diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index bd9e21983..1954528e3 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 *2017.09.02*. 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 Issues with outdated version will be rejected.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 **2017.09.02** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.09.24*. 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 Issues with outdated version will be rejected.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 **2017.09.24** ### 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 @@ -35,7 +35,7 @@ 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 2017.09.02 +[debug] youtube-dl version 2017.09.24 [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/.gitignore b/.gitignore index a5b585f43..fbf7cecb2 100644 --- a/.gitignore +++ b/.gitignore @@ -22,6 +22,7 @@ cover/ updates_key.pem *.egg-info *.srt +*.ttml *.sbv *.vtt *.flv diff --git a/AUTHORS b/AUTHORS index 478c7872f..7e012247c 100644 --- a/AUTHORS +++ b/AUTHORS @@ -224,3 +224,10 @@ Giuseppe Fabiano Örn Guðjónsson Parmjit Virk Genki Sky +Ľuboš Katrinec +Corey Nicholson +Ashutosh Chaudhary +John Dong +Tatsuyuki Ishi +Daniel Weber +Kay Bouché diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index a8091e7b5..333acee80 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -82,6 +82,8 @@ To run the test, simply invoke your favorite test runner, or execute a test file python test/test_download.py nosetests +See item 6 of [new extractor tutorial](#adding-support-for-a-new-site) for how to run extractor specific test cases. + If you want to create a build of youtube-dl yourself, you'll need * python @@ -149,7 +151,7 @@ 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. +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. 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: diff --git a/ChangeLog b/ChangeLog index c439c8ef9..da60c1b36 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,84 @@ +version 2017.09.24 + +Core ++ [options] Accept lrc as a subtitle conversion target format (#14292) +* [utils] Fix handling raw TTML subtitles (#14191) + +Extractors +* [24video] Fix timestamp extraction and make non fatal (#14295) ++ [24video] Add support for 24video.adult (#14295) ++ [kakao] Add support for tv.kakao.com (#12298, #14007) ++ [twitter] Add support for URLs without user id (#14270) ++ [americastestkitchen] Add support for americastestkitchen.com (#10764, + #13996) +* [generic] Fix support for multiple HTML5 videos on one page (#14080) +* [mixcloud] Fix extraction (#14088, #14132) ++ [lynda] Add support for educourse.ga (#14286) +* [beeg] Fix extraction (#14275) +* [nbcsports:vplayer] Correct theplatform URL (#13873) +* [twitter] Fix duration extraction (#14141) +* [tvplay] Bypass geo restriction ++ [heise] Add support for YouTube embeds (#14109) ++ [popcorntv] Add support for popcorntv.it (#5914, #14211) +* [viki] Update app data (#14181) +* [morningstar] Relax URL regular expression (#14222) +* [openload] Fix extraction (#14225, #14257) +* [noovo] Fix extraction (#14214) +* [dailymotion:playlist] Relax URL regular expression (#14219) ++ [twitch] Add support for go.twitch.tv URLs (#14215) +* [vgtv] Relax URL regular expression (#14223) + + +version 2017.09.15 + +Core +* [downloader/fragment] Restart inconsistent incomplete fragment downloads + (#13731) +* [YoutubeDL] Download raw subtitles files (#12909, #14191) + +Extractors +* [condenast] Fix extraction (#14196, #14207) ++ [orf] Add support for f4m stories +* [tv4] Relax URL regular expression (#14206) +* [animeondemand] Bypass geo restriction ++ [animeondemand] Add support for flash videos (#9944) + + +version 2017.09.11 + +Extractors +* [rutube:playlist] Fix suitable (#14166) + + +version 2017.09.10 + +Core ++ [utils] Introduce bool_or_none +* [YoutubeDL] Ensure dir existence for each requested format (#14116) + +Extractors +* [fox] Fix extraction (#14147) +* [rutube] Use bool_or_none +* [rutube] Rework and generalize playlist extractors (#13565) ++ [rutube:playlist] Add support for playlists (#13534, #13565) ++ [radiocanada] Add fallback for title extraction (#14145) +* [vk] Use dedicated YouTube embeds extraction routine +* [vice] Use dedicated YouTube embeds extraction routine +* [cracked] Use dedicated YouTube embeds extraction routine +* [chilloutzone] Use dedicated YouTube embeds extraction routine +* [abcnews] Use dedicated YouTube embeds extraction routine +* [youtube] Separate methods for embeds extraction +* [redtube] Fix formats extraction (#14122) +* [arte] Relax unavailability check (#14112) ++ [manyvids] Add support for preview videos from manyvids.com (#14053, #14059) +* [vidme:user] Relax URL regular expression (#14054) +* [bpb] Fix extraction (#14043, #14086) +* [soundcloud] Fix download URL with private tracks (#14093) +* [aliexpress:live] Add support for live.aliexpress.com (#13698, #13707) +* [viidea] Capture and output lecture error message (#14099) +* [radiocanada] Skip unsupported platforms (#14100) + + version 2017.09.02 Extractors diff --git a/README.md b/README.md index 28ee63f40..7818e58df 100644 --- a/README.md +++ b/README.md @@ -427,7 +427,7 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo syntax. Example: --exec 'adb push {} /sdcard/Music/ && rm {}' --convert-subs FORMAT Convert the subtitles to other format - (currently supported: srt|ass|vtt) + (currently supported: srt|ass|vtt|lrc) # CONFIGURATION diff --git a/devscripts/check-porn.py b/devscripts/check-porn.py index 7a219ebe9..72b2ee422 100644 --- a/devscripts/check-porn.py +++ b/devscripts/check-porn.py @@ -14,7 +14,7 @@ import os import sys sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -from test.helper import get_testcases +from test.helper import gettestcases from youtube_dl.utils import compat_urllib_parse_urlparse from youtube_dl.utils import compat_urllib_request @@ -24,7 +24,7 @@ if len(sys.argv) > 1: else: METHOD = 'EURISTIC' -for test in get_testcases(): +for test in gettestcases(): if METHOD == 'EURISTIC': try: webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read() diff --git a/docs/supportedsites.md b/docs/supportedsites.md index dbec6c8dc..d36a07cf6 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -38,10 +38,12 @@ - **afreecatv**: afreecatv.com - **afreecatv:global**: afreecatv.com - **AirMozilla** + - **AliExpressLive** - **AlJazeera** - **Allocine** - **AlphaPorno** - **AMCNetworks** + - **AmericasTestKitchen** - **anderetijden**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl - **AnimeOnDemand** - **anitube.se** @@ -377,6 +379,7 @@ - **Jove** - **jpopsuki.tv** - **JWPlatform** + - **Kakao** - **Kaltura** - **Kamcord** - **KanalPlay**: Kanal 5/9/11 Play @@ -437,6 +440,7 @@ - **MakerTV** - **mangomolo:live** - **mangomolo:video** + - **ManyVids** - **MatchTV** - **MDR**: MDR.DE and KiKA - **media.ccc.de** @@ -591,6 +595,7 @@ - **Openload** - **OraTV** - **orf:fm4**: radio FM4 + - **orf:fm4:story**: fm4.orf.at stories - **orf:iptv**: iptv.ORF.at - **orf:oe1**: Radio Österreich 1 - **orf:tvthek**: ORF TVthek @@ -624,6 +629,7 @@ - **Pokemon** - **PolskieRadio** - **PolskieRadioCategory** + - **PopcornTV** - **PornCom** - **PornerBros** - **PornFlip** @@ -701,6 +707,7 @@ - **rutube:embed**: Rutube embedded videos - **rutube:movie**: Rutube movies - **rutube:person**: Rutube person videos + - **rutube:playlist**: Rutube playlists - **RUTV**: RUTV.RU - **Ruutu** - **Ruv** diff --git a/test/test_utils.py b/test/test_utils.py index e50f3764e..efa73d0f4 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -1064,7 +1064,7 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')

