0-9]+-episode-[^/\#]+ - )? - )$ - ''' - - _TESTS = [{ - # URL with 'episode' - 'url': 'http://www.telebaern.tv/118-show-news/13735-episode-donnerstag-15-dezember-2016', - 'info_dict': { - 'id': '118-show-news/13735-episode-donnerstag-15-dezember-2016', - 'title': 'News - Donnerstag, 15. Dezember 2016', - }, - 'playlist_count': 9, - }, { - # URL with 'themen' - 'url': 'http://www.telem1.ch/258-themen-tele-m1-classics', - 'info_dict': { - 'id': '258-themen-tele-m1-classics', - 'title': 'Tele M1 Classics', - }, - 'playlist_mincount': 15, - }, { - # URL with 'topic', contains nested playlists - 'url': 'http://www.telezueri.ch/219-topic-aera-trump-hat-offiziell-begonnen', - 'only_matching': True, - }, { - # URL with 'show' only - 'url': 'http://www.telezueri.ch/86-show-talktaeglich', - 'only_matching': True - }] - - def _real_extract(self, url): - show_id = self._match_id(url) - webpage = self._download_webpage(url, show_id) - - entries = [] - - partner_id = self._search_regex( - r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)', - webpage, 'kaltura partner id', default=None) - - if partner_id: - entries = [ - self._kaltura_video(partner_id, m.group('id')) - for m in re.finditer( - r'data-id=(["\'])(?P(?:(?!\1).)+)\1', webpage)] - - if not entries: - entries = [ - self.url_result(m.group('url'), ie=AZMedienIE.ie_key()) - for m in re.finditer( - r']+data-real=(["\'])(?Phttp.+?)\1', webpage)] - - if not entries: - entries = [ - # May contain nested playlists (e.g. [1]) thus no explicit - # ie_key - # 1. http://www.telezueri.ch/219-topic-aera-trump-hat-offiziell-begonnen) - self.url_result(urljoin(url, m.group('url'))) - for m in re.finditer( - r']+name=[^>]+href=(["\'])(?P/.+?)\1', webpage)] - - title = self._search_regex( - r'episodeShareTitle\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', - webpage, 'title', - default=strip_or_none(get_element_by_id( - 'video-title', webpage)), group='title') - - return self.playlist_result(entries, show_id, title) - - -class AZMedienShowPlaylistIE(AZMedienBaseIE): - IE_DESC = 'AZ Medien show playlists' - _VALID_URL = r'''(?x) - https?:// - (?:www\.)? - (?: - telezueri\.ch| - telebaern\.tv| - telem1\.ch - )/ - (?: - all-episodes| - alle-episoden - )/ - (?P<id>[^/?#&]+) - ''' - - _TEST = { - 'url': 'http://www.telezueri.ch/all-episodes/astrotalk', - 'info_dict': { - 'id': 'astrotalk', - 'title': 'TeleZüri: AstroTalk - alle episoden', - 'description': 'md5:4c0f7e7d741d906004266e295ceb4a26', - }, - 'playlist_mincount': 13, - } - - def _real_extract(self, url): - playlist_id = self._match_id(url) - webpage = self._download_webpage(url, playlist_id) - episodes = get_element_by_class('search-mobile-box', webpage) - entries = [self.url_result( - urljoin(url, m.group('url'))) for m in re.finditer( - r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1', episodes)] - title = self._og_search_title(webpage, fatal=False) - description = self._og_search_description(webpage) - return self.playlist_result(entries, playlist_id, title, description) + return self._kaltura_video(self._PARTNER_ID, entry_id) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index b41cd65d7..9b68c9efe 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -88,11 +88,7 @@ from .awaan import ( AWAANLiveIE, AWAANSeasonIE, ) -from .azmedien import ( - AZMedienIE, - AZMedienPlaylistIE, - AZMedienShowPlaylistIE, -) +from .azmedien import AZMedienIE from .baidu import BaiduVideoIE from .bambuser import BambuserIE, BambuserChannelIE from .bandcamp import BandcampIE, BandcampAlbumIE, BandcampWeeklyIE From 573531dcfb6869afa143761faf4ebc6ab405f808 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 3 Nov 2018 01:32:29 +0700 Subject: [PATCH 276/558] [azmedien] Simplify (closes #17746) --- youtube_dl/extractor/azmedien.py | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) diff --git a/youtube_dl/extractor/azmedien.py b/youtube_dl/extractor/azmedien.py index 9d606ee67..a57a5f114 100644 --- a/youtube_dl/extractor/azmedien.py +++ b/youtube_dl/extractor/azmedien.py @@ -8,16 +8,7 @@ from .common import InfoExtractor from .kaltura import KalturaIE -class AZMedienBaseIE(InfoExtractor): - _PARTNER_ID = '1719221' - - def _kaltura_video(self, partner_id, entry_id): - return self.url_result( - 'kaltura:%s:%s' % (partner_id, entry_id), ie=KalturaIE.ie_key(), - video_id=entry_id) - - -class AZMedienIE(AZMedienBaseIE): +class AZMedienIE(InfoExtractor): IE_DESC = 'AZ Medien videos' _VALID_URL = r'''(?x) https?:// @@ -58,9 +49,11 @@ class AZMedienIE(AZMedienBaseIE): 'only_matching': True }] + _PARTNER_ID = '1719221' + def _real_extract(self, url): - video_id = self._match_id(url) mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') entry_id = mobj.group('kaltura_id') if not entry_id: @@ -92,4 +85,6 @@ class AZMedienIE(AZMedienBaseIE): data=json.dumps(payload).encode()) entry_id = json_data['data']['article']['mainAssetRelation']['asset']['kalturaId'] - return self._kaltura_video(self._PARTNER_ID, entry_id) + return self.url_result( + 'kaltura:%s:%s' % (self._PARTNER_ID, entry_id), + ie=KalturaIE.ie_key(), video_id=entry_id) From faac1c1f70425ddd60ff39d3b6a2b34c7941463b Mon Sep 17 00:00:00 2001 From: Alexander Seiler <seileralex@gmail.com> Date: Tue, 1 May 2018 05:36:03 +0200 Subject: [PATCH 277/558] [ehftv] Add extractor (closes #15408) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/laola1tv.py | 115 ++++++++++++++++++----------- 2 files changed, 73 insertions(+), 43 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 9b68c9efe..e5488cce4 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -539,6 +539,7 @@ from .la7 import LA7IE from .laola1tv import ( Laola1TvEmbedIE, Laola1TvIE, + EHFTVIE, ITTFIE, ) from .lci import LCIIE diff --git a/youtube_dl/extractor/laola1tv.py b/youtube_dl/extractor/laola1tv.py index c7f813370..d985bd3ca 100644 --- a/youtube_dl/extractor/laola1tv.py +++ b/youtube_dl/extractor/laola1tv.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals import json +import re from .common import InfoExtractor from ..utils import ( @@ -119,9 +120,59 @@ class Laola1TvEmbedIE(InfoExtractor): } -class Laola1TvIE(Laola1TvEmbedIE): +class Laola1TvBaseIE(Laola1TvEmbedIE): + def _extract_video(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + if 'Dieser Livestream ist bereits beendet.' in webpage: + raise ExtractorError('This live stream has already finished.', expected=True) + + conf = self._parse_json(self._search_regex( + r'(?s)conf\s*=\s*({.+?});', webpage, 'conf'), + display_id, + transform_source=lambda s: js_to_json(re.sub(r'shareurl:.+,', '', s))) + video_id = conf['videoid'] + + config = self._download_json(conf['configUrl'], video_id, query={ + 'videoid': video_id, + 'partnerid': conf['partnerid'], + 'language': conf.get('language', ''), + 'portal': conf.get('portalid', ''), + }) + error = config.get('error') + if error: + raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True) + + video_data = config['video'] + title = video_data['title'] + is_live = video_data.get('isLivestream') and video_data.get('isLive') + meta = video_data.get('metaInformation') + sports = meta.get('sports') + categories = sports.split(',') if sports else [] + + token_url = self._extract_token_url( + video_data['streamAccess'], video_id, + video_data['abo']['required']) + + formats = self._extract_formats(token_url, video_id) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': self._live_title(title) if is_live else title, + 'description': video_data.get('description'), + 'thumbnail': video_data.get('image'), + 'categories': categories, + 'formats': formats, + 'is_live': is_live, + } + + +class Laola1TvIE(Laola1TvBaseIE): IE_NAME = 'laola1tv' _VALID_URL = r'https?://(?:www\.)?laola1\.tv/[a-z]+-[a-z]+/[^/]+/(?P<id>[^/?#&]+)' + _TESTS = [{ 'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html', 'info_dict': { @@ -169,52 +220,30 @@ class Laola1TvIE(Laola1TvEmbedIE): }] def _real_extract(self, url): - display_id = self._match_id(url) + return self._extract_video(url) - webpage = self._download_webpage(url, display_id) - if 'Dieser Livestream ist bereits beendet.' in webpage: - raise ExtractorError('This live stream has already finished.', expected=True) +class EHFTVIE(Laola1TvBaseIE): + IE_NAME = 'ehftv' + _VALID_URL = r'https?://(?:www\.)?ehftv\.com/[a-z]+(-[a-z]+)?/[^/]+/(?P<id>[^/?#&]+)' - conf = self._parse_json(self._search_regex( - r'(?s)conf\s*=\s*({.+?});', webpage, 'conf'), - display_id, js_to_json) + _TESTS = [{ + 'url': 'https://www.ehftv.com/int/video/paris-saint-germain-handball-pge-vive-kielce/1166761', + 'info_dict': { + 'id': '1166761', + 'display_id': 'paris-saint-germain-handball-pge-vive-kielce', + 'ext': 'mp4', + 'title': 'Paris Saint-Germain Handball - PGE Vive Kielce', + 'is_live': False, + 'categories': ['Handball'], + }, + 'params': { + 'skip_download': True, + }, + }] - video_id = conf['videoid'] - - config = self._download_json(conf['configUrl'], video_id, query={ - 'videoid': video_id, - 'partnerid': conf['partnerid'], - 'language': conf.get('language', ''), - 'portal': conf.get('portalid', ''), - }) - error = config.get('error') - if error: - raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True) - - video_data = config['video'] - title = video_data['title'] - is_live = video_data.get('isLivestream') and video_data.get('isLive') - meta = video_data.get('metaInformation') - sports = meta.get('sports') - categories = sports.split(',') if sports else [] - - token_url = self._extract_token_url( - video_data['streamAccess'], video_id, - video_data['abo']['required']) - - formats = self._extract_formats(token_url, video_id) - - return { - 'id': video_id, - 'display_id': display_id, - 'title': self._live_title(title) if is_live else title, - 'description': video_data.get('description'), - 'thumbnail': video_data.get('image'), - 'categories': categories, - 'formats': formats, - 'is_live': is_live, - } + def _real_extract(self, url): + return self._extract_video(url) class ITTFIE(InfoExtractor): From 6895ea4d3f9d44048fa59800a06ab8177a24bd1d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 3 Nov 2018 02:44:35 +0700 Subject: [PATCH 278/558] [laola1tv:embed] Set correct stream access URL scheme (closes #16341) --- youtube_dl/extractor/laola1tv.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/laola1tv.py b/youtube_dl/extractor/laola1tv.py index d985bd3ca..fa217365a 100644 --- a/youtube_dl/extractor/laola1tv.py +++ b/youtube_dl/extractor/laola1tv.py @@ -33,7 +33,8 @@ class Laola1TvEmbedIE(InfoExtractor): def _extract_token_url(self, stream_access_url, video_id, data): return self._download_json( - stream_access_url, video_id, headers={ + self._proto_relative_url(stream_access_url, 'https:'), video_id, + headers={ 'Content-Type': 'application/json', }, data=json.dumps(data).encode())['data']['stream-access'][0] @@ -225,7 +226,7 @@ class Laola1TvIE(Laola1TvBaseIE): class EHFTVIE(Laola1TvBaseIE): IE_NAME = 'ehftv' - _VALID_URL = r'https?://(?:www\.)?ehftv\.com/[a-z]+(-[a-z]+)?/[^/]+/(?P<id>[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?ehftv\.com/[a-z]+(?:-[a-z]+)?/[^/]+/(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'https://www.ehftv.com/int/video/paris-saint-germain-handball-pge-vive-kielce/1166761', From a085410936a5e0c90a8eb3059a5cd9e0703848bc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 3 Nov 2018 02:56:14 +0700 Subject: [PATCH 279/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/ChangeLog b/ChangeLog index 57dbde12d..05857596a 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,25 @@ +version <unreleased> + +Core +* [extractor/common] Ensure response handle is not prematurely closed before + it can be read if it matches expected_status (#17195, #17846, #17447) + +Extractors +* [laola1tv:embed] Set correct stream access URL scheme (#16341) ++ [ehftv] Add support for ehftv.com (#15408) +* [azmedien] Adopt to major site redesign (#17745, #17746) ++ [twitcasting] Add support for twitcasting.tv (#17981) +* [orf:tvthek] Fix extraction (#17737, #17956, #18024) ++ [openload] Add support for oload.fun (#18045) +* [njpwworld] Fix authentication (#17427) ++ [linkedin:learning] Add support for linkedin.com/learning (#13545) +* [theplatform] Improve error detection (#13222) +* [cnbc] Simplify extraction (#14280, #17110) ++ [cbnc] Add support for new URL schema (#14193) +* [aparat] Improve extraction and extract more metadata (#17445, #18008) +* [aparat] Fix extraction + + version 2018.10.29 Core From 38c32dbf19d0168295d02b0afaed9227fed46338 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 3 Nov 2018 02:57:48 +0700 Subject: [PATCH 280/558] release 2018.11.03 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 7 +++++-- youtube_dl/version.py | 2 +- 4 files changed, 10 insertions(+), 7 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index aefed163a..eb8cef8ef 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.10.29*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.10.29** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.11.03*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.11.03** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.10.29 +[debug] youtube-dl version 2018.11.03 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 05857596a..11e1ba333 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.11.03 Core * [extractor/common] Ensure response handle is not prematurely closed before diff --git a/docs/supportedsites.md b/docs/supportedsites.md index e5a6879bc..24c3254c3 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -84,8 +84,6 @@ - **awaan:season** - **awaan:video** - **AZMedien**: AZ Medien videos - - **AZMedienPlaylist**: AZ Medien playlists - - **AZMedienShowPlaylist**: AZ Medien show playlists - **BaiduVideo**: 百度视频 - **bambuser** - **bambuser:channel** @@ -178,6 +176,7 @@ - **Clyp** - **cmt.com** - **CNBC** + - **CNBCVideo** - **CNN** - **CNNArticle** - **CNNBlogs** @@ -251,6 +250,7 @@ - **EchoMsk** - **egghead:course**: egghead.io course - **egghead:lesson**: egghead.io lesson + - **ehftv** - **eHow** - **EinsUndEinsTV** - **Einthusan** @@ -445,6 +445,8 @@ - **limelight:channel** - **limelight:channel_list** - **LineTV** + - **linkedin:learning** + - **linkedin:learning:course** - **LiTV** - **LiveLeak** - **LiveLeakEmbed** @@ -930,6 +932,7 @@ - **TVPlayer** - **TVPlayHome** - **Tweakers** + - **TwitCasting** - **twitch:chapter** - **twitch:clips** - **twitch:profile** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index ae9a77966..90de01214 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.10.29' +__version__ = '2018.11.03' From dbdaaa231add0a8d1fa8138c448ccb344f585894 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 3 Nov 2018 06:26:16 +0700 Subject: [PATCH 281/558] [youtube] Add fallback metadata extraction from videoDetails (closes #18052) --- youtube_dl/extractor/youtube.py | 34 ++++++++++++++++++++++++++++++++- 1 file changed, 33 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 78203ef84..abadfa545 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -41,6 +41,7 @@ from ..utils import ( remove_quotes, remove_start, smuggle_url, + str_or_none, str_to_int, try_get, unescapeHTML, @@ -501,6 +502,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'categories': ['Science & Technology'], 'tags': ['youtube-dl'], 'duration': 10, + 'view_count': int, 'like_count': int, 'dislike_count': int, 'start_time': 1, @@ -583,6 +585,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'categories': ['Science & Technology'], 'tags': ['youtube-dl'], 'duration': 10, + 'view_count': int, 'like_count': int, 'dislike_count': int, }, @@ -1538,6 +1541,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def extract_view_count(v_info): return int_or_none(try_get(v_info, lambda x: x['view_count'][0])) + player_response = {} + # Get video info embed_webpage = None if re.search(r'player-age-gate-content">', video_webpage) is not None: @@ -1580,6 +1585,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if args.get('livestream') == '1' or args.get('live_playback') == 1: is_live = True sts = ytplayer_config.get('sts') + if not player_response: + pl_response = str_or_none(args.get('player_response')) + if pl_response: + pl_response = self._parse_json(pl_response, video_id, fatal=False) + if isinstance(pl_response, dict): + player_response = pl_response if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): # We also try looking in get_video_info since it may contain different dashmpd # URL that points to a DASH manifest with possibly different itag set (some itags @@ -1608,6 +1619,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if not video_info_webpage: continue get_video_info = compat_parse_qs(video_info_webpage) + if not player_response: + pl_response = get_video_info.get('player_response', [None])[0] + if isinstance(pl_response, dict): + player_response = pl_response add_dash_mpd(get_video_info) if view_count is None: view_count = extract_view_count(get_video_info) @@ -1653,9 +1668,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor): '"token" parameter not in video info for unknown reason', video_id=video_id) + video_details = try_get( + player_response, lambda x: x['videoDetails'], dict) or {} + # title if 'title' in video_info: video_title = video_info['title'][0] + elif 'title' in player_response: + video_title = video_details['title'] else: self._downloader.report_warning('Unable to extract video title') video_title = '_' @@ -1718,6 +1738,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if view_count is None: view_count = extract_view_count(video_info) + if view_count is None and video_details: + view_count = int_or_none(video_details.get('viewCount')) # Check for "rental" videos if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: @@ -1898,7 +1920,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info') # uploader - video_uploader = try_get(video_info, lambda x: x['author'][0], compat_str) + video_uploader = try_get( + video_info, lambda x: x['author'][0], + compat_str) or str_or_none(video_details.get('author')) if video_uploader: video_uploader = compat_urllib_parse_unquote_plus(video_uploader) else: @@ -2011,12 +2035,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor): like_count = _extract_count('like') dislike_count = _extract_count('dislike') + if view_count is None: + view_count = str_to_int(self._search_regex( + r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage, + 'view count', default=None)) + # subtitles video_subtitles = self.extract_subtitles(video_id, video_webpage) automatic_captions = self.extract_automatic_captions(video_id, video_webpage) video_duration = try_get( video_info, lambda x: int_or_none(x['length_seconds'][0])) + if not video_duration: + video_duration = int_or_none(video_details.get('lengthSeconds')) if not video_duration: video_duration = parse_duration(self._html_search_meta( 'duration', video_webpage, 'video duration')) @@ -2244,6 +2275,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'description': 'md5:507cdcb5a49ac0da37a920ece610be80', 'categories': ['People & Blogs'], 'tags': list, + 'view_count': int, 'like_count': int, 'dislike_count': int, }, From 22e07ce502275fbede32d212eacdaeabee22fe4c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 5 Nov 2018 00:11:36 +0700 Subject: [PATCH 282/558] [README.md] Improve documentation on safe metadata extraction and add more examples --- README.md | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index fdd115c9b..35c3de512 100644 --- a/README.md +++ b/README.md @@ -1168,7 +1168,28 @@ title = self._search_regex( ### Use safe conversion functions -Wrap all extracted numeric data into safe functions from `utils`: `int_or_none`, `float_or_none`. Use them for string to number conversions as well. +Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well. + +Use `url_or_none` for safe URL processing. + +Use `try_get` for safe metadata extraction from parsed JSON. + +Explore [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions. + +#### More examples + +##### Safely extract optional description from parsed JSON +```python +description = try_get(response, lambda x: x['result']['video'][0]['summary'], compat_str) +``` + +##### Safely extract more optional metadata +```python +video = try_get(response, lambda x: x['result']['video'][0], dict) or {} +description = video.get('summary') +duration = float_or_none(video.get('durationMs'), scale=1000) +view_count = int_or_none(video.get('views')) +``` # EMBEDDING YOUTUBE-DL From 16d896b2a74e2b9989fc0483728f8009876fc4cf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 5 Nov 2018 15:52:46 +0700 Subject: [PATCH 283/558] [zattoo] Arrange API hosts for derived extractors (closes #18035) --- youtube_dl/extractor/zattoo.py | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/zattoo.py b/youtube_dl/extractor/zattoo.py index bbe0aecb6..cb1bac3a3 100644 --- a/youtube_dl/extractor/zattoo.py +++ b/youtube_dl/extractor/zattoo.py @@ -22,7 +22,7 @@ class ZattooPlatformBaseIE(InfoExtractor): _power_guide_hash = None def _host_url(self): - return 'https://%s' % self._HOST + return 'https://%s' % (self._API_HOST if hasattr(self, '_API_HOST') else self._HOST) def _login(self): username, password = self._get_login_info() @@ -286,6 +286,7 @@ class ZattooLiveIE(ZattooBaseIE): class NetPlusIE(ZattooIE): _NETRC_MACHINE = 'netplus' _HOST = 'netplus.tv' + _API_HOST = 'www.%s' % _HOST _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ @@ -300,7 +301,7 @@ class MNetTVIE(ZattooIE): _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ - 'url': 'https://www.tvplus.m-net.de/watch/abc/123-abc', + 'url': 'https://tvplus.m-net.de/watch/abc/123-abc', 'only_matching': True, }] @@ -311,7 +312,7 @@ class WalyTVIE(ZattooIE): _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ - 'url': 'https://www.player.waly.tv/watch/abc/123-abc', + 'url': 'https://player.waly.tv/watch/abc/123-abc', 'only_matching': True, }] @@ -319,6 +320,7 @@ class WalyTVIE(ZattooIE): class BBVTVIE(ZattooIE): _NETRC_MACHINE = 'bbvtv' _HOST = 'bbv-tv.net' + _API_HOST = 'www.%s' % _HOST _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ @@ -330,6 +332,7 @@ class BBVTVIE(ZattooIE): class VTXTVIE(ZattooIE): _NETRC_MACHINE = 'vtxtv' _HOST = 'vtxtv.ch' + _API_HOST = 'www.%s' % _HOST _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ @@ -341,6 +344,7 @@ class VTXTVIE(ZattooIE): class MyVisionTVIE(ZattooIE): _NETRC_MACHINE = 'myvisiontv' _HOST = 'myvisiontv.ch' + _API_HOST = 'www.%s' % _HOST _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ @@ -355,7 +359,7 @@ class GlattvisionTVIE(ZattooIE): _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ - 'url': 'https://www.iptv.glattvision.ch/watch/abc/123-abc', + 'url': 'https://iptv.glattvision.ch/watch/abc/123-abc', 'only_matching': True, }] @@ -363,6 +367,7 @@ class GlattvisionTVIE(ZattooIE): class SAKTVIE(ZattooIE): _NETRC_MACHINE = 'saktv' _HOST = 'saktv.ch' + _API_HOST = 'www.%s' % _HOST _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ @@ -377,7 +382,7 @@ class EWETVIE(ZattooIE): _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ - 'url': 'https://www.tvonline.ewe.de/watch/abc/123-abc', + 'url': 'https://tvonline.ewe.de/watch/abc/123-abc', 'only_matching': True, }] @@ -385,6 +390,7 @@ class EWETVIE(ZattooIE): class QuantumTVIE(ZattooIE): _NETRC_MACHINE = 'quantumtv' _HOST = 'quantum-tv.com' + _API_HOST = 'www.%s' % _HOST _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ @@ -399,7 +405,7 @@ class OsnatelTVIE(ZattooIE): _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ - 'url': 'https://www.onlinetv.osnatel.de/watch/abc/123-abc', + 'url': 'https://tvonline.osnatel.de/watch/abc/123-abc', 'only_matching': True, }] @@ -407,6 +413,7 @@ class OsnatelTVIE(ZattooIE): class EinsUndEinsTVIE(ZattooIE): _NETRC_MACHINE = '1und1tv' _HOST = '1und1.tv' + _API_HOST = 'www.%s' % _HOST _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ From 2004e2210bc74aa950feba0f22df4d5a8980b3e8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 5 Nov 2018 17:09:57 +0700 Subject: [PATCH 284/558] [osnateltv] Update host --- youtube_dl/extractor/zattoo.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/zattoo.py b/youtube_dl/extractor/zattoo.py index cb1bac3a3..896276301 100644 --- a/youtube_dl/extractor/zattoo.py +++ b/youtube_dl/extractor/zattoo.py @@ -401,7 +401,7 @@ class QuantumTVIE(ZattooIE): class OsnatelTVIE(ZattooIE): _NETRC_MACHINE = 'osnateltv' - _HOST = 'onlinetv.osnatel.de' + _HOST = 'tvonline.osnatel.de' _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ From c0345b825f8758571a8de871ab9349c46b062fc0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 5 Nov 2018 19:08:39 +0700 Subject: [PATCH 285/558] [youtube:playlist] Add support for invidio.us (closes #18077) --- youtube_dl/extractor/youtube.py | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index abadfa545..6ab2db274 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -2162,7 +2162,11 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): (?:https?://)? (?:\w+\.)? (?: - youtube\.com/ + (?: + youtube\.com| + invidio\.us + ) + / (?: (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11})) \? (?:.*?[&;])*? (?:p|a|list)= @@ -2314,6 +2318,9 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): # music album playlist 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', 'only_matching': True, + }, { + 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU', + 'only_matching': True, }] def _real_initialize(self): From 432cd4841023091811db46cd82c188698a386841 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 6 Nov 2018 23:29:42 +0700 Subject: [PATCH 286/558] [cliphinter] Fix extraction (closes #18083) --- youtube_dl/extractor/cliphunter.py | 21 ++++++--------------- 1 file changed, 6 insertions(+), 15 deletions(-) diff --git a/youtube_dl/extractor/cliphunter.py b/youtube_dl/extractor/cliphunter.py index ab651d1c8..f2ca7a337 100644 --- a/youtube_dl/extractor/cliphunter.py +++ b/youtube_dl/extractor/cliphunter.py @@ -1,19 +1,10 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import int_or_none - - -_translation_table = { - 'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n', - 'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r', - 'y': 'l', 'z': 'i', - '$': ':', '&': '.', '(': '=', '^': '&', '=': '/', -} - - -def _decode(s): - return ''.join(_translation_table.get(c, c) for c in s) +from ..utils import ( + int_or_none, + url_or_none, +) class CliphunterIE(InfoExtractor): @@ -60,14 +51,14 @@ class CliphunterIE(InfoExtractor): formats = [] for format_id, f in gexo_files.items(): - video_url = f.get('url') + video_url = url_or_none(f.get('url')) if not video_url: continue fmt = f.get('fmt') height = f.get('h') format_id = '%s_%sp' % (fmt, height) if fmt and height else format_id formats.append({ - 'url': _decode(video_url), + 'url': video_url, 'format_id': format_id, 'width': int_or_none(f.get('w')), 'height': int_or_none(height), From 0df514f07e23ce70cccec045b4e71bdec151fcc7 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 6 Nov 2018 21:22:00 +0100 Subject: [PATCH 287/558] [facebook] fix tahoe request(closes #17171) --- youtube_dl/extractor/facebook.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 97cfe0fc3..74954049d 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -57,7 +57,7 @@ class FacebookIE(InfoExtractor): _CHROME_USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36' _VIDEO_PAGE_TEMPLATE = 'https://www.facebook.com/video/video.php?v=%s' - _VIDEO_PAGE_TAHOE_TEMPLATE = 'https://www.facebook.com/video/tahoe/async/%s/?chain=true&isvideo=true' + _VIDEO_PAGE_TAHOE_TEMPLATE = 'https://www.facebook.com/video/tahoe/async/%s/?chain=true&isvideo=true&payloadtype=primary' _TESTS = [{ 'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf', From 2511eee215c2a66020ae927c86face826f48ba8e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 7 Nov 2018 09:55:59 +0700 Subject: [PATCH 288/558] [youtube] Add another JS signature function name regex (closes #18091, closes #18093, closes #18094) --- youtube_dl/extractor/youtube.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 6ab2db274..3f49f3889 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1192,7 +1192,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(', r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', - r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\('), + r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', + r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('), jscode, 'Initial JS player signature function name', group='sig') jsi = JSInterpreter(jscode) From f81d44aab6d8ee01024a637cb80374251737872e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 7 Nov 2018 09:58:08 +0700 Subject: [PATCH 289/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/ChangeLog b/ChangeLog index 11e1ba333..920a4855a 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,15 @@ +version <unreleased> + +Extractors ++ [youtube] Add another JS signature function name regex (#18091, #18093, + #18094) +* [facebook] Fix tahoe request (#17171) +* [cliphunter] Fix extraction (#18083) ++ [youtube:playlist] Add support for invidio.us (#18077) +* [zattoo] Arrange API hosts for derived extractors (#18035) ++ [youtube] Add fallback metadata extraction from videoDetails (#18052) + + version 2018.11.03 Core From 532782ade1dab884606dbbd82081ed7ab9c52a13 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 7 Nov 2018 01:38:25 +0700 Subject: [PATCH 290/558] release 2018.11.07 --- .github/ISSUE_TEMPLATE.md | 6 +++--- CONTRIBUTING.md | 23 ++++++++++++++++++++++- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 4 files changed, 27 insertions(+), 6 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index eb8cef8ef..7607e0e03 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.11.03*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.11.03** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.11.07*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.11.07** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.11.03 +[debug] youtube-dl version 2018.11.07 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 333acee80..bbcb78808 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -296,5 +296,26 @@ title = self._search_regex( ### Use safe conversion functions -Wrap all extracted numeric data into safe functions from `utils`: `int_or_none`, `float_or_none`. Use them for string to number conversions as well. +Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well. + +Use `url_or_none` for safe URL processing. + +Use `try_get` for safe metadata extraction from parsed JSON. + +Explore [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions. + +#### More examples + +##### Safely extract optional description from parsed JSON +```python +description = try_get(response, lambda x: x['result']['video'][0]['summary'], compat_str) +``` + +##### Safely extract more optional metadata +```python +video = try_get(response, lambda x: x['result']['video'][0], dict) or {} +description = video.get('summary') +duration = float_or_none(video.get('durationMs'), scale=1000) +view_count = int_or_none(video.get('views')) +``` diff --git a/ChangeLog b/ChangeLog index 920a4855a..fa5de8b04 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.11.07 Extractors + [youtube] Add another JS signature function name regex (#18091, #18093, diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 90de01214..7f32ad36c 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.11.03' +__version__ = '2018.11.07' From cab26223bf480553d67840fc9f46aa9ff89ec29f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 10 Nov 2018 15:22:59 +0700 Subject: [PATCH 291/558] [ruutu] Update API endpoint (closes #18138) --- youtube_dl/extractor/ruutu.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/ruutu.py b/youtube_dl/extractor/ruutu.py index 9fa8688f8..f530f0083 100644 --- a/youtube_dl/extractor/ruutu.py +++ b/youtube_dl/extractor/ruutu.py @@ -65,7 +65,8 @@ class RuutuIE(InfoExtractor): video_id = self._match_id(url) video_xml = self._download_xml( - 'http://gatling.ruutu.fi/media-xml-cache?id=%s' % video_id, video_id) + 'https://gatling.nelonenmedia.fi/media-xml-cache', video_id, + query={'id': video_id}) formats = [] processed_urls = [] From 96a91b15513af2121be1dd93871cc3769c06da3e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 10 Nov 2018 23:37:27 +0700 Subject: [PATCH 292/558] [vivo] Fix extraction (closes #18139) --- youtube_dl/extractor/shared.py | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index b2250afdd..931a0f70e 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -5,6 +5,7 @@ from ..compat import compat_b64decode from ..utils import ( ExtractorError, int_or_none, + url_or_none, urlencode_postdata, ) @@ -86,9 +87,16 @@ class VivoIE(SharedBaseIE): } def _extract_video_url(self, webpage, video_id, *args): + def decode_url(encoded_url): + return compat_b64decode(encoded_url).decode('utf-8') + + stream_url = url_or_none(decode_url(self._search_regex( + r'data-stream\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, + 'stream url', default=None, group='url'))) + if stream_url: + return stream_url return self._parse_json( self._search_regex( r'InitializeStream\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'stream', group='url'), - video_id, - transform_source=lambda x: compat_b64decode(x).decode('utf-8'))[0] + video_id, transform_source=decode_url)[0] From 83852e57bf2f96ba50418b1a888ae5a1836549cc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 11 Nov 2018 00:44:49 +0700 Subject: [PATCH 293/558] [zype] Add extractor (closes #18143) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/generic.py | 20 +++++++++++ youtube_dl/extractor/zype.py | 57 ++++++++++++++++++++++++++++++ 3 files changed, 78 insertions(+) create mode 100644 youtube_dl/extractor/zype.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index e5488cce4..b2b00c86f 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1478,3 +1478,4 @@ from .zattoo import ( ) from .zdf import ZDFIE, ZDFChannelIE from .zingmp3 import ZingMp3IE +from .zype import ZypeIE diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 545e03371..59cf03faf 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -114,6 +114,7 @@ from .apa import APAIE from .foxnews import FoxNewsIE from .viqeo import ViqeoIE from .expressen import ExpressenIE +from .zype import ZypeIE class GenericIE(InfoExtractor): @@ -2070,6 +2071,20 @@ class GenericIE(InfoExtractor): }, 'playlist_count': 6, }, + { + # Zype embed + 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites', + 'info_dict': { + 'id': '5b400b834b32992a310622b9', + 'ext': 'mp4', + 'title': 'Smoky Barbecue Favorites', + 'thumbnail': r're:^https?://.*\.jpe?g', + }, + 'add_ie': [ZypeIE.ie_key()], + 'params': { + 'skip_download': True, + }, + }, { # videojs embed 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904', @@ -3129,6 +3144,11 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key()) + zype_urls = ZypeIE._extract_urls(webpage) + if zype_urls: + return self.playlist_from_matches( + zype_urls, video_id, video_title, ie=ZypeIE.ie_key()) + # Look for HTML5 media entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls') if entries: diff --git a/youtube_dl/extractor/zype.py b/youtube_dl/extractor/zype.py new file mode 100644 index 000000000..3b16e703b --- /dev/null +++ b/youtube_dl/extractor/zype.py @@ -0,0 +1,57 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class ZypeIE(InfoExtractor): + _VALID_URL = r'https?://player\.zype\.com/embed/(?P<id>[\da-fA-F]+)\.js\?.*?api_key=[^&]+' + _TEST = { + 'url': 'https://player.zype.com/embed/5b400b834b32992a310622b9.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ&autoplay=false&controls=true&da=false', + 'md5': 'eaee31d474c76a955bdaba02a505c595', + 'info_dict': { + 'id': '5b400b834b32992a310622b9', + 'ext': 'mp4', + 'title': 'Smoky Barbecue Favorites', + 'thumbnail': r're:^https?://.*\.jpe?g', + }, + } + + @staticmethod + def _extract_urls(webpage): + return [ + mobj.group('url') + for mobj in re.finditer( + r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//player\.zype\.com/embed/[\da-fA-F]+\.js\?.*?api_key=.+?)\1', + webpage)] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + title = self._search_regex( + r'video_title\s*[:=]\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, + 'title', group='value') + + m3u8_url = self._search_regex( + r'(["\'])(?P<url>(?:(?!\1).)+\.m3u8(?:(?!\1).)*)\1', webpage, + 'm3u8 url', group='url') + + formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + self._sort_formats(formats) + + thumbnail = self._search_regex( + r'poster\s*[:=]\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'thumbnail', + default=False, group='url') + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } From f17a24a6df293370b94082c7feb6c447a3e7d8d9 Mon Sep 17 00:00:00 2001 From: Patrick Griffis <tingping@tingping.se> Date: Mon, 21 May 2018 17:02:16 -0400 Subject: [PATCH 294/558] [picarto] Use API and add token support This is just more reliable than trying to extract it from the page itself. --- youtube_dl/extractor/picarto.py | 36 +++++++++------------------------ 1 file changed, 9 insertions(+), 27 deletions(-) diff --git a/youtube_dl/extractor/picarto.py b/youtube_dl/extractor/picarto.py index 2366dfb34..27ee9643b 100644 --- a/youtube_dl/extractor/picarto.py +++ b/youtube_dl/extractor/picarto.py @@ -8,14 +8,13 @@ from ..compat import compat_str from ..utils import ( ExtractorError, js_to_json, - try_get, update_url_query, urlencode_postdata, ) class PicartoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P<id>[a-zA-Z0-9]+)' + _VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P<id>[a-zA-Z0-9]+)(?:/(?P<token>[a-zA-Z0-9]+))?' _TEST = { 'url': 'https://picarto.tv/Setz', 'info_dict': { @@ -34,19 +33,11 @@ class PicartoIE(InfoExtractor): def _real_extract(self, url): channel_id = self._match_id(url) - stream_page = self._download_webpage(url, channel_id) + metadata = self._download_json( + 'https://api.picarto.tv/v1/channel/name/' + channel_id, + channel_id) - if '>This channel does not exist' in stream_page: - raise ExtractorError( - 'Channel %s does not exist' % channel_id, expected=True) - - player = self._parse_json( - self._search_regex( - r'(?s)playerSettings\[\d+\]\s*=\s*(\{.+?\}\s*\n)', stream_page, - 'player settings'), - channel_id, transform_source=js_to_json) - - if player.get('online') is False: + if metadata.get('online') is False: raise ExtractorError('Stream is offline', expected=True) cdn_data = self._download_json( @@ -54,20 +45,13 @@ class PicartoIE(InfoExtractor): data=urlencode_postdata({'loadbalancinginfo': channel_id}), note='Downloading load balancing info') - def get_event(key): - return try_get(player, lambda x: x['event'][key], compat_str) or '' - + token = self._VALID_URL_RE.match(url).group('token') or 'public' params = { - 'token': player.get('token') or '', - 'ticket': get_event('ticket'), 'con': int(time.time() * 1000), - 'type': get_event('ticket'), - 'scope': get_event('scope'), + 'token': token, } prefered_edge = cdn_data.get('preferedEdge') - default_tech = player.get('defaultTech') - formats = [] for edge in cdn_data['edges']: @@ -81,8 +65,6 @@ class PicartoIE(InfoExtractor): preference = 0 if edge_id == prefered_edge: preference += 1 - if tech_type == default_tech: - preference += 1 format_id = [] if edge_id: format_id.append(edge_id) @@ -109,7 +91,7 @@ class PicartoIE(InfoExtractor): continue self._sort_formats(formats) - mature = player.get('mature') + mature = metadata.get('adult') if mature is None: age_limit = None else: @@ -119,7 +101,7 @@ class PicartoIE(InfoExtractor): 'id': channel_id, 'title': self._live_title(channel_id), 'is_live': True, - 'thumbnail': player.get('vodThumb'), + 'thumbnail': metadata.get('thumbnails', {}).get('web'), 'age_limit': age_limit, 'formats': formats, } From 730c0d12a06f349907481570f1f2890251f7a181 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 11 Nov 2018 16:08:54 +0700 Subject: [PATCH 295/558] [picarto] Extract more metadata (closes #16518) --- youtube_dl/extractor/picarto.py | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/picarto.py b/youtube_dl/extractor/picarto.py index 27ee9643b..8099ef1d6 100644 --- a/youtube_dl/extractor/picarto.py +++ b/youtube_dl/extractor/picarto.py @@ -1,6 +1,7 @@ # coding: utf-8 from __future__ import unicode_literals +import re import time from .common import InfoExtractor @@ -8,6 +9,7 @@ from ..compat import compat_str from ..utils import ( ExtractorError, js_to_json, + try_get, update_url_query, urlencode_postdata, ) @@ -32,7 +34,9 @@ class PicartoIE(InfoExtractor): return False if PicartoVodIE.suitable(url) else super(PicartoIE, cls).suitable(url) def _real_extract(self, url): - channel_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + channel_id = mobj.group('id') + metadata = self._download_json( 'https://api.picarto.tv/v1/channel/name/' + channel_id, channel_id) @@ -45,7 +49,7 @@ class PicartoIE(InfoExtractor): data=urlencode_postdata({'loadbalancinginfo': channel_id}), note='Downloading load balancing info') - token = self._VALID_URL_RE.match(url).group('token') or 'public' + token = mobj.group('token') or 'public' params = { 'con': int(time.time() * 1000), 'token': token, @@ -99,9 +103,11 @@ class PicartoIE(InfoExtractor): return { 'id': channel_id, - 'title': self._live_title(channel_id), + 'title': self._live_title(metadata.get('title') or channel_id), 'is_live': True, - 'thumbnail': metadata.get('thumbnails', {}).get('web'), + 'thumbnail': try_get(metadata, lambda x: x['thumbnails']['web']), + 'channel': channel_id, + 'channel_url': 'https://picarto.tv/%s' % channel_id, 'age_limit': age_limit, 'formats': formats, } From 9b9b3501c5bee18d608dd2961a80936667f8ece2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 16 Nov 2018 22:55:35 +0700 Subject: [PATCH 296/558] [tnaflixnetwork:embed] Fix extraction (closes #18205) --- youtube_dl/extractor/tnaflix.py | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/tnaflix.py b/youtube_dl/extractor/tnaflix.py index 0c2f8f119..6798ef4c3 100644 --- a/youtube_dl/extractor/tnaflix.py +++ b/youtube_dl/extractor/tnaflix.py @@ -18,8 +18,9 @@ from ..utils import ( class TNAFlixNetworkBaseIE(InfoExtractor): # May be overridden in descendants if necessary _CONFIG_REGEX = [ - r'flashvars\.config\s*=\s*escape\("([^"]+)"', - r'<input[^>]+name="config\d?" value="([^"]+)"', + r'flashvars\.config\s*=\s*escape\("(?P<url>[^"]+)"', + r'<input[^>]+name="config\d?" value="(?P<url>[^"]+)"', + r'config\s*=\s*(["\'])(?P<url>(?:https?:)?//(?:(?!\1).)+)\1', ] _HOST = 'tna' _VKEY_SUFFIX = '' @@ -85,7 +86,8 @@ class TNAFlixNetworkBaseIE(InfoExtractor): webpage = self._download_webpage(url, display_id) cfg_url = self._proto_relative_url(self._html_search_regex( - self._CONFIG_REGEX, webpage, 'flashvars.config', default=None), 'http:') + self._CONFIG_REGEX, webpage, 'flashvars.config', default=None, + group='url'), 'http:') if not cfg_url: inputs = self._hidden_inputs(webpage) From 2599956c9ff0162e7afbddebb00d73eea6b0403c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 17 Nov 2018 00:07:59 +0700 Subject: [PATCH 297/558] [rte] Add support for new API endpoint (closes #18206) --- youtube_dl/extractor/rte.py | 129 +++++++++++++++++++++--------------- 1 file changed, 77 insertions(+), 52 deletions(-) diff --git a/youtube_dl/extractor/rte.py b/youtube_dl/extractor/rte.py index a6fac6c35..1fbc72915 100644 --- a/youtube_dl/extractor/rte.py +++ b/youtube_dl/extractor/rte.py @@ -8,7 +8,10 @@ from ..compat import compat_HTTPError from ..utils import ( float_or_none, parse_iso8601, + str_or_none, + try_get, unescapeHTML, + url_or_none, ExtractorError, ) @@ -17,65 +20,87 @@ class RteBaseIE(InfoExtractor): def _real_extract(self, url): item_id = self._match_id(url) - try: - json_string = self._download_json( - 'http://www.rte.ie/rteavgen/getplaylist/?type=web&format=json&id=' + item_id, - item_id) - except ExtractorError as ee: - if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404: - error_info = self._parse_json(ee.cause.read().decode(), item_id, fatal=False) - if error_info: - raise ExtractorError( - '%s said: %s' % (self.IE_NAME, error_info['message']), - expected=True) - raise - - # NB the string values in the JSON are stored using XML escaping(!) - show = json_string['shows'][0] - title = unescapeHTML(show['title']) - description = unescapeHTML(show.get('description')) - thumbnail = show.get('thumbnail') - duration = float_or_none(show.get('duration'), 1000) - timestamp = parse_iso8601(show.get('published')) - - mg = show['media:group'][0] - + info_dict = {} formats = [] - if mg.get('url'): - m = re.match(r'(?P<url>rtmpe?://[^/]+)/(?P<app>.+)/(?P<playpath>mp4:.*)', mg['url']) - if m: - m = m.groupdict() - formats.append({ - 'url': m['url'] + '/' + m['app'], - 'app': m['app'], - 'play_path': m['playpath'], - 'player_url': url, - 'ext': 'flv', - 'format_id': 'rtmp', - }) + ENDPOINTS = ( + 'https://feeds.rasset.ie/rteavgen/player/playlist?type=iptv&format=json&showId=', + 'http://www.rte.ie/rteavgen/getplaylist/?type=web&format=json&id=', + ) - if mg.get('hls_server') and mg.get('hls_url'): - formats.extend(self._extract_m3u8_formats( - mg['hls_server'] + mg['hls_url'], item_id, 'mp4', - entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)) + for num, ep_url in enumerate(ENDPOINTS, start=1): + try: + data = self._download_json(ep_url + item_id, item_id) + except ExtractorError as ee: + if num < len(ENDPOINTS) or formats: + continue + if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404: + error_info = self._parse_json(ee.cause.read().decode(), item_id, fatal=False) + if error_info: + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, error_info['message']), + expected=True) + raise - if mg.get('hds_server') and mg.get('hds_url'): - formats.extend(self._extract_f4m_formats( - mg['hds_server'] + mg['hds_url'], item_id, - f4m_id='hds', fatal=False)) + # NB the string values in the JSON are stored using XML escaping(!) + show = try_get(data, lambda x: x['shows'][0], dict) + if not show: + continue + + if not info_dict: + title = unescapeHTML(show['title']) + description = unescapeHTML(show.get('description')) + thumbnail = show.get('thumbnail') + duration = float_or_none(show.get('duration'), 1000) + timestamp = parse_iso8601(show.get('published')) + info_dict = { + 'id': item_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + } + + mg = try_get(show, lambda x: x['media:group'][0], dict) + if not mg: + continue + + if mg.get('url'): + m = re.match(r'(?P<url>rtmpe?://[^/]+)/(?P<app>.+)/(?P<playpath>mp4:.*)', mg['url']) + if m: + m = m.groupdict() + formats.append({ + 'url': m['url'] + '/' + m['app'], + 'app': m['app'], + 'play_path': m['playpath'], + 'player_url': url, + 'ext': 'flv', + 'format_id': 'rtmp', + }) + + if mg.get('hls_server') and mg.get('hls_url'): + formats.extend(self._extract_m3u8_formats( + mg['hls_server'] + mg['hls_url'], item_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)) + + if mg.get('hds_server') and mg.get('hds_url'): + formats.extend(self._extract_f4m_formats( + mg['hds_server'] + mg['hds_url'], item_id, + f4m_id='hds', fatal=False)) + + mg_rte_server = str_or_none(mg.get('rte:server')) + mg_url = str_or_none(mg.get('url')) + if mg_rte_server and mg_url: + hds_url = url_or_none(mg_rte_server + mg_url) + if hds_url: + formats.extend(self._extract_f4m_formats( + hds_url, item_id, f4m_id='hds', fatal=False)) self._sort_formats(formats) - return { - 'id': item_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'timestamp': timestamp, - 'duration': duration, - 'formats': formats, - } + info_dict['formats'] = formats + return info_dict class RteIE(RteBaseIE): From 0919cd4d011d0545a6afadfab0b71de8c0a4fe02 Mon Sep 17 00:00:00 2001 From: NeroBurner <pyro4hell@gmail.com> Date: Fri, 16 Nov 2018 18:18:50 +0100 Subject: [PATCH 298/558] [atvat] Fix extraction (closes #18041) --- youtube_dl/extractor/atvat.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/atvat.py b/youtube_dl/extractor/atvat.py index 1584d53fc..95e572d70 100644 --- a/youtube_dl/extractor/atvat.py +++ b/youtube_dl/extractor/atvat.py @@ -28,8 +28,10 @@ class ATVAtIE(InfoExtractor): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) video_data = self._parse_json(unescapeHTML(self._search_regex( - r'class="[^"]*jsb_video/FlashPlayer[^"]*"[^>]+data-jsb="([^"]+)"', - webpage, 'player data')), display_id)['config']['initial_video'] + [r'flashPlayerOptions\s*=\s*(["\'])(?P<json>(?:(?!\1).)+)\1', + r'class="[^"]*jsb_video/FlashPlayer[^"]*"[^>]+data-jsb="(?P<json>[^"]+)"'], + webpage, 'player data', group='json')), + display_id)['config']['initial_video'] video_id = video_data['id'] video_title = video_data['title'] From d0058c76d5e14ffe89e8265fa3d984e28e922d78 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 17 Nov 2018 16:59:20 +0700 Subject: [PATCH 299/558] [openload] Use original host during extraction (closes #18211) --- youtube_dl/extractor/openload.py | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index 2473536fd..cf51e4770 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -243,7 +243,18 @@ class PhantomJSwrapper(object): class OpenloadIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun))/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)' + _VALID_URL = r'''(?x) + https?:// + (?P<host> + (?:www\.)? + (?: + openload\.(?:co|io|link)| + oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun) + ) + )/ + (?:f|embed)/ + (?P<id>[a-zA-Z0-9-_]+) + ''' _TESTS = [{ 'url': 'https://openload.co/f/kUEfGclsU9o', @@ -334,8 +345,11 @@ class OpenloadIE(InfoExtractor): webpage) def _real_extract(self, url): - video_id = self._match_id(url) - url_pattern = 'https://openload.co/%%s/%s/' % video_id + mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') + video_id = mobj.group('id') + + url_pattern = 'https://%s/%%s/%s/' % (host, video_id) headers = { 'User-Agent': self._USER_AGENT, } @@ -368,7 +382,7 @@ class OpenloadIE(InfoExtractor): r'>\s*([\w~-]+~[a-f0-9:]+~[\w~-]+)'), webpage, 'stream URL')) - video_url = 'https://openload.co/stream/%s?mime=true' % decoded_id + video_url = 'https://%s/stream/%s?mime=true' % (host, decoded_id) title = self._og_search_title(webpage, default=None) or self._search_regex( r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage, @@ -379,7 +393,7 @@ class OpenloadIE(InfoExtractor): entry = entries[0] if entries else {} subtitles = entry.get('subtitles') - info_dict = { + return { 'id': video_id, 'title': title, 'thumbnail': entry.get('thumbnail') or self._og_search_thumbnail(webpage, default=None), @@ -388,4 +402,3 @@ class OpenloadIE(InfoExtractor): 'subtitles': subtitles, 'http_headers': headers, } - return info_dict From a640c4d226e7b790fe8db43f1c5bdf2358caf839 Mon Sep 17 00:00:00 2001 From: aviperes <avipr24@gmail.com> Date: Sat, 17 Nov 2018 15:59:13 +0200 Subject: [PATCH 300/558] [vk] Detect geo restriction --- youtube_dl/extractor/vk.py | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index ef8b9bcb7..b52d15ac6 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -293,8 +293,12 @@ class VKIE(VKBaseIE): # This video is no longer available, because its author has been blocked. 'url': 'https://vk.com/video-10639516_456240611', 'only_matching': True, - } - ] + }, + { + # The video is not available in your region. + 'url': 'https://vk.com/video-51812607_171445436', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -354,6 +358,9 @@ class VKIE(VKBaseIE): r'<!>This video is no longer available, because it has been deleted.': 'Video %s is no longer available, because it has been deleted.', + + r'<!>The video .+? is not available in your region.': + 'Video %s is not available in your region.', } for error_re, error_msg in ERRORS.items(): From 11d19ff50393cd195af884c6865aff6d89ed66ac Mon Sep 17 00:00:00 2001 From: mttronc <mrtn.mtth@gmx.de> Date: Thu, 6 Sep 2018 15:41:07 +0200 Subject: [PATCH 301/558] [wwe] Add extractor --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/wwe.py | 56 ++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+) create mode 100644 youtube_dl/extractor/wwe.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index b2b00c86f..87c7d8b0c 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1386,6 +1386,7 @@ from .wsj import ( WSJIE, WSJArticleIE, ) +from .wwe import WWEIE from .xbef import XBefIE from .xboxclips import XboxClipsIE from .xfileshare import XFileShareIE diff --git a/youtube_dl/extractor/wwe.py b/youtube_dl/extractor/wwe.py new file mode 100644 index 000000000..c471a79f5 --- /dev/null +++ b/youtube_dl/extractor/wwe.py @@ -0,0 +1,56 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import urljoin + + +class WWEIE(InfoExtractor): + _VALID_URL = r'https?://(?:\w+\.)?wwe.com/(?:.*/)?videos/(?P<id>[\w-]+)' + _TESTS = [{ + 'url': 'https://www.wwe.com/videos/daniel-bryan-vs-andrade-cien-almas-smackdown-live-sept-4-2018', + 'md5': '30cbc824b51f4010ea885bfcaec76972', + 'info_dict': { + 'id': '40048199', + 'ext': 'mp4', + 'title': 'Daniel Bryan vs. Andrade "Cien" Almas: SmackDown LIVE, Sept. 4, 2018', + 'description': 'Still fuming after he and his wife Brie Bella were attacked by The Miz and Maryse last week, Daniel Bryan takes care of some unfinished business with Andrade "Cien" Almas.', + 'thumbnail': r're:^https?://.*\.jpg$', + } + }, { + 'url': 'https://de.wwe.com/videos/gran-metalik-vs-tony-nese-wwe-205-live-sept-4-2018', + 'only_matching': True, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + drupal_settings = self._parse_json( + self._html_search_regex( + r'(?s)Drupal\.settings\s*,\s*({.+?})\);', + webpage, 'drupal settings'), + display_id) + + player = drupal_settings['WWEVideoLanding']['initialVideo'] + metadata = player['playlist'][0] + + id = compat_str(metadata['nid']) + title = metadata.get('title') or self._og_search_title(webpage) + video_url = 'https:' + metadata['file'] + thumbnail = None + if metadata.get('image') is not None: + thumbnail = urljoin(url, metadata.get('image')) + description = metadata.get('description') + + formats = self._extract_m3u8_formats(video_url, id, 'mp4') + + return { + 'id': id, + 'title': title, + 'formats': formats, + 'url': video_url, + 'display_id': display_id, + 'thumbnail': thumbnail, + 'description': description, + } From 006374e3aebc3be3f20b7e812c987cdf15b3ae35 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 17 Nov 2018 23:59:20 +0700 Subject: [PATCH 302/558] [wwe] Fix issues, extract subtitles and add support for playlists (closes #14781, closes #17450) --- youtube_dl/extractor/wwe.py | 138 +++++++++++++++++++++++++++++------- 1 file changed, 111 insertions(+), 27 deletions(-) diff --git a/youtube_dl/extractor/wwe.py b/youtube_dl/extractor/wwe.py index c471a79f5..bebc77bb5 100644 --- a/youtube_dl/extractor/wwe.py +++ b/youtube_dl/extractor/wwe.py @@ -1,20 +1,75 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..compat import compat_str -from ..utils import urljoin +from ..utils import ( + try_get, + unescapeHTML, + url_or_none, + urljoin, +) -class WWEIE(InfoExtractor): - _VALID_URL = r'https?://(?:\w+\.)?wwe.com/(?:.*/)?videos/(?P<id>[\w-]+)' +class WWEBaseIE(InfoExtractor): + _SUBTITLE_LANGS = { + 'English': 'en', + 'Deutsch': 'de', + } + + def _extract_entry(self, data, url, video_id=None): + video_id = compat_str(video_id or data['nid']) + title = data['title'] + + formats = self._extract_m3u8_formats( + data['file'], video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + + description = data.get('description') + thumbnail = urljoin(url, data.get('image')) + series = data.get('show_name') + episode = data.get('episode_name') + + subtitles = {} + tracks = data.get('tracks') + if isinstance(tracks, list): + for track in tracks: + if not isinstance(track, dict): + continue + if track.get('kind') != 'captions': + continue + track_file = url_or_none(track.get('file')) + if not track_file: + continue + label = track.get('label') + lang = self._SUBTITLE_LANGS.get(label, label) or 'en' + subtitles.setdefault(lang, []).append({ + 'url': track_file, + }) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'series': series, + 'episode': episode, + 'formats': formats, + 'subtitles': subtitles, + } + + +class WWEIE(WWEBaseIE): + _VALID_URL = r'https?://(?:[^/]+\.)?wwe\.com/(?:[^/]+/)*videos/(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'https://www.wwe.com/videos/daniel-bryan-vs-andrade-cien-almas-smackdown-live-sept-4-2018', - 'md5': '30cbc824b51f4010ea885bfcaec76972', + 'md5': '92811c6a14bfc206f7a6a9c5d9140184', 'info_dict': { 'id': '40048199', 'ext': 'mp4', 'title': 'Daniel Bryan vs. Andrade "Cien" Almas: SmackDown LIVE, Sept. 4, 2018', - 'description': 'Still fuming after he and his wife Brie Bella were attacked by The Miz and Maryse last week, Daniel Bryan takes care of some unfinished business with Andrade "Cien" Almas.', + 'description': 'md5:2d7424dbc6755c61a0e649d2a8677f67', 'thumbnail': r're:^https?://.*\.jpg$', } }, { @@ -26,31 +81,60 @@ class WWEIE(InfoExtractor): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - drupal_settings = self._parse_json( + landing = self._parse_json( self._html_search_regex( - r'(?s)Drupal\.settings\s*,\s*({.+?})\);', + r'(?s)Drupal\.settings\s*,\s*({.+?})\s*\)\s*;', webpage, 'drupal settings'), - display_id) + display_id)['WWEVideoLanding'] - player = drupal_settings['WWEVideoLanding']['initialVideo'] - metadata = player['playlist'][0] + data = landing['initialVideo']['playlist'][0] + video_id = landing.get('initialVideoId') - id = compat_str(metadata['nid']) - title = metadata.get('title') or self._og_search_title(webpage) - video_url = 'https:' + metadata['file'] - thumbnail = None - if metadata.get('image') is not None: - thumbnail = urljoin(url, metadata.get('image')) - description = metadata.get('description') + info = self._extract_entry(data, url, video_id) + info['display_id'] = display_id + return info - formats = self._extract_m3u8_formats(video_url, id, 'mp4') - return { - 'id': id, - 'title': title, - 'formats': formats, - 'url': video_url, - 'display_id': display_id, - 'thumbnail': thumbnail, - 'description': description, - } +class WWEPlaylistIE(WWEBaseIE): + _VALID_URL = r'https?://(?:[^/]+\.)?wwe\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)' + _TESTS = [{ + 'url': 'https://www.wwe.com/shows/raw/2018-11-12', + 'info_dict': { + 'id': '2018-11-12', + }, + 'playlist_mincount': 11, + }, { + 'url': 'http://www.wwe.com/article/walk-the-prank-wwe-edition', + 'only_matching': True, + }, { + 'url': 'https://www.wwe.com/shows/wwenxt/article/matt-riddle-interview', + 'only_matching': True, + }] + + @classmethod + def suitable(cls, url): + return False if WWEIE.suitable(url) else super(WWEPlaylistIE, cls).suitable(url) + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + entries = [] + for mobj in re.finditer( + r'data-video\s*=\s*(["\'])(?P<data>{.+?})\1', webpage): + video = self._parse_json( + mobj.group('data'), display_id, transform_source=unescapeHTML, + fatal=False) + if not video: + continue + data = try_get(video, lambda x: x['playlist'][0], dict) + if not data: + continue + try: + entry = self._extract_entry(data, url) + except Exception: + continue + entry['extractor_key'] = WWEIE.ie_key() + entries.append(entry) + + return self.playlist_result(entries, display_id) From 02df855e1339942c00f365dc59a0e418abb4b26f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 18 Nov 2018 00:07:40 +0700 Subject: [PATCH 303/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/ChangeLog b/ChangeLog index fa5de8b04..15daa1bec 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,20 @@ +version <unreleased> + +Extractors ++ [wwe] Extract subtitles ++ [wwe] Add support for playlistst (#14781) ++ [wwe] Add support for wwe.com (#14781, #17450) +* [vk] Detect geo restriction (#17767) +* [openload] Use original host during extraction (#18211) +* [atvat] Fix extraction (#18041) ++ [rte] Add support for new API endpoint (#18206) +* [tnaflixnetwork:embed] Fix extraction (#18205) +* [picarto] Use API and add token support (#16518) ++ [zype] Add support for player.zype.com (#18143) +* [vivo] Fix extraction (#18139) +* [ruutu] Update API endpoint (#18138) + + version 2018.11.07 Extractors From 5bb04792696c41f66f2114b0cc05b01135fa1f68 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 18 Nov 2018 00:11:54 +0700 Subject: [PATCH 304/558] release 2018.11.18 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 2 ++ youtube_dl/version.py | 2 +- 4 files changed, 7 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 7607e0e03..905576364 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.11.07*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.11.07** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.11.18*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.11.18** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.11.07 +[debug] youtube-dl version 2018.11.18 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 15daa1bec..0083c4631 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.11.18 Extractors + [wwe] Extract subtitles diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 24c3254c3..9009f7e9e 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -1080,6 +1080,7 @@ - **wrzuta.pl:playlist** - **WSJ**: Wall Street Journal - **WSJArticle** + - **WWE** - **XBef** - **XboxClips** - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC, VidBom, vidlo, RapidVideo.TV, FastVideo.me @@ -1139,3 +1140,4 @@ - **ZDF** - **ZDFChannel** - **zingmp3**: mp3.zing.vn + - **Zype** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 7f32ad36c..7f5ad7bf4 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.11.07' +__version__ = '2018.11.18' From 4167148fa45e43a93ed202e5923223b7797340ea Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 18 Nov 2018 01:07:54 +0700 Subject: [PATCH 305/558] [nova:embed] Fix extraction (closes #18222) --- youtube_dl/extractor/nova.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/nova.py b/youtube_dl/extractor/nova.py index 80186ec50..901f44b54 100644 --- a/youtube_dl/extractor/nova.py +++ b/youtube_dl/extractor/nova.py @@ -35,7 +35,7 @@ class NovaEmbedIE(InfoExtractor): bitrates = self._parse_json( self._search_regex( - r'(?s)bitrates\s*=\s*({.+?})\s*;', webpage, 'formats'), + r'(?s)(?:src|bitrates)\s*=\s*({.+?})\s*;', webpage, 'formats'), video_id, transform_source=js_to_json) QUALITIES = ('lq', 'mq', 'hq', 'hd') From 1febf99da1924c46a491790639371f4ee9069193 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 18 Nov 2018 06:26:08 +0700 Subject: [PATCH 306/558] [pornhub] Add pornhub.net alias --- youtube_dl/extractor/pornhub.py | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 19eaf389f..7ee64dbf6 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -27,7 +27,7 @@ class PornHubIE(InfoExtractor): _VALID_URL = r'''(?x) https?:// (?: - (?:[^/]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| + (?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| (?:www\.)?thumbzilla\.com/video/ ) (?P<id>[\da-z]+) @@ -340,7 +340,7 @@ class PornHubPlaylistBaseIE(InfoExtractor): class PornHubPlaylistIE(PornHubPlaylistBaseIE): - _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/playlist/(?P<id>\d+)' + _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.(?:com|net)/playlist/(?P<id>\d+)' _TESTS = [{ 'url': 'http://www.pornhub.com/playlist/4667351', 'info_dict': { @@ -355,7 +355,7 @@ class PornHubPlaylistIE(PornHubPlaylistBaseIE): class PornHubUserVideosIE(PornHubPlaylistBaseIE): - _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos' + _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos' _TESTS = [{ 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public', 'info_dict': { @@ -393,6 +393,9 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE): }, { 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload', 'only_matching': True, + }, { + 'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933', + 'only_matching': True, }] def _real_extract(self, url): From f97c099131f625104f64a99a02a8c9894620171a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 18 Nov 2018 11:14:46 +0700 Subject: [PATCH 307/558] [pornhub] Move test to correct place --- youtube_dl/extractor/pornhub.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 7ee64dbf6..c9c884095 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -121,6 +121,9 @@ class PornHubIE(InfoExtractor): }, { 'url': 'http://www.pornhub.com/video/show?viewkey=648719015', 'only_matching': True, + }, { + 'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933', + 'only_matching': True, }] @staticmethod @@ -393,9 +396,6 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE): }, { 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload', 'only_matching': True, - }, { - 'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933', - 'only_matching': True, }] def _real_extract(self, url): From 964b989dc88c37b027481fb01de835b1e796ba5e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 18 Nov 2018 20:44:51 +0700 Subject: [PATCH 308/558] [americastestkitchen] Add support for zype embeds (closes #18225) --- youtube_dl/extractor/americastestkitchen.py | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/americastestkitchen.py b/youtube_dl/extractor/americastestkitchen.py index 01736872d..8b32aa886 100644 --- a/youtube_dl/extractor/americastestkitchen.py +++ b/youtube_dl/extractor/americastestkitchen.py @@ -43,10 +43,6 @@ class AmericasTestKitchenIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - partner_id = self._search_regex( - r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)', - webpage, 'kaltura partner id') - video_data = self._parse_json( self._search_regex( r'window\.__INITIAL_STATE__\s*=\s*({.+?})\s*;\s*</script>', @@ -58,7 +54,18 @@ class AmericasTestKitchenIE(InfoExtractor): (lambda x: x['episodeDetail']['content']['data'], lambda x: x['videoDetail']['content']['data']), dict) ep_meta = ep_data.get('full_video', {}) - external_id = ep_data.get('external_id') or ep_meta['external_id'] + + zype_id = ep_meta.get('zype_id') + if zype_id: + embed_url = 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % zype_id + ie_key = 'Zype' + else: + partner_id = self._search_regex( + r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)', + webpage, 'kaltura partner id') + external_id = ep_data.get('external_id') or ep_meta['external_id'] + embed_url = 'kaltura:%s:%s' % (partner_id, external_id) + ie_key = 'Kaltura' title = ep_data.get('title') or ep_meta.get('title') description = clean_html(ep_meta.get('episode_description') or ep_data.get( @@ -72,8 +79,8 @@ class AmericasTestKitchenIE(InfoExtractor): return { '_type': 'url_transparent', - 'url': 'kaltura:%s:%s' % (partner_id, external_id), - 'ie_key': 'Kaltura', + 'url': embed_url, + 'ie_key': ie_key, 'title': title, 'description': description, 'thumbnail': thumbnail, From 9b27a78a881bceb9d62f3364399d7572e8e2be24 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 18 Nov 2018 16:13:46 +0100 Subject: [PATCH 309/558] [kaltura] limit requested MediaEntry fields --- youtube_dl/extractor/kaltura.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index 04f68fce4..fdf7f5bbc 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -192,6 +192,8 @@ class KalturaIE(InfoExtractor): 'entryId': video_id, 'service': 'baseentry', 'ks': '{1:result:ks}', + 'responseProfile:fields': 'createdAt,dataUrl,duration,name,plays,thumbnailUrl,userId', + 'responseProfile:type': 1, }, { 'action': 'getbyentryid', From 8578ea4dcb17834ee3843e0e337c15af706f9803 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 18 Nov 2018 16:15:10 +0100 Subject: [PATCH 310/558] [bitchute] use _html_search_regex for title extraction --- youtube_dl/extractor/bitchute.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py index 446a1ab19..43b4732aa 100644 --- a/youtube_dl/extractor/bitchute.py +++ b/youtube_dl/extractor/bitchute.py @@ -37,7 +37,7 @@ class BitChuteIE(InfoExtractor): 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.57 Safari/537.36', }) - title = self._search_regex( + title = self._html_search_regex( (r'<[^>]+\bid=["\']video-title[^>]+>([^<]+)', r'<title>([^<]+)'), webpage, 'title', default=None) or self._html_search_meta( 'description', webpage, 'title', From 2e1280ed432257244ea52a47efe6a7f0e226b897 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 19 Nov 2018 18:15:51 +0100 Subject: [PATCH 311/558] [sixplay] fix format extraction --- youtube_dl/extractor/sixplay.py | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) diff --git a/youtube_dl/extractor/sixplay.py b/youtube_dl/extractor/sixplay.py index 207ab4477..0c4f865ef 100644 --- a/youtube_dl/extractor/sixplay.py +++ b/youtube_dl/extractor/sixplay.py @@ -64,7 +64,7 @@ class SixPlayIE(InfoExtractor): for asset in clip_data['assets']: asset_url = asset.get('full_physical_path') protocol = asset.get('protocol') - if not asset_url or protocol == 'primetime' or asset_url in urls: + if not asset_url or protocol == 'primetime' or asset.get('type') == 'usp_hlsfp_h264' or asset_url in urls: continue urls.append(asset_url) container = asset.get('video_container') @@ -81,19 +81,17 @@ class SixPlayIE(InfoExtractor): if not urlh: continue asset_url = urlh.geturl() - asset_url = re.sub(r'/([^/]+)\.ism/[^/]*\.m3u8', r'/\1.ism/\1.m3u8', asset_url) - formats.extend(self._extract_m3u8_formats( - asset_url, video_id, 'mp4', 'm3u8_native', - m3u8_id='hls', fatal=False)) - formats.extend(self._extract_f4m_formats( - asset_url.replace('.m3u8', '.f4m'), - video_id, f4m_id='hds', fatal=False)) - formats.extend(self._extract_mpd_formats( - asset_url.replace('.m3u8', '.mpd'), - video_id, mpd_id='dash', fatal=False)) - formats.extend(self._extract_ism_formats( - re.sub(r'/[^/]+\.m3u8', '/Manifest', asset_url), - video_id, ism_id='mss', fatal=False)) + for i in range(3, 0, -1): + asset_url = asset_url = asset_url.replace('_sd1/', '_sd%d/' % i) + m3u8_formats = self._extract_m3u8_formats( + asset_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False) + formats.extend(m3u8_formats) + formats.extend(self._extract_mpd_formats( + asset_url.replace('.m3u8', '.mpd'), + video_id, mpd_id='dash', fatal=False)) + if m3u8_formats: + break else: formats.extend(self._extract_m3u8_formats( asset_url, video_id, 'mp4', 'm3u8_native', From 15ed5a27840e748d9f786c50b78a4c6326e9f186 Mon Sep 17 00:00:00 2001 From: Alexander Seiler <seileralex@gmail.com> Date: Tue, 20 Nov 2018 20:50:40 +0100 Subject: [PATCH 312/558] [nzz] Relax kaltura regex --- youtube_dl/extractor/nzz.py | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/nzz.py b/youtube_dl/extractor/nzz.py index 2d352f53f..61ee77adb 100644 --- a/youtube_dl/extractor/nzz.py +++ b/youtube_dl/extractor/nzz.py @@ -11,20 +11,27 @@ from ..utils import ( class NZZIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?nzz\.ch/(?:[^/]+/)*[^/?#]+-ld\.(?P<id>\d+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.nzz.ch/zuerich/gymizyte/gymizyte-schreiben-schueler-heute-noch-diktate-ld.9153', 'info_dict': { 'id': '9153', }, 'playlist_mincount': 6, - } + }, { + 'url': 'https://www.nzz.ch/video/nzz-standpunkte/cvp-auf-der-suche-nach-dem-mass-der-mitte-ld.1368112', + 'info_dict': { + 'id': '1368112', + }, + 'playlist_count': 1, + }] def _real_extract(self, url): page_id = self._match_id(url) webpage = self._download_webpage(url, page_id) entries = [] - for player_element in re.findall(r'(<[^>]+class="kalturaPlayer"[^>]*>)', webpage): + for player_element in re.findall( + r'(<[^>]+class="kalturaPlayer[^"]*"[^>]*>)', webpage): player_params = extract_attributes(player_element) if player_params.get('data-type') not in ('kaltura_singleArticle',): self.report_warning('Unsupported player type') From 05bd5e9c77e0e8acb95f47396be4c970fc9f39c4 Mon Sep 17 00:00:00 2001 From: Austin de Coup-Crank <austindcc@gmail.com> Date: Fri, 26 Oct 2018 19:15:44 -0700 Subject: [PATCH 313/558] [ciscolive] Add extractor --- youtube_dl/extractor/ciscolive.py | 136 +++++++++++++++++++++++++++++ youtube_dl/extractor/extractors.py | 1 + 2 files changed, 137 insertions(+) create mode 100644 youtube_dl/extractor/ciscolive.py diff --git a/youtube_dl/extractor/ciscolive.py b/youtube_dl/extractor/ciscolive.py new file mode 100644 index 000000000..2db7aad2c --- /dev/null +++ b/youtube_dl/extractor/ciscolive.py @@ -0,0 +1,136 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse_urlparse, + compat_parse_qs +) +from ..utils import ( + clean_html, + int_or_none, + try_get, + urlencode_postdata, +) + + +class CiscoLiveIE(InfoExtractor): + IE_NAME = 'ciscolive' + _VALID_URL = r'(?:https?://)?ciscolive\.cisco\.com/on-demand-library/\??(?P<query>[^#]+)#/(?:session/(?P<id>.+))?$' + _TESTS = [ + { + 'url': 'https://ciscolive.cisco.com/on-demand-library/?