Ignored, three

- ''' + '''.encode('utf-8') srt_data = '''1 00:00:00,000 --> 00:00:01,000 The following line contains Chinese characters and special symbols @@ -1089,7 +1089,7 @@ Line

The first line

- ''' + '''.encode('utf-8') srt_data = '''1 00:00:00,000 --> 00:00:01,000 The first line @@ -1115,7 +1115,7 @@ The first line

inner
style

-''' +'''.encode('utf-8') srt_data = '''1 00:00:02,080 --> 00:00:05,839 default stylecustom style @@ -1138,6 +1138,26 @@ part 3 ''' self.assertEqual(dfxp2srt(dfxp_data_with_style), srt_data) + dfxp_data_non_utf8 = ''' + + +
+

Line 1

+

第二行

+
+ + '''.encode('utf-16') + srt_data = '''1 +00:00:00,000 --> 00:00:01,000 +Line 1 + +2 +00:00:01,000 --> 00:00:02,000 +第二行 + +''' + self.assertEqual(dfxp2srt(dfxp_data_non_utf8), srt_data) + def test_cli_option(self): self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128']) self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), []) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 4f208f1e1..0a7f36c98 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -92,6 +92,7 @@ from .utils import ( ) from .cache import Cache from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER +from .extractor.openload import PhantomJSwrapper from .downloader import get_suitable_downloader from .downloader.rtmp import rtmpdump_version from .postprocessor import ( @@ -1763,29 +1764,30 @@ class YoutubeDL(object): ie = self.get_info_extractor(info_dict['extractor_key']) for sub_lang, sub_info in subtitles.items(): sub_format = sub_info['ext'] - if sub_info.get('data') is not None: - sub_data = sub_info['data'] + sub_filename = subtitles_filename(filename, sub_lang, sub_format) + if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)): + self.to_screen('[info] Video subtitle %s.%s is already present' % (sub_lang, sub_format)) else: - try: - sub_data = ie._download_webpage( - sub_info['url'], info_dict['id'], note=False) - except ExtractorError as err: - self.report_warning('Unable to download subtitle for "%s": %s' % - (sub_lang, error_to_compat_str(err.cause))) - continue - try: - sub_filename = subtitles_filename(filename, sub_lang, sub_format) - if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)): - self.to_screen('[info] Video subtitle %s.%s is already_present' % (sub_lang, sub_format)) + self.to_screen('[info] Writing video subtitles to: ' + sub_filename) + if sub_info.get('data') is not None: + try: + # Use newline='' to prevent conversion of newline characters + # See https://github.com/rg3/youtube-dl/issues/10268 + with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8', newline='') as subfile: + subfile.write(sub_info['data']) + except (OSError, IOError): + self.report_error('Cannot write subtitles file ' + sub_filename) + return else: - self.to_screen('[info] Writing video subtitles to: ' + sub_filename) - # Use newline='' to prevent conversion of newline characters - # See https://github.com/rg3/youtube-dl/issues/10268 - with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8', newline='') as subfile: - subfile.write(sub_data) - except (OSError, IOError): - self.report_error('Cannot write subtitles file ' + sub_filename) - return + try: + sub_data = ie._request_webpage( + sub_info['url'], info_dict['id'], note=False).read() + with io.open(encodeFilename(sub_filename), 'wb') as subfile: + subfile.write(sub_data) + except (ExtractorError, IOError, OSError, ValueError) as