#/session/1423353499155001FoSs', + 'md5': 'c98acf395ed9c9f766941c70f5352e22', + 'info_dict': { + 'id': '5803694304001', + 'ext': 'mp4', + 'title': '13 Smart Automations to Monitor Your Cisco IOS Network', + 'description': 'md5:ec4a436019e09a918dec17714803f7cc', + 'timestamp': 1530305395, + 'uploader_id': '5647924234001', + 'upload_date': '20180629', + 'location': '16B Mezz.', + }, + }, + { + 'url': 'https://ciscolive.cisco.com/on-demand-library/?search.event=ciscoliveus2018&search.technicallevel=scpsSkillLevel_aintroductory&search.focus=scpsSessionFocus_designAndDeployment#/', + 'md5': '993d4cf051f6174059328b1dce8e94bd', + 'info_dict': { + 'upload_date': '20180629', + 'title': 'DevNet Panel-Applying Design Thinking to Building Products in Cisco', + 'timestamp': 1530316421, + 'uploader_id': '5647924234001', + 'id': '5803751616001', + 'description': 'md5:5f144575cd6848117fe2f756855b038b', + 'location': 'WoS, DevNet Theater', + 'ext': 'mp4', + }, + }, + { + 'url': 'https://ciscolive.cisco.com/on-demand-library/?search.technology=scpsTechnology_applicationDevelopment&search.technology=scpsTechnology_ipv6&search.focus=scpsSessionFocus_troubleshootingTroubleshooting#/', + 'md5': '80e0c3b87e373fe3a3316b934b8915bf', + 'info_dict': { + 'upload_date': '20180629', + 'title': 'Beating the CCIE Routing & Switching', + 'timestamp': 1530311842, + 'uploader_id': '5647924234001', + 'id': '5803735679001', + 'description': 'md5:e71970799e92d7f5ff57ae23f64b0929', + 'location': 'Tulúm 02', + 'ext': 'mp4', + }, + } + ] + + # These appear to be constant across all Cisco Live presentations + # and are not tied to any user session or event + RAINFOCUS_API_URL = 'https://events.rainfocus.com/api/%s' + RAINFOCUS_APIPROFILEID = 'Na3vqYdAlJFSxhYTYQGuMbpafMqftalz' + RAINFOCUS_WIDGETID = 'n6l4Lo05R8fiy3RpUBm447dZN8uNWoye' + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5647924234001/SyK2FdqjM_default/index.html?videoId=%s' + + def _parse_rf_item(self, rf_item): + ''' Parses metadata and passes to Brightcove extractor ''' + event_name = rf_item.get('eventName') + title = rf_item['title'] + description = clean_html(rf_item.get('abstract')) + presenter_name = try_get(rf_item, lambda x: x['participants'][0]['fullName']) + bc_id = rf_item['videos'][0]['url'] + bc_url = self.BRIGHTCOVE_URL_TEMPLATE % bc_id + duration = int_or_none(try_get(rf_item, lambda x: x['times'][0]['length'])) + location = try_get(rf_item, lambda x: x['times'][0]['room']) + + if duration: + duration = duration * 60 + + return { + '_type': 'url_transparent', + 'creator': presenter_name, + 'description': description, + 'duration': duration, + 'ie_key': 'BrightcoveNew', + 'location': location, + 'series': event_name, + 'title': title, + 'url': bc_url, + } + + def _check_bc_id_exists(self, rf_item): + ''' Checks for the existence of a Brightcove URL in an API result ''' + bc_id = try_get(rf_item, lambda x: x['videos'][0]['url']) + if bc_id: + if bc_id.strip().isdigit(): + return rf_item + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + HEADERS = { + 'Origin': 'https://ciscolive.cisco.com', + 'rfApiProfileId': self.RAINFOCUS_APIPROFILEID, + 'rfWidgetId': self.RAINFOCUS_WIDGETID, + 'Referer': url, + } + # Single session URL (single video) + if mobj.group('id'): + rf_id = mobj.group('id') + request = self.RAINFOCUS_API_URL % 'session' + data = urlencode_postdata({'id': rf_id}) + rf_result = self._download_json(request, rf_id, data=data, headers=HEADERS) + rf_item = self._check_bc_id_exists(rf_result['items'][0]) + return self._parse_rf_item(rf_item) + else: + # Filter query URL (multiple videos) + rf_query = compat_parse_qs((compat_urllib_parse_urlparse(url).query)) + rf_query['type'] = 'session' + rf_query['size'] = 1000 + data = urlencode_postdata(rf_query) + request = self.RAINFOCUS_API_URL % 'search' + rf_results = self._download_json(request, 'Filter query', data=data, headers=HEADERS) + entries = [ + self._parse_rf_item(rf_item) + for rf_item + in rf_results['sectionList'][0]['items'] + if self._check_bc_id_exists(rf_item) + ] + return self.playlist_result(entries, 'Filter query') diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 87c7d8b0c..2c5988a14 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -194,6 +194,7 @@ from .chirbit import ( ChirbitProfileIE, ) from .cinchcast import CinchcastIE +from .ciscolive import CiscoLiveIE from .cjsw import CJSWIE from .cliphunter import CliphunterIE from .clippit import ClippitIE From 6a6d7f064178427d28986884524bd3434f0ca957 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 21 Nov 2018 05:25:43 +0700 Subject: [PATCH 314/558] [ciscolive] Fix issues and improve extraction (closes #17984) --- youtube_dl/extractor/ciscolive.py | 176 ++++++++++++++--------------- youtube_dl/extractor/extractors.py | 5 +- 2 files changed, 87 insertions(+), 94 deletions(-) diff --git a/youtube_dl/extractor/ciscolive.py b/youtube_dl/extractor/ciscolive.py index 2db7aad2c..32f645713 100644 --- a/youtube_dl/extractor/ciscolive.py +++ b/youtube_dl/extractor/ciscolive.py @@ -1,84 +1,49 @@ # coding: utf-8 from __future__ import unicode_literals -import re from .common import InfoExtractor from ..compat import ( + compat_parse_qs, compat_urllib_parse_urlparse, - compat_parse_qs ) from ..utils import ( clean_html, + float_or_none, int_or_none, try_get, urlencode_postdata, ) -class CiscoLiveIE(InfoExtractor): - IE_NAME = 'ciscolive' - _VALID_URL = r'(?:https?://)?ciscolive\.cisco\.com/on-demand-library/\??(?P<query>[^#]+)#/(?:session/(?P<id>.+))?$' - _TESTS = [ - { - 'url': 'https://ciscolive.cisco.com/on-demand-library/?#/session/1423353499155001FoSs', - 'md5': 'c98acf395ed9c9f766941c70f5352e22', - 'info_dict': { - 'id': '5803694304001', - 'ext': 'mp4', - 'title': '13 Smart Automations to Monitor Your Cisco IOS Network', - 'description': 'md5:ec4a436019e09a918dec17714803f7cc', - 'timestamp': 1530305395, - 'uploader_id': '5647924234001', - 'upload_date': '20180629', - 'location': '16B Mezz.', - }, - }, - { - 'url': 'https://ciscolive.cisco.com/on-demand-library/?search.event=ciscoliveus2018&search.technicallevel=scpsSkillLevel_aintroductory&search.focus=scpsSessionFocus_designAndDeployment#/', - 'md5': '993d4cf051f6174059328b1dce8e94bd', - 'info_dict': { - 'upload_date': '20180629', - 'title': 'DevNet Panel-Applying Design Thinking to Building Products in Cisco', - 'timestamp': 1530316421, - 'uploader_id': '5647924234001', - 'id': '5803751616001', - 'description': 'md5:5f144575cd6848117fe2f756855b038b', - 'location': 'WoS, DevNet Theater', - 'ext': 'mp4', - }, - }, - { - 'url': 'https://ciscolive.cisco.com/on-demand-library/?search.technology=scpsTechnology_applicationDevelopment&search.technology=scpsTechnology_ipv6&search.focus=scpsSessionFocus_troubleshootingTroubleshooting#/', - 'md5': '80e0c3b87e373fe3a3316b934b8915bf', - 'info_dict': { - 'upload_date': '20180629', - 'title': 'Beating the CCIE Routing & Switching', - 'timestamp': 1530311842, - 'uploader_id': '5647924234001', - 'id': '5803735679001', - 'description': 'md5:e71970799e92d7f5ff57ae23f64b0929', - 'location': 'Tulúm 02', - 'ext': 'mp4', - }, - } - ] - +class CiscoLiveBaseIE(InfoExtractor): # These appear to be constant across all Cisco Live presentations # and are not tied to any user session or event RAINFOCUS_API_URL = 'https://events.rainfocus.com/api/%s' - RAINFOCUS_APIPROFILEID = 'Na3vqYdAlJFSxhYTYQGuMbpafMqftalz' - RAINFOCUS_WIDGETID = 'n6l4Lo05R8fiy3RpUBm447dZN8uNWoye' + RAINFOCUS_API_PROFILE_ID = 'Na3vqYdAlJFSxhYTYQGuMbpafMqftalz' + RAINFOCUS_WIDGET_ID = 'n6l4Lo05R8fiy3RpUBm447dZN8uNWoye' BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5647924234001/SyK2FdqjM_default/index.html?videoId=%s' + HEADERS = { + 'Origin': 'https://ciscolive.cisco.com', + 'rfApiProfileId': RAINFOCUS_API_PROFILE_ID, + 'rfWidgetId': RAINFOCUS_WIDGET_ID, + } + + def _call_api(self, ep, rf_id, query, referrer): + headers = self.HEADERS.copy() + headers['Referer'] = referrer + return self._download_json( + self.RAINFOCUS_API_URL % ep, rf_id, data=urlencode_postdata(query), + headers=headers) + def _parse_rf_item(self, rf_item): - ''' Parses metadata and passes to Brightcove extractor ''' event_name = rf_item.get('eventName') title = rf_item['title'] description = clean_html(rf_item.get('abstract')) presenter_name = try_get(rf_item, lambda x: x['participants'][0]['fullName']) bc_id = rf_item['videos'][0]['url'] bc_url = self.BRIGHTCOVE_URL_TEMPLATE % bc_id - duration = int_or_none(try_get(rf_item, lambda x: x['times'][0]['length'])) + duration = float_or_none(try_get(rf_item, lambda x: x['times'][0]['length'])) location = try_get(rf_item, lambda x: x['times'][0]['room']) if duration: @@ -86,51 +51,76 @@ class CiscoLiveIE(InfoExtractor): return { '_type': 'url_transparent', - 'creator': presenter_name, + 'url': bc_url, + 'ie_key': 'BrightcoveNew', + 'title': title, 'description': description, 'duration': duration, - 'ie_key': 'BrightcoveNew', + 'creator': presenter_name, 'location': location, 'series': event_name, - 'title': title, - 'url': bc_url, } - def _check_bc_id_exists(self, rf_item): - ''' Checks for the existence of a Brightcove URL in an API result ''' - bc_id = try_get(rf_item, lambda x: x['videos'][0]['url']) - if bc_id: - if bc_id.strip().isdigit(): - return rf_item + +class CiscoLiveSessionIE(CiscoLiveBaseIE): + _VALID_URL = r'https?://ciscolive\.cisco\.com/on-demand-library/\??[^#]*#/session/(?P<id>[^/?&]+)' + _TEST = { + 'url': 'https://ciscolive.cisco.com/on-demand-library/?#/session/1423353499155001FoSs', + 'md5': 'c98acf395ed9c9f766941c70f5352e22', + 'info_dict': { + 'id': '5803694304001', + 'ext': 'mp4', + 'title': '13 Smart Automations to Monitor Your Cisco IOS Network', + 'description': 'md5:ec4a436019e09a918dec17714803f7cc', + 'timestamp': 1530305395, + 'upload_date': '20180629', + 'uploader_id': '5647924234001', + 'location': '16B Mezz.', + }, + 'params': { + 'proxy': '127.0.0.1:8118', + } + } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - HEADERS = { - 'Origin': 'https://ciscolive.cisco.com', - 'rfApiProfileId': self.RAINFOCUS_APIPROFILEID, - 'rfWidgetId': self.RAINFOCUS_WIDGETID, - 'Referer': url, + rf_id = self._match_id(url) + rf_result = self._call_api('session', rf_id, {'id': rf_id}, url) + return self._parse_rf_item(rf_result['items'][0]) + + +class CiscoLiveSearchIE(CiscoLiveBaseIE): + _VALID_URL = r'https?://ciscolive\.cisco\.com/on-demand-library/' + _TESTS = [{ + 'url': 'https://ciscolive.cisco.com/on-demand-library/?search.event=ciscoliveus2018&search.technicallevel=scpsSkillLevel_aintroductory&search.focus=scpsSessionFocus_designAndDeployment#/', + 'info_dict': { + 'title': 'Filter query', + }, + 'playlist_count': 5, + 'params': { + 'proxy': '127.0.0.1:8118', } - # Single session URL (single video) - if mobj.group('id'): - rf_id = mobj.group('id') - request = self.RAINFOCUS_API_URL % 'session' - data = urlencode_postdata({'id': rf_id}) - rf_result = self._download_json(request, rf_id, data=data, headers=HEADERS) - rf_item = self._check_bc_id_exists(rf_result['items'][0]) - return self._parse_rf_item(rf_item) - else: - # Filter query URL (multiple videos) - rf_query = compat_parse_qs((compat_urllib_parse_urlparse(url).query)) - rf_query['type'] = 'session' - rf_query['size'] = 1000 - data = urlencode_postdata(rf_query) - request = self.RAINFOCUS_API_URL % 'search' - rf_results = self._download_json(request, 'Filter query', data=data, headers=HEADERS) - entries = [ - self._parse_rf_item(rf_item) - for rf_item - in rf_results['sectionList'][0]['items'] - if self._check_bc_id_exists(rf_item) - ] - return self.playlist_result(entries, 'Filter query') + }, { + 'url': 'https://ciscolive.cisco.com/on-demand-library/?search.technology=scpsTechnology_applicationDevelopment&search.technology=scpsTechnology_ipv6&search.focus=scpsSessionFocus_troubleshootingTroubleshooting#/', + 'only_matching': True, + }] + + @classmethod + def suitable(cls, url): + return False if CiscoLiveSessionIE.suitable(url) else super(CiscoLiveSearchIE, cls).suitable(url) + + @staticmethod + def _check_bc_id_exists(rf_item): + return int_or_none(try_get(rf_item, lambda x: x['videos'][0]['url'])) is not None + + def _real_extract(self, url): + rf_query = compat_parse_qs(compat_urllib_parse_urlparse(url).query) + rf_query['type'] = 'session' + rf_query['size'] = 1000 + rf_results = self._call_api('search', None, rf_query, url) + entries = [ + self._parse_rf_item(rf_item) + for rf_item + in rf_results['sectionList'][0]['items'] + if self._check_bc_id_exists(rf_item) + ] + return self.playlist_result(entries, playlist_title='Filter query') diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 2c5988a14..60e6175b1 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -194,7 +194,10 @@ from .chirbit import ( ChirbitProfileIE, ) from .cinchcast import CinchcastIE -from .ciscolive import CiscoLiveIE +from .ciscolive import ( + CiscoLiveSessionIE, + CiscoLiveSearchIE, +) from .cjsw import CJSWIE from .cliphunter import CliphunterIE from .clippit import ClippitIE From 183417a50fd68c0c63b1d0621c6a0b44fbf2ac52 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 21 Nov 2018 06:04:34 +0700 Subject: [PATCH 315/558] [ciscolive:search] Add support for pagination --- youtube_dl/extractor/ciscolive.py | 58 ++++++++++++++++++++----------- 1 file changed, 37 insertions(+), 21 deletions(-) diff --git a/youtube_dl/extractor/ciscolive.py b/youtube_dl/extractor/ciscolive.py index 32f645713..c99b6ee58 100644 --- a/youtube_dl/extractor/ciscolive.py +++ b/youtube_dl/extractor/ciscolive.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import itertools + from .common import InfoExtractor from ..compat import ( compat_parse_qs, @@ -29,12 +31,12 @@ class CiscoLiveBaseIE(InfoExtractor): 'rfWidgetId': RAINFOCUS_WIDGET_ID, } - def _call_api(self, ep, rf_id, query, referrer): + def _call_api(self, ep, rf_id, query, referrer, note=None): headers = self.HEADERS.copy() headers['Referer'] = referrer return self._download_json( - self.RAINFOCUS_API_URL % ep, rf_id, data=urlencode_postdata(query), - headers=headers) + self.RAINFOCUS_API_URL % ep, rf_id, note=note, + data=urlencode_postdata(query), headers=headers) def _parse_rf_item(self, rf_item): event_name = rf_item.get('eventName') @@ -77,9 +79,6 @@ class CiscoLiveSessionIE(CiscoLiveBaseIE): 'uploader_id': '5647924234001', 'location': '16B Mezz.', }, - 'params': { - 'proxy': '127.0.0.1:8118', - } } def _real_extract(self, url): @@ -93,12 +92,9 @@ class CiscoLiveSearchIE(CiscoLiveBaseIE): _TESTS = [{ 'url': 'https://ciscolive.cisco.com/on-demand-library/?search.event=ciscoliveus2018&search.technicallevel=scpsSkillLevel_aintroductory&search.focus=scpsSessionFocus_designAndDeployment#/', 'info_dict': { - 'title': 'Filter query', + 'title': 'Search query', }, 'playlist_count': 5, - 'params': { - 'proxy': '127.0.0.1:8118', - } }, { 'url': 'https://ciscolive.cisco.com/on-demand-library/?search.technology=scpsTechnology_applicationDevelopment&search.technology=scpsTechnology_ipv6&search.focus=scpsSessionFocus_troubleshootingTroubleshooting#/', 'only_matching': True, @@ -112,15 +108,35 @@ class CiscoLiveSearchIE(CiscoLiveBaseIE): def _check_bc_id_exists(rf_item): return int_or_none(try_get(rf_item, lambda x: x['videos'][0]['url'])) is not None + def _entries(self, query, url): + query['size'] = 50 + query['from'] = 0 + for page_num in itertools.count(1): + results = self._call_api( + 'search', None, query, url, + 'Downloading search JSON page %d' % page_num) + sl = try_get(results, lambda x: x['sectionList'][0], dict) + if sl: + results = sl + items = results.get('items') + if not items or not isinstance(items, list): + break + for item in items: + if not isinstance(item, dict): + continue + if not self._check_bc_id_exists(item): + continue + yield self._parse_rf_item(item) + size = int_or_none(results.get('size')) + if size is not None: + query['size'] = size + total = int_or_none(results.get('total')) + if total is not None and query['from'] + query['size'] > total: + break + query['from'] += query['size'] + def _real_extract(self, url): - rf_query = compat_parse_qs(compat_urllib_parse_urlparse(url).query) - rf_query['type'] = 'session' - rf_query['size'] = 1000 - rf_results = self._call_api('search', None, rf_query, url) - entries = [ - self._parse_rf_item(rf_item) - for rf_item - in rf_results['sectionList'][0]['items'] - if self._check_bc_id_exists(rf_item) - ] - return self.playlist_result(entries, playlist_title='Filter query') + query = compat_parse_qs(compat_urllib_parse_urlparse(url).query) + query['type'] = 'session' + return self.playlist_result( + self._entries(query, url), playlist_title='Search query') From 6c882aa8991383e1c39a6457cbde5dcab260bff5 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 21 Nov 2018 09:44:10 +0100 Subject: [PATCH 316/558] [loc] relax _VALID_URL regex and improve formats extraction --- youtube_dl/extractor/libraryofcongress.py | 37 +++++++++++++++-------- 1 file changed, 24 insertions(+), 13 deletions(-) diff --git a/youtube_dl/extractor/libraryofcongress.py b/youtube_dl/extractor/libraryofcongress.py index 40295a30b..1e5c82c66 100644 --- a/youtube_dl/extractor/libraryofcongress.py +++ b/youtube_dl/extractor/libraryofcongress.py @@ -16,7 +16,7 @@ from ..utils import ( class LibraryOfCongressIE(InfoExtractor): IE_NAME = 'loc' IE_DESC = 'Library of Congress' - _VALID_URL = r'https?://(?:www\.)?loc\.gov/(?:item/|today/cyberlc/feature_wdesc\.php\?.*\brec=)(?P<id>[0-9]+)' + _VALID_URL = r'https?://(?:www\.)?loc\.gov/(?:item/|today/cyberlc/feature_wdesc\.php\?.*\brec=)(?P<id>[0-9a-z_.]+)' _TESTS = [{ # embedded via <div class="media-player" 'url': 'http://loc.gov/item/90716351/', @@ -57,6 +57,12 @@ class LibraryOfCongressIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + 'url': 'https://www.loc.gov/item/ihas.200197114/', + 'only_matching': True, + }, { + 'url': 'https://www.loc.gov/item/afc1981005_afs20503/', + 'only_matching': True, }] def _real_extract(self, url): @@ -67,12 +73,13 @@ class LibraryOfCongressIE(InfoExtractor): (r'id=(["\'])media-player-(?P<id>.+?)\1', r'<video[^>]+id=(["\'])uuid-(?P<id>.+?)\1', r'<video[^>]+data-uuid=(["\'])(?P<id>.+?)\1', - r'mediaObjectId\s*:\s*(["\'])(?P<id>.+?)\1'), + r'mediaObjectId\s*:\s*(["\'])(?P<id>.+?)\1', + r'data-tab="share-media-(?P<id>[0-9A-F]{32})"'), webpage, 'media id', group='id') data = self._download_json( 'https://media.loc.gov/services/v1/media?id=%s&context=json' % media_id, - video_id)['mediaObject'] + media_id)['mediaObject'] derivative = data['derivatives'][0] media_url = derivative['derivativeUrl'] @@ -89,25 +96,29 @@ class LibraryOfCongressIE(InfoExtractor): if ext not in ('mp4', 'mp3'): media_url += '.mp4' if is_video else '.mp3' - if 'vod/mp4:' in media_url: - formats = [{ - 'url': media_url.replace('vod/mp4:', 'hls-vod/media/') + '.m3u8', + formats = [] + if '/vod/mp4:' in media_url: + formats.append({ + 'url': media_url.replace('/vod/mp4:', '/hls-vod/media/') + '.m3u8', 'format_id': 'hls', 'ext': 'mp4', 'protocol': 'm3u8_native', 'quality': 1, - }] - elif 'vod/mp3:' in media_url: - formats = [{ - 'url': media_url.replace('vod/mp3:', ''), - 'vcodec': 'none', - }] + }) + http_format = { + 'url': re.sub(r'(://[^/]+/)(?:[^/]+/)*(?:mp4|mp3):', r'\1', media_url), + 'format_id': 'http', + 'quality': 1, + } + if not is_video: + http_format['vcodec'] = 'none' + formats.append(http_format) download_urls = set() for m in re.finditer( r'<option[^>]+value=(["\'])(?P<url>.+?)\1[^>]+data-file-download=[^>]+>\s*(?P<id>.+?)(?:(?: |\s+)\((?P<size>.+?)\))?\s*<', webpage): format_id = m.group('id').lower() - if format_id == 'gif': + if format_id in ('gif', 'jpeg'): continue download_url = m.group('url') if download_url in download_urls: From 35328915b5fe5c8915b924cfbc54bbdd6d6d1430 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 21 Nov 2018 09:46:13 +0100 Subject: [PATCH 317/558] [foxsports] fix extraction(closes #17543) --- youtube_dl/extractor/foxsports.py | 17 +++-------------- youtube_dl/extractor/theplatform.py | 5 +++-- 2 files changed, 6 insertions(+), 16 deletions(-) diff --git a/youtube_dl/extractor/foxsports.py b/youtube_dl/extractor/foxsports.py index 985542727..596fded20 100644 --- a/youtube_dl/extractor/foxsports.py +++ b/youtube_dl/extractor/foxsports.py @@ -8,7 +8,7 @@ from ..utils import ( class FoxSportsIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?foxsports\.com/(?:[^/]+/)*(?P<id>[^/]+)' + _VALID_URL = r'https?://(?:www\.)?foxsports\.com/(?:[^/]+/)*video/(?P<id>\d+)' _TEST = { 'url': 'http://www.foxsports.com/tennessee/video/432609859715', @@ -28,16 +28,5 @@ class FoxSportsIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - config = self._parse_json( - self._html_search_regex( - r"""class="[^"]*(?:fs-player|platformPlayer-wrapper)[^"]*".+?data-player-config='([^']+)'""", - webpage, 'data player config'), - video_id) - - return self.url_result(smuggle_url(update_url_query( - config['releaseURL'], { - 'mbr': 'true', - 'switch': 'http', - }), {'force_smil_url': True})) + return self.url_result( + 'https://feed.theplatform.com/f/BKQ29B/foxsports-all?byId=' + video_id, 'ThePlatformFeed') diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index 181620615..90b351cbb 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -343,7 +343,7 @@ class ThePlatformFeedIE(ThePlatformBaseIE): def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}, account_id=None): real_url = self._URL_TEMPLATE % (self.http_scheme(), provider_id, feed_id, filter_query) entry = self._download_json(real_url, video_id)['entries'][0] - main_smil_url = 'http://link.theplatform.com/s/%s/media/guid/%d/%s' % (provider_id, account_id, entry['guid']) if account_id else None + main_smil_url = 'http://link.theplatform.com/s/%s/media/guid/%d/%s' % (provider_id, account_id, entry['guid']) if account_id else entry.get('plmedia$publicUrl') formats = [] subtitles = {} @@ -356,7 +356,8 @@ class ThePlatformFeedIE(ThePlatformBaseIE): if first_video_id is None: first_video_id = cur_video_id duration = float_or_none(item.get('plfile$duration')) - for asset_type in item['plfile$assetTypes']: + file_asset_types = item.get('plfile$assetTypes') or compat_parse_qs(compat_urllib_parse_urlparse(smil_url).query)['assetTypes'] + for asset_type in file_asset_types: if asset_type in asset_types: continue asset_types.append(asset_type) From 4e33e0792a3e134b494bd71f257a674294cca8d9 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 21 Nov 2018 12:00:50 +0100 Subject: [PATCH 318/558] [loc] update test --- youtube_dl/extractor/libraryofcongress.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/youtube_dl/extractor/libraryofcongress.py b/youtube_dl/extractor/libraryofcongress.py index 1e5c82c66..03f205144 100644 --- a/youtube_dl/extractor/libraryofcongress.py +++ b/youtube_dl/extractor/libraryofcongress.py @@ -20,12 +20,11 @@ class LibraryOfCongressIE(InfoExtractor): _TESTS = [{ # embedded via <div class="media-player" 'url': 'http://loc.gov/item/90716351/', - 'md5': '353917ff7f0255aa6d4b80a034833de8', + 'md5': '6ec0ae8f07f86731b1b2ff70f046210a', 'info_dict': { 'id': '90716351', 'ext': 'mp4', 'title': "Pa's trip to Mars", - 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 0, 'view_count': int, }, From 6866f2449437eeb0ad93b80e5bf39cf758af7a26 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 21 Nov 2018 12:08:46 +0100 Subject: [PATCH 319/558] [foxsports] update test --- youtube_dl/extractor/foxsports.py | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/foxsports.py b/youtube_dl/extractor/foxsports.py index 596fded20..2b2cb6c6f 100644 --- a/youtube_dl/extractor/foxsports.py +++ b/youtube_dl/extractor/foxsports.py @@ -1,10 +1,6 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import ( - smuggle_url, - update_url_query, -) class FoxSportsIE(InfoExtractor): @@ -14,14 +10,19 @@ class FoxSportsIE(InfoExtractor): 'url': 'http://www.foxsports.com/tennessee/video/432609859715', 'md5': 'b49050e955bebe32c301972e4012ac17', 'info_dict': { - 'id': 'bwduI3X_TgUB', + 'id': '432609859715', 'ext': 'mp4', 'title': 'Courtney Lee on going up 2-0 in series vs. Blazers', 'description': 'Courtney Lee talks about Memphis being focused.', - 'upload_date': '20150423', - 'timestamp': 1429761109, + # TODO: fix timestamp + 'upload_date': '19700101', # '20150423', + # 'timestamp': 1429761109, 'uploader': 'NEWA-FNG-FOXSPORTS', }, + 'params': { + # m3u8 download + 'skip_download': True, + }, 'add_ie': ['ThePlatform'], } From a843464a7e0608b679651f913cbd9447a7b928c0 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 21 Nov 2018 12:10:06 +0100 Subject: [PATCH 320/558] [nbc] fix NBCNews article extraction(closes #16194) --- youtube_dl/extractor/nbc.py | 91 ++++++++----------------------------- 1 file changed, 19 insertions(+), 72 deletions(-) diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index 765c46fd2..3282f84ee 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -9,10 +9,8 @@ from .theplatform import ThePlatformIE from .adobepass import AdobePassIE from ..compat import compat_urllib_parse_unquote from ..utils import ( - find_xpath_attr, smuggle_url, try_get, - unescapeHTML, update_url_query, int_or_none, ) @@ -269,27 +267,14 @@ class CSNNEIE(InfoExtractor): class NBCNewsIE(ThePlatformIE): - _VALID_URL = r'''(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/ - (?:video/.+?/(?P<id>\d+)| - ([^/]+/)*(?:.*-)?(?P<mpx_id>[^/?]+)) - ''' + _VALID_URL = r'(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/([^/]+/)*(?:.*-)?(?P<id>[^/?]+)' _TESTS = [ - { - 'url': 'http://www.nbcnews.com/video/nbc-news/52753292', - 'md5': '47abaac93c6eaf9ad37ee6c4463a5179', - 'info_dict': { - 'id': '52753292', - 'ext': 'flv', - 'title': 'Crew emerges after four-month Mars food study', - 'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1', - }, - }, { 'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880', 'md5': 'af1adfa51312291a017720403826bb64', 'info_dict': { - 'id': 'p_tweet_snow_140529', + 'id': '269389891880', 'ext': 'mp4', 'title': 'How Twitter Reacted To The Snowden Interview', 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64', @@ -313,7 +298,7 @@ class NBCNewsIE(ThePlatformIE): 'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844', 'md5': '73135a2e0ef819107bbb55a5a9b2a802', 'info_dict': { - 'id': 'nn_netcast_150204', + 'id': '394064451844', 'ext': 'mp4', 'title': 'Nightly News with Brian Williams Full Broadcast (February 4)', 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5', @@ -326,7 +311,7 @@ class NBCNewsIE(ThePlatformIE): 'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456', 'md5': 'a49e173825e5fcd15c13fc297fced39d', 'info_dict': { - 'id': 'x_lon_vwhorn_150922', + 'id': '529953347624', 'ext': 'mp4', 'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up', 'description': 'md5:c8be487b2d80ff0594c005add88d8351', @@ -339,7 +324,7 @@ class NBCNewsIE(ThePlatformIE): 'url': 'http://www.today.com/video/see-the-aurora-borealis-from-space-in-stunning-new-nasa-video-669831235788', 'md5': '118d7ca3f0bea6534f119c68ef539f71', 'info_dict': { - 'id': 'tdy_al_space_160420', + 'id': '669831235788', 'ext': 'mp4', 'title': 'See the aurora borealis from space in stunning new NASA video', 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1', @@ -352,7 +337,7 @@ class NBCNewsIE(ThePlatformIE): 'url': 'http://www.msnbc.com/all-in-with-chris-hayes/watch/the-chaotic-gop-immigration-vote-314487875924', 'md5': '6d236bf4f3dddc226633ce6e2c3f814d', 'info_dict': { - 'id': 'n_hayes_Aimm_140801_272214', + 'id': '314487875924', 'ext': 'mp4', 'title': 'The chaotic GOP immigration vote', 'description': 'The Republican House votes on a border bill that has no chance of getting through the Senate or signed by the President and is drawing criticism from all sides.', @@ -374,60 +359,22 @@ class NBCNewsIE(ThePlatformIE): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - if video_id is not None: - all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id) - info = all_info.find('video') - - return { - 'id': video_id, - 'title': info.find('headline').text, - 'ext': 'flv', - 'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text, - 'description': info.find('caption').text, - 'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text, - } - else: - # "feature" and "nightly-news" pages use theplatform.com - video_id = mobj.group('mpx_id') + video_id = self._match_id(url) + if not video_id.isdigit(): webpage = self._download_webpage(url, video_id) - filter_param = 'byId' - bootstrap_json = self._search_regex( - [r'(?m)(?:var\s+(?:bootstrapJson|playlistData)|NEWS\.videoObj)\s*=\s*({.+});?\s*$', - r'videoObj\s*:\s*({.+})', r'data-video="([^"]+)"', - r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);'], - webpage, 'bootstrap json', default=None) - if bootstrap_json: - bootstrap = self._parse_json( - bootstrap_json, video_id, transform_source=unescapeHTML) + data = self._parse_json(self._search_regex( + r'window\.__data\s*=\s*({.+});', webpage, + 'bootstrap json'), video_id) + video_id = data['article']['content'][0]['primaryMedia']['video']['mpxMetadata']['id'] - info = None - if 'results' in bootstrap: - info = bootstrap['results'][0]['video'] - elif 'video' in bootstrap: - info = bootstrap['video'] - elif 'msnbcVideoInfo' in bootstrap: - info = bootstrap['msnbcVideoInfo']['meta'] - elif 'msnbcThePlatform' in bootstrap: - info = bootstrap['msnbcThePlatform']['videoPlayer']['video'] - else: - info = bootstrap - - if 'guid' in info: - video_id = info['guid'] - filter_param = 'byGuid' - elif 'mpxId' in info: - video_id = info['mpxId'] - - return { - '_type': 'url_transparent', - 'id': video_id, - # http://feed.theplatform.com/f/2E2eJC/nbcnews also works - 'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {filter_param: video_id}), - 'ie_key': 'ThePlatformFeed', - } + return { + '_type': 'url_transparent', + 'id': video_id, + # http://feed.theplatform.com/f/2E2eJC/nbcnews also works + 'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {'byId': video_id}), + 'ie_key': 'ThePlatformFeed', + } class NBCOlympicsIE(InfoExtractor): From af60e81e3c557ace943aab35c1364d3d03d5a3bf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 22 Nov 2018 02:00:38 +0700 Subject: [PATCH 321/558] [setup.py] Add more relevant classifiers --- setup.py | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/setup.py b/setup.py index 7dbb5805f..a1a08f1e2 100644 --- a/setup.py +++ b/setup.py @@ -124,6 +124,8 @@ setup( 'Development Status :: 5 - Production/Stable', 'Environment :: Console', 'License :: Public Domain', + 'Programming Language :: Python', + 'Programming Language :: Python :: 2', 'Programming Language :: Python :: 2.6', 'Programming Language :: Python :: 2.7', 'Programming Language :: Python :: 3', @@ -132,6 +134,12 @@ setup( 'Programming Language :: Python :: 3.4', 'Programming Language :: Python :: 3.5', 'Programming Language :: Python :: 3.6', + 'Programming Language :: Python :: 3.7', + 'Programming Language :: Python :: Implementation', + 'Programming Language :: Python :: Implementation :: CPython', + 'Programming Language :: Python :: Implementation :: IronPython', + 'Programming Language :: Python :: Implementation :: Jython', + 'Programming Language :: Python :: Implementation :: PyPy', ], cmdclass={'build_lazy_extractors': build_lazy_extractors}, From bd2d553c7b1529f793c2b7343c514a558543fc0d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 22 Nov 2018 02:01:22 +0700 Subject: [PATCH 322/558] [travis] Add python 3.7 build --- .travis.yml | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/.travis.yml b/.travis.yml index 92f326860..1ea640071 100644 --- a/.travis.yml +++ b/.travis.yml @@ -15,6 +15,12 @@ env: - YTDL_TEST_SET=download matrix: include: + - python: 3.7 + dist: xenial + env: YTDL_TEST_SET=core + - python: 3.7 + dist: xenial + env: YTDL_TEST_SET=download - env: JYTHON=true; YTDL_TEST_SET=core - env: JYTHON=true; YTDL_TEST_SET=download fast_finish: true From 157eef3e635230cbba0dd0c74f7115029867533e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 22 Nov 2018 02:08:41 +0700 Subject: [PATCH 323/558] [setup.py] Add python 3.8 classifier --- setup.py | 1 + 1 file changed, 1 insertion(+) diff --git a/setup.py b/setup.py index a1a08f1e2..dfb669ad2 100644 --- a/setup.py +++ b/setup.py @@ -135,6 +135,7 @@ setup( 'Programming Language :: Python :: 3.5', 'Programming Language :: Python :: 3.6', 'Programming Language :: Python :: 3.7', + 'Programming Language :: Python :: 3.8', 'Programming Language :: Python :: Implementation', 'Programming Language :: Python :: Implementation :: CPython', 'Programming Language :: Python :: Implementation :: IronPython', From 305ce767d586e8796d873270abf771e69ff5586c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 22 Nov 2018 02:34:35 +0700 Subject: [PATCH 324/558] [travis] Add python 3.8-dev build --- .travis.yml | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/.travis.yml b/.travis.yml index 1ea640071..79287ccf6 100644 --- a/.travis.yml +++ b/.travis.yml @@ -21,6 +21,12 @@ matrix: - python: 3.7 dist: xenial env: YTDL_TEST_SET=download + - python: 3.8-dev + dist: xenial + env: YTDL_TEST_SET=core + - python: 3.8-dev + dist: xenial + env: YTDL_TEST_SET=download - env: JYTHON=true; YTDL_TEST_SET=core - env: JYTHON=true; YTDL_TEST_SET=download fast_finish: true From 560020da3049bec19e5714e9e24fc90fadd06582 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 21 Nov 2018 23:19:46 +0100 Subject: [PATCH 325/558] [mixcloud] fallback to hardcoded decryption key(closes #18016) --- youtube_dl/extractor/mixcloud.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index b7bccb504..a2d19d3ef 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -161,11 +161,17 @@ class MixcloudIE(InfoExtractor): stream_info = info_json['streamInfo'] formats = [] + def decrypt_url(f_url): + for k in (key, 'IFYOUWANTTHEARTISTSTOGETPAIDDONOTDOWNLOADFROMMIXCLOUD'): + decrypted_url = self._decrypt_xor_cipher(k, compat_b64decode(f_url)) + if re.search(r'^https?://[0-9a-z.]+/[0-9A-Za-z/.?=&_-]+$', decrypted_url): + return decrypted_url + for url_key in ('url', 'hlsUrl', 'dashUrl'): format_url = stream_info.get(url_key) if not format_url: continue - decrypted = self._decrypt_xor_cipher(key, compat_b64decode(format_url)) + decrypted = decrypt_url(format_url) if not decrypted: continue if url_key == 'hlsUrl': From 6f2883a2df45ca89d272bc8a0975f09758af5eb3 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 21 Nov 2018 23:25:38 +0100 Subject: [PATCH 326/558] [mixcloud] base64 decode before decryption --- youtube_dl/extractor/mixcloud.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index a2d19d3ef..bcac13ec5 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -163,7 +163,7 @@ class MixcloudIE(InfoExtractor): def decrypt_url(f_url): for k in (key, 'IFYOUWANTTHEARTISTSTOGETPAIDDONOTDOWNLOADFROMMIXCLOUD'): - decrypted_url = self._decrypt_xor_cipher(k, compat_b64decode(f_url)) + decrypted_url = self._decrypt_xor_cipher(k, f_url) if re.search(r'^https?://[0-9a-z.]+/[0-9A-Za-z/.?=&_-]+$', decrypted_url): return decrypted_url @@ -171,7 +171,7 @@ class MixcloudIE(InfoExtractor): format_url = stream_info.get(url_key) if not format_url: continue - decrypted = decrypt_url(format_url) + decrypted = decrypt_url(compat_b64decode(format_url)) if not decrypted: continue if url_key == 'hlsUrl': From 66173211c4177d36612486acfd99fc4634b8004e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 23 Nov 2018 00:14:43 +0700 Subject: [PATCH 327/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/ChangeLog b/ChangeLog index 0083c4631..beb002041 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,23 @@ +version <unreleased> + +Core ++ [setup.py] Add more relevant classifiers + +Extractors +* [mixcloud] Fallback to hardcoded decryption key (#18016) +* [nbc:news] Fix article extraction (#16194) +* [foxsports] Fix extraction (#17543) +* [loc] Relax regular expression and improve formats extraction ++ [ciscolive] Add support for ciscolive.cisco.com (#17984) +* [nzz] Relax kaltura regex (#18228) +* [sixplay] Fix formats extraction +* [bitchute] Improve title extraction +* [kaltura] Limit requested MediaEntry fields ++ [americastestkitchen] Add support for zype embeds (#18225) ++ [pornhub] Add pornhub.net alias +* [nova:embed] Fix extraction (#18222) + + version 2018.11.18 Extractors From d861a9d5814408973e0715bb9160fb7db34fbcd0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 23 Nov 2018 00:16:45 +0700 Subject: [PATCH 328/558] release 2018.11.23 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 2 ++ youtube_dl/version.py | 2 +- 4 files changed, 7 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 905576364..35cc8d6d0 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.11.18*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.11.18** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.11.23*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.11.23** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.11.18 +[debug] youtube-dl version 2018.11.23 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index beb002041..f82c7ea35 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.11.23 Core + [setup.py] Add more relevant classifiers diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 9009f7e9e..7d72ad82d 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -163,6 +163,8 @@ - **chirbit** - **chirbit:profile** - **Cinchcast** + - **CiscoLiveSearch** + - **CiscoLiveSession** - **CJSW** - **cliphunter** - **Clippit** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 7f5ad7bf4..4956365d0 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.11.18' +__version__ = '2018.11.23' From 6864855eb111dbf6e0efe9ed086f48efa1d9f209 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 23 Nov 2018 00:43:42 +0700 Subject: [PATCH 329/558] [tests] Fix invalid escape sequences --- test/test_compat.py | 2 +- test/test_postprocessors.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/test/test_compat.py b/test/test_compat.py index d6c54e135..51fe6aa0b 100644 --- a/test/test_compat.py +++ b/test/test_compat.py @@ -39,7 +39,7 @@ class TestCompat(unittest.TestCase): def test_compat_expanduser(self): old_home = os.environ.get('HOME') - test_str = 'C:\Documents and Settings\тест\Application Data' + test_str = r'C:\Documents and Settings\тест\Application Data' compat_setenv('HOME', test_str) self.assertEqual(compat_expanduser('~'), test_str) compat_setenv('HOME', old_home or '') diff --git a/test/test_postprocessors.py b/test/test_postprocessors.py index addb69d6f..4209d1d9a 100644 --- a/test/test_postprocessors.py +++ b/test/test_postprocessors.py @@ -14,4 +14,4 @@ from youtube_dl.postprocessor import MetadataFromTitlePP class TestMetadataFromTitle(unittest.TestCase): def test_format_to_regex(self): pp = MetadataFromTitlePP(None, '%(title)s - %(artist)s') - self.assertEqual(pp._titleregex, '(?P<title>.+)\ \-\ (?P<artist>.+)') + self.assertEqual(pp._titleregex, r'(?P<title>.+)\ \-\ (?P<artist>.+)') From 641e86e3cf751f1050ca331b9d13152bd0e18558 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 24 Nov 2018 21:47:41 +0700 Subject: [PATCH 330/558] [wistia] Add support for fast.wistia.com (closes #18287) --- youtube_dl/extractor/wistia.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py index 2182d6fd4..01a51275e 100644 --- a/youtube_dl/extractor/wistia.py +++ b/youtube_dl/extractor/wistia.py @@ -12,7 +12,7 @@ from ..utils import ( class WistiaIE(InfoExtractor): - _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.net/embed/iframe/)(?P<id>[a-z0-9]+)' + _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/iframe/)(?P<id>[a-z0-9]+)' _API_URL = 'http://fast.wistia.com/embed/medias/%s.json' _IFRAME_URL = 'http://fast.wistia.net/embed/iframe/%s' @@ -35,12 +35,15 @@ class WistiaIE(InfoExtractor): # with hls video 'url': 'wistia:807fafadvk', 'only_matching': True, + }, { + 'url': 'http://fast.wistia.com/embed/iframe/sh7fpupwlt', + 'only_matching': True, }] @staticmethod def _extract_url(webpage): match = re.search( - r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage) + r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/iframe/.+?)\1', webpage) if match: return unescapeHTML(match.group('url')) From d19600df07128c73ef7242af7e1cd8c819951aba Mon Sep 17 00:00:00 2001 From: Alexander Seiler <seileralex@gmail.com> Date: Sat, 24 Nov 2018 16:14:27 +0100 Subject: [PATCH 331/558] [joj] Fix extraction (closes #18280) --- youtube_dl/extractor/joj.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/joj.py b/youtube_dl/extractor/joj.py index d9f8dbfd2..62b28e980 100644 --- a/youtube_dl/extractor/joj.py +++ b/youtube_dl/extractor/joj.py @@ -61,7 +61,7 @@ class JojIE(InfoExtractor): bitrates = self._parse_json( self._search_regex( - r'(?s)bitrates\s*=\s*({.+?});', webpage, 'bitrates', + r'(?s)(?:src|bitrates)\s*=\s*({.+?});', webpage, 'bitrates', default='{}'), video_id, transform_source=js_to_json, fatal=False) From ca01d178844129bd4b6ed74740fbd30e7f84c1c2 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 28 Nov 2018 19:53:22 +0100 Subject: [PATCH 332/558] [vimeo] Add support for VHX(Vimeo OTT)(#14835) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/vimeo.py | 85 +++++++++++++++++++++++++++++- 2 files changed, 85 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 60e6175b1..cd91c0fcb 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1303,6 +1303,7 @@ from .vimeo import ( VimeoReviewIE, VimeoUserIE, VimeoWatchLaterIE, + VHXEmbedIE, ) from .vimple import VimpleIE from .vine import ( diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 88f4d9979..6353c6831 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -14,10 +14,13 @@ from ..compat import ( from ..utils import ( determine_ext, ExtractorError, + js_to_json, InAdvancePagedList, int_or_none, merge_dicts, NO_DEFAULT, + parse_filesize, + qualities, RegexNotFoundError, sanitized_Request, smuggle_url, @@ -27,7 +30,6 @@ from ..utils import ( unsmuggle_url, urlencode_postdata, unescapeHTML, - parse_filesize, ) @@ -1063,3 +1065,84 @@ class VimeoLikesIE(InfoExtractor): 'description': description, 'entries': pl, } + + +class VHXEmbedIE(InfoExtractor): + IE_NAME = 'vhx:embed' + _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)' + + def _call_api(self, video_id, access_token, path='', query=None): + return self._download_json( + 'https://api.vhx.tv/videos/' + video_id + path, video_id, headers={ + 'Authorization': 'Bearer ' + access_token, + }, query=query) + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + credentials = self._parse_json(self._search_regex( + r'(?s)credentials\s*:\s*({.+?}),', webpage, + 'config'), video_id, js_to_json) + access_token = credentials['access_token'] + + query = {} + for k, v in credentials.items(): + if k in ('authorization', 'authUserToken', 'ticket') and v and v != 'undefined': + if k == 'authUserToken': + query['auth_user_token'] = v + else: + query[k] = v + files = self._call_api(video_id, access_token, '/files', query) + + formats = [] + for f in files: + href = try_get(f, lambda x: x['_links']['source']['href']) + if not href: + continue + method = f.get('method') + if method == 'hls': + formats.extend(self._extract_m3u8_formats( + href, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + elif method == 'dash': + formats.extend(self._extract_mpd_formats( + href, video_id, mpd_id='dash', fatal=False)) + else: + fmt = { + 'filesize': int_or_none(try_get(f, lambda x: x['size']['bytes'])), + 'format_id': 'http', + 'preference': 1, + 'url': href, + 'vcodec': f.get('codec'), + } + quality = f.get('quality') + if quality: + fmt.update({ + 'format_id': 'http-' + quality, + 'height': int_or_none(self._search_regex(r'(\d+)p', quality, 'height', default=None)), + }) + formats.append(fmt) + self._sort_formats(formats) + + video_data = self._call_api(video_id, access_token) + title = video_data.get('title') or video_data['name'] + + q = qualities(['small', 'medium', 'large', 'source']) + thumbnails = [] + for thumbnail_id, thumbnail_url in video_data.get('thumbnail', {}).items(): + thumbnails.append({ + 'id': thumbnail_id, + 'url': thumbnail_url, + 'preference': q(thumbnail_id), + }) + + return { + 'id': video_id, + 'title': title, + 'description': video_data.get('description'), + 'duration': int_or_none(try_get(video_data, lambda x: x['duration']['seconds'])), + 'formats': formats, + 'thumbnails': thumbnails, + 'timestamp': unified_timestamp(video_data.get('created_at')), + 'view_count': int_or_none(video_data.get('plays_count')), + } From d9df8f120b325766181fb474a8c534e51df78f17 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 28 Nov 2018 20:13:36 +0100 Subject: [PATCH 333/558] [vimeo] extract VHX subtitles --- youtube_dl/extractor/vimeo.py | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 6353c6831..5e15f060b 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -1127,6 +1127,17 @@ class VHXEmbedIE(InfoExtractor): video_data = self._call_api(video_id, access_token) title = video_data.get('title') or video_data['name'] + subtitles = {} + for subtitle in try_get(video_data, lambda x: x['tracks']['subtitles'], list) or []: + lang = subtitle.get('srclang') or subtitle.get('label') + for _link in subtitle.get('_links', {}).values(): + href = _link.get('href') + if not href: + continue + subtitles.setdefault(lang, []).append({ + 'url': href, + }) + q = qualities(['small', 'medium', 'large', 'source']) thumbnails = [] for thumbnail_id, thumbnail_url in video_data.get('thumbnail', {}).items(): @@ -1142,6 +1153,7 @@ class VHXEmbedIE(InfoExtractor): 'description': video_data.get('description'), 'duration': int_or_none(try_get(video_data, lambda x: x['duration']['seconds'])), 'formats': formats, + 'subtitles': subtitles, 'thumbnails': thumbnails, 'timestamp': unified_timestamp(video_data.get('created_at')), 'view_count': int_or_none(video_data.get('plays_count')), From 053e5b12b2e38b7d343aafbb7dc13fb8e4933015 Mon Sep 17 00:00:00 2001 From: Alexander Seiler <seileralex@gmail.com> Date: Thu, 29 Nov 2018 18:12:18 +0100 Subject: [PATCH 334/558] [azmedien] Fix extraction (closes #18334) --- youtube_dl/extractor/azmedien.py | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/azmedien.py b/youtube_dl/extractor/azmedien.py index a57a5f114..fcbdc71b9 100644 --- a/youtube_dl/extractor/azmedien.py +++ b/youtube_dl/extractor/azmedien.py @@ -36,7 +36,6 @@ class AZMedienIE(InfoExtractor): 'id': '1_anruz3wy', 'ext': 'mp4', 'title': 'Bundesrats-Vakanzen / EU-Rahmenabkommen', - 'description': 'md5:dd9f96751ec9c35e409a698a328402f3', 'uploader_id': 'TVOnline', 'upload_date': '20180930', 'timestamp': 1538328802, @@ -53,15 +52,12 @@ class AZMedienIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') video_id = mobj.group('id') entry_id = mobj.group('kaltura_id') if not entry_id: - webpage = self._download_webpage(url, video_id) - api_path = self._search_regex( - r'["\']apiPath["\']\s*:\s*["\']([^"^\']+)["\']', - webpage, 'api path') - api_url = 'https://www.%s%s' % (mobj.group('host'), api_path) + api_url = 'https://www.%s/api/pub/gql/%s' % (host, host.split('.')[0]) payload = { 'query': '''query VideoContext($articleId: ID!) { article: node(id: $articleId) { From adbbdefc8126a933d9ff0a6e603fb312e4b4cbdc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 30 Nov 2018 00:48:15 +0700 Subject: [PATCH 335/558] [hotstar] Add support for alternative app state layout (closes #18320) --- youtube_dl/extractor/hotstar.py | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/hotstar.py b/youtube_dl/extractor/hotstar.py index bf5717f1b..45aa5e7ea 100644 --- a/youtube_dl/extractor/hotstar.py +++ b/youtube_dl/extractor/hotstar.py @@ -43,6 +43,7 @@ class HotStarIE(HotStarBaseIE): IE_NAME = 'hotstar' _VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+?[/-])?(?P<id>\d{10})' _TESTS = [{ + # contentData 'url': 'https://www.hotstar.com/can-you-not-spread-rumours/1000076273', 'info_dict': { 'id': '1000076273', @@ -57,6 +58,10 @@ class HotStarIE(HotStarBaseIE): # m3u8 download 'skip_download': True, } + }, { + # contentDetail + 'url': 'https://www.hotstar.com/movies/radha-gopalam/1000057157', + 'only_matching': True, }, { 'url': 'http://www.hotstar.com/sports/cricket/rajitha-sizzles-on-debut-with-329/2001477583', 'only_matching': True, @@ -74,8 +79,12 @@ class HotStarIE(HotStarBaseIE): r'<script>window\.APP_STATE\s*=\s*({.+?})</script>', webpage, 'app state'), video_id) video_data = {} + getters = ( + lambda x, k=k: x['initialState']['content%s' % k]['content'] + for k in ('Data', 'Detail') + ) for v in app_state.values(): - content = try_get(v, lambda x: x['initialState']['contentData']['content'], dict) + content = try_get(v, getters, dict) if content and content.get('contentId') == video_id: video_data = content From 16597c2f9492651c55e01f441ee9cb5c276209cb Mon Sep 17 00:00:00 2001 From: Jimm Stout <jamesstout1@gmail.com> Date: Thu, 29 Nov 2018 13:07:07 -0500 Subject: [PATCH 336/558] [gfycat] Update API endpoint (closes #18333) --- youtube_dl/extractor/gfycat.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/gfycat.py b/youtube_dl/extractor/gfycat.py index a0670b645..c1b36a59b 100644 --- a/youtube_dl/extractor/gfycat.py +++ b/youtube_dl/extractor/gfycat.py @@ -53,7 +53,7 @@ class GfycatIE(InfoExtractor): video_id = self._match_id(url) gfy = self._download_json( - 'http://gfycat.com/cajax/get/%s' % video_id, + 'https://api.gfycat.com/v1/gfycats/%s' % video_id, video_id, 'Downloading video info') if 'error' in gfy: raise ExtractorError('Gfycat said: ' + gfy['error'], expected=True) From f012823082c893c0fc1f96afb8a91f5b1c1ae07a Mon Sep 17 00:00:00 2001 From: Hakim Boyles <hak@volkanite.net> Date: Thu, 29 Nov 2018 14:20:27 -0400 Subject: [PATCH 337/558] [lynda] Fix authentication (closes #18158) --- youtube_dl/extractor/lynda.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py index 4ba61cd8a..3084c6dff 100644 --- a/youtube_dl/extractor/lynda.py +++ b/youtube_dl/extractor/lynda.py @@ -15,7 +15,7 @@ from ..utils import ( class LyndaBaseIE(InfoExtractor): - _SIGNIN_URL = 'https://www.lynda.com/signin' + _SIGNIN_URL = 'https://www.lynda.com/signin/lynda' _PASSWORD_URL = 'https://www.lynda.com/signin/password' _USER_URL = 'https://www.lynda.com/signin/user' _ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to provide lynda.com account credentials.' From 3430ff9b07d4dc9dd39617af54aeffb381d88737 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 1 Dec 2018 16:45:51 +0700 Subject: [PATCH 338/558] [pornhub] Use actual URL host for requests (closes #18359) --- youtube_dl/extractor/pornhub.py | 34 +++++++++++++++++++-------------- 1 file changed, 20 insertions(+), 14 deletions(-) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index c9c884095..e377de196 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -27,7 +27,7 @@ class PornHubIE(InfoExtractor): _VALID_URL = r'''(?x) https?:// (?: - (?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| + (?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| (?:www\.)?thumbzilla\.com/video/ ) (?P<id>[\da-z]+) @@ -129,7 +129,7 @@ class PornHubIE(InfoExtractor): @staticmethod def _extract_urls(webpage): return re.findall( - r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/[\da-z]+)', + r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.(?:com|net)/embed/[\da-z]+)', webpage) def _extract_count(self, pattern, webpage, name): @@ -137,14 +137,16 @@ class PornHubIE(InfoExtractor): pattern, webpage, '%s count' % name, fatal=False)) def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') or 'pornhub.com' + video_id = mobj.group('id') - self._set_cookie('pornhub.com', 'age_verified', '1') + self._set_cookie(host, 'age_verified', '1') def dl_webpage(platform): - self._set_cookie('pornhub.com', 'platform', platform) + self._set_cookie(host, 'platform', platform) return self._download_webpage( - 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id, + 'http://www.%s/view_video.php?viewkey=%s' % (host, video_id), video_id, 'Downloading %s webpage' % platform) webpage = dl_webpage('pc') @@ -306,7 +308,7 @@ class PornHubIE(InfoExtractor): class PornHubPlaylistBaseIE(InfoExtractor): - def _extract_entries(self, webpage): + def _extract_entries(self, webpage, host): # Only process container div with main playlist content skipping # drop-down menu that uses similar pattern for videos (see # https://github.com/rg3/youtube-dl/issues/11594). @@ -316,7 +318,7 @@ class PornHubPlaylistBaseIE(InfoExtractor): return [ self.url_result( - 'http://www.pornhub.com/%s' % video_url, + 'http://www.%s/%s' % (host, video_url), PornHubIE.ie_key(), video_title=title) for video_url, title in orderedSet(re.findall( r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"', @@ -324,11 +326,13 @@ class PornHubPlaylistBaseIE(InfoExtractor): ] def _real_extract(self, url): - playlist_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') + playlist_id = mobj.group('id') webpage = self._download_webpage(url, playlist_id) - entries = self._extract_entries(webpage) + entries = self._extract_entries(webpage, host) playlist = self._parse_json( self._search_regex( @@ -343,7 +347,7 @@ class PornHubPlaylistBaseIE(InfoExtractor): class PornHubPlaylistIE(PornHubPlaylistBaseIE): - _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.(?:com|net)/playlist/(?P<id>\d+)' + _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/playlist/(?P<id>\d+)' _TESTS = [{ 'url': 'http://www.pornhub.com/playlist/4667351', 'info_dict': { @@ -358,7 +362,7 @@ class PornHubPlaylistIE(PornHubPlaylistBaseIE): class PornHubUserVideosIE(PornHubPlaylistBaseIE): - _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos' + _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos' _TESTS = [{ 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public', 'info_dict': { @@ -399,7 +403,9 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE): }] def _real_extract(self, url): - user_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') + user_id = mobj.group('id') entries = [] for page_num in itertools.count(1): @@ -411,7 +417,7 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE): if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: break raise - page_entries = self._extract_entries(webpage) + page_entries = self._extract_entries(webpage, host) if not page_entries: break entries.extend(page_entries) From aa374bc78e5e4dbb8453bd367ae0e3c0db702a7a Mon Sep 17 00:00:00 2001 From: Alexander Seiler <seileralex@gmail.com> Date: Sat, 1 Dec 2018 18:05:15 +0100 Subject: [PATCH 339/558] [utils] Fix random_birthday to generate existing dates only --- youtube_dl/utils.py | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index e84d35d4d..0b1c7cd6c 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -3948,8 +3948,12 @@ def write_xattr(path, key, value): def random_birthday(year_field, month_field, day_field): + start_date = datetime.date(1950, 1, 1) + end_date = datetime.date(1995, 12, 31) + offset = random.randint(0, (end_date - start_date).days) + random_date = start_date + datetime.timedelta(offset) return { - year_field: str(random.randint(1950, 1995)), - month_field: str(random.randint(1, 12)), - day_field: str(random.randint(1, 31)), + year_field: str(random_date.year), + month_field: str(random_date.month), + day_field: str(random_date.day), } From 1ead840d2c18d4add340117f676fd6694f0650d3 Mon Sep 17 00:00:00 2001 From: Ken Swenson <flat@esoteric.moe> Date: Fri, 9 Nov 2018 16:49:20 -0500 Subject: [PATCH 340/558] [tiktok] Add extractor (closes #18108) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/tiktok.py | 79 ++++++++++++++++++++++++++++++ 2 files changed, 80 insertions(+) create mode 100644 youtube_dl/extractor/tiktok.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index cd91c0fcb..547331078 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1124,6 +1124,7 @@ from .thisamericanlife import ThisAmericanLifeIE from .thisav import ThisAVIE from .thisoldhouse import ThisOldHouseIE from .threeqsdn import ThreeQSDNIE +from .tiktok import TikTokIE from .tinypic import TinyPicIE from .tmz import ( TMZIE, diff --git a/youtube_dl/extractor/tiktok.py b/youtube_dl/extractor/tiktok.py new file mode 100644 index 000000000..d71b09c66 --- /dev/null +++ b/youtube_dl/extractor/tiktok.py @@ -0,0 +1,79 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + compat_str, + int_or_none, + str_or_none, + try_get, + url_or_none, +) + + +class TikTokIE(InfoExtractor): + _VALID_URL = r'https?://(?:m\.)?tiktok\.com/v/(?P<id>[0-9]+)' + _TEST = { + 'url': 'https://m.tiktok.com/v/6606727368545406213.html', + 'md5': 'd584b572e92fcd48888051f238022420', + 'info_dict': { + 'id': '6606727368545406213', + 'ext': 'mp4', + 'title': 'Zureeal on TikTok', + 'thumbnail': r're:^https?://.*~noop.image', + 'description': '#bowsette#mario#cosplay#uk#lgbt#gaming#asian#bowsettecosplay', + 'uploader': 'Zureeal', + 'width': 540, + 'height': 960, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + data = self._parse_json( + self._search_regex( + r'var\s+data\s*=\s*({.+?});', webpage, 'data' + ), video_id) + + title = self._og_search_title(webpage) + + description = str_or_none(try_get(data, lambda x: x['desc'])) + width = int_or_none(try_get(data, lambda x: x['video']['width'])) + height = int_or_none(try_get(data, lambda x: x['video']['height'])) + + formats = [] + + for count, (key, label) in enumerate((('play_addr_lowbr', 'Low'), ('play_addr', 'Normal'), ('download_addr', 'Download')), -2): + for format in try_get(data, lambda x: x['video'][key]['url_list']): + format_url = url_or_none(format) + if not format_url: + continue + formats.append({ + 'url': format_url, + 'ext': 'mp4', + 'height': height, + 'width': width, + 'format_note': label, + 'quality': count + }) + + self._sort_formats(formats) + + uploader = try_get(data, lambda x: x['author']['nickname'], compat_str) + + thumbnail = url_or_none( + try_get( + data, lambda x: x['video']['cover']['url_list'][0], compat_str)) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'uploader': uploader, + 'formats': formats, + 'thumbnail': thumbnail, + 'width': width, + 'height': height, + } From ce18a19be9af1e227e7162636cbf6b277adc1b41 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 2 Dec 2018 02:39:22 +0700 Subject: [PATCH 341/558] [tiktok] Improve extraction and add support for user pages (closes #18135) --- youtube_dl/extractor/extractors.py | 5 +- youtube_dl/extractor/tiktok.py | 136 ++++++++++++++++++----------- 2 files changed, 91 insertions(+), 50 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 547331078..0baed6b27 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1124,7 +1124,10 @@ from .thisamericanlife import ThisAmericanLifeIE from .thisav import ThisAVIE from .thisoldhouse import ThisOldHouseIE from .threeqsdn import ThreeQSDNIE -from .tiktok import TikTokIE +from .tiktok import ( + TikTokIE, + TikTokUserIE, +) from .tinypic import TinyPicIE from .tmz import ( TMZIE, diff --git a/youtube_dl/extractor/tiktok.py b/youtube_dl/extractor/tiktok.py index d71b09c66..083e9f36d 100644 --- a/youtube_dl/extractor/tiktok.py +++ b/youtube_dl/extractor/tiktok.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( compat_str, + ExtractorError, int_or_none, str_or_none, try_get, @@ -11,69 +12,106 @@ from ..utils import ( ) -class TikTokIE(InfoExtractor): - _VALID_URL = r'https?://(?:m\.)?tiktok\.com/v/(?P<id>[0-9]+)' +class TikTokBaseIE(InfoExtractor): + def _extract_aweme(self, data): + video = data['video'] + description = str_or_none(try_get(data, lambda x: x['desc'])) + width = int_or_none(try_get(data, lambda x: video['width'])) + height = int_or_none(try_get(data, lambda x: video['height'])) + + format_urls = set() + formats = [] + for format_id in ( + 'play_addr_lowbr', 'play_addr', 'play_addr_h264', + 'download_addr'): + for format in try_get( + video, lambda x: x[format_id]['url_list'], list) or []: + format_url = url_or_none(format) + if not format_url: + continue + if format_url in format_urls: + continue + format_urls.add(format_url) + formats.append({ + 'url': format_url, + 'ext': 'mp4', + 'height': height, + 'width': width, + }) + self._sort_formats(formats) + + thumbnail = url_or_none(try_get( + video, lambda x: x['cover']['url_list'][0], compat_str)) + uploader = try_get(data, lambda x: x['author']['nickname'], compat_str) + timestamp = int_or_none(data.get('create_time')) + comment_count = int_or_none(data.get('comment_count')) or int_or_none( + try_get(data, lambda x: x['statistics']['comment_count'])) + repost_count = int_or_none(try_get( + data, lambda x: x['statistics']['share_count'])) + + aweme_id = data['aweme_id'] + + return { + 'id': aweme_id, + 'title': uploader or aweme_id, + 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'timestamp': timestamp, + 'comment_count': comment_count, + 'repost_count': repost_count, + 'formats': formats, + } + + +class TikTokIE(TikTokBaseIE): + _VALID_URL = r'https?://(?:m\.)?tiktok\.com/v/(?P<id>\d+)' _TEST = { 'url': 'https://m.tiktok.com/v/6606727368545406213.html', 'md5': 'd584b572e92fcd48888051f238022420', 'info_dict': { 'id': '6606727368545406213', 'ext': 'mp4', - 'title': 'Zureeal on TikTok', - 'thumbnail': r're:^https?://.*~noop.image', + 'title': 'Zureeal', 'description': '#bowsette#mario#cosplay#uk#lgbt#gaming#asian#bowsettecosplay', + 'thumbnail': r're:^https?://.*~noop.image', 'uploader': 'Zureeal', - 'width': 540, - 'height': 960, + 'timestamp': 1538248586, + 'upload_date': '20180929', + 'comment_count': int, + 'repost_count': int, } } def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + data = self._parse_json(self._search_regex( + r'\bdata\s*=\s*({.+?})\s*;', webpage, 'data'), video_id) + return self._extract_aweme(data) - data = self._parse_json( - self._search_regex( - r'var\s+data\s*=\s*({.+?});', webpage, 'data' - ), video_id) - title = self._og_search_title(webpage) +class TikTokUserIE(TikTokBaseIE): + _VALID_URL = r'https?://(?:m\.)?tiktok\.com/h5/share/usr/(?P<id>\d+)' + _TEST = { + 'url': 'https://m.tiktok.com/h5/share/usr/188294915489964032.html', + 'info_dict': { + 'id': '188294915489964032', + }, + 'playlist_mincount': 24, + } - description = str_or_none(try_get(data, lambda x: x['desc'])) - width = int_or_none(try_get(data, lambda x: x['video']['width'])) - height = int_or_none(try_get(data, lambda x: x['video']['height'])) - - formats = [] - - for count, (key, label) in enumerate((('play_addr_lowbr', 'Low'), ('play_addr', 'Normal'), ('download_addr', 'Download')), -2): - for format in try_get(data, lambda x: x['video'][key]['url_list']): - format_url = url_or_none(format) - if not format_url: - continue - formats.append({ - 'url': format_url, - 'ext': 'mp4', - 'height': height, - 'width': width, - 'format_note': label, - 'quality': count - }) - - self._sort_formats(formats) - - uploader = try_get(data, lambda x: x['author']['nickname'], compat_str) - - thumbnail = url_or_none( - try_get( - data, lambda x: x['video']['cover']['url_list'][0], compat_str)) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'uploader': uploader, - 'formats': formats, - 'thumbnail': thumbnail, - 'width': width, - 'height': height, - } + def _real_extract(self, url): + user_id = self._match_id(url) + data = self._download_json( + 'https://m.tiktok.com/h5/share/usr/list/%s/' % user_id, user_id, + query={'_signature': '_'}) + entries = [] + for aweme in data['aweme_list']: + try: + entry = self._extract_aweme(aweme) + except ExtractorError: + continue + entry['extractor_key'] = TikTokIE.ie_key() + entries.append(entry) + return self.playlist_result(entries, user_id) From 1fa59a928e48ac81e2afb5dfe134fa6c40f64e44 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 3 Dec 2018 00:06:54 +0700 Subject: [PATCH 342/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/ChangeLog b/ChangeLog index f82c7ea35..ddd4bec14 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,20 @@ +version <unreleased> + +Core +* [utils] Fix random_birthday to generate existing dates only (#18284) + +Extractors ++ [tiktok] Add support for tiktok.com (#18108, #18135) +* [pornhub] Use actual URL host for requests (#18359) +* [lynda] Fix authentication (#18158, #18217) +* [gfycat] Update API endpoint (#18333, #18343) ++ [hotstar] Add support for alternative app state layout (#18320) +* [azmedien] Fix extraction (#18334, #18336) ++ [vimeo] Add support for VHX (Vimeo OTT) (#14835) +* [joj] Fix extraction (#18280, #18281) ++ [wistia] Add support for fast.wistia.com (#18287) + + version 2018.11.23 Core From ab896fa894d2395b886e5bb8168ca0e0e6e9517d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 3 Dec 2018 00:10:20 +0700 Subject: [PATCH 343/558] release 2018.12.03 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 3 +++ youtube_dl/version.py | 2 +- 4 files changed, 8 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 35cc8d6d0..4b35244a8 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.11.23*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.11.23** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.12.03*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.12.03** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.11.23 +[debug] youtube-dl version 2018.12.03 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index ddd4bec14..689d07826 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2018.12.03 Core * [utils] Fix random_birthday to generate existing dates only (#18284) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 7d72ad82d..837b0199b 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -885,6 +885,8 @@ - **ThisAmericanLife** - **ThisAV** - **ThisOldHouse** + - **TikTok** + - **TikTokUser** - **tinypic**: tinypic.com videos - **TMZ** - **TMZArticle** @@ -979,6 +981,7 @@ - **VevoPlaylist** - **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet - **vh1.com** + - **vhx:embed** - **Viafree** - **vice** - **vice:article** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 4956365d0..8e1203892 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.11.23' +__version__ = '2018.12.03' From 5547014ad972a4364c4d4a613db6d3a18f25950e Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 2 Dec 2018 20:01:36 +0100 Subject: [PATCH 344/558] [gamespot] add support reviews URLs --- youtube_dl/extractor/gamespot.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py index ab647dd41..4236a5ed8 100644 --- a/youtube_dl/extractor/gamespot.py +++ b/youtube_dl/extractor/gamespot.py @@ -14,7 +14,7 @@ from ..utils import ( class GameSpotIE(OnceIE): - _VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article|review)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)' _TESTS = [{ 'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/', 'md5': 'b2a30deaa8654fcccd43713a6b6a4825', @@ -41,6 +41,9 @@ class GameSpotIE(OnceIE): }, { 'url': 'https://www.gamespot.com/articles/the-last-of-us-2-receives-new-ps4-trailer/1100-6454469/', 'only_matching': True, + }, { + 'url': 'https://www.gamespot.com/reviews/gears-of-war-review/1900-6161188/', + 'only_matching': True, }] def _real_extract(self, url): From 8bb0c9cc16b841ab89e15e620e00ee954ab316ed Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 5 Dec 2018 07:03:00 +0100 Subject: [PATCH 345/558] [tbs] fix info extraction(fixes #18403) --- youtube_dl/extractor/tbs.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/tbs.py b/youtube_dl/extractor/tbs.py index 784f8ed66..e8a7c65e0 100644 --- a/youtube_dl/extractor/tbs.py +++ b/youtube_dl/extractor/tbs.py @@ -16,7 +16,7 @@ from ..utils import ( class TBSIE(TurnerBaseIE): - _VALID_URL = r'https?://(?:www\.)?(?P<site>tbs|tntdrama)\.com/(?:movies|shows/[^/]+/(?:clips|season-\d+/episode-\d+))/(?P<id>[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?(?P<site>tbs|tntdrama)\.com(?P<path>/(?:movies|shows/[^/]+/(?:clips|season-\d+/episode-\d+))/(?P<id>[^/?#]+))' _TESTS = [{ 'url': 'http://www.tntdrama.com/shows/the-alienist/clips/monster', 'info_dict': { @@ -40,12 +40,12 @@ class TBSIE(TurnerBaseIE): }] def _real_extract(self, url): - site, display_id = re.match(self._VALID_URL, url).groups() + site, path, display_id = re.match(self._VALID_URL, url).groups() webpage = self._download_webpage(url, display_id) drupal_settings = self._parse_json(self._search_regex( r'<script[^>]+?data-drupal-selector="drupal-settings-json"[^>]*?>({.+?})</script>', webpage, 'drupal setting'), display_id) - video_data = drupal_settings['turner_playlist'][0] + video_data = next(v for v in drupal_settings['turner_playlist'] if v.get('url') == path) media_id = video_data['mediaID'] title = video_data['title'] From ae9d77dab54630ac480bd4082468d543a15c341e Mon Sep 17 00:00:00 2001 From: v-delta <45652398+v-delta@users.noreply.github.com> Date: Thu, 6 Dec 2018 17:24:35 +0100 Subject: [PATCH 346/558] [yourporn] Fix extraction (closes #18424) --- youtube_dl/extractor/yourporn.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/yourporn.py b/youtube_dl/extractor/yourporn.py index 6602f7c03..a9951f3b8 100644 --- a/youtube_dl/extractor/yourporn.py +++ b/youtube_dl/extractor/yourporn.py @@ -26,7 +26,7 @@ class YourPornIE(InfoExtractor): self._search_regex( r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info', group='data'), - video_id)[video_id]) + video_id)[video_id]).replace('/cdn/', '/cdn2/') title = (self._search_regex( r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title', From 33cc1ea586480ccc60fd25f2d42cfb44eec605c6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 7 Dec 2018 00:00:06 +0700 Subject: [PATCH 347/558] [nrktv] Relax _VALID_URL (closes #18304, closes #18387) --- youtube_dl/extractor/nrk.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index a231735fb..c5001ef48 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -248,7 +248,7 @@ class NRKTVIE(NRKBaseIE): _VALID_URL = r'''(?x) https?:// (?:tv|radio)\.nrk(?:super)?\.no/ - (?:serie/[^/]+|program)/ + (?:serie(?:/[^/]+){1,2}|program)/ (?![Ee]pisodes)%s (?:/\d{2}-\d{2}-\d{4})? (?:\#del=(?P<part_id>\d+))? @@ -362,6 +362,9 @@ class NRKTVIE(NRKBaseIE): }, { 'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#', 'only_matching': True, + }, { + 'url': 'https://tv.nrk.no/serie/lindmo/2018/MUHU11006318/avspiller', + 'only_matching': True, }] From 15699ec8b0a9cb8d519b721a5cb8199afe62fc3c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 7 Dec 2018 00:49:24 +0700 Subject: [PATCH 348/558] [nrktv:season,series] Fix extraction and update tests (closes #17159, closes #17258) --- youtube_dl/extractor/nrk.py | 68 +++++++++++++++++++++++-------------- 1 file changed, 43 insertions(+), 25 deletions(-) diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index c5001ef48..48bc6fd7a 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -211,13 +211,13 @@ class NRKIE(NRKBaseIE): _TESTS = [{ # video 'url': 'http://www.nrk.no/video/PS*150533', - 'md5': '2f7f6eeb2aacdd99885f355428715cfa', + 'md5': '706f34cdf1322577589e369e522b50ef', 'info_dict': { 'id': '150533', 'ext': 'mp4', 'title': 'Dompap og andre fugler i Piip-Show', 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f', - 'duration': 263, + 'duration': 262, } }, { # audio @@ -256,14 +256,14 @@ class NRKTVIE(NRKBaseIE): _API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no') _TESTS = [{ 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014', - 'md5': '4e9ca6629f09e588ed240fb11619922a', + 'md5': '9a167e54d04671eb6317a37b7bc8a280', 'info_dict': { 'id': 'MUHH48000314AA', 'ext': 'mp4', 'title': '20 spørsmål 23.05.2014', 'description': 'md5:bdea103bc35494c143c6a9acdd84887a', 'duration': 1741, - 'series': '20 spørsmål - TV', + 'series': '20 spørsmål', 'episode': '23.05.2014', }, }, { @@ -301,7 +301,7 @@ class NRKTVIE(NRKBaseIE): 'id': 'MSPO40010515AH', 'ext': 'mp4', 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 1)', - 'description': 'md5:c03aba1e917561eface5214020551b7a', + 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d', 'duration': 772, 'series': 'Tour de Ski', 'episode': '06.01.2015', @@ -314,7 +314,7 @@ class NRKTVIE(NRKBaseIE): 'id': 'MSPO40010515BH', 'ext': 'mp4', 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 2)', - 'description': 'md5:c03aba1e917561eface5214020551b7a', + 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d', 'duration': 6175, 'series': 'Tour de Ski', 'episode': '06.01.2015', @@ -326,7 +326,7 @@ class NRKTVIE(NRKBaseIE): 'info_dict': { 'id': 'MSPO40010515', 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015', - 'description': 'md5:c03aba1e917561eface5214020551b7a', + 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d', }, 'expected_warnings': ['Video is geo restricted'], }, { @@ -406,21 +406,35 @@ class NRKTVSerieBaseIE(InfoExtractor): def _extract_series(self, webpage, display_id, fatal=True): config = self._parse_json( self._search_regex( - r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>', webpage, 'config', - default='{}' if not fatal else NO_DEFAULT), + (r'INITIAL_DATA_*\s*=\s*({.+?})\s*;', + r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>'), + webpage, 'config', default='{}' if not fatal else NO_DEFAULT), display_id, fatal=False) if not config: return - return try_get(config, lambda x: x['series'], dict) + return try_get( + config, + (lambda x: x['initialState']['series'], lambda x: x['series']), + dict) + + def _extract_seasons(self, seasons): + if not isinstance(seasons, list): + return [] + entries = [] + for season in seasons: + entries.extend(self._extract_episodes(season)) + return entries def _extract_episodes(self, season): - entries = [] if not isinstance(season, dict): - return entries - episodes = season.get('episodes') - if not isinstance(episodes, list): - return entries - for episode in episodes: + return [] + return self._extract_entries(season.get('episodes')) + + def _extract_entries(self, entry_list): + if not isinstance(entry_list, list): + return [] + entries = [] + for episode in entry_list: nrk_id = episode.get('prfId') if not nrk_id or not isinstance(nrk_id, compat_str): continue @@ -465,7 +479,7 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE): _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)' _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)' _TESTS = [{ - # new layout + # new layout, seasons 'url': 'https://tv.nrk.no/serie/backstage', 'info_dict': { 'id': 'backstage', @@ -474,20 +488,21 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE): }, 'playlist_mincount': 60, }, { - # old layout + # new layout, instalments 'url': 'https://tv.nrk.no/serie/groenn-glede', 'info_dict': { 'id': 'groenn-glede', 'title': 'Grønn glede', 'description': 'md5:7576e92ae7f65da6993cf90ee29e4608', }, - 'playlist_mincount': 9, + 'playlist_mincount': 10, }, { - 'url': 'http://tv.nrksuper.no/serie/labyrint', + # old layout + 'url': 'https://tv.nrksuper.no/serie/labyrint', 'info_dict': { 'id': 'labyrint', 'title': 'Labyrint', - 'description': 'md5:58afd450974c89e27d5a19212eee7115', + 'description': 'md5:318b597330fdac5959247c9b69fdb1ec', }, 'playlist_mincount': 3, }, { @@ -520,11 +535,11 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE): description = try_get( series, lambda x: x['titles']['subtitle'], compat_str) entries = [] - for season in series['seasons']: - entries.extend(self._extract_episodes(season)) + entries.extend(self._extract_seasons(series.get('seasons'))) + entries.extend(self._extract_entries(series.get('instalments'))) return self.playlist_result(entries, series_id, title, description) - # Old layout (e.g. https://tv.nrk.no/serie/groenn-glede) + # Old layout (e.g. https://tv.nrksuper.no/serie/labyrint) entries = [ self.url_result( 'https://tv.nrk.no/program/Episodes/{series}/{season}'.format( @@ -536,6 +551,9 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE): 'seriestitle', webpage, 'title', default=None) or self._og_search_title( webpage, fatal=False) + if title: + title = self._search_regex( + r'NRK (?:Super )?TV\s*[-–]\s*(.+)', title, 'title', default=title) description = self._html_search_meta( 'series_description', webpage, @@ -596,7 +614,7 @@ class NRKPlaylistIE(NRKPlaylistBaseIE): 'title': 'Rivertonprisen til Karin Fossum', 'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.', }, - 'playlist_count': 5, + 'playlist_count': 2, }] def _extract_title(self, webpage): From c976873c5b2912c06ff53e5193640ee8627edee4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 7 Dec 2018 00:54:58 +0700 Subject: [PATCH 349/558] [nrktv:series] Add support for extra materials --- youtube_dl/extractor/nrk.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index 48bc6fd7a..072f920a9 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -537,6 +537,7 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE): entries = [] entries.extend(self._extract_seasons(series.get('seasons'))) entries.extend(self._extract_entries(series.get('instalments'))) + entries.extend(self._extract_episodes(series.get('extraMaterial'))) return self.playlist_result(entries, series_id, title, description) # Old layout (e.g. https://tv.nrksuper.no/serie/labyrint) From dfe0a3a9d2e07ac1e5ad221912d03b999ebb4d75 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 7 Dec 2018 03:27:11 +0700 Subject: [PATCH 350/558] [lecturio] Add extractor (closes #18405) --- youtube_dl/extractor/extractors.py | 4 + youtube_dl/extractor/lecturio.py | 186 +++++++++++++++++++++++++++++ 2 files changed, 190 insertions(+) create mode 100644 youtube_dl/extractor/lecturio.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 0baed6b27..e5f18a75d 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -553,6 +553,10 @@ from .lcp import ( ) from .learnr import LearnrIE from .lecture2go import Lecture2GoIE +from .lecturio import ( + LecturioIE, + LecturioCourseIE, +) from .leeco import ( LeIE, LePlaylistIE, diff --git a/youtube_dl/extractor/lecturio.py b/youtube_dl/extractor/lecturio.py new file mode 100644 index 000000000..62ff28e02 --- /dev/null +++ b/youtube_dl/extractor/lecturio.py @@ -0,0 +1,186 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + determine_ext, + extract_attributes, + ExtractorError, + float_or_none, + int_or_none, + str_or_none, + url_or_none, + urlencode_postdata, + urljoin, +) + + +class LecturioBaseIE(InfoExtractor): + _LOGIN_URL = 'https://app.lecturio.com/en/login' + _NETRC_MACHINE = 'lecturio' + + def _real_initialize(self): + self._login() + + def _login(self): + username, password = self._get_login_info() + if username is None: + return + + # Sets some cookies + _, urlh = self._download_webpage_handle( + self._LOGIN_URL, None, 'Downloading login popup') + + def is_logged(url_handle): + return self._LOGIN_URL not in compat_str(url_handle.geturl()) + + # Already logged in + if is_logged(urlh): + return + + login_form = { + 'signin[email]': username, + 'signin[password]': password, + 'signin[remember]': 'on', + } + + response, urlh = self._download_webpage_handle( + self._LOGIN_URL, None, 'Logging in', + data=urlencode_postdata(login_form)) + + # Logged in successfully + if is_logged(urlh): + return + + errors = self._html_search_regex( + r'(?s)<ul[^>]+class=["\']error_list[^>]+>(.+?)</ul>', response, + 'errors', default=None) + if errors: + raise ExtractorError('Unable to login: %s' % errors, expected=True) + raise ExtractorError('Unable to log in') + + +class LecturioIE(LecturioBaseIE): + _VALID_URL = r'https://app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.lecture' + _TEST = { + 'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos', + 'md5': 'f576a797a5b7a5e4e4bbdfc25a6a6870', + 'info_dict': { + 'id': '39634', + 'ext': 'mp4', + 'title': 'Important Concepts and Terms – Introduction to Microbiology', + }, + 'skip': 'Requires lecturio account credentials', + } + + _CC_LANGS = { + 'German': 'de', + 'English': 'en', + 'Spanish': 'es', + 'French': 'fr', + 'Polish': 'pl', + 'Russian': 'ru', + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage( + 'https://app.lecturio.com/en/lecture/%s/player.html' % display_id, + display_id) + + lecture_id = self._search_regex( + r'lecture_id\s*=\s*(?:L_)?(\d+)', webpage, 'lecture id') + + api_url = self._search_regex( + r'lectureDataLink\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, + 'api url', group='url') + + video = self._download_json(api_url, display_id) + + title = video['title'].strip() + + formats = [] + for format_ in video['content']['media']: + if not isinstance(format_, dict): + continue + file_ = format_.get('file') + if not file_: + continue + ext = determine_ext(file_) + if ext == 'smil': + # smil contains only broken RTMP formats anyway + continue + file_url = url_or_none(file_) + if not file_url: + continue + label = str_or_none(format_.get('label')) + filesize = int_or_none(format_.get('fileSize')) + formats.append({ + 'url': file_url, + 'format_id': label, + 'filesize': float_or_none(filesize, invscale=1000) + }) + self._sort_formats(formats) + + subtitles = {} + automatic_captions = {} + cc = self._parse_json( + self._search_regex( + r'subtitleUrls\s*:\s*({.+?})\s*,', webpage, 'subtitles', + default='{}'), display_id, fatal=False) + for cc_label, cc_url in cc.items(): + cc_url = url_or_none(cc_url) + if not cc_url: + continue + sub_dict = automatic_captions if 'auto-translated' in cc_label else subtitles + lang = self._search_regex( + r'/([a-z]{2})_', cc_url, 'lang', default=cc_label.split()[0]) + sub_dict.setdefault(self._CC_LANGS.get(lang, lang), []).append({ + 'url': cc_url, + }) + + return { + 'id': lecture_id, + 'title': title, + 'formats': formats, + 'subtitles': subtitles, + 'automatic_captions': automatic_captions, + } + + +class LecturioCourseIE(LecturioBaseIE): + _VALID_URL = r'https://app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.course' + _TEST = { + 'url': 'https://app.lecturio.com/medical-courses/microbiology-introduction.course#/', + 'info_dict': { + 'id': 'microbiology-introduction', + 'title': 'Microbiology: Introduction', + }, + 'playlist_count': 45, + 'skip': 'Requires lecturio account credentials', + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + entries = [] + for mobj in re.finditer( + r'(?s)<[^>]+\bdata-url=(["\'])(?:(?!\1).)+\.lecture\b[^>]+>', + webpage): + params = extract_attributes(mobj.group(0)) + lecture_url = urljoin(url, params.get('data-url')) + lecture_id = params.get('data-id') + entries.append(self.url_result( + lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id)) + + title = self._search_regex( + r'<span[^>]+class=["\']content-title[^>]+>([^<]+)', webpage, + 'title', default=None) + + return self.playlist_result(entries, display_id, title) From ebb0449049c198f04103502c95a13171b854d1c7 Mon Sep 17 00:00:00 2001 From: ealgase <mostdigitsofpi@gmail.com> Date: Thu, 6 Dec 2018 15:36:08 -0500 Subject: [PATCH 351/558] [xvideos] Switch to HTTPS (closes #18422) --- youtube_dl/extractor/xvideos.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py index efee95651..ec2d913fc 100644 --- a/youtube_dl/extractor/xvideos.py +++ b/youtube_dl/extractor/xvideos.py @@ -45,7 +45,7 @@ class XVideosIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage( - 'http://www.xvideos.com/video%s/' % video_id, video_id) + 'https://www.xvideos.com/video%s/' % video_id, video_id) mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage) if mobj: From 8c5879715f4d979b83c49d44a9094307247097ba Mon Sep 17 00:00:00 2001 From: Alexander Seiler <seileralex@gmail.com> Date: Thu, 6 Dec 2018 21:41:02 +0100 Subject: [PATCH 352/558] [ard:mediathek] Fix title and description extraction (closes #18349) --- youtube_dl/extractor/ard.py | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 6bf8f61eb..84e96f769 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -173,13 +173,18 @@ class ARDMediathekIE(InfoExtractor): title = self._html_search_regex( [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>', r'<meta name="dcterms\.title" content="(.*?)"/>', - r'<h4 class="headline">(.*?)</h4>'], + r'<h4 class="headline">(.*?)</h4>', + r'<title[^>]*>(.*?)'], webpage, 'title') description = self._html_search_meta( 'dcterms.abstract', webpage, 'description', default=None) if description is None: description = self._html_search_meta( - 'description', webpage, 'meta description') + 'description', webpage, 'meta description', default=None) + if description is None: + description = self._html_search_regex( + r'(.+?)