err: + self.report_warning('Unable to download subtitle for "%s": %s' % + (sub_lang, error_to_compat_str(err))) + continue if self.params.get('writeinfojson', False): infofn = replace_extension(filename, 'info.json', info_dict.get('ext')) @@ -2216,6 +2218,7 @@ class YoutubeDL(object): exe_versions = FFmpegPostProcessor.get_versions(self) exe_versions['rtmpdump'] = rtmpdump_version() + exe_versions['phantomjs'] = PhantomJSwrapper._version() exe_str = ', '.join( '%s %s' % (exe, v) for exe, v in sorted(exe_versions.items()) diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index c4589411e..ba684a075 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -206,7 +206,7 @@ def _real_main(argv=None): if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']: parser.error('invalid video recode format specified') if opts.convertsubtitles is not None: - if opts.convertsubtitles not in ['srt', 'vtt', 'ass']: + if opts.convertsubtitles not in ['srt', 'vtt', 'ass', 'lrc']: parser.error('invalid subtitle format specified') if opts.date is not None: diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index 9e4e13bcf..2a62248ef 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -6,6 +6,7 @@ import collections import email import getpass import io +import itertools import optparse import os import re @@ -15,7 +16,6 @@ import socket import struct import subprocess import sys -import itertools import xml.etree.ElementTree @@ -2898,6 +2898,13 @@ else: compat_struct_pack = struct.pack compat_struct_unpack = struct.unpack +try: + from future_builtins import zip as compat_zip +except ImportError: # not 2.6+ or is 3.x + try: + from itertools import izip as compat_zip # < 2.5 or 3.x + except ImportError: + compat_zip = zip __all__ = [ 'compat_HTMLParseError', @@ -2948,5 +2955,6 @@ __all__ = [ 'compat_urlretrieve', 'compat_xml_parse_error', 'compat_xpath', + 'compat_zip', 'workaround_optparse_bug9161', ] diff --git a/youtube_dl/downloader/fragment.py b/youtube_dl/downloader/fragment.py index bccc8ecc1..6f6fb4a77 100644 --- a/youtube_dl/downloader/fragment.py +++ b/youtube_dl/downloader/fragment.py @@ -151,10 +151,15 @@ class FragmentFD(FileDownloader): if self.__do_ytdl_file(ctx): if os.path.isfile(encodeFilename(self.ytdl_filename(ctx['filename']))): self._read_ytdl_file(ctx) + if ctx['fragment_index'] > 0 and resume_len == 0: + self.report_error( + 'Inconsistent state of incomplete fragment download. ' + 'Restarting from the beginning...') + ctx['fragment_index'] = resume_len = 0 + self._write_ytdl_file(ctx) else: self._write_ytdl_file(ctx) - if ctx['fragment_index'] > 0: - assert resume_len > 0 + assert ctx['fragment_index'] == 0 dest_stream, tmpfilename = sanitize_open(tmpfilename, open_mode) diff --git a/youtube_dl/extractor/americastestkitchen.py b/youtube_dl/extractor/americastestkitchen.py new file mode 100755 index 000000000..01736872d --- /dev/null +++ b/youtube_dl/extractor/americastestkitchen.py @@ -0,0 +1,85 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + clean_html, + int_or_none, + try_get, + unified_strdate, +) + + +class AmericasTestKitchenIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?americastestkitchen\.com/(?:episode|videos)/(?P\d+)' + _TESTS = [{ + 'url': 'https://www.americastestkitchen.com/episode/548-summer-dinner-party', + 'md5': 'b861c3e365ac38ad319cfd509c30577f', + 'info_dict': { + 'id': '1_5g5zua6e', + 'title': 'Summer Dinner Party', + 'ext': 'mp4', + 'description': 'md5:858d986e73a4826979b6a5d9f8f6a1ec', + 'thumbnail': r're:^https?://.