', + webpage, 'teaser text', default=None) # Thumbnail is sometimes not present. # It is in the mobile version, but that seems to use a different URL From c3c098dcf2826ab4d668a92c9137cca2c0c42a4f Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 7 Dec 2018 18:52:01 +0100 Subject: [PATCH 353/558] [hotstar] fix video data extraction(closes #18386) --- youtube_dl/extractor/hotstar.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/hotstar.py b/youtube_dl/extractor/hotstar.py index 45aa5e7ea..8de9c4faf 100644 --- a/youtube_dl/extractor/hotstar.py +++ b/youtube_dl/extractor/hotstar.py @@ -79,7 +79,7 @@ class HotStarIE(HotStarBaseIE): r'', webpage, 'app state'), video_id) video_data = {} - getters = ( + getters = list( lambda x, k=k: x['initialState']['content%s' % k]['content'] for k in ('Data', 'Detail') ) @@ -87,6 +87,7 @@ class HotStarIE(HotStarBaseIE): content = try_get(v, getters, dict) if content and content.get('contentId') == video_id: video_data = content + break title = video_data['title'] From 9235b5091cedcc21c8dc32d4b292340edeee4ed0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 8 Dec 2018 23:57:40 +0700 Subject: [PATCH 354/558] [iprima] Relax _VALID_URL (closes #18453) --- youtube_dl/extractor/iprima.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py index 1d58d6e85..11a6629d2 100644 --- a/youtube_dl/extractor/iprima.py +++ b/youtube_dl/extractor/iprima.py @@ -12,7 +12,7 @@ from ..utils import ( class IPrimaIE(InfoExtractor): - _VALID_URL = r'https?://(?:play|prima)\.iprima\.cz/(?:.+/)?(?P[^?#]+)' + _VALID_URL = r'https?://(?:play|prima|www)\.iprima\.cz/(?:[^/]+/)*(?P[^/?#&]+)' _GEO_BYPASS = False _TESTS = [{ @@ -41,6 +41,9 @@ class IPrimaIE(InfoExtractor): # iframe prima.iprima.cz 'url': 'https://prima.iprima.cz/porady/jak-se-stavi-sen/rodina-rathousova-praha', 'only_matching': True, + }, { + 'url': 'http://www.iprima.cz/filmy/desne-rande', + 'only_matching': True, }] def _real_extract(self, url): From 1d88b3e6e6e59e4b52305faf6c1bf1fd69c555ee Mon Sep 17 00:00:00 2001 From: aegamesi Date: Sat, 29 Apr 2017 22:56:33 -0700 Subject: [PATCH 355/558] [YoutubeDL] Recognize expires=0 as session cookies and send session cookies with requests --- youtube_dl/YoutubeDL.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 38ba43a97..2433f74f4 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -2300,7 +2300,13 @@ class YoutubeDL(object): self.cookiejar = compat_cookiejar.MozillaCookieJar( opts_cookiefile) if os.access(opts_cookiefile, os.R_OK): - self.cookiejar.load() + self.cookiejar.load(ignore_discard=True, ignore_expires=True) + # Force CookieJar to treat 'expires=0' cookies as session/discard cookies + # Fixes https://bugs.python.org/issue17164 + for cookie in self.cookiejar: + if cookie.expires == 0: + cookie.expires = None + cookie.discard = True cookie_processor = YoutubeDLCookieProcessor(self.cookiejar) if opts_proxy is not None: From 1bab3437046646da4ebe2b8e0c7fdc25aa1072ce Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 9 Dec 2018 06:00:32 +0700 Subject: [PATCH 356/558] [YoutubeDL] Introduce YoutubeDLCookieJar and clarify the rationale behind session cookies (closes #12929) --- youtube_dl/YoutubeDL.py | 12 +++--------- youtube_dl/utils.py | 28 ++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+), 9 deletions(-) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 2433f74f4..4493fd0e1 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -88,6 +88,7 @@ from .utils import ( version_tuple, write_json_file, write_string, + YoutubeDLCookieJar, YoutubeDLCookieProcessor, YoutubeDLHandler, ) @@ -558,7 +559,7 @@ class YoutubeDL(object): self.restore_console_title() if self.params.get('cookiefile') is not None: - self.cookiejar.save() + self.cookiejar.save(ignore_discard=True, ignore_expires=True) def trouble(self, message=None, tb=None): """Determine action to take when a download problem appears. @@ -2297,16 +2298,9 @@ class YoutubeDL(object): self.cookiejar = compat_cookiejar.CookieJar() else: opts_cookiefile = expand_path(opts_cookiefile) - self.cookiejar = compat_cookiejar.MozillaCookieJar( - opts_cookiefile) + self.cookiejar = YoutubeDLCookieJar(opts_cookiefile) if os.access(opts_cookiefile, os.R_OK): self.cookiejar.load(ignore_discard=True, ignore_expires=True) - # Force CookieJar to treat 'expires=0' cookies as session/discard cookies - # Fixes https://bugs.python.org/issue17164 - for cookie in self.cookiejar: - if cookie.expires == 0: - cookie.expires = None - cookie.discard = True cookie_processor = YoutubeDLCookieProcessor(self.cookiejar) if opts_proxy is not None: diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 0b1c7cd6c..62e769fd5 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -39,6 +39,7 @@ from .compat import ( compat_HTMLParser, compat_basestring, compat_chr, + compat_cookiejar, compat_ctypes_WINFUNCTYPE, compat_etree_fromstring, compat_expanduser, @@ -1139,6 +1140,33 @@ class YoutubeDLHTTPSHandler(compat_urllib_request.HTTPSHandler): req, **kwargs) +class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar): + def save(self, filename=None, ignore_discard=False, ignore_expires=False): + # Store session cookies with `expires` set to 0 instead of an empty + # string + for cookie in self: + if cookie.expires is None: + cookie.expires = 0 + compat_cookiejar.MozillaCookieJar.save(self, filename, ignore_discard, ignore_expires) + + def load(self, filename=None, ignore_discard=False, ignore_expires=False): + compat_cookiejar.MozillaCookieJar.load(self, filename, ignore_discard, ignore_expires) + # Session cookies are denoted by either `expires` field set to + # an empty string or 0. MozillaCookieJar only recognizes the former + # (see [1]). So we need force the latter to be recognized as session + # cookies on our own. + # Session cookies may be important for cookies-based authentication, + # e.g. usually, when user does not check 'Remember me' check box while + # logging in on a site, some important cookies are stored as session + # cookies so that not recognizing them will result in failed login. + # 1. https://bugs.python.org/issue17164 + for cookie in self: + # Treat `expires=0` cookies as session cookies + if cookie.expires == 0: + cookie.expires = None + cookie.discard = True + + class YoutubeDLCookieProcessor(compat_urllib_request.HTTPCookieProcessor): def __init__(self, cookiejar=None): compat_urllib_request.HTTPCookieProcessor.__init__(self, cookiejar) From 5f47a60c5d66d65b505131a672a3bad67ddaa00f Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sun, 9 Dec 2018 09:35:17 +0100 Subject: [PATCH 357/558] [imgur] improve gallery and album detection and extraction(closes #9133)(closes #16577)(closes #17223)(closes #18404) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/imgur.py | 86 +++++++++++++++--------------- 2 files changed, 44 insertions(+), 43 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index e5f18a75d..e28db6968 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -483,6 +483,7 @@ from .imdb import ( from .imgur import ( ImgurIE, ImgurAlbumIE, + ImgurGalleryIE, ) from .ina import InaIE from .inc import IncIE diff --git a/youtube_dl/extractor/imgur.py b/youtube_dl/extractor/imgur.py index ecc958a17..0eb54db3f 100644 --- a/youtube_dl/extractor/imgur.py +++ b/youtube_dl/extractor/imgur.py @@ -12,7 +12,7 @@ from ..utils import ( class ImgurIE(InfoExtractor): - _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:gallery|(?:topic|r)/[^/]+)/)?(?P[a-zA-Z0-9]{6,})(?:[/?#&]+|\.[a-z0-9]+)?$' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?!(?:a|gallery|(?:t(?:opic)?|r)/[^/]+)/)(?P[a-zA-Z0-9]+)' _TESTS = [{ 'url': 'https://i.imgur.com/A61SaA1.gifv', @@ -20,28 +20,9 @@ class ImgurIE(InfoExtractor): 'id': 'A61SaA1', 'ext': 'mp4', 'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$', - 'description': 'Imgur: The magic of the Internet', }, }, { 'url': 'https://imgur.com/A61SaA1', - 'info_dict': { - 'id': 'A61SaA1', - 'ext': 'mp4', - 'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$', - 'description': 'Imgur: The magic of the Internet', - }, - }, { - 'url': 'https://imgur.com/gallery/YcAQlkx', - 'info_dict': { - 'id': 'YcAQlkx', - 'ext': 'mp4', - 'title': 'Classic Steve Carell gif...cracks me up everytime....damn the repost downvotes....', - } - }, { - 'url': 'http://imgur.com/topic/Funny/N8rOudd', - 'only_matching': True, - }, { - 'url': 'http://imgur.com/r/aww/VQcQPhM', 'only_matching': True, }, { 'url': 'https://i.imgur.com/crGpqCV.mp4', @@ -50,8 +31,8 @@ class ImgurIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - gifv_url = 'https://i.imgur.com/{id}.gifv'.format(id=video_id) - webpage = self._download_webpage(gifv_url, video_id) + webpage = self._download_webpage( + 'https://i.imgur.com/{id}.gifv'.format(id=video_id), video_id) width = int_or_none(self._og_search_property( 'video:width', webpage, default=None)) @@ -72,7 +53,6 @@ class ImgurIE(InfoExtractor): 'format_id': m.group('type').partition('/')[2], 'url': self._proto_relative_url(m.group('src')), 'ext': mimetype2ext(m.group('type')), - 'acodec': 'none', 'width': width, 'height': height, 'http_headers': { @@ -107,44 +87,64 @@ class ImgurIE(InfoExtractor): return { 'id': video_id, 'formats': formats, - 'description': self._og_search_description(webpage, default=None), 'title': self._og_search_title(webpage), } -class ImgurAlbumIE(InfoExtractor): - _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:a|gallery|topic/[^/]+)/)?(?P[a-zA-Z0-9]{5})(?:[/?#&]+)?$' +class ImgurGalleryIE(InfoExtractor): + IE_NAME = 'imgur:gallery' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:gallery|(?:t(?:opic)?|r)/[^/]+)/(?P[a-zA-Z0-9]+)' _TESTS = [{ 'url': 'http://imgur.com/gallery/Q95ko', 'info_dict': { 'id': 'Q95ko', + 'title': 'Adding faces make every GIF better', }, 'playlist_count': 25, }, { - 'url': 'http://imgur.com/a/j6Orj', + 'url': 'http://imgur.com/topic/Aww/ll5Vk', 'only_matching': True, }, { - 'url': 'http://imgur.com/topic/Aww/ll5Vk', + 'url': 'https://imgur.com/gallery/YcAQlkx', + 'info_dict': { + 'id': 'YcAQlkx', + 'ext': 'mp4', + 'title': 'Classic Steve Carell gif...cracks me up everytime....damn the repost downvotes....', + } + }, { + 'url': 'http://imgur.com/topic/Funny/N8rOudd', + 'only_matching': True, + }, { + 'url': 'http://imgur.com/r/aww/VQcQPhM', 'only_matching': True, }] def _real_extract(self, url): - album_id = self._match_id(url) + gallery_id = self._match_id(url) - album_images = self._download_json( - 'http://imgur.com/gallery/%s/album_images/hit.json?all=true' % album_id, - album_id, fatal=False) + data = self._download_json( + 'https://imgur.com/gallery/%s.json' % gallery_id, + gallery_id)['data']['image'] - if album_images: - data = album_images.get('data') - if data and isinstance(data, dict): - images = data.get('images') - if images and isinstance(images, list): - entries = [ - self.url_result('http://imgur.com/%s' % image['hash']) - for image in images if image.get('hash')] - return self.playlist_result(entries, album_id) + if data.get('is_album'): + entries = [ + self.url_result('http://imgur.com/%s' % image['hash'], ImgurIE.ie_key(), image['hash']) + for image in data['album_images']['images'] if image.get('hash')] + return self.playlist_result(entries, gallery_id, data.get('title'), data.get('description')) - # Fallback to single video - return self.url_result('http://imgur.com/%s' % album_id, ImgurIE.ie_key()) + return self.url_result('http://imgur.com/%s' % gallery_id, ImgurIE.ie_key(), gallery_id) + + +class ImgurAlbumIE(ImgurGalleryIE): + IE_NAME = 'imgur:album' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/a/(?P[a-zA-Z0-9]+)' + + _TESTS = [{ + 'url': 'http://imgur.com/a/j6Orj', + 'info_dict': { + 'id': 'j6Orj', + 'title': 'A Literary Analysis of "Star Wars: The Force Awakens"', + }, + 'playlist_count': 12, + }] From 3ad6dabd33307c0125fd462c4988083e360c40ad Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sun, 9 Dec 2018 10:04:00 +0100 Subject: [PATCH 358/558] [aenetworks] add support for History Vault(closes #18460) --- youtube_dl/extractor/aenetworks.py | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/aenetworks.py b/youtube_dl/extractor/aenetworks.py index 398e56ea3..85ec6392d 100644 --- a/youtube_dl/extractor/aenetworks.py +++ b/youtube_dl/extractor/aenetworks.py @@ -22,18 +22,19 @@ class AENetworksBaseIE(ThePlatformIE): class AENetworksIE(AENetworksBaseIE): IE_NAME = 'aenetworks' - IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network' + IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault' _VALID_URL = r'''(?x) https?:// (?:www\.)? (?P - (?:history|aetv|mylifetime|lifetimemovieclub)\.com| + (?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com| fyi\.tv )/ (?: shows/(?P[^/]+(?:/[^/]+){0,2})| movies/(?P[^/]+)(?:/full-movie)?| - specials/(?P[^/]+)/full-special + specials/(?P[^/]+)/full-special| + collections/[^/]+/(?P[^/]+) ) ''' _TESTS = [{ @@ -80,6 +81,9 @@ class AENetworksIE(AENetworksBaseIE): }, { 'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special', 'only_matching': True + }, { + 'url': 'https://www.historyvault.com/collections/america-the-story-of-us/westward', + 'only_matching': True }] _DOMAIN_TO_REQUESTOR_ID = { 'history.com': 'HISTORY', @@ -90,9 +94,9 @@ class AENetworksIE(AENetworksBaseIE): } def _real_extract(self, url): - domain, show_path, movie_display_id, special_display_id = re.match(self._VALID_URL, url).groups() - display_id = show_path or movie_display_id or special_display_id - webpage = self._download_webpage(url, display_id) + domain, show_path, movie_display_id, special_display_id, collection_display_id = re.match(self._VALID_URL, url).groups() + display_id = show_path or movie_display_id or special_display_id or collection_display_id + webpage = self._download_webpage(url, display_id, headers=self.geo_verification_headers()) if show_path: url_parts = show_path.split('/') url_parts_len = len(url_parts) From 5ee7ae5c7577c9c137a7b38edd5ad01ae3a40376 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 9 Dec 2018 22:28:24 +0700 Subject: [PATCH 359/558] [teachable] Add support for teachable based platform sites (closes #5451, closes #18150, closes #18272) --- youtube_dl/extractor/extractors.py | 8 +- youtube_dl/extractor/generic.py | 5 + .../extractor/{upskill.py => teachable.py} | 129 ++++++++++++++---- 3 files changed, 115 insertions(+), 27 deletions(-) rename youtube_dl/extractor/{upskill.py => teachable.py} (52%) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index e28db6968..6a5d12ab1 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1091,6 +1091,10 @@ from .tass import TassIE from .tastytrade import TastyTradeIE from .tbs import TBSIE from .tdslifeway import TDSLifewayIE +from .teachable import ( + TeachableIE, + TeachableCourseIE, +) from .teachertube import ( TeacherTubeIE, TeacherTubeUserIE, @@ -1240,10 +1244,6 @@ from .uplynk import ( UplynkIE, UplynkPreplayIE, ) -from .upskill import ( - UpskillIE, - UpskillCourseIE, -) from .urort import UrortIE from .urplay import URPlayIE from .usanetwork import USANetworkIE diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 59cf03faf..65b482333 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -109,6 +109,7 @@ from .vice import ViceIE from .xfileshare import XFileShareIE from .cloudflarestream import CloudflareStreamIE from .peertube import PeerTubeIE +from .teachable import TeachableIE from .indavideo import IndavideoEmbedIE from .apa import APAIE from .foxnews import FoxNewsIE @@ -3112,6 +3113,10 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key()) + teachable_url = TeachableIE._extract_url(webpage, url) + if teachable_url: + return self.url_result(teachable_url) + indavideo_urls = IndavideoEmbedIE._extract_urls(webpage) if indavideo_urls: return self.playlist_from_matches( diff --git a/youtube_dl/extractor/upskill.py b/youtube_dl/extractor/teachable.py similarity index 52% rename from youtube_dl/extractor/upskill.py rename to youtube_dl/extractor/teachable.py index 30297b4dd..a0c46b2e6 100644 --- a/youtube_dl/extractor/upskill.py +++ b/youtube_dl/extractor/teachable.py @@ -14,20 +14,38 @@ from ..utils import ( ) -class UpskillBaseIE(InfoExtractor): - _LOGIN_URL = 'http://upskillcourses.com/sign_in' - _NETRC_MACHINE = 'upskill' +class TeachableBaseIE(InfoExtractor): + _NETRC_MACHINE = 'teachable' + _URL_PREFIX = 'teachable:' + + _SITES = { + # Only notable ones here + 'upskillcourses.com': 'upskill', + 'academy.gns3.com': 'gns3', + 'academyhacker.com': 'academyhacker', + 'stackskills.com': 'stackskills', + 'market.saleshacker.com': 'saleshacker', + 'learnability.org': 'learnability', + 'edurila.com': 'edurila', + } + + _VALID_URL_SUB_TUPLE = (_URL_PREFIX, '|'.join(re.escape(site) for site in _SITES.keys())) def _real_initialize(self): - self._login() + self._logged_in = False - def _login(self): - username, password = self._get_login_info() + def _login(self, site): + if self._logged_in: + return + + username, password = self._get_login_info( + netrc_machine=self._SITES.get(site, site)) if username is None: return login_page, urlh = self._download_webpage_handle( - self._LOGIN_URL, None, 'Downloading login page') + 'https://%s/sign_in' % site, None, + 'Downloading %s login page' % site) login_url = compat_str(urlh.geturl()) @@ -46,18 +64,24 @@ class UpskillBaseIE(InfoExtractor): post_url = urljoin(login_url, post_url) response = self._download_webpage( - post_url, None, 'Logging in', + post_url, None, 'Logging in to %s' % site, data=urlencode_postdata(login_form), headers={ 'Content-Type': 'application/x-www-form-urlencoded', 'Referer': login_url, }) + if '>I accept the new Privacy Policy<' in response: + raise ExtractorError( + 'Unable to login: %s asks you to accept new Privacy Policy. ' + 'Go to https://%s/ and accept.' % (site, site), expected=True) + # Successful login if any(re.search(p, response) for p in ( r'class=["\']user-signout', r']+\bhref=["\']/sign_out', r'>\s*Log out\s*<')): + self._logged_in = True return message = get_element_by_class('alert', response) @@ -68,8 +92,14 @@ class UpskillBaseIE(InfoExtractor): raise ExtractorError('Unable to log in') -class UpskillIE(UpskillBaseIE): - _VALID_URL = r'https?://(?:www\.)?upskillcourses\.com/courses/[^/]+/lectures/(?P\d+)' +class TeachableIE(TeachableBaseIE): + _VALID_URL = r'''(?x) + (?: + %shttps?://(?P[^/]+)| + https?://(?:www\.)?(?P%s) + ) + /courses/[^/]+/lectures/(?P\d+) + ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE _TESTS = [{ 'url': 'http://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100', @@ -77,7 +107,7 @@ class UpskillIE(UpskillBaseIE): 'id': 'uzw6zw58or', 'ext': 'mp4', 'title': 'Welcome to the Course!', - 'description': 'md5:8d66c13403783370af62ca97a7357bdd', + 'description': 'md5:65edb0affa582974de4625b9cdea1107', 'duration': 138.763, 'timestamp': 1479846621, 'upload_date': '20161122', @@ -88,10 +118,38 @@ class UpskillIE(UpskillBaseIE): }, { 'url': 'http://upskillcourses.com/courses/119763/lectures/1747100', 'only_matching': True, + }, { + 'url': 'https://academy.gns3.com/courses/423415/lectures/6885939', + 'only_matching': True, + }, { + 'url': 'teachable:https://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100', + 'only_matching': True, }] + @staticmethod + def _is_teachable(webpage): + return 'teachableTracker.linker:autoLink' in webpage and re.search( + r']+href=["\']https?://process\.fs\.teachablecdn\.com', + webpage) + + @staticmethod + def _extract_url(webpage, source_url): + if not TeachableIE._is_teachable(webpage): + print('NOT TEACHABLE') + return + if re.match(r'https?://[^/]+/(?:courses|p)', source_url): + return '%s%s' % (TeachableBaseIE._URL_PREFIX, source_url) + def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + site = mobj.group('site') or mobj.group('site_t') + video_id = mobj.group('id') + + self._login(site) + + prefixed = url.startswith(self._URL_PREFIX) + if prefixed: + url = url[len(self._URL_PREFIX):] webpage = self._download_webpage(url, video_id) @@ -113,12 +171,18 @@ class UpskillIE(UpskillBaseIE): } -class UpskillCourseIE(UpskillBaseIE): - _VALID_URL = r'https?://(?:www\.)?upskillcourses\.com/courses/(?:enrolled/)?(?P[^/?#&]+)' +class TeachableCourseIE(TeachableBaseIE): + _VALID_URL = r'''(?x) + (?: + %shttps?://(?P[^/]+)| + https?://(?:www\.)?(?P%s) + ) + /(?:courses|p)/(?:enrolled/)?(?P[^/?#&]+) + ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE _TESTS = [{ 'url': 'http://upskillcourses.com/courses/essential-web-developer-course/', 'info_dict': { - 'id': '119763', + 'id': 'essential-web-developer-course', 'title': 'The Essential Web Developer Course (Free)', }, 'playlist_count': 192, @@ -128,21 +192,37 @@ class UpskillCourseIE(UpskillBaseIE): }, { 'url': 'http://upskillcourses.com/courses/enrolled/119763', 'only_matching': True, + }, { + 'url': 'https://academy.gns3.com/courses/enrolled/423415', + 'only_matching': True, + }, { + 'url': 'teachable:https://learn.vrdev.school/p/gear-vr-developer-mini', + 'only_matching': True, + }, { + 'url': 'teachable:https://filmsimplified.com/p/davinci-resolve-15-crash-course', + 'only_matching': True, }] @classmethod def suitable(cls, url): - return False if UpskillIE.suitable(url) else super( - UpskillCourseIE, cls).suitable(url) + return False if TeachableIE.suitable(url) else super( + TeachableCourseIE, cls).suitable(url) def _real_extract(self, url): - course_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + site = mobj.group('site') or mobj.group('site_t') + course_id = mobj.group('id') + + self._login(site) + + prefixed = url.startswith(self._URL_PREFIX) + if prefixed: + prefix = self._URL_PREFIX + url = url[len(prefix):] webpage = self._download_webpage(url, course_id) - course_id = self._search_regex( - r'data-course-id=["\'](\d+)', webpage, 'course id', - default=course_id) + url_base = 'https://%s/' % site entries = [] @@ -162,10 +242,13 @@ class UpskillCourseIE(UpskillBaseIE): title = self._html_search_regex( r']+class=["\']lecture-name[^>]+>([^<]+)', li, 'title', default=None) + entry_url = urljoin(url_base, lecture_url) + if prefixed: + entry_url = self._URL_PREFIX + entry_url entries.append( self.url_result( - urljoin('http://upskillcourses.com/', lecture_url), - ie=UpskillIE.ie_key(), video_id=lecture_id, + entry_url, + ie=TeachableIE.ie_key(), video_id=lecture_id, video_title=clean_html(title))) course_title = self._html_search_regex( From 9e02c2c704d15d56b92ebe2fc8d481f99f5d106d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 9 Dec 2018 22:56:33 +0700 Subject: [PATCH 360/558] [YoutubeDLCookieJar] Add test for keeping session cookies --- test/test_YoutubeDLCookieJar.py | 34 +++++++++++++++++++++++ test/testdata/cookies/session_cookies.txt | 6 ++++ 2 files changed, 40 insertions(+) create mode 100644 test/test_YoutubeDLCookieJar.py create mode 100644 test/testdata/cookies/session_cookies.txt diff --git a/test/test_YoutubeDLCookieJar.py b/test/test_YoutubeDLCookieJar.py new file mode 100644 index 000000000..6a8243590 --- /dev/null +++ b/test/test_YoutubeDLCookieJar.py @@ -0,0 +1,34 @@ +#!/usr/bin/env python +# coding: utf-8 + +from __future__ import unicode_literals + +import os +import re +import sys +import tempfile +import unittest +sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + +from youtube_dl.utils import YoutubeDLCookieJar + + +class TestYoutubeDLCookieJar(unittest.TestCase): + def test_keep_session_cookies(self): + cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/session_cookies.txt') + cookiejar.load(ignore_discard=True, ignore_expires=True) + tf = tempfile.NamedTemporaryFile(delete=False) + try: + cookiejar.save(filename=tf.name, ignore_discard=True, ignore_expires=True) + temp = tf.read().decode('utf-8') + self.assertTrue(re.search( + r'www\.foobar\.foobar\s+FALSE\s+/\s+TRUE\s+0\s+YoutubeDLExpiresEmpty\s+YoutubeDLExpiresEmptyValue', temp)) + self.assertTrue(re.search( + r'www\.foobar\.foobar\s+FALSE\s+/\s+TRUE\s+0\s+YoutubeDLExpires0\s+YoutubeDLExpires0Value', temp)) + finally: + tf.close() + os.remove(tf.name) + + +if __name__ == '__main__': + unittest.main() diff --git a/test/testdata/cookies/session_cookies.txt b/test/testdata/cookies/session_cookies.txt new file mode 100644 index 000000000..91e5c9231 --- /dev/null +++ b/test/testdata/cookies/session_cookies.txt @@ -0,0 +1,6 @@ +# Netscape HTTP Cookie File +# http://curl.haxx.se/rfc/cookie_spec.html +# This is a generated file! Do not edit. + +www.foobar.foobar FALSE / TRUE 0 YoutubeDLExpires0 YoutubeDLExpires0Value +www.foobar.foobar FALSE / TRUE 0 YoutubeDLExpiresEmpty YoutubeDLExpiresEmptyValue From 24cc64254c03c56229654b13d833c600d7048bbb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 9 Dec 2018 23:08:16 +0700 Subject: [PATCH 361/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/ChangeLog b/ChangeLog index 689d07826..6afee3a28 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,27 @@ +version + +Core +* [YoutubeDL] Keep session cookies in cookie file between runs +* [YoutubeDL] Recognize session cookies with expired set to 0 (#12929) + +Extractors ++ [teachable] Add support for teachable platform sites (#5451, #18150, #18272) ++ [aenetworks] Add support for historyvault.com (#18460) +* [imgur] Improve gallery and album detection and extraction (#9133, #16577, + #17223, #18404) +* [iprima] Relax URL regular expression (#18453) +* [hotstar] Fix video data extraction (#18386) +* [ard:mediathek] Fix title and description extraction (#18349, #18371) +* [xvideos] Switch to HTTPS (#18422, #18427) ++ [lecturio] Add support for lecturio.com (#18405) ++ [nrktv:series] Add support for extra materials +* [nrktv:season,series] Fix extraction (#17159, #17258) +* [nrktv] Relax URL regular expression (#18304, #18387) +* [yourporn] Fix extraction (#18424, #18425) +* [tbs] Fix info extraction (#18403) ++ [gamespot] Add support for review URLs + + version 2018.12.03 Core From cefe42c412168e95b78dcefc5cdba608dba7dd02 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 9 Dec 2018 23:11:32 +0700 Subject: [PATCH 362/558] release 2018.12.09 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 11 +++++++---- youtube_dl/version.py | 2 +- 4 files changed, 12 insertions(+), 9 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 4b35244a8..1ccf410a7 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.12.03*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.12.03** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.12.09*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.12.09** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.12.03 +[debug] youtube-dl version 2018.12.09 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 6afee3a28..9aef67b52 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2018.12.09 Core * [YoutubeDL] Keep session cookies in cookie file between runs diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 837b0199b..31d20f255 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -33,7 +33,7 @@ - **AdobeTVShow** - **AdobeTVVideo** - **AdultSwim** - - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network + - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault - **afreecatv**: afreecatv.com - **AirMozilla** - **AliExpressLive** @@ -376,7 +376,8 @@ - **imdb**: Internet Movie Database trailers - **imdb:list**: Internet Movie Database lists - **Imgur** - - **ImgurAlbum** + - **imgur:album** + - **imgur:gallery** - **Ina** - **Inc** - **IndavideoEmbed** @@ -435,6 +436,8 @@ - **Le**: 乐视网 - **Learnr** - **Lecture2Go** + - **Lecturio** + - **LecturioCourse** - **LEGO** - **Lemonde** - **Lenta** @@ -853,6 +856,8 @@ - **TastyTrade** - **TBS** - **TDSLifeway** + - **Teachable** + - **TeachableCourse** - **teachertube**: teachertube.com videos - **teachertube:user:collection**: teachertube.com user and collection videos - **TeachingChannel** @@ -961,8 +966,6 @@ - **uol.com.br** - **uplynk** - **uplynk:preplay** - - **Upskill** - - **UpskillCourse** - **Urort**: NRK P3 Urørt - **URPlay** - **USANetwork** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 8e1203892..d15b9583f 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.12.03' +__version__ = '2018.12.09' From 59c3940165efaee6705ff06ef4fc4ac2c701107d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 10 Dec 2018 01:37:10 +0700 Subject: [PATCH 363/558] [ard:mediathek] Add support for classic.ardmediathek.de (closes #18473) --- youtube_dl/extractor/ard.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 84e96f769..2e1536a1b 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -21,7 +21,7 @@ from ..compat import compat_etree_fromstring class ARDMediathekIE(InfoExtractor): IE_NAME = 'ARD:mediathek' - _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' + _VALID_URL = r'^https?://(?:(?:(?:www|classic)\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' _TESTS = [{ # available till 26.07.2022 @@ -51,6 +51,9 @@ class ARDMediathekIE(InfoExtractor): # audio 'url': 'http://mediathek.rbb-online.de/radio/Hörspiel/Vor-dem-Fest/kulturradio/Audio?documentId=30796318&topRessort=radio&bcastId=9839158', 'only_matching': True, + }, { + 'url': 'https://classic.ardmediathek.de/tv/Panda-Gorilla-Co/Panda-Gorilla-Co-Folge-274/Das-Erste/Video?bcastId=16355486&documentId=58234698', + 'only_matching': True, }] def _extract_media_info(self, media_info_url, webpage, video_id): From 6e29458f2479c4535f8605032b9492f52bb37f17 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 10 Dec 2018 04:30:00 +0700 Subject: [PATCH 364/558] [test/testdata/cookies/session_cookies.txt] Fix empty expires test data --- test/testdata/cookies/session_cookies.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/test/testdata/cookies/session_cookies.txt b/test/testdata/cookies/session_cookies.txt index 91e5c9231..f6996f031 100644 --- a/test/testdata/cookies/session_cookies.txt +++ b/test/testdata/cookies/session_cookies.txt @@ -2,5 +2,5 @@ # http://curl.haxx.se/rfc/cookie_spec.html # This is a generated file! Do not edit. +www.foobar.foobar FALSE / TRUE YoutubeDLExpiresEmpty YoutubeDLExpiresEmptyValue www.foobar.foobar FALSE / TRUE 0 YoutubeDLExpires0 YoutubeDLExpires0Value -www.foobar.foobar FALSE / TRUE 0 YoutubeDLExpiresEmpty YoutubeDLExpiresEmptyValue From 102a4e54c5c0819233773cc15398bc901a218f4c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 10 Dec 2018 10:10:28 +0700 Subject: [PATCH 365/558] [teachable] Remove debug output --- youtube_dl/extractor/teachable.py | 1 - 1 file changed, 1 deletion(-) diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py index a0c46b2e6..47ac95ee8 100644 --- a/youtube_dl/extractor/teachable.py +++ b/youtube_dl/extractor/teachable.py @@ -135,7 +135,6 @@ class TeachableIE(TeachableBaseIE): @staticmethod def _extract_url(webpage, source_url): if not TeachableIE._is_teachable(webpage): - print('NOT TEACHABLE') return if re.match(r'https?://[^/]+/(?:courses|p)', source_url): return '%s%s' % (TeachableBaseIE._URL_PREFIX, source_url) From 13e17cd28e7f9e3bd8be4fa7b073a5cb96f5959f Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 10 Dec 2018 14:59:57 +0100 Subject: [PATCH 366/558] [uol] fix format url extraction(closes 18480) --- youtube_dl/extractor/uol.py | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/uol.py b/youtube_dl/extractor/uol.py index e67083004..08f0c072e 100644 --- a/youtube_dl/extractor/uol.py +++ b/youtube_dl/extractor/uol.py @@ -61,7 +61,7 @@ class UOLIE(InfoExtractor): 'height': 360, }, '5': { - 'width': 1080, + 'width': 1280, 'height': 720, }, '6': { @@ -80,6 +80,10 @@ class UOLIE(InfoExtractor): 'width': 568, 'height': 320, }, + '11': { + 'width': 640, + 'height': 360, + } } def _real_extract(self, url): @@ -111,19 +115,31 @@ class UOLIE(InfoExtractor): 'ver': video_data.get('numRevision', 2), 'r': 'http://mais.uol.com.br', } + for k in ('token', 'sign'): + v = video_data.get(k) + if v: + query[k] = v + formats = [] for f in video_data.get('formats', []): f_url = f.get('url') or f.get('secureUrl') if not f_url: continue + f_url = update_url_query(f_url, query) format_id = str_or_none(f.get('id')) + if format_id == '10': + formats.extend(self._extract_m3u8_formats( + f_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + continue fmt = { 'format_id': format_id, - 'url': update_url_query(f_url, query), + 'url': f_url, + 'source_preference': 1, } fmt.update(self._FORMATS.get(format_id, {})) formats.append(fmt) - self._sort_formats(formats) + self._sort_formats(formats, ('height', 'width', 'source_preference', 'tbr', 'ext')) tags = [] for tag in video_data.get('tags', []): From 0a05cfabb6338be750474a7286ce0d72a4d7c142 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 11 Dec 2018 23:45:02 +0700 Subject: [PATCH 367/558] [lecturio] Improve subtitles extraction (closes #18488) --- youtube_dl/extractor/lecturio.py | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/lecturio.py b/youtube_dl/extractor/lecturio.py index 62ff28e02..0f1265cdf 100644 --- a/youtube_dl/extractor/lecturio.py +++ b/youtube_dl/extractor/lecturio.py @@ -136,9 +136,15 @@ class LecturioIE(LecturioBaseIE): cc_url = url_or_none(cc_url) if not cc_url: continue - sub_dict = automatic_captions if 'auto-translated' in cc_label else subtitles lang = self._search_regex( - r'/([a-z]{2})_', cc_url, 'lang', default=cc_label.split()[0]) + r'/([a-z]{2})_', cc_url, 'lang', + default=cc_label.split()[0] if cc_label else 'en') + original_lang = self._search_regex( + r'/[a-z]{2}_([a-z]{2})_', cc_url, 'original lang', + default=None) + sub_dict = (automatic_captions + if 'auto-translated' in cc_label or original_lang + else subtitles) sub_dict.setdefault(self._CC_LANGS.get(lang, lang), []).append({ 'url': cc_url, }) From 8fe104947d6b772ccacd0b8af51d1adb16865e99 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 15 Dec 2018 22:25:12 +0700 Subject: [PATCH 368/558] [youtube] Fix multifeed extraction (closes #18531) --- youtube_dl/extractor/youtube.py | 52 ++++++++++++++++++--------------- 1 file changed, 29 insertions(+), 23 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 3f49f3889..c582ab2ff 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1712,30 +1712,36 @@ class YoutubeIE(YoutubeBaseInfoExtractor): else: video_description = '' - if 'multifeed_metadata_list' in video_info and not smuggled_data.get('force_singlefeed', False): + if not smuggled_data.get('force_singlefeed', False): if not self._downloader.params.get('noplaylist'): - entries = [] - feed_ids = [] - multifeed_metadata_list = video_info['multifeed_metadata_list'][0] - for feed in multifeed_metadata_list.split(','): - # Unquote should take place before split on comma (,) since textual - # fields may contain comma as well (see - # https://github.com/rg3/youtube-dl/issues/8536) - feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed)) - entries.append({ - '_type': 'url_transparent', - 'ie_key': 'Youtube', - 'url': smuggle_url( - '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]), - {'force_singlefeed': True}), - 'title': '%s (%s)' % (video_title, feed_data['title'][0]), - }) - feed_ids.append(feed_data['id'][0]) - self.to_screen( - 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' - % (', '.join(feed_ids), video_id)) - return self.playlist_result(entries, video_id, video_title, video_description) - self.to_screen('Downloading just video %s because of --no-playlist' % video_id) + multifeed_metadata_list = try_get( + player_response, + lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'], + compat_str) or try_get( + video_info, lambda x: x['multifeed_metadata_list'][0], compat_str) + if multifeed_metadata_list: + entries = [] + feed_ids = [] + for feed in multifeed_metadata_list.split(','): + # Unquote should take place before split on comma (,) since textual + # fields may contain comma as well (see + # https://github.com/rg3/youtube-dl/issues/8536) + feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed)) + entries.append({ + '_type': 'url_transparent', + 'ie_key': 'Youtube', + 'url': smuggle_url( + '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]), + {'force_singlefeed': True}), + 'title': '%s (%s)' % (video_title, feed_data['title'][0]), + }) + feed_ids.append(feed_data['id'][0]) + self.to_screen( + 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' + % (', '.join(feed_ids), video_id)) + return self.playlist_result(entries, video_id, video_title, video_description) + else: + self.to_screen('Downloading just video %s because of --no-playlist' % video_id) if view_count is None: view_count = extract_view_count(video_info) From 7f41a598b3fba1bcab2817de64a08941200aa3c8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 15 Dec 2018 23:08:14 +0700 Subject: [PATCH 369/558] [safari] Add support for learning.oreilly.com (closes #18510) --- youtube_dl/extractor/safari.py | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py index 30e2a38b4..c0d32a1b9 100644 --- a/youtube_dl/extractor/safari.py +++ b/youtube_dl/extractor/safari.py @@ -15,10 +15,10 @@ from ..utils import ( class SafariBaseIE(InfoExtractor): - _LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/' + _LOGIN_URL = 'https://learning.oreilly.com/accounts/login/' _NETRC_MACHINE = 'safari' - _API_BASE = 'https://www.safaribooksonline.com/api/v1' + _API_BASE = 'https://learning.oreilly.com/api/v1' _API_FORMAT = 'json' LOGGED_IN = False @@ -76,7 +76,7 @@ class SafariIE(SafariBaseIE): IE_DESC = 'safaribooksonline.com online video' _VALID_URL = r'''(?x) https?:// - (?:www\.)?safaribooksonline\.com/ + (?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/ (?: library/view/[^/]+/(?P[^/]+)/(?P[^/?\#&]+)\.html| videos/[^/]+/[^/]+/(?P[^-]+-[^/?\#&]+) @@ -104,6 +104,9 @@ class SafariIE(SafariBaseIE): }, { 'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314/9780134217314-PYMC_13_00', 'only_matching': True, + }, { + 'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838/9780133392838-00_SeriesIntro', + 'only_matching': True, }] _PARTNER_ID = '1926081' @@ -160,7 +163,7 @@ class SafariIE(SafariBaseIE): class SafariApiIE(SafariBaseIE): IE_NAME = 'safari:api' - _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/api/v1/book/(?P[^/]+)/chapter(?:-content)?/(?P[^/?#&]+)\.html' + _VALID_URL = r'https?://(?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/api/v1/book/(?P[^/]+)/chapter(?:-content)?/(?P[^/?#&]+)\.html' _TESTS = [{ 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html', @@ -185,7 +188,7 @@ class SafariCourseIE(SafariBaseIE): _VALID_URL = r'''(?x) https?:// (?: - (?:www\.)?safaribooksonline\.com/ + (?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/ (?: library/view/[^/]+| api/v1/book| @@ -213,6 +216,9 @@ class SafariCourseIE(SafariBaseIE): }, { 'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314', 'only_matching': True, + }, { + 'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838', + 'only_matching': True, }] @classmethod From c984196cf1c9eb34725091e07a4f094b7eea1d4f Mon Sep 17 00:00:00 2001 From: Sergey M Date: Sat, 15 Dec 2018 23:59:17 +0700 Subject: [PATCH 370/558] [README.md] Bind info dict URLs to a fixed blob (closes #18492) --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 35c3de512..a1d2904c0 100644 --- a/README.md +++ b/README.md @@ -1024,7 +1024,7 @@ After you have ensured this site is distributing its content legally, you can fo ``` 5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py). 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in. -7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want. +7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want. 8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+. 9. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this: @@ -1045,7 +1045,7 @@ Extractors are very fragile by nature since they depend on the layout of the sou ### Mandatory and optional metafields -For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L75-L257) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl: +For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl: - `id` (media identifier) - `title` (media title) @@ -1053,7 +1053,7 @@ For extraction to work youtube-dl relies on metadata your extractor extracts and In fact only the last option is technically mandatory (i.e. if you can't figure out the download location of the media the extraction does not make any sense). But by convention youtube-dl also treats `id` and `title` as mandatory. Thus the aforementioned metafields are the critical data that the extraction does not make any sense without and if any of them fail to be extracted then the extractor is considered completely broken. -[Any field](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L149-L257) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. +[Any field](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L188-L303) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. #### Example From 21c340b83fb41094ef59b87d52c4eb1d90d1df04 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 16 Dec 2018 19:35:48 +0700 Subject: [PATCH 371/558] [youtube] Fix mark watched (closes #18546) --- youtube_dl/extractor/youtube.py | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index c582ab2ff..44c25c11c 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -48,6 +48,7 @@ from ..utils import ( unified_strdate, unsmuggle_url, uppercase_escape, + url_or_none, urlencode_postdata, ) @@ -1386,8 +1387,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): self._downloader.report_warning(err_msg) return {} - def _mark_watched(self, video_id, video_info): - playback_url = video_info.get('videostats_playback_base_url', [None])[0] + def _mark_watched(self, video_id, video_info, player_response): + playback_url = url_or_none(try_get( + player_response, + lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get( + video_info, lambda x: x['videostats_playback_base_url'][0])) if not playback_url: return parsed_playback_url = compat_urlparse.urlparse(playback_url) @@ -2122,7 +2126,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): self._sort_formats(formats) - self.mark_watched(video_id, video_info) + self.mark_watched(video_id, video_info, player_response) return { 'id': video_id, From c8b37510868b20b0829583557899d70db2ea6243 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sun, 16 Dec 2018 14:28:40 +0100 Subject: [PATCH 372/558] [vrv] fix initial state extraction --- youtube_dl/extractor/vrv.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/vrv.py b/youtube_dl/extractor/vrv.py index ac0819c7c..483a3be3a 100644 --- a/youtube_dl/extractor/vrv.py +++ b/youtube_dl/extractor/vrv.py @@ -120,8 +120,10 @@ class VRVIE(VRVBaseIE): url, video_id, headers=self.geo_verification_headers()) media_resource = self._parse_json(self._search_regex( - r'window\.__INITIAL_STATE__\s*=\s*({.+?})', - webpage, 'inital state'), video_id).get('watch', {}).get('mediaResource') or {} + [ + r'window\.__INITIAL_STATE__\s*=\s*({.+?})(?:|;)', + r'window\.__INITIAL_STATE__\s*=\s*({.+})' + ], webpage, 'inital state'), video_id).get('watch', {}).get('mediaResource') or {} video_data = media_resource.get('json') if not video_data: From 90046d77616f8f24e3716c64443118a9dcbec996 Mon Sep 17 00:00:00 2001 From: yonaikerlol Date: Sun, 16 Dec 2018 17:10:36 -0400 Subject: [PATCH 373/558] [iprima] Relax _VALID_URL (closes #18515) --- youtube_dl/extractor/iprima.py | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py index 11a6629d2..11bbeb592 100644 --- a/youtube_dl/extractor/iprima.py +++ b/youtube_dl/extractor/iprima.py @@ -12,7 +12,7 @@ from ..utils import ( class IPrimaIE(InfoExtractor): - _VALID_URL = r'https?://(?:play|prima|www)\.iprima\.cz/(?:[^/]+/)*(?P[^/?#&]+)' + _VALID_URL = r'https?://(?:[^/]+)\.iprima\.cz/(?:[^/]+/)*(?P[^/?#&]+)' _GEO_BYPASS = False _TESTS = [{ @@ -44,6 +44,21 @@ class IPrimaIE(InfoExtractor): }, { 'url': 'http://www.iprima.cz/filmy/desne-rande', 'only_matching': True, + }, { + 'url': 'https://zoom.iprima.cz/10-nejvetsich-tajemstvi-zahad/posvatna-mista-a-stavby', + 'only_matching': True, + }, { + 'url': 'https://krimi.iprima.cz/mraz-0/sebevrazdy', + 'only_matching': True, + }, { + 'url': 'https://cool.iprima.cz/derava-silnice-nevadi', + 'only_matching': True, + }, { + 'url': 'https://love.iprima.cz/laska-az-za-hrob/slib-dany-bratrovi', + 'only_matching': True, + }, { + 'url': 'https://autosalon.iprima.cz/motorsport/7-epizoda-1', + 'only_matching': True, }] def _real_extract(self, url): From 252e172dea96b90191682afac837535de4d33107 Mon Sep 17 00:00:00 2001 From: Tim Landscheidt Date: Sun, 16 Dec 2018 21:29:12 +0000 Subject: [PATCH 374/558] [acast] Add support for embed.acast.com --- youtube_dl/extractor/acast.py | 22 ++++------------------ 1 file changed, 4 insertions(+), 18 deletions(-) diff --git a/youtube_dl/extractor/acast.py b/youtube_dl/extractor/acast.py index 6d846ea7a..1fbff705d 100644 --- a/youtube_dl/extractor/acast.py +++ b/youtube_dl/extractor/acast.py @@ -17,25 +17,8 @@ from ..utils import ( class ACastIE(InfoExtractor): IE_NAME = 'acast' - _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P[^/]+)/(?P[^/#?]+)' + _VALID_URL = r'https?://(?:(?:embed|www)\.)?acast\.com/(?P[^/]+)/(?P[^/#?]+)' _TESTS = [{ - # test with one bling - 'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan', - 'md5': 'ada3de5a1e3a2a381327d749854788bb', - 'info_dict': { - 'id': '57de3baa-4bb0-487e-9418-2692c1277a34', - 'ext': 'mp3', - 'title': '"Where Are You?": Taipei 101, Taiwan', - 'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e', - 'timestamp': 1196172000, - 'upload_date': '20071127', - 'duration': 211, - 'creator': 'Concierge', - 'series': 'Condé Nast Traveler Podcast', - 'episode': '"Where Are You?": Taipei 101, Taiwan', - } - }, { - # test with multiple blings 'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna', 'md5': 'a02393c74f3bdb1801c3ec2695577ce0', 'info_dict': { @@ -50,6 +33,9 @@ class ACastIE(InfoExtractor): 'series': 'Spår', 'episode': '2. Raggarmordet - Röster ur det förflutna', } + }, { + 'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015', + 'only_matching': True, }] def _real_extract(self, url): From 50a498a68e2f6754f5b26e5ad1f6eabfd9aeeb14 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 17 Dec 2018 04:32:59 +0700 Subject: [PATCH 375/558] [acast] Extend _VALID_URL --- youtube_dl/extractor/acast.py | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/acast.py b/youtube_dl/extractor/acast.py index 1fbff705d..b32f74a37 100644 --- a/youtube_dl/extractor/acast.py +++ b/youtube_dl/extractor/acast.py @@ -17,7 +17,14 @@ from ..utils import ( class ACastIE(InfoExtractor): IE_NAME = 'acast' - _VALID_URL = r'https?://(?:(?:embed|www)\.)?acast\.com/(?P[^/]+)/(?P[^/#?]+)' + _VALID_URL = r'''(?x) + https?:// + (?: + (?:(?:embed|www)\.)?acast\.com/| + play\.acast\.com/s/ + ) + (?P[^/]+)/(?P[^/#?]+) + ''' _TESTS = [{ 'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna', 'md5': 'a02393c74f3bdb1801c3ec2695577ce0', @@ -36,6 +43,9 @@ class ACastIE(InfoExtractor): }, { 'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015', 'only_matching': True, + }, { + 'url': 'https://play.acast.com/s/rattegangspodden/s04e09-styckmordet-i-helenelund-del-22', + 'only_matching': True, }] def _real_extract(self, url): From 1c82122741783adf6653df25fa81ef0f95a22279 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 17 Dec 2018 04:51:57 +0700 Subject: [PATCH 376/558] [ard:beta] Relax _VALID_URL (closes #18441) --- youtube_dl/extractor/ard.py | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 2e1536a1b..a5df7f0f9 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -56,6 +56,10 @@ class ARDMediathekIE(InfoExtractor): 'only_matching': True, }] + @classmethod + def suitable(cls, url): + return False if ARDBetaMediathekIE.suitable(url) else super(ARDMediathekIE, cls).suitable(url) + def _extract_media_info(self, media_info_url, webpage, video_id): media_info = self._download_json( media_info_url, video_id, 'Downloading media JSON') @@ -296,7 +300,7 @@ class ARDIE(InfoExtractor): class ARDBetaMediathekIE(InfoExtractor): - _VALID_URL = r'https://beta\.ardmediathek\.de/[a-z]+/player/(?P[a-zA-Z0-9]+)/(?P[^/?#]+)' + _VALID_URL = r'https://(?:beta|www)\.ardmediathek\.de/[^/]+/(?:player|live)/(?P[a-zA-Z0-9]+)(?:/(?P[^/?#]+))?' _TESTS = [{ 'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita', 'md5': '2d02d996156ea3c397cfc5036b5d7f8f', @@ -310,12 +314,18 @@ class ARDBetaMediathekIE(InfoExtractor): 'upload_date': '20180826', 'ext': 'mp4', }, + }, { + 'url': 'https://www.ardmediathek.de/ard/player/Y3JpZDovL3N3ci5kZS9hZXgvbzEwNzE5MTU/', + 'only_matching': True, + }, { + 'url': 'https://www.ardmediathek.de/swr/live/Y3JpZDovL3N3ci5kZS8xMzQ4MTA0Mg', + 'only_matching': True, }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('video_id') - display_id = mobj.group('display_id') + display_id = mobj.group('display_id') or video_id webpage = self._download_webpage(url, display_id) data_json = self._search_regex(r'window\.__APOLLO_STATE__\s*=\s*(\{.*);\n', webpage, 'json') From 752582183a1942b12880139039137b3a60962611 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 17 Dec 2018 05:29:59 +0700 Subject: [PATCH 377/558] [ard:beta] Improve extraction robustness, fix subtitles extraction, improve geo restricted videos extraction --- youtube_dl/extractor/ard.py | 58 +++++++++++++++++++++++++------------ 1 file changed, 40 insertions(+), 18 deletions(-) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index a5df7f0f9..8adae4644 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -8,13 +8,16 @@ from .generic import GenericIE from ..utils import ( determine_ext, ExtractorError, - qualities, int_or_none, parse_duration, + qualities, + str_or_none, + try_get, unified_strdate, - xpath_text, + unified_timestamp, update_url_query, url_or_none, + xpath_text, ) from ..compat import compat_etree_fromstring @@ -336,43 +339,62 @@ class ARDBetaMediathekIE(InfoExtractor): 'display_id': display_id, } formats = [] + subtitles = {} + geoblocked = False for widget in data.values(): - if widget.get('_geoblocked'): - raise ExtractorError('This video is not available due to geoblocking', expected=True) - + if widget.get('_geoblocked') is True: + geoblocked = True if '_duration' in widget: - res['duration'] = widget['_duration'] + res['duration'] = int_or_none(widget['_duration']) if 'clipTitle' in widget: res['title'] = widget['clipTitle'] if '_previewImage' in widget: res['thumbnail'] = widget['_previewImage'] if 'broadcastedOn' in widget: - res['upload_date'] = unified_strdate(widget['broadcastedOn']) + res['timestamp'] = unified_timestamp(widget['broadcastedOn']) if 'synopsis' in widget: res['description'] = widget['synopsis'] - if '_subtitleUrl' in widget: - res['subtitles'] = {'de': [{ + subtitle_url = url_or_none(widget.get('_subtitleUrl')) + if subtitle_url: + subtitles.setdefault('de', []).append({ 'ext': 'ttml', - 'url': widget['_subtitleUrl'], - }]} + 'url': subtitle_url, + }) if '_quality' in widget: - format_url = widget['_stream']['json'][0] - - if format_url.endswith('.f4m'): + format_url = url_or_none(try_get( + widget, lambda x: x['_stream']['json'][0])) + if not format_url: + continue + ext = determine_ext(format_url) + if ext == 'f4m': formats.extend(self._extract_f4m_formats( format_url + '?hdcore=3.11.0', video_id, f4m_id='hds', fatal=False)) - elif format_url.endswith('m3u8'): + elif ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - format_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) + format_url, video_id, 'mp4', m3u8_id='hls', + fatal=False)) else: + # HTTP formats are not available when geoblocked is True, + # other formats are fine though + if geoblocked: + continue + quality = str_or_none(widget.get('_quality')) formats.append({ - 'format_id': 'http-' + widget['_quality'], + 'format_id': ('http-' + quality) if quality else 'http', 'url': format_url, 'preference': 10, # Plain HTTP, that's nice }) + if not formats and geoblocked: + self.raise_geo_restricted( + msg='This video is not available due to geoblocking', + countries=['DE']) + self._sort_formats(formats) - res['formats'] = formats + res.update({ + 'subtitles': subtitles, + 'formats': formats, + }) return res From cbb3e4b14f59fe2dba5983f7e55308eba2ea025b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 17 Dec 2018 05:34:55 +0700 Subject: [PATCH 378/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/ChangeLog b/ChangeLog index 9aef67b52..291ae42bb 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,21 @@ +version + +Extractors +* [ard:beta] Improve geo restricted videos extraction +* [ard:beta] Fix subtitles extraction +* [ard:beta] Improve extraction robustness +* [ard:beta] Relax URL regular expression (#18441) +* [acast] Add support for embed.acast.com and play.acast.com (#18483) +* [iprima] Relax URL regular expression (#18515, #18540) +* [vrv] Fix initial state extraction (#18553) +* [youtube] Fix mark watched (#18546) ++ [safari] Add support for learning.oreilly.com (#18510) +* [youtube] Fix multifeed extraction (#18531) +* [lecturio] Improve subtitles extraction (#18488) +* [uol] Fix format URL extraction (#18480) ++ [ard:mediathek] Add support for classic.ardmediathek.de (#18473) + + version 2018.12.09 Core From 4cee62ade0d991eedb2feae927c44370be3c389e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 17 Dec 2018 05:37:50 +0700 Subject: [PATCH 379/558] release 2018.12.17 --- .github/ISSUE_TEMPLATE.md | 6 +++--- CONTRIBUTING.md | 6 +++--- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 1ccf410a7..b84559932 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.12.09*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.12.09** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.12.17*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.12.17** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.12.09 +[debug] youtube-dl version 2018.12.17 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index bbcb78808..cba87190d 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -152,7 +152,7 @@ After you have ensured this site is distributing its content legally, you can fo ``` 5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py). 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in. -7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want. +7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want. 8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+. 9. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this: @@ -173,7 +173,7 @@ Extractors are very fragile by nature since they depend on the layout of the sou ### Mandatory and optional metafields -For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L75-L257) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl: +For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl: - `id` (media identifier) - `title` (media title) @@ -181,7 +181,7 @@ For extraction to work youtube-dl relies on metadata your extractor extracts and In fact only the last option is technically mandatory (i.e. if you can't figure out the download location of the media the extraction does not make any sense). But by convention youtube-dl also treats `id` and `title` as mandatory. Thus the aforementioned metafields are the critical data that the extraction does not make any sense without and if any of them fail to be extracted then the extractor is considered completely broken. -[Any field](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L149-L257) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. +[Any field](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L188-L303) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. #### Example diff --git a/ChangeLog b/ChangeLog index 291ae42bb..510013e89 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2018.12.17 Extractors * [ard:beta] Improve geo restricted videos extraction diff --git a/youtube_dl/version.py b/youtube_dl/version.py index d15b9583f..0461aac0c 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.12.09' +__version__ = '2018.12.17' From 7216e9bff71b4c537bb8d56386d789bb83f921f9 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 17 Dec 2018 16:34:51 +0100 Subject: [PATCH 380/558] [discovery] Add support for Scripps Networks watch domains(closes #17947) --- youtube_dl/extractor/discovery.py | 35 +++++++++++++++++-------- youtube_dl/extractor/scrippsnetworks.py | 29 +++++--------------- 2 files changed, 31 insertions(+), 33 deletions(-) diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index 3589bd428..44fbc41bb 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -17,16 +17,29 @@ from ..compat import compat_HTTPError class DiscoveryIE(DiscoveryGoBaseIE): - _VALID_URL = r'''(?x)https?://(?:www\.)?(?P - discovery| - investigationdiscovery| - discoverylife| - animalplanet| - ahctv| - destinationamerica| - sciencechannel| - tlc| - velocity + _VALID_URL = r'''(?x)https?:// + (?P + (?:www\.)? + (?: + discovery| + investigationdiscovery| + discoverylife| + animalplanet| + ahctv| + destinationamerica| + sciencechannel| + tlc| + velocity + )| + watch\. + (?: + hgtv| + foodnetwork| + travelchannel| + diynetwork| + cookingchanneltv| + motortrend + ) )\.com(?P/tv-shows/[^/]+/(?:video|full-episode)s/(?P[^./?#]+))''' _TESTS = [{ 'url': 'https://www.discovery.com/tv-shows/cash-cab/videos/dave-foley', @@ -71,7 +84,7 @@ class DiscoveryIE(DiscoveryGoBaseIE): if not access_token: access_token = self._download_json( - 'https://www.%s.com/anonymous' % site, display_id, query={ + 'https://%s.com/anonymous' % site, display_id, query={ 'authRel': 'authorization', 'client_id': try_get( react_data, lambda x: x['application']['apiClientId'], diff --git a/youtube_dl/extractor/scrippsnetworks.py b/youtube_dl/extractor/scrippsnetworks.py index 4023aeef8..8b3275735 100644 --- a/youtube_dl/extractor/scrippsnetworks.py +++ b/youtube_dl/extractor/scrippsnetworks.py @@ -19,7 +19,7 @@ class ScrippsNetworksWatchIE(AWSIE): _VALID_URL = r'''(?x) https?:// watch\. - (?Phgtv|foodnetwork|travelchannel|diynetwork|cookingchanneltv|geniuskitchen)\.com/ + (?Pgeniuskitchen)\.com/ (?: player\.[A-Z0-9]+\.html\#| show/(?:[^/]+/){2}| @@ -28,38 +28,23 @@ class ScrippsNetworksWatchIE(AWSIE): (?P\d+) ''' _TESTS = [{ - 'url': 'http://watch.hgtv.com/show/HGTVE/Best-Ever-Treehouses/2241515/Best-Ever-Treehouses/', - 'md5': '26545fd676d939954c6808274bdb905a', + 'url': 'http://watch.geniuskitchen.com/player/3787617/Ample-Hills-Ice-Cream-Bike/', 'info_dict': { - 'id': '4173834', + 'id': '4194875', 'ext': 'mp4', - 'title': 'Best Ever Treehouses', - 'description': "We're searching for the most over the top treehouses.", + 'title': 'Ample Hills Ice Cream Bike', + 'description': 'Courtney Rada churns up a signature GK Now ice cream with The Scoopmaster.', 'uploader': 'ANV', - 'upload_date': '20170922', - 'timestamp': 1506056400, + 'upload_date': '20171011', + 'timestamp': 1507698000, }, 'params': { 'skip_download': True, }, 'add_ie': [AnvatoIE.ie_key()], - }, { - 'url': 'http://watch.diynetwork.com/show/DSAL/Salvage-Dawgs/2656646/Covington-Church/', - 'only_matching': True, - }, { - 'url': 'http://watch.diynetwork.com/player.HNT.html#2656646', - 'only_matching': True, - }, { - 'url': 'http://watch.geniuskitchen.com/player/3787617/Ample-Hills-Ice-Cream-Bike/', - 'only_matching': True, }] _SNI_TABLE = { - 'hgtv': 'hgtv', - 'diynetwork': 'diy', - 'foodnetwork': 'food', - 'cookingchanneltv': 'cook', - 'travelchannel': 'trav', 'geniuskitchen': 'genius', } From 386d1fea79e861b11c77a7353c07eb162fbb4dae Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 17 Dec 2018 23:43:12 +0700 Subject: [PATCH 381/558] [lecturio] Add support for lecturio.de (closes #18562) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/lecturio.py | 45 +++++++++++++++++++++++++++--- 2 files changed, 42 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 6a5d12ab1..d72f52e36 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -557,6 +557,7 @@ from .lecture2go import Lecture2GoIE from .lecturio import ( LecturioIE, LecturioCourseIE, + LecturioDeCourseIE, ) from .leeco import ( LeIE, diff --git a/youtube_dl/extractor/lecturio.py b/youtube_dl/extractor/lecturio.py index 0f1265cdf..24f78d928 100644 --- a/youtube_dl/extractor/lecturio.py +++ b/youtube_dl/extractor/lecturio.py @@ -64,8 +64,14 @@ class LecturioBaseIE(InfoExtractor): class LecturioIE(LecturioBaseIE): - _VALID_URL = r'https://app\.lecturio\.com/[^/]+/(?P[^/?#&]+)\.lecture' - _TEST = { + _VALID_URL = r'''(?x) + https:// + (?: + app\.lecturio\.com/[^/]+/(?P[^/?#&]+)\.lecture| + (?:www\.)?lecturio\.de/[^/]+/(?P[^/?#&]+)\.vortrag + ) + ''' + _TESTS = [{ 'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos', 'md5': 'f576a797a5b7a5e4e4bbdfc25a6a6870', 'info_dict': { @@ -74,7 +80,10 @@ class LecturioIE(LecturioBaseIE): 'title': 'Important Concepts and Terms – Introduction to Microbiology', }, 'skip': 'Requires lecturio account credentials', - } + }, { + 'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag', + 'only_matching': True, + }] _CC_LANGS = { 'German': 'de', @@ -86,7 +95,8 @@ class LecturioIE(LecturioBaseIE): } def _real_extract(self, url): - display_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') or mobj.group('id_de') webpage = self._download_webpage( 'https://app.lecturio.com/en/lecture/%s/player.html' % display_id, @@ -190,3 +200,30 @@ class LecturioCourseIE(LecturioBaseIE): 'title', default=None) return self.playlist_result(entries, display_id, title) + + +class LecturioDeCourseIE(LecturioBaseIE): + _VALID_URL = r'https://(?:www\.)?lecturio\.de/[^/]+/(?P[^/?#&]+)\.kurs' + _TEST = { + 'url': 'https://www.lecturio.de/jura/grundrechte.kurs', + 'only_matching': True, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + entries = [] + for mobj in re.finditer( + r'(?s)]+\bdata-lecture-id=["\'](?P\d+).+?\bhref=(["\'])(?P(?:(?!\2).)+\.vortrag)\b[^>]+>', + webpage): + lecture_url = urljoin(url, mobj.group('url')) + lecture_id = mobj.group('id') + entries.append(self.url_result( + lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id)) + + title = self._search_regex( + r']*>([^<]+)', webpage, 'title', default=None) + + return self.playlist_result(entries, display_id, title) From cfd13c4c45f63c408a3e53ac31561c286c9a3acc Mon Sep 17 00:00:00 2001 From: Daan van Vugt Date: Mon, 17 Dec 2018 18:03:00 +0100 Subject: [PATCH 382/558] [mediasite] Relax _VALID_URL --- youtube_dl/extractor/mediasite.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/mediasite.py b/youtube_dl/extractor/mediasite.py index 84876b883..de37df0c6 100644 --- a/youtube_dl/extractor/mediasite.py +++ b/youtube_dl/extractor/mediasite.py @@ -21,7 +21,7 @@ from ..utils import ( class MediasiteIE(InfoExtractor): - _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/Play/(?P[0-9a-f]{32,34})(?P\?[^#]+|)' + _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/(?:Play|Showcase/livebroadcast/Presentation)/(?P[0-9a-f]{32,34})(?P\?[^#]+|)' _TESTS = [ { 'url': 'https://hitsmediaweb.h-its.org/mediasite/Play/2db6c271681e4f199af3c60d1f82869b1d', @@ -84,7 +84,11 @@ class MediasiteIE(InfoExtractor): 'timestamp': 1333983600, 'duration': 7794, } - } + }, + { + 'url': 'https://collegerama.tudelft.nl/Mediasite/Showcase/livebroadcast/Presentation/ada7020854f743c49fbb45c9ec7dbb351d', + 'only_matching': True, + }, ] # look in Mediasite.Core.js (Mediasite.ContentStreamType[*]) From 4ee184545455d1ebf4a9f97f86ade2c4a3b3e03b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 18 Dec 2018 01:55:13 +0700 Subject: [PATCH 383/558] [mediasite] Extend _VALID_URL even more --- youtube_dl/extractor/mediasite.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/mediasite.py b/youtube_dl/extractor/mediasite.py index de37df0c6..ef9628e65 100644 --- a/youtube_dl/extractor/mediasite.py +++ b/youtube_dl/extractor/mediasite.py @@ -21,7 +21,7 @@ from ..utils import ( class MediasiteIE(InfoExtractor): - _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/(?:Play|Showcase/livebroadcast/Presentation)/(?P[0-9a-f]{32,34})(?P\?[^#]+|)' + _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/(?:Play|Showcase/(?:default|livebroadcast)/Presentation)/(?P[0-9a-f]{32,34})(?P\?[^#]+|)' _TESTS = [ { 'url': 'https://hitsmediaweb.h-its.org/mediasite/Play/2db6c271681e4f199af3c60d1f82869b1d', @@ -89,6 +89,10 @@ class MediasiteIE(InfoExtractor): 'url': 'https://collegerama.tudelft.nl/Mediasite/Showcase/livebroadcast/Presentation/ada7020854f743c49fbb45c9ec7dbb351d', 'only_matching': True, }, + { + 'url': 'https://mediasite.ntnu.no/Mediasite/Showcase/default/Presentation/7d8b913259334b688986e970fae6fcb31d', + 'only_matching': True, + }, ] # look in Mediasite.Core.js (Mediasite.ContentStreamType[*]) From 65e29cdac3f3ee14e07c200293438426b1135719 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 18 Dec 2018 22:46:19 +0100 Subject: [PATCH 384/558] [twitter] pass referer with card request(closes #18579) --- youtube_dl/extractor/twitter.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py index de41065d6..41d0b6be8 100644 --- a/youtube_dl/extractor/twitter.py +++ b/youtube_dl/extractor/twitter.py @@ -171,7 +171,8 @@ class TwitterCardIE(TwitterBaseIE): urls.append('https://twitter.com/i/videos/' + video_id) for u in urls: - webpage = self._download_webpage(u, video_id) + webpage = self._download_webpage( + u, video_id, headers={'Referer': 'https://twitter.com/'}) iframe_url = self._html_search_regex( r']+src="((?:https?:)?//(?:www\.youtube\.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"', From 904bb599be0fcf5fa861f17eee757c3c9494208b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Elan=20Ruusam=C3=A4e?= Date: Wed, 19 Dec 2018 22:22:10 +0200 Subject: [PATCH 385/558] [README.md] Add flake8 instructions --- README.md | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index a1d2904c0..b3c39bf66 100644 --- a/README.md +++ b/README.md @@ -1025,15 +1025,19 @@ After you have ensured this site is distributing its content legally, you can fo 5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py). 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in. 7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want. -8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+. -9. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this: +8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](http://flake8.pycqa.org/en/latest/index.html#quickstart): + + $ flake8 youtube_dl/extractor/yourextractor.py + +9. Make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+. +10. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this: $ git add youtube_dl/extractor/extractors.py $ git add youtube_dl/extractor/yourextractor.py $ git commit -m '[yourextractor] Add new extractor' $ git push origin yourextractor -10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. +11. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. In any case, thank you very much for your contributions! From 835e45abab88e2a1661b86be255e06323e88ec7a Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 19 Dec 2018 22:07:37 +0100 Subject: [PATCH 386/558] [crackle] extract ism and http formats --- youtube_dl/extractor/crackle.py | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/youtube_dl/extractor/crackle.py b/youtube_dl/extractor/crackle.py index 8dd9d6687..f73ef6b63 100644 --- a/youtube_dl/extractor/crackle.py +++ b/youtube_dl/extractor/crackle.py @@ -48,6 +48,21 @@ class CrackleIE(InfoExtractor): 'only_matching': True, }] + _MEDIA_FILE_SLOTS = { + '360p.mp4': { + 'width': 640, + 'height': 360, + }, + '480p.mp4': { + 'width': 768, + 'height': 432, + }, + '480p_1mbps.mp4': { + 'width': 852, + 'height': 480, + }, + } + def _real_extract(self, url): video_id = self._match_id(url) @@ -95,6 +110,20 @@ class CrackleIE(InfoExtractor): elif ext == 'mpd': formats.extend(self._extract_mpd_formats( format_url, video_id, mpd_id='dash', fatal=False)) + elif format_url.endswith('.ism/Manifest'): + formats.extend(self._extract_ism_formats( + format_url, video_id, ism_id='mss', fatal=False)) + else: + mfs_path = e.get('Type') + mfs_info = self._MEDIA_FILE_SLOTS.get(mfs_path) + if not mfs_info: + continue + formats.append({ + 'url': format_url, + 'format_id': 'http-' + mfs_path.split('.')[0], + 'width': mfs_info['width'], + 'height': mfs_info['height'], + }) self._sort_formats(formats) description = media.get('Description') From e1a0628797e2dc7e5e032f853ab4ddc6a7a08020 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Thu, 20 Dec 2018 23:22:51 +0100 Subject: [PATCH 387/558] [liveleak] add support for another embed type and restore original format extraction --- youtube_dl/extractor/liveleak.py | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/liveleak.py b/youtube_dl/extractor/liveleak.py index 26671753c..22a067e40 100644 --- a/youtube_dl/extractor/liveleak.py +++ b/youtube_dl/extractor/liveleak.py @@ -87,7 +87,7 @@ class LiveLeakIE(InfoExtractor): @staticmethod def _extract_urls(webpage): return re.findall( - r']+src="(https?://(?:\w+\.)?liveleak\.com/ll_embed\?[^"]*[if]=[\w_]+[^"]+)"', + r']+src="(https?://(?:\w+\.)?liveleak\.com/ll_embed\?[^"]*[ift]=[\w_]+[^"]+)"', webpage) def _real_extract(self, url): @@ -120,13 +120,27 @@ class LiveLeakIE(InfoExtractor): } for idx, info_dict in enumerate(entries): + formats = [] for a_format in info_dict['formats']: if not a_format.get('height'): a_format['height'] = int_or_none(self._search_regex( r'([0-9]+)p\.mp4', a_format['url'], 'height label', default=None)) + formats.append(a_format) - self._sort_formats(info_dict['formats']) + # Removing '.*.mp4' gives the raw video, which is essentially + # the same video without the LiveLeak logo at the top (see + # https://github.com/rg3/youtube-dl/pull/4768) + orig_url = re.sub(r'\.mp4\.[^.]+', '', a_format['url']) + if a_format['url'] != orig_url: + format_id = a_format.get('format_id') + formats.append({ + 'format_id': 'original' + ('-' + format_id if format_id else ''), + 'url': orig_url, + 'preference': 1, + }) + self._sort_formats(formats) + info_dict['formats'] = formats # Don't append entry ID for one-video pages to keep backward compatibility if len(entries) > 1: @@ -146,7 +160,7 @@ class LiveLeakIE(InfoExtractor): class LiveLeakEmbedIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?liveleak\.com/ll_embed\?.*?\b(?P[if])=(?P[\w_]+)' + _VALID_URL = r'https?://(?:www\.)?liveleak\.com/ll_embed\?.*?\b(?P[ift])=(?P[\w_]+)' # See generic.py for actual test cases _TESTS = [{ @@ -158,15 +172,14 @@ class LiveLeakEmbedIE(InfoExtractor): }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - kind, video_id = mobj.group('kind', 'id') + kind, video_id = re.match(self._VALID_URL, url).groups() if kind == 'f': webpage = self._download_webpage(url, video_id) liveleak_url = self._search_regex( - r'logourl\s*:\s*(?P[\'"])(?P%s)(?P=q1)' % LiveLeakIE._VALID_URL, + r'(?:logourl\s*:\s*|window\.open\()(?P[\'"])(?P%s)(?P=q1)' % LiveLeakIE._VALID_URL, webpage, 'LiveLeak URL', group='url') - elif kind == 'i': - liveleak_url = 'http://www.liveleak.com/view?i=%s' % video_id + else: + liveleak_url = 'http://www.liveleak.com/view?%s=%s' % (kind, video_id) return self.url_result(liveleak_url, ie=LiveLeakIE.ie_key()) From 4273caf5c7e4a79783106938802c1f4e1aa9c950 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 23 Dec 2018 16:38:16 +0700 Subject: [PATCH 388/558] [youtube] Extend html5 player regex (closes #17516) --- youtube_dl/extractor/youtube.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 44c25c11c..906774875 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1834,7 +1834,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): else: player_version = self._search_regex( [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', - r'(?:www|player)-([^/]+)(?:/[a-z]{2}_[A-Z]{2})?/base\.js'], + r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2}_[A-Z]{2})?/base\.js'], player_url, 'html5 player', fatal=False) player_desc = 'html5 player %s' % player_version From 63529e935cf5f87e6080607ef9d9196fe435e092 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 23 Dec 2018 16:57:10 +0700 Subject: [PATCH 389/558] [youtube] Relax html5 player regexes (closes #18465, closes #18466) --- youtube_dl/extractor/youtube.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 906774875..954853e00 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1105,7 +1105,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def _extract_signature_function(self, video_id, player_url, example_sig): id_m = re.match( - r'.*?-(?P[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2}_[A-Z]{2})?/base)?\.(?P[a-z]+)$', + r'.*?-(?P[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P[a-z]+)$', player_url) if not id_m: raise ExtractorError('Cannot identify player %r' % player_url) @@ -1834,7 +1834,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): else: player_version = self._search_regex( [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', - r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2}_[A-Z]{2})?/base\.js'], + r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'], player_url, 'html5 player', fatal=False) player_desc = 'html5 player %s' % player_version From 825cd268a3a02e80a9c36dada664d25074243d26 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 26 Dec 2018 09:30:48 +0100 Subject: [PATCH 390/558] [youtube] detect DRM protected videos(#1774) --- youtube_dl/extractor/youtube.py | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 954853e00..4b06cb597 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1077,6 +1077,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'url': 'https://invidio.us/watch?v=BaW_jenozKc', 'only_matching': True, }, + { + # DRM protected + 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc', + 'only_matching': True, + } ] def __init__(self, *args, **kwargs): @@ -1673,6 +1678,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): '"token" parameter not in video info for unknown reason', video_id=video_id) + if video_info.get('license_info'): + raise ExtractorError('This video is DRM protected.', expected=True) + video_details = try_get( player_response, lambda x: x['videoDetails'], dict) or {} From 140a13f5de1ff8e6bf7ba0d27b38063a2b20fa33 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 26 Dec 2018 10:55:28 +0100 Subject: [PATCH 391/558] [youtube] extract more format metadata --- youtube_dl/extractor/youtube.py | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 4b06cb597..ac3b4fc17 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1794,6 +1794,25 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'height': int_or_none(width_height[1]), } q = qualities(['small', 'medium', 'hd720']) + streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list) + if streaming_formats: + for fmt in streaming_formats: + itag = str_or_none(fmt.get('itag')) + if not itag: + continue + quality = fmt.get('quality') + quality_label = fmt.get('qualityLabel') or quality + formats_spec[itag] = { + 'asr': int_or_none(fmt.get('audioSampleRate')), + 'filesize': int_or_none(fmt.get('contentLength')), + 'format_note': quality_label, + 'fps': int_or_none(fmt.get('fps')), + 'height': int_or_none(fmt.get('height')), + 'quality': q(quality), + # bitrate for itag 43 is always 2147483647 + 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None, + 'width': int_or_none(fmt.get('width')), + } formats = [] for url_data_str in encoded_url_map.split(','): url_data = compat_parse_qs(url_data_str) @@ -1876,7 +1895,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): filesize = int_or_none(url_data.get( 'clen', [None])[0]) or _extract_filesize(url) - quality = url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0] + quality = url_data.get('quality', [None])[0] more_fields = { 'filesize': filesize, @@ -1884,7 +1903,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'width': width, 'height': height, 'fps': int_or_none(url_data.get('fps', [None])[0]), - 'format_note': quality, + 'format_note': url_data.get('quality_label', [None])[0] or quality, 'quality': q(quality), } for key, value in more_fields.items(): From c2dd2dc086653f46defe0bc6bee9b5e339e67dea Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 31 Dec 2018 19:57:01 +0700 Subject: [PATCH 392/558] [youtube] Unescape HTML for series (closes #18641) --- youtube_dl/extractor/youtube.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index ac3b4fc17..539ff6ff2 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -2043,7 +2043,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): r']+id="watch7-headline"[^>]*>\s*]*>.*?>(?P[^<]+)\s*S(?P\d+)\s*•\s*E(?P\d+)', video_webpage) if m_episode: - series = m_episode.group('series') + series = unescapeHTML(m_episode.group('series')) season_number = int(m_episode.group('season')) episode_number = int(m_episode.group('episode')) else: From e4d51e751e361faaedaa50baf37501106459ab73 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 31 Dec 2018 20:59:53 +0700 Subject: [PATCH 393/558] [beeg] Fix extraction (closes #18610, closes #18626) --- youtube_dl/extractor/beeg.py | 75 ++++++------------------------------ 1 file changed, 11 insertions(+), 64 deletions(-) diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py index bf22a41b7..1086d7632 100644 --- a/youtube_dl/extractor/beeg.py +++ b/youtube_dl/extractor/beeg.py @@ -1,15 +1,10 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import ( - compat_chr, - compat_ord, - compat_urllib_parse_unquote, -) +from ..compat import compat_str from ..utils import ( int_or_none, - parse_iso8601, - urljoin, + unified_timestamp, ) @@ -36,29 +31,9 @@ class BeegIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - cpl_url = self._search_regex( - r']+src=(["\'])(?P(?:/static|(?:https?:)?//static\.beeg\.com)/cpl/\d+\.js.*?)\1', - webpage, 'cpl', default=None, group='url') - - cpl_url = urljoin(url, cpl_url) - - beeg_version, beeg_salt = [None] * 2 - - if cpl_url: - cpl = self._download_webpage( - self._proto_relative_url(cpl_url), video_id, - 'Downloading cpl JS', fatal=False) - if cpl: - beeg_version = int_or_none(self._search_regex( - r'beeg_version\s*=\s*([^\b]+)', cpl, - 'beeg version', default=None)) or self._search_regex( - r'/(\d+)\.js', cpl_url, 'beeg version', default=None) - beeg_salt = self._search_regex( - r'beeg_salt\s*=\s*(["\'])(?P.+?)\1', cpl, 'beeg salt', - default=None, group='beeg_salt') - - beeg_version = beeg_version or '2185' - beeg_salt = beeg_salt or 'pmweAkq8lAYKdfWcFCUj0yoVgoPlinamH5UE1CB3H' + beeg_version = self._search_regex( + r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version', + default='1546225636701') for api_path in ('', 'api.'): video = self._download_json( @@ -68,37 +43,6 @@ class BeegIE(InfoExtractor): if video: break - def split(o, e): - def cut(s, x): - n.append(s[:x]) - return s[x:] - n = [] - r = len(o) % e - if r > 0: - o = cut(o, r) - while len(o) > e: - o = cut(o, e) - n.append(o) - return n - - def decrypt_key(key): - # Reverse engineered from http://static.beeg.com/cpl/1738.js - a = beeg_salt - e = compat_urllib_parse_unquote(key) - o = ''.join([ - compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 21) - for n in range(len(e))]) - return ''.join(split(o, 3)[::-1]) - - def decrypt_url(encrypted_url): - encrypted_url = self._proto_relative_url( - encrypted_url.replace('{DATA_MARKERS}', ''), 'https:') - key = self._search_regex( - r'/key=(.*?)%2Cend=', encrypted_url, 'key', default=None) - if not key: - return encrypted_url - return encrypted_url.replace(key, decrypt_key(key)) - formats = [] for format_id, video_url in video.items(): if not video_url: @@ -108,18 +52,20 @@ class BeegIE(InfoExtractor): if not height: continue formats.append({ - 'url': decrypt_url(video_url), + 'url': self._proto_relative_url( + video_url.replace('{DATA_MARKERS}', 'data=pc_XX__%s_0' % beeg_version), 'https:'), 'format_id': format_id, 'height': int(height), }) self._sort_formats(formats) title = video['title'] - video_id = video.get('id') or video_id + video_id = compat_str(video.get('id') or video_id) display_id = video.get('code') description = video.get('desc') + series = video.get('ps_name') - timestamp = parse_iso8601(video.get('date'), ' ') + timestamp = unified_timestamp(video.get('date')) duration = int_or_none(video.get('duration')) tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None @@ -129,6 +75,7 @@ class BeegIE(InfoExtractor): 'display_id': display_id, 'title': title, 'description': description, + 'series': series, 'timestamp': timestamp, 'duration': duration, 'tags': tags, From 4e1ddc8da9b318873d71d0283838af6aec1bc98d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 31 Dec 2018 21:05:07 +0700 Subject: [PATCH 394/558] [npo:live] Add support for npostart.nl (closes #18644) --- youtube_dl/extractor/npo.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index c2cb85a73..5a427c396 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -363,7 +363,7 @@ class NPOIE(NPOBaseIE): class NPOLiveIE(NPOBaseIE): IE_NAME = 'npo.nl:live' - _VALID_URL = r'https?://(?:www\.)?npo\.nl/live(?:/(?P[^/?#&]+))?' + _VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P[^/?#&]+))?' _TESTS = [{ 'url': 'http://www.npo.nl/live/npo-1', @@ -380,6 +380,9 @@ class NPOLiveIE(NPOBaseIE): }, { 'url': 'http://www.npo.nl/live', 'only_matching': True, + }, { + 'url': 'https://www.npostart.nl/live/npo-1', + 'only_matching': True, }] def _real_extract(self, url): From 373941c5f0c163bf9f2fbbe7f65ee549a228720f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 31 Dec 2018 23:20:40 +0700 Subject: [PATCH 395/558] [bbc] Add support for another embed pattern (closes #18643) --- youtube_dl/extractor/bbc.py | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index abcfa301d..eac9a5a46 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -795,6 +795,15 @@ class BBCIE(BBCCoUkIE): 'uploader': 'Radio 3', 'uploader_id': 'bbc_radio_three', }, + }, { + 'url': 'http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227', + 'info_dict': { + 'id': 'p06w9tws', + 'ext': 'mp4', + 'title': 'md5:2fabf12a726603193a2879a055f72514', + 'description': 'Learn English words and phrases from this story', + }, + 'add_ie': [BBCCoUkIE.ie_key()], }] @classmethod @@ -945,6 +954,15 @@ class BBCIE(BBCCoUkIE): if entries: return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) + # http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227 + group_id = self._search_regex( + r']+\bclass=["\']video["\'][^>]+\bdata-pid=["\'](%s)' % self._ID_REGEX, + webpage, 'group id', default=None) + if playlist_id: + return self.url_result( + 'https://www.bbc.co.uk/programmes/%s' % group_id, + ie=BBCCoUkIE.ie_key()) + # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) programme_id = self._search_regex( [r'data-(?:video-player|media)-vpid="(%s)"' % self._ID_REGEX, From 32ac3d49ae83fe933515096a74068a8033131f4d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 31 Dec 2018 23:57:46 +0700 Subject: [PATCH 396/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/ChangeLog b/ChangeLog index 510013e89..31458dbd9 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,23 @@ +version + +Extractors ++ [bbc] Add support for another embed pattern (#18643) ++ [npo:live] Add support for npostart.nl (#18644) +* [beeg] Fix extraction (#18610, #18626) +* [youtube] Unescape HTML for series (#18641) ++ [youtube] Extract more format metadata +* [youtube] Detect DRM protected videos (#1774) +* [youtube] Relax HTML5 player regular expressions (#18465, #18466) +* [youtube] Extend HTML5 player regular expression (#17516) ++ [liveleak] Add support for another embed type and restore original + format extraction ++ [crackle] Extract ISM and HTTP formats ++ [twitter] Pass Referer with card request (#18579) +* [mediasite] Extend URL regular expression (#18558) ++ [lecturio] Add support for lecturio.de (#18562) ++ [discovery] Add support for Scripps Networks watch domains (#17947) + + version 2018.12.17 Extractors From 9d9daed4647c0a0798adee5a580e9fd95478cf6a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 31 Dec 2018 23:59:52 +0700 Subject: [PATCH 397/558] release 2018.12.31 --- .github/ISSUE_TEMPLATE.md | 6 +++--- CONTRIBUTING.md | 10 +++++++--- ChangeLog | 2 +- docs/supportedsites.md | 1 + youtube_dl/version.py | 2 +- 5 files changed, 13 insertions(+), 8 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index b84559932..b2fe6ee6a 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.12.17*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.12.17** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.12.31*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.12.31** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.12.17 +[debug] youtube-dl version 2018.12.31 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index cba87190d..24617264c 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -153,15 +153,19 @@ After you have ensured this site is distributing its content legally, you can fo 5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py). 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in. 7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want. -8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+. -9. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this: +8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](http://flake8.pycqa.org/en/latest/index.html#quickstart): + + $ flake8 youtube_dl/extractor/yourextractor.py + +9. Make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+. +10. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this: $ git add youtube_dl/extractor/extractors.py $ git add youtube_dl/extractor/yourextractor.py $ git commit -m '[yourextractor] Add new extractor' $ git push origin yourextractor -10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. +11. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. In any case, thank you very much for your contributions! diff --git a/ChangeLog b/ChangeLog index 31458dbd9..72bfe2110 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2018.12.31 Extractors + [bbc] Add support for another embed pattern (#18643) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 31d20f255..e92064432 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -438,6 +438,7 @@ - **Lecture2Go** - **Lecturio** - **LecturioCourse** + - **LecturioDeCourse** - **LEGO** - **Lemonde** - **Lenta** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 0461aac0c..87de5848d 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.12.17' +__version__ = '2018.12.31' From 6b688b8942a0bd18b2a3835e69a903f1eeffee2a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 1 Jan 2019 18:12:44 +0700 Subject: [PATCH 398/558] [bitchute] Fix extraction (closes #18567) --- youtube_dl/extractor/bitchute.py | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py index 43b4732aa..aa034355a 100644 --- a/youtube_dl/extractor/bitchute.py +++ b/youtube_dl/extractor/bitchute.py @@ -5,7 +5,10 @@ import itertools import re from .common import InfoExtractor -from ..utils import urlencode_postdata +from ..utils import ( + orderedSet, + urlencode_postdata, +) class BitChuteIE(InfoExtractor): @@ -43,10 +46,15 @@ class BitChuteIE(InfoExtractor): 'description', webpage, 'title', default=None) or self._og_search_description(webpage) + format_urls = [] + for mobj in re.finditer( + r'addWebSeed\s*\(\s*(["\'])(?P(?:(?!\1).)+)\1', webpage): + format_urls.append(mobj.group('url')) + format_urls.extend(re.findall(r'as=(https?://[^&"\']+)', webpage)) + formats = [ - {'url': mobj.group('url')} - for mobj in re.finditer( - r'addWebSeed\s*\(\s*(["\'])(?P(?:(?!\1).)+)\1', webpage)] + {'url': format_url} + for format_url in orderedSet(format_urls)] self._sort_formats(formats) description = self._html_search_regex( From 38d15ba7f981cc82db91edcbf05ea3844082d045 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 1 Jan 2019 20:31:48 +0700 Subject: [PATCH 399/558] [manyvids] Fix extraction (closes #18604, closes #18614) --- youtube_dl/extractor/manyvids.py | 62 +++++++++++++++++++++++++++----- 1 file changed, 53 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/manyvids.py b/youtube_dl/extractor/manyvids.py index b94b3c2ab..e8d7163e4 100644 --- a/youtube_dl/extractor/manyvids.py +++ b/youtube_dl/extractor/manyvids.py @@ -2,12 +2,18 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + determine_ext, + int_or_none, + str_to_int, + urlencode_postdata, +) class ManyVidsIE(InfoExtractor): _VALID_URL = r'(?i)https?://(?:www\.)?manyvids\.com/video/(?P\d+)' - _TEST = { + _TESTS = [{ + # preview video 'url': 'https://www.manyvids.com/Video/133957/everthing-about-me/', 'md5': '03f11bb21c52dd12a05be21a5c7dcc97', 'info_dict': { @@ -17,7 +23,18 @@ class ManyVidsIE(InfoExtractor): 'view_count': int, 'like_count': int, }, - } + }, { + # full video + 'url': 'https://www.manyvids.com/Video/935718/MY-FACE-REVEAL/', + 'md5': 'f3e8f7086409e9b470e2643edb96bdcc', + 'info_dict': { + 'id': '935718', + 'ext': 'mp4', + 'title': 'MY FACE REVEAL', + 'view_count': int, + 'like_count': int, + }, + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -28,12 +45,41 @@ class ManyVidsIE(InfoExtractor): r'data-(?:video-filepath|meta-video)\s*=s*(["\'])(?P(?:(?!\1).)+)\1', webpage, 'video URL', group='url') - title = '%s (Preview)' % self._html_search_regex( - r']+class="m-a-0"[^>]*>([^<]+)', webpage, 'title') + title = self._html_search_regex( + (r']+class=["\']item-title[^>]+>([^<]+)', + r']+class=["\']h2 m-0["\'][^>]*>([^<]+)'), + webpage, 'title', default=None) or self._html_search_meta( + 'twitter:title', webpage, 'title', fatal=True) + + if any(p in webpage for p in ('preview_videos', '_preview.mp4')): + title += ' (Preview)' + + mv_token = self._search_regex( + r'data-mvtoken=(["\'])(?P(?:(?!\1).)+)\1', webpage, + 'mv token', default=None, group='value') + + if mv_token: + # Sets some cookies + self._download_webpage( + 'https://www.manyvids.com/includes/ajax_repository/you_had_me_at_hello.php', + video_id, fatal=False, data=urlencode_postdata({ + 'mvtoken': mv_token, + 'vid': video_id, + }), headers={ + 'Referer': url, + 'X-Requested-With': 'XMLHttpRequest' + }) + + if determine_ext(video_url) == 'm3u8': + formats = self._extract_m3u8_formats( + video_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + else: + formats = [{'url': video_url}] like_count = int_or_none(self._search_regex( r'data-likes=["\'](\d+)', webpage, 'like count', default=None)) - view_count = int_or_none(self._html_search_regex( + view_count = str_to_int(self._html_search_regex( r'(?s)]+class="views-wrapper"[^>]*>(.+?) Date: Sun, 30 Dec 2018 14:30:36 +0100 Subject: [PATCH 400/558] [rmcdecouverte] Update _VALID_URL (closes #18595) --- youtube_dl/extractor/rmcdecouverte.py | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/rmcdecouverte.py b/youtube_dl/extractor/rmcdecouverte.py index e921ca3e6..c44b90274 100644 --- a/youtube_dl/extractor/rmcdecouverte.py +++ b/youtube_dl/extractor/rmcdecouverte.py @@ -10,18 +10,18 @@ from ..compat import ( class RMCDecouverteIE(InfoExtractor): - _VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/mediaplayer-replay.*?\bid=(?P\d+)' + _VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/.+/program_(?P\d+)' _TEST = { - 'url': 'http://rmcdecouverte.bfmtv.com/mediaplayer-replay/?id=13502&title=AQUAMEN:LES%20ROIS%20DES%20AQUARIUMS%20:UN%20DELICIEUX%20PROJET', + 'url': 'https://rmcdecouverte.bfmtv.com/wheeler-dealers-occasions-a-saisir/program_2566/', 'info_dict': { - 'id': '5419055995001', + 'id': '5983675500001', 'ext': 'mp4', - 'title': 'UN DELICIEUX PROJET', - 'description': 'md5:63610df7c8b1fc1698acd4d0d90ba8b5', + 'title': 'CORVETTE', + 'description': 'md5:c1e8295521e45ffebf635d6a7658f506', 'uploader_id': '1969646226001', - 'upload_date': '20170502', - 'timestamp': 1493745308, + 'upload_date': '20181226', + 'timestamp': 1545861635, }, 'params': { 'skip_download': True, From d9f1123c08e21c7170b906c7de2562b7293f7a3c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 1 Jan 2019 20:49:13 +0700 Subject: [PATCH 401/558] [rmcdecouverte] Improve, bypass geo restriction and add support for live (closes #18697) --- youtube_dl/extractor/rmcdecouverte.py | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/rmcdecouverte.py b/youtube_dl/extractor/rmcdecouverte.py index c44b90274..c3623edcc 100644 --- a/youtube_dl/extractor/rmcdecouverte.py +++ b/youtube_dl/extractor/rmcdecouverte.py @@ -1,18 +1,21 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from .brightcove import BrightcoveLegacyIE from ..compat import ( compat_parse_qs, compat_urlparse, ) +from ..utils import smuggle_url class RMCDecouverteIE(InfoExtractor): - _VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/.+/program_(?P\d+)' + _VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/(?:(?:[^/]+/)*program_(?P\d+)|(?Pmediaplayer-direct))' - _TEST = { + _TESTS = [{ 'url': 'https://rmcdecouverte.bfmtv.com/wheeler-dealers-occasions-a-saisir/program_2566/', 'info_dict': { 'id': '5983675500001', @@ -27,12 +30,17 @@ class RMCDecouverteIE(InfoExtractor): 'skip_download': True, }, 'skip': 'only available for a week', - } + }, { + # live, geo restricted, bypassable + 'url': 'https://rmcdecouverte.bfmtv.com/mediaplayer-direct/', + 'only_matching': True, + }] BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1969646226001/default_default/index.html?videoId=%s' def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') or mobj.group('live_id') + webpage = self._download_webpage(url, display_id) brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage) if brightcove_legacy_url: brightcove_id = compat_parse_qs(compat_urlparse.urlparse( @@ -41,5 +49,7 @@ class RMCDecouverteIE(InfoExtractor): brightcove_id = self._search_regex( r'data-video-id=["\'](\d+)', webpage, 'brightcove id') return self.url_result( - self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', - brightcove_id) + smuggle_url( + self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, + {'geo_countries': ['FR']}), + 'BrightcoveNew', brightcove_id) From 9b5c8751eeb10fd41c560696d73fec3401055ddc Mon Sep 17 00:00:00 2001 From: iwconfig Date: Tue, 1 Jan 2019 15:39:18 +0100 Subject: [PATCH 402/558] [extractors] Add missing age limits --- youtube_dl/extractor/cammodels.py | 2 ++ youtube_dl/extractor/camtube.py | 2 ++ youtube_dl/extractor/camwithher.py | 2 ++ youtube_dl/extractor/yourporn.py | 2 ++ 4 files changed, 8 insertions(+) diff --git a/youtube_dl/extractor/cammodels.py b/youtube_dl/extractor/cammodels.py index 79350817f..1eb81b75e 100644 --- a/youtube_dl/extractor/cammodels.py +++ b/youtube_dl/extractor/cammodels.py @@ -14,6 +14,7 @@ class CamModelsIE(InfoExtractor): _TESTS = [{ 'url': 'https://www.cammodels.com/cam/AutumnKnight/', 'only_matching': True, + 'age_limit': 18 }] def _real_extract(self, url): @@ -93,4 +94,5 @@ class CamModelsIE(InfoExtractor): 'title': self._live_title(user_id), 'is_live': True, 'formats': formats, + 'age_limit': 18 } diff --git a/youtube_dl/extractor/camtube.py b/youtube_dl/extractor/camtube.py index c7d40f849..b3be3bdcf 100644 --- a/youtube_dl/extractor/camtube.py +++ b/youtube_dl/extractor/camtube.py @@ -20,6 +20,7 @@ class CamTubeIE(InfoExtractor): 'duration': 1274, 'timestamp': 1528018608, 'upload_date': '20180603', + 'age_limit': 18 }, 'params': { 'skip_download': True, @@ -66,4 +67,5 @@ class CamTubeIE(InfoExtractor): 'like_count': like_count, 'creator': creator, 'formats': formats, + 'age_limit': 18 } diff --git a/youtube_dl/extractor/camwithher.py b/youtube_dl/extractor/camwithher.py index afbc5ea26..bbc5205fd 100644 --- a/youtube_dl/extractor/camwithher.py +++ b/youtube_dl/extractor/camwithher.py @@ -25,6 +25,7 @@ class CamWithHerIE(InfoExtractor): 'comment_count': int, 'uploader': 'MileenaK', 'upload_date': '20160322', + 'age_limit': 18, }, 'params': { 'skip_download': True, @@ -84,4 +85,5 @@ class CamWithHerIE(InfoExtractor): 'comment_count': comment_count, 'uploader': uploader, 'upload_date': upload_date, + 'age_limit': 18 } diff --git a/youtube_dl/extractor/yourporn.py b/youtube_dl/extractor/yourporn.py index a9951f3b8..432d1fff4 100644 --- a/youtube_dl/extractor/yourporn.py +++ b/youtube_dl/extractor/yourporn.py @@ -14,6 +14,7 @@ class YourPornIE(InfoExtractor): 'ext': 'mp4', 'title': 'md5:c9f43630bd968267672651ba905a7d35', 'thumbnail': r're:^https?://.*\.jpg$', + 'age_limit': 18 }, } @@ -38,4 +39,5 @@ class YourPornIE(InfoExtractor): 'url': video_url, 'title': title, 'thumbnail': thumbnail, + 'age_limit': 18 } From 0e713dbb116493181218c38dc03716feda2fa7d9 Mon Sep 17 00:00:00 2001 From: biwubo <45994985+biwubo@users.noreply.github.com> Date: Tue, 1 Jan 2019 15:48:06 +0000 Subject: [PATCH 403/558] [acast:channel] Add support for play.acast.com (closes #18587) --- youtube_dl/extractor/acast.py | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/youtube_dl/extractor/acast.py b/youtube_dl/extractor/acast.py index b32f74a37..c4362be88 100644 --- a/youtube_dl/extractor/acast.py +++ b/youtube_dl/extractor/acast.py @@ -79,17 +79,27 @@ class ACastIE(InfoExtractor): class ACastChannelIE(InfoExtractor): IE_NAME = 'acast:channel' - _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P[^/#?]+)' - _TEST = { - 'url': 'https://www.acast.com/condenasttraveler', + _VALID_URL = r'''(?x) + https?:// + (?: + (?:www\.)?acast\.com/| + play\.acast\.com/s/ + ) + (?P[^/#?]+) + ''' + _TESTS = [{ + 'url': 'https://www.acast.com/todayinfocus', 'info_dict': { - 'id': '50544219-29bb-499e-a083-6087f4cb7797', - 'title': 'Condé Nast Traveler Podcast', - 'description': 'md5:98646dee22a5b386626ae31866638fbd', + 'id': '4efc5294-5385-4847-98bd-519799ce5786', + 'title': 'Today in Focus', + 'description': 'md5:9ba5564de5ce897faeb12963f4537a64', }, - 'playlist_mincount': 20, - } - _API_BASE_URL = 'https://www.acast.com/api/' + 'playlist_mincount': 35, + }, { + 'url': 'http://play.acast.com/s/ft-banking-weekly', + 'only_matching': True, + }] + _API_BASE_URL = 'https://play.acast.com/api/' _PAGE_SIZE = 10 @classmethod @@ -102,7 +112,7 @@ class ACastChannelIE(InfoExtractor): channel_slug, note='Download page %d of channel data' % page) for cast in casts: yield self.url_result( - 'https://www.acast.com/%s/%s' % (channel_slug, cast['url']), + 'https://play.acast.com/s/%s/%s' % (channel_slug, cast['url']), 'ACast', cast['id']) def _real_extract(self, url): From 696f4e41149a8f91e963d33e2f6ea9bc835f2260 Mon Sep 17 00:00:00 2001 From: Sergey M Date: Tue, 1 Jan 2019 23:13:39 +0700 Subject: [PATCH 404/558] [README.md] Add more guide lines for regular expressions --- README.md | 28 +++++++++++++++++++++++++--- 1 file changed, 25 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index b3c39bf66..bdc5faeec 100644 --- a/README.md +++ b/README.md @@ -1133,11 +1133,33 @@ title = meta.get('title') or self._og_search_title(webpage) This code will try to extract from `meta` first and if it fails it will try extracting `og:title` from a `webpage`. -### Make regular expressions flexible +### Regular expressions -When using regular expressions try to write them fuzzy and flexible. +#### Don't capture groups you don't use + +Capturing group must be an indication that it's used somewhere in the code. Any group that is not used must be non capturing. + +##### Example + +Don't capture id attribute name here since you can't use it for anything anyway. + +Correct: + +```python +r'(?:id|ID)=(?P\d+)' +``` + +Incorrect: +```python +r'(id|ID)=(?P\d+)' +``` + + +#### Make regular expressions relaxed and flexible + +When using regular expressions try to write them fuzzy, relaxed and flexible, skipping insignificant parts that are more likely to change, allowing both single and double quotes for quoted values and so on. -#### Example +##### Example Say you need to extract `title` from the following HTML code: From 1d803085d730bf2aaf54e5cea2362133b3fdb831 Mon Sep 17 00:00:00 2001 From: v-delta <45652398+v-delta@users.noreply.github.com> Date: Tue, 1 Jan 2019 17:26:59 +0100 Subject: [PATCH 405/558] [yourporn] Fix extraction --- youtube_dl/extractor/yourporn.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/yourporn.py b/youtube_dl/extractor/yourporn.py index 432d1fff4..c8dc29bd8 100644 --- a/youtube_dl/extractor/yourporn.py +++ b/youtube_dl/extractor/yourporn.py @@ -27,7 +27,7 @@ class YourPornIE(InfoExtractor): self._search_regex( r'data-vnfo=(["\'])(?P{.+?})\1', webpage, 'data info', group='data'), - video_id)[video_id]).replace('/cdn/', '/cdn2/') + video_id)[video_id]).replace('/cdn/', '/cdn3/') title = (self._search_regex( r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title', From 8437f5089f2fac85a249c4368c2ea1415955d8b0 Mon Sep 17 00:00:00 2001 From: Sergey M Date: Tue, 1 Jan 2019 23:50:02 +0700 Subject: [PATCH 406/558] [README.md] Add long lines policy to coding conventions --- README.md | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/README.md b/README.md index bdc5faeec..901595444 100644 --- a/README.md +++ b/README.md @@ -1192,6 +1192,25 @@ title = self._search_regex( webpage, 'title', group='title') ``` +### Long lines policy + +There is a soft limit to keep lines of code under 80 characters long. This means it should be respected if possible and if it does not make readability and code maintenance worse. + +For example, you should **never** split long string literals like URLs or some other often copied entities over multiple lines to fit this limit: + +Correct: + +```python +'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4' +``` + +Incorrect: + +```python +'https://www.youtube.com/watch?v=FqZTN594JQw&list=' +'PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4' +``` + ### Use safe conversion functions Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well. From d226c560a6250d03ff5f27d5b078f894d448a0b4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Elan=20Ruusam=C3=A4e?= Date: Tue, 1 Jan 2019 18:56:05 +0200 Subject: [PATCH 407/558] Refactor code to use url_result --- youtube_dl/extractor/audiomack.py | 2 +- youtube_dl/extractor/cnn.py | 12 ++---------- youtube_dl/extractor/freespeech.py | 7 ++----- youtube_dl/extractor/generic.py | 5 +---- youtube_dl/extractor/livestream.py | 5 +---- youtube_dl/extractor/savefrom.py | 7 ++----- youtube_dl/extractor/ted.py | 6 ++---- youtube_dl/extractor/testurl.py | 6 +----- youtube_dl/extractor/wimp.py | 6 +----- 9 files changed, 13 insertions(+), 43 deletions(-) diff --git a/youtube_dl/extractor/audiomack.py b/youtube_dl/extractor/audiomack.py index 62049b921..cc7771354 100644 --- a/youtube_dl/extractor/audiomack.py +++ b/youtube_dl/extractor/audiomack.py @@ -62,7 +62,7 @@ class AudiomackIE(InfoExtractor): # Audiomack wraps a lot of soundcloud tracks in their branded wrapper # if so, pass the work off to the soundcloud extractor if SoundcloudIE.suitable(api_response['url']): - return {'_type': 'url', 'url': api_response['url'], 'ie_key': 'Soundcloud'} + return self.url_result(api_response['url'], SoundcloudIE.ie_key()) return { 'id': compat_str(api_response.get('id', album_url_tag)), diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py index 5fc311f53..774b71055 100644 --- a/youtube_dl/extractor/cnn.py +++ b/youtube_dl/extractor/cnn.py @@ -119,11 +119,7 @@ class CNNBlogsIE(InfoExtractor): def _real_extract(self, url): webpage = self._download_webpage(url, url_basename(url)) cnn_url = self._html_search_regex(r'data-url="(.+?)"', webpage, 'cnn url') - return { - '_type': 'url', - 'url': cnn_url, - 'ie_key': CNNIE.ie_key(), - } + return self.url_result(cnn_url, CNNIE.ie_key()) class CNNArticleIE(InfoExtractor): @@ -145,8 +141,4 @@ class CNNArticleIE(InfoExtractor): def _real_extract(self, url): webpage = self._download_webpage(url, url_basename(url)) cnn_url = self._html_search_regex(r"video:\s*'([^']+)'", webpage, 'cnn url') - return { - '_type': 'url', - 'url': 'http://cnn.com/video/?/video/' + cnn_url, - 'ie_key': CNNIE.ie_key(), - } + return self.url_result('http://cnn.com/video/?/video/' + cnn_url, CNNIE.ie_key()) diff --git a/youtube_dl/extractor/freespeech.py b/youtube_dl/extractor/freespeech.py index 486a49c05..ea9c3e317 100644 --- a/youtube_dl/extractor/freespeech.py +++ b/youtube_dl/extractor/freespeech.py @@ -1,6 +1,7 @@ from __future__ import unicode_literals from .common import InfoExtractor +from .youtube import YoutubeIE class FreespeechIE(InfoExtractor): @@ -27,8 +28,4 @@ class FreespeechIE(InfoExtractor): r'data-video-url="([^"]+)"', webpage, 'youtube url') - return { - '_type': 'url', - 'url': youtube_url, - 'ie_key': 'Youtube', - } + return self.url_result(youtube_url, YoutubeIE.ie_key()) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 65b482333..067de28cd 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2197,10 +2197,7 @@ class GenericIE(InfoExtractor): def _real_extract(self, url): if url.startswith('//'): - return { - '_type': 'url', - 'url': self.http_scheme() + url, - } + return self.url_result(self.http_scheme() + url) parsed_url = compat_urlparse.urlparse(url) if not parsed_url.scheme: diff --git a/youtube_dl/extractor/livestream.py b/youtube_dl/extractor/livestream.py index c4776bbf3..e55b1a202 100644 --- a/youtube_dl/extractor/livestream.py +++ b/youtube_dl/extractor/livestream.py @@ -363,7 +363,4 @@ class LivestreamShortenerIE(InfoExtractor): id = mobj.group('id') webpage = self._download_webpage(url, id) - return { - '_type': 'url', - 'url': self._og_search_url(webpage), - } + return self.url_result(self._og_search_url(webpage)) diff --git a/youtube_dl/extractor/savefrom.py b/youtube_dl/extractor/savefrom.py index 30f9cf824..21e44b69a 100644 --- a/youtube_dl/extractor/savefrom.py +++ b/youtube_dl/extractor/savefrom.py @@ -30,8 +30,5 @@ class SaveFromIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = os.path.splitext(url.split('/')[-1])[0] - return { - '_type': 'url', - 'id': video_id, - 'url': mobj.group('url'), - } + + return self.url_result(mobj.group('url'), video_id=video_id) diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index f9b6aa48f..d3e4205f5 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -203,10 +203,8 @@ class TEDIE(InfoExtractor): ext_url = None if service.lower() == 'youtube': ext_url = external.get('code') - return { - '_type': 'url', - 'url': ext_url or external['uri'], - } + + return self.url_result(ext_url or external['uri']) resources_ = player_talk.get('resources') or talk_info.get('resources') diff --git a/youtube_dl/extractor/testurl.py b/youtube_dl/extractor/testurl.py index 46918adb0..84a14a0bd 100644 --- a/youtube_dl/extractor/testurl.py +++ b/youtube_dl/extractor/testurl.py @@ -61,8 +61,4 @@ class TestURLIE(InfoExtractor): self.to_screen('Test URL: %s' % tc['url']) - return { - '_type': 'url', - 'url': tc['url'], - 'id': video_id, - } + return self.url_result(tc['url'], video_id=video_id) diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index 3dab9145b..ea234e3c5 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -40,11 +40,7 @@ class WimpIE(InfoExtractor): r'data-id=["\']([0-9A-Za-z_-]{11})'), webpage, 'video URL', default=None) if youtube_id: - return { - '_type': 'url', - 'url': youtube_id, - 'ie_key': YoutubeIE.ie_key(), - } + return self.url_result(youtube_id, YoutubeIE.ie_key()) info_dict = self._extract_jwplayer_data( webpage, video_id, require_title=False) From 751e051557372ab3fa41d839e7e6a149aa2d04b8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 2 Jan 2019 17:26:15 +0700 Subject: [PATCH 408/558] [packtpub] Add support for subscription.packtpub.com (closes #18718) --- youtube_dl/extractor/packtpub.py | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/packtpub.py b/youtube_dl/extractor/packtpub.py index 56a2a1083..1324137df 100644 --- a/youtube_dl/extractor/packtpub.py +++ b/youtube_dl/extractor/packtpub.py @@ -24,9 +24,9 @@ class PacktPubBaseIE(InfoExtractor): class PacktPubIE(PacktPubBaseIE): - _VALID_URL = r'https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P\d+)/(?P\d+)/(?P\d+)' + _VALID_URL = r'https?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P\d+)/(?P\d+)/(?P\d+)' - _TEST = { + _TESTS = [{ 'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215/20528/20530/Project+Intro', 'md5': '1e74bd6cfd45d7d07666f4684ef58f70', 'info_dict': { @@ -37,7 +37,10 @@ class PacktPubIE(PacktPubBaseIE): 'timestamp': 1490918400, 'upload_date': '20170331', }, - } + }, { + 'url': 'https://subscription.packtpub.com/video/web_development/9781787122215/20528/20530/project-intro', + 'only_matching': True, + }] _NETRC_MACHINE = 'packtpub' _TOKEN = None @@ -110,15 +113,18 @@ class PacktPubIE(PacktPubBaseIE): class PacktPubCourseIE(PacktPubBaseIE): - _VALID_URL = r'(?Phttps?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P\d+))' - _TEST = { + _VALID_URL = r'(?Phttps?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P\d+))' + _TESTS = [{ 'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215', 'info_dict': { 'id': '9781787122215', 'title': 'Learn Nodejs by building 12 projects [Video]', }, 'playlist_count': 90, - } + }, { + 'url': 'https://subscription.packtpub.com/video/web_development/9781787122215', + 'only_matching': True, + }] @classmethod def suitable(cls, url): From 2122d7151deca9c7047426320cd73152cb907afa Mon Sep 17 00:00:00 2001 From: nyuszika7h Date: Wed, 2 Jan 2019 17:46:07 +0100 Subject: [PATCH 409/558] [discovery] Use geo verification headers --- youtube_dl/extractor/discovery.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index 44fbc41bb..b70c307a7 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -94,11 +94,12 @@ class DiscoveryIE(DiscoveryGoBaseIE): })['access_token'] try: + headers = self.geo_verification_headers() + headers['Authorization'] = 'Bearer ' + access_token + stream = self._download_json( 'https://api.discovery.com/v1/streaming/video/' + video_id, - display_id, headers={ - 'Authorization': 'Bearer ' + access_token, - }) + display_id, headers=headers) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 403): e_description = self._parse_json( From aeb72b3a413c8a9d11e3c002b8ab2612b9075a56 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 2 Jan 2019 23:51:23 +0700 Subject: [PATCH 410/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/ChangeLog b/ChangeLog index 72bfe2110..1a28d6be0 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,18 @@ +version + +Extractors +* [discovery] Use geo verification headers (#17838) ++ [packtpub] Add support for subscription.packtpub.com (#18718) +* [yourporn] Fix extraction (#18583) ++ [acast:channel] Add support for play.acast.com (#18587) ++ [extractors] Add missing age limits (#18621) ++ [rmcdecouverte] Add support for live stream +* [rmcdecouverte] Bypass geo restriction +* [rmcdecouverte] Update URL regular expression (#18595, 18697) +* [manyvids] Fix extraction (#18604, #18614) +* [bitchute] Fix extraction (#18567) + + version 2018.12.31 Extractors From d7c3af7a72a1e6bd7f93321cce4daf2a13ebdf12 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 2 Jan 2019 23:52:54 +0700 Subject: [PATCH 411/558] release 2019.01.02 --- .github/ISSUE_TEMPLATE.md | 6 ++--- CONTRIBUTING.md | 47 ++++++++++++++++++++++++++++++++++++--- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 4 files changed, 49 insertions(+), 8 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index b2fe6ee6a..3986bbc8e 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.12.31*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.12.31** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.02*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.02** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.12.31 +[debug] youtube-dl version 2019.01.02 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 24617264c..a71b045d0 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -261,11 +261,33 @@ title = meta.get('title') or self._og_search_title(webpage) This code will try to extract from `meta` first and if it fails it will try extracting `og:title` from a `webpage`. -### Make regular expressions flexible +### Regular expressions -When using regular expressions try to write them fuzzy and flexible. +#### Don't capture groups you don't use + +Capturing group must be an indication that it's used somewhere in the code. Any group that is not used must be non capturing. + +##### Example + +Don't capture id attribute name here since you can't use it for anything anyway. + +Correct: + +```python +r'(?:id|ID)=(?P\d+)' +``` + +Incorrect: +```python +r'(id|ID)=(?P\d+)' +``` + + +#### Make regular expressions relaxed and flexible + +When using regular expressions try to write them fuzzy, relaxed and flexible, skipping insignificant parts that are more likely to change, allowing both single and double quotes for quoted values and so on. -#### Example +##### Example Say you need to extract `title` from the following HTML code: @@ -298,6 +320,25 @@ title = self._search_regex( webpage, 'title', group='title') ``` +### Long lines policy + +There is a soft limit to keep lines of code under 80 characters long. This means it should be respected if possible and if it does not make readability and code maintenance worse. + +For example, you should **never** split long string literals like URLs or some other often copied entities over multiple lines to fit this limit: + +Correct: + +```python +'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4' +``` + +Incorrect: + +```python +'https://www.youtube.com/watch?v=FqZTN594JQw&list=' +'PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4' +``` + ### Use safe conversion functions Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well. diff --git a/ChangeLog b/ChangeLog index 1a28d6be0..41d190a72 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2019.01.02 Extractors * [discovery] Use geo verification headers (#17838) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 87de5848d..07a444706 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.12.31' +__version__ = '2019.01.02' From c87f65e43dea0f9edf1b5ed8979e274902fb60a9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 4 Jan 2019 22:21:53 +0700 Subject: [PATCH 412/558] [carambatv:page] Fix extraction (closes #18739) --- youtube_dl/extractor/carambatv.py | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/youtube_dl/extractor/carambatv.py b/youtube_dl/extractor/carambatv.py index 9ba909a91..b57b86af7 100644 --- a/youtube_dl/extractor/carambatv.py +++ b/youtube_dl/extractor/carambatv.py @@ -82,6 +82,12 @@ class CarambaTVPageIE(InfoExtractor): webpage = self._download_webpage(url, video_id) videomore_url = VideomoreIE._extract_url(webpage) + if not videomore_url: + videomore_id = self._search_regex( + r'getVMCode\s*\(\s*["\']?(\d+)', webpage, 'videomore id', + default=None) + if videomore_id: + videomore_url = 'videomore:%s' % videomore_id if videomore_url: title = self._og_search_title(webpage) return { From de0359c0af3667605464212e66ba4048b6ba093b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 5 Jan 2019 03:40:41 +0700 Subject: [PATCH 413/558] [tvnow] Fix and rework extractors, prepare for a switch to the new API (closes #17245, closes #18499) --- youtube_dl/extractor/extractors.py | 4 +- youtube_dl/extractor/tvnow.py | 378 +++++++++++++++++++++-------- 2 files changed, 283 insertions(+), 99 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index d72f52e36..3b1dfc451 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1193,7 +1193,9 @@ from .tvnet import TVNetIE from .tvnoe import TVNoeIE from .tvnow import ( TVNowIE, - TVNowListIE, + TVNowNewIE, + TVNowSeasonIE, + TVNowAnnualIE, TVNowShowIE, ) from .tvp import ( diff --git a/youtube_dl/extractor/tvnow.py b/youtube_dl/extractor/tvnow.py index 60937616f..3c6a60c39 100644 --- a/youtube_dl/extractor/tvnow.py +++ b/youtube_dl/extractor/tvnow.py @@ -10,8 +10,9 @@ from ..utils import ( int_or_none, parse_iso8601, parse_duration, - try_get, + str_or_none, update_url_query, + urljoin, ) @@ -24,8 +25,7 @@ class TVNowBaseIE(InfoExtractor): def _call_api(self, path, video_id, query): return self._download_json( - 'https://api.tvnow.de/v3/' + path, - video_id, query=query) + 'https://api.tvnow.de/v3/' + path, video_id, query=query) def _extract_video(self, info, display_id): video_id = compat_str(info['id']) @@ -108,6 +108,11 @@ class TVNowIE(TVNowBaseIE): (?!(?:list|jahr)(?:/|$))(?P[^/?\#&]+) ''' + @classmethod + def suitable(cls, url): + return (False if TVNowNewIE.suitable(url) or TVNowSeasonIE.suitable(url) or TVNowAnnualIE.suitable(url) or TVNowShowIE.suitable(url) + else super(TVNowIE, cls).suitable(url)) + _TESTS = [{ 'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/der-neue-porsche-911-gt-3/player', 'info_dict': { @@ -116,7 +121,6 @@ class TVNowIE(TVNowBaseIE): 'ext': 'mp4', 'title': 'Der neue Porsche 911 GT 3', 'description': 'md5:6143220c661f9b0aae73b245e5d898bb', - 'thumbnail': r're:^https?://.*\.jpg$', 'timestamp': 1495994400, 'upload_date': '20170528', 'duration': 5283, @@ -161,136 +165,314 @@ class TVNowIE(TVNowBaseIE): info = self._call_api( 'movies/' + display_id, display_id, query={ 'fields': ','.join(self._VIDEO_FIELDS), - 'station': mobj.group(1), }) return self._extract_video(info, display_id) -class TVNowListBaseIE(TVNowBaseIE): - _SHOW_VALID_URL = r'''(?x) - (?P - https?:// - (?:www\.)?tvnow\.(?:de|at|ch)/[^/]+/ - (?P[^/]+) - ) +class TVNowNewIE(InfoExtractor): + _VALID_URL = r'''(?x) + (?Phttps?:// + (?:www\.)?tvnow\.(?:de|at|ch)/ + (?:shows|serien))/ + (?P[^/]+)-\d+/ + [^/]+/ + episode-\d+-(?P[^/?$&]+)-(?P\d+) ''' - def _extract_list_info(self, display_id, show_id): - fields = list(self._SHOW_FIELDS) - fields.extend('formatTabs.%s' % field for field in self._SEASON_FIELDS) - fields.extend( - 'formatTabs.formatTabPages.container.movies.%s' % field - for field in self._VIDEO_FIELDS) - return self._call_api( - 'formats/seo', display_id, query={ - 'fields': ','.join(fields), - 'name': show_id + '.php' - }) - - -class TVNowListIE(TVNowListBaseIE): - _VALID_URL = r'%s/(?:list|jahr)/(?P[^?\#&]+)' % TVNowListBaseIE._SHOW_VALID_URL - - _SHOW_FIELDS = ('title', ) - _SEASON_FIELDS = ('id', 'headline', 'seoheadline', ) - _VIDEO_FIELDS = ('id', 'headline', 'seoUrl', ) - _TESTS = [{ - 'url': 'https://www.tvnow.de/rtl/30-minuten-deutschland/list/aktuell', - 'info_dict': { - 'id': '28296', - 'title': '30 Minuten Deutschland - Aktuell', - }, - 'playlist_mincount': 1, - }, { - 'url': 'https://www.tvnow.de/vox/ab-ins-beet/list/staffel-14', - 'only_matching': True, - }, { - 'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/jahr/2018/3', + 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05/episode-405-der-neue-porsche-911-gt-3-331082', 'only_matching': True, }] - @classmethod - def suitable(cls, url): - return (False if TVNowIE.suitable(url) - else super(TVNowListIE, cls).suitable(url)) + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + base_url = re.sub(r'(?:shows|serien)', '_', mobj.group('base_url')) + show, episode = mobj.group('show', 'episode') + return self.url_result( + # Rewrite new URLs to the old format and use extraction via old API + # at api.tvnow.de as a loophole for bypassing premium content checks + '%s/%s/%s' % (base_url, show, episode), + ie=TVNowIE.ie_key(), video_id=mobj.group('id')) + + +class TVNowNewBaseIE(InfoExtractor): + def _call_api(self, path, video_id, query={}): + result = self._download_json( + 'https://apigw.tvnow.de/module/' + path, video_id, query=query) + error = result.get('error') + if error: + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, error), expected=True) + return result + + +""" +TODO: new apigw.tvnow.de based version of TVNowIE. Replace old TVNowIE with it +when api.tvnow.de is shut down. This version can't bypass premium checks though. +class TVNowIE(TVNowNewBaseIE): + _VALID_URL = r'''(?x) + https?:// + (?:www\.)?tvnow\.(?:de|at|ch)/ + (?:shows|serien)/[^/]+/ + (?:[^/]+/)+ + (?P[^/?$&]+)-(?P\d+) + ''' + + _TESTS = [{ + # episode with annual navigation + 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05/episode-405-der-neue-porsche-911-gt-3-331082', + 'info_dict': { + 'id': '331082', + 'display_id': 'grip-das-motormagazin/der-neue-porsche-911-gt-3', + 'ext': 'mp4', + 'title': 'Der neue Porsche 911 GT 3', + 'description': 'md5:6143220c661f9b0aae73b245e5d898bb', + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1495994400, + 'upload_date': '20170528', + 'duration': 5283, + 'series': 'GRIP - Das Motormagazin', + 'season_number': 14, + 'episode_number': 405, + 'episode': 'Der neue Porsche 911 GT 3', + }, + }, { + # rtl2, episode with season navigation + 'url': 'https://www.tvnow.de/shows/armes-deutschland-11471/staffel-3/episode-14-bernd-steht-seit-der-trennung-von-seiner-frau-allein-da-526124', + 'only_matching': True, + }, { + # rtlnitro + 'url': 'https://www.tvnow.de/serien/alarm-fuer-cobra-11-die-autobahnpolizei-1815/staffel-13/episode-5-auf-eigene-faust-pilot-366822', + 'only_matching': True, + }, { + # superrtl + 'url': 'https://www.tvnow.de/shows/die-lustigsten-schlamassel-der-welt-1221/staffel-2/episode-14-u-a-ketchup-effekt-364120', + 'only_matching': True, + }, { + # ntv + 'url': 'https://www.tvnow.de/shows/startup-news-10674/staffel-2/episode-39-goetter-in-weiss-387630', + 'only_matching': True, + }, { + # vox + 'url': 'https://www.tvnow.de/shows/auto-mobil-174/2017-11/episode-46-neues-vom-automobilmarkt-2017-11-19-17-00-00-380072', + 'only_matching': True, + }, { + 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05/episode-405-der-neue-porsche-911-gt-3-331082', + 'only_matching': True, + }] + + def _extract_video(self, info, url, display_id): + config = info['config'] + source = config['source'] + + video_id = compat_str(info.get('id') or source['videoId']) + title = source['title'].strip() + + paths = [] + for manifest_url in (info.get('manifest') or {}).values(): + if not manifest_url: + continue + manifest_url = update_url_query(manifest_url, {'filter': ''}) + path = self._search_regex(r'https?://[^/]+/(.+?)\.ism/', manifest_url, 'path') + if path in paths: + continue + paths.append(path) + + def url_repl(proto, suffix): + return re.sub( + r'(?:hls|dash|hss)([.-])', proto + r'\1', re.sub( + r'\.ism/(?:[^.]*\.(?:m3u8|mpd)|[Mm]anifest)', + '.ism/' + suffix, manifest_url)) + + formats = self._extract_mpd_formats( + url_repl('dash', '.mpd'), video_id, + mpd_id='dash', fatal=False) + formats.extend(self._extract_ism_formats( + url_repl('hss', 'Manifest'), + video_id, ism_id='mss', fatal=False)) + formats.extend(self._extract_m3u8_formats( + url_repl('hls', '.m3u8'), video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False)) + if formats: + break + else: + if try_get(info, lambda x: x['rights']['isDrm']): + raise ExtractorError( + 'Video %s is DRM protected' % video_id, expected=True) + if try_get(config, lambda x: x['boards']['geoBlocking']['block']): + raise self.raise_geo_restricted() + if not info.get('free', True): + raise ExtractorError( + 'Video %s is not available for free' % video_id, expected=True) + self._sort_formats(formats) + + description = source.get('description') + thumbnail = url_or_none(source.get('poster')) + timestamp = unified_timestamp(source.get('previewStart')) + duration = parse_duration(source.get('length')) + + series = source.get('format') + season_number = int_or_none(self._search_regex( + r'staffel-(\d+)', url, 'season number', default=None)) + episode_number = int_or_none(self._search_regex( + r'episode-(\d+)', url, 'episode number', default=None)) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'series': series, + 'season_number': season_number, + 'episode_number': episode_number, + 'episode': title, + 'formats': formats, + } def _real_extract(self, url): - base_url, show_id, season_id = re.match(self._VALID_URL, url).groups() + display_id, video_id = re.match(self._VALID_URL, url).groups() + info = self._call_api('player/' + video_id, video_id) + return self._extract_video(info, video_id, display_id) +""" - list_info = self._extract_list_info(season_id, show_id) - season = next( - season for season in list_info['formatTabs']['items'] - if season.get('seoheadline') == season_id) +class TVNowListBaseIE(TVNowNewBaseIE): + _SHOW_VALID_URL = r'''(?x) + (?P + https?:// + (?:www\.)?tvnow\.(?:de|at|ch)/(?:shows|serien)/ + [^/?#&]+-(?P\d+) + ) + ''' - title = list_info.get('title') - headline = season.get('headline') - if title and headline: - title = '%s - %s' % (title, headline) - else: - title = headline or title + @classmethod + def suitable(cls, url): + return (False if TVNowNewIE.suitable(url) + else super(TVNowListBaseIE, cls).suitable(url)) + + def _extract_items(self, url, show_id, list_id, query): + items = self._call_api( + 'teaserrow/format/episode/' + show_id, list_id, + query=query)['items'] entries = [] - for container in season['formatTabPages']['items']: - items = try_get( - container, lambda x: x['container']['movies']['items'], - list) or [] - for info in items: - seo_url = info.get('seoUrl') - if not seo_url: - continue - video_id = info.get('id') - entries.append(self.url_result( - '%s/%s/player' % (base_url, seo_url), TVNowIE.ie_key(), - compat_str(video_id) if video_id else None)) + for item in items: + if not isinstance(item, dict): + continue + item_url = urljoin(url, item.get('url')) + if not item_url: + continue + video_id = str_or_none(item.get('id') or item.get('videoId')) + item_title = item.get('subheadline') or item.get('text') + entries.append(self.url_result( + item_url, ie=TVNowNewIE.ie_key(), video_id=video_id, + video_title=item_title)) - return self.playlist_result( - entries, compat_str(season.get('id') or season_id), title) + return self.playlist_result(entries, '%s/%s' % (show_id, list_id)) + + +class TVNowSeasonIE(TVNowListBaseIE): + _VALID_URL = r'%s/staffel-(?P\d+)' % TVNowListBaseIE._SHOW_VALID_URL + _TESTS = [{ + 'url': 'https://www.tvnow.de/serien/alarm-fuer-cobra-11-die-autobahnpolizei-1815/staffel-13', + 'info_dict': { + 'id': '1815/13', + }, + 'playlist_mincount': 22, + }] + + def _real_extract(self, url): + _, show_id, season_id = re.match(self._VALID_URL, url).groups() + return self._extract_items( + url, show_id, season_id, {'season': season_id}) + + +class TVNowAnnualIE(TVNowListBaseIE): + _VALID_URL = r'%s/(?P\d{4})-(?P\d{2})' % TVNowListBaseIE._SHOW_VALID_URL + _TESTS = [{ + 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05', + 'info_dict': { + 'id': '1669/2017-05', + }, + 'playlist_mincount': 2, + }] + + def _real_extract(self, url): + _, show_id, year, month = re.match(self._VALID_URL, url).groups() + return self._extract_items( + url, show_id, '%s-%s' % (year, month), { + 'year': int(year), + 'month': int(month), + }) class TVNowShowIE(TVNowListBaseIE): _VALID_URL = TVNowListBaseIE._SHOW_VALID_URL - - _SHOW_FIELDS = ('id', 'title', ) - _SEASON_FIELDS = ('id', 'headline', 'seoheadline', ) - _VIDEO_FIELDS = () - _TESTS = [{ - 'url': 'https://www.tvnow.at/vox/ab-ins-beet', + # annual navigationType + 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669', 'info_dict': { - 'id': 'ab-ins-beet', - 'title': 'Ab ins Beet!', + 'id': '1669', }, - 'playlist_mincount': 7, + 'playlist_mincount': 73, }, { - 'url': 'https://www.tvnow.at/vox/ab-ins-beet/list', - 'only_matching': True, - }, { - 'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/jahr/', - 'only_matching': True, + # season navigationType + 'url': 'https://www.tvnow.de/shows/armes-deutschland-11471', + 'info_dict': { + 'id': '11471', + }, + 'playlist_mincount': 3, }] @classmethod def suitable(cls, url): - return (False if TVNowIE.suitable(url) or TVNowListIE.suitable(url) + return (False if TVNowNewIE.suitable(url) or TVNowSeasonIE.suitable(url) or TVNowAnnualIE.suitable(url) else super(TVNowShowIE, cls).suitable(url)) def _real_extract(self, url): base_url, show_id = re.match(self._VALID_URL, url).groups() - list_info = self._extract_list_info(show_id, show_id) + result = self._call_api( + 'teaserrow/format/navigation/' + show_id, show_id) + + items = result['items'] entries = [] - for season_info in list_info['formatTabs']['items']: - season_url = season_info.get('seoheadline') - if not season_url: - continue - season_id = season_info.get('id') - entries.append(self.url_result( - '%s/list/%s' % (base_url, season_url), TVNowListIE.ie_key(), - compat_str(season_id) if season_id else None, - season_info.get('headline'))) + navigation = result.get('navigationType') + if navigation == 'annual': + for item in items: + if not isinstance(item, dict): + continue + year = int_or_none(item.get('year')) + if year is None: + continue + months = item.get('months') + if not isinstance(months, list): + continue + for month_dict in months: + if not isinstance(month_dict, dict) or not month_dict: + continue + month_number = int_or_none(list(month_dict.keys())[0]) + if month_number is None: + continue + entries.append(self.url_result( + '%s/%04d-%02d' % (base_url, year, month_number), + ie=TVNowAnnualIE.ie_key())) + elif navigation == 'season': + for item in items: + if not isinstance(item, dict): + continue + season_number = int_or_none(item.get('season')) + if season_number is None: + continue + entries.append(self.url_result( + '%s/staffel-%d' % (base_url, season_number), + ie=TVNowSeasonIE.ie_key())) + else: + raise ExtractorError('Unknown navigationType') - return self.playlist_result(entries, show_id, list_info.get('title')) + return self.playlist_result(entries, show_id) From b7acc83550598b9facf1b31d3d9a1c2823b29cbe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 7 Jan 2019 00:55:39 +0700 Subject: [PATCH 414/558] [utils] Add language codes replaced in 1989 revision of ISO 639 to ISO639Utils (closes #18765) --- youtube_dl/utils.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 62e769fd5..64b524d2f 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -2968,6 +2968,7 @@ class ISO639Utils(object): 'gv': 'glv', 'ha': 'hau', 'he': 'heb', + 'iw': 'heb', # Replaced by he in 1989 revision 'hi': 'hin', 'ho': 'hmo', 'hr': 'hrv', @@ -2977,6 +2978,7 @@ class ISO639Utils(object): 'hz': 'her', 'ia': 'ina', 'id': 'ind', + 'in': 'ind', # Replaced by id in 1989 revision 'ie': 'ile', 'ig': 'ibo', 'ii': 'iii', @@ -3091,6 +3093,7 @@ class ISO639Utils(object): 'wo': 'wol', 'xh': 'xho', 'yi': 'yid', + 'ji': 'yid', # Replaced by he yi 1989 revision 'yo': 'yor', 'za': 'zha', 'zh': 'zho', From 04fb6928da5e34fb3c7eaf50592a141400e00487 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 7 Jan 2019 00:57:24 +0700 Subject: [PATCH 415/558] [postprocessor/ffmpeg] Embed subtitles with non-standard language codes (refs #18765) --- youtube_dl/postprocessor/ffmpeg.py | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 757b496a1..efcd39d57 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -384,9 +384,8 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor): opts += ['-c:s', 'mov_text'] for (i, lang) in enumerate(sub_langs): opts.extend(['-map', '%d:0' % (i + 1)]) - lang_code = ISO639Utils.short2long(lang) - if lang_code is not None: - opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code]) + lang_code = ISO639Utils.short2long(lang) or lang + opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code]) temp_filename = prepend_extension(filename, 'temp') self._downloader.to_screen('[ffmpeg] Embedding subtitles in \'%s\'' % filename) From e9a50fba8603128dcb81fa1b59206a0cb106d540 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 7 Jan 2019 01:02:34 +0700 Subject: [PATCH 416/558] [utils] Fix typo --- youtube_dl/utils.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 64b524d2f..d2d3c1a9f 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -3093,7 +3093,7 @@ class ISO639Utils(object): 'wo': 'wol', 'xh': 'xho', 'yi': 'yid', - 'ji': 'yid', # Replaced by he yi 1989 revision + 'ji': 'yid', # Replaced by yi in 1989 revision 'yo': 'yor', 'za': 'zha', 'zh': 'zho', From bcc334a3c66f2465cd63be284e389cc4c7a78203 Mon Sep 17 00:00:00 2001 From: 4rensiker <4rensics@gmx.de> Date: Tue, 8 Jan 2019 02:44:42 +0100 Subject: [PATCH 417/558] [dtube] Fix extraction (closes #18741) --- youtube_dl/extractor/dtube.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/dtube.py b/youtube_dl/extractor/dtube.py index 5887887e1..20190c9cc 100644 --- a/youtube_dl/extractor/dtube.py +++ b/youtube_dl/extractor/dtube.py @@ -48,7 +48,7 @@ class DTubeIE(InfoExtractor): def canonical_url(h): if not h: return None - return 'https://ipfs.io/ipfs/' + h + return 'https://video.dtube.top/ipfs/' + h formats = [] for q in ('240', '480', '720', '1080', ''): From 0266854f63baaa9669b30ee49c5e7e9f353970dd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 8 Jan 2019 08:46:34 +0700 Subject: [PATCH 418/558] [dtube] Update test --- youtube_dl/extractor/dtube.py | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/dtube.py b/youtube_dl/extractor/dtube.py index 20190c9cc..114d2dbe3 100644 --- a/youtube_dl/extractor/dtube.py +++ b/youtube_dl/extractor/dtube.py @@ -15,16 +15,16 @@ from ..utils import ( class DTubeIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?d\.tube/(?:#!/)?v/(?P[0-9a-z.-]+)/(?P[0-9a-z]{8})' _TEST = { - 'url': 'https://d.tube/#!/v/benswann/zqd630em', - 'md5': 'a03eaa186618ffa7a3145945543a251e', + 'url': 'https://d.tube/#!/v/broncnutz/x380jtr1', + 'md5': '9f29088fa08d699a7565ee983f56a06e', 'info_dict': { - 'id': 'zqd630em', + 'id': 'x380jtr1', 'ext': 'mp4', - 'title': 'Reality Check: FDA\'s Disinformation Campaign on Kratom', - 'description': 'md5:700d164e066b87f9eac057949e4227c2', - 'uploader_id': 'benswann', - 'upload_date': '20180222', - 'timestamp': 1519328958, + 'title': 'Lefty 3-Rings is Back Baby!! NCAA Picks', + 'description': 'md5:60be222088183be3a42f196f34235776', + 'uploader_id': 'broncnutz', + 'upload_date': '20190107', + 'timestamp': 1546854054, }, 'params': { 'format': '480p', From 8cb5c2181ac039e92a20247f266f48cee2411748 Mon Sep 17 00:00:00 2001 From: Awal Garg Date: Mon, 7 Jan 2019 17:41:12 +0530 Subject: [PATCH 419/558] [hungama] Add extractor --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/hungama.py | 32 ++++++++++++++++++++++++++++++ 2 files changed, 33 insertions(+) create mode 100644 youtube_dl/extractor/hungama.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 3b1dfc451..5ff34216f 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -469,6 +469,7 @@ from .hrti import ( ) from .huajiao import HuajiaoIE from .huffpost import HuffPostIE +from .hungama import HungamaIE from .hypem import HypemIE from .iconosquare import IconosquareIE from .ign import ( diff --git a/youtube_dl/extractor/hungama.py b/youtube_dl/extractor/hungama.py new file mode 100644 index 000000000..e51440299 --- /dev/null +++ b/youtube_dl/extractor/hungama.py @@ -0,0 +1,32 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class HungamaIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)hungama\.com/song/[\w\d-]+/(?P[0-9]+)' + _TEST = { + 'url': 'https://www.hungama.com/song/kitni-haseen-zindagi/2931166/', + 'md5': '396fa7e8e7e67aa25da0edc4cac9b785', + 'info_dict': { + 'id': '2931166', + 'ext': 'mp4', + 'title': 'Kitni Haseen Zindagi', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + player_data = self._download_json('https://www.hungama.com/audio-player-data/track/%s?_country=IN' % video_id, video_id)[0] + title = player_data.get('song_name') or self._og_search_title(webpage) + track_data = self._download_json(player_data['file'], video_id) + media_url = track_data['response']['media_url'] + + return { + 'id': video_id, + 'title': title, + 'formats': self._extract_m3u8_formats(media_url, video_id, ext='mp4'), + } From 06b4b90c70636d8044b7a2f588503cadf8b202d9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 8 Jan 2019 09:09:49 +0700 Subject: [PATCH 420/558] [hungama] Fix code and extract more metadata (closes #18771) --- youtube_dl/extractor/hungama.py | 41 +++++++++++++++++++++++++-------- 1 file changed, 32 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/hungama.py b/youtube_dl/extractor/hungama.py index e51440299..d9ad1281a 100644 --- a/youtube_dl/extractor/hungama.py +++ b/youtube_dl/extractor/hungama.py @@ -2,31 +2,54 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import int_or_none class HungamaIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)hungama\.com/song/[\w\d-]+/(?P[0-9]+)' + _VALID_URL = r'https?://(?:www\.)?hungama\.com/song/[^/]+/(?P[0-9]+)' _TEST = { 'url': 'https://www.hungama.com/song/kitni-haseen-zindagi/2931166/', - 'md5': '396fa7e8e7e67aa25da0edc4cac9b785', + 'md5': 'a845a6d1ebd08d80c1035126d49bd6a0', 'info_dict': { 'id': '2931166', 'ext': 'mp4', - 'title': 'Kitni Haseen Zindagi', + 'title': 'Lucky Ali - Kitni Haseen Zindagi', + 'track': 'Kitni Haseen Zindagi', + 'artist': 'Lucky Ali', + 'album': 'Aks', + 'release_year': 2000, } } def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - player_data = self._download_json('https://www.hungama.com/audio-player-data/track/%s?_country=IN' % video_id, video_id)[0] - title = player_data.get('song_name') or self._og_search_title(webpage) - track_data = self._download_json(player_data['file'], video_id) - media_url = track_data['response']['media_url'] + data = self._download_json( + 'https://www.hungama.com/audio-player-data/track/%s' % video_id, + video_id, query={'_country': 'IN'})[0] + + track = data['song_name'] + artist = data.get('singer_name') + + m3u8_url = self._download_json( + data.get('file') or data['preview_link'], + video_id)['response']['media_url'] + + formats = self._extract_m3u8_formats( + m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + self._sort_formats(formats) + + title = '%s - %s' % (artist, track) if artist else track + thumbnail = data.get('img_src') or data.get('album_image') return { 'id': video_id, 'title': title, - 'formats': self._extract_m3u8_formats(media_url, video_id, ext='mp4'), + 'thumbnail': thumbnail, + 'track': track, + 'artist': artist, + 'album': data.get('album_name'), + 'release_year': int_or_none(data.get('date')), + 'formats': formats, } From 391256dc0ee5e6ac8d3022455de207b8b02a5b10 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 8 Jan 2019 10:02:00 +0700 Subject: [PATCH 421/558] [extractor/common] Add support for movies in _json_ld --- youtube_dl/extractor/common.py | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index e5f8136fc..f507400cc 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1250,6 +1250,13 @@ class InfoExtractor(object): part_of_series = e.get('partOfSeries') or e.get('partOfTVSeries') if isinstance(part_of_series, dict) and part_of_series.get('@type') in ('TVSeries', 'Series', 'CreativeWorkSeries'): info['series'] = unescapeHTML(part_of_series.get('name')) + elif item_type == 'Movie': + info.update({ + 'title': unescapeHTML(e.get('name')), + 'description': unescapeHTML(e.get('description')), + 'duration': parse_duration(e.get('duration')), + 'timestamp': unified_timestamp(e.get('dateCreated')), + }) elif item_type in ('Article', 'NewsArticle'): info.update({ 'timestamp': parse_iso8601(e.get('datePublished')), From 440863ade10c70bec272c1ffe17b63c877e46ca7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 8 Jan 2019 10:02:49 +0700 Subject: [PATCH 422/558] [extractor/common] Use episode name as title in _json_ld --- youtube_dl/extractor/common.