*\.jpg', + 'timestamp': 1497285541, + 'upload_date': '20170612', + 'uploader_id': 'roger.metcalf@americastestkitchen.com', + 'release_date': '20170617', + 'series': "America's Test Kitchen", + 'season_number': 17, + 'episode': 'Summer Dinner Party', + 'episode_number': 24, + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + 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*', + webpage, 'initial context'), + video_id) + + ep_data = try_get( + video_data, + (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'] + + title = ep_data.get('title') or ep_meta.get('title') + description = clean_html(ep_meta.get('episode_description') or ep_data.get( + 'description') or ep_meta.get('description')) + thumbnail = try_get(ep_meta, lambda x: x['photo']['image_url']) + release_date = unified_strdate(ep_data.get('aired_at')) + + season_number = int_or_none(ep_meta.get('season_number')) + episode = ep_meta.get('title') + episode_number = int_or_none(ep_meta.get('episode_number')) + + return { + '_type': 'url_transparent', + 'url': 'kaltura:%s:%s' % (partner_id, external_id), + 'ie_key': 'Kaltura', + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'release_date': release_date, + 'series': "America's Test Kitchen", + 'season_number': season_number, + 'episode': episode, + 'episode_number': episode_number, + } diff --git a/youtube_dl/extractor/animeondemand.py b/youtube_dl/extractor/animeondemand.py index 9e28f2579..69d363311 100644 --- a/youtube_dl/extractor/animeondemand.py +++ b/youtube_dl/extractor/animeondemand.py @@ -3,16 +3,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urlparse, - compat_str, -) +from ..compat import compat_str from ..utils import ( determine_ext, extract_attributes, ExtractorError, - sanitized_Request, urlencode_postdata, + urljoin, ) @@ -21,6 +18,8 @@ class AnimeOnDemandIE(InfoExtractor): _LOGIN_URL = 'https://www.anime-on-demand.de/users/sign_in' _APPLY_HTML5_URL = 'https://www.anime-on-demand.de/html5apply' _NETRC_MACHINE = 'animeondemand' + # German-speaking countries of Europe + _GEO_COUNTRIES = ['AT', 'CH', 'DE', 'LI', 'LU'] _TESTS = [{ # jap, OmU 'url': 'https://www.anime-on-demand.de/anime/161', @@ -46,6 +45,10 @@ class AnimeOnDemandIE(InfoExtractor): # Full length film, non-series, ger/jap, Dub/OmU, account required 'url': 'https://www.anime-on-demand.de/anime/185', 'only_matching': True, + }, { + # Flash videos + 'url': 'https://www.anime-on-demand.de/anime/12', + 'only_matching': True, }] def _login(self): @@ -72,14 +75,13 @@ class AnimeOnDemandIE(InfoExtractor): 'post url', default=self._LOGIN_URL, group='url') if not post_url.startswith('http'): - post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url) - - request = sanitized_Request( - post_url, urlencode_postdata(login_form)) - request.add_header('Referer', self._LOGIN_URL) + post_url = urljoin(self._LOGIN_URL, post_url) response = self._download_webpage( - request, None, 'Logging in as %s' % username) + post_url, None, 'Logging in as %s' % username, + data=urlencode_postdata(login_form), headers={ + 'Referer': self._LOGIN_URL, + }) if all(p not in response for p in ('>Logout<', 'href="/users/sign_out"')): error = self._search_regex( @@ -120,10 +122,11 @@ class AnimeOnDemandIE(InfoExtractor): formats = [] for input_ in re.findall( - r']+class=["\'].*?streamstarter_html5[^>]+>', html): + r']+class=["\'].*?streamstarter[^>]+>', html): attributes = extract_attributes(input_) + title = attributes.get('data-dialog-header') playlist_urls = [] - for playlist_key in ('data-playlist', 'data-otherplaylist'): + for playlist_key in ('data-playlist', 'data-otherplaylist', 'data-stream'): playlist_url = attributes.get(playlist_key) if isinstance(playlist_url, compat_str) and re.match( r'/?[\da-zA-Z]+', playlist_url): @@ -147,19 +150,38 @@ class AnimeOnDemandIE(InfoExtractor): format_id_list.append(compat_str(num)) format_id = '-'.join(format_id_list) format_note = ', '.join(filter(None, (kind, lang_note))) - request = sanitized_Request( - compat_urlparse.urljoin(url, playlist_url), + item_id_list = [] + if format_id: + item_id_list.append(format_id) + item_id_list.append('videomaterial') + playlist = self._download_json( + urljoin(url, playlist_url), video_id, + 'Downloading %s JSON' % ' '.join(item_id_list), headers={ 'X-Requested-With': 'XMLHttpRequest', 'X-CSRF-Token': csrf_token, 'Referer': url, 'Accept': 'application/json, text/javascript, */*; q=0.01', - }) - playlist = self._download_json( - request, video_id, 'Downloading %s playlist JSON' % format_id, - fatal=False) + }, fatal=False) if not playlist: continue + stream_url = playlist.get('streamurl') + if stream_url: + rtmp = re.search( + r'^(?Prtmpe?://(?P[^/]+)/(?P.+/))(?Pmp[34]:.+)', + stream_url) + if rtmp: + formats.append({ + 'url': rtmp.group('url'), + 'app': rtmp.group('app'), + 'play_path': rtmp.group('playpath'), + 'page_url': url, + 'player_url': 'https://www.anime-on-demand.de/assets/jwplayer.flash-55abfb34080700304d49125ce9ffb4a6.swf', + 'rtmp_real_time': True, + 'format_id': 'rtmp', + 'ext': 'flv', + }) + continue start_video = playlist.get('startvideo', 0) playlist = playlist.get('playlist') if not playlist or not isinstance(playlist, list): @@ -222,7 +244,7 @@ class AnimeOnDemandIE(InfoExtractor): f.update({ 'id': '%s-%s' % (f['id'], m.group('kind').lower()), 'title': m.group('title'), - 'url': compat_urlparse.urljoin(url, m.group('href')), + 'url': urljoin(url, m.group('href')), }) entries.append(f) diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py index d5c5822f2..bbeae4bac 100644 --- a/youtube_dl/extractor/beeg.py +++ b/youtube_dl/extractor/beeg.py @@ -9,6 +9,7 @@ from ..compat import ( from ..utils import ( int_or_none, parse_iso8601, + urljoin, ) @@ -36,9 +37,11 @@ class BeegIE(InfoExtractor): webpage = self._download_webpage(url, video_id) cpl_url = self._search_regex( - r']+src=(["\'])(?P(?:https?:)?//static\.beeg\.com/cpl/\d+\.js.*?)\1', + 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: @@ -54,7 +57,7 @@ class BeegIE(InfoExtractor): r'beeg_salt\s*=\s*(["\'])(?P.+?)\1', cpl, 'beeg salt', default=None, group='beeg_salt') - beeg_version = beeg_version or '2000' + beeg_version = beeg_version or '2185' beeg_salt = beeg_salt or 'pmweAkq8lAYKdfWcFCUj0yoVgoPlinamH5UE1CB3H' video = self._download_json( diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 74d30ec50..2bbbf8f4d 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -2449,10 +2449,12 @@ class InfoExtractor(object): self._downloader.report_warning(msg) return res - def _set_cookie(self, domain, name, value, expire_time=None): + def _set_cookie(self, domain, name, value, expire_time=None, port=None, + path='/', secure=False, discard=False, rest={}, **kwargs): cookie = compat_cookiejar.Cookie( - 0, name, value, None, None, domain, None, - None, '/', True, False, expire_time, '', None, None, None) + 0, name, value, port, port is not None, domain, True, + domain.startswith('.'), path, True, secure, expire_time, + discard, None, None, rest) self._downloader.cookiejar.set_cookie(cookie) def _get_cookies(self, url): diff --git a/youtube_dl/extractor/condenast.py b/youtube_dl/extractor/condenast.py index 0c3f0c0e4..ed278fefc 100644 --- a/youtube_dl/extractor/condenast.py +++ b/youtube_dl/extractor/condenast.py @@ -116,16 +116,16 @@ class CondeNastIE(InfoExtractor): entries = [self.url_result(build_url(path), 'CondeNast') for path in paths] return self.playlist_result(entries, playlist_title=title) - def _extract_video_params(self, webpage): - query = {} - params = self._search_regex( - r'(?s)var params = {(.