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index f507400cc..9e7febcad 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1239,11 +1239,14 @@ class InfoExtractor(object): if expected_type is not None and expected_type != item_type: return info if item_type in ('TVEpisode', 'Episode'): + episode_name = unescapeHTML(e.get('name')) info.update({ - 'episode': unescapeHTML(e.get('name')), + 'episode': episode_name, 'episode_number': int_or_none(e.get('episodeNumber')), 'description': unescapeHTML(e.get('description')), }) + if not info.get('title') and episode_name: + info['title'] = episode_name part_of_season = e.get('partOfSeason') if isinstance(part_of_season, dict) and part_of_season.get('@type') in ('TVSeason', 'Season', 'CreativeWorkSeason'): info['season_number'] = int_or_none(part_of_season.get('seasonNumber')) From 2543938bbe393ceef8dca6a69b441d54df099107 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 8 Jan 2019 10:03:44 +0700 Subject: [PATCH 423/558] [hungama] Add support for videos (closes #17402) --- youtube_dl/extractor/extractors.py | 5 +- youtube_dl/extractor/hungama.py | 78 +++++++++++++++++++++++++++--- 2 files changed, 74 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 5ff34216f..ddeb70284 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -469,7 +469,10 @@ from .hrti import ( ) from .huajiao import HuajiaoIE from .huffpost import HuffPostIE -from .hungama import HungamaIE +from .hungama import ( + HungamaIE, + HungamaSongIE, +) from .hypem import HypemIE from .iconosquare import IconosquareIE from .ign import ( diff --git a/youtube_dl/extractor/hungama.py b/youtube_dl/extractor/hungama.py index d9ad1281a..3fdaac5b6 100644 --- a/youtube_dl/extractor/hungama.py +++ b/youtube_dl/extractor/hungama.py @@ -2,11 +2,73 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + urlencode_postdata, +) class HungamaIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?hungama\.com/song/[^/]+/(?P[0-9]+)' + _VALID_URL = r'''(?x) + https?:// + (?:www\.)?hungama\.com/ + (?: + (?:video|movie)/[^/]+/| + tv-show/(?:[^/]+/){2}\d+/episode/[^/]+/ + ) + (?P\d+) + ''' + _TESTS = [{ + 'url': 'http://www.hungama.com/video/krishna-chants/39349649/', + 'md5': 'a845a6d1ebd08d80c1035126d49bd6a0', + 'info_dict': { + 'id': '2931166', + 'ext': 'mp4', + 'title': 'Lucky Ali - Kitni Haseen Zindagi', + 'track': 'Kitni Haseen Zindagi', + 'artist': 'Lucky Ali', + 'album': 'Aks', + 'release_year': 2000, + } + }, { + 'url': 'https://www.hungama.com/movie/kahaani-2/44129919/', + 'only_matching': True, + }, { + 'url': 'https://www.hungama.com/tv-show/padded-ki-pushup/season-1/44139461/episode/ep-02-training-sasu-pathlaag-karing/44139503/', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + info = self._search_json_ld(webpage, video_id) + + m3u8_url = self._download_json( + 'https://www.hungama.com/index.php', video_id, + data=urlencode_postdata({'content_id': video_id}), headers={ + 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', + 'X-Requested-With': 'XMLHttpRequest', + }, query={ + 'c': 'common', + 'm': 'get_video_mdn_url', + })['stream_url'] + + formats = self._extract_m3u8_formats( + m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + self._sort_formats(formats) + + info.update({ + 'id': video_id, + 'formats': formats, + }) + return info + + +class HungamaSongIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?hungama\.com/song/[^/]+/(?P\d+)' _TEST = { 'url': 'https://www.hungama.com/song/kitni-haseen-zindagi/2931166/', 'md5': 'a845a6d1ebd08d80c1035126d49bd6a0', @@ -22,21 +84,21 @@ class HungamaIE(InfoExtractor): } def _real_extract(self, url): - video_id = self._match_id(url) + audio_id = self._match_id(url) data = self._download_json( - 'https://www.hungama.com/audio-player-data/track/%s' % video_id, - video_id, query={'_country': 'IN'})[0] + 'https://www.hungama.com/audio-player-data/track/%s' % audio_id, + audio_id, query={'_country': 'IN'})[0] track = data['song_name'] artist = data.get('singer_name') m3u8_url = self._download_json( data.get('file') or data['preview_link'], - video_id)['response']['media_url'] + audio_id)['response']['media_url'] formats = self._extract_m3u8_formats( - m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native', + m3u8_url, audio_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls') self._sort_formats(formats) @@ -44,7 +106,7 @@ class HungamaIE(InfoExtractor): thumbnail = data.get('img_src') or data.get('album_image') return { - 'id': video_id, + 'id': audio_id, 'title': title, 'thumbnail': thumbnail, 'track': track, From 6089ff40e7cc7710e399db1be87fea103a190ee6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 9 Jan 2019 00:37:01 +0700 Subject: [PATCH 424/558] [youporn] Fix title and description extraction (closes #18748) --- youtube_dl/extractor/youporn.py | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index ea0bce784..d4eccb4b2 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -68,11 +68,9 @@ class YouPornIE(InfoExtractor): request.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(request, display_id) - title = self._search_regex( - [r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P(?:(?!\1).)+)\1', - r'<h1[^>]+class=["\']heading\d?["\'][^>]*>(?P<title>[^<]+)<'], - webpage, 'title', group='title', - default=None) or self._og_search_title( + title = self._html_search_regex( + r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>', + webpage, 'title', default=None) or self._og_search_title( webpage, default=None) or self._html_search_meta( 'title', webpage, fatal=True) @@ -134,7 +132,11 @@ class YouPornIE(InfoExtractor): formats.append(f) self._sort_formats(formats) - description = self._og_search_description(webpage, default=None) + description = self._html_search_regex( + r'(?s)<div[^>]+\bid=["\']description["\'][^>]*>(.+?)</div>', + webpage, 'description', + default=None) or self._og_search_description( + webpage, default=None) thumbnail = self._search_regex( r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1', webpage, 'thumbnail', fatal=False, group='thumbnail') From 3c1089dba41f137dcc6c373daacdc19a24aef81c Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 9 Jan 2019 14:23:26 +0100 Subject: [PATCH 425/558] [gaia] Add new extractor(#14605) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/gaia.py | 98 ++++++++++++++++++++++++++++++ 2 files changed, 99 insertions(+) create mode 100644 youtube_dl/extractor/gaia.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index ddeb70284..c7d04d366 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -411,6 +411,7 @@ from .funk import ( from .funnyordie import FunnyOrDieIE from .fusion import FusionIE from .fxnetworks import FXNetworksIE +from .gaia import GaiaIE from .gameinformer import GameInformerIE from .gameone import ( GameOneIE, diff --git a/youtube_dl/extractor/gaia.py b/youtube_dl/extractor/gaia.py new file mode 100644 index 000000000..f2eef3f4c --- /dev/null +++ b/youtube_dl/extractor/gaia.py @@ -0,0 +1,98 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + int_or_none, + str_or_none, + strip_or_none, + try_get, +) + + +class GaiaIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?gaia\.com/video/(?P<id>[^/?]+).*?\bfullplayer=(?P<type>feature|preview)' + _TESTS = [{ + 'url': 'https://www.gaia.com/video/connecting-universal-consciousness?fullplayer=feature', + 'info_dict': { + 'id': '89356', + 'ext': 'mp4', + 'title': 'Connecting with Universal Consciousness', + 'description': 'md5:844e209ad31b7d31345f5ed689e3df6f', + 'upload_date': '20151116', + 'timestamp': 1447707266, + 'duration': 936, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'https://www.gaia.com/video/connecting-universal-consciousness?fullplayer=preview', + 'info_dict': { + 'id': '89351', + 'ext': 'mp4', + 'title': 'Connecting with Universal Consciousness', + 'description': 'md5:844e209ad31b7d31345f5ed689e3df6f', + 'upload_date': '20151116', + 'timestamp': 1447707266, + 'duration': 53, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }] + + def _real_extract(self, url): + display_id, vtype = re.search(self._VALID_URL, url).groups() + node_id = self._download_json( + 'https://brooklyn.gaia.com/pathinfo', display_id, query={ + 'path': 'video/' + display_id, + })['id'] + node = self._download_json( + 'https://brooklyn.gaia.com/node/%d' % node_id, node_id) + vdata = node[vtype] + media_id = compat_str(vdata['nid']) + title = node['title'] + + media = self._download_json( + 'https://brooklyn.gaia.com/media/' + media_id, media_id) + formats = self._extract_m3u8_formats( + media['mediaUrls']['bcHLS'], media_id, 'mp4') + self._sort_formats(formats) + + subtitles = {} + text_tracks = media.get('textTracks', {}) + for key in ('captions', 'subtitles'): + for lang, sub_url in text_tracks.get(key, {}).items(): + subtitles.setdefault(lang, []).append({ + 'url': sub_url, + }) + + fivestar = node.get('fivestar', {}) + fields = node.get('fields', {}) + + def get_field_value(key, value_key='value'): + return try_get(fields, lambda x: x[key][0][value_key]) + + return { + 'id': media_id, + 'display_id': display_id, + 'title': title, + 'formats': formats, + 'description': strip_or_none(get_field_value('body') or get_field_value('teaser')), + 'timestamp': int_or_none(node.get('created')), + 'subtitles': subtitles, + 'duration': int_or_none(vdata.get('duration')), + 'like_count': int_or_none(try_get(fivestar, lambda x: x['up_count']['value'])), + 'dislike_count': int_or_none(try_get(fivestar, lambda x: x['down_count']['value'])), + 'comment_count': int_or_none(node.get('comment_count')), + 'series': try_get(node, lambda x: x['series']['title'], compat_str), + 'season_number': int_or_none(get_field_value('season')), + 'season_id': str_or_none(get_field_value('series_nid', 'nid')), + 'episode_number': int_or_none(get_field_value('episode')), + } From 65615be36874fe98d5a972546e8024cda3879c86 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 9 Jan 2019 19:17:58 +0100 Subject: [PATCH 426/558] [globo] set GLBID cookie manually(closes #17346) --- youtube_dl/extractor/globo.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/globo.py b/youtube_dl/extractor/globo.py index c2140c362..fb8f7679b 100644 --- a/youtube_dl/extractor/globo.py +++ b/youtube_dl/extractor/globo.py @@ -72,7 +72,7 @@ class GloboIE(InfoExtractor): return try: - self._download_json( + glb_id = (self._download_json( 'https://login.globo.com/api/authentication', None, data=json.dumps({ 'payload': { 'email': email, @@ -81,7 +81,9 @@ class GloboIE(InfoExtractor): }, }).encode(), headers={ 'Content-Type': 'application/json; charset=utf-8', - }) + }) or {}).get('glbId') + if glb_id: + self._set_cookie('.globo.com', 'GLBID', glb_id) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: resp = self._parse_json(e.cause.read(), None) From 4ad159c7b0ce476171aad1eaa8a36f7b9b1cce65 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 9 Jan 2019 20:39:48 +0100 Subject: [PATCH 427/558] [playplustv] Add new extractor(closes #18789) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/playplustv.py | 109 +++++++++++++++++++++++++++++ 2 files changed, 110 insertions(+) create mode 100644 youtube_dl/extractor/playplustv.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index c7d04d366..7d7e4247a 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -861,6 +861,7 @@ from .piksel import PikselIE from .pinkbike import PinkbikeIE from .pladform import PladformIE from .playfm import PlayFMIE +from .playplustv import PlayPlusTVIE from .plays import PlaysTVIE from .playtvak import PlaytvakIE from .playvid import PlayvidIE diff --git a/youtube_dl/extractor/playplustv.py b/youtube_dl/extractor/playplustv.py new file mode 100644 index 000000000..419c2974b --- /dev/null +++ b/youtube_dl/extractor/playplustv.py @@ -0,0 +1,109 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..compat import compat_HTTPError +from ..utils import ( + clean_html, + ExtractorError, + int_or_none, + PUTRequest, +) + + +class PlayPlusTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?playplus\.tv/VOD/(?P<project_id>[0-9]+)/(?P<id>[0-9a-f]{32})' + _TEST = { + 'url': 'https://www.playplus.tv/VOD/7572/db8d274a5163424e967f35a30ddafb8e', + 'md5': 'd078cb89d7ab6b9df37ce23c647aef72', + 'info_dict': { + 'id': 'db8d274a5163424e967f35a30ddafb8e', + 'ext': 'mp4', + 'title': 'Capítulo 179 - Final', + 'description': 'md5:01085d62d8033a1e34121d3c3cabc838', + 'timestamp': 1529992740, + 'upload_date': '20180626', + }, + 'skip': 'Requires account credential', + } + _NETRC_MACHINE = 'playplustv' + _GEO_COUNTRIES = ['BR'] + _token = None + _profile_id = None + + def _call_api(self, resource, video_id=None, query=None): + return self._download_json('https://api.playplus.tv/api/media/v2/get' + resource, video_id, headers={ + 'Authorization': 'Bearer ' + self._token, + }, query=query) + + def _real_initialize(self): + email, password = self._get_login_info() + if email is None: + self.raise_login_required() + + req = PUTRequest( + 'https://api.playplus.tv/api/web/login', json.dumps({ + 'email': email, + 'password': password, + }).encode(), { + 'Content-Type': 'application/json; charset=utf-8', + }) + + try: + self._token = self._download_json(req, None)['token'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + raise ExtractorError(self._parse_json( + e.cause.read(), None)['errorMessage'], expected=True) + raise + + self._profile = self._call_api('Profiles')['list'][0]['_id'] + + def _real_extract(self, url): + project_id, media_id = re.match(self._VALID_URL, url).groups() + media = self._call_api( + 'Media', media_id, { + 'profileId': self._profile, + 'projectId': project_id, + 'mediaId': media_id, + })['obj'] + title = media['title'] + + formats = [] + for f in media.get('files', []): + f_url = f.get('url') + if not f_url: + continue + file_info = f.get('fileInfo') or {} + formats.append({ + 'url': f_url, + 'width': int_or_none(file_info.get('width')), + 'height': int_or_none(file_info.get('height')), + }) + self._sort_formats(formats) + + thumbnails = [] + for thumb in media.get('thumbs', []): + thumb_url = thumb.get('url') + if not thumb_url: + continue + thumbnails.append({ + 'url': thumb_url, + 'width': int_or_none(thumb.get('width')), + 'height': int_or_none(thumb.get('height')), + }) + + return { + 'id': media_id, + 'title': title, + 'formats': formats, + 'thumbnails': thumbnails, + 'description': clean_html(media.get('description')) or media.get('shortDescription'), + 'timestamp': int_or_none(media.get('publishDate'), 1000), + 'view_count': int_or_none(media.get('numberOfViews')), + 'comment_count': int_or_none(media.get('numberOfComments')), + 'tags': media.get('tags'), + } From 96c186e1fd8af4943eeaa8c858f9cb0f15e8b265 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 10 Jan 2019 09:05:00 +0100 Subject: [PATCH 428/558] [fox] add support National Geographic(closes #17985)(closes #15333)(closes #14698) --- youtube_dl/extractor/extractors.py | 6 +- youtube_dl/extractor/fox.py | 93 +++++++------- youtube_dl/extractor/nationalgeographic.py | 135 --------------------- 3 files changed, 48 insertions(+), 186 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 7d7e4247a..a01d99b85 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -687,11 +687,7 @@ from .myvi import ( MyviEmbedIE, ) from .myvidster import MyVidsterIE -from .nationalgeographic import ( - NationalGeographicVideoIE, - NationalGeographicIE, - NationalGeographicEpisodeGuideIE, -) +from .nationalgeographic import NationalGeographicVideoIE from .naver import NaverIE from .nba import NBAIE from .nbc import ( diff --git a/youtube_dl/extractor/fox.py b/youtube_dl/extractor/fox.py index 11d6c9c32..b1c91f095 100644 --- a/youtube_dl/extractor/fox.py +++ b/youtube_dl/extractor/fox.py @@ -1,11 +1,11 @@ # coding: utf-8 from __future__ import unicode_literals +# import json +# import uuid + from .adobepass import AdobePassIE -from .uplynk import UplynkPreplayIE -from ..compat import compat_str from ..utils import ( - HEADRequest, int_or_none, parse_age_limit, parse_duration, @@ -16,7 +16,7 @@ from ..utils import ( class FOXIE(AdobePassIE): - _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[\da-fA-F]+)' + _VALID_URL = r'https?://(?:www\.)?(?:fox\.com|nationalgeographic\.com/tv)/watch/(?P<id>[\da-fA-F]+)' _TESTS = [{ # clip 'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/', @@ -43,41 +43,47 @@ class FOXIE(AdobePassIE): # episode, geo-restricted, tv provided required 'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/', 'only_matching': True, + }, { + 'url': 'https://www.nationalgeographic.com/tv/watch/f690e05ebbe23ab79747becd0cc223d1/', + 'only_matching': True, }] + # _access_token = None + + # def _call_api(self, path, video_id, data=None): + # headers = { + # 'X-Api-Key': '238bb0a0c2aba67922c48709ce0c06fd', + # } + # if self._access_token: + # headers['Authorization'] = 'Bearer ' + self._access_token + # return self._download_json( + # 'https://api2.fox.com/v2.0/' + path, video_id, data=data, headers=headers) + + # def _real_initialize(self): + # self._access_token = self._call_api( + # 'login', None, json.dumps({ + # 'deviceId': compat_str(uuid.uuid4()), + # }).encode())['accessToken'] def _real_extract(self, url): video_id = self._match_id(url) video = self._download_json( - 'https://api.fox.com/fbc-content/v1_4/video/%s' % video_id, + 'https://api.fox.com/fbc-content/v1_5/video/%s' % video_id, video_id, headers={ 'apikey': 'abdcbed02c124d393b39e818a4312055', 'Content-Type': 'application/json', 'Referer': url, }) + # video = self._call_api('vodplayer/' + video_id, video_id) title = video['name'] release_url = video['videoRelease']['url'] - - description = video.get('description') - duration = int_or_none(video.get('durationInSeconds')) or int_or_none( - video.get('duration')) or parse_duration(video.get('duration')) - timestamp = unified_timestamp(video.get('datePublished')) - rating = video.get('contentRating') - age_limit = parse_age_limit(rating) + # release_url = video['url'] data = try_get( video, lambda x: x['trackingData']['properties'], dict) or {} - creator = data.get('brand') or data.get('network') or video.get('network') - - series = video.get('seriesName') or data.get( - 'seriesName') or data.get('show') - season_number = int_or_none(video.get('seasonNumber')) - episode = video.get('name') - episode_number = int_or_none(video.get('episodeNumber')) - release_year = int_or_none(video.get('releaseYear')) - + rating = video.get('contentRating') if data.get('authRequired'): resource = self._get_mvpd_resource( 'fbc-fox', title, video.get('guid'), rating) @@ -86,6 +92,18 @@ class FOXIE(AdobePassIE): 'auth': self._extract_mvpd_auth( url, video_id, 'fbc-fox', resource) }) + m3u8_url = self._download_json(release_url, video_id)['playURL'] + formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls') + self._sort_formats(formats) + + duration = int_or_none(video.get('durationInSeconds')) or int_or_none( + video.get('duration')) or parse_duration(video.get('duration')) + timestamp = unified_timestamp(video.get('datePublished')) + creator = data.get('brand') or data.get('network') or video.get('network') + series = video.get('seriesName') or data.get( + 'seriesName') or data.get('show') subtitles = {} for doc_rel in video.get('documentReleases', []): @@ -98,36 +116,19 @@ class FOXIE(AdobePassIE): }] break - info = { + return { 'id': video_id, 'title': title, - 'description': description, + 'formats': formats, + 'description': video.get('description'), 'duration': duration, 'timestamp': timestamp, - 'age_limit': age_limit, + 'age_limit': parse_age_limit(rating), 'creator': creator, 'series': series, - 'season_number': season_number, - 'episode': episode, - 'episode_number': episode_number, - 'release_year': release_year, + 'season_number': int_or_none(video.get('seasonNumber')), + 'episode': video.get('name'), + 'episode_number': int_or_none(video.get('episodeNumber')), + 'release_year': int_or_none(video.get('releaseYear')), 'subtitles': subtitles, } - - urlh = self._request_webpage(HEADRequest(release_url), video_id) - video_url = compat_str(urlh.geturl()) - - if UplynkPreplayIE.suitable(video_url): - info.update({ - '_type': 'url_transparent', - 'url': video_url, - 'ie_key': UplynkPreplayIE.ie_key(), - }) - else: - m3u8_url = self._download_json(release_url, video_id)['playURL'] - formats = self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', - entry_protocol='m3u8_native', m3u8_id='hls') - self._sort_formats(formats) - info['formats'] = formats - return info diff --git a/youtube_dl/extractor/nationalgeographic.py b/youtube_dl/extractor/nationalgeographic.py index 4d2ee6408..165964ca0 100644 --- a/youtube_dl/extractor/nationalgeographic.py +++ b/youtube_dl/extractor/nationalgeographic.py @@ -1,15 +1,9 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from .adobepass import AdobePassIE -from .theplatform import ThePlatformIE from ..utils import ( smuggle_url, url_basename, - update_url_query, - get_element_by_class, ) @@ -64,132 +58,3 @@ class NationalGeographicVideoIE(InfoExtractor): {'force_smil_url': True}), 'id': guid, } - - -class NationalGeographicIE(ThePlatformIE, AdobePassIE): - IE_NAME = 'natgeo' - _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:(?:(?:wild/)?[^/]+/)?(?:videos|episodes)|u)/(?P<id>[^/?]+)' - - _TESTS = [ - { - 'url': 'http://channel.nationalgeographic.com/u/kdi9Ld0PN2molUUIMSBGxoeDhD729KRjQcnxtetilWPMevo8ZwUBIDuPR0Q3D2LVaTsk0MPRkRWDB8ZhqWVeyoxfsZZm36yRp1j-zPfsHEyI_EgAeFY/', - 'md5': '518c9aa655686cf81493af5cc21e2a04', - 'info_dict': { - 'id': 'vKInpacll2pC', - 'ext': 'mp4', - 'title': 'Uncovering a Universal Knowledge', - 'description': 'md5:1a89148475bf931b3661fcd6ddb2ae3a', - 'timestamp': 1458680907, - 'upload_date': '20160322', - 'uploader': 'NEWA-FNG-NGTV', - }, - 'add_ie': ['ThePlatform'], - }, - { - 'url': 'http://channel.nationalgeographic.com/u/kdvOstqYaBY-vSBPyYgAZRUL4sWUJ5XUUPEhc7ISyBHqoIO4_dzfY3K6EjHIC0hmFXoQ7Cpzm6RkET7S3oMlm6CFnrQwSUwo/', - 'md5': 'c4912f656b4cbe58f3e000c489360989', - 'info_dict': { - 'id': 'Pok5lWCkiEFA', - 'ext': 'mp4', - 'title': 'The Stunning Red Bird of Paradise', - 'description': 'md5:7bc8cd1da29686be4d17ad1230f0140c', - 'timestamp': 1459362152, - 'upload_date': '20160330', - 'uploader': 'NEWA-FNG-NGTV', - }, - 'add_ie': ['ThePlatform'], - }, - { - 'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episodes/the-power-of-miracles/', - 'only_matching': True, - }, - { - 'url': 'http://channel.nationalgeographic.com/videos/treasures-rediscovered/', - 'only_matching': True, - }, - { - 'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/videos/uncovering-a-universal-knowledge/', - 'only_matching': True, - }, - { - 'url': 'http://channel.nationalgeographic.com/wild/destination-wild/videos/the-stunning-red-bird-of-paradise/', - 'only_matching': True, - } - ] - - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - release_url = self._search_regex( - r'video_auth_playlist_url\s*=\s*"([^"]+)"', - webpage, 'release url') - theplatform_path = self._search_regex(r'https?://link\.theplatform\.com/s/([^?]+)', release_url, 'theplatform path') - video_id = theplatform_path.split('/')[-1] - query = { - 'mbr': 'true', - } - is_auth = self._search_regex(r'video_is_auth\s*=\s*"([^"]+)"', webpage, 'is auth', fatal=False) - if is_auth == 'auth': - auth_resource_id = self._search_regex( - r"video_auth_resourceId\s*=\s*'([^']+)'", - webpage, 'auth resource id') - query['auth'] = self._extract_mvpd_auth(url, video_id, 'natgeo', auth_resource_id) - - formats = [] - subtitles = {} - for key, value in (('switch', 'http'), ('manifest', 'm3u')): - tp_query = query.copy() - tp_query.update({ - key: value, - }) - tp_formats, tp_subtitles = self._extract_theplatform_smil( - update_url_query(release_url, tp_query), video_id, 'Downloading %s SMIL data' % value) - formats.extend(tp_formats) - subtitles = self._merge_subtitles(subtitles, tp_subtitles) - self._sort_formats(formats) - - info = self._extract_theplatform_metadata(theplatform_path, display_id) - info.update({ - 'id': video_id, - 'formats': formats, - 'subtitles': subtitles, - 'display_id': display_id, - }) - return info - - -class NationalGeographicEpisodeGuideIE(InfoExtractor): - IE_NAME = 'natgeo:episodeguide' - _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?(?P<id>[^/]+)/episode-guide' - _TESTS = [ - { - 'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episode-guide/', - 'info_dict': { - 'id': 'the-story-of-god-with-morgan-freeman-season-1', - 'title': 'The Story of God with Morgan Freeman - Season 1', - }, - 'playlist_mincount': 6, - }, - { - 'url': 'http://channel.nationalgeographic.com/underworld-inc/episode-guide/?s=2', - 'info_dict': { - 'id': 'underworld-inc-season-2', - 'title': 'Underworld, Inc. - Season 2', - }, - 'playlist_mincount': 7, - }, - ] - - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - show = get_element_by_class('show', webpage) - selected_season = self._search_regex( - r'<div[^>]+class="select-seasons[^"]*".*?<a[^>]*>(.*?)</a>', - webpage, 'selected season') - entries = [ - self.url_result(self._proto_relative_url(entry_url), 'NationalGeographic') - for entry_url in re.findall('(?s)<div[^>]+class="col-inner"[^>]*?>.*?<a[^>]+href="([^"]+)"', webpage)] - return self.playlist_result( - entries, '%s-%s' % (display_id, selected_season.lower().replace(' ', '-')), - '%s - %s' % (show, selected_season)) From 7c072f00d66f3b3f44d301059443480a5c83d3c0 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 10 Jan 2019 10:50:18 +0100 Subject: [PATCH 429/558] [jwplatform] use JW Platform Delivery API V2 and add support for more urls --- youtube_dl/extractor/jwplatform.py | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/jwplatform.py b/youtube_dl/extractor/jwplatform.py index 63d0dc998..d19a6a774 100644 --- a/youtube_dl/extractor/jwplatform.py +++ b/youtube_dl/extractor/jwplatform.py @@ -7,8 +7,8 @@ from .common import InfoExtractor class JWPlatformIE(InfoExtractor): - _VALID_URL = r'(?:https?://content\.jwplatform\.com/(?:feeds|players|jw6)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})' - _TEST = { + _VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview|video|manifest)s|jw6|v2/media)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})' + _TESTS = [{ 'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js', 'md5': 'fa8899fa601eb7c83a64e9d568bdf325', 'info_dict': { @@ -19,7 +19,10 @@ class JWPlatformIE(InfoExtractor): 'upload_date': '20081127', 'timestamp': 1227796140, } - } + }, { + 'url': 'https://cdn.jwplayer.com/players/nPripu9l-ALJ3XQCI.js', + 'only_matching': True, + }] @staticmethod def _extract_url(webpage): @@ -34,5 +37,5 @@ class JWPlatformIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - json_data = self._download_json('http://content.jwplatform.com/feeds/%s.json' % video_id, video_id) + json_data = self._download_json('https://cdn.jwplayer.com/v2/media/' + video_id, video_id) return self._parse_jwplayer_data(json_data, video_id) From 432aba1c5e68cf8efccb868107785a15617d5109 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 10 Jan 2019 10:54:46 +0100 Subject: [PATCH 430/558] [outsidetv] Add new extractor(closes #18774) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/outsidetv.py | 28 ++++++++++++++++++++++++++++ 2 files changed, 29 insertions(+) create mode 100644 youtube_dl/extractor/outsidetv.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index a01d99b85..de38c6641 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -829,6 +829,7 @@ from .orf import ( ORFOE1IE, ORFIPTVIE, ) +from .outsidetv import OutsideTVIE from .packtpub import ( PacktPubIE, PacktPubCourseIE, diff --git a/youtube_dl/extractor/outsidetv.py b/youtube_dl/extractor/outsidetv.py new file mode 100644 index 000000000..c5333b08c --- /dev/null +++ b/youtube_dl/extractor/outsidetv.py @@ -0,0 +1,28 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class OutsideTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?outsidetv\.com/(?:[^/]+/)*?play/[a-zA-Z0-9]{8}/\d+/\d+/(?P<id>[a-zA-Z0-9]{8})' + _TESTS = [{ + 'url': 'http://www.outsidetv.com/category/snow/play/ZjQYboH6/1/10/Hdg0jukV/4', + 'md5': '192d968fedc10b2f70ec31865ffba0da', + 'info_dict': { + 'id': 'Hdg0jukV', + 'ext': 'mp4', + 'title': 'Home - Jackson Ep 1 | Arbor Snowboards', + 'description': 'md5:41a12e94f3db3ca253b04bb1e8d8f4cd', + 'upload_date': '20181225', + 'timestamp': 1545742800, + } + }, { + 'url': 'http://www.outsidetv.com/home/play/ZjQYboH6/1/10/Hdg0jukV/4', + 'only_matching': True, + }] + + def _real_extract(self, url): + jw_media_id = self._match_id(url) + return self.url_result( + 'jwplatform:' + jw_media_id, 'JWPlatform', jw_media_id) From c3e543893bfba7faa7c13e53fbe6b60f936b81f1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 10 Jan 2019 22:46:53 +0700 Subject: [PATCH 431/558] [youtube] Extract live HLS URL from player response (closes #18799) --- youtube_dl/extractor/youtube.py | 55 +++++++++++++++++++-------------- 1 file changed, 31 insertions(+), 24 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 539ff6ff2..29773877e 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1931,31 +1931,38 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'http_chunk_size': 10485760, } formats.append(dct) - elif video_info.get('hlsvp'): - manifest_url = video_info['hlsvp'][0] - formats = [] - m3u8_formats = self._extract_m3u8_formats( - manifest_url, video_id, 'mp4', fatal=False) - for a_format in m3u8_formats: - itag = self._search_regex( - r'/itag/(\d+)/', a_format['url'], 'itag', default=None) - if itag: - a_format['format_id'] = itag - if itag in self._formats: - dct = self._formats[itag].copy() - dct.update(a_format) - a_format = dct - a_format['player_url'] = player_url - # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming - a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True' - formats.append(a_format) else: - error_message = clean_html(video_info.get('reason', [None])[0]) - if not error_message: - error_message = extract_unavailable_message() - if error_message: - raise ExtractorError(error_message, expected=True) - raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info') + manifest_url = ( + url_or_none(try_get( + player_response, + lambda x: x['streamingData']['hlsManifestUrl'], + compat_str)) or + url_or_none(try_get( + video_info, lambda x: x['hlsvp'][0], compat_str))) + if manifest_url: + formats = [] + m3u8_formats = self._extract_m3u8_formats( + manifest_url, video_id, 'mp4', fatal=False) + for a_format in m3u8_formats: + itag = self._search_regex( + r'/itag/(\d+)/', a_format['url'], 'itag', default=None) + if itag: + a_format['format_id'] = itag + if itag in self._formats: + dct = self._formats[itag].copy() + dct.update(a_format) + a_format = dct + a_format['player_url'] = player_url + # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming + a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True' + formats.append(a_format) + else: + error_message = clean_html(video_info.get('reason', [None])[0]) + if not error_message: + error_message = extract_unavailable_message() + if error_message: + raise ExtractorError(error_message, expected=True) + raise ExtractorError('no conn, hlsvp, hlsManifestUrl or url_encoded_fmt_stream_map information found in video info') # uploader video_uploader = try_get( From a4491dd55c5feaf02ac8969caafd637265cbeede Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 10 Jan 2019 23:23:19 +0700 Subject: [PATCH 432/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/ChangeLog b/ChangeLog index 41d190a72..c7d090c6c 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,29 @@ +version <unreleased> + +Core +* [extractor/common] Use episode name as title in _json_ld ++ [extractor/common] Add support for movies in _json_ld +* [postprocessor/ffmpeg] Embed subtitles with non-standard language codes + (#18765) ++ [utils] Add language codes replaced in 1989 revision of ISO 639 + to ISO639Utils (#18765) + +Extractors +* [youtube] Extract live HLS URL from player response (#18799) ++ [outsidetv] Add support for outsidetv.com (#18774) +* [jwplatform] Use JW Platform Delivery API V2 and add support for more URLs ++ [fox] Add support National Geographic (#17985, #15333, #14698) ++ [playplustv] Add support for playplus.tv (#18789) +* [globo] Set GLBID cookie manually (#17346) ++ [gaia] Add support for gaia.com (#14605) +* [youporn] Fix title and description extraction (#18748) ++ [hungama] Add support for hungama.com (#17402, #18771) +* [dtube] Fix extraction (#18741) +* [tvnow] Fix and rework extractors and prepare for a switch to the new API + (#17245, #18499) +* [carambatv:page] Fix extraction (#18739) + + version 2019.01.02 Extractors From b64f6e690ff84052751c593a8826a40a63cb1d84 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 10 Jan 2019 23:26:54 +0700 Subject: [PATCH 433/558] release 2019.01.10 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 11 ++++++++--- youtube_dl/version.py | 2 +- 4 files changed, 13 insertions(+), 8 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 3986bbc8e..d6abdbcb7 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.02*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.02** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.10*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.10** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.01.02 +[debug] youtube-dl version 2019.01.10 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index c7d090c6c..3d60754c5 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.01.10 Core * [extractor/common] Use episode name as title in _json_ld diff --git a/docs/supportedsites.md b/docs/supportedsites.md index e92064432..c01409419 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -320,6 +320,7 @@ - **Fusion** - **Fux** - **FXNetworks** + - **Gaia** - **GameInformer** - **GameOne** - **gameone:playlist** @@ -370,6 +371,8 @@ - **HRTiPlaylist** - **Huajiao**: 花椒直播 - **HuffPost**: Huffington Post + - **Hungama** + - **HungamaSong** - **Hypem** - **Iconosquare** - **ign.com** @@ -540,8 +543,6 @@ - **MyviEmbed** - **MyVisionTV** - **n-tv.de** - - **natgeo** - - **natgeo:episodeguide** - **natgeo:video** - **Naver** - **NBA** @@ -642,6 +643,7 @@ - **orf:oe1**: Radio Österreich 1 - **orf:tvthek**: ORF TVthek - **OsnatelTV** + - **OutsideTV** - **PacktPub** - **PacktPubCourse** - **PandaTV**: 熊猫TV @@ -666,6 +668,7 @@ - **Pinkbike** - **Pladform** - **play.fm** + - **PlayPlusTV** - **PlaysTV** - **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz - **Playvid** @@ -934,7 +937,9 @@ - **TVNet** - **TVNoe** - **TVNow** - - **TVNowList** + - **TVNowAnnual** + - **TVNowNew** + - **TVNowSeason** - **TVNowShow** - **tvp**: Telewizja Polska - **tvp:embed**: Telewizja Polska diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 07a444706..5ba61f489 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.01.02' +__version__ = '2019.01.10' From c469e8808c723d6ba090c0b33c292622a3cb555e Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 10 Jan 2019 18:48:52 +0100 Subject: [PATCH 434/558] [playplustv] add support for playplus.com(#18789) --- youtube_dl/extractor/playplustv.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/playplustv.py b/youtube_dl/extractor/playplustv.py index 419c2974b..1e30ab23a 100644 --- a/youtube_dl/extractor/playplustv.py +++ b/youtube_dl/extractor/playplustv.py @@ -15,7 +15,7 @@ from ..utils import ( class PlayPlusTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?playplus\.tv/VOD/(?P<project_id>[0-9]+)/(?P<id>[0-9a-f]{32})' + _VALID_URL = r'https?://(?:www\.)?playplus\.(?:com|tv)/VOD/(?P<project_id>[0-9]+)/(?P<id>[0-9a-f]{32})' _TEST = { 'url': 'https://www.playplus.tv/VOD/7572/db8d274a5163424e967f35a30ddafb8e', 'md5': 'd078cb89d7ab6b9df37ce23c647aef72', From a64646e417615173c9436887116402c9c4c9f6ee Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 11 Jan 2019 15:09:44 +0100 Subject: [PATCH 435/558] [postprocessor/ffmpeg] sanitize ffmpeg version for Ubuntu and Arch Linux systems(closes #18813) --- youtube_dl/postprocessor/ffmpeg.py | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index efcd39d57..173bdbe68 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -79,6 +79,19 @@ class FFmpegPostProcessor(PostProcessor): programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe'] prefer_ffmpeg = True + def get_ffmpeg_version(path): + ver = get_exe_version(path, args=['-version']) + if ver: + regexs = [ + r'([0-9.]+)-0ubuntu0\.[0-9.]+$', # Ubuntu + r'n([0-9.]+)$', # Arch Linux + ] + for regex in regexs: + mobj = re.match(regex, ver) + if mobj: + ver = mobj.group(1) + return ver + self.basename = None self.probe_basename = None @@ -110,11 +123,10 @@ class FFmpegPostProcessor(PostProcessor): self._paths = dict( (p, os.path.join(location, p)) for p in programs) self._versions = dict( - (p, get_exe_version(self._paths[p], args=['-version'])) - for p in programs) + (p, get_ffmpeg_version(self._paths[p])) for p in programs) if self._versions is None: self._versions = dict( - (p, get_exe_version(p, args=['-version'])) for p in programs) + (p, get_ffmpeg_version(p)) for p in programs) self._paths = dict((p, p) for p in programs) if prefer_ffmpeg is False: From 5caa531a1a7e070e3bef8cc60c3d00c3f7ab1e6c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 11 Jan 2019 23:47:23 +0700 Subject: [PATCH 436/558] [postprocessor/ffmpeg] PEP 8 --- youtube_dl/postprocessor/ffmpeg.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 173bdbe68..a9fafa363 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -83,8 +83,8 @@ class FFmpegPostProcessor(PostProcessor): ver = get_exe_version(path, args=['-version']) if ver: regexs = [ - r'([0-9.]+)-0ubuntu0\.[0-9.]+$', # Ubuntu - r'n([0-9.]+)$', # Arch Linux + r'([0-9.]+)-0ubuntu0\.[0-9.]+$', # Ubuntu + r'n([0-9.]+)$', # Arch Linux ] for regex in regexs: mobj = re.match(regex, ver) From cbdc688c41876714f1d7e2f82ba9d11f6695448a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 12 Jan 2019 00:30:06 +0700 Subject: [PATCH 437/558] [postprocessor/ffmpeg] Relax ubuntu ffmpeg version regex --- youtube_dl/postprocessor/ffmpeg.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index a9fafa363..39a905380 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -83,8 +83,9 @@ class FFmpegPostProcessor(PostProcessor): ver = get_exe_version(path, args=['-version']) if ver: regexs = [ - r'([0-9.]+)-0ubuntu0\.[0-9.]+$', # Ubuntu + r'(?:\d+:)?([0-9.]+)-[0-9]+ubuntu[0-9.]+$', # Ubuntu, see [1] r'n([0-9.]+)$', # Arch Linux + # 1. http://www.ducea.com/2006/06/17/ubuntu-package-version-naming-explanation/ ] for regex in regexs: mobj = re.match(regex, ver) From 60a899bb7ed583b4c40289925c8127e746c683ea Mon Sep 17 00:00:00 2001 From: Atlas Sullivan <AtlasJan@gmx.com> Date: Fri, 11 Jan 2019 19:15:48 +0000 Subject: [PATCH 438/558] [README.md] Fix typo --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 901595444..70bcfaccf 100644 --- a/README.md +++ b/README.md @@ -496,7 +496,7 @@ The `-o` option allows users to indicate a template for the output file names. **tl;dr:** [navigate me to examples](#output-template-examples). -The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "https://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a formatting operations. Allowed names along with sequence type are: +The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "https://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by formatting operations. Allowed names along with sequence type are: - `id` (string): Video identifier - `title` (string): Video title From ed8db0a25c93f5611dfae81ee8f15cbc177bd0ab Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 12 Jan 2019 04:56:17 +0700 Subject: [PATCH 439/558] [wistia] Extend _VALID_URL (closes #18823) --- youtube_dl/extractor/wistia.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py index 01a51275e..fa142b974 100644 --- a/youtube_dl/extractor/wistia.py +++ b/youtube_dl/extractor/wistia.py @@ -12,7 +12,7 @@ from ..utils import ( class WistiaIE(InfoExtractor): - _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/iframe/)(?P<id>[a-z0-9]+)' + _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/)(?P<id>[a-z0-9]+)' _API_URL = 'http://fast.wistia.com/embed/medias/%s.json' _IFRAME_URL = 'http://fast.wistia.net/embed/iframe/%s' @@ -38,6 +38,9 @@ class WistiaIE(InfoExtractor): }, { 'url': 'http://fast.wistia.com/embed/iframe/sh7fpupwlt', 'only_matching': True, + }, { + 'url': 'http://fast.wistia.net/embed/medias/sh7fpupwlt.json', + 'only_matching': True, }] @staticmethod From d65f6e734b5c00acbb396f4569907f7957e1cbef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 13 Jan 2019 03:57:31 +0700 Subject: [PATCH 440/558] [bitchute] Check formats (#18833) --- youtube_dl/extractor/bitchute.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py index aa034355a..4f39424f5 100644 --- a/youtube_dl/extractor/bitchute.py +++ b/youtube_dl/extractor/bitchute.py @@ -55,6 +55,7 @@ class BitChuteIE(InfoExtractor): formats = [ {'url': format_url} for format_url in orderedSet(format_urls)] + self._check_formats(formats, video_id) self._sort_formats(formats) description = self._html_search_regex( From f1ab3b7de7667c0382bf6eb6364ccab4260c0654 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 13 Jan 2019 10:01:26 +0100 Subject: [PATCH 441/558] [downloader/hls] fix uplynk ad skipping(closes #18824) --- youtube_dl/downloader/hls.py | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py index fd304527e..4def8e2d5 100644 --- a/youtube_dl/downloader/hls.py +++ b/youtube_dl/downloader/hls.py @@ -75,10 +75,14 @@ class HlsFD(FragmentFD): fd.add_progress_hook(ph) return fd.real_download(filename, info_dict) - def is_ad_fragment(s): + def is_ad_fragment_start(s): return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s or s.startswith('#UPLYNK-SEGMENT') and s.endswith(',ad')) + def is_ad_fragment_end(s): + return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=master' in s or + s.startswith('#UPLYNK-SEGMENT') and s.endswith(',segment')) + media_frags = 0 ad_frags = 0 ad_frag_next = False @@ -87,12 +91,13 @@ class HlsFD(FragmentFD): if not line: continue if line.startswith('#'): - if is_ad_fragment(line): - ad_frags += 1 + if is_ad_fragment_start(line): ad_frag_next = True + elif is_ad_fragment_end(line): + ad_frag_next = False continue if ad_frag_next: - ad_frag_next = False + ad_frags += 1 continue media_frags += 1 @@ -123,7 +128,6 @@ class HlsFD(FragmentFD): if line: if not line.startswith('#'): if ad_frag_next: - ad_frag_next = False continue frag_index += 1 if frag_index <= ctx['fragment_index']: @@ -196,8 +200,10 @@ class HlsFD(FragmentFD): 'start': sub_range_start, 'end': sub_range_start + int(splitted_byte_range[0]), } - elif is_ad_fragment(line): + elif is_ad_fragment_start(line): ad_frag_next = True + elif is_ad_fragment_end(line): + ad_frag_next = False self._finish_frag_download(ctx) From 3b983ee471305946709dcb83fa3799fc26a7db03 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 13 Jan 2019 15:46:54 +0100 Subject: [PATCH 442/558] [curiositystream] add support for non app urls --- youtube_dl/extractor/curiositystream.py | 56 +++++++++++++------------ 1 file changed, 29 insertions(+), 27 deletions(-) diff --git a/youtube_dl/extractor/curiositystream.py b/youtube_dl/extractor/curiositystream.py index 35b1e7a34..e4a7fca6c 100644 --- a/youtube_dl/extractor/curiositystream.py +++ b/youtube_dl/extractor/curiositystream.py @@ -46,8 +46,24 @@ class CuriosityStreamBaseIE(InfoExtractor): self._handle_errors(result) self._auth_token = result['message']['auth_token'] - def _extract_media_info(self, media): - video_id = compat_str(media['id']) + +class CuriosityStreamIE(CuriosityStreamBaseIE): + IE_NAME = 'curiositystream' + _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/video/(?P<id>\d+)' + _TEST = { + 'url': 'https://app.curiositystream.com/video/2', + 'md5': '262bb2f257ff301115f1973540de8983', + 'info_dict': { + 'id': '2', + 'ext': 'mp4', + 'title': 'How Did You Develop The Internet?', + 'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + media = self._call_api('media/' + video_id, video_id) title = media['title'] formats = [] @@ -114,38 +130,21 @@ class CuriosityStreamBaseIE(InfoExtractor): } -class CuriosityStreamIE(CuriosityStreamBaseIE): - IE_NAME = 'curiositystream' - _VALID_URL = r'https?://app\.curiositystream\.com/video/(?P<id>\d+)' - _TEST = { - 'url': 'https://app.curiositystream.com/video/2', - 'md5': '262bb2f257ff301115f1973540de8983', - 'info_dict': { - 'id': '2', - 'ext': 'mp4', - 'title': 'How Did You Develop The Internet?', - 'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.', - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - media = self._call_api('media/' + video_id, video_id) - return self._extract_media_info(media) - - class CuriosityStreamCollectionIE(CuriosityStreamBaseIE): IE_NAME = 'curiositystream:collection' - _VALID_URL = r'https?://app\.curiositystream\.com/collection/(?P<id>\d+)' - _TEST = { + _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/(?:collection|series)/(?P<id>\d+)' + _TESTS = [{ 'url': 'https://app.curiositystream.com/collection/2', 'info_dict': { 'id': '2', 'title': 'Curious Minds: The Internet', 'description': 'How is the internet shaping our lives in the 21st Century?', }, - 'playlist_mincount': 12, - } + 'playlist_mincount': 17, + }, { + 'url': 'https://curiositystream.com/series/2', + 'only_matching': True, + }] def _real_extract(self, url): collection_id = self._match_id(url) @@ -153,7 +152,10 @@ class CuriosityStreamCollectionIE(CuriosityStreamBaseIE): 'collections/' + collection_id, collection_id) entries = [] for media in collection.get('media', []): - entries.append(self._extract_media_info(media)) + media_id = compat_str(media.get('id')) + entries.append(self.url_result( + 'https://curiositystream.com/video/' + media_id, + CuriosityStreamIE.ie_key(), media_id)) return self.playlist_result( entries, collection_id, collection.get('title'), collection.get('description')) From 10026329c2534635876921da229f382098b8f8e8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 14 Jan 2019 23:23:51 +0700 Subject: [PATCH 443/558] [skylinewebcams] Fix extraction (closes #18853) --- youtube_dl/extractor/skylinewebcams.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/skylinewebcams.py b/youtube_dl/extractor/skylinewebcams.py index 5b4aaac6f..b7f8ac736 100644 --- a/youtube_dl/extractor/skylinewebcams.py +++ b/youtube_dl/extractor/skylinewebcams.py @@ -26,7 +26,7 @@ class SkylineWebcamsIE(InfoExtractor): webpage = self._download_webpage(url, video_id) stream_url = self._search_regex( - r'url\s*:\s*(["\'])(?P<url>(?:https?:)?//.+?\.m3u8.*?)\1', webpage, + r'(?:url|source)\s*:\s*(["\'])(?P<url>(?:https?:)?//.+?\.m3u8.*?)\1', webpage, 'stream url', group='url') title = self._og_search_title(webpage) From 929ba3997b026fd9fafe15d447732d8ccdf367bb Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 15 Jan 2019 10:23:59 +0100 Subject: [PATCH 444/558] [funimation] fix extraction(closes #14089) --- youtube_dl/extractor/funimation.py | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/funimation.py b/youtube_dl/extractor/funimation.py index 07d01caec..8bbedca26 100644 --- a/youtube_dl/extractor/funimation.py +++ b/youtube_dl/extractor/funimation.py @@ -1,6 +1,9 @@ # coding: utf-8 from __future__ import unicode_literals +import random +import string + from .common import InfoExtractor from ..compat import compat_HTTPError from ..utils import ( @@ -87,7 +90,7 @@ class FunimationIE(InfoExtractor): video_id = title_data.get('id') or self._search_regex([ r"KANE_customdimensions.videoID\s*=\s*'(\d+)';", - r'<iframe[^>]+src="/player/(\d+)"', + r'<iframe[^>]+src="/player/(\d+)', ], webpage, 'video_id', default=None) if not video_id: player_url = self._html_search_meta([ @@ -108,8 +111,10 @@ class FunimationIE(InfoExtractor): if self._TOKEN: headers['Authorization'] = 'Token %s' % self._TOKEN sources = self._download_json( - 'https://prod-api-funimationnow.dadcdigital.com/api/source/catalog/video/%s/signed/' % video_id, - video_id, headers=headers)['items'] + 'https://www.funimation.com/api/showexperience/%s/' % video_id, + video_id, headers=headers, query={ + 'pinst_id': ''.join([random.choice(string.digits + string.ascii_letters) for _ in range(8)]), + })['items'] except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: error = self._parse_json(e.cause.read(), video_id)['errors'][0] From 561b456e2d10e60b74a1bee6154bb7fdb0bfaf60 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 16 Jan 2019 01:12:58 +0700 Subject: [PATCH 445/558] [youtube] Extract DASH formats from player response (closes #18804) --- youtube_dl/extractor/youtube.py | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 29773877e..cca149107 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1545,6 +1545,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if dash_mpd and dash_mpd[0] not in dash_mpds: dash_mpds.append(dash_mpd[0]) + def add_dash_mpd_pr(pl_response): + dash_mpd = url_or_none(try_get( + pl_response, lambda x: x['streamingData']['dashManifestUrl'], + compat_str)) + if dash_mpd and dash_mpd not in dash_mpds: + dash_mpds.append(dash_mpd) + is_live = None view_count = None @@ -1602,6 +1609,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if isinstance(pl_response, dict): player_response = pl_response if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): + add_dash_mpd_pr(player_response) # We also try looking in get_video_info since it may contain different dashmpd # URL that points to a DASH manifest with possibly different itag set (some itags # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH @@ -1633,6 +1641,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): pl_response = get_video_info.get('player_response', [None])[0] if isinstance(pl_response, dict): player_response = pl_response + add_dash_mpd_pr(player_response) add_dash_mpd(get_video_info) if view_count is None: view_count = extract_view_count(get_video_info) From 2f483bc1c389709623117079439708783122b5ec Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 16 Jan 2019 01:28:50 +0700 Subject: [PATCH 446/558] [youtube] Skip unsupported adaptive stream type (#18804) --- youtube_dl/extractor/youtube.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index cca149107..5e93b5329 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1827,6 +1827,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): url_data = compat_parse_qs(url_data_str) if 'itag' not in url_data or 'url' not in url_data: continue + stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0])) + # Unsupported FORMAT_STREAM_TYPE_OTF + if stream_type == 3: + continue format_id = url_data['itag'][0] url = url_data['url'][0] From a16c7c033a161f310b69d444edc9dbf67cfc49ff Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 16 Jan 2019 02:17:49 +0700 Subject: [PATCH 447/558] [test/helper] Add support for maxcount and count collection len test checkers --- test/helper.py | 34 ++++++++++++++++++++++++++++++---- 1 file changed, 30 insertions(+), 4 deletions(-) diff --git a/test/helper.py b/test/helper.py index aa9a1c9b2..e62aab11e 100644 --- a/test/helper.py +++ b/test/helper.py @@ -153,15 +153,27 @@ def expect_value(self, got, expected, field): isinstance(got, compat_str), 'Expected field %s to be a unicode object, but got value %r of type %r' % (field, got, type(got))) got = 'md5:' + md5(got) - elif isinstance(expected, compat_str) and expected.startswith('mincount:'): + elif isinstance(expected, compat_str) and re.match(r'^(?:min|max)?count:\d+', expected): self.assertTrue( isinstance(got, (list, dict)), 'Expected field %s to be a list or a dict, but it is of type %s' % ( field, type(got).__name__)) - expected_num = int(expected.partition(':')[2]) - assertGreaterEqual( + op, _, expected_num = expected.partition(':') + expected_num = int(expected_num) + if op == 'mincount': + assert_func = assertGreaterEqual + msg_tmpl = 'Expected %d items in field %s, but only got %d' + elif op == 'maxcount': + assert_func = assertLessEqual + msg_tmpl = 'Expected maximum %d items in field %s, but got %d' + elif op == 'count': + assert_func = assertEqual + msg_tmpl = 'Expected exactly %d items in field %s, but got %d' + else: + assert False + assert_func( self, len(got), expected_num, - 'Expected %d items in field %s, but only got %d' % (expected_num, field, len(got))) + msg_tmpl % (expected_num, field, len(got))) return self.assertEqual( expected, got, @@ -237,6 +249,20 @@ def assertGreaterEqual(self, got, expected, msg=None): self.assertTrue(got >= expected, msg) +def assertLessEqual(self, got, expected, msg=None): + if not (got <= expected): + if msg is None: + msg = '%r not less than or equal to %r' % (got, expected) + self.assertTrue(got <= expected, msg) + + +def assertEqual(self, got, expected, msg=None): + if not (got == expected): + if msg is None: + msg = '%r not equal to %r' % (got, expected) + self.assertTrue(got == expected, msg) + + def expect_warnings(ydl, warnings_re): real_warning = ydl.report_warning From 4fe54c128a11d394874505af75aaa5a2276aa3ba Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 16 Jan 2019 02:18:27 +0700 Subject: [PATCH 448/558] [youtube] Update tests and add a tests for #18804 --- youtube_dl/extractor/youtube.py | 57 +++++++++++++++++---------------- 1 file changed, 29 insertions(+), 28 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 5e93b5329..730935657 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -498,7 +498,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', 'upload_date': '20121002', - 'license': 'Standard YouTube License', 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .', 'categories': ['Science & Technology'], 'tags': ['youtube-dl'], @@ -527,7 +526,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': 'Icona Pop', 'uploader_id': 'IconaPop', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop', - 'license': 'Standard YouTube License', 'creator': 'Icona Pop', 'track': 'I Love It (feat. Charli XCX)', 'artist': 'Icona Pop', @@ -540,14 +538,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': '07FYdnEawAQ', 'ext': 'mp4', 'upload_date': '20130703', - 'title': 'Justin Timberlake - Tunnel Vision (Explicit)', + 'title': 'Justin Timberlake - Tunnel Vision (Official Music Video) (Explicit)', 'alt_title': 'Tunnel Vision', - 'description': 'md5:64249768eec3bc4276236606ea996373', + 'description': 'md5:07dab3356cde4199048e4c7cd93471e1', 'duration': 419, 'uploader': 'justintimberlakeVEVO', 'uploader_id': 'justintimberlakeVEVO', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO', - 'license': 'Standard YouTube License', 'creator': 'Justin Timberlake', 'track': 'Tunnel Vision', 'artist': 'Justin Timberlake', @@ -566,7 +563,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': 'SET India', 'uploader_id': 'setindia', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia', - 'license': 'Standard YouTube License', 'age_limit': 18, } }, @@ -581,7 +577,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_id': 'phihag', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', 'upload_date': '20121002', - 'license': 'Standard YouTube License', 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .', 'categories': ['Science & Technology'], 'tags': ['youtube-dl'], @@ -605,7 +600,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO', 'description': '', 'uploader': '8KVIDEO', - 'license': 'Standard YouTube License', 'title': 'UHDTV TEST 8K VIDEO.mp4' }, 'params': { @@ -620,13 +614,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'info_dict': { 'id': 'IB3lcPjvWLA', 'ext': 'm4a', - 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson', - 'description': 'md5:1900ed86ee514927b9e00fbead6969a5', + 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson', + 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf', 'duration': 244, 'uploader': 'AfrojackVEVO', 'uploader_id': 'AfrojackVEVO', 'upload_date': '20131011', - 'license': 'Standard YouTube License', }, 'params': { 'youtube_include_dash_manifest': True, @@ -640,13 +633,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': 'nfWlot6h_JM', 'ext': 'm4a', 'title': 'Taylor Swift - Shake It Off', - 'alt_title': 'Shake It Off', - 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3', + 'description': 'md5:bec2185232c05479482cb5a9b82719bf', 'duration': 242, 'uploader': 'TaylorSwiftVEVO', 'uploader_id': 'TaylorSwiftVEVO', 'upload_date': '20140818', - 'license': 'Standard YouTube License', 'creator': 'Taylor Swift', }, 'params': { @@ -662,10 +653,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'ext': 'mp4', 'duration': 219, 'upload_date': '20100909', - 'uploader': 'TJ Kirk', + 'uploader': 'Amazing Atheist', 'uploader_id': 'TheAmazingAtheist', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist', - 'license': 'Standard YouTube License', 'title': 'Burning Everyone\'s Koran', 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html', } @@ -683,7 +673,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_id': 'WitcherGame', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame', 'upload_date': '20140605', - 'license': 'Standard YouTube License', 'age_limit': 18, }, }, @@ -692,7 +681,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU', 'info_dict': { 'id': '6kLq3WMV1nU', - 'ext': 'webm', + 'ext': 'mp4', 'title': 'Dedication To My Ex (Miss That) (Lyric Video)', 'description': 'md5:33765bb339e1b47e7e72b5490139bb41', 'duration': 246, @@ -700,7 +689,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_id': 'LloydVEVO', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO', 'upload_date': '20110629', - 'license': 'Standard YouTube License', 'age_limit': 18, }, }, @@ -718,7 +706,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'creator': 'deadmau5', 'description': 'md5:12c56784b8032162bb936a5f76d55360', 'uploader': 'deadmau5', - 'license': 'Standard YouTube License', 'title': 'Deadmau5 - Some Chords (HD)', 'alt_title': 'Some Chords', }, @@ -736,7 +723,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'upload_date': '20150827', 'uploader_id': 'olympic', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic', - 'license': 'Standard YouTube License', 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', 'uploader': 'Olympic', 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', @@ -758,7 +744,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow', 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯', 'uploader': '孫ᄋᄅ', - 'license': 'Standard YouTube License', 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', }, }, @@ -792,7 +777,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_id': 'dorappi2000', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000', 'uploader': 'dorappi2000', - 'license': 'Standard YouTube License', 'formats': 'mincount:31', }, 'skip': 'not actual anymore', @@ -808,7 +792,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': 'Airtek', 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.', 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ', - 'license': 'Standard YouTube License', 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015', }, 'params': { @@ -881,6 +864,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'params': { 'skip_download': True, }, + 'skip': 'This video is not available.', }, { # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536) @@ -917,7 +901,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_id': 'IronSoulElf', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf', 'uploader': 'IronSoulElf', - 'license': 'Standard YouTube License', 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan', 'track': 'Dark Walk - Position Music', 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan', @@ -1021,13 +1004,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': 'iqKdEhx-dD4', 'ext': 'mp4', 'title': 'Isolation - Mind Field (Ep 1)', - 'description': 'md5:25b78d2f64ae81719f5c96319889b736', + 'description': 'md5:46a29be4ceffa65b92d277b93f463c0f', 'duration': 2085, 'upload_date': '20170118', 'uploader': 'Vsauce', 'uploader_id': 'Vsauce', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce', - 'license': 'Standard YouTube License', 'series': 'Mind Field', 'season_number': 1, 'episode_number': 1, @@ -1053,7 +1035,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': 'New Century Foundation', 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg', - 'license': 'Standard YouTube License', }, 'params': { 'skip_download': True, @@ -1081,6 +1062,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # DRM protected 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc', 'only_matching': True, + }, + { + # Video with unsupported adaptive stream type formats + 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U', + 'info_dict': { + 'id': 'Z4Vy8R84T1U', + 'ext': 'mp4', + 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'duration': 433, + 'upload_date': '20130923', + 'uploader': 'Amelia Putri Harwita', + 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q', + 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q', + 'formats': 'maxcount:10', + }, + 'params': { + 'skip_download': True, + 'youtube_include_dash_manifest': False, + }, } ] From b0d73a745656443baf3e2134d9ca03bd3a4a934c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 16 Jan 2019 02:20:10 +0700 Subject: [PATCH 449/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/ChangeLog b/ChangeLog index 3d60754c5..d25169074 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,21 @@ +version <unreleased> + +Core ++ [test/helper] Add support for maxcount and count collection len checkers +* [downloader/hls] Fix uplynk ad skipping (#18824) +* [postprocessor/ffmpeg] Improve ffmpeg version parsing (#18813) + +Extractors +* [youtube] Skip unsupported adaptive stream type (#18804) ++ [youtube] Extract DASH formats from player response (#18804) +* [funimation] Fix extraction (#14089) +* [skylinewebcams] Fix extraction (#18853) ++ [curiositystream] Add support for non app URLs ++ [bitchute] Check formats (#18833) +* [wistia] Extend URL regular expression (#18823) ++ [playplustv] Add support for playplus.com (#18789) + + version 2019.01.10 Core From bfc8eeea57251796d44f1e10b61d06760690bc25 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 16 Jan 2019 02:24:08 +0700 Subject: [PATCH 450/558] release 2019.01.16 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index d6abdbcb7..650f78511 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.10*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.10** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.16*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.16** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.01.10 +[debug] youtube-dl version 2019.01.16 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index d25169074..13019bf2b 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.01.16 Core + [test/helper] Add support for maxcount and count collection len checkers diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 5ba61f489..c13f3a38a 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.01.10' +__version__ = '2019.01.16' From fa4ac365f69cbd51e4c9801984ebea49a12825b7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 17 Jan 2019 10:24:44 +0700 Subject: [PATCH 451/558] [youtube] Extend JS player signature function name regexes (closes #18890, closes #18891, closes #18893) --- youtube_dl/extractor/youtube.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 730935657..c8bf98b58 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1198,8 +1198,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): funcname = self._search_regex( (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(', - r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', - r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', + r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?(?P<sig>[a-zA-Z0-9$]+)\(', + r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(', r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('), jscode, 'Initial JS player signature function name', group='sig') From f53cecd796dbb698abbde6ac2f7f973dba78f8a9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 17 Jan 2019 10:25:50 +0700 Subject: [PATCH 452/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/ChangeLog b/ChangeLog index 13019bf2b..171034a75 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,10 @@ +version <unreleased> + +Extractors +* [youtube] Extend JS player signature function name regular expressions + (#18890, #18891, #18893) + + version 2019.01.16 Core From 29639b363ddab7903ceae096912a0227c8017533 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 17 Jan 2019 10:27:17 +0700 Subject: [PATCH 453/558] release 2019.01.17 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 650f78511..841bca914 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.16*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.16** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.17*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.17** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.01.16 +[debug] youtube-dl version 2019.01.17 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 171034a75..902301765 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.01.17 Extractors * [youtube] Extend JS player signature function name regular expressions diff --git a/youtube_dl/version.py b/youtube_dl/version.py index c13f3a38a..ea3f62928 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.01.16' +__version__ = '2019.01.17' From 79fec976b0c250446ea9a9eb7323fb2045ee37fe Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 17 Jan 2019 09:44:08 +0100 Subject: [PATCH 454/558] [vimeo] fix extraction for password protected player URLs(closes #18889) --- youtube_dl/extractor/vimeo.py | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 5e15f060b..fd37f919b 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -1,6 +1,7 @@ # coding: utf-8 from __future__ import unicode_literals +import base64 import json import re import itertools @@ -392,6 +393,22 @@ class VimeoIE(VimeoBaseInfoExtractor): 'skip_download': True, }, }, + { + 'url': 'http://player.vimeo.com/video/68375962', + 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7', + 'info_dict': { + 'id': '68375962', + 'ext': 'mp4', + 'title': 'youtube-dl password protected test video', + 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128', + 'uploader_id': 'user18948128', + 'uploader': 'Jaime Marquínez Ferrándiz', + 'duration': 10, + }, + 'params': { + 'videopassword': 'youtube-dl', + }, + }, { 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741', 'only_matching': True, @@ -452,7 +469,9 @@ class VimeoIE(VimeoBaseInfoExtractor): password = self._downloader.params.get('videopassword') if password is None: raise ExtractorError('This video is protected by a password, use the --video-password option') - data = urlencode_postdata({'password': password}) + data = urlencode_postdata({ + 'password': base64.b64encode(password.encode()), + }) pass_url = url + '/check-password' password_request = sanitized_Request(pass_url, data) password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') From e2dd132f054df5b6c09b7c274752a77d8ba44f8d Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 17 Jan 2019 23:56:37 +0100 Subject: [PATCH 455/558] [cartoonnetwork] fix extraction(closes #15664)(closes #17224) --- youtube_dl/extractor/cartoonnetwork.py | 56 +++++++++++++++++--------- 1 file changed, 38 insertions(+), 18 deletions(-) diff --git a/youtube_dl/extractor/cartoonnetwork.py b/youtube_dl/extractor/cartoonnetwork.py index 6aeebd7b3..48b33617f 100644 --- a/youtube_dl/extractor/cartoonnetwork.py +++ b/youtube_dl/extractor/cartoonnetwork.py @@ -1,20 +1,19 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .turner import TurnerBaseIE +from ..utils import int_or_none class CartoonNetworkIE(TurnerBaseIE): _VALID_URL = r'https?://(?:www\.)?cartoonnetwork\.com/video/(?:[^/]+/)+(?P<id>[^/?#]+)-(?:clip|episode)\.html' _TEST = { - 'url': 'http://www.cartoonnetwork.com/video/teen-titans-go/starfire-the-cat-lady-clip.html', + 'url': 'https://www.cartoonnetwork.com/video/ben-10/how-to-draw-upgrade-episode.html', 'info_dict': { - 'id': '8a250ab04ed07e6c014ef3f1e2f9016c', + 'id': '6e3375097f63874ebccec7ef677c1c3845fa850e', 'ext': 'mp4', - 'title': 'Starfire the Cat Lady', - 'description': 'Robin decides to become a cat so that Starfire will finally love him.', + 'title': 'How to Draw Upgrade', + 'description': 'md5:2061d83776db7e8be4879684eefe8c0f', }, 'params': { # m3u8 download @@ -25,18 +24,39 @@ class CartoonNetworkIE(TurnerBaseIE): def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - id_type, video_id = re.search(r"_cnglobal\.cvp(Video|Title)Id\s*=\s*'([^']+)';", webpage).groups() - query = ('id' if id_type == 'Video' else 'titleId') + '=' + video_id - return self._extract_cvp_info( - 'http://www.cartoonnetwork.com/video-seo-svc/episodeservices/getCvpPlaylist?networkName=CN2&' + query, video_id, { - 'secure': { - 'media_src': 'http://androidhls-secure.cdn.turner.com/toon/big', - 'tokenizer_src': 'https://token.vgtf.net/token/token_mobile', - }, - }, { + + def find_field(global_re, name, content_re=None, value_re='[^"]+', fatal=False): + metadata_re = '' + if content_re: + metadata_re = r'|video_metadata\.content_' + content_re + return self._search_regex( + r'(?:_cnglobal\.currentVideo\.%s%s)\s*=\s*"(%s)";' % (global_re, metadata_re, value_re), + webpage, name, fatal=fatal) + + media_id = find_field('mediaId', 'media id', 'id', '[0-9a-f]{40}', True) + title = find_field('episodeTitle', 'title', '(?:episodeName|name)', fatal=True) + + info = self._extract_ngtv_info( + media_id, {'networkId': 'cartoonnetwork'}, { 'url': url, 'site_name': 'CartoonNetwork', - 'auth_required': self._search_regex( - r'_cnglobal\.cvpFullOrPreviewAuth\s*=\s*(true|false);', - webpage, 'auth required', default='false') == 'true', + 'auth_required': find_field('authType', 'auth type') != 'unauth', }) + + series = find_field( + 'propertyName', 'series', 'showName') or self._html_search_meta('partOfSeries', webpage) + info.update({ + 'id': media_id, + 'display_id': display_id, + 'title': title, + 'description': self._html_search_meta('description', webpage), + 'series': series, + 'episode': title, + }) + + for field in ('season', 'episode'): + field_name = field + 'Number' + info[field + '_number'] = int_or_none(find_field( + field_name, field + ' number', value_re=r'\d+') or self._html_search_meta(field_name, webpage)) + + return info From 2bfc1d9d68dec097fd8093dc0284dd0cd64beb2e Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 19 Jan 2019 21:25:15 +0100 Subject: [PATCH 456/558] [extractor/common] imporove HLS video only format detection(closes #18923) --- youtube_dl/extractor/common.py | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 9e7febcad..af621b74b 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1596,6 +1596,7 @@ class InfoExtractor(object): # References: # 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-21 # 2. https://github.com/rg3/youtube-dl/issues/12211 + # 3. https://github.com/rg3/youtube-dl/issues/18923 # We should try extracting formats only from master playlists [1, 4.3.4], # i.e. playlists that describe available qualities. On the other hand @@ -1667,11 +1668,16 @@ class InfoExtractor(object): rendition = stream_group[0] return rendition.get('NAME') or stream_group_id + # parse EXT-X-MEDIA tags before EXT-X-STREAM-INF inorder to have the + # chance to detect video only formats when EXT-X-STREAM-INF tags + # precede EXT-X-MEDIA tags in HLS manifest such as [3]. + for line in m3u8_doc.splitlines(): + if line.startswith('#EXT-X-MEDIA:'): + extract_media(line) + for line in m3u8_doc.splitlines(): if line.startswith('#EXT-X-STREAM-INF:'): last_stream_inf = parse_m3u8_attributes(line) - elif line.startswith('#EXT-X-MEDIA:'): - extract_media(line) elif line.startswith('#') or not line.strip(): continue else: From f28363ad1fb45b4450ae6f09ff9aff8f93227e40 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 19 Jan 2019 21:25:53 +0100 Subject: [PATCH 457/558] [ted] correct acodec for http formats(#18923) --- youtube_dl/extractor/ted.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index d3e4205f5..645942dfd 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -265,6 +265,8 @@ class TEDIE(InfoExtractor): 'format_id': m3u8_format['format_id'].replace('hls', 'http'), 'protocol': 'http', }) + if f.get('acodec') == 'none': + del f['acodec'] formats.append(f) audio_download = talk_info.get('audioDownload') From 379306ef55b64c966392c072b17a450831fec252 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 19 Jan 2019 21:35:02 +0100 Subject: [PATCH 458/558] [extractor/common] fix typo --- youtube_dl/extractor/common.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index af621b74b..6e36e6778 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1668,7 +1668,7 @@ class InfoExtractor(object): rendition = stream_group[0] return rendition.get('NAME') or stream_group_id - # parse EXT-X-MEDIA tags before EXT-X-STREAM-INF inorder to have the + # parse EXT-X-MEDIA tags before EXT-X-STREAM-INF in order to have the # chance to detect video only formats when EXT-X-STREAM-INF tags # precede EXT-X-MEDIA tags in HLS manifest such as [3]. for line in m3u8_doc.splitlines(): From 2cc779f497ae20d6e0e28fc546a25723cfea631a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 20 Jan 2019 13:48:09 +0700 Subject: [PATCH 459/558] [YoutubeDL] Add negation support for string comparisons in format selection expressions (closes #18600, closes #18805) --- README.md | 3 ++- test/test_YoutubeDL.py | 46 +++++++++++++++++++++++++++++++++++++++++ youtube_dl/YoutubeDL.py | 9 +++++--- 3 files changed, 54 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 70bcfaccf..886696015 100644 --- a/README.md +++ b/README.md @@ -667,13 +667,14 @@ The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, ` - `asr`: Audio sampling rate in Hertz - `fps`: Frame rate -Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begins with), `$=` (ends with), `*=` (contains) and following string meta fields: +Also filtering work for comparisons `=` (equals), `^=` (starts with), `$=` (ends with), `*=` (contains) and following string meta fields: - `ext`: File extension - `acodec`: Name of the audio codec in use - `vcodec`: Name of the video codec in use - `container`: Name of the container format - `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `http_dash_segments`, `m3u8`, or `m3u8_native`) - `format_id`: A short description of the format +Any string comparison may be prefixed with negation `!` in order to produce an opposite comparison, e.g. `!*=` (does not contain). Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the video hoster. diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index f0f5a8470..df8994b84 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -239,6 +239,52 @@ class TestFormatSelection(unittest.TestCase): downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot') + def test_format_selection_string_ops(self): + formats = [ + {'format_id': 'abc-cba', 'ext': 'mp4', 'url': TEST_URL}, + ] + info_dict = _make_result(formats) + + # equals (=) + ydl = YDL({'format': '[format_id=abc-cba]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'abc-cba') + + # does not equal (!=) + ydl = YDL({'format': '[format_id!=abc-cba]'}) + self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) + + # starts with (^=) + ydl = YDL({'format': '[format_id^=abc]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'abc-cba') + + # does not start with (!^=) + ydl = YDL({'format': '[format_id!^=abc-cba]'}) + self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) + + # ends with ($=) + ydl = YDL({'format': '[format_id$=cba]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'abc-cba') + + # does not end with (!$=) + ydl = YDL({'format': '[format_id!$=abc-cba]'}) + self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) + + # contains (*=) + ydl = YDL({'format': '[format_id*=-]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'abc-cba') + + # does not contain (!*=) + ydl = YDL({'format': '[format_id!*=-]'}) + self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) + def test_youtube_format_selection(self): order = [ '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '17', '36', '13', diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 4493fd0e1..a827414dc 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -1063,21 +1063,24 @@ class YoutubeDL(object): if not m: STR_OPERATORS = { '=': operator.eq, - '!=': operator.ne, '^=': lambda attr, value: attr.startswith(value), '$=': lambda attr, value: attr.endswith(value), '*=': lambda attr, value: value in attr, } str_operator_rex = re.compile(r'''(?x) \s*(?P<key>ext|acodec|vcodec|container|protocol|format_id) - \s*(?P<op>%s)(?P<none_inclusive>\s*\?)? + \s*(?P<negation>!\s*)?(?P<op>%s)(?P<none_inclusive>\s*\?)? \s*(?P<value>[a-zA-Z0-9._-]+) \s*$ ''' % '|'.join(map(re.escape, STR_OPERATORS.keys()))) m = str_operator_rex.search(filter_spec) if m: comparison_value = m.group('value') - op = STR_OPERATORS[m.group('op')] + str_op = STR_OPERATORS[m.group('op')] + if m.group('negation'): + op = lambda attr, value: not str_op + else: + op = str_op if not m: raise ValueError('Invalid filter specification %r' % filter_spec) From 4e58d9fabbfef80b2ecc0d20959bdf9dd3705e73 Mon Sep 17 00:00:00 2001 From: Sergey M <dstftw@gmail.com> Date: Sun, 20 Jan 2019 14:23:35 +0700 Subject: [PATCH 460/558] [README.md] Fix formatting --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 886696015..4ba982907 100644 --- a/README.md +++ b/README.md @@ -674,6 +674,7 @@ Also filtering work for comparisons `=` (equals), `^=` (starts with), `$=` (ends - `container`: Name of the container format - `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `http_dash_segments`, `m3u8`, or `m3u8_native`) - `format_id`: A short description of the format + Any string comparison may be prefixed with negation `!` in order to produce an opposite comparison, e.g. `!*=` (does not contain). Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the video hoster. From fc746c3fdd7d40935a11e72b5cb69a8aee840e94 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 20 Jan 2019 09:04:51 +0100 Subject: [PATCH 461/558] [test/test_InfoExtractor] add test for #18923 --- test/test_InfoExtractor.py | 59 ++++++++++++++++++++++++++++++- test/testdata/m3u8/ted_18923.m3u8 | 28 +++++++++++++++ 2 files changed, 86 insertions(+), 1 deletion(-) create mode 100644 test/testdata/m3u8/ted_18923.m3u8 diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py index 06be72616..75fa0bbb7 100644 --- a/test/test_InfoExtractor.py +++ b/test/test_InfoExtractor.py @@ -497,7 +497,64 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/ 'width': 1280, 'height': 720, }] - ) + ), + ( + # https://github.com/rg3/youtube-dl/issues/18923 + # https://www.ted.com/talks/boris_hesser_a_grassroots_healthcare_revolution_in_africa + 'ted_18923', + 'http://hls.ted.com/talks/31241.m3u8', + [{ + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '600k-Audio', + 'vcodec': 'none', + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '68', + 'vcodec': 'none', + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/64k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '163', + 'acodec': 'none', + 'width': 320, + 'height': 180, + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/180k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '481', + 'acodec': 'none', + 'width': 512, + 'height': 288, + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/320k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '769', + 'acodec': 'none', + 'width': 512, + 'height': 288, + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/450k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '984', + 'acodec': 'none', + 'width': 512, + 'height': 288, + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/600k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '1255', + 'acodec': 'none', + 'width': 640, + 'height': 360, + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/950k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '1693', + 'acodec': 'none', + 'width': 853, + 'height': 480, + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/1500k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '2462', + 'acodec': 'none', + 'width': 1280, + 'height': 720, + }] + ), ] for m3u8_file, m3u8_url, expected_formats in _TEST_CASES: diff --git a/test/testdata/m3u8/ted_18923.m3u8 b/test/testdata/m3u8/ted_18923.m3u8 new file mode 100644 index 000000000..52a27118b --- /dev/null +++ b/test/testdata/m3u8/ted_18923.m3u8 @@ -0,0 +1,28 @@ +#EXTM3U +#EXT-X-VERSION:4 +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=1255659,PROGRAM-ID=1,CODECS="avc1.42c01e,mp4a.40.2",RESOLUTION=640x360 +/videos/BorisHesser_2018S/video/600k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=163154,PROGRAM-ID=1,CODECS="avc1.42c00c,mp4a.40.2",RESOLUTION=320x180 +/videos/BorisHesser_2018S/video/64k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=481701,PROGRAM-ID=1,CODECS="avc1.42c015,mp4a.40.2",RESOLUTION=512x288 +/videos/BorisHesser_2018S/video/180k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=769968,PROGRAM-ID=1,CODECS="avc1.42c015,mp4a.40.2",RESOLUTION=512x288 +/videos/BorisHesser_2018S/video/320k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=984037,PROGRAM-ID=1,CODECS="avc1.42c015,mp4a.40.2",RESOLUTION=512x288 +/videos/BorisHesser_2018S/video/450k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=1693925,PROGRAM-ID=1,CODECS="avc1.4d401f,mp4a.40.2",RESOLUTION=853x480 +/videos/BorisHesser_2018S/video/950k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=2462469,PROGRAM-ID=1,CODECS="avc1.640028,mp4a.40.2",RESOLUTION=1280x720 +/videos/BorisHesser_2018S/video/1500k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=68101,PROGRAM-ID=1,CODECS="mp4a.40.2",DEFAULT=YES +/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b + +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=74298,PROGRAM-ID=1,CODECS="avc1.42c00c",RESOLUTION=320x180,URI="/videos/BorisHesser_2018S/video/64k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=216200,PROGRAM-ID=1,CODECS="avc1.42c015",RESOLUTION=512x288,URI="/videos/BorisHesser_2018S/video/180k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=304717,PROGRAM-ID=1,CODECS="avc1.42c015",RESOLUTION=512x288,URI="/videos/BorisHesser_2018S/video/320k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=350933,PROGRAM-ID=1,CODECS="avc1.42c015",RESOLUTION=512x288,URI="/videos/BorisHesser_2018S/video/450k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=495850,PROGRAM-ID=1,CODECS="avc1.42c01e",RESOLUTION=640x360,URI="/videos/BorisHesser_2018S/video/600k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=810750,PROGRAM-ID=1,CODECS="avc1.4d401f",RESOLUTION=853x480,URI="/videos/BorisHesser_2018S/video/950k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=1273700,PROGRAM-ID=1,CODECS="avc1.640028",RESOLUTION=1280x720,URI="/videos/BorisHesser_2018S/video/1500k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" + +#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="600k",LANGUAGE="en",NAME="Audio",AUTOSELECT=YES,DEFAULT=YES,URI="/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b",BANDWIDTH=614400 From 15870747f02effba9376fd1a1500c32d36d1b811 Mon Sep 17 00:00:00 2001 From: aviperes <avipr24@gmail.com> Date: Sun, 20 Jan 2019 10:15:01 +0200 Subject: [PATCH 462/558] [odnoklassniki] Detect paid videos --- youtube_dl/extractor/odnoklassniki.py | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/youtube_dl/extractor/odnoklassniki.py b/youtube_dl/extractor/odnoklassniki.py index 190d8af4d..114b93c07 100644 --- a/youtube_dl/extractor/odnoklassniki.py +++ b/youtube_dl/extractor/odnoklassniki.py @@ -115,6 +115,10 @@ class OdnoklassnikiIE(InfoExtractor): }, { 'url': 'https://m.ok.ru/dk?st.cmd=movieLayer&st.discId=863789452017&st.retLoc=friend&st.rtu=%2Fdk%3Fst.cmd%3DfriendMovies%26st.mode%3Down%26st.mrkId%3D%257B%2522uploadedMovieMarker%2522%253A%257B%2522marker%2522%253A%25221519410114503%2522%252C%2522hasMore%2522%253Atrue%257D%252C%2522sharedMovieMarker%2522%253A%257B%2522marker%2522%253Anull%252C%2522hasMore%2522%253Afalse%257D%257D%26st.friendId%3D561722190321%26st.frwd%3Don%26_prevCmd%3DfriendMovies%26tkn%3D7257&st.discType=MOVIE&st.mvId=863789452017&_prevCmd=friendMovies&tkn=3648#lst#', 'only_matching': True, + }, { + # Paid video + 'url': 'https://ok.ru/video/954886983203', + 'only_matching': True, }] def _real_extract(self, url): @@ -244,6 +248,11 @@ class OdnoklassnikiIE(InfoExtractor): 'ext': 'flv', }) + if not formats: + payment_info = metadata.get('paymentInfo') + if payment_info: + raise ExtractorError('This video is paid, subscribe to download it', expected=True) + self._sort_formats(formats) info['formats'] = formats From 31fbedc06a349bc555ab934588544f75734e3a55 Mon Sep 17 00:00:00 2001 From: jhwgh1968 <jhwgh1968@users.noreply.github.com> Date: Sun, 20 Jan 2019 09:10:46 +0000 Subject: [PATCH 463/558] [instagram] Add base extractor for playlists and tag extractor --- youtube_dl/extractor/extractors.py | 6 +- youtube_dl/extractor/instagram.py | 136 +++++++++++++++++++++-------- 2 files changed, 105 insertions(+), 37 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index de38c6641..24361def4 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -494,7 +494,11 @@ from .ina import InaIE from .inc import IncIE from .indavideo import IndavideoEmbedIE from .infoq import InfoQIE -from .instagram import InstagramIE, InstagramUserIE +from .instagram import ( + InstagramIE, + InstagramUserIE, + InstagramTagIE, +) from .internazionale import InternazionaleIE from .internetvideoarchive import InternetVideoArchiveIE from .iprima import IPrimaIE diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index 7e0e838f0..ffd87b55f 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -227,44 +227,37 @@ class InstagramIE(InfoExtractor): } -class InstagramUserIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P<id>[^/]{2,})/?(?:$|[?#])' - IE_DESC = 'Instagram user profile' - IE_NAME = 'instagram:user' - _TEST = { - 'url': 'https://instagram.com/porsche', - 'info_dict': { - 'id': 'porsche', - 'title': 'porsche', - }, - 'playlist_count': 5, - 'params': { - 'extract_flat': True, - 'skip_download': True, - 'playlistend': 5, - } - } +class InstagramPlaylistIE(InfoExtractor): + # A superclass for handling any kind of query based on GraphQL which + # results in a playlist. - _gis_tmpl = None + _gis_tmpl = None # used to cache GIS request type - def _entries(self, data): + def _parse_graphql(self, webpage, item_id): + # Reads a webpage and returns its GraphQL data. + return self._parse_json( + self._search_regex( + r'sharedData\s*=\s*({.+?})\s*;\s*[<\n]', webpage, 'data'), + item_id) + + def _extract_graphql(self, data, url): + # Parses GraphQL queries containing videos and generates a playlist. def get_count(suffix): return int_or_none(try_get( node, lambda x: x['edge_media_' + suffix]['count'])) - uploader_id = data['entry_data']['ProfilePage'][0]['graphql']['user']['id'] + uploader_id = self._match_id(url) csrf_token = data['config']['csrf_token'] rhx_gis = data.get('rhx_gis') or '3c7ca9dcefcf966d11dacf1f151335e8' - self._set_cookie('instagram.com', 'ig_pr', '1') - cursor = '' for page_num in itertools.count(1): - variables = json.dumps({ - 'id': uploader_id, + variables = { 'first': 12, 'after': cursor, - }) + } + variables.update(self._query_vars_for(data)) + variables = json.dumps(variables) if self._gis_tmpl: gis_tmpls = [self._gis_tmpl] @@ -276,21 +269,26 @@ class InstagramUserIE(InfoExtractor): '%s:%s:%s' % (rhx_gis, csrf_token, std_headers['User-Agent']), ] + # try all of the ways to generate a GIS query, and not only use the + # first one that works, but cache it for future requests for gis_tmpl in gis_tmpls: try: - media = self._download_json( + json_data = self._download_json( 'https://www.instagram.com/graphql/query/', uploader_id, 'Downloading JSON page %d' % page_num, headers={ 'X-Requested-With': 'XMLHttpRequest', 'X-Instagram-GIS': hashlib.md5( ('%s:%s' % (gis_tmpl, variables)).encode('utf-8')).hexdigest(), }, query={ - 'query_hash': '42323d64886122307be10013ad2dcc44', + 'query_hash': self._QUERY_HASH, 'variables': variables, - })['data']['user']['edge_owner_to_timeline_media'] + }) + media = self._parse_timeline_from(json_data) self._gis_tmpl = gis_tmpl break except ExtractorError as e: + # if it's an error caused by a bad query, and there are + # more GIS templates to try, ignore it and keep trying if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: if gis_tmpl != gis_tmpls[-1]: continue @@ -348,14 +346,80 @@ class InstagramUserIE(InfoExtractor): break def _real_extract(self, url): - username = self._match_id(url) + user_or_tag = self._match_id(url) + webpage = self._download_webpage(url, user_or_tag) + data = self._parse_graphql(webpage, user_or_tag) - webpage = self._download_webpage(url, username) - - data = self._parse_json( - self._search_regex( - r'sharedData\s*=\s*({.+?})\s*;\s*[<\n]', webpage, 'data'), - username) + self._set_cookie('instagram.com', 'ig_pr', '1') return self.playlist_result( - self._entries(data), username, username) + self._extract_graphql(data, url), user_or_tag, user_or_tag) + + +class InstagramUserIE(InstagramPlaylistIE): + _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P<id>[^/]{2,})/?(?:$|[?#])' + IE_DESC = 'Instagram user profile' + IE_NAME = 'instagram:user' + _TEST = { + 'url': 'https://instagram.com/porsche', + 'info_dict': { + 'id': 'porsche', + 'title': 'porsche', + }, + 'playlist_count': 5, + 'params': { + 'extract_flat': True, + 'skip_download': True, + 'playlistend': 5, + } + } + + _QUERY_HASH = '42323d64886122307be10013ad2dcc44', + + @staticmethod + def _parse_timeline_from(data): + # extracts the media timeline data from a GraphQL result + return data['data']['user']['edge_owner_to_timeline_media'] + + @staticmethod + def _query_vars_for(data): + # returns a dictionary of variables to add to the timeline query based + # on the GraphQL of the original page + return { + 'id': data['entry_data']['ProfilePage'][0]['graphql']['user']['id'] + } + + +class InstagramTagIE(InstagramPlaylistIE): + _VALID_URL = r'https?://(?:www\.)?instagram\.com/explore/tags/(?P<id>[^/]+)' + IE_DESC = 'Instagram hashtag search' + IE_NAME = 'instagram:tag' + _TEST = { + 'url': 'https://instagram.com/explore/tags/lolcats', + 'info_dict': { + 'id': 'lolcats', + 'title': 'lolcats', + }, + 'playlist_count': 50, + 'params': { + 'extract_flat': True, + 'skip_download': True, + 'playlistend': 50, + } + } + + _QUERY_HASH = 'f92f56d47dc7a55b606908374b43a314', + + @staticmethod + def _parse_timeline_from(data): + # extracts the media timeline data from a GraphQL result + return data['data']['hashtag']['edge_hashtag_to_media'] + + @staticmethod + def _query_vars_for(data): + # returns a dictionary of variables to add to the timeline query based + # on the GraphQL of the original page + return { + 'tag_name': + data['entry_data']['TagPage'][0]['graphql']['hashtag']['name'] + } From 6ca3fa898cd066422daea3d5be53efdae22187d8 Mon Sep 17 00:00:00 2001 From: yonaikerlol <lawlietrs7@gmail.com> Date: Sun, 20 Jan 2019 05:24:21 -0400 Subject: [PATCH 464/558] [streamango] Add support for fruithosts.net --- youtube_dl/extractor/streamango.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/streamango.py b/youtube_dl/extractor/streamango.py index fcaa5ac0b..efb259f96 100644 --- a/youtube_dl/extractor/streamango.py +++ b/youtube_dl/extractor/streamango.py @@ -14,7 +14,7 @@ from ..utils import ( class StreamangoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?streamango\.com/(?:f|embed)/(?P<id>[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?(?:streamango\.com|fruithosts\.net)/(?:f|embed)/(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'https://streamango.com/f/clapasobsptpkdfe/20170315_150006_mp4', 'md5': 'e992787515a182f55e38fc97588d802a', @@ -38,6 +38,9 @@ class StreamangoIE(InfoExtractor): }, { 'url': 'https://streamango.com/embed/clapasobsptpkdfe/20170315_150006_mp4', 'only_matching': True, + }, { + 'url': 'https://fruithosts.net/f/mreodparcdcmspsm/w1f1_r4lph_2018_brrs_720p_latino_mp4', + 'only_matching': True, }] def _real_extract(self, url): From 289ef490f77cb35c43d98b9d2ea4cf529c24895e Mon Sep 17 00:00:00 2001 From: Anthony Fok <foka@debian.org> Date: Sun, 30 Dec 2018 02:44:40 -0700 Subject: [PATCH 465/558] [hketv] Add extractor --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/hketv.py | 185 +++++++++++++++++++++++++++++ 2 files changed, 186 insertions(+) create mode 100644 youtube_dl/extractor/hketv.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 24361def4..574a47e6d 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -452,6 +452,7 @@ from .hellporno import HellPornoIE from .helsinki import HelsinkiIE from .hentaistigma import HentaiStigmaIE from .hgtv import HGTVComShowIE +from .hketv import HKETVIE from .hidive import HiDiveIE from .historicfilms import HistoricFilmsIE from .hitbox import HitboxIE, HitboxLiveIE diff --git a/youtube_dl/extractor/hketv.py b/youtube_dl/extractor/hketv.py new file mode 100644 index 000000000..b5790cdee --- /dev/null +++ b/youtube_dl/extractor/hketv.py @@ -0,0 +1,185 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + clean_html, + ExtractorError, + int_or_none, + merge_dicts, + str_or_none, + str_to_int, + try_get, + unified_strdate, + urlencode_postdata, + urljoin, +) + + +class HKETVIE(InfoExtractor): + IE_NAME = 'hketv' + IE_DESC = '香港教育局教育電視 (HKETV) Educational Television, Hong Kong Educational Bureau' + _GEO_BYPASS = False + _GEO_COUNTRIES = ['HK'] + _VALID_URL = r'https?://(?:www\.)?hkedcity\.net/etv/resource/(?P<id>[0-9]+)' + _TESTS = [{ + 'url': 'https://www.hkedcity.net/etv/resource/2932360618', + 'md5': 'f193712f5f7abb208ddef3c5ea6ed0b7', + 'info_dict': { + 'id': '2932360618', + 'ext': 'mp4', + 'title': '喜閱一生(共享閱讀樂) (中、英文字幕可供選擇)', + 'description': '本節目輯錄了「閱讀滿Fun嘉年華」和「二○一八響應世界閱讀日――悅愛閱讀・愈讀愈愛」的活動花絮,並由學者、作家、演藝界人士等,分享培養子女閱讀興趣和習慣的方法,以及呼籲大家一同分享閱讀的樂趣。', + 'upload_date': '20181024', + 'duration': 900, + 'subtitles': { + 'en': [{ + 'url': 'https://apps.hkedcity.net/media/mediaplayer/caption.php?f=74395&lang=en', + 'ext': 'srt', + }], + 'zh-Hant': [{ + 'url': 'https://apps.hkedcity.net/media/mediaplayer/caption.php?f=74395&lang=qmt', + 'ext': 'srt', + }], + } + }, + }, { + 'url': 'https://www.hkedcity.net/etv/resource/972641418', + 'md5': '1ed494c1c6cf7866a8290edad9b07dc9', + 'info_dict': { + 'id': '972641418', + 'ext': 'mp4', + 'title': '衣冠楚楚 (天使系列之一)', + 'description': '天國仙境,有兩位可愛的天使小姐妹。她們對幾千年來天使衣著一成不變頗有不滿。她們下望人世間:只見人們穿著七彩繽紛、款式各異的服裝,漂亮極了。天使姐妹決定下凡考察衣著,以設計天使新裝。 下到人間,姐妹試穿各式各樣的衣著,引發連串奇特有趣的情節:她們穿著校服在街上閒逛時,被女警誤認為逃學而送回學校,到校後又被體育老師誤認為是新同學,匆匆忙忙換上運動服後在操場上大顯神通。她們穿著護士服在醫院散步時,又被誤認為當班護士,而投入追尋失蹤病童、治病救人的工作中去。姐妹倆還到過玩具店,與布娃娃們談論衣著。她們也去過服裝設計學校,被當成小模特兒而試穿各式服裝。最令姐妹倆興奮的是一場盛大的民族服裝表演會。身穿盛裝的十二個民族的少女在台上翩翩起舞,各種服飾七彩繽紛、美不勝收。姐妹們情不自禁地穿上民族服裝,小天使變成了少數民族姑娘……最後天使姐妹回到天上,對於天使究竟穿甚麼樣的衣服好,她們還是拿不定主意。 節目通過天使姐妹的奇特經歷,反復示範各式衣服鞋襪的正確讀音及談論衣著時的常用句式,並以盛大的民族服裝表演活動,帶出有關服裝的文化知識。內容豐富而饒有趣味。', + 'upload_date': '20070109', + 'duration': 907, + 'subtitles': {}, + }, + }] + + _CC_LANGS = { + '中文(繁體中文)': 'zh-Hant', + '中文(简体中文)': 'zh-Hans', + 'English': 'en', + 'Bahasa Indonesia': 'id', + '\u0939\u093f\u0928\u094d\u0926\u0940': 'hi', + '\u0928\u0947\u092a\u093e\u0932\u0940': 'ne', + 'Tagalog': 'tl', + '\u0e44\u0e17\u0e22': 'th', + '\u0627\u0631\u062f\u0648': 'ur', + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + title = self._html_search_meta('ed_title', webpage, fatal=True) + + file_id = self._html_search_regex(r'post_var\["file_id"\]\s*=\s*(.+?);', webpage, 'file ID') + curr_url = self._html_search_regex(r'post_var\["curr_url"\]\s*=\s*"(.+?)";', webpage, 'curr URL') + data = { + 'action': 'get_info', + 'curr_url': curr_url, + 'file_id': file_id, + 'video_url': file_id, + } + _APPS_BASE_URL = 'https://apps.hkedcity.net' + handler_url = _APPS_BASE_URL + '/media/play/handler.php' + + response = self._download_json( + handler_url, video_id, + data=urlencode_postdata(data), + headers=merge_dicts({'Content-Type': 'application/x-www-form-urlencoded'}, + self.geo_verification_headers())) + + result = response['result'] + + formats = [] + subtitles = {} + + if response.get('success') and response.get('access'): + width = int_or_none(result.get('width')) + height = int_or_none(result.get('height')) + + playlist0 = try_get(result, lambda x: x['playlist'][0], dict) + fmts = playlist0.get('sources') + for fmt in fmts: + file_path = fmt.get('file') + if file_path: + file_url = urljoin(_APPS_BASE_URL, file_path) + # If we ever wanted to provide the final resolved URL that + # does not require cookies, albeit with a shorter lifespan: + # urlh = self._downloader.urlopen(file_url) + # resolved_url = urlh.geturl() + + label = fmt.get('label') + w = None + h = None + if label == 'HD': + h = 720 + elif label == 'SD': + h = 360 + if h: + if width and height: + w = h * width // height + else: + w = h * 4 // 3 + + formats.append({ + 'format_id': label, + 'ext': fmt.get('type'), + 'url': file_url, + 'width': w, + 'height': h, + }) + + tracks = playlist0.get('tracks', []) + for track in tracks: + if not isinstance(track, dict): + continue + track_kind = str_or_none(track.get('kind')) + if not track_kind or not isinstance(track_kind, compat_str): + continue + if track_kind.lower() not in ('captions', 'subtitles'): + continue + track_url = urljoin(_APPS_BASE_URL, track.get('file')) + if not track_url: + continue + track_label = track.get('label') + subtitles.setdefault(self._CC_LANGS.get(track_label, track_label), []).append({ + 'url': self._proto_relative_url(track_url), + 'ext': 'srt', + }) + + else: + error = clean_html(response.get('access_err_msg')) + if 'Video streaming is not available in your country' in error: + self.raise_geo_restricted(msg=error, countries=self._GEO_COUNTRIES) + else: + raise ExtractorError(error) + + # Likes + emotion = self._download_json( + 'https://emocounter.hkedcity.net/handler.php', + video_id, + data=urlencode_postdata({ + 'action': 'get_emotion', + 'data[bucket_id]': 'etv', + 'data[identifier]': video_id, + }), + headers={'Content-Type': 'application/x-www-form-urlencoded'}, + fatal=False) + like_count = int_or_none(try_get(emotion, lambda x: x['data']['emotion_data'][0]['count'])) + + return { + 'id': video_id, + 'title': title, + 'description': self._html_search_meta('description', webpage, fatal=False), + 'upload_date': unified_strdate(self._html_search_meta('ed_date', webpage, fatal=False), day_first=False), + 'duration': int_or_none(result.get('length')), + 'formats': formats, + 'subtitles': subtitles, + 'thumbnail': urljoin(_APPS_BASE_URL, result.get('image')), + 'view_count': str_to_int(result.get('view_count')), + 'like_count': like_count, + } From 73c19aaa9f74e9383a7aaf0dfb3c608727d5b6b2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 20 Jan 2019 17:42:25 +0700 Subject: [PATCH 466/558] [hketv] Improve and simplify (closes #18696) --- youtube_dl/extractor/hketv.py | 180 ++++++++++++++++++---------------- 1 file changed, 93 insertions(+), 87 deletions(-) diff --git a/youtube_dl/extractor/hketv.py b/youtube_dl/extractor/hketv.py index b5790cdee..b57927fc1 100644 --- a/youtube_dl/extractor/hketv.py +++ b/youtube_dl/extractor/hketv.py @@ -8,8 +8,8 @@ from ..utils import ( ExtractorError, int_or_none, merge_dicts, + parse_count, str_or_none, - str_to_int, try_get, unified_strdate, urlencode_postdata, @@ -30,20 +30,12 @@ class HKETVIE(InfoExtractor): 'id': '2932360618', 'ext': 'mp4', 'title': '喜閱一生(共享閱讀樂) (中、英文字幕可供選擇)', - 'description': '本節目輯錄了「閱讀滿Fun嘉年華」和「二○一八響應世界閱讀日――悅愛閱讀・愈讀愈愛」的活動花絮,並由學者、作家、演藝界人士等,分享培養子女閱讀興趣和習慣的方法,以及呼籲大家一同分享閱讀的樂趣。', + 'description': 'md5:d5286d05219ef50e0613311cbe96e560', 'upload_date': '20181024', 'duration': 900, - 'subtitles': { - 'en': [{ - 'url': 'https://apps.hkedcity.net/media/mediaplayer/caption.php?f=74395&lang=en', - 'ext': 'srt', - }], - 'zh-Hant': [{ - 'url': 'https://apps.hkedcity.net/media/mediaplayer/caption.php?f=74395&lang=qmt', - 'ext': 'srt', - }], - } + 'subtitles': 'count:2', }, + 'skip': 'Geo restricted to HK', }, { 'url': 'https://www.hkedcity.net/etv/resource/972641418', 'md5': '1ed494c1c6cf7866a8290edad9b07dc9', @@ -51,11 +43,15 @@ class HKETVIE(InfoExtractor): 'id': '972641418', 'ext': 'mp4', 'title': '衣冠楚楚 (天使系列之一)', - 'description': '天國仙境,有兩位可愛的天使小姐妹。她們對幾千年來天使衣著一成不變頗有不滿。她們下望人世間:只見人們穿著七彩繽紛、款式各異的服裝,漂亮極了。天使姐妹決定下凡考察衣著,以設計天使新裝。 下到人間,姐妹試穿各式各樣的衣著,引發連串奇特有趣的情節:她們穿著校服在街上閒逛時,被女警誤認為逃學而送回學校,到校後又被體育老師誤認為是新同學,匆匆忙忙換上運動服後在操場上大顯神通。她們穿著護士服在醫院散步時,又被誤認為當班護士,而投入追尋失蹤病童、治病救人的工作中去。姐妹倆還到過玩具店,與布娃娃們談論衣著。她們也去過服裝設計學校,被當成小模特兒而試穿各式服裝。最令姐妹倆興奮的是一場盛大的民族服裝表演會。身穿盛裝的十二個民族的少女在台上翩翩起舞,各種服飾七彩繽紛、美不勝收。姐妹們情不自禁地穿上民族服裝,小天使變成了少數民族姑娘……最後天使姐妹回到天上,對於天使究竟穿甚麼樣的衣服好,她們還是拿不定主意。 節目通過天使姐妹的奇特經歷,反復示範各式衣服鞋襪的正確讀音及談論衣著時的常用句式,並以盛大的民族服裝表演活動,帶出有關服裝的文化知識。內容豐富而饒有趣味。', + 'description': 'md5:10bb3d659421e74f58e5db5691627b0f', 'upload_date': '20070109', 'duration': 907, 'subtitles': {}, }, + 'params': { + 'geo_verification_proxy': '<HK proxy here>', + }, + 'skip': 'Geo restricted to HK', }] _CC_LANGS = { @@ -69,117 +65,127 @@ class HKETVIE(InfoExtractor): '\u0e44\u0e17\u0e22': 'th', '\u0627\u0631\u062f\u0648': 'ur', } + _FORMAT_HEIGHTS = { + 'SD': 360, + 'HD': 720, + } + _APPS_BASE_URL = 'https://apps.hkedcity.net' def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - title = self._html_search_meta('ed_title', webpage, fatal=True) - file_id = self._html_search_regex(r'post_var\["file_id"\]\s*=\s*(.+?);', webpage, 'file ID') - curr_url = self._html_search_regex(r'post_var\["curr_url"\]\s*=\s*"(.+?)";', webpage, 'curr URL') + title = ( + self._html_search_meta( + ('ed_title', 'search.ed_title'), webpage, default=None) or + self._search_regex( + r'data-favorite_title_(?:eng|chi)=(["\'])(?P<id>(?:(?!\1).)+)\1', + webpage, 'title', default=None, group='url') or + self._html_search_regex( + r'<h1>([^<]+)</h1>', webpage, 'title', default=None) or + self._og_search_title(webpage) + ) + + file_id = self._search_regex( + r'post_var\[["\']file_id["\']\s*\]\s*=\s*(.+?);', + webpage, 'file ID') + curr_url = self._search_regex( + r'post_var\[["\']curr_url["\']\s*\]\s*=\s*"(.+?)";', + webpage, 'curr URL') data = { 'action': 'get_info', 'curr_url': curr_url, 'file_id': file_id, 'video_url': file_id, } - _APPS_BASE_URL = 'https://apps.hkedcity.net' - handler_url = _APPS_BASE_URL + '/media/play/handler.php' response = self._download_json( - handler_url, video_id, + self._APPS_BASE_URL + '/media/play/handler.php', video_id, data=urlencode_postdata(data), - headers=merge_dicts({'Content-Type': 'application/x-www-form-urlencoded'}, - self.geo_verification_headers())) + headers=merge_dicts({ + 'Content-Type': 'application/x-www-form-urlencoded'}, + self.geo_verification_headers())) result = response['result'] + if not response.get('success') or not response.get('access'): + error = clean_html(response.get('access_err_msg')) + if 'Video streaming is not available in your country' in error: + self.raise_geo_restricted( + msg=error, countries=self._GEO_COUNTRIES) + else: + raise ExtractorError(error, expected=True) + formats = [] + + width = int_or_none(result.get('width')) + height = int_or_none(result.get('height')) + + playlist0 = result['playlist'][0] + for fmt in playlist0['sources']: + file_url = urljoin(self._APPS_BASE_URL, fmt.get('file')) + if not file_url: + continue + # If we ever wanted to provide the final resolved URL that + # does not require cookies, albeit with a shorter lifespan: + # urlh = self._downloader.urlopen(file_url) + # resolved_url = urlh.geturl() + label = fmt.get('label') + h = self._FORMAT_HEIGHTS.get(label) + w = h * width // height if h and width and height else None + formats.append({ + 'format_id': label, + 'ext': fmt.get('type'), + 'url': file_url, + 'width': w, + 'height': h, + }) + self._sort_formats(formats) + subtitles = {} - - if response.get('success') and response.get('access'): - width = int_or_none(result.get('width')) - height = int_or_none(result.get('height')) - - playlist0 = try_get(result, lambda x: x['playlist'][0], dict) - fmts = playlist0.get('sources') - for fmt in fmts: - file_path = fmt.get('file') - if file_path: - file_url = urljoin(_APPS_BASE_URL, file_path) - # If we ever wanted to provide the final resolved URL that - # does not require cookies, albeit with a shorter lifespan: - # urlh = self._downloader.urlopen(file_url) - # resolved_url = urlh.geturl() - - label = fmt.get('label') - w = None - h = None - if label == 'HD': - h = 720 - elif label == 'SD': - h = 360 - if h: - if width and height: - w = h * width // height - else: - w = h * 4 // 3 - - formats.append({ - 'format_id': label, - 'ext': fmt.get('type'), - 'url': file_url, - 'width': w, - 'height': h, - }) - - tracks = playlist0.get('tracks', []) - for track in tracks: - if not isinstance(track, dict): - continue - track_kind = str_or_none(track.get('kind')) - if not track_kind or not isinstance(track_kind, compat_str): - continue - if track_kind.lower() not in ('captions', 'subtitles'): - continue - track_url = urljoin(_APPS_BASE_URL, track.get('file')) - if not track_url: - continue - track_label = track.get('label') - subtitles.setdefault(self._CC_LANGS.get(track_label, track_label), []).append({ + tracks = try_get(playlist0, lambda x: x['tracks'], list) or [] + for track in tracks: + if not isinstance(track, dict): + continue + track_kind = str_or_none(track.get('kind')) + if not track_kind or not isinstance(track_kind, compat_str): + continue + if track_kind.lower() not in ('captions', 'subtitles'): + continue + track_url = urljoin(self._APPS_BASE_URL, track.get('file')) + if not track_url: + continue + track_label = track.get('label') + subtitles.setdefault(self._CC_LANGS.get( + track_label, track_label), []).append({ 'url': self._proto_relative_url(track_url), 'ext': 'srt', }) - else: - error = clean_html(response.get('access_err_msg')) - if 'Video streaming is not available in your country' in error: - self.raise_geo_restricted(msg=error, countries=self._GEO_COUNTRIES) - else: - raise ExtractorError(error) - # Likes emotion = self._download_json( - 'https://emocounter.hkedcity.net/handler.php', - video_id, + 'https://emocounter.hkedcity.net/handler.php', video_id, data=urlencode_postdata({ 'action': 'get_emotion', 'data[bucket_id]': 'etv', 'data[identifier]': video_id, }), headers={'Content-Type': 'application/x-www-form-urlencoded'}, - fatal=False) - like_count = int_or_none(try_get(emotion, lambda x: x['data']['emotion_data'][0]['count'])) + fatal=False) or {} + like_count = int_or_none(try_get( + emotion, lambda x: x['data']['emotion_data'][0]['count'])) return { 'id': video_id, 'title': title, - 'description': self._html_search_meta('description', webpage, fatal=False), - 'upload_date': unified_strdate(self._html_search_meta('ed_date', webpage, fatal=False), day_first=False), + 'description': self._html_search_meta( + 'description', webpage, fatal=False), + 'upload_date': unified_strdate(self._html_search_meta( + 'ed_date', webpage, fatal=False), day_first=False), 'duration': int_or_none(result.get('length')), 'formats': formats, 'subtitles': subtitles, - 'thumbnail': urljoin(_APPS_BASE_URL, result.get('image')), - 'view_count': str_to_int(result.get('view_count')), + 'thumbnail': urljoin(self._APPS_BASE_URL, result.get('image')), + 'view_count': parse_count(result.get('view_count')), 'like_count': like_count, } From a1a460759815414c6194bc921ac77a5533b6e02e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 20 Jan 2019 18:21:31 +0700 Subject: [PATCH 467/558] [vimeo] Fix video password verification for videos protected by Referer HTTP header --- youtube_dl/extractor/vimeo.py | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index fd37f919b..6215b3258 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -435,6 +435,8 @@ class VimeoIE(VimeoBaseInfoExtractor): 'url': 'https://vimeo.com/160743502/abd0e13fb4', 'only_matching': True, } + # https://gettingthingsdone.com/workflowmap/ + # vimeo embed with check-password page protected by Referer header ] @staticmethod @@ -465,20 +467,22 @@ class VimeoIE(VimeoBaseInfoExtractor): urls = VimeoIE._extract_urls(url, webpage) return urls[0] if urls else None - def _verify_player_video_password(self, url, video_id): + def _verify_player_video_password(self, url, video_id, headers): password = self._downloader.params.get('videopassword') if password is None: raise ExtractorError('This video is protected by a password, use the --video-password option') data = urlencode_postdata({ 'password': base64.b64encode(password.encode()), }) - pass_url = url + '/check-password' - password_request = sanitized_Request(pass_url, data) - password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') - password_request.add_header('Referer', url) - return self._download_json( - password_request, video_id, - 'Verifying the password', 'Wrong password') + headers = merge_dicts(headers, { + 'Content-Type': 'application/x-www-form-urlencoded', + }) + checked = self._download_json( + url + '/check-password', video_id, + 'Verifying the password', data=data, headers=headers) + if checked is False: + raise ExtractorError('Wrong video password', expected=True) + return checked def _real_initialize(self): self._login() @@ -591,7 +595,7 @@ class VimeoIE(VimeoBaseInfoExtractor): cause=e) else: if config.get('view') == 4: - config = self._verify_player_video_password(redirect_url, video_id) + config = self._verify_player_video_password(redirect_url, video_id, headers) vod = config.get('video', {}).get('vod', {}) From 29cfcb43da8ac60e6c2eddad095a41c800d4d95a Mon Sep 17 00:00:00 2001 From: Alexandre Huot <alexandre.huot@usherbrooke.ca> Date: Sun, 20 Jan 2019 06:33:09 -0500 Subject: [PATCH 468/558] [radiocanada] Relax DRM check --- youtube_dl/extractor/radiocanada.py | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/radiocanada.py b/youtube_dl/extractor/radiocanada.py index b952e59b4..302f67d96 100644 --- a/youtube_dl/extractor/radiocanada.py +++ b/youtube_dl/extractor/radiocanada.py @@ -49,6 +49,16 @@ class RadioCanadaIE(InfoExtractor): # m3u8 download 'skip_download': True, }, + }, + { + # with protectionType but not actually DRM protected + 'url': 'radiocanada:toutv:140872', + 'info_dict': { + 'id': '140872', + 'title': 'Épisode 1', + 'series': 'District 31', + }, + 'only_matching': True, } ] @@ -67,8 +77,10 @@ class RadioCanadaIE(InfoExtractor): el = find_xpath_attr(metadata, './/Meta', 'name', name) return el.text if el is not None else None + # protectionType does not necessarily mean the video is DRM protected (see + # https://github.com/rg3/youtube-dl/pull/18609). if get_meta('protectionType'): - raise ExtractorError('This video is DRM protected.', expected=True) + self.report_warning('This video is probably DRM protected.') device_types = ['ipad'] if not smuggled_data: From 6945b9e78f38284eb4e440b7badea2fc60b66c2f Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 20 Jan 2019 13:31:41 +0100 Subject: [PATCH 469/558] [extractor/common] improve jwplayer relative url handling(closes #18892) --- youtube_dl/extractor/common.py | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 6e36e6778..95456b291 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -2630,7 +2630,7 @@ class InfoExtractor(object): 'id': this_video_id, 'title': unescapeHTML(video_data['title'] if require_title else video_data.get('title')), 'description': video_data.get('description'), - 'thumbnail': self._proto_relative_url(video_data.get('image')), + 'thumbnail': urljoin(base_url, self._proto_relative_url(video_data.get('image'))), 'timestamp': int_or_none(video_data.get('pubdate')), 'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')), 'subtitles': subtitles, @@ -2657,12 +2657,9 @@ class InfoExtractor(object): for source in jwplayer_sources_data: if not isinstance(source, dict): continue - source_url = self._proto_relative_url(source.get('file')) - if not source_url: - continue - if base_url: - source_url = compat_urlparse.urljoin(base_url, source_url) - if source_url in urls: + source_url = urljoin( + base_url, self._proto_relative_url(source.get('file'))) + if not source_url or source_url in urls: continue urls.append(source_url) source_type = source.get('type') or '' From fad4ceb53404227f471af2f3544c4c14a5df4acb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 20 Jan 2019 20:21:24 +0700 Subject: [PATCH 470/558] [utils] Fix urljoin for paths with non-http(s) schemes --- test/test_utils.py | 2 ++ youtube_dl/utils.py | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/test/test_utils.py b/test/test_utils.py index 9e28e008f..409482c3b 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -507,6 +507,8 @@ class TestUtil(unittest.TestCase): self.assertEqual(urljoin('http://foo.de/', ''), None) self.assertEqual(urljoin('http://foo.de/', ['foobar']), None) self.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt') + self.assertEqual(urljoin('http://foo.de/a/b/c.txt', 'rtmp://foo.de'), 'rtmp://foo.de') + self.assertEqual(urljoin(None, 'rtmp://foo.de'), 'rtmp://foo.de') def test_url_or_none(self): self.assertEqual(url_or_none(None), None) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index d2d3c1a9f..d0cb65814 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1868,7 +1868,7 @@ def urljoin(base, path): path = path.decode('utf-8') if not isinstance(path, compat_str) or not path: return None - if re.match(r'^(?:https?:)?//', path): + if re.match(r'^(?:[a-zA-Z][a-zA-Z0-9+-.]*:)?//', path): return path if isinstance(base, bytes): base = base.decode('utf-8') From 07f9febc4b86a9cd819329f3a7daafdbe9455f40 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 20 Jan 2019 22:07:01 +0700 Subject: [PATCH 471/558] [tnaflix] Pass Referer in metadata request (closes #18925) --- youtube_dl/extractor/tnaflix.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/tnaflix.py b/youtube_dl/extractor/tnaflix.py index 6798ef4c3..b3573c6e0 100644 --- a/youtube_dl/extractor/tnaflix.py +++ b/youtube_dl/extractor/tnaflix.py @@ -96,7 +96,7 @@ class TNAFlixNetworkBaseIE(InfoExtractor): cfg_xml = self._download_xml( cfg_url, display_id, 'Downloading metadata', - transform_source=fix_xml_ampersands) + transform_source=fix_xml_ampersands, headers={'Referer': url}) formats = [] From 19d6991312405f5af108af28b3721966720fc72d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 22 Jan 2019 03:03:53 +0700 Subject: [PATCH 472/558] [videomore] Improve extraction and fix season extractor (closes #18908) --- youtube_dl/extractor/videomore.py | 96 ++++++++++++++++++++++++++++--- 1 file changed, 88 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/videomore.py b/youtube_dl/extractor/videomore.py index 9b56630de..e3eda3327 100644 --- a/youtube_dl/extractor/videomore.py +++ b/youtube_dl/extractor/videomore.py @@ -4,8 +4,14 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( int_or_none, + orderedSet, + parse_duration, + str_or_none, + unified_strdate, + url_or_none, xpath_element, xpath_text, ) @@ -13,7 +19,19 @@ from ..utils import ( class VideomoreIE(InfoExtractor): IE_NAME = 'videomore' - _VALID_URL = r'videomore:(?P<sid>\d+)$|https?://videomore\.ru/(?:(?:embed|[^/]+/[^/]+)/|[^/]+\?.*\btrack_id=)(?P<id>\d+)(?:[/?#&]|\.(?:xml|json)|$)' + _VALID_URL = r'''(?x) + videomore:(?P<sid>\d+)$| + https?://(?:player\.)?videomore\.ru/ + (?: + (?: + embed| + [^/]+/[^/]+ + )/| + [^/]*\?.*?\btrack_id= + ) + (?P<id>\d+) + (?:[/?#&]|\.(?:xml|json)|$) + ''' _TESTS = [{ 'url': 'http://videomore.ru/kino_v_detalayah/5_sezon/367617', 'md5': '44455a346edc0d509ac5b5a5b531dc35', @@ -79,6 +97,9 @@ class VideomoreIE(InfoExtractor): }, { 'url': 'videomore:367617', 'only_matching': True, + }, { + 'url': 'https://player.videomore.ru/?partner_id=97&track_id=736234&autoplay=0&userToken=', + 'only_matching': True, }] @staticmethod @@ -136,7 +157,7 @@ class VideomoreIE(InfoExtractor): class VideomoreVideoIE(InfoExtractor): IE_NAME = 'videomore:video' - _VALID_URL = r'https?://videomore\.ru/(?:(?:[^/]+/){2})?(?P<id>[^/?#&]+)[/?#&]*$' + _VALID_URL = r'https?://videomore\.ru/(?:(?:[^/]+/){2})?(?P<id>[^/?#&]+)(?:/*|[?#&].*?)$' _TESTS = [{ # single video with og:video:iframe 'url': 'http://videomore.ru/elki_3', @@ -176,6 +197,9 @@ class VideomoreVideoIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + 'url': 'https://videomore.ru/molodezhka/6_sezon/29_seriya?utm_so', + 'only_matching': True, }] @classmethod @@ -196,13 +220,16 @@ class VideomoreVideoIE(InfoExtractor): r'track-id=["\'](\d+)', r'xcnt_product_id\s*=\s*(\d+)'), webpage, 'video id') video_url = 'videomore:%s' % video_id + else: + video_id = None - return self.url_result(video_url, VideomoreIE.ie_key()) + return self.url_result( + video_url, ie=VideomoreIE.ie_key(), video_id=video_id) class VideomoreSeasonIE(InfoExtractor): IE_NAME = 'videomore:season' - _VALID_URL = r'https?://videomore\.ru/(?!embed)(?P<id>[^/]+/[^/?#&]+)[/?#&]*$' + _VALID_URL = r'https?://videomore\.ru/(?!embed)(?P<id>[^/]+/[^/?#&]+)(?:/*|[?#&].*?)$' _TESTS = [{ 'url': 'http://videomore.ru/molodezhka/sezon_promo', 'info_dict': { @@ -210,8 +237,16 @@ class VideomoreSeasonIE(InfoExtractor): 'title': 'Молодежка Промо', }, 'playlist_mincount': 12, + }, { + 'url': 'http://videomore.ru/molodezhka/sezon_promo?utm_so', + 'only_matching': True, }] + @classmethod + def suitable(cls, url): + return (False if (VideomoreIE.suitable(url) or VideomoreVideoIE.suitable(url)) + else super(VideomoreSeasonIE, cls).suitable(url)) + def _real_extract(self, url): display_id = self._match_id(url) @@ -219,9 +254,54 @@ class VideomoreSeasonIE(InfoExtractor): title = self._og_search_title(webpage) - entries = [ - self.url_result(item) for item in re.findall( - r'<a[^>]+href="((?:https?:)?//videomore\.ru/%s/[^/]+)"[^>]+class="widget-item-desc"' - % display_id, webpage)] + data = self._parse_json( + self._html_search_regex( + r'\bclass=["\']seasons-tracks["\'][^>]+\bdata-custom-data=(["\'])(?P<value>{.+?})\1', + webpage, 'data', default='{}', group='value'), + display_id, fatal=False) + + entries = [] + + if data: + episodes = data.get('episodes') + if isinstance(episodes, list): + for ep in episodes: + if not isinstance(ep, dict): + continue + ep_id = int_or_none(ep.get('id')) + ep_url = url_or_none(ep.get('url')) + if ep_id: + e = { + 'url': 'videomore:%s' % ep_id, + 'id': compat_str(ep_id), + } + elif ep_url: + e = {'url': ep_url} + else: + continue + e.update({ + '_type': 'url', + 'ie_key': VideomoreIE.ie_key(), + 'title': str_or_none(ep.get('title')), + 'thumbnail': url_or_none(ep.get('image')), + 'duration': parse_duration(ep.get('duration')), + 'episode_number': int_or_none(ep.get('number')), + 'upload_date': unified_strdate(ep.get('date')), + }) + entries.append(e) + + if not entries: + entries = [ + self.url_result( + 'videomore:%s' % video_id, ie=VideomoreIE.ie_key(), + video_id=video_id) + for video_id in orderedSet(re.findall( + r':(?:id|key)=["\'](\d+)["\']', webpage))] + + if not entries: + entries = [ + self.url_result(item) for item in re.findall( + r'<a[^>]+href="((?:https?:)?//videomore\.ru/%s/[^/]+)"[^>]+class="widget-item-desc"' + % display_id, webpage)] return self.playlist_result(entries, display_id, title) From 4b85f0f9db9329ef1774a66c3e2fd4da558a5201 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 22 Jan 2019 14:38:29 +0100 Subject: [PATCH 473/558] [vrv] add support for authentication(closes #14307) --- youtube_dl/extractor/vrv.py | 95 ++++++++++++++++++++++--------------- 1 file changed, 56 insertions(+), 39 deletions(-) diff --git a/youtube_dl/extractor/vrv.py b/youtube_dl/extractor/vrv.py index 483a3be3a..014513051 100644 --- a/youtube_dl/extractor/vrv.py +++ b/youtube_dl/extractor/vrv.py @@ -11,10 +11,12 @@ import time from .common import InfoExtractor from ..compat import ( + compat_HTTPError, compat_urllib_parse_urlencode, compat_urllib_parse, ) from ..utils import ( + ExtractorError, float_or_none, int_or_none, ) @@ -24,29 +26,41 @@ class VRVBaseIE(InfoExtractor): _API_DOMAIN = None _API_PARAMS = {} _CMS_SIGNING = {} + _TOKEN = None + _TOKEN_SECRET = '' def _call_api(self, path, video_id, note, data=None): + # https://tools.ietf.org/html/rfc5849#section-3 base_url = self._API_DOMAIN + '/core/' + path - encoded_query = compat_urllib_parse_urlencode({ + query = { 'oauth_consumer_key': self._API_PARAMS['oAuthKey'], 'oauth_nonce': ''.join([random.choice(string.ascii_letters) for _ in range(32)]), 'oauth_signature_method': 'HMAC-SHA1', 'oauth_timestamp': int(time.time()), - 'oauth_version': '1.0', - }) + } + if self._TOKEN: + query['oauth_token'] = self._TOKEN + encoded_query = compat_urllib_parse_urlencode(query) headers = self.geo_verification_headers() if data: data = json.dumps(data).encode() headers['Content-Type'] = 'application/json' - method = 'POST' if data else 'GET' - base_string = '&'.join([method, compat_urllib_parse.quote(base_url, ''), compat_urllib_parse.quote(encoded_query, '')]) + base_string = '&'.join([ + 'POST' if data else 'GET', + compat_urllib_parse.quote(base_url, ''), + compat_urllib_parse.quote(encoded_query, '')]) oauth_signature = base64.b64encode(hmac.new( - (self._API_PARAMS['oAuthSecret'] + '&').encode('ascii'), + (self._API_PARAMS['oAuthSecret'] + '&' + self._TOKEN_SECRET).encode('ascii'), base_string.encode(), hashlib.sha1).digest()).decode() encoded_query += '&oauth_signature=' + compat_urllib_parse.quote(oauth_signature, '') - return self._download_json( - '?'.join([base_url, encoded_query]), video_id, - note='Downloading %s JSON metadata' % note, headers=headers, data=data) + try: + return self._download_json( + '?'.join([base_url, encoded_query]), video_id, + note='Downloading %s JSON metadata' % note, headers=headers, data=data) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + raise ExtractorError(json.loads(e.cause.read().decode())['message'], expected=True) + raise def _call_cms(self, path, video_id, note): if not self._CMS_SIGNING: @@ -55,19 +69,22 @@ class VRVBaseIE(InfoExtractor): self._API_DOMAIN + path, video_id, query=self._CMS_SIGNING, note='Downloading %s JSON metadata' % note, headers=self.geo_verification_headers()) - def _set_api_params(self, webpage, video_id): - if not self._API_PARAMS: - self._API_PARAMS = self._parse_json(self._search_regex( - r'window\.__APP_CONFIG__\s*=\s*({.+?})</script>', - webpage, 'api config'), video_id)['cxApiParams'] - self._API_DOMAIN = self._API_PARAMS.get('apiDomain', 'https://api.vrv.co') - def _get_cms_resource(self, resource_key, video_id): return self._call_api( 'cms_resource', video_id, 'resource path', data={ 'resource_key': resource_key, })['__links__']['cms_resource']['href'] + def _real_initialize(self): + webpage = self._download_webpage( + 'https://vrv.co/', None, headers=self.geo_verification_headers()) + self._API_PARAMS = self._parse_json(self._search_regex( + [ + r'window\.__APP_CONFIG__\s*=\s*({.+?})(?:</script>|;)', + r'window\.__APP_CONFIG__\s*=\s*({.+})' + ], webpage, 'app config'), None)['cxApiParams'] + self._API_DOMAIN = self._API_PARAMS.get('apiDomain', 'https://api.vrv.co') + class VRVIE(VRVBaseIE): IE_NAME = 'vrv' @@ -86,6 +103,22 @@ class VRVIE(VRVBaseIE): 'skip_download': True, }, }] + _NETRC_MACHINE = 'vrv' + + def _real_initialize(self): + super(VRVIE, self)._real_initialize() + + email, password = self._get_login_info() + if email is None: + return + + token_credentials = self._call_api( + 'authenticate/by:credentials', None, 'Token Credentials', data={ + 'email': email, + 'password': password, + }) + self._TOKEN = token_credentials['oauth_token'] + self._TOKEN_SECRET = token_credentials['oauth_token_secret'] def _extract_vrv_formats(self, url, video_id, stream_format, audio_lang, hardsub_lang): if not url or stream_format not in ('hls', 'dash'): @@ -116,28 +149,16 @@ class VRVIE(VRVBaseIE): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage( - url, video_id, - headers=self.geo_verification_headers()) - media_resource = self._parse_json(self._search_regex( - [ - r'window\.__INITIAL_STATE__\s*=\s*({.+?})(?:</script>|;)', - r'window\.__INITIAL_STATE__\s*=\s*({.+})' - ], webpage, 'inital state'), video_id).get('watch', {}).get('mediaResource') or {} - video_data = media_resource.get('json') - if not video_data: - self._set_api_params(webpage, video_id) - episode_path = self._get_cms_resource( - 'cms:/episodes/' + video_id, video_id) - video_data = self._call_cms(episode_path, video_id, 'video') + episode_path = self._get_cms_resource( + 'cms:/episodes/' + video_id, video_id) + video_data = self._call_cms(episode_path, video_id, 'video') title = video_data['title'] - streams_json = media_resource.get('streams', {}).get('json', {}) - if not streams_json: - self._set_api_params(webpage, video_id) - streams_path = video_data['__links__']['streams']['href'] - streams_json = self._call_cms(streams_path, video_id, 'streams') + streams_path = video_data['__links__'].get('streams', {}).get('href') + if not streams_path: + self.raise_login_required() + streams_json = self._call_cms(streams_path, video_id, 'streams') audio_locale = streams_json.get('audio_locale') formats = [] @@ -202,11 +223,7 @@ class VRVSeriesIE(VRVBaseIE): def _real_extract(self, url): series_id = self._match_id(url) - webpage = self._download_webpage( - url, series_id, - headers=self.geo_verification_headers()) - self._set_api_params(webpage, series_id) seasons_path = self._get_cms_resource( 'cms:/seasons?series_id=' + series_id, series_id) seasons_data = self._call_cms(seasons_path, series_id, 'seasons') From 503b604a316837b9dd6ef32045e4e9bbfb6a1363 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 22 Jan 2019 18:21:37 +0100 Subject: [PATCH 474/558] [vrv] fix oauth signing for python 2(#14307) --- youtube_dl/extractor/vrv.py | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/vrv.py b/youtube_dl/extractor/vrv.py index 014513051..6c060ae76 100644 --- a/youtube_dl/extractor/vrv.py +++ b/youtube_dl/extractor/vrv.py @@ -32,14 +32,14 @@ class VRVBaseIE(InfoExtractor): def _call_api(self, path, video_id, note, data=None): # https://tools.ietf.org/html/rfc5849#section-3 base_url = self._API_DOMAIN + '/core/' + path - query = { - 'oauth_consumer_key': self._API_PARAMS['oAuthKey'], - 'oauth_nonce': ''.join([random.choice(string.ascii_letters) for _ in range(32)]), - 'oauth_signature_method': 'HMAC-SHA1', - 'oauth_timestamp': int(time.time()), - } + query = [ + ('oauth_consumer_key', self._API_PARAMS['oAuthKey']), + ('oauth_nonce', ''.join([random.choice(string.ascii_letters) for _ in range(32)])), + ('oauth_signature_method', 'HMAC-SHA1'), + ('oauth_timestamp', int(time.time())), + ] if self._TOKEN: - query['oauth_token'] = self._TOKEN + query.append(('oauth_token', self._TOKEN)) encoded_query = compat_urllib_parse_urlencode(query) headers = self.geo_verification_headers() if data: From 278d061a0c5eae20963c0a6df4b9b13fd1537186 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 23 Jan 2019 03:51:29 +0700 Subject: [PATCH 475/558] [pornhub] Bypass scrape detection (closes #5930) --- youtube_dl/extractor/pornhub.py | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index e377de196..f5f3e6593 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -10,7 +10,9 @@ from .common import InfoExtractor from ..compat import ( compat_HTTPError, compat_str, + compat_urllib_request, ) +from .openload import PhantomJSwrapper from ..utils import ( ExtractorError, int_or_none, @@ -126,6 +128,26 @@ class PornHubIE(InfoExtractor): 'only_matching': True, }] + def _download_webpage_handle(self, *args, **kwargs): + def dl(*args, **kwargs): + return super(PornHubIE, self)._download_webpage_handle(*args, **kwargs) + + webpage, urlh = dl(*args, **kwargs) + + if any(re.search(p, webpage) for p in ( + r'<body\b[^>]+\bonload=["\']go\(\)', + r'document\.cookie\s*=\s*["\']RNKEY=', + r'document\.location\.reload\(true\)')): + url_or_request = args[0] + url = (url_or_request.get_full_url() + if isinstance(url_or_request, compat_urllib_request.Request) + else url_or_request) + phantom = PhantomJSwrapper(self, required_version='2.0') + phantom.get(url, html=webpage) + webpage, urlh = dl(*args, **kwargs) + + return webpage, urlh + @staticmethod def _extract_urls(webpage): return re.findall( From 6510a3aa971c00525969040ad654249c0c73f125 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 23 Jan 2019 03:55:41 +0700 Subject: [PATCH 476/558] [crunchyroll] Extend _VALID_URL (closes #18955) --- youtube_dl/extractor/crunchyroll.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 4a68d092b..5e2cbe41d 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -144,7 +144,7 @@ class CrunchyrollBaseIE(InfoExtractor): class CrunchyrollIE(CrunchyrollBaseIE, VRVIE): IE_NAME = 'crunchyroll' - _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)' + _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|(?:[^/]*/){1,2}[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)' _TESTS = [{ 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', 'info_dict': { @@ -269,6 +269,9 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE): }, { 'url': 'http://www.crunchyroll.com/media-723735', 'only_matching': True, + }, { + 'url': 'https://www.crunchyroll.com/en-gb/mob-psycho-100/episode-2-urban-legends-encountering-rumors-780921', + 'only_matching': True, }] _FORMAT_IDS = { From 71a1f61700789fb0d61fc6ad9681b6f0899d2f51 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 23 Jan 2019 04:12:06 +0700 Subject: [PATCH 477/558] [pornhub] Apply scrape detection bypass for all extractors --- youtube_dl/extractor/pornhub.py | 46 +++++++++++++++++---------------- 1 file changed, 24 insertions(+), 22 deletions(-) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index f5f3e6593..be93d5d48 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -24,7 +24,29 @@ from ..utils import ( ) -class PornHubIE(InfoExtractor): +class PornHubBaseIE(InfoExtractor): + def _download_webpage_handle(self, *args, **kwargs): + def dl(*args, **kwargs): + return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs) + + webpage, urlh = dl(*args, **kwargs) + + if any(re.search(p, webpage) for p in ( + r'<body\b[^>]+\bonload=["\']go\(\)', + r'document\.cookie\s*=\s*["\']RNKEY=', + r'document\.location\.reload\(true\)')): + url_or_request = args[0] + url = (url_or_request.get_full_url() + if isinstance(url_or_request, compat_urllib_request.Request) + else url_or_request) + phantom = PhantomJSwrapper(self, required_version='2.0') + phantom.get(url, html=webpage) + webpage, urlh = dl(*args, **kwargs) + + return webpage, urlh + + +class PornHubIE(PornHubBaseIE): IE_DESC = 'PornHub and Thumbzilla' _VALID_URL = r'''(?x) https?:// @@ -128,26 +150,6 @@ class PornHubIE(InfoExtractor): 'only_matching': True, }] - def _download_webpage_handle(self, *args, **kwargs): - def dl(*args, **kwargs): - return super(PornHubIE, self)._download_webpage_handle(*args, **kwargs) - - webpage, urlh = dl(*args, **kwargs) - - if any(re.search(p, webpage) for p in ( - r'<body\b[^>]+\bonload=["\']go\(\)', - r'document\.cookie\s*=\s*["\']RNKEY=', - r'document\.location\.reload\(true\)')): - url_or_request = args[0] - url = (url_or_request.get_full_url() - if isinstance(url_or_request, compat_urllib_request.Request) - else url_or_request) - phantom = PhantomJSwrapper(self, required_version='2.0') - phantom.get(url, html=webpage) - webpage, urlh = dl(*args, **kwargs) - - return webpage, urlh - @staticmethod def _extract_urls(webpage): return re.findall( @@ -329,7 +331,7 @@ class PornHubIE(InfoExtractor): } -class PornHubPlaylistBaseIE(InfoExtractor): +class PornHubPlaylistBaseIE(PornHubBaseIE): def _extract_entries(self, webpage, host): # Only process container div with main playlist content skipping # drop-down menu that uses similar pattern for videos (see From 0670bdd8f2bca39fdeadc63e1cd53b5d5b3e638c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 23 Jan 2019 04:43:55 +0700 Subject: [PATCH 478/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/ChangeLog b/ChangeLog index 902301765..687796a0e 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,32 @@ +version <unreleased> + +Core +* [utils] Fix urljoin for paths with non-http(s) schemes +* [extractor/common] Improve jwplayer relative URL handling (#18892) ++ [YoutubeDL] Add negation support for string comparisons in format selection + expressions (#18600, #18805) +* [extractor/common] Improve HLS video-only format detection (#18923) + +Extractors +* [crunchyroll] Extend URL regular expression (#18955) +* [pornhub] Bypass scrape detection (#4822, #5930, #7074, #10175, #12722, + #17197, #18338 #18842, #18899) ++ [vrv] Add support for authentication (#14307) +* [videomore:season] Fix extraction +* [videomore] Improve extraction (#18908) ++ [tnaflix] Pass Referer in metadata request (#18925) +* [radiocanada] Relax DRM check (#18608, #18609) +* [vimeo] Fix video password verification for videos protected by + Referer HTTP header ++ [hketv] Add support for hkedcity.net (#18696) ++ [streamango] Add support for fruithosts.net (#18710) ++ [instagram] Add support for tags (#18757) ++ [odnoklassniki] Detect paid videos (#18876) +* [ted] Correct acodec for HTTP formats (#18923) +* [cartoonnetwork] Fix extraction (#15664, #17224) +* [vimeo] Fix extraction for password protected player URLs (#18889) + + version 2019.01.17 Extractors From 435e382423f860aca82a58d7c3db58cbfa242b40 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 23 Jan 2019 04:46:55 +0700 Subject: [PATCH 479/558] release 2019.01.23 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 2 ++ youtube_dl/version.py | 2 +- 4 files changed, 7 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 841bca914..db3ebaeed 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.17*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.17** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.23*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.23** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.01.17 +[debug] youtube-dl version 2019.01.23 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 687796a0e..55ad44315 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.01.23 Core * [utils] Fix urljoin for paths with non-http(s) schemes diff --git a/docs/supportedsites.md b/docs/supportedsites.md index c01409419..d759d0273 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -361,6 +361,7 @@ - **hitbox** - **hitbox:live** - **HitRecord** + - **hketv**: 香港教育局教育電視 (HKETV) Educational Television, Hong Kong Educational Bureau - **HornBunny** - **HotNewHipHop** - **hotstar** @@ -386,6 +387,7 @@ - **IndavideoEmbed** - **InfoQ** - **Instagram** + - **instagram:tag**: Instagram hashtag search - **instagram:user**: Instagram user profile - **Internazionale** - **InternetVideoArchive** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index ea3f62928..d77949eed 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.01.17' +__version__ = '2019.01.23' From e118a8794ffe5a3a414afd489726f34d753b0b23 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 24 Jan 2019 01:34:41 +0700 Subject: [PATCH 480/558] [YoutubeDL] Fix typo in string negation implementation and add more tests (closes #18961) --- test/test_YoutubeDL.py | 30 +++++++++++++++++++++++++++--- youtube_dl/YoutubeDL.py | 2 +- 2 files changed, 28 insertions(+), 4 deletions(-) diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index df8994b84..1d7452744 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -242,6 +242,7 @@ class TestFormatSelection(unittest.TestCase): def test_format_selection_string_ops(self): formats = [ {'format_id': 'abc-cba', 'ext': 'mp4', 'url': TEST_URL}, + {'format_id': 'zxc-cxz', 'ext': 'webm', 'url': TEST_URL}, ] info_dict = _make_result(formats) @@ -253,6 +254,11 @@ class TestFormatSelection(unittest.TestCase): # does not equal (!=) ydl = YDL({'format': '[format_id!=abc-cba]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'zxc-cxz') + + ydl = YDL({'format': '[format_id!=abc-cba][format_id!=zxc-cxz]'}) self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) # starts with (^=) @@ -262,7 +268,12 @@ class TestFormatSelection(unittest.TestCase): self.assertEqual(downloaded['format_id'], 'abc-cba') # does not start with (!^=) - ydl = YDL({'format': '[format_id!^=abc-cba]'}) + ydl = YDL({'format': '[format_id!^=abc]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'zxc-cxz') + + ydl = YDL({'format': '[format_id!^=abc][format_id!^=zxc]'}) self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) # ends with ($=) @@ -272,16 +283,29 @@ class TestFormatSelection(unittest.TestCase): self.assertEqual(downloaded['format_id'], 'abc-cba') # does not end with (!$=) - ydl = YDL({'format': '[format_id!$=abc-cba]'}) + ydl = YDL({'format': '[format_id!$=cba]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'zxc-cxz') + + ydl = YDL({'format': '[format_id!$=cba][format_id!$=cxz]'}) self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) # contains (*=) - ydl = YDL({'format': '[format_id*=-]'}) + ydl = YDL({'format': '[format_id*=bc-cb]'}) ydl.process_ie_result(info_dict.copy()) downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded['format_id'], 'abc-cba') # does not contain (!*=) + ydl = YDL({'format': '[format_id!*=bc-cb]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'zxc-cxz') + + ydl = YDL({'format': '[format_id!*=abc][format_id!*=zxc]'}) + self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) + ydl = YDL({'format': '[format_id!*=-]'}) self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index a827414dc..80ed8d7e5 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -1078,7 +1078,7 @@ class YoutubeDL(object): comparison_value = m.group('value') str_op = STR_OPERATORS[m.group('op')] if m.group('negation'): - op = lambda attr, value: not str_op + op = lambda attr, value: not str_op(attr, value) else: op = str_op From 7d311586eda9eae9430da3f6d18932d79127daa7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 24 Jan 2019 01:44:09 +0700 Subject: [PATCH 481/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/ChangeLog b/ChangeLog index 55ad44315..a28c6e951 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,9 @@ +version <unreleased> + +Core +* [YoutubeDL] Fix negation for string operators in format selection (#18961) + + version 2019.01.23 Core From a1e171233d86a064865353cc820969c10cb1f251 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 24 Jan 2019 01:46:23 +0700 Subject: [PATCH 482/558] release 2019.01.24 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index db3ebaeed..63aefe013 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.23*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.23** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.24*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.24** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.01.23 +[debug] youtube-dl version 2019.01.24 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index a28c6e951..1fda747bb 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.01.24 Core * [YoutubeDL] Fix negation for string operators in format selection (#18961) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index d77949eed..18c1f8d4c 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.01.23' +__version__ = '2019.01.24' From 9713d1d1e0a7eff5c1b9873a2f4f054111a568ab Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 24 Jan 2019 02:30:12 +0700 Subject: [PATCH 483/558] [openload] Add support for oload.club (closes #18969) --- youtube_dl/extractor/openload.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index cf51e4770..b713e78b8 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -249,7 +249,7 @@ class OpenloadIE(InfoExtractor): (?:www\.)? (?: openload\.(?:co|io|link)| - oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun) + oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club) ) )/ (?:f|embed)/ @@ -334,6 +334,9 @@ class OpenloadIE(InfoExtractor): }, { 'url': 'https://oload.fun/f/gb6G1H4sHXY', 'only_matching': True, + }, { + 'url': 'https://oload.club/f/Nr1L-aZ2dbQ', + 'only_matching': True, }] _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36' From 118afcf52ff23726e5f0c436083710f5c63230fa Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 23 Jan 2019 22:16:21 +0100 Subject: [PATCH 484/558] [go] fix adobe pass requests for Disney Now(closes #18901) --- youtube_dl/extractor/go.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/go.py b/youtube_dl/extractor/go.py index ec9dd6e3a..206d89e82 100644 --- a/youtube_dl/extractor/go.py +++ b/youtube_dl/extractor/go.py @@ -25,15 +25,15 @@ class GoIE(AdobePassIE): }, 'watchdisneychannel': { 'brand': '004', - 'requestor_id': 'Disney', + 'resource_id': 'Disney', }, 'watchdisneyjunior': { 'brand': '008', - 'requestor_id': 'DisneyJunior', + 'resource_id': 'DisneyJunior', }, 'watchdisneyxd': { 'brand': '009', - 'requestor_id': 'DisneyXD', + 'resource_id': 'DisneyXD', } } _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))'\ @@ -130,8 +130,8 @@ class GoIE(AdobePassIE): 'device': '001', } if video_data.get('accesslevel') == '1': - requestor_id = site_info['requestor_id'] - resource = self._get_mvpd_resource( + requestor_id = site_info.get('requestor_id', 'DisneyChannels') + resource = site_info.get('resource_id') or self._get_mvpd_resource( requestor_id, title, video_id, None) auth = self._extract_mvpd_auth( url, video_id, requestor_id, resource) From eb35b163adf61f8ff0ee6c504e98bc94db16e705 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 24 Jan 2019 20:23:04 +0100 Subject: [PATCH 485/558] [postprocessor/ffmpeg] fallback to ffmpeg/avconv for audio codec detection(closes #681) --- youtube_dl/postprocessor/ffmpeg.py | 53 +++++++++++++++++++----------- 1 file changed, 34 insertions(+), 19 deletions(-) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 39a905380..b952b0970 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -9,9 +9,6 @@ import re from .common import AudioConversionError, PostProcessor -from ..compat import ( - compat_subprocess_get_DEVNULL, -) from ..utils import ( encodeArgument, encodeFilename, @@ -165,27 +162,45 @@ class FFmpegPostProcessor(PostProcessor): return self._paths[self.probe_basename] def get_audio_codec(self, path): - if not self.probe_available: - raise PostProcessingError('ffprobe or avprobe not found. Please install one.') + if not self.probe_available and not self.available: + raise PostProcessingError('ffprobe/avprobe and ffmpeg/avconv not found. Please install one.') try: - cmd = [ - encodeFilename(self.probe_executable, True), - encodeArgument('-show_streams'), - encodeFilename(self._ffmpeg_filename_argument(path), True)] + if self.probe_available: + cmd = [ + encodeFilename(self.probe_executable, True), + encodeArgument('-show_streams')] + else: + cmd = [ + encodeFilename(self.executable, True), + encodeArgument('-i')] + cmd.append(encodeFilename(self._ffmpeg_filename_argument(path), True)) if self._downloader.params.get('verbose', False): - self._downloader.to_screen('[debug] %s command line: %s' % (self.basename, shell_quote(cmd))) - handle = subprocess.Popen(cmd, stderr=compat_subprocess_get_DEVNULL(), stdout=subprocess.PIPE, stdin=subprocess.PIPE) - output = handle.communicate()[0] - if handle.wait() != 0: + self._downloader.to_screen( + '[debug] %s command line: %s' % (self.basename, shell_quote(cmd))) + handle = subprocess.Popen( + cmd, stderr=subprocess.PIPE, + stdout=subprocess.PIPE, stdin=subprocess.PIPE) + stdout_data, stderr_data = handle.communicate() + expected_ret = 0 if self.probe_available else 1 + if handle.wait() != expected_ret: return None except (IOError, OSError): return None - audio_codec = None - for line in output.decode('ascii', 'ignore').split('\n'): - if line.startswith('codec_name='): - audio_codec = line.split('=')[1].strip() - elif line.strip() == 'codec_type=audio' and audio_codec is not None: - return audio_codec + output = (stdout_data if self.probe_available else stderr_data).decode('ascii', 'ignore') + if self.probe_available: + audio_codec = None + for line in output.split('\n'): + if line.startswith('codec_name='): + audio_codec = line.split('=')[1].strip() + elif line.strip() == 'codec_type=audio' and audio_codec is not None: + return audio_codec + else: + # Stream #FILE_INDEX:STREAM_INDEX[STREAM_ID](LANGUAGE): CODEC_TYPE: CODEC_NAME + mobj = re.search( + r'Stream\s*#\d+:\d+(?:\[0x[0-9a-f]+\])?(?:\([a-z]{3}\))?:\s*Audio:\s*([0-9a-z]+)', + output) + if mobj: + return mobj.group(1) return None def run_ffmpeg_multiple_files(self, input_paths, out_path, opts): From 0eba178fce80923515f4a9ac411e46648a19d78c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 25 Jan 2019 04:04:58 +0700 Subject: [PATCH 486/558] [nhk] Extend _VALID_URL (closes #18968) --- youtube_dl/extractor/nhk.py | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/nhk.py b/youtube_dl/extractor/nhk.py index 5c8cd76dc..d4acbcc3e 100644 --- a/youtube_dl/extractor/nhk.py +++ b/youtube_dl/extractor/nhk.py @@ -5,8 +5,8 @@ from ..utils import ExtractorError class NhkVodIE(InfoExtractor): - _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/vod/(?P<id>[^/]+/[^/?#&]+)' - _TEST = { + _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/(?:vod|ondemand)/(?P<id>[^/]+/[^/?#&]+)' + _TESTS = [{ # Videos available only for a limited period of time. Visit # http://www3.nhk.or.jp/nhkworld/en/vod/ for working samples. 