+?)}[;,]', webpage, 'player params', default=None) - if params: - query.update({ - 'videoId': self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id'), - 'playerId': self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, 'player id'), - 'target': self._search_regex(r'target: [\'"](.+?)[\'"]', params, 'target'), - }) + def _extract_video_params(self, webpage, display_id): + query = self._parse_json( + self._search_regex( + r'(?s)var\s+params\s*=\s*({.+?})[;,]', webpage, 'player params', + default='{}'), + display_id, transform_source=js_to_json, fatal=False) + if query: + query['videoId'] = self._search_regex( + r'(?:data-video-id=|currentVideoId\s*=\s*)["\']([\da-f]+)', + webpage, 'video id', default=None) else: params = extract_attributes(self._search_regex( r'(<[^>]+data-js="video-player"[^>]+>)', @@ -141,17 +141,27 @@ class CondeNastIE(InfoExtractor): video_id = params['videoId'] video_info = None - if params.get('playerId'): - info_page = self._download_json( - 'http://player.cnevids.com/player/video.js', - video_id, 'Downloading video info', fatal=False, query=params) - if info_page: - video_info = info_page.get('video') - if not video_info: - info_page = self._download_webpage( - 'http://player.cnevids.com/player/loader.js', - video_id, 'Downloading loader info', query=params) - else: + + # New API path + query = params.copy() + query['embedType'] = 'inline' + info_page = self._download_json( + 'http://player.cnevids.com/embed-api.json', video_id, + 'Downloading embed info', fatal=False, query=query) + + # Old fallbacks + if not info_page: + if params.get('playerId'): + info_page = self._download_json( + 'http://player.cnevids.com/player/video.js', video_id, + 'Downloading video info', fatal=False, query=params) + if info_page: + video_info = info_page.get('video') + if not video_info: + info_page = self._download_webpage( + 'http://player.cnevids.com/player/loader.js', + video_id, 'Downloading loader info', query=params) + if not video_info: info_page = self._download_webpage( 'https://player.cnevids.com/inline/video/%s.js' % video_id, video_id, 'Downloading inline info', query={ @@ -215,7 +225,7 @@ class CondeNastIE(InfoExtractor): if url_type == 'series': return self._extract_series(url, webpage) else: - params = self._extract_video_params(webpage) + params = self._extract_video_params(webpage, display_id) info = self._search_json_ld( webpage, display_id, fatal=False) info.update(self._extract_video(params)) diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 74e991331..e9d0dd19c 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -325,7 +325,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor): class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): IE_NAME = 'dailymotion:playlist' - _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P.+?)/' + _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P[^/?#&]+)' _MORE_PAGES_INDICATOR = r'(?s)
.*?[0-9]+)' - _TEST = { - 'url': 'http://www.fox.com/watch/255180355939/7684182528', + _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P[\da-fA-F]+)' + _TESTS = [{ + # clip + 'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/', 'md5': 'ebd296fcc41dd4b19f8115d8461a3165', 'info_dict': { - 'id': '255180355939', + 'id': '4b765a60490325103ea69888fb2bd4e8', 'ext': 'mp4', - 'title': 'Official Trailer: Gotham', - 'description': 'Tracing the rise of the great DC Comics Super-Villains and vigilantes, Gotham reveals an entirely new chapter that has never been told.', - 'duration': 129, - 'timestamp': 1400020798, - 'upload_date': '20140513', - 'uploader': 'NEWA-FNG-FOXCOM', + 'title': 'Aftermath: Bruce Wayne Develops Into The Dark