'url': 'http://www3.nhk.or.jp/nhkworld/en/vod/tokyofashion/20160815', @@ -19,7 +19,10 @@ class NhkVodIE(InfoExtractor): 'episode': 'The Kimono as Global Fashion', }, 'skip': 'Videos available only for a limited period of time', - } + }, { + 'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2015173/', + 'only_matching': True, + }] _API_URL = 'http://api.nhk.or.jp/nhkworld/vodesdlist/v1/all/all/all.json?apikey=EJfK8jdS57GqlupFgAfAAwr573q01y6k' def _real_extract(self, url): From 1602a240a7742f9e0a02b3f0effd215d00d859f2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 25 Jan 2019 04:16:49 +0700 Subject: [PATCH 487/558] [drtv] Fix extraction (closes #18989) --- youtube_dl/extractor/drtv.py | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py index f757745ba..8d63ca433 100644 --- a/youtube_dl/extractor/drtv.py +++ b/youtube_dl/extractor/drtv.py @@ -77,10 +77,9 @@ class DRTVIE(InfoExtractor): r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'), webpage, 'video id') - programcard = self._download_json( - 'http://www.dr.dk/mu/programcard/expanded/%s' % video_id, - video_id, 'Downloading video JSON') - data = programcard['Data'][0] + data = self._download_json( + 'https://www.dr.dk/mu-online/api/1.4/programcard/%s' % video_id, + video_id, 'Downloading video JSON', query={'expanded': 'true'}) title = remove_end(self._og_search_title( webpage, default=None), ' | TV | DR') or data['Title'] @@ -97,7 +96,7 @@ class DRTVIE(InfoExtractor): formats = [] subtitles = {} - for asset in data['Assets']: + for asset in [data['PrimaryAsset']]: kind = asset.get('Kind') if kind == 'Image': thumbnail = asset.get('Uri') From ae18d58297c16a300a89693360efd19be4a97e92 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 25 Jan 2019 11:01:27 +0100 Subject: [PATCH 488/558] [usatoday] fix extraction for videos with custom brightcove partner id(closes #18990) --- youtube_dl/extractor/usatoday.py | 29 ++++++++++++++++++++++------- 1 file changed, 22 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/usatoday.py b/youtube_dl/extractor/usatoday.py index e5678dc78..b2103448d 100644 --- a/youtube_dl/extractor/usatoday.py +++ b/youtube_dl/extractor/usatoday.py @@ -3,21 +3,23 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( + ExtractorError, get_element_by_attribute, parse_duration, + try_get, update_url_query, - ExtractorError, ) from ..compat import compat_str class USATodayIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?usatoday\.com/(?:[^/]+/)*(?P<id>[^?/#]+)' - _TEST = { + _TESTS = [{ + # Brightcove Partner ID = 29906170001 'url': 'http://www.usatoday.com/media/cinematic/video/81729424/us-france-warn-syrian-regime-ahead-of-new-peace-talks/', - 'md5': '4d40974481fa3475f8bccfd20c5361f8', + 'md5': '033587d2529dc3411a1ab3644c3b8827', 'info_dict': { - 'id': '81729424', + 'id': '4799374959001', 'ext': 'mp4', 'title': 'US, France warn Syrian regime ahead of new peace talks', 'timestamp': 1457891045, @@ -25,8 +27,20 @@ class USATodayIE(InfoExtractor): 'uploader_id': '29906170001', 'upload_date': '20160313', } - } - BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/29906170001/38a9eecc-bdd8-42a3-ba14-95397e48b3f8_default/index.html?videoId=%s' + }, { + # ui-video-data[asset_metadata][items][brightcoveaccount] = 28911775001 + 'url': 'https://www.usatoday.com/story/tech/science/2018/08/21/yellowstone-supervolcano-eruption-stop-worrying-its-blow/973633002/', + 'info_dict': { + 'id': '5824495846001', + 'ext': 'mp4', + 'title': 'Yellowstone more likely to crack rather than explode', + 'timestamp': 1534790612, + 'description': 'md5:3715e7927639a4f16b474e9391687c62', + 'uploader_id': '28911775001', + 'upload_date': '20180820', + } + }] + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' def _real_extract(self, url): display_id = self._match_id(url) @@ -35,10 +49,11 @@ class USATodayIE(InfoExtractor): if not ui_video_data: raise ExtractorError('no video on the webpage', expected=True) video_data = self._parse_json(ui_video_data, display_id) + item = try_get(video_data, lambda x: x['asset_metadata']['items'], dict) or {} return { '_type': 'url_transparent', - 'url': self.BRIGHTCOVE_URL_TEMPLATE % video_data['brightcove_id'], + 'url': self.BRIGHTCOVE_URL_TEMPLATE % (item.get('brightcoveaccount', '29906170001'), item.get('brightcoveid') or video_data['brightcove_id']), 'id': compat_str(video_data['id']), 'title': video_data['title'], 'thumbnail': video_data.get('thumbnail'), From 252abb1e8b881aa9d3942c436711ac33235b37cd Mon Sep 17 00:00:00 2001 From: Sergey M <dstftw@gmail.com> Date: Sat, 26 Jan 2019 15:29:19 +0700 Subject: [PATCH 489/558] [README.md] Mention more convenience extraction functions --- README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 4ba982907..c1572f771 100644 --- a/README.md +++ b/README.md @@ -1213,7 +1213,7 @@ Incorrect: 'PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4' ``` -### Use safe conversion functions +### Use convenience conversion and parsing functions Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well. @@ -1221,6 +1221,8 @@ Use `url_or_none` for safe URL processing. Use `try_get` for safe metadata extraction from parsed JSON. +Use `unified_strdate` for uniform `upload_date` or any `YYYYMMDD` meta field extraction, `unified_timestamp` for uniform `timestamp` extraction, `parse_filesize` for `filesize` extraction, `parse_count` for count meta fields extraction, `parse_resolution`, `parse_duration` for `duration` extraction, `parse_age_limit` for `age_limit` extraction. + Explore [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions. #### More examples From 845333acf6280761d19f91b3e018c418d922a0de Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 27 Jan 2019 04:14:54 +0700 Subject: [PATCH 490/558] [wakanim] Add extractor (closes #14374) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/wakanim.py | 55 ++++++++++++++++++++++++++++++ 2 files changed, 56 insertions(+) create mode 100644 youtube_dl/extractor/wakanim.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 574a47e6d..2ffcffa9e 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1373,6 +1373,7 @@ from .vuclip import VuClipIE from .vvvvid import VVVVIDIE from .vyborymos import VyboryMosIE from .vzaar import VzaarIE +from .wakanim import WakanimIE from .walla import WallaIE from .washingtonpost import ( WashingtonPostIE, diff --git a/youtube_dl/extractor/wakanim.py b/youtube_dl/extractor/wakanim.py new file mode 100644 index 000000000..1d588bdd6 --- /dev/null +++ b/youtube_dl/extractor/wakanim.py @@ -0,0 +1,55 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + merge_dicts, + urljoin, +) + + +class WakanimIE(InfoExtractor): + _VALID_URL = r'https://(?:www\.)?wakanim\.tv/[^/]+/v2/catalogue/episode/(?P<id>\d+)' + _TEST = { + 'url': 'https://www.wakanim.tv/de/v2/catalogue/episode/2997/the-asterisk-war-omu-staffel-1-episode-02-omu', + 'info_dict': { + 'id': '2997', + 'ext': 'mp4', + 'title': 'Episode 02', + 'description': 'md5:2927701ea2f7e901de8bfa8d39b2852d', + 'series': 'The Asterisk War (OmU.)', + 'season_number': 1, + 'episode': 'Episode 02', + 'episode_number': 2, + }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + m3u8_url = urljoin(url, self._search_regex( + r'file\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'm3u8 url', + group='url')) + + formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + + info = self._search_json_ld(webpage, video_id, default={}) + + title = self._search_regex( + (r'<h1[^>]+\bclass=["\']episode_h1[^>]+\btitle=(["\'])(?P<title>(?:(?!\1).)+)\1', + r'<span[^>]+\bclass=["\']episode_title["\'][^>]*>(?P<title>[^<]+)'), + webpage, 'title', default=None, group='title') + + return merge_dicts(info, { + 'id': video_id, + 'title': title, + 'formats': formats, + }) From 458fd30f56785d514862dcb8a604a329d8e29ec6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 27 Jan 2019 04:36:58 +0700 Subject: [PATCH 491/558] [extractor/common] Extract season in _json_ld --- youtube_dl/extractor/common.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 95456b291..c4ea2882f 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1249,7 +1249,10 @@ class InfoExtractor(object): info['title'] = episode_name part_of_season = e.get('partOfSeason') if isinstance(part_of_season, dict) and part_of_season.get('@type') in ('TVSeason', 'Season', 'CreativeWorkSeason'): - info['season_number'] = int_or_none(part_of_season.get('seasonNumber')) + info.update({ + 'season': unescapeHTML(part_of_season.get('name')), + 'season_number': int_or_none(part_of_season.get('seasonNumber')), + }) part_of_series = e.get('partOfSeries') or e.get('partOfTVSeries') if isinstance(part_of_series, dict) and part_of_series.get('@type') in ('TVSeries', 'Series', 'CreativeWorkSeries'): info['series'] = unescapeHTML(part_of_series.get('name')) From 30cd1a5f3920d7485225a5d57b6ce41be4cde672 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 26 Jan 2019 22:52:54 +0100 Subject: [PATCH 492/558] [wakanim] detect DRM protected videos --- youtube_dl/extractor/wakanim.py | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/wakanim.py b/youtube_dl/extractor/wakanim.py index 1d588bdd6..f9a2395d9 100644 --- a/youtube_dl/extractor/wakanim.py +++ b/youtube_dl/extractor/wakanim.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( + ExtractorError, merge_dicts, urljoin, ) @@ -10,7 +11,7 @@ from ..utils import ( class WakanimIE(InfoExtractor): _VALID_URL = r'https://(?:www\.)?wakanim\.tv/[^/]+/v2/catalogue/episode/(?P<id>\d+)' - _TEST = { + _TESTS = [{ 'url': 'https://www.wakanim.tv/de/v2/catalogue/episode/2997/the-asterisk-war-omu-staffel-1-episode-02-omu', 'info_dict': { 'id': '2997', @@ -26,7 +27,11 @@ class WakanimIE(InfoExtractor): 'format': 'bestvideo', 'skip_download': True, }, - } + }, { + # DRM Protected + 'url': 'https://www.wakanim.tv/de/v2/catalogue/episode/7843/sword-art-online-alicization-omu-arc-2-folge-15-omu', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -36,6 +41,12 @@ class WakanimIE(InfoExtractor): m3u8_url = urljoin(url, self._search_regex( r'file\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'm3u8 url', group='url')) + # https://docs.microsoft.com/en-us/azure/media-services/previous/media-services-content-protection-overview#streaming-urls + encryption = self._search_regex( + r'encryption%3D(c(?:enc|bc(?:s-aapl)?))', + m3u8_url, 'encryption', default=None) + if encryption and encryption in ('cenc', 'cbcs-aapl'): + raise ExtractorError('This video is DRM protected.', expected=True) formats = self._extract_m3u8_formats( m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', From 1fcc91663bc84a599cc613ff1fa0e4bc15f42a9e Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 27 Jan 2019 10:53:38 +0100 Subject: [PATCH 493/558] [vice] fix extraction for locked videos(closes #16248) --- youtube_dl/extractor/vice.py | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py index 538258617..8fdfd743d 100644 --- a/youtube_dl/extractor/vice.py +++ b/youtube_dl/extractor/vice.py @@ -94,7 +94,6 @@ class ViceIE(AdobePassIE): 'url': 'https://www.viceland.com/en_us/video/thursday-march-1-2018/5a8f2d7ff1cdb332dd446ec1', 'only_matching': True, }] - _PREPLAY_HOST = 'vms.vice' @staticmethod def _extract_urls(webpage): @@ -158,9 +157,8 @@ class ViceIE(AdobePassIE): }) try: - host = 'www.viceland' if is_locked else self._PREPLAY_HOST preplay = self._download_json( - 'https://%s.com/%s/video/preplay/%s' % (host, locale, video_id), + 'https://vms.vice.com/%s/video/preplay/%s' % (locale, video_id), video_id, query=query) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 401): From bf8ebc9cfe1ae2b62baf2116f84748db03c4df7c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 27 Jan 2019 21:25:43 +0700 Subject: [PATCH 494/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/ChangeLog b/ChangeLog index 1fda747bb..9d5c25273 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,22 @@ +version <unreleased> + +Core ++ [extractor/common] Extract season in _json_ld +* [postprocessor/ffmpeg] Fallback to ffmpeg/avconv for audio codec detection + (#681) + +Extractors +* [vice] Fix extraction for locked videos (#16248) ++ [wakanim] Detect DRM protected videos ++ [wakanim] Add support for wakanim.tv (#14374) +* [usatoday] Fix extraction for videos with custom brightcove partner id + (#18990) +* [drtv] Fix extraction (#18989) +* [nhk] Extend URL regular expression (#18968) +* [go] Fix Adobe Pass requests for Disney Now (#18901) ++ [openload] Add support for oload.club (#18969) + + version 2019.01.24 Core From e71be6ee9f239308765443d49d91358fa306e48a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 27 Jan 2019 21:28:09 +0700 Subject: [PATCH 495/558] release 2019.01.27 --- .github/ISSUE_TEMPLATE.md | 6 +++--- CONTRIBUTING.md | 4 +++- ChangeLog | 2 +- docs/supportedsites.md | 1 + youtube_dl/version.py | 2 +- 5 files changed, 9 insertions(+), 6 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 63aefe013..f529e3f4b 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.24*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.24** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.27*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.27** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.01.24 +[debug] youtube-dl version 2019.01.27 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index a71b045d0..6c1739860 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -339,7 +339,7 @@ Incorrect: 'PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4' ``` -### Use safe conversion functions +### Use convenience conversion and parsing functions Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well. @@ -347,6 +347,8 @@ Use `url_or_none` for safe URL processing. Use `try_get` for safe metadata extraction from parsed JSON. +Use `unified_strdate` for uniform `upload_date` or any `YYYYMMDD` meta field extraction, `unified_timestamp` for uniform `timestamp` extraction, `parse_filesize` for `filesize` extraction, `parse_count` for count meta fields extraction, `parse_resolution`, `parse_duration` for `duration` extraction, `parse_age_limit` for `age_limit` extraction. + Explore [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions. #### More examples diff --git a/ChangeLog b/ChangeLog index 9d5c25273..d94fe36ec 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.01.27 Core + [extractor/common] Extract season in _json_ld diff --git a/docs/supportedsites.md b/docs/supportedsites.md index d759d0273..6377bf815 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -1069,6 +1069,7 @@ - **VVVVID** - **VyboryMos** - **Vzaar** + - **Wakanim** - **Walla** - **WalyTV** - **washingtonpost** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 18c1f8d4c..ec89cfc64 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.01.24' +__version__ = '2019.01.27' From 2b3afe6b0fee226bb1e61027d815df088cb40757 Mon Sep 17 00:00:00 2001 From: Andrew Udvare <audvare@gmail.com> Date: Sun, 27 Jan 2019 22:24:37 -0500 Subject: [PATCH 496/558] [postprocessor/ffmpeg] Disable "Last message repeated" messages which cause non-zero exit status --- youtube_dl/postprocessor/ffmpeg.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index b952b0970..8ef03f43b 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -218,6 +218,7 @@ class FFmpegPostProcessor(PostProcessor): encodeFilename(self._ffmpeg_filename_argument(path), True) ]) cmd = ([encodeFilename(self.executable, True), encodeArgument('-y')] + + ['-loglevel', 'repeat+info'] + files_cmd + [encodeArgument(o) for o in opts] + [encodeFilename(self._ffmpeg_filename_argument(out_path), True)]) From 7f903dd8bfbc9c2de129d5b0be23ef62d8ca3df3 Mon Sep 17 00:00:00 2001 From: Tatsh <Tatsh@users.noreply.github.com> Date: Mon, 28 Jan 2019 10:57:14 -0500 Subject: [PATCH 497/558] [postprocessor/ffmpeg] Do not copy Apple TV chapter tracks while embedding subtitles (closes #19042) Related issue: https://trac.ffmpeg.org/ticket/6016 --- youtube_dl/postprocessor/ffmpeg.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index b952b0970..fff2021ff 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -407,6 +407,9 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor): # Don't copy the existing subtitles, we may be running the # postprocessor a second time '-map', '-0:s', + # Don't copy Apple TV chapters track, bin_data (see #19042, #19024, + # https://trac.ffmpeg.org/ticket/6016) + '-map', '-0:d', ] if information['ext'] == 'mp4': opts += ['-c:s', 'mov_text'] From 61ff92e11ea876532697451b1ed727f42274b109 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 29 Jan 2019 01:59:56 +0700 Subject: [PATCH 498/558] [postprocessor/ffmpeg] Wrap loglevel args in encodeArgument --- youtube_dl/postprocessor/ffmpeg.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 33dbcad9f..88b9ae9be 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -218,7 +218,7 @@ class FFmpegPostProcessor(PostProcessor): encodeFilename(self._ffmpeg_filename_argument(path), True) ]) cmd = ([encodeFilename(self.executable, True), encodeArgument('-y')] + - ['-loglevel', 'repeat+info'] + + [encodeArgument('-loglevel'), encodeArgument('repeat+info')] + files_cmd + [encodeArgument(o) for o in opts] + [encodeFilename(self._ffmpeg_filename_argument(out_path), True)]) From a81daba2311cb4d6c5bc7e62b47438a78aa5c10f Mon Sep 17 00:00:00 2001 From: Alexander Seiler <seileralex@gmail.com> Date: Mon, 28 Jan 2019 20:20:46 +0100 Subject: [PATCH 499/558] [zattoo] Add support for tv.salt.ch --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/zattoo.py | 11 +++++++++++ 2 files changed, 12 insertions(+) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 2ffcffa9e..9d776ff45 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1497,6 +1497,7 @@ from .zattoo import ( QuantumTVIE, QuicklineIE, QuicklineLiveIE, + SaltTVIE, SAKTVIE, VTXTVIE, WalyTVIE, diff --git a/youtube_dl/extractor/zattoo.py b/youtube_dl/extractor/zattoo.py index 896276301..ee514666b 100644 --- a/youtube_dl/extractor/zattoo.py +++ b/youtube_dl/extractor/zattoo.py @@ -420,3 +420,14 @@ class EinsUndEinsTVIE(ZattooIE): 'url': 'https://www.1und1.tv/watch/abc/123-abc', 'only_matching': True, }] + + +class SaltTVIE(ZattooIE): + _NETRC_MACHINE = 'salttv' + _HOST = 'tv.salt.ch' + _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) + + _TESTS = [{ + 'url': 'https://tv.salt.ch/watch/abc/123-abc', + 'only_matching': True, + }] From 41c2c254d3c30afde395e8abbe0ced2c53485a78 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 28 Jan 2019 22:39:08 +0100 Subject: [PATCH 500/558] [fox] fix extraction for free videos(#19060) --- youtube_dl/extractor/fox.py | 46 ++++++++++++++++--------------------- 1 file changed, 20 insertions(+), 26 deletions(-) diff --git a/youtube_dl/extractor/fox.py b/youtube_dl/extractor/fox.py index b1c91f095..2d6c97ec9 100644 --- a/youtube_dl/extractor/fox.py +++ b/youtube_dl/extractor/fox.py @@ -1,10 +1,11 @@ # coding: utf-8 from __future__ import unicode_literals -# import json -# import uuid +import json +import uuid from .adobepass import AdobePassIE +from ..compat import compat_str from ..utils import ( int_or_none, parse_age_limit, @@ -47,38 +48,31 @@ class FOXIE(AdobePassIE): 'url': 'https://www.nationalgeographic.com/tv/watch/f690e05ebbe23ab79747becd0cc223d1/', 'only_matching': True, }] - # _access_token = None + _access_token = None - # def _call_api(self, path, video_id, data=None): - # headers = { - # 'X-Api-Key': '238bb0a0c2aba67922c48709ce0c06fd', - # } - # if self._access_token: - # headers['Authorization'] = 'Bearer ' + self._access_token - # return self._download_json( - # 'https://api2.fox.com/v2.0/' + path, video_id, data=data, headers=headers) + def _call_api(self, path, video_id, data=None): + headers = { + 'X-Api-Key': '238bb0a0c2aba67922c48709ce0c06fd', + } + if self._access_token: + headers['Authorization'] = 'Bearer ' + self._access_token + return self._download_json( + 'https://api2.fox.com/v2.0/' + path, + video_id, data=data, headers=headers) - # def _real_initialize(self): - # self._access_token = self._call_api( - # 'login', None, json.dumps({ - # 'deviceId': compat_str(uuid.uuid4()), - # }).encode())['accessToken'] + def _real_initialize(self): + self._access_token = self._call_api( + 'login', None, json.dumps({ + 'deviceId': compat_str(uuid.uuid4()), + }).encode())['accessToken'] def _real_extract(self, url): video_id = self._match_id(url) - video = self._download_json( - 'https://api.fox.com/fbc-content/v1_5/video/%s' % video_id, - video_id, headers={ - 'apikey': 'abdcbed02c124d393b39e818a4312055', - 'Content-Type': 'application/json', - 'Referer': url, - }) - # video = self._call_api('vodplayer/' + video_id, video_id) + video = self._call_api('vodplayer/' + video_id, video_id) title = video['name'] - release_url = video['videoRelease']['url'] - # release_url = video['url'] + release_url = video['url'] data = try_get( video, lambda x: x['trackingData']['properties'], dict) or {} From 6df196f32e68ec22bd854c4d779b9d94e04e63b2 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 29 Jan 2019 00:31:49 +0100 Subject: [PATCH 501/558] [fox] add support for locked videos using cookies(closes #19060) --- youtube_dl/extractor/extractors.py | 5 ++- youtube_dl/extractor/fox.py | 50 +++++++++++----------- youtube_dl/extractor/nationalgeographic.py | 22 ++++++++++ 3 files changed, 51 insertions(+), 26 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 9d776ff45..b40be42e6 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -692,7 +692,10 @@ from .myvi import ( MyviEmbedIE, ) from .myvidster import MyVidsterIE -from .nationalgeographic import NationalGeographicVideoIE +from .nationalgeographic import ( + NationalGeographicVideoIE, + NationalGeographicTVIE, +) from .naver import NaverIE from .nba import NBAIE from .nbc import ( diff --git a/youtube_dl/extractor/fox.py b/youtube_dl/extractor/fox.py index 2d6c97ec9..568656542 100644 --- a/youtube_dl/extractor/fox.py +++ b/youtube_dl/extractor/fox.py @@ -5,19 +5,23 @@ import json import uuid from .adobepass import AdobePassIE -from ..compat import compat_str +from ..compat import ( + compat_HTTPError, + compat_str, + compat_urllib_parse_unquote, +) from ..utils import ( + ExtractorError, int_or_none, parse_age_limit, parse_duration, try_get, unified_timestamp, - update_url_query, ) class FOXIE(AdobePassIE): - _VALID_URL = r'https?://(?:www\.)?(?:fox\.com|nationalgeographic\.com/tv)/watch/(?P<id>[\da-fA-F]+)' + _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[\da-fA-F]+)' _TESTS = [{ # clip 'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/', @@ -32,6 +36,7 @@ class FOXIE(AdobePassIE): 'upload_date': '20170901', 'creator': 'FOX', 'series': 'Gotham', + 'age_limit': 14, }, 'params': { 'skip_download': True, @@ -44,15 +49,14 @@ class FOXIE(AdobePassIE): # episode, geo-restricted, tv provided required 'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/', 'only_matching': True, - }, { - 'url': 'https://www.nationalgeographic.com/tv/watch/f690e05ebbe23ab79747becd0cc223d1/', - 'only_matching': True, }] + _HOME_PAGE_URL = 'https://www.fox.com/' + _API_KEY = 'abdcbed02c124d393b39e818a4312055' _access_token = None def _call_api(self, path, video_id, data=None): headers = { - 'X-Api-Key': '238bb0a0c2aba67922c48709ce0c06fd', + 'X-Api-Key': self._API_KEY, } if self._access_token: headers['Authorization'] = 'Bearer ' + self._access_token @@ -61,10 +65,16 @@ class FOXIE(AdobePassIE): video_id, data=data, headers=headers) def _real_initialize(self): - self._access_token = self._call_api( - 'login', None, json.dumps({ - 'deviceId': compat_str(uuid.uuid4()), - }).encode())['accessToken'] + if not self._access_token: + mvpd_auth = self._get_cookies(self._HOME_PAGE_URL).get('mvpd-auth') + if mvpd_auth: + self._access_token = (self._parse_json(compat_urllib_parse_unquote( + mvpd_auth.value), None, fatal=False) or {}).get('accessToken') + if not self._access_token: + self._access_token = self._call_api( + 'login', None, json.dumps({ + 'deviceId': compat_str(uuid.uuid4()), + }).encode())['accessToken'] def _real_extract(self, url): video_id = self._match_id(url) @@ -73,25 +83,15 @@ class FOXIE(AdobePassIE): title = video['name'] release_url = video['url'] - - data = try_get( - video, lambda x: x['trackingData']['properties'], dict) or {} - - rating = video.get('contentRating') - if data.get('authRequired'): - resource = self._get_mvpd_resource( - 'fbc-fox', title, video.get('guid'), rating) - release_url = update_url_query( - release_url, { - 'auth': self._extract_mvpd_auth( - url, video_id, 'fbc-fox', resource) - }) m3u8_url = self._download_json(release_url, video_id)['playURL'] formats = self._extract_m3u8_formats( m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls') self._sort_formats(formats) + data = try_get( + video, lambda x: x['trackingData']['properties'], dict) or {} + duration = int_or_none(video.get('durationInSeconds')) or int_or_none( video.get('duration')) or parse_duration(video.get('duration')) timestamp = unified_timestamp(video.get('datePublished')) @@ -117,7 +117,7 @@ class FOXIE(AdobePassIE): 'description': video.get('description'), 'duration': duration, 'timestamp': timestamp, - 'age_limit': parse_age_limit(rating), + 'age_limit': parse_age_limit(video.get('contentRating')), 'creator': creator, 'series': series, 'season_number': int_or_none(video.get('seasonNumber')), diff --git a/youtube_dl/extractor/nationalgeographic.py b/youtube_dl/extractor/nationalgeographic.py index 165964ca0..ee12e2b47 100644 --- a/youtube_dl/extractor/nationalgeographic.py +++ b/youtube_dl/extractor/nationalgeographic.py @@ -1,6 +1,7 @@ from __future__ import unicode_literals from .common import InfoExtractor +from .fox import FOXIE from ..utils import ( smuggle_url, url_basename, @@ -58,3 +59,24 @@ class NationalGeographicVideoIE(InfoExtractor): {'force_smil_url': True}), 'id': guid, } + + +class NationalGeographicTVIE(FOXIE): + _VALID_URL = r'https?://(?:www\.)?nationalgeographic\.com/tv/watch/(?P<id>[\da-fA-F]+)' + _TESTS = [{ + 'url': 'https://www.nationalgeographic.com/tv/watch/6a875e6e734b479beda26438c9f21138/', + 'info_dict': { + 'id': '6a875e6e734b479beda26438c9f21138', + 'ext': 'mp4', + 'title': 'Why Nat Geo? Valley of the Boom', + 'description': 'The lives of prominent figures in the tech world, including their friendships, rivalries, victories and failures.', + 'timestamp': 1542662458, + 'upload_date': '20181119', + 'age_limit': 14, + }, + 'params': { + 'skip_download': True, + }, + }] + _HOME_PAGE_URL = 'https://www.nationalgeographic.com/tv/' + _API_KEY = '238bb0a0c2aba67922c48709ce0c06fd' From a2d821d7112fb1423f99ddf309a843c80cc3be2d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 29 Jan 2019 23:33:09 +0700 Subject: [PATCH 502/558] [drtv] Improve extraction (closes #19039) + Add support for EncryptedUri videos + Extract more metadata * Fix subtitles extraction --- youtube_dl/extractor/drtv.py | 133 +++++++++++++++++++++++++++-------- 1 file changed, 102 insertions(+), 31 deletions(-) diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py index 8d63ca433..c5f211128 100644 --- a/youtube_dl/extractor/drtv.py +++ b/youtube_dl/extractor/drtv.py @@ -1,15 +1,25 @@ # coding: utf-8 from __future__ import unicode_literals +import binascii +import hashlib +import re + + from .common import InfoExtractor +from ..aes import aes_cbc_decrypt +from ..compat import compat_urllib_parse_unquote from ..utils import ( + bytes_to_intlist, ExtractorError, int_or_none, + intlist_to_bytes, float_or_none, mimetype2ext, - parse_iso8601, - remove_end, + str_or_none, + unified_timestamp, update_url_query, + url_or_none, ) @@ -20,23 +30,31 @@ class DRTVIE(InfoExtractor): IE_NAME = 'drtv' _TESTS = [{ 'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10', - 'md5': '7ae17b4e18eb5d29212f424a7511c184', + 'md5': '25e659cccc9a2ed956110a299fdf5983', 'info_dict': { 'id': 'klassen-darlig-taber-10', 'ext': 'mp4', 'title': 'Klassen - Dårlig taber (10)', 'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa', - 'timestamp': 1471991907, - 'upload_date': '20160823', + 'timestamp': 1539085800, + 'upload_date': '20181009', 'duration': 606.84, + 'series': 'Klassen', + 'season': 'Klassen I', + 'season_number': 1, + 'season_id': 'urn:dr:mu:bundle:57d7e8216187a4031cfd6f6b', + 'episode': 'Episode 10', + 'episode_number': 10, + 'release_year': 2016, }, + 'expected_warnings': ['Unable to download f4m manifest'], }, { # embed 'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang', 'info_dict': { - 'id': 'christiania-pusher-street-ryddes-drdkrjpo', + 'id': 'urn:dr:mu:programcard:57c926176187a50a9c6e83c6', 'ext': 'mp4', - 'title': 'LIVE Christianias rydning af Pusher Street er i gang', + 'title': 'christiania pusher street ryddes drdkrjpo', 'description': 'md5:2a71898b15057e9b97334f61d04e6eb5', 'timestamp': 1472800279, 'upload_date': '20160902', @@ -45,17 +63,18 @@ class DRTVIE(InfoExtractor): 'params': { 'skip_download': True, }, + 'expected_warnings': ['Unable to download f4m manifest'], }, { # with SignLanguage formats 'url': 'https://www.dr.dk/tv/se/historien-om-danmark/-/historien-om-danmark-stenalder', 'info_dict': { 'id': 'historien-om-danmark-stenalder', 'ext': 'mp4', - 'title': 'Historien om Danmark: Stenalder (1)', + 'title': 'Historien om Danmark: Stenalder', 'description': 'md5:8c66dcbc1669bbc6f873879880f37f2a', - 'timestamp': 1490401996, - 'upload_date': '20170325', - 'duration': 3502.04, + 'timestamp': 1546628400, + 'upload_date': '20190104', + 'duration': 3502.56, 'formats': 'mincount:20', }, 'params': { @@ -74,19 +93,26 @@ class DRTVIE(InfoExtractor): video_id = self._search_regex( (r'data-(?:material-identifier|episode-slug)="([^"]+)"', - r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'), - webpage, 'video id') + r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'), + webpage, 'video id', default=None) + + if not video_id: + video_id = compat_urllib_parse_unquote(self._search_regex( + r'(urn(?:%3A|:)dr(?:%3A|:)mu(?:%3A|:)programcard(?:%3A|:)[\da-f]+)', + webpage, 'urn')) data = self._download_json( 'https://www.dr.dk/mu-online/api/1.4/programcard/%s' % video_id, video_id, 'Downloading video JSON', query={'expanded': 'true'}) - title = remove_end(self._og_search_title( - webpage, default=None), ' | TV | DR') or data['Title'] + title = str_or_none(data.get('Title')) or re.sub( + r'\s*\|\s*(?:TV\s*\|\s*DR|DRTV)$', '', + self._og_search_title(webpage)) description = self._og_search_description( webpage, default=None) or data.get('Description') - timestamp = parse_iso8601(data.get('CreatedTime')) + timestamp = unified_timestamp( + data.get('PrimaryBroadcastStartTime') or data.get('SortDateTime')) thumbnail = None duration = None @@ -96,16 +122,51 @@ class DRTVIE(InfoExtractor): formats = [] subtitles = {} - for asset in [data['PrimaryAsset']]: + assets = [] + primary_asset = data.get('PrimaryAsset') + if isinstance(primary_asset, dict): + assets.append(primary_asset) + secondary_assets = data.get('SecondaryAssets') + if isinstance(secondary_assets, list): + for secondary_asset in secondary_assets: + if isinstance(secondary_asset, dict): + assets.append(secondary_asset) + + def hex_to_bytes(hex): + return binascii.a2b_hex(hex.encode('ascii')) + + def decrypt_uri(e): + n = int(e[2:10], 16) + a = e[10 + n:] + data = bytes_to_intlist(hex_to_bytes(e[10:10 + n])) + key = bytes_to_intlist(hashlib.sha256( + ('%s:sRBzYNXBzkKgnjj8pGtkACch' % a).encode('utf-8')).digest()) + iv = bytes_to_intlist(hex_to_bytes(a)) + decrypted = aes_cbc_decrypt(data, key, iv) + return intlist_to_bytes( + decrypted[:-decrypted[-1]]).decode('utf-8').split('?')[0] + + for asset in assets: kind = asset.get('Kind') if kind == 'Image': - thumbnail = asset.get('Uri') + thumbnail = url_or_none(asset.get('Uri')) elif kind in ('VideoResource', 'AudioResource'): duration = float_or_none(asset.get('DurationInMilliseconds'), 1000) restricted_to_denmark = asset.get('RestrictedToDenmark') asset_target = asset.get('Target') for link in asset.get('Links', []): uri = link.get('Uri') + if not uri: + encrypted_uri = link.get('EncryptedUri') + if not encrypted_uri: + continue + try: + uri = decrypt_uri(encrypted_uri) + except Exception: + self.report_warning( + 'Unable to decrypt EncryptedUri', video_id) + continue + uri = url_or_none(uri) if not uri: continue target = link.get('Target') @@ -139,19 +200,22 @@ class DRTVIE(InfoExtractor): 'vcodec': 'none' if kind == 'AudioResource' else None, 'preference': preference, }) - subtitles_list = asset.get('SubtitlesList') - if isinstance(subtitles_list, list): - LANGS = { - 'Danish': 'da', - } - for subs in subtitles_list: - if not subs.get('Uri'): - continue - lang = subs.get('Language') or 'da' - subtitles.setdefault(LANGS.get(lang, lang), []).append({ - 'url': subs['Uri'], - 'ext': mimetype2ext(subs.get('MimeType')) or 'vtt' - }) + subtitles_list = asset.get('SubtitlesList') or asset.get('Subtitleslist') + if isinstance(subtitles_list, list): + LANGS = { + 'Danish': 'da', + } + for subs in subtitles_list: + if not isinstance(subs, dict): + continue + sub_uri = url_or_none(subs.get('Uri')) + if not sub_uri: + continue + lang = subs.get('Language') or 'da' + subtitles.setdefault(LANGS.get(lang, lang), []).append({ + 'url': sub_uri, + 'ext': mimetype2ext(subs.get('MimeType')) or 'vtt' + }) if not formats and restricted_to_denmark: self.raise_geo_restricted( @@ -169,6 +233,13 @@ class DRTVIE(InfoExtractor): 'duration': duration, 'formats': formats, 'subtitles': subtitles, + 'series': str_or_none(data.get('SeriesTitle')), + 'season': str_or_none(data.get('SeasonTitle')), + 'season_number': int_or_none(data.get('SeasonNumber')), + 'season_id': str_or_none(data.get('SeasonUrn')), + 'episode': str_or_none(data.get('EpisodeTitle')), + 'episode_number': int_or_none(data.get('EpisodeNumber')), + 'release_year': int_or_none(data.get('ProductionYear')), } From 41cff90c41006b30213c7f676bd3920a1612b717 Mon Sep 17 00:00:00 2001 From: JChris246 <43832407+JChris246@users.noreply.github.com> Date: Mon, 28 Jan 2019 19:42:49 -0400 Subject: [PATCH 503/558] [yourporn] Fix extraction and extract duration (closes #18815, closes #18852) change cdn to cdn4 for the video_url --- youtube_dl/extractor/yourporn.py | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/yourporn.py b/youtube_dl/extractor/yourporn.py index c8dc29bd8..01e5f0c0e 100644 --- a/youtube_dl/extractor/yourporn.py +++ b/youtube_dl/extractor/yourporn.py @@ -1,7 +1,10 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import urljoin +from ..utils import ( + parse_duration, + urljoin +) class YourPornIE(InfoExtractor): @@ -27,17 +30,21 @@ class YourPornIE(InfoExtractor): self._search_regex( r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info', group='data'), - video_id)[video_id]).replace('/cdn/', '/cdn3/') + video_id)[video_id]).replace('/cdn/', '/cdn4/') title = (self._search_regex( r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title', default=None) or self._og_search_description(webpage)).strip() + thumbnail = self._og_search_thumbnail(webpage) + duration = parse_duration(self._search_regex(r'duration:[^0-9]*([0-9:]+)', + webpage, 'duration', default=None)) return { 'id': video_id, 'url': video_url, 'title': title, + 'duration': duration, 'thumbnail': thumbnail, 'age_limit': 18 } From 9868f1ab1853484d7a6c38cd6fa0d94a11914cae Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 29 Jan 2019 23:56:42 +0700 Subject: [PATCH 504/558] [yourporn] Improve (closes #19061) --- youtube_dl/extractor/yourporn.py | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/yourporn.py b/youtube_dl/extractor/yourporn.py index 01e5f0c0e..2c63f9752 100644 --- a/youtube_dl/extractor/yourporn.py +++ b/youtube_dl/extractor/yourporn.py @@ -3,7 +3,7 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( parse_duration, - urljoin + urljoin, ) @@ -17,7 +17,11 @@ class YourPornIE(InfoExtractor): 'ext': 'mp4', 'title': 'md5:c9f43630bd968267672651ba905a7d35', 'thumbnail': r're:^https?://.*\.jpg$', - 'age_limit': 18 + 'duration': 165, + 'age_limit': 18, + }, + 'params': { + 'skip_download': True, }, } @@ -35,16 +39,16 @@ class YourPornIE(InfoExtractor): title = (self._search_regex( r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title', default=None) or self._og_search_description(webpage)).strip() - thumbnail = self._og_search_thumbnail(webpage) + duration = parse_duration(self._search_regex( + r'duration\s*:\s*<[^>]+>([\d:]+)', webpage, 'duration', + default=None)) - duration = parse_duration(self._search_regex(r'duration:[^0-9]*([0-9:]+)', - webpage, 'duration', default=None)) return { 'id': video_id, 'url': video_url, 'title': title, - 'duration': duration, 'thumbnail': thumbnail, - 'age_limit': 18 + 'duration': duration, + 'age_limit': 18, } From 5496754ae4c9097f37cfd9b307261cbbca438260 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 30 Jan 2019 00:03:19 +0700 Subject: [PATCH 505/558] [fox] Remove unused imports --- youtube_dl/extractor/fox.py | 2 -- 1 file changed, 2 deletions(-) diff --git a/youtube_dl/extractor/fox.py b/youtube_dl/extractor/fox.py index 568656542..0ffceeb7c 100644 --- a/youtube_dl/extractor/fox.py +++ b/youtube_dl/extractor/fox.py @@ -6,12 +6,10 @@ import uuid from .adobepass import AdobePassIE from ..compat import ( - compat_HTTPError, compat_str, compat_urllib_parse_unquote, ) from ..utils import ( - ExtractorError, int_or_none, parse_age_limit, parse_duration, From ca01e5f9039dd6c0d5abff5c7139f82c5d1dfba7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 30 Jan 2019 00:05:32 +0700 Subject: [PATCH 506/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/ChangeLog b/ChangeLog index d94fe36ec..8f5343b23 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,21 @@ +version <unreleased> + +Core +* [postprocessor/ffmpeg] Do not copy Apple TV chapter tracks while embedding + subtitles (#19024, #19042) +* [postprocessor/ffmpeg] Disable "Last message repeated" messages (#19025) + +Extractors +* [yourporn] Fix extraction and extract duration (#18815, #18852, #19061) +* [drtv] Improve extraction (#19039) + + Add support for EncryptedUri videos + + Extract more metadata + * Fix subtitles extraction ++ [fox] Add support for locked videos using cookies (#19060) +* [fox] Fix extraction for free videos (#19060) ++ [zattoo] Add support for tv.salt.ch (#19059) + + version 2019.01.27 Core From 1063b4c7073ce056f694b1690dd5d5a1a06fb347 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 30 Jan 2019 00:08:39 +0700 Subject: [PATCH 507/558] release 2019.01.30 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 2 ++ youtube_dl/version.py | 2 +- 4 files changed, 7 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index f529e3f4b..3944a4a38 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.27*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.27** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.30*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.30** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.01.27 +[debug] youtube-dl version 2019.01.30 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index 8f5343b23..745fffeaa 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.01.30 Core * [postprocessor/ffmpeg] Do not copy Apple TV chapter tracks while embedding diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 6377bf815..2918520c3 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -546,6 +546,7 @@ - **MyVisionTV** - **n-tv.de** - **natgeo:video** + - **NationalGeographicTV** - **Naver** - **NBA** - **NBC** @@ -776,6 +777,7 @@ - **safari:api** - **safari:course**: safaribooksonline.com online courses - **SAKTV** + - **SaltTV** - **Sapo**: SAPO Vídeos - **savefrom.net** - **SBS**: sbs.com.au diff --git a/youtube_dl/version.py b/youtube_dl/version.py index ec89cfc64..97818d0c7 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.01.27' +__version__ = '2019.01.30' From ce52c7c111602f41d7f9c498f2915fd255ba2eab Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 30 Jan 2019 06:15:23 +0700 Subject: [PATCH 508/558] [postprocessor/ffmpeg] Fix avconv processing broken in #19025 (closes #19067) --- youtube_dl/postprocessor/ffmpeg.py | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 88b9ae9be..5bcb00ac0 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -217,11 +217,13 @@ class FFmpegPostProcessor(PostProcessor): encodeArgument('-i'), encodeFilename(self._ffmpeg_filename_argument(path), True) ]) - cmd = ([encodeFilename(self.executable, True), encodeArgument('-y')] + - [encodeArgument('-loglevel'), encodeArgument('repeat+info')] + - files_cmd + - [encodeArgument(o) for o in opts] + - [encodeFilename(self._ffmpeg_filename_argument(out_path), True)]) + cmd = [encodeFilename(self.executable, True), encodeArgument('-y')] + # avconv does not have repeat option + if self.basename == 'ffmpeg': + cmd += [encodeArgument('-loglevel'), encodeArgument('repeat+info')] + cmd += (files_cmd + + [encodeArgument(o) for o in opts] + + [encodeFilename(self._ffmpeg_filename_argument(out_path), True)]) if self._downloader.params.get('verbose', False): self._downloader.to_screen('[debug] ffmpeg command line: %s' % shell_quote(cmd)) From c2a0fe2ea7422c437a27c8fac57c7e865517354b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 30 Jan 2019 06:17:25 +0700 Subject: [PATCH 509/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/ChangeLog b/ChangeLog index 745fffeaa..e6de6ca03 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,9 @@ +version <unreleased> + +Core +* [postprocessor/ffmpeg] Fix avconv processing broken in #19025 (#19067) + + version 2019.01.30 Core From 7b0f9df23d9842ddb2a545a0ceaf594daa0e12ba Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 30 Jan 2019 06:19:36 +0700 Subject: [PATCH 510/558] release 2019.01.30.1 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 3944a4a38..423a08e4d 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.30*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.30** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.30.1*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.30.1** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.01.30 +[debug] youtube-dl version 2019.01.30.1 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index e6de6ca03..4872cd9fc 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.01.30.1 Core * [postprocessor/ffmpeg] Fix avconv processing broken in #19025 (#19067) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 97818d0c7..be3bbdd73 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.01.30' +__version__ = '2019.01.30.1' From 645c4885cf38ecb244412dffda2760f4c0e72033 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 30 Jan 2019 14:43:44 +0100 Subject: [PATCH 511/558] [crackle] authorize media detail request(closes #16931) --- youtube_dl/extractor/crackle.py | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/crackle.py b/youtube_dl/extractor/crackle.py index f73ef6b63..49bf3a4f9 100644 --- a/youtube_dl/extractor/crackle.py +++ b/youtube_dl/extractor/crackle.py @@ -1,7 +1,10 @@ # coding: utf-8 from __future__ import unicode_literals, division +import hashlib +import hmac import re +import time from .common import InfoExtractor from ..compat import compat_HTTPError @@ -74,13 +77,16 @@ class CrackleIE(InfoExtractor): for country in countries: try: + # Authorization generation algorithm is reverse engineered from: + # https://www.sonycrackle.com/static/js/main.ea93451f.chunk.js + media_detail_url = 'https://web-api-us.crackle.com/Service.svc/details/media/%s/%s?disableProtocols=true' % (video_id, country) + timestamp = time.strftime('%Y%m%d%H%M', time.gmtime()) + h = hmac.new(b'IGSLUQCBDFHEOIFM', '|'.join([media_detail_url, timestamp]).encode(), hashlib.sha1).hexdigest().upper() media = self._download_json( - 'https://web-api-us.crackle.com/Service.svc/details/media/%s/%s' - % (video_id, country), video_id, - 'Downloading media JSON as %s' % country, - 'Unable to download media JSON', query={ - 'disableProtocols': 'true', - 'format': 'json' + media_detail_url, video_id, 'Downloading media JSON as %s' % country, + 'Unable to download media JSON', headers={ + 'Accept': 'application/json', + 'Authorization': '|'.join([h, timestamp, '117', '1']), }) except ExtractorError as e: # 401 means geo restriction, trying next country From 15e832ff2a1bee42b299d3498439cf789c16fffa Mon Sep 17 00:00:00 2001 From: Batuhan's Unmaintained Account <batuhanosmantaskaya@gmail.com> Date: Wed, 30 Jan 2019 19:39:02 +0300 Subject: [PATCH 512/558] [openload] Add support for oload.info --- youtube_dl/extractor/openload.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index b713e78b8..747aa298a 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -249,7 +249,7 @@ class OpenloadIE(InfoExtractor): (?:www\.)? (?: openload\.(?:co|io|link)| - oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club) + oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info) ) )/ (?:f|embed)/ @@ -337,6 +337,9 @@ class OpenloadIE(InfoExtractor): }, { 'url': 'https://oload.club/f/Nr1L-aZ2dbQ', 'only_matching': True, + }, { + 'url': 'https://oload.info/f/5NEAbI2BDSk', + 'only_matching': True, }] _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36' From 9613e14a92429046b162145dfd40dee5795ca409 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 31 Jan 2019 00:15:45 +0700 Subject: [PATCH 513/558] [openload] Add support for openload.pw and oload.pw (closes #18930) --- youtube_dl/extractor/openload.py | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index 747aa298a..a2ae25272 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -248,8 +248,8 @@ class OpenloadIE(InfoExtractor): (?P<host> (?:www\.)? (?: - openload\.(?:co|io|link)| - oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info) + openload\.(?:co|io|link|pw)| + oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw) ) )/ (?:f|embed)/ @@ -340,6 +340,12 @@ class OpenloadIE(InfoExtractor): }, { 'url': 'https://oload.info/f/5NEAbI2BDSk', 'only_matching': True, + }, { + 'url': 'https://openload.pw/f/WyKgK8s94N0', + 'only_matching': True, + }, { + 'url': 'https://oload.pw/f/WyKgK8s94N0', + 'only_matching': True, }] _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36' From 49fe4175ae165527a0b06b8d97cdc85d83041fef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 1 Feb 2019 01:48:10 +0700 Subject: [PATCH 514/558] [drtv] Improve preference (closes #19079) --- youtube_dl/extractor/drtv.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py index c5f211128..0c7e350f0 100644 --- a/youtube_dl/extractor/drtv.py +++ b/youtube_dl/extractor/drtv.py @@ -171,10 +171,13 @@ class DRTVIE(InfoExtractor): continue target = link.get('Target') format_id = target or '' - preference = None - if asset_target in ('SpokenSubtitles', 'SignLanguage'): + if asset_target in ('SpokenSubtitles', 'SignLanguage', 'VisuallyInterpreted'): preference = -1 format_id += '-%s' % asset_target + elif asset_target == 'Default': + preference = 1 + else: + preference = None if target == 'HDS': f4m_formats = self._extract_f4m_formats( uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43', From 3ef2da2d21061bd44df0b0a0d27e82a365209662 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 2 Feb 2019 04:00:29 +0700 Subject: [PATCH 515/558] [soundcloud] Fix paged playlists extraction, add support for albums and update client id --- youtube_dl/extractor/soundcloud.py | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 81c81c8d5..030840fd8 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -34,7 +34,7 @@ class SoundcloudIE(InfoExtractor): (?:(?:(?:www\.|m\.)?soundcloud\.com/ (?!stations/track) (?P<uploader>[\w\d-]+)/ - (?!(?:tracks|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#])) + (?!(?:tracks|albums|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#])) (?P<title>[\w\d-]+)/? (?P<token>[^?]+?)?(?:[?].*)?$) |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+) @@ -157,7 +157,7 @@ class SoundcloudIE(InfoExtractor): }, ] - _CLIENT_ID = 'LvWovRaJZlWCHql0bISuum8Bd2KX79mb' + _CLIENT_ID = 'NmW1FlPaiL94ueEu7oziOWjYEzZzQDcK' @staticmethod def _extract_urls(webpage): @@ -368,7 +368,6 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE): class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): - _API_BASE = 'https://api.soundcloud.com' _API_V2_BASE = 'https://api-v2.soundcloud.com' def _extract_playlist(self, base_url, playlist_id, playlist_title): @@ -389,8 +388,12 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): next_href, playlist_id, 'Downloading track page %s' % (i + 1)) collection = response['collection'] - if not collection: - break + + if not isinstance(collection, list): + collection = [] + + # Empty collection may be returned, in this case we proceed + # straight to next_href def resolve_permalink_url(candidates): for cand in candidates: @@ -429,7 +432,7 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE): (?:(?:www|m)\.)?soundcloud\.com/ (?P<user>[^/]+) (?:/ - (?P<rsrc>tracks|sets|reposts|likes|spotlight) + (?P<rsrc>tracks|albums|sets|reposts|likes|spotlight) )? /?(?:[?#].*)?$ ''' @@ -476,13 +479,17 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE): 'title': 'Grynpyret (Spotlight)', }, 'playlist_mincount': 1, + }, { + 'url': 'https://soundcloud.com/soft-cell-official/albums', + 'only_matching': True, }] _BASE_URL_MAP = { - 'all': '%s/profile/soundcloud:users:%%s' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'tracks': '%s/users/%%s/tracks' % SoundcloudPagedPlaylistBaseIE._API_BASE, + 'all': '%s/stream/users/%%s' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, + 'tracks': '%s/users/%%s/tracks' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, + 'albums': '%s/users/%%s/albums' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, 'sets': '%s/users/%%s/playlists' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'reposts': '%s/profile/soundcloud:users:%%s/reposts' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, + 'reposts': '%s/stream/users/%%s/reposts' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, 'likes': '%s/users/%%s/likes' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, 'spotlight': '%s/users/%%s/spotlight' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, } @@ -490,6 +497,7 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE): _TITLE_MAP = { 'all': 'All', 'tracks': 'Tracks', + 'albums': 'Albums', 'sets': 'Playlists', 'reposts': 'Reposts', 'likes': 'Likes', From b6423e6ca215e1583e013cf7b2c1faf8d3dcace7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 2 Feb 2019 04:11:32 +0700 Subject: [PATCH 516/558] [soundcloud:user] Update tests --- youtube_dl/extractor/soundcloud.py | 48 ++++++++++++++++-------------- 1 file changed, 26 insertions(+), 22 deletions(-) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 030840fd8..13463ae4f 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -438,40 +438,47 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE): ''' IE_NAME = 'soundcloud:user' _TESTS = [{ - 'url': 'https://soundcloud.com/the-akashic-chronicler', + 'url': 'https://soundcloud.com/soft-cell-official', 'info_dict': { - 'id': '114582580', - 'title': 'The Akashic Chronicler (All)', + 'id': '207965082', + 'title': 'Soft Cell (All)', }, - 'playlist_mincount': 74, + 'playlist_mincount': 28, }, { - 'url': 'https://soundcloud.com/the-akashic-chronicler/tracks', + 'url': 'https://soundcloud.com/soft-cell-official/tracks', 'info_dict': { - 'id': '114582580', - 'title': 'The Akashic Chronicler (Tracks)', + 'id': '207965082', + 'title': 'Soft Cell (Tracks)', }, - 'playlist_mincount': 37, + 'playlist_mincount': 27, }, { - 'url': 'https://soundcloud.com/the-akashic-chronicler/sets', + 'url': 'https://soundcloud.com/soft-cell-official/albums', 'info_dict': { - 'id': '114582580', - 'title': 'The Akashic Chronicler (Playlists)', + 'id': '207965082', + 'title': 'Soft Cell (Albums)', + }, + 'playlist_mincount': 1, + }, { + 'url': 'https://soundcloud.com/jcv246/sets', + 'info_dict': { + 'id': '12982173', + 'title': 'Jordi / cv (Playlists)', }, 'playlist_mincount': 2, }, { - 'url': 'https://soundcloud.com/the-akashic-chronicler/reposts', + 'url': 'https://soundcloud.com/jcv246/reposts', 'info_dict': { - 'id': '114582580', - 'title': 'The Akashic Chronicler (Reposts)', + 'id': '12982173', + 'title': 'Jordi / cv (Reposts)', }, - 'playlist_mincount': 7, + 'playlist_mincount': 6, }, { - 'url': 'https://soundcloud.com/the-akashic-chronicler/likes', + 'url': 'https://soundcloud.com/clalberg/likes', 'info_dict': { - 'id': '114582580', - 'title': 'The Akashic Chronicler (Likes)', + 'id': '11817582', + 'title': 'clalberg (Likes)', }, - 'playlist_mincount': 321, + 'playlist_mincount': 5, }, { 'url': 'https://soundcloud.com/grynpyret/spotlight', 'info_dict': { @@ -479,9 +486,6 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE): 'title': 'Grynpyret (Spotlight)', }, 'playlist_mincount': 1, - }, { - 'url': 'https://soundcloud.com/soft-cell-official/albums', - 'only_matching': True, }] _BASE_URL_MAP = { From e9fef7ee4e666b60bc7a757391f16e2be76f6cbb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 2 Feb 2019 05:44:31 +0700 Subject: [PATCH 517/558] [YoutubeDL] Fallback to ie_key of matching extractor while making download archive id when no explicit ie_key is provided (#19022) --- youtube_dl/YoutubeDL.py | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 80ed8d7e5..c168415ce 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -2060,15 +2060,21 @@ class YoutubeDL(object): self.report_warning('Unable to remove downloaded original file') def _make_archive_id(self, info_dict): + video_id = info_dict.get('id') + if not video_id: + return # Future-proof against any change in case # and backwards compatibility with prior versions - extractor = info_dict.get('extractor_key') + extractor = info_dict.get('extractor_key') or info_dict.get('ie_key') # key in a playlist if extractor is None: - if 'id' in info_dict: - extractor = info_dict.get('ie_key') # key in a playlist - if extractor is None: - return None # Incomplete video information - return extractor.lower() + ' ' + info_dict['id'] + # Try to find matching extractor for the URL and take its ie_key + for ie in self._ies: + if ie.suitable(info_dict['url']): + extractor = ie.ie_key() + break + else: + return + return extractor.lower() + ' ' + video_id def in_download_archive(self, info_dict): fn = self.params.get('download_archive') @@ -2076,7 +2082,7 @@ class YoutubeDL(object): return False vid_id = self._make_archive_id(info_dict) - if vid_id is None: + if not vid_id: return False # Incomplete video information try: From b9bc1cff721b6f63e733c6ababeec45b92f1484b Mon Sep 17 00:00:00 2001 From: JChris246 <43832407+JChris246@users.noreply.github.com> Date: Fri, 1 Feb 2019 19:04:00 -0400 Subject: [PATCH 518/558] [drtuber] Extract duration --- youtube_dl/extractor/drtuber.py | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py index 5c41c8022..2baea585b 100644 --- a/youtube_dl/extractor/drtuber.py +++ b/youtube_dl/extractor/drtuber.py @@ -4,7 +4,9 @@ import re from .common import InfoExtractor from ..utils import ( + int_or_none, NO_DEFAULT, + parse_duration, str_to_int, ) @@ -65,6 +67,9 @@ class DrTuberIE(InfoExtractor): }) self._sort_formats(formats) + duration = int_or_none(video_data.get('duration')) or parse_duration( + video_data.get('duration_format')) + title = self._html_search_regex( (r'<h1[^>]+class=["\']title[^>]+>([^<]+)', r'<title>([^<]+)\s*@\s+DrTuber', @@ -103,4 +108,5 @@ class DrTuberIE(InfoExtractor): 'comment_count': comment_count, 'categories': categories, 'age_limit': self._rta_search(webpage), + 'duration': duration, } From 6cc6e0c34d0f67747be7bac91690820f47b26acb Mon Sep 17 00:00:00 2001 From: Cory Hall <corydantehall@gmail.com> Date: Thu, 31 Jan 2019 20:51:37 -0500 Subject: [PATCH 519/558] [soundcloud:pagedplaylist] Add ie and title to entries (#19022) rel: https://github.com/rg3/youtube-dl/issues/19022 --- youtube_dl/extractor/soundcloud.py | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 13463ae4f..1c8d3c53b 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -395,18 +395,20 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): # Empty collection may be returned, in this case we proceed # straight to next_href - def resolve_permalink_url(candidates): - for cand in candidates: + def append_url_result(entries, item): + for cand in (item, item.get('track'), item.get('playlist')): if isinstance(cand, dict): permalink_url = cand.get('permalink_url') - entry_id = self._extract_id(cand) if permalink_url and permalink_url.startswith('http'): - return permalink_url, entry_id + return entries.append( + self.url_result( + permalink_url, + ie=SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None, + video_id=self._extract_id(cand), + video_title=cand.get('title'))) for e in collection: - permalink_url, entry_id = resolve_permalink_url((e, e.get('track'), e.get('playlist'))) - if permalink_url: - entries.append(self.url_result(permalink_url, video_id=entry_id)) + append_url_result(entries, e) next_href = response.get('next_href') if not next_href: From 7c5307f4c4e91ef6551d70cd844b93fbdc5c3cf0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 2 Feb 2019 23:40:06 +0700 Subject: [PATCH 520/558] [soundcloud:pagedplaylist] Improve (closes #19086) --- youtube_dl/extractor/soundcloud.py | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 1c8d3c53b..5536e7851 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -18,6 +18,7 @@ from ..utils import ( int_or_none, unified_strdate, update_url_query, + url_or_none, ) @@ -395,20 +396,23 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): # Empty collection may be returned, in this case we proceed # straight to next_href - def append_url_result(entries, item): - for cand in (item, item.get('track'), item.get('playlist')): - if isinstance(cand, dict): - permalink_url = cand.get('permalink_url') - if permalink_url and permalink_url.startswith('http'): - return entries.append( - self.url_result( - permalink_url, - ie=SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None, - video_id=self._extract_id(cand), - video_title=cand.get('title'))) + def resolve_entry(candidates): + for cand in candidates: + if not isinstance(cand, dict): + continue + permalink_url = url_or_none(cand.get('permalink_url')) + if not permalink_url: + continue + return self.url_result( + permalink_url, + ie=SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None, + video_id=self._extract_id(cand), + video_title=cand.get('title')) for e in collection: - append_url_result(entries, e) + entry = resolve_entry((e, e.get('track'), e.get('playlist'))) + if entry: + entries.append(entry) next_href = response.get('next_href') if not next_href: From 0efcb5a2fe0c3024d3e5affe74b3d0d416413ffa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 3 Feb 2019 00:33:45 +0700 Subject: [PATCH 521/558] [vporn] Remove extractor (closes #16276) Handled by generic extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/vporn.py | 123 ----------------------------- 2 files changed, 124 deletions(-) delete mode 100644 youtube_dl/extractor/vporn.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index b40be42e6..693c16e49 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1362,7 +1362,6 @@ from .voxmedia import ( VoxMediaVolumeIE, VoxMediaIE, ) -from .vporn import VpornIE from .vrt import VRTIE from .vrak import VrakIE from .vrv import ( diff --git a/youtube_dl/extractor/vporn.py b/youtube_dl/extractor/vporn.py deleted file mode 100644 index 858ac9e71..000000000 --- a/youtube_dl/extractor/vporn.py +++ /dev/null @@ -1,123 +0,0 @@ -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - parse_duration, - str_to_int, - urljoin, -) - - -class VpornIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?vporn\.com/[^/]+/(?P<display_id>[^/]+)/(?P<id>\d+)' - _TESTS = [ - { - 'url': 'http://www.vporn.com/masturbation/violet-on-her-th-birthday/497944/', - 'md5': 'facf37c1b86546fa0208058546842c55', - 'info_dict': { - 'id': '497944', - 'display_id': 'violet-on-her-th-birthday', - 'ext': 'mp4', - 'title': 'Violet on her 19th birthday', - 'description': 'Violet dances in front of the camera which is sure to get you horny.', - 'thumbnail': r're:^https?://.*\.jpg$', - 'uploader': 'kileyGrope', - 'categories': ['Masturbation', 'Teen'], - 'duration': 393, - 'age_limit': 18, - 'view_count': int, - }, - 'skip': 'video removed', - }, - { - 'url': 'http://www.vporn.com/female/hana-shower/523564/', - 'md5': 'ced35a4656198a1664cf2cda1575a25f', - 'info_dict': { - 'id': '523564', - 'display_id': 'hana-shower', - 'ext': 'mp4', - 'title': 'Hana Shower', - 'description': 'Hana showers at the bathroom.', - 'thumbnail': r're:^https?://.*\.jpg$', - 'uploader': 'Hmmmmm', - 'categories': ['Big Boobs', 'Erotic', 'Teen', 'Female', '720p'], - 'duration': 588, - 'age_limit': 18, - 'view_count': int, - } - }, - ] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - display_id = mobj.group('display_id') - - webpage = self._download_webpage(url, display_id) - - errmsg = 'This video has been deleted due to Copyright Infringement or by the account owner!' - if errmsg in webpage: - raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True) - - title = self._html_search_regex( - r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip() - description = self._html_search_regex( - r'class="(?:descr|description_txt)">(.*?)</div>', - webpage, 'description', fatal=False) - thumbnail = urljoin('http://www.vporn.com', self._html_search_regex( - r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description', - default=None)) - - uploader = self._html_search_regex( - r'(?s)Uploaded by:.*?<a href="/user/[^"]+"[^>]*>(.+?)</a>', - webpage, 'uploader', fatal=False) - - categories = re.findall(r'<a href="/cat/[^"]+"[^>]*>([^<]+)</a>', webpage) - - duration = parse_duration(self._search_regex( - r'Runtime:\s*</span>\s*(\d+ min \d+ sec)', - webpage, 'duration', fatal=False)) - - view_count = str_to_int(self._search_regex( - r'class="views">([\d,\.]+) [Vv]iews<', - webpage, 'view count', fatal=False)) - comment_count = str_to_int(self._html_search_regex( - r"'Comments \(([\d,\.]+)\)'", - webpage, 'comment count', default=None)) - - formats = [] - - for video in re.findall(r'flashvars\.videoUrl([^=]+?)\s*=\s*"(https?://[^"]+)"', webpage): - video_url = video[1] - fmt = { - 'url': video_url, - 'format_id': video[0], - } - m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)_(?P<vbr>\d+)k\.mp4$', video_url) - if m: - fmt.update({ - 'width': int(m.group('width')), - 'height': int(m.group('height')), - 'vbr': int(m.group('vbr')), - }) - formats.append(fmt) - - self._sort_formats(formats) - - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'uploader': uploader, - 'categories': categories, - 'duration': duration, - 'view_count': view_count, - 'comment_count': comment_count, - 'age_limit': 18, - 'formats': formats, - } From eecf788b90fa4d49567c714f5a613fdd2b6e2507 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 3 Feb 2019 09:10:09 +0100 Subject: [PATCH 522/558] [teachable] add support for courses.workitdaily.com (closes #18871) --- youtube_dl/extractor/teachable.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py index 47ac95ee8..c1a9deafe 100644 --- a/youtube_dl/extractor/teachable.py +++ b/youtube_dl/extractor/teachable.py @@ -27,6 +27,7 @@ class TeachableBaseIE(InfoExtractor): 'market.saleshacker.com': 'saleshacker', 'learnability.org': 'learnability', 'edurila.com': 'edurila', + 'courses.workitdaily.com': 'workitdaily', } _VALID_URL_SUB_TUPLE = (_URL_PREFIX, '|'.join(re.escape(site) for site in _SITES.keys())) From 07fbfef1c7e36b25dd7098be73ab76b87378a015 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 3 Feb 2019 12:10:41 +0100 Subject: [PATCH 523/558] [radiocanada] switch to the new media requests(closes #19115) --- youtube_dl/extractor/radiocanada.py | 133 ++++++++-------------------- 1 file changed, 39 insertions(+), 94 deletions(-) diff --git a/youtube_dl/extractor/radiocanada.py b/youtube_dl/extractor/radiocanada.py index 302f67d96..58e294892 100644 --- a/youtube_dl/extractor/radiocanada.py +++ b/youtube_dl/extractor/radiocanada.py @@ -5,14 +5,10 @@ import re from .common import InfoExtractor from ..utils import ( - xpath_text, - find_xpath_attr, determine_ext, + ExtractorError, int_or_none, unified_strdate, - xpath_element, - ExtractorError, - determine_protocol, unsmuggle_url, ) @@ -61,107 +57,53 @@ class RadioCanadaIE(InfoExtractor): 'only_matching': True, } ] + _GEO_COUNTRIES = ['CA'] + + def _call_api(self, path, video_id, app_code, query): + query.update({ + 'appCode': app_code, + 'idMedia': video_id, + 'output': 'json', + }) + return self._download_json( + 'https://services.radio-canada.ca/media/' + path, video_id, headers={ + 'Authorization': 'Client-Key 773aea60-0e80-41bb-9c7f-e6d7c3ad17fb' + }, query=query) def _real_extract(self, url): url, smuggled_data = unsmuggle_url(url, {}) app_code, video_id = re.match(self._VALID_URL, url).groups() - metadata = self._download_xml( - 'http://api.radio-canada.ca/metaMedia/v1/index.ashx', - video_id, note='Downloading metadata XML', query={ - 'appCode': app_code, - 'idMedia': video_id, - }) + metas = self._call_api('meta/v1/index.ashx', video_id, app_code, {})['Metas'] def get_meta(name): - el = find_xpath_attr(metadata, './/Meta', 'name', name) - return el.text if el is not None else None + for meta in metas: + if meta.get('name') == name: + text = meta.get('text') + if text: + return text # protectionType does not necessarily mean the video is DRM protected (see # https://github.com/rg3/youtube-dl/pull/18609). if get_meta('protectionType'): self.report_warning('This video is probably DRM protected.') - device_types = ['ipad'] - if not smuggled_data: - device_types.append('flash') - device_types.append('android') - - formats = [] - error = None - # TODO: extract f4m formats - # f4m formats can be extracted using flashhd device_type but they produce unplayable file - for device_type in device_types: - validation_url = 'http://api.radio-canada.ca/validationMedia/v1/Validation.ashx' - query = { - 'appCode': app_code, - 'idMedia': video_id, - 'connectionType': 'broadband', - 'multibitrate': 'true', - 'deviceType': device_type, - } - if smuggled_data: - validation_url = 'https://services.radio-canada.ca/media/validation/v2/' - query.update(smuggled_data) - else: - query.update({ - # paysJ391wsHjbOJwvCs26toz and bypasslock are used to bypass geo-restriction - 'paysJ391wsHjbOJwvCs26toz': 'CA', - 'bypasslock': 'NZt5K62gRqfc', - }) - v_data = self._download_xml(validation_url, video_id, note='Downloading %s XML' % device_type, query=query, fatal=False) - v_url = xpath_text(v_data, 'url') - if not v_url: - continue - if v_url == 'null': - error = xpath_text(v_data, 'message') - continue - ext = determine_ext(v_url) - if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - v_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) - elif ext == 'f4m': - formats.extend(self._extract_f4m_formats( - v_url, video_id, f4m_id='hds', fatal=False)) - else: - ext = determine_ext(v_url) - bitrates = xpath_element(v_data, 'bitrates') - for url_e in bitrates.findall('url'): - tbr = int_or_none(url_e.get('bitrate')) - if not tbr: - continue - f_url = re.sub(r'\d+\.%s' % ext, '%d.%s' % (tbr, ext), v_url) - protocol = determine_protocol({'url': f_url}) - f = { - 'format_id': '%s-%d' % (protocol, tbr), - 'url': f_url, - 'ext': 'flv' if protocol == 'rtmp' else ext, - 'protocol': protocol, - 'width': int_or_none(url_e.get('width')), - 'height': int_or_none(url_e.get('height')), - 'tbr': tbr, - } - mobj = re.match(r'(?P<url>rtmp://[^/]+/[^/]+)/(?P<playpath>[^?]+)(?P<auth>\?.+)', f_url) - if mobj: - f.update({ - 'url': mobj.group('url') + mobj.group('auth'), - 'play_path': mobj.group('playpath'), - }) - formats.append(f) - if protocol == 'rtsp': - base_url = self._search_regex( - r'rtsp://([^?]+)', f_url, 'base url', default=None) - if base_url: - base_url = 'http://' + base_url - formats.extend(self._extract_m3u8_formats( - base_url + '/playlist.m3u8', video_id, 'mp4', - 'm3u8_native', m3u8_id='hls', fatal=False)) - formats.extend(self._extract_f4m_formats( - base_url + '/manifest.f4m', video_id, - f4m_id='hds', fatal=False)) - if not formats and error: + query = { + 'connectionType': 'hd', + 'deviceType': 'ipad', + 'multibitrate': 'true', + } + if smuggled_data: + query.update(smuggled_data) + v_data = self._call_api('validation/v2/', video_id, app_code, query) + v_url = v_data.get('url') + if not v_url: + error = v_data['message'] + if error == "Le contenu sélectionné n'est pas disponible dans votre pays": + raise self.raise_geo_restricted(error, self._GEO_COUNTRIES) raise ExtractorError( '%s said: %s' % (self.IE_NAME, error), expected=True) + formats = self._extract_m3u8_formats(v_url, video_id, 'mp4') self._sort_formats(formats) subtitles = {} @@ -189,8 +131,8 @@ class RadioCanadaIE(InfoExtractor): class RadioCanadaAudioVideoIE(InfoExtractor): 'radiocanada:audiovideo' - _VALID_URL = r'https?://ici\.radio-canada\.ca/audio-video/media-(?P<id>[0-9]+)' - _TEST = { + _VALID_URL = r'https?://ici\.radio-canada\.ca/([^/]+/)*media-(?P<id>[0-9]+)' + _TESTS = [{ 'url': 'http://ici.radio-canada.ca/audio-video/media-7527184/barack-obama-au-vietnam', 'info_dict': { 'id': '7527184', @@ -203,7 +145,10 @@ class RadioCanadaAudioVideoIE(InfoExtractor): # m3u8 download 'skip_download': True, }, - } + }, { + 'url': 'https://ici.radio-canada.ca/info/videos/media-7527184/barack-obama-au-vietnam', + 'only_matching': True, + }] def _real_extract(self, url): return self.url_result('radiocanada:medianet:%s' % self._match_id(url)) From 70c3ee13671798d7e3b80ea9be863ef73bd08653 Mon Sep 17 00:00:00 2001 From: JChris246 <43832407+JChris246@users.noreply.github.com> Date: Mon, 4 Feb 2019 13:06:04 -0400 Subject: [PATCH 524/558] [pornhd] Extract like count --- youtube_dl/extractor/pornhd.py | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py index b52879c7a..a079cd32a 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -23,6 +23,7 @@ class PornHdIE(InfoExtractor): 'description': 'md5:3748420395e03e31ac96857a8f125b2b', 'thumbnail': r're:^https?://.*\.jpg', 'view_count': int, + 'like_count': int, 'age_limit': 18, } }, { @@ -37,6 +38,7 @@ class PornHdIE(InfoExtractor): 'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294', 'thumbnail': r're:^https?://.*\.jpg', 'view_count': int, + 'like_count': int, 'age_limit': 18, }, 'skip': 'Not available anymore', @@ -85,6 +87,11 @@ class PornHdIE(InfoExtractor): r"poster'?\s*:\s*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage, 'thumbnail', fatal=False, group='url') + like_count = int_or_none(self._search_regex( + (r'(\d+)\s*</11[^>]+>(?: |\s)*\blikes', + r'class=["\']save-count["\'][^>]*>\s*(\d+)'), + webpage, 'like count', fatal=False)) + return { 'id': video_id, 'display_id': display_id, @@ -92,6 +99,7 @@ class PornHdIE(InfoExtractor): 'description': description, 'thumbnail': thumbnail, 'view_count': view_count, + 'like_count': like_count, 'formats': formats, 'age_limit': 18, } From 48fb963b2f9495922a4acf751608167cbc273693 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 5 Feb 2019 00:07:37 +0700 Subject: [PATCH 525/558] [pornhd] Fix formats extraction --- youtube_dl/extractor/pornhd.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py index a079cd32a..27d65d4b9 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -4,9 +4,11 @@ import re from .common import InfoExtractor from ..utils import ( + determine_ext, ExtractorError, int_or_none, js_to_json, + urljoin, ) @@ -14,7 +16,7 @@ class PornHdIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?' _TESTS = [{ 'url': 'http://www.pornhd.com/videos/9864/selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video', - 'md5': 'c8b964b1f0a4b5f7f28ae3a5c9f86ad5', + 'md5': '87f1540746c1d32ec7a2305c12b96b25', 'info_dict': { 'id': '9864', 'display_id': 'selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video', @@ -67,12 +69,14 @@ class PornHdIE(InfoExtractor): formats = [] for format_id, video_url in sources.items(): + video_url = urljoin(url, video_url) if not video_url: continue height = int_or_none(self._search_regex( r'^(\d+)[pP]', format_id, 'height', default=None)) formats.append({ 'url': video_url, + 'ext': determine_ext(video_url, 'mp4'), 'format_id': format_id, 'height': height, }) From d2d970d07ec82f648b62bff8b15ac0b57d0d0496 Mon Sep 17 00:00:00 2001 From: JChris246 <chris.401@live.com> Date: Mon, 4 Feb 2019 13:33:54 -0400 Subject: [PATCH 526/558] [pornhub] Fix tags and categories extraction (closes #13720) --- youtube_dl/extractor/pornhub.py | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index be93d5d48..428324ef0 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -16,7 +16,6 @@ from .openload import PhantomJSwrapper from ..utils import ( ExtractorError, int_or_none, - js_to_json, orderedSet, remove_quotes, str_to_int, @@ -303,14 +302,17 @@ class PornHubIE(PornHubBaseIE): comment_count = self._extract_count( r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment') - page_params = self._parse_json(self._search_regex( - r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})', - webpage, 'page parameters', group='data', default='{}'), - video_id, transform_source=js_to_json, fatal=False) - tags = categories = None - if page_params: - tags = page_params.get('tags', '').split(',') - categories = page_params.get('categories', '').split(',') + def _get_items(class_name): + div = self._search_regex( + r'<div class="' + class_name + '">([\S\s]+?)</div>', + webpage, class_name, default=None) + if div: + return [a for a in re.findall(r'<a href=[^>]+>([^<]+)', div)] + else: + return None + + categories = _get_items('categoriesWrapper') + tags = _get_items('tagsWrapper') return { 'id': video_id, From 5dda1edef93d94c9a49672f905df0c49c75c5739 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 5 Feb 2019 23:06:55 +0700 Subject: [PATCH 527/558] [pornhub] Improve and simplify (closes #19135) --- youtube_dl/extractor/pornhub.py | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 428324ef0..641083da7 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -302,17 +302,12 @@ class PornHubIE(PornHubBaseIE): comment_count = self._extract_count( r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment') - def _get_items(class_name): + def extract_list(meta_key): div = self._search_regex( - r'<div class="' + class_name + '">([\S\s]+?)</div>', - webpage, class_name, default=None) + r'(?s)<div[^>]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)</div>' + % meta_key, webpage, meta_key, default=None) if div: - return [a for a in re.findall(r'<a href=[^>]+>([^<]+)', div)] - else: - return None - - categories = _get_items('categoriesWrapper') - tags = _get_items('tagsWrapper') + return re.findall(r'<a[^>]+\bhref=[^>]+>([^<]+)', div) return { 'id': video_id, @@ -327,8 +322,8 @@ class PornHubIE(PornHubBaseIE): 'comment_count': comment_count, 'formats': formats, 'age_limit': 18, - 'tags': tags, - 'categories': categories, + 'tags': extract_list('tags'), + 'categories': extract_list('categories'), 'subtitles': subtitles, } From 8fecc7353df35f6cac305c04a4e203fb2bbb4827 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 6 Feb 2019 13:59:12 +0100 Subject: [PATCH 528/558] [toutv] fix authentication(closes #16398)(closes #18700) --- youtube_dl/extractor/radiocanada.py | 47 +++++++++++++++++--------- youtube_dl/extractor/toutv.py | 51 +++++++++-------------------- 2 files changed, 47 insertions(+), 51 deletions(-) diff --git a/youtube_dl/extractor/radiocanada.py b/youtube_dl/extractor/radiocanada.py index 58e294892..dd95f99f2 100644 --- a/youtube_dl/extractor/radiocanada.py +++ b/youtube_dl/extractor/radiocanada.py @@ -4,12 +4,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_HTTPError from ..utils import ( determine_ext, ExtractorError, int_or_none, unified_strdate, - unsmuggle_url, ) @@ -58,23 +58,35 @@ class RadioCanadaIE(InfoExtractor): } ] _GEO_COUNTRIES = ['CA'] + _access_token = None + _claims = None - def _call_api(self, path, video_id, app_code, query): + def _call_api(self, path, video_id=None, app_code=None, query=None): + if not query: + query = {} query.update({ - 'appCode': app_code, - 'idMedia': video_id, + 'client_key': '773aea60-0e80-41bb-9c7f-e6d7c3ad17fb', 'output': 'json', }) - return self._download_json( - 'https://services.radio-canada.ca/media/' + path, video_id, headers={ - 'Authorization': 'Client-Key 773aea60-0e80-41bb-9c7f-e6d7c3ad17fb' - }, query=query) + if video_id: + query.update({ + 'appCode': app_code, + 'idMedia': video_id, + }) + if self._access_token: + query['access_token'] = self._access_token + try: + return self._download_json( + 'https://services.radio-canada.ca/media/' + path, video_id, query=query) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 422): + data = self._parse_json(e.cause.read().decode(), None) + error = data.get('error_description') or data['errorMessage']['text'] + raise ExtractorError(error, expected=True) + raise - def _real_extract(self, url): - url, smuggled_data = unsmuggle_url(url, {}) - app_code, video_id = re.match(self._VALID_URL, url).groups() - - metas = self._call_api('meta/v1/index.ashx', video_id, app_code, {})['Metas'] + def _extract_info(self, app_code, video_id): + metas = self._call_api('meta/v1/index.ashx', video_id, app_code)['Metas'] def get_meta(name): for meta in metas: @@ -93,14 +105,16 @@ class RadioCanadaIE(InfoExtractor): 'deviceType': 'ipad', 'multibitrate': 'true', } - if smuggled_data: - query.update(smuggled_data) + if self._claims: + query['claims'] = self._claims v_data = self._call_api('validation/v2/', video_id, app_code, query) v_url = v_data.get('url') if not v_url: error = v_data['message'] if error == "Le contenu sélectionné n'est pas disponible dans votre pays": raise self.raise_geo_restricted(error, self._GEO_COUNTRIES) + if error == 'Le contenu sélectionné est disponible seulement en premium': + self.raise_login_required(error) raise ExtractorError( '%s said: %s' % (self.IE_NAME, error), expected=True) formats = self._extract_m3u8_formats(v_url, video_id, 'mp4') @@ -128,6 +142,9 @@ class RadioCanadaIE(InfoExtractor): 'formats': formats, } + def _real_extract(self, url): + return self._extract_info(*re.match(self._VALID_URL, url).groups()) + class RadioCanadaAudioVideoIE(InfoExtractor): 'radiocanada:audiovideo' diff --git a/youtube_dl/extractor/toutv.py b/youtube_dl/extractor/toutv.py index 2e7876cc5..f1ab91cf2 100644 --- a/youtube_dl/extractor/toutv.py +++ b/youtube_dl/extractor/toutv.py @@ -3,22 +3,19 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor +from .radiocanada import RadioCanadaIE from ..utils import ( - int_or_none, - js_to_json, - urlencode_postdata, extract_attributes, - smuggle_url, + int_or_none, + merge_dicts, + urlencode_postdata, ) -class TouTvIE(InfoExtractor): +class TouTvIE(RadioCanadaIE): _NETRC_MACHINE = 'toutv' IE_NAME = 'tou.tv' _VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/S[0-9]+[EC][0-9]+)?)' - _access_token = None - _claims = None _TESTS = [{ 'url': 'http://ici.tou.tv/garfield-tout-court/S2015E17', @@ -46,18 +43,14 @@ class TouTvIE(InfoExtractor): email, password = self._get_login_info() if email is None: return - state = 'http://ici.tou.tv/' - webpage = self._download_webpage(state, None, 'Downloading homepage') - toutvlogin = self._parse_json(self._search_regex( - r'(?s)toutvlogin\s*=\s*({.+?});', webpage, 'toutvlogin'), None, js_to_json) - authorize_url = toutvlogin['host'] + '/auth/oauth/v2/authorize' login_webpage = self._download_webpage( - authorize_url, None, 'Downloading login page', query={ - 'client_id': toutvlogin['clientId'], - 'redirect_uri': 'https://ici.tou.tv/login/loginCallback', + 'https://services.radio-canada.ca/auth/oauth/v2/authorize', + None, 'Downloading login page', query={ + 'client_id': '4dd36440-09d5-4468-8923-b6d91174ad36', + 'redirect_uri': 'https://ici.tou.tv/logincallback', 'response_type': 'token', - 'scope': 'media-drmt openid profile email id.write media-validation.read.privileged', - 'state': state, + 'scope': 'id.write media-validation.read', + 'state': '/', }) def extract_form_url_and_data(wp, default_form_url, form_spec_re=''): @@ -86,12 +79,7 @@ class TouTvIE(InfoExtractor): self._access_token = self._search_regex( r'access_token=([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})', urlh.geturl(), 'access token') - self._claims = self._download_json( - 'https://services.radio-canada.ca/media/validation/v2/getClaims', - None, 'Extracting Claims', query={ - 'token': self._access_token, - 'access_token': self._access_token, - })['claims'] + self._claims = self._call_api('validation/v2/getClaims')['claims'] def _real_extract(self, url): path = self._match_id(url) @@ -102,19 +90,10 @@ class TouTvIE(InfoExtractor): self.report_warning('This video is probably DRM protected.', path) video_id = metadata['IdMedia'] details = metadata['Details'] - title = details['OriginalTitle'] - video_url = 'radiocanada:%s:%s' % (metadata.get('AppCode', 'toutv'), video_id) - if self._access_token and self._claims: - video_url = smuggle_url(video_url, { - 'access_token': self._access_token, - 'claims': self._claims, - }) - return { - '_type': 'url_transparent', - 'url': video_url, + return merge_dicts({ 'id': video_id, - 'title': title, + 'title': details.get('OriginalTitle'), 'thumbnail': details.get('ImageUrl'), 'duration': int_or_none(details.get('LengthInSeconds')), - } + }, self._extract_info(metadata.get('AppCode', 'toutv'), video_id)) From 241c5d7d384dcb01a62702274cfbead01f537145 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 6 Feb 2019 19:38:10 +0100 Subject: [PATCH 529/558] [trutv] fix extraction(closes #17336) --- youtube_dl/extractor/trutv.py | 84 +++++++++++++++++++++++------------ 1 file changed, 56 insertions(+), 28 deletions(-) diff --git a/youtube_dl/extractor/trutv.py b/youtube_dl/extractor/trutv.py index 3a5782525..ce892c8c5 100644 --- a/youtube_dl/extractor/trutv.py +++ b/youtube_dl/extractor/trutv.py @@ -4,44 +4,72 @@ from __future__ import unicode_literals import re from .turner import TurnerBaseIE +from ..utils import ( + int_or_none, + parse_iso8601, +) class TruTVIE(TurnerBaseIE): - _VALID_URL = r'https?://(?:www\.)?trutv\.com(?:(?P<path>/shows/[^/]+/videos/[^/?#]+?)\.html|/full-episodes/[^/]+/(?P<id>\d+))' + _VALID_URL = r'https?://(?:www\.)?trutv\.com/(?:shows|full-episodes)/(?P<series_slug>[0-9A-Za-z-]+)/(?:videos/(?P<clip_slug>[0-9A-Za-z-]+)|(?P<id>\d+))' _TEST = { - 'url': 'http://www.trutv.com/shows/10-things/videos/you-wont-believe-these-sports-bets.html', - 'md5': '2cdc844f317579fed1a7251b087ff417', + 'url': 'https://www.trutv.com/shows/the-carbonaro-effect/videos/sunlight-activated-flower.html', 'info_dict': { - 'id': '/shows/10-things/videos/you-wont-believe-these-sports-bets', + 'id': 'f16c03beec1e84cd7d1a51f11d8fcc29124cc7f1', 'ext': 'mp4', - 'title': 'You Won\'t Believe These Sports Bets', - 'description': 'Jamie Lee sits down with a bookie to discuss the bizarre world of illegal sports betting.', - 'upload_date': '20130305', - } + 'title': 'Sunlight-Activated Flower', + 'description': "A customer is stunned when he sees Michael's sunlight-activated flower.", + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, } def _real_extract(self, url): - path, video_id = re.match(self._VALID_URL, url).groups() - auth_required = False - if path: - data_src = 'http://www.trutv.com/video/cvp/v2/xml/content.xml?id=%s.xml' % path + series_slug, clip_slug, video_id = re.match(self._VALID_URL, url).groups() + + if video_id: + path = 'episode' + display_id = video_id else: - webpage = self._download_webpage(url, video_id) - video_id = self._search_regex( - r"TTV\.TVE\.episodeId\s*=\s*'([^']+)';", - webpage, 'video id', default=video_id) - auth_required = self._search_regex( - r'TTV\.TVE\.authRequired\s*=\s*(true|false);', - webpage, 'auth required', default='false') == 'true' - data_src = 'http://www.trutv.com/tveverywhere/services/cvpXML.do?titleId=' + video_id - return self._extract_cvp_info( - data_src, path, { - 'secure': { - 'media_src': 'http://androidhls-secure.cdn.turner.com/trutv/big', - 'tokenizer_src': 'http://www.trutv.com/tveverywhere/processors/services/token_ipadAdobe.do', - }, - }, { + path = 'series/clip' + display_id = clip_slug + + data = self._download_json( + 'https://api.trutv.com/v2/web/%s/%s/%s' % (path, series_slug, display_id), + display_id) + video_data = data['episode'] if video_id else data['info'] + media_id = video_data['mediaId'] + title = video_data['title'].strip() + + info = self._extract_ngtv_info( + media_id, {}, { 'url': url, 'site_name': 'truTV', - 'auth_required': auth_required, + 'auth_required': video_data.get('isAuthRequired'), }) + + thumbnails = [] + for image in video_data.get('images', []): + image_url = image.get('srcUrl') + if not image_url: + continue + thumbnails.append({ + 'url': image_url, + 'width': int_or_none(image.get('width')), + 'height': int_or_none(image.get('height')), + }) + + info.update({ + 'id': media_id, + 'display_id': display_id, + 'title': title, + 'description': video_data.get('description'), + 'thumbnails': thumbnails, + 'timestamp': parse_iso8601(video_data.get('publicationDate')), + 'series': video_data.get('showTitle'), + 'season_number': int_or_none(video_data.get('seasonNum')), + 'episode_number': int_or_none(video_data.get('episodeNum')), + }) + return info From f06a1cabe8b3831b5f2ff3bc27f5e7336c597e92 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 7 Feb 2019 23:57:58 +0700 Subject: [PATCH 530/558] [spankbang] Extend _VALID_URL --- youtube_dl/extractor/spankbang.py | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/spankbang.py b/youtube_dl/extractor/spankbang.py index 67500b69c..e48cfff71 100644 --- a/youtube_dl/extractor/spankbang.py +++ b/youtube_dl/extractor/spankbang.py @@ -12,7 +12,7 @@ from ..utils import ( class SpankBangIE(InfoExtractor): - _VALID_URL = r'https?://(?:(?:www|m|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video' + _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)' _TESTS = [{ 'url': 'http://spankbang.com/3vvn/video/fantasy+solo', 'md5': '1cc433e1d6aa14bc376535b8679302f7', @@ -41,13 +41,22 @@ class SpankBangIE(InfoExtractor): # 4k 'url': 'https://spankbang.com/1vwqx/video/jade+kush+solo+4k', 'only_matching': True, + }, { + 'url': 'https://m.spankbang.com/3vvn/play/fantasy+solo/480p/', + 'only_matching': True, + }, { + 'url': 'https://m.spankbang.com/3vvn/play', + 'only_matching': True, + }, { + 'url': 'https://spankbang.com/2y3td/embed/', + 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id, headers={ - 'Cookie': 'country=US' - }) + webpage = self._download_webpage( + url.replace('/%s/embed' % video_id, '/%s/video' % video_id), + video_id, headers={'Cookie': 'country=US'}) if re.search(r'<[^>]+\bid=["\']video_removed', webpage): raise ExtractorError( From 49bd993fd9adbcf6b5c11a7ec11c2b4a552e49c5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 8 Feb 2019 00:09:50 +0700 Subject: [PATCH 531/558] [spankbang:playlist] Add extractor (closes #19145) --- youtube_dl/extractor/extractors.py | 5 ++++- youtube_dl/extractor/spankbang.py | 33 +++++++++++++++++++++++++++++- 2 files changed, 36 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 693c16e49..d7685cd87 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1058,7 +1058,10 @@ from .southpark import ( SouthParkEsIE, SouthParkNlIE ) -from .spankbang import SpankBangIE +from .spankbang import ( + SpankBangIE, + SpankBangPlaylistIE, +) from .spankwire import SpankwireIE from .spiegel import SpiegelIE, SpiegelArticleIE from .spiegeltv import SpiegeltvIE diff --git a/youtube_dl/extractor/spankbang.py b/youtube_dl/extractor/spankbang.py index e48cfff71..fbe6ef31a 100644 --- a/youtube_dl/extractor/spankbang.py +++ b/youtube_dl/extractor/spankbang.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from ..utils import ( ExtractorError, + orderedSet, parse_duration, parse_resolution, str_to_int, @@ -12,7 +13,7 @@ from ..utils import ( class SpankBangIE(InfoExtractor): - _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)' + _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)\b' _TESTS = [{ 'url': 'http://spankbang.com/3vvn/video/fantasy+solo', 'md5': '1cc433e1d6aa14bc376535b8679302f7', @@ -103,3 +104,33 @@ class SpankBangIE(InfoExtractor): 'formats': formats, 'age_limit': age_limit, } + + +class SpankBangPlaylistIE(InfoExtractor): + _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/[^/]+' + _TEST = { + 'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties', + 'info_dict': { + 'id': 'ug0k', + 'title': 'Big Ass Titties', + }, + 'playlist_mincount': 50, + } + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage( + url, playlist_id, headers={'Cookie': 'country=US; mobile=on'}) + + entries = [self.url_result( + 'https://spankbang.com/%s/video' % video_id, + ie=SpankBangIE.ie_key(), video_id=video_id) + for video_id in orderedSet(re.findall( + r'<a[^>]+\bhref=["\']/?([\da-z]+)/play/', webpage))] + + title = self._html_search_regex( + r'<h1>([^<]+)\s+playlist</h1>', webpage, 'playlist title', + fatal=False) + + return self.playlist_result(entries, playlist_id, title) From 22f5f5c6fcd2d7f0c9f1ff3019fe0b957b771f44 Mon Sep 17 00:00:00 2001 From: Ales Jirasek <schunkac@gmail.com> Date: Wed, 10 Oct 2018 23:47:21 +0200 Subject: [PATCH 532/558] [malltv] Add extractor (closes #18058) --- test/test_InfoExtractor.py | 2 ++ youtube_dl/extractor/common.py | 2 +- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/malltv.py | 58 ++++++++++++++++++++++++++++++ youtube_dl/utils.py | 2 +- 5 files changed, 63 insertions(+), 2 deletions(-) create mode 100644 youtube_dl/extractor/malltv.py diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py index 75fa0bbb7..f0aa8466b 100644 --- a/test/test_InfoExtractor.py +++ b/test/test_InfoExtractor.py @@ -61,6 +61,7 @@ class TestInfoExtractor(unittest.TestCase): <meta content='Foo' property=og:foobar> <meta name="og:test1" content='foo > < bar'/> <meta name="og:test2" content="foo >//< bar"/> + <meta property=og-test3 content='Ill-formatted opengraph'/> ''' self.assertEqual(ie._og_search_title(html), 'Foo') self.assertEqual(ie._og_search_description(html), 'Some video\'s description ') @@ -69,6 +70,7 @@ class TestInfoExtractor(unittest.TestCase): self.assertEqual(ie._og_search_property('foobar', html), 'Foo') self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar') self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar') + self.assertEqual(ie._og_search_property('test3', html), 'Ill-formatted opengraph') self.assertEqual(ie._og_search_property(('test0', 'test1'), html), 'foo > < bar') self.assertRaises(RegexNotFoundError, ie._og_search_property, 'test0', html, None, fatal=True) self.assertRaises(RegexNotFoundError, ie._og_search_property, ('test0', 'test00'), html, None, fatal=True) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index c4ea2882f..c3b0586a0 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1058,7 +1058,7 @@ class InfoExtractor(object): @staticmethod def _og_regexes(prop): content_re = r'content=(?:"([^"]+?)"|\'([^\']+?)\'|\s*([^\s"\'=<>`]+?))' - property_re = (r'(?:name|property)=(?:\'og:%(prop)s\'|"og:%(prop)s"|\s*og:%(prop)s\b)' + property_re = (r'(?:name|property)=(?:\'og[:-]%(prop)s\'|"og[:-]%(prop)s"|\s*og[:-]%(prop)s\b)' % {'prop': re.escape(prop)}) template = r'<meta[^>]+?%s[^>]+?%s' return [ diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index d7685cd87..f212b5116 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -619,6 +619,7 @@ from .mailru import ( MailRuMusicSearchIE, ) from .makertv import MakerTVIE +from .malltv import MallTVIE from .mangomolo import ( MangomoloVideoIE, MangomoloLiveIE, diff --git a/youtube_dl/extractor/malltv.py b/youtube_dl/extractor/malltv.py new file mode 100644 index 000000000..7e0876ecc --- /dev/null +++ b/youtube_dl/extractor/malltv.py @@ -0,0 +1,58 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +from .common import InfoExtractor +from ..utils import parse_duration, merge_dicts + + +class MallTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?mall\.tv/(?:.+/)?(?P<id>.+)(?:\?.*$|$)' + _TESTS = [ + { + 'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', + 'md5': '9ced0de056534410837077e23bfba796', + 'info_dict': { + 'id': 't0zzt0', + 'ext': 'mp4', + 'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?', + 'description': 'Pokud někdo hospodaří s penězmi daňových poplatníků, pak logicky chceme vědět, jak s nimi nakládá. Objem dotací pro neziskovky roste, ale opravdu jsou tyto organizace „pijavice", jak o nich hovoří And', + 'upload_date': '20181007', + 'timestamp': 1538870400 + } + }, + { + 'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', + 'md5': '9ced0de056534410837077e23bfba796', + 'only_matching': 1, + 'info_dict': { + 'id': 't0zzt0', + 'ext': 'mp4', + 'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?', + 'description': 'Pokud někdo hospodaří s penězmi daňových poplatníků, pak logicky chceme vědět, jak s nimi nakládá. Objem dotací pro neziskovky roste, ale opravdu jsou tyto organizace „pijavice", jak o nich hovoří And', + 'upload_date': '20181007', + 'timestamp': 1538870400 + } + } + ] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + src_id_regex = r'(?P<src><source src=([\"\'])?.+?/(?P<id>\w{6,}?)/index)(?P<after>\1?[^>]*?>)' + video_id = self._search_regex(src_id_regex, webpage, 'ID', + group='id') + info = self._search_json_ld(webpage, video_id, default={}) + html = re.sub(src_id_regex, r'\g<src>.m3u8\g<after>', webpage) + media = self._parse_html5_media_entries(url, html, video_id) + thumbnail = info.get('thumbnail', self._og_search_thumbnail(webpage)) + duration = parse_duration(info.get('duration')) + result = { + 'id': video_id, + 'title': info.get('title', self._og_search_title(webpage)), + 'description': self._og_search_description(webpage) + } + result.update({'thumbnail': thumbnail}) + result.update({'duration': duration}) + + return merge_dicts(media[0], info, result) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index d0cb65814..f5a0bb4b0 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -184,7 +184,7 @@ DATE_FORMATS_MONTH_FIRST.extend([ ]) PACKED_CODES_RE = r"}\('(.+)',(\d+),(\d+),'([^']+)'\.split\('\|'\)" -JSON_LD_RE = r'(?is)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>' +JSON_LD_RE = r'(?is)<script[^>]+type=(["\']?)application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>' def preferredencoding(): From 4de3cb883c61eeec56d8d271375a0624d481ad37 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 8 Feb 2019 00:43:10 +0700 Subject: [PATCH 533/558] [malltv] Fix issues and simplify (closes #17856) --- youtube_dl/extractor/malltv.py | 85 ++++++++++++++++------------------ 1 file changed, 40 insertions(+), 45 deletions(-) diff --git a/youtube_dl/extractor/malltv.py b/youtube_dl/extractor/malltv.py index 7e0876ecc..e13c2e11a 100644 --- a/youtube_dl/extractor/malltv.py +++ b/youtube_dl/extractor/malltv.py @@ -2,57 +2,52 @@ from __future__ import unicode_literals import re + from .common import InfoExtractor -from ..utils import parse_duration, merge_dicts +from ..utils import merge_dicts class MallTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?mall\.tv/(?:.+/)?(?P<id>.+)(?:\?.*$|$)' - _TESTS = [ - { - 'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', - 'md5': '9ced0de056534410837077e23bfba796', - 'info_dict': { - 'id': 't0zzt0', - 'ext': 'mp4', - 'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?', - 'description': 'Pokud někdo hospodaří s penězmi daňových poplatníků, pak logicky chceme vědět, jak s nimi nakládá. Objem dotací pro neziskovky roste, ale opravdu jsou tyto organizace „pijavice", jak o nich hovoří And', - 'upload_date': '20181007', - 'timestamp': 1538870400 - } - }, - { - 'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', - 'md5': '9ced0de056534410837077e23bfba796', - 'only_matching': 1, - 'info_dict': { - 'id': 't0zzt0', - 'ext': 'mp4', - 'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?', - 'description': 'Pokud někdo hospodaří s penězmi daňových poplatníků, pak logicky chceme vědět, jak s nimi nakládá. Objem dotací pro neziskovky roste, ale opravdu jsou tyto organizace „pijavice", jak o nich hovoří And', - 'upload_date': '20181007', - 'timestamp': 1538870400 - } + _VALID_URL = r'https?://(?:www\.)?mall\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)' + _TESTS = [{ + 'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', + 'md5': '1c4a37f080e1f3023103a7b43458e518', + 'info_dict': { + 'id': 't0zzt0', + 'display_id': '18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', + 'ext': 'mp4', + 'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?', + 'description': 'md5:25fc0ec42a72ba602b602c683fa29deb', + 'duration': 216, + 'timestamp': 1538870400, + 'upload_date': '20181007', + 'view_count': int, } - ] + }, { + 'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', + 'only_matching': True, + }] def _real_extract(self, url): display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - src_id_regex = r'(?P<src><source src=([\"\'])?.+?/(?P<id>\w{6,}?)/index)(?P<after>\1?[^>]*?>)' - video_id = self._search_regex(src_id_regex, webpage, 'ID', - group='id') - info = self._search_json_ld(webpage, video_id, default={}) - html = re.sub(src_id_regex, r'\g<src>.m3u8\g<after>', webpage) - media = self._parse_html5_media_entries(url, html, video_id) - thumbnail = info.get('thumbnail', self._og_search_thumbnail(webpage)) - duration = parse_duration(info.get('duration')) - result = { - 'id': video_id, - 'title': info.get('title', self._og_search_title(webpage)), - 'description': self._og_search_description(webpage) - } - result.update({'thumbnail': thumbnail}) - result.update({'duration': duration}) - return merge_dicts(media[0], info, result) + webpage = self._download_webpage( + url, display_id, headers=self.geo_verification_headers()) + + SOURCE_RE = r'(<source[^>]+\bsrc=(?:(["\'])(?:(?!\2).)+|[^\s]+)/(?P<id>[\da-z]+)/index)\b' + video_id = self._search_regex( + SOURCE_RE, webpage, 'video id', group='id') + + media = self._parse_html5_media_entries( + url, re.sub(SOURCE_RE, r'\1.m3u8', webpage), video_id, + m3u8_id='hls', m3u8_entry_protocol='m3u8_native')[0] + + info = self._search_json_ld(webpage, video_id, default={}) + + return merge_dicts(media, info, { + 'id': video_id, + 'display_id': display_id, + 'title': self._og_search_title(webpage, default=None) or display_id, + 'description': self._og_search_description(webpage, default=None), + 'thumbnail': self._og_search_thumbnail(webpage, default=None), + }) From 1211bb6dace4773f67bbf46b8944317679573a1f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 8 Feb 2019 01:08:48 +0700 Subject: [PATCH 534/558] [YoutubeDL] Improve _make_archive_id (closes #19149) --- youtube_dl/YoutubeDL.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index c168415ce..bc9fc270c 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -82,6 +82,7 @@ from .utils import ( sanitize_url, sanitized_Request, std_headers, + str_or_none, subtitles_filename, UnavailableVideoError, url_basename, @@ -2067,9 +2068,12 @@ class YoutubeDL(object): # and backwards compatibility with prior versions extractor = info_dict.get('extractor_key') or info_dict.get('ie_key') # key in a playlist if extractor is None: + url = str_or_none(info_dict.get('url')) + if not url: + return # Try to find matching extractor for the URL and take its ie_key for ie in self._ies: - if ie.suitable(info_dict['url']): + if ie.suitable(url): extractor = ie.ie_key() break else: From f1f5b47255a44e791a84b769c523127e0f047578 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 8 Feb 2019 01:10:12 +0700 Subject: [PATCH 535/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/ChangeLog b/ChangeLog index 4872cd9fc..b0fbde43d 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,32 @@ +version <unreleased> + +Core +* [utils] Improve JSON-LD regular expression (#18058) +* [YoutubeDL] Fallback to ie_key of matching extractor while making + download archive id when no explicit ie_key is provided (#19022) + +Extractors ++ [malltv] Add support for mall.tv (#18058, #17856) ++ [spankbang:playlist] Add support for playlists (#19145) +* [spankbang] Extend URL regular expression +* [trutv] Fix extraction (#17336) +* [toutv] Fix authentication (#16398, #18700) +* [pornhub] Fix tags and categories extraction (#13720, #19135) +* [pornhd] Fix formats extraction ++ [pornhd] Extract like count (#19123, #19125) +* [radiocanada] Switch to the new media requests (#19115) ++ [teachable] Add support for courses.workitdaily.com (#18871) +- [vporn] Remove extractor (#16276) ++ [soundcloud:pagedplaylist] Add ie and title to entries (#19022, #19086) ++ [drtuber] Extract duration (#19078) +* [soundcloud] Fix paged playlists extraction, add support for albums and update client id +* [soundcloud] Update client id +* [drtv] Improve preference (#19079) ++ [openload] Add support for openload.pw and oload.pw (#18930) ++ [openload] Add support for oload.info (#19073) +* [crackle] Authorize media detail request (#16931) + + version 2019.01.30.1 Core From 04eacf54530e6a17129d3f1b90f759f9935f2b85 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 8 Feb 2019 01:12:51 +0700 Subject: [PATCH 536/558] release 2019.02.08 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 3 ++- youtube_dl/version.py | 2 +- 4 files changed, 7 insertions(+), 6 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 423a08e4d..7128d998f 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.30.1*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.30.1** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.02.08*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.02.08** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.01.30.1 +[debug] youtube-dl version 2019.02.08 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index b0fbde43d..398528f76 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.02.08 Core * [utils] Improve JSON-LD regular expression (#18058) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 2918520c3..32fe6b647 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -476,6 +476,7 @@ - **mailru:music**: Музыка@Mail.Ru - **mailru:music:search**: Музыка@Mail.Ru - **MakerTV** + - **MallTV** - **mangomolo:live** - **mangomolo:video** - **ManyVids** @@ -827,6 +828,7 @@ - **southpark.nl** - **southparkstudios.dk** - **SpankBang** + - **SpankBangPlaylist** - **Spankwire** - **Spiegel** - **Spiegel:Article**: Articles on spiegel.de @@ -1057,7 +1059,6 @@ - **Voot** - **VoxMedia** - **VoxMediaVolume** - - **Vporn** - **vpro**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl - **Vrak** - **VRT**: deredactie.be, sporza.be, cobra.be and cobra.canvas.be diff --git a/youtube_dl/version.py b/youtube_dl/version.py index be3bbdd73..4dc5a611e 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.01.30.1' +__version__ = '2019.02.08' From 91effe22a091035bc5abace2fcf562a0db89090f Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 8 Feb 2019 07:21:31 +0100 Subject: [PATCH 537/558] [linkedin:learning] extract chapter_number and chapter_id(closes #19162) --- youtube_dl/extractor/linkedin.py | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/linkedin.py b/youtube_dl/extractor/linkedin.py index 259fc4c5e..5a86b0064 100644 --- a/youtube_dl/extractor/linkedin.py +++ b/youtube_dl/extractor/linkedin.py @@ -34,12 +34,15 @@ class LinkedInLearningBaseIE(InfoExtractor): 'Csrf-Token': self._get_cookies(api_url)['JSESSIONID'].value, }, query=query)['elements'][0] - def _get_video_id(self, urn, course_slug, video_slug): + def _get_urn_id(self, video_data): + urn = video_data.get('urn') if urn: mobj = re.search(r'urn:li:lyndaCourse:\d+,(\d+)', urn) if mobj: return mobj.group(1) - return '%s/%s' % (course_slug, video_slug) + + def _get_video_id(self, video_data, course_slug, video_slug): + return self._get_urn_id(video_data) or '%s/%s' % (course_slug, video_slug) def _real_initialize(self): email, password = self._get_login_info() @@ -123,7 +126,7 @@ class LinkedInLearningIE(LinkedInLearningBaseIE): self._sort_formats(formats, ('width', 'height', 'source_preference', 'tbr', 'abr')) return { - 'id': self._get_video_id(video_data.get('urn'), course_slug, video_slug), + 'id': self._get_video_id(video_data, course_slug, video_slug), 'title': title, 'formats': formats, 'thumbnail': video_data.get('defaultThumbnail'), @@ -154,18 +157,21 @@ class LinkedInLearningCourseIE(LinkedInLearningBaseIE): course_data = self._call_api(course_slug, 'chapters,description,title') entries = [] - for chapter in course_data.get('chapters', []): + for chapter_number, chapter in enumerate(course_data.get('chapters', []), 1): chapter_title = chapter.get('title') + chapter_id = self._get_urn_id(chapter) for video in chapter.get('videos', []): video_slug = video.get('slug') if not video_slug: continue entries.append({ '_type': 'url_transparent', - 'id': self._get_video_id(video.get('urn'), course_slug, video_slug), + 'id': self._get_video_id(video, course_slug, video_slug), 'title': video.get('title'), 'url': 'https://www.linkedin.com/learning/%s/%s' % (course_slug, video_slug), 'chapter': chapter_title, + 'chapter_number': chapter_number, + 'chapter_id': chapter_id, 'ie_key': LinkedInLearningIE.ie_key(), }) From e9dee7f1b26e1c23b011a5ad5433d4debc6b48ed Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 9 Feb 2019 23:49:37 +0700 Subject: [PATCH 538/558] [trunews] Add extractor (closes #19153) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/trunews.py | 75 ++++++++++++++++++++++++++++++ 2 files changed, 76 insertions(+) create mode 100644 youtube_dl/extractor/trunews.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index f212b5116..3e1b63b4b 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1171,6 +1171,7 @@ from .toutv import TouTvIE from .toypics import ToypicsUserIE, ToypicsIE from .traileraddict import TrailerAddictIE from .trilulilu import TriluliluIE +from .trunews import TruNewsIE from .trutv import TruTVIE from .tube8 import Tube8IE from .tubitv import TubiTvIE diff --git a/youtube_dl/extractor/trunews.py b/youtube_dl/extractor/trunews.py new file mode 100644 index 000000000..b0c7caabf --- /dev/null +++ b/youtube_dl/extractor/trunews.py @@ -0,0 +1,75 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + dict_get, + float_or_none, + int_or_none, + unified_timestamp, + update_url_query, + url_or_none, +) + + +class TruNewsIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?trunews\.com/stream/(?P<id>[^/?#&]+)' + _TEST = { + 'url': 'https://www.trunews.com/stream/will-democrats-stage-a-circus-during-president-trump-s-state-of-the-union-speech', + 'md5': 'a19c024c3906ff954fac9b96ce66bb08', + 'info_dict': { + 'id': '5c5a21e65d3c196e1c0020cc', + 'display_id': 'will-democrats-stage-a-circus-during-president-trump-s-state-of-the-union-speech', + 'ext': 'mp4', + 'title': "Will Democrats Stage a Circus During President Trump's State of the Union Speech?", + 'description': 'md5:c583b72147cc92cf21f56a31aff7a670', + 'duration': 3685, + 'timestamp': 1549411440, + 'upload_date': '20190206', + }, + 'add_ie': ['Zype'], + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + video = self._download_json( + 'https://api.zype.com/videos', display_id, query={ + 'app_key': 'PUVKp9WgGUb3-JUw6EqafLx8tFVP6VKZTWbUOR-HOm__g4fNDt1bCsm_LgYf_k9H', + 'per_page': 1, + 'active': 'true', + 'friendly_title': display_id, + })['response'][0] + + zype_id = video['_id'] + + thumbnails = [] + thumbnails_list = video.get('thumbnails') + if isinstance(thumbnails_list, list): + for thumbnail in thumbnails_list: + if not isinstance(thumbnail, dict): + continue + thumbnail_url = url_or_none(thumbnail.get('url')) + if not thumbnail_url: + continue + thumbnails.append({ + 'url': thumbnail_url, + 'width': int_or_none(thumbnail.get('width')), + 'height': int_or_none(thumbnail.get('height')), + }) + + return { + '_type': 'url_transparent', + 'url': update_url_query( + 'https://player.zype.com/embed/%s.js' % zype_id, + {'api_key': 'X5XnahkjCwJrT_l5zUqypnaLEObotyvtUKJWWlONxDoHVjP8vqxlArLV8llxMbyt'}), + 'ie_key': 'Zype', + 'id': zype_id, + 'display_id': display_id, + 'title': video.get('title'), + 'description': dict_get(video, ('description', 'ott_description', 'short_description')), + 'duration': int_or_none(video.get('duration')), + 'timestamp': unified_timestamp(video.get('published_at')), + 'average_rating': float_or_none(video.get('rating')), + 'view_count': int_or_none(video.get('request_count')), + 'thumbnails': thumbnails, + } From f516f44094d2244a805d8d0ac4d809fc6cd16782 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 10 Feb 2019 23:44:08 +0700 Subject: [PATCH 539/558] [soundcloud] Extract more metadata --- youtube_dl/extractor/soundcloud.py | 65 +++++++++++++++++++++++++----- 1 file changed, 56 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 5536e7851..15da3496e 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -16,7 +16,8 @@ from ..compat import ( from ..utils import ( ExtractorError, int_or_none, - unified_strdate, + try_get, + unified_timestamp, update_url_query, url_or_none, ) @@ -51,12 +52,17 @@ class SoundcloudIE(InfoExtractor): 'info_dict': { 'id': '62986583', 'ext': 'mp3', - 'upload_date': '20121011', + 'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1', 'description': 'No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o\'d', 'uploader': 'E.T. ExTerrestrial Music', - 'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1', + 'timestamp': 1349920598, + 'upload_date': '20121011', 'duration': 143, 'license': 'all-rights-reserved', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_count': int, } }, # not streamable song @@ -68,9 +74,14 @@ class SoundcloudIE(InfoExtractor): 'title': 'Goldrushed', 'description': 'From Stockholm Sweden\r\nPovel / Magnus / Filip / David\r\nwww.theroyalconcept.com', 'uploader': 'The Royal Concept', + 'timestamp': 1337635207, 'upload_date': '20120521', - 'duration': 227, + 'duration': 30, 'license': 'all-rights-reserved', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_count': int, }, 'params': { # rtmp @@ -85,11 +96,16 @@ class SoundcloudIE(InfoExtractor): 'id': '123998367', 'ext': 'mp3', 'title': 'Youtube - Dl Test Video \'\' Ä↭', - 'uploader': 'jaimeMF', 'description': 'test chars: \"\'/\\ä↭', + 'uploader': 'jaimeMF', + 'timestamp': 1386604920, 'upload_date': '20131209', 'duration': 9, 'license': 'all-rights-reserved', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_count': int, }, }, # private link (alt format) @@ -100,11 +116,16 @@ class SoundcloudIE(InfoExtractor): 'id': '123998367', 'ext': 'mp3', 'title': 'Youtube - Dl Test Video \'\' Ä↭', - 'uploader': 'jaimeMF', 'description': 'test chars: \"\'/\\ä↭', + 'uploader': 'jaimeMF', + 'timestamp': 1386604920, 'upload_date': '20131209', 'duration': 9, 'license': 'all-rights-reserved', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_count': int, }, }, # downloadable song @@ -117,9 +138,14 @@ class SoundcloudIE(InfoExtractor): 'title': 'Bus Brakes', 'description': 'md5:0053ca6396e8d2fd7b7e1595ef12ab66', 'uploader': 'oddsamples', + 'timestamp': 1389232924, 'upload_date': '20140109', 'duration': 17, 'license': 'cc-by-sa', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_count': int, }, }, # private link, downloadable format @@ -132,9 +158,14 @@ class SoundcloudIE(InfoExtractor): 'title': 'Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav]', 'description': 'md5:fa20ee0fca76a3d6df8c7e57f3715366', 'uploader': 'Ori Uplift Music', + 'timestamp': 1504206263, 'upload_date': '20170831', 'duration': 7449, 'license': 'all-rights-reserved', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_count': int, }, }, # no album art, use avatar pic for thumbnail @@ -147,10 +178,15 @@ class SoundcloudIE(InfoExtractor): 'title': 'Sideways (Prod. Mad Real)', 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', 'uploader': 'garyvee', + 'timestamp': 1488152409, 'upload_date': '20170226', 'duration': 207, 'thumbnail': r're:https?://.*\.jpg', 'license': 'all-rights-reserved', + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'repost_count': int, }, 'params': { 'skip_download': True, @@ -176,22 +212,33 @@ class SoundcloudIE(InfoExtractor): def _extract_info_dict(self, info, full_title=None, quiet=False, secret_token=None): track_id = compat_str(info['id']) + title = info['title'] name = full_title or track_id if quiet: self.report_extraction(name) thumbnail = info.get('artwork_url') or info.get('user', {}).get('avatar_url') if isinstance(thumbnail, compat_str): thumbnail = thumbnail.replace('-large', '-t500x500') + username = try_get(info, lambda x: x['user']['username'], compat_str) + + def extract_count(key): + return int_or_none(info.get('%s_count' % key)) + result = { 'id': track_id, - 'uploader': info.get('user', {}).get('username'), - 'upload_date': unified_strdate(info.get('created_at')), - 'title': info['title'], + 'uploader': username, + 'timestamp': unified_timestamp(info.get('created_at')), + 'title': title, 'description': info.get('description'), 'thumbnail': thumbnail, 'duration': int_or_none(info.get('duration'), 1000), 'webpage_url': info.get('permalink_url'), 'license': info.get('license'), + 'view_count': extract_count('playback'), + 'like_count': extract_count('favoritings'), + 'comment_count': extract_count('comment'), + 'repost_count': extract_count('reposts'), + 'genre': info.get('genre'), } formats = [] query = {'client_id': self._CLIENT_ID} From 4c0e0dc9dc13d53a334f75f7d7b9073f79a2dfc0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 11 Feb 2019 00:49:51 +0700 Subject: [PATCH 540/558] [rutube:embed] Fix extraction and add support private videos (closes #19163) --- youtube_dl/extractor/rutube.py | 115 +++++++++++++++++++++------------ 1 file changed, 72 insertions(+), 43 deletions(-) diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index 10ac8ed1f..8f54d5675 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -21,7 +21,17 @@ from ..utils import ( class RutubeBaseIE(InfoExtractor): - def _extract_video(self, video, video_id=None, require_title=True): + def _download_api_info(self, video_id, query=None): + if not query: + query = {} + query['format'] = 'json' + return self._download_json( + 'http://rutube.ru/api/video/%s/' % video_id, + video_id, 'Downloading video JSON', + 'Unable to download video JSON', query=query) + + @staticmethod + def _extract_info(video, video_id=None, require_title=True): title = video['title'] if require_title else video.get('title') age_limit = video.get('is_adult') @@ -32,7 +42,7 @@ class RutubeBaseIE(InfoExtractor): category = try_get(video, lambda x: x['category']['name']) return { - 'id': video.get('id') or video_id, + 'id': video.get('id') or video_id if video_id else video['id'], 'title': title, 'description': video.get('description'), 'thumbnail': video.get('thumbnail_url'), @@ -47,6 +57,42 @@ class RutubeBaseIE(InfoExtractor): 'is_live': bool_or_none(video.get('is_livestream')), } + def _download_and_extract_info(self, video_id, query=None): + return self._extract_info( + self._download_api_info(video_id, query=query), video_id) + + def _download_api_options(self, video_id, query=None): + if not query: + query = {} + query['format'] = 'json' + return self._download_json( + 'http://rutube.ru/api/play/options/%s/' % video_id, + video_id, 'Downloading options JSON', + 'Unable to download options JSON', + headers=self.geo_verification_headers(), query=query) + + def _extract_formats(self, options, video_id): + formats = [] + for format_id, format_url in options['video_balancer'].items(): + ext = determine_ext(format_url) + if ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)) + elif ext == 'f4m': + formats.extend(self._extract_f4m_formats( + format_url, video_id, f4m_id=format_id, fatal=False)) + else: + formats.append({ + 'url': format_url, + 'format_id': format_id, + }) + self._sort_formats(formats) + return formats + + def _download_and_extract_formats(self, video_id, query=None): + return self._extract_formats( + self._download_api_options(video_id, query=query), video_id) + class RutubeIE(RutubeBaseIE): IE_NAME = 'rutube' @@ -55,13 +101,13 @@ class RutubeIE(RutubeBaseIE): _TESTS = [{ 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/', - 'md5': '79938ade01294ef7e27574890d0d3769', + 'md5': '1d24f180fac7a02f3900712e5a5764d6', 'info_dict': { 'id': '3eac3b4561676c17df9132a9a1e62e3e', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Раненный кенгуру забежал в аптеку', 'description': 'http://www.ntdtv.ru ', - 'duration': 80, + 'duration': 81, 'uploader': 'NTDRussian', 'uploader_id': '29790', 'timestamp': 1381943602, @@ -94,39 +140,12 @@ class RutubeIE(RutubeBaseIE): def _real_extract(self, url): video_id = self._match_id(url) - - video = self._download_json( - 'http://rutube.ru/api/video/%s/?format=json' % video_id, - video_id, 'Downloading video JSON') - - info = self._extract_video(video, video_id) - - options = self._download_json( - 'http://rutube.ru/api/play/options/%s/?format=json' % video_id, - video_id, 'Downloading options JSON', - headers=self.geo_verification_headers()) - - formats = [] - for format_id, format_url in options['video_balancer'].items(): - ext = determine_ext(format_url) - if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)) - elif ext == 'f4m': - formats.extend(self._extract_f4m_formats( - format_url, video_id, f4m_id=format_id, fatal=False)) - else: - formats.append({ - 'url': format_url, - 'format_id': format_id, - }) - self._sort_formats(formats) - - info['formats'] = formats + info = self._download_and_extract_info(video_id) + info['formats'] = self._download_and_extract_formats(video_id) return info -class RutubeEmbedIE(InfoExtractor): +class RutubeEmbedIE(RutubeBaseIE): IE_NAME = 'rutube:embed' IE_DESC = 'Rutube embedded videos' _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)' @@ -135,7 +154,7 @@ class RutubeEmbedIE(InfoExtractor): 'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=', 'info_dict': { 'id': 'a10e53b86e8f349080f718582ce4c661', - 'ext': 'flv', + 'ext': 'mp4', 'timestamp': 1387830582, 'upload_date': '20131223', 'uploader_id': '297833', @@ -149,16 +168,26 @@ class RutubeEmbedIE(InfoExtractor): }, { 'url': 'http://rutube.ru/play/embed/8083783', 'only_matching': True, + }, { + # private video + 'url': 'https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ', + 'only_matching': True, }] def _real_extract(self, url): embed_id = self._match_id(url) - webpage = self._download_webpage(url, embed_id) - - canonical_url = self._html_search_regex( - r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage, - 'Canonical URL') - return self.url_result(canonical_url, RutubeIE.ie_key()) + # Query may contain private videos token and should be passed to API + # requests (see #19163) + query = compat_parse_qs(compat_urllib_parse_urlparse(url).query) + options = self._download_api_options(embed_id, query) + video_id = options['effective_video'] + formats = self._extract_formats(options, video_id) + info = self._download_and_extract_info(video_id, query) + info.update({ + 'extractor_key': 'Rutube', + 'formats': formats, + }) + return info class RutubePlaylistBaseIE(RutubeBaseIE): @@ -181,7 +210,7 @@ class RutubePlaylistBaseIE(RutubeBaseIE): video_url = url_or_none(result.get('video_url')) if not video_url: continue - entry = self._extract_video(result, require_title=False) + entry = self._extract_info(result, require_title=False) entry.update({ '_type': 'url', 'url': video_url, From d777f3e81c5f9f6c7be39586703f1f076a2025a9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 11 Feb 2019 04:39:23 +0700 Subject: [PATCH 541/558] [tvplayhome] Fix episode metadata extraction (closes #19190) --- youtube_dl/extractor/tvplay.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py index 8f1ff3b76..7c07b26bc 100644 --- a/youtube_dl/extractor/tvplay.py +++ b/youtube_dl/extractor/tvplay.py @@ -537,8 +537,9 @@ class TVPlayHomeIE(InfoExtractor): r'(\d+)(?:[.\s]+sezona|\s+HOOAEG)', season or '', 'season number', default=None)) episode = self._search_regex( - r'(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, 'episode', - default=None, group='value') + (r'\bepisode\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1', + r'data-subtitle\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage, + 'episode', default=None, group='value') episode_number = int_or_none(self._search_regex( r'(?:S[eē]rija|Osa)\s+(\d+)', episode or '', 'episode number', default=None)) From 7d8b89163c43dfec27dab5250183e52fce838389 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 11 Feb 2019 04:41:28 +0700 Subject: [PATCH 542/558] [tvplayhome] Fix video id extraction (closes #19190) --- youtube_dl/extractor/tvplay.py | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py index 7c07b26bc..d82d48f94 100644 --- a/youtube_dl/extractor/tvplay.py +++ b/youtube_dl/extractor/tvplay.py @@ -493,10 +493,9 @@ class TVPlayHomeIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_id = self._search_regex( - r'data-asset-id\s*=\s*["\'](\d{5,7})\b', webpage, 'video id', - default=None) + r'data-asset-id\s*=\s*["\'](\d{5,})\b', webpage, 'video id') - if video_id: + if len(video_id) < 8: return self.url_result( 'mtg:%s' % video_id, ie=TVPlayIE.ie_key(), video_id=video_id) From 985637cbbfc1a79091eb2f5ca4afec84f6616c75 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 12 Feb 2019 00:13:50 +0700 Subject: [PATCH 543/558] [twitch] Add new source format detection approach (closes #19193) --- youtube_dl/extractor/twitch.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index 401615683..8c87f6dd3 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -136,7 +136,12 @@ class TwitchBaseIE(InfoExtractor): source = next(f for f in formats if f['format_id'] == 'Source') source['preference'] = 10 except StopIteration: - pass # No Source stream present + for f in formats: + if '/chunked/' in f['url']: + f.update({ + 'source_preference': 10, + 'format_note': 'Source', + }) self._sort_formats(formats) From 6f5c1807f43b9dfd17fdc6932ae7ecb6c77fb1a0 Mon Sep 17 00:00:00 2001 From: bitraid <bitraid@protonmail.ch> Date: Tue, 12 Feb 2019 19:02:29 +0200 Subject: [PATCH 544/558] [imgur] Use video id as title fallback (closes #18590) --- youtube_dl/extractor/imgur.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/imgur.py b/youtube_dl/extractor/imgur.py index 0eb54db3f..a5ba03efa 100644 --- a/youtube_dl/extractor/imgur.py +++ b/youtube_dl/extractor/imgur.py @@ -27,6 +27,10 @@ class ImgurIE(InfoExtractor): }, { 'url': 'https://i.imgur.com/crGpqCV.mp4', 'only_matching': True, + }, { + # no title + 'url': 'https://i.imgur.com/jxBXAMC.gifv', + 'only_matching': True, }] def _real_extract(self, url): @@ -87,7 +91,7 @@ class ImgurIE(InfoExtractor): return { 'id': video_id, 'formats': formats, - 'title': self._og_search_title(webpage), + 'title': self._og_search_title(webpage, default=video_id), } From 7bee705d8f110f09d8e72b1c863ff197ccc1d4f1 Mon Sep 17 00:00:00 2001 From: yonaikerlol <lawlietrs7@gmail.com> Date: Thu, 14 Feb 2019 11:28:16 -0400 Subject: [PATCH 545/558] [openload] Add support for oload.live --- youtube_dl/extractor/openload.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index a2ae25272..c1dcbb7eb 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -249,7 +249,7 @@ class OpenloadIE(InfoExtractor): (?:www\.)? (?: openload\.(?:co|io|link|pw)| - oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw) + oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw|live) ) )/ (?:f|embed)/ @@ -346,6 +346,9 @@ class OpenloadIE(InfoExtractor): }, { 'url': 'https://oload.pw/f/WyKgK8s94N0', 'only_matching': True, + }, { + 'url': 'https://oload.live/f/-Z58UZ-GR4M', + 'only_matching': True, }] _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36' From 794c1b6e02591b04da931fa59745bc47bfae7492 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 14 Feb 2019 23:40:46 +0700 Subject: [PATCH 546/558] [vshare] Pass Referer to download request (closes #19205, closes #19221) --- youtube_dl/extractor/vshare.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/vshare.py b/youtube_dl/extractor/vshare.py index e4ec77889..c631ac1fa 100644 --- a/youtube_dl/extractor/vshare.py +++ b/youtube_dl/extractor/vshare.py @@ -48,7 +48,7 @@ class VShareIE(InfoExtractor): webpage = self._download_webpage( 'https://vshare.io/v/%s/width-650/height-430/1' % video_id, - video_id) + video_id, headers={'Referer': url}) title = self._html_search_regex( r'<title>([^<]+)', webpage, 'title') From 2b2da3ba10cc325d00b665aae87f0fa8508bccdf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 15 Feb 2019 23:56:29 +0700 Subject: [PATCH 547/558] [rai] Relax _VALID_URL (closes #19232) --- youtube_dl/extractor/rai.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py index 548a6553b..149153b8f 100644 --- a/youtube_dl/extractor/rai.py +++ b/youtube_dl/extractor/rai.py @@ -288,7 +288,7 @@ class RaiPlayPlaylistIE(InfoExtractor): class RaiIE(RaiBaseIE): - _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/dl/.+?-(?P%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE + _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/.+?-(?P%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE _TESTS = [{ # var uniquename = "ContentItem-..." # data-id="ContentItem-..." @@ -375,6 +375,9 @@ class RaiIE(RaiBaseIE): # Direct MMS URL 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-b63a4089-ac28-48cf-bca5-9f5b5bc46df5.html', 'only_matching': True, + }, { + 'url': 'https://www.rainews.it/tgr/marche/notiziari/video/2019/02/ContentItem-6ba945a2-889c-4a80-bdeb-8489c70a8db9.html', + 'only_matching': True, }] def _extract_from_content_id(self, content_id, url): From ba2e3730d125eab952eded3bb7749d479a2262d3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 16 Feb 2019 22:45:53 +0700 Subject: [PATCH 548/558] [noovo] Fix extraction (closes #19230) --- youtube_dl/extractor/noovo.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/noovo.py b/youtube_dl/extractor/noovo.py index 974de3c3e..b40770d07 100644 --- a/youtube_dl/extractor/noovo.py +++ b/youtube_dl/extractor/noovo.py @@ -57,7 +57,8 @@ class NoovoIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - bc_url = BrightcoveNewIE._extract_url(self, webpage) + brightcove_id = self._search_regex( + r'data-video-id=["\'](\d+)', webpage, 'brightcove id') data = self._parse_json( self._search_regex( @@ -89,7 +90,10 @@ class NoovoIE(InfoExtractor): return { '_type': 'url_transparent', 'ie_key': BrightcoveNewIE.ie_key(), - 'url': smuggle_url(bc_url, {'geo_countries': ['CA']}), + 'url': smuggle_url( + self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, + {'geo_countries': ['CA']}), + 'id': brightcove_id, 'title': title, 'description': description, 'series': series, From ae65c93a26f2b3cf806477a3ee891aa461b5c6b0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 17 Feb 2019 00:58:13 +0700 Subject: [PATCH 549/558] [udemy] Update User-Agent and detect captcha (closes #14713, closes #15839, closes #18126) --- youtube_dl/extractor/udemy.py | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py index 105826e9b..89a7f6ade 100644 --- a/youtube_dl/extractor/udemy.py +++ b/youtube_dl/extractor/udemy.py @@ -123,10 +123,22 @@ class UdemyIE(InfoExtractor): def _download_webpage_handle(self, *args, **kwargs): headers = kwargs.get('headers', {}).copy() - headers['User-Agent'] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/603.2.4 (KHTML, like Gecko) Version/10.1.1 Safari/603.2.4' + headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36' kwargs['headers'] = headers - return super(UdemyIE, self)._download_webpage_handle( + ret = super(UdemyIE, self)._download_webpage_handle( *args, **compat_kwargs(kwargs)) + if not ret: + return ret + webpage, _ = ret + if any(p in webpage for p in ( + '>Please verify you are a human', + 'Access to this page has been denied because we believe you are using automation tools to browse the website', + '"_pxCaptcha"')): + raise ExtractorError( + 'Udemy asks you to solve a CAPTCHA. Login with browser, ' + 'solve CAPTCHA, then export cookies and pass cookie file to ' + 'youtube-dl with --cookies.', expected=True) + return ret def _download_json(self, url_or_request, *args, **kwargs): headers = { From d7d513891b7e63337218c5cb0bf743c8f7044381 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 17 Feb 2019 01:05:01 +0700 Subject: [PATCH 550/558] [udemy] Extend _VALID_URLs (closes #14330, closes #15883) --- youtube_dl/extractor/udemy.py | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py index 89a7f6ade..ae8de9897 100644 --- a/youtube_dl/extractor/udemy.py +++ b/youtube_dl/extractor/udemy.py @@ -29,7 +29,7 @@ class UdemyIE(InfoExtractor): IE_NAME = 'udemy' _VALID_URL = r'''(?x) https?:// - www\.udemy\.com/ + (?:[^/]+\.)?udemy\.com/ (?: [^#]+\#/lecture/| lecture/view/?\?lectureId=| @@ -64,6 +64,9 @@ class UdemyIE(InfoExtractor): # only outputs rendition 'url': 'https://www.udemy.com/how-you-can-help-your-local-community-5-amazing-examples/learn/v4/t/lecture/3225750?start=0', 'only_matching': True, + }, { + 'url': 'https://wipro.udemy.com/java-tutorial/#/lecture/172757', + 'only_matching': True, }] def _extract_course_info(self, webpage, video_id): @@ -415,8 +418,14 @@ class UdemyIE(InfoExtractor): class UdemyCourseIE(UdemyIE): IE_NAME = 'udemy:course' - _VALID_URL = r'https?://(?:www\.)?udemy\.com/(?P[^/?#&]+)' - _TESTS = [] + _VALID_URL = r'https?://(?:[^/]+\.)?udemy\.com/(?P[^/?#&]+)' + _TESTS = [{ + 'url': 'https://www.udemy.com/java-tutorial/', + 'only_matching': True, + }, { + 'url': 'https://wipro.udemy.com/java-tutorial/', + 'only_matching': True, + }] @classmethod def suitable(cls, url): From c9a0ea6e51eff28b9a383a47215870fd5875fc3e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 17 Feb 2019 05:00:16 +0700 Subject: [PATCH 551/558] [bilibili] Update keys (closes #19233) --- youtube_dl/extractor/bilibili.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py index 4d6b051fe..3746671d3 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -93,8 +93,8 @@ class BiliBiliIE(InfoExtractor): }] }] - _APP_KEY = '84956560bc028eb7' - _BILIBILI_KEY = '94aba54af9065f71de72f5508f1cd42e' + _APP_KEY = 'iVGUTjsxvpLeuDCf' + _BILIBILI_KEY = 'aHRmhWMLkdeMuILqORnYZocwMBpMEOdt' def _report_error(self, result): if 'message' in result: From 659e93fcf5c0480ac461cda412335cecf6a5595f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 17 Feb 2019 07:12:10 +0700 Subject: [PATCH 552/558] [linuxacademy] Add extractor (closes #12207) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/linuxacademy.py | 174 +++++++++++++++++++++++++++ 2 files changed, 175 insertions(+) create mode 100644 youtube_dl/extractor/linuxacademy.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 3e1b63b4b..c70452dcd 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -593,6 +593,7 @@ from .linkedin import ( LinkedInLearningIE, LinkedInLearningCourseIE, ) +from .linuxacademy import LinuxAcademyIE from .litv import LiTVIE from .liveleak import ( LiveLeakIE, diff --git a/youtube_dl/extractor/linuxacademy.py b/youtube_dl/extractor/linuxacademy.py new file mode 100644 index 000000000..a78c6556e --- /dev/null +++ b/youtube_dl/extractor/linuxacademy.py @@ -0,0 +1,174 @@ +from __future__ import unicode_literals + +import json +import random +import re + +from .common import InfoExtractor +from ..compat import ( + compat_b64decode, + compat_HTTPError, + compat_str, +) +from ..utils import ( + ExtractorError, + orderedSet, + unescapeHTML, + urlencode_postdata, + urljoin, +) + + +class LinuxAcademyIE(InfoExtractor): + _VALID_URL = r'''(?x) + https?:// + (?:www\.)?linuxacademy\.com/cp/ + (?: + courses/lesson/course/(?P\d+)/lesson/(?P\d+)| + modules/view/id/(?P\d+) + ) + ''' + _TESTS = [{ + 'url': 'https://linuxacademy.com/cp/courses/lesson/course/1498/lesson/2/module/154', + 'info_dict': { + 'id': '1498-2', + 'ext': 'mp4', + 'title': "Introduction to the Practitioner's Brief", + }, + 'params': { + 'skip_download': True, + }, + 'skip': 'Requires Linux Academy account credentials', + }, { + 'url': 'https://linuxacademy.com/cp/courses/lesson/course/1498/lesson/2', + 'only_matching': True, + }, { + 'url': 'https://linuxacademy.com/cp/modules/view/id/154', + 'info_dict': { + 'id': '154', + 'title': 'AWS Certified Cloud Practitioner', + 'description': 'md5:039db7e60e4aac9cf43630e0a75fa834', + }, + 'playlist_count': 41, + 'skip': 'Requires Linux Academy account credentials', + }] + + _AUTHORIZE_URL = 'https://login.linuxacademy.com/authorize' + _ORIGIN_URL = 'https://linuxacademy.com' + _CLIENT_ID = 'KaWxNn1C2Gc7n83W9OFeXltd8Utb5vvx' + _NETRC_MACHINE = 'linuxacademy' + + def _real_initialize(self): + self._login() + + def _login(self): + username, password = self._get_login_info() + if username is None: + return + + def random_string(): + return ''.join([ + random.choice('0123456789ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz-._~') + for _ in range(32)]) + + webpage, urlh = self._download_webpage_handle( + self._AUTHORIZE_URL, None, 'Downloading authorize page', query={ + 'client_id': self._CLIENT_ID, + 'response_type': 'token id_token', + 'redirect_uri': self._ORIGIN_URL, + 'scope': 'openid email user_impersonation profile', + 'audience': self._ORIGIN_URL, + 'state': random_string(), + 'nonce': random_string(), + }) + + login_data = self._parse_json( + self._search_regex( + r'atob\(\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, + 'login info', group='value'), None, + transform_source=lambda x: compat_b64decode(x).decode('utf-8') + )['extraParams'] + + login_data.update({ + 'client_id': self._CLIENT_ID, + 'redirect_uri': self._ORIGIN_URL, + 'tenant': 'lacausers', + 'connection': 'Username-Password-Authentication', + 'username': username, + 'password': password, + 'sso': 'true', + }) + + login_state_url = compat_str(urlh.geturl()) + + try: + login_page = self._download_webpage( + 'https://login.linuxacademy.com/usernamepassword/login', None, + 'Downloading login page', data=json.dumps(login_data).encode(), + headers={ + 'Content-Type': 'application/json', + 'Origin': 'https://login.linuxacademy.com', + 'Referer': login_state_url, + }) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + error = self._parse_json(e.cause.read(), None) + message = error.get('description') or error['code'] + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, message), expected=True) + raise + + callback_page, urlh = self._download_webpage_handle( + 'https://login.linuxacademy.com/login/callback', None, + 'Downloading callback page', + data=urlencode_postdata(self._hidden_inputs(login_page)), + headers={ + 'Content-Type': 'application/x-www-form-urlencoded', + 'Origin': 'https://login.linuxacademy.com', + 'Referer': login_state_url, + }) + + access_token = self._search_regex( + r'access_token=([^=&]+)', compat_str(urlh.geturl()), + 'access token') + + self._download_webpage( + 'https://linuxacademy.com/cp/login/tokenValidateLogin/token/%s' + % access_token, None, 'Downloading token validation page') + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + chapter_id, lecture_id, course_id = mobj.group('chapter_id', 'lesson_id', 'course_id') + item_id = course_id if course_id else '%s-%s' % (chapter_id, lecture_id) + + webpage = self._download_webpage(url, item_id) + + # course path + if course_id: + entries = [ + self.url_result( + urljoin(url, lesson_url), ie=LinuxAcademyIE.ie_key()) + for lesson_url in orderedSet(re.findall( + r']+\bhref=["\'](/cp/courses/lesson/course/\d+/lesson/\d+/module/\d+)', + webpage))] + title = unescapeHTML(self._html_search_regex( + (r'class=["\']course-title["\'][^>]*>(?P[^<]+)', + r'var\s+title\s*=\s*(["\'])(?P(?:(?!\1).)+)\1'), + webpage, 'title', default=None, group='value')) + description = unescapeHTML(self._html_search_regex( + r'var\s+description\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', + webpage, 'description', default=None, group='value')) + return self.playlist_result(entries, course_id, title, description) + + # single video path + info = self._extract_jwplayer_data( + webpage, item_id, require_title=False, m3u8_id='hls',) + title = self._search_regex( + (r'>Lecture\s*:\s*(?P[^<]+)', + r'lessonName\s*=\s*(["\'])(?P(?:(?!\1).)+)\1'), webpage, + 'title', group='value') + info.update({ + 'id': item_id, + 'title': title, + }) + return info From 3c9647372e78134777d201e157a5ef42345c9da2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 17 Feb 2019 13:38:21 +0700 Subject: [PATCH 553/558] [tvp] Fix description extraction, make thumbnail optional and fix tests --- youtube_dl/extractor/tvp.py | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py index 3954f0b93..f9bf600b0 100644 --- a/youtube_dl/extractor/tvp.py +++ b/youtube_dl/extractor/tvp.py @@ -19,12 +19,12 @@ class TVPIE(InfoExtractor): _TESTS = [{ 'url': 'https://vod.tvp.pl/video/czas-honoru,i-seria-odc-13,194536', - 'md5': '8aa518c15e5cc32dfe8db400dc921fbb', + 'md5': 'a21eb0aa862f25414430f15fdfb9e76c', 'info_dict': { 'id': '194536', 'ext': 'mp4', - 'title': 'Czas honoru, I seria – odc. 13', - 'description': 'md5:381afa5bca72655fe94b05cfe82bf53d', + 'title': 'Czas honoru, odc. 13 – Władek', + 'description': 'md5:437f48b93558370b031740546b696e24', }, }, { 'url': 'http://www.tvp.pl/there-can-be-anything-so-i-shortened-it/17916176', @@ -45,6 +45,7 @@ class TVPIE(InfoExtractor): 'title': 'Wiadomości, 28.09.2017, 19:30', 'description': 'Wydanie główne codziennego serwisu informacyjnego.' }, + 'skip': 'HTTP Error 404: Not Found', }, { 'url': 'http://vod.tvp.pl/seriale/obyczajowe/na-sygnale/sezon-2-27-/odc-39/17834272', 'only_matching': True, @@ -75,8 +76,10 @@ class TVPIE(InfoExtractor): return { '_type': 'url_transparent', 'url': 'tvp:' + video_id, - 'description': self._og_search_description(webpage, default=None), - 'thumbnail': self._og_search_thumbnail(webpage), + 'description': self._og_search_description( + webpage, default=None) or self._html_search_meta( + 'description', webpage, default=None), + 'thumbnail': self._og_search_thumbnail(webpage, default=None), 'ie_key': 'TVPEmbed', } @@ -87,6 +90,14 @@ class TVPEmbedIE(InfoExtractor): _VALID_URL = r'(?:tvp:|https?://[^/]+\.tvp\.(?:pl|info)/sess/tvplayer\.php\?.*?object_id=)(?P\d+)' _TESTS = [{ + 'url': 'tvp:194536', + 'md5': 'a21eb0aa862f25414430f15fdfb9e76c', + 'info_dict': { + 'id': '194536', + 'ext': 'mp4', + 'title': 'Czas honoru, odc. 13 – Władek', + }, + }, { 'url': 'http://www.tvp.pl/sess/tvplayer.php?object_id=22670268', 'md5': '8c9cd59d16edabf39331f93bf8a766c7', 'info_dict': { From 34568dc2967d227630ed9d7150deaa62a689b937 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 17 Feb 2019 13:39:00 +0700 Subject: [PATCH 554/558] [tvp] Detect unavailable videos --- youtube_dl/extractor/tvp.py | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py index f9bf600b0..536b580fc 100644 --- a/youtube_dl/extractor/tvp.py +++ b/youtube_dl/extractor/tvp.py @@ -98,6 +98,7 @@ class TVPEmbedIE(InfoExtractor): 'title': 'Czas honoru, odc. 13 – Władek', }, }, { + # not available 'url': 'http://www.tvp.pl/sess/tvplayer.php?object_id=22670268', 'md5': '8c9cd59d16edabf39331f93bf8a766c7', 'info_dict': { @@ -105,6 +106,7 @@ class TVPEmbedIE(InfoExtractor): 'ext': 'mp4', 'title': 'Panorama, 07.12.2015, 15:40', }, + 'skip': 'Transmisja została zakończona lub materiał niedostępny', }, { 'url': 'tvp:22670268', 'only_matching': True, @@ -116,10 +118,13 @@ class TVPEmbedIE(InfoExtractor): webpage = self._download_webpage( 'http://www.tvp.pl/sess/tvplayer.php?object_id=%s' % video_id, video_id) - error_massage = get_element_by_attribute('class', 'msg error', webpage) - if error_massage: + error = self._html_search_regex( + r'(?s)]+\bclass=["\']notAvailable__text["\'][^>]*>(.+?)

', + webpage, 'error', default=None) or clean_html( + get_element_by_attribute('class', 'msg error', webpage)) + if error: raise ExtractorError('%s said: %s' % ( - self.IE_NAME, clean_html(error_massage)), expected=True) + self.IE_NAME, clean_html(error)), expected=True) title = self._search_regex( r'name\s*:\s*([\'"])Title\1\s*,\s*value\s*:\s*\1(?P.+?)\1', From d93083789bf9c318b18d52ac132e9495345b9ebc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 17 Feb 2019 14:09:30 +0700 Subject: [PATCH 555/558] [tvp:series] Fix extraction --- youtube_dl/extractor/tvp.py | 67 ++++++++++++++++--------------------- 1 file changed, 29 insertions(+), 38 deletions(-) diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py index 536b580fc..05669a366 100644 --- a/youtube_dl/extractor/tvp.py +++ b/youtube_dl/extractor/tvp.py @@ -1,14 +1,16 @@ # coding: utf-8 from __future__ import unicode_literals +import itertools import re from .common import InfoExtractor from ..utils import ( - determine_ext, clean_html, - get_element_by_attribute, + determine_ext, ExtractorError, + get_element_by_attribute, + orderedSet, ) @@ -198,46 +200,35 @@ class TVPEmbedIE(InfoExtractor): class TVPSeriesIE(InfoExtractor): IE_NAME = 'tvp:series' - _VALID_URL = r'https?://vod\.tvp\.pl/(?:[^/]+/){2}(?P<id>[^/]+)/?$' + _VALID_URL = r'https?://vod\.tvp\.pl/website/(?P<display_id>[^,]+),(?P<id>\d+)/video' _TESTS = [{ - 'url': 'http://vod.tvp.pl/filmy-fabularne/filmy-za-darmo/ogniem-i-mieczem', + 'url': 'https://vod.tvp.pl/website/lzy-cennet,38678312/video', 'info_dict': { - 'title': 'Ogniem i mieczem', - 'id': '4278026', + 'id': '38678312', }, - 'playlist_count': 4, - }, { - 'url': 'http://vod.tvp.pl/audycje/podroze/boso-przez-swiat', - 'info_dict': { - 'title': 'Boso przez świat', - 'id': '9329207', - }, - 'playlist_count': 86, + 'playlist_count': 115, }] + def _entries(self, url, display_id): + for page_num in itertools.count(1): + page = self._download_webpage( + url, display_id, 'Downloading page %d' % page_num, + query={'page': page_num}) + + video_ids = orderedSet(re.findall( + r'<a[^>]+\bhref=["\']/video/%s,[^,]+,(\d+)' % display_id, + page)) + + if not video_ids: + break + + for video_id in video_ids: + yield self.url_result( + 'tvp:%s' % video_id, ie=TVPEmbedIE.ie_key(), + video_id=video_id) + def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id, tries=5) - - title = self._html_search_regex( - r'(?s) id=[\'"]path[\'"]>(?:.*? / ){2}(.*?)</span>', webpage, 'series') - playlist_id = self._search_regex(r'nodeId:\s*(\d+)', webpage, 'playlist id') - playlist = self._download_webpage( - 'http://vod.tvp.pl/vod/seriesAjax?type=series&nodeId=%s&recommend' - 'edId=0&sort=&page=0&pageSize=10000' % playlist_id, display_id, tries=5, - note='Downloading playlist') - - videos_paths = re.findall( - '(?s)class="shortTitle">.*?href="(/[^"]+)', playlist) - entries = [ - self.url_result('http://vod.tvp.pl%s' % v_path, ie=TVPIE.ie_key()) - for v_path in videos_paths] - - return { - '_type': 'playlist', - 'id': playlist_id, - 'display_id': display_id, - 'title': title, - 'entries': entries, - } + mobj = re.match(self._VALID_URL, url) + display_id, playlist_id = mobj.group('display_id', 'id') + return self.playlist_result(self._entries(url, display_id), playlist_id) From 388cfbd3d8915ebb99714ac8e7ce4151edf96d8d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 17 Feb 2019 14:27:00 +0700 Subject: [PATCH 556/558] [tvp:website] Improve support --- youtube_dl/extractor/extractors.py | 2 +- youtube_dl/extractor/tvp.py | 26 ++++++++++++++++++++++---- 2 files changed, 23 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index c70452dcd..923dfe7f4 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1218,7 +1218,7 @@ from .tvnow import ( from .tvp import ( TVPEmbedIE, TVPIE, - TVPSeriesIE, + TVPWebsiteIE, ) from .tvplay import ( TVPlayIE, diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py index 05669a366..accff75b5 100644 --- a/youtube_dl/extractor/tvp.py +++ b/youtube_dl/extractor/tvp.py @@ -198,19 +198,36 @@ class TVPEmbedIE(InfoExtractor): } -class TVPSeriesIE(InfoExtractor): +class TVPWebsiteIE(InfoExtractor): IE_NAME = 'tvp:series' - _VALID_URL = r'https?://vod\.tvp\.pl/website/(?P<display_id>[^,]+),(?P<id>\d+)/video' + _VALID_URL = r'https?://vod\.tvp\.pl/website/(?P<display_id>[^,]+),(?P<id>\d+)' _TESTS = [{ + # series 'url': 'https://vod.tvp.pl/website/lzy-cennet,38678312/video', 'info_dict': { 'id': '38678312', }, 'playlist_count': 115, + }, { + # film + 'url': 'https://vod.tvp.pl/website/gloria,35139666', + 'info_dict': { + 'id': '36637049', + 'ext': 'mp4', + 'title': 'Gloria, Gloria', + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': ['TVPEmbed'], + }, { + 'url': 'https://vod.tvp.pl/website/lzy-cennet,38678312', + 'only_matching': True, }] - def _entries(self, url, display_id): + def _entries(self, display_id, playlist_id): + url = 'https://vod.tvp.pl/website/%s,%s/video' % (display_id, playlist_id) for page_num in itertools.count(1): page = self._download_webpage( url, display_id, 'Downloading page %d' % page_num, @@ -231,4 +248,5 @@ class TVPSeriesIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) display_id, playlist_id = mobj.group('display_id', 'id') - return self.playlist_result(self._entries(url, display_id), playlist_id) + return self.playlist_result( + self._entries(display_id, playlist_id), playlist_id) From c76fc5b22a70f9ac24fe7e34c37aa8ef82e85c49 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 18 Feb 2019 02:10:06 +0700 Subject: [PATCH 557/558] [ChangeLog] Actualize [ci skip] --- ChangeLog | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/ChangeLog b/ChangeLog index 398528f76..adbdf166d 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,28 @@ +version <unreleased> + +Extractors +* [tvp:website] Fix and improve extraction ++ [tvp] Detect unavailable videos +* [tvp] Fix description extraction and make thumbnail optional ++ [linuxacademy] Add support for linuxacademy.com (#12207) +* [bilibili] Update keys (#19233) +* [udemy] Extend URL regular expressions (#14330, #15883) +* [udemy] Update User-Agent and detect captcha (#14713, #15839, #18126) +* [noovo] Fix extraction (#19230) +* [rai] Relax URL regular expression (#19232) ++ [vshare] Pass Referer to download request (#19205, #19221) ++ [openload] Add support for oload.live (#19222) +* [imgur] Use video id as title fallback (#18590) ++ [twitch] Add new source format detection approach (#19193) +* [tvplayhome] Fix video id extraction (#19190) +* [tvplayhome] Fix episode metadata extraction (#19190) +* [rutube:embed] Fix extraction (#19163) ++ [rutube:embed] Add support private videos (#19163) ++ [soundcloud] Extract more metadata ++ [trunews] Add support for trunews.com (#19153) ++ [linkedin:learning] Extract chapter_number and chapter_id (#19162) + + version 2019.02.08 Core From 77a842c8926625fe791ed36613f183bb195394cb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Mon, 18 Feb 2019 02:11:11 +0700 Subject: [PATCH 558/558] release 2019.02.18 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 2 ++ youtube_dl/version.py | 2 +- 4 files changed, 7 insertions(+), 5 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 7128d998f..ff626883d 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.02.08*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.02.08** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.02.18*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.02.18** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2019.02.08 +[debug] youtube-dl version 2019.02.18 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/ChangeLog b/ChangeLog index adbdf166d..f9dd7928f 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.02.18 Extractors * [tvp:website] Fix and improve extraction diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 32fe6b647..d8a8d7ede 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -458,6 +458,7 @@ - **LineTV** - **linkedin:learning** - **linkedin:learning:course** + - **LinuxAcademy** - **LiTV** - **LiveLeak** - **LiveLeakEmbed** @@ -915,6 +916,7 @@ - **ToypicsUser**: Toypics user profile - **TrailerAddict** (Currently broken) - **Trilulilu** + - **TruNews** - **TruTV** - **Tube8** - **TubiTv** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 4dc5a611e..ea1d5a4a5 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.02.08' +__version__ = '2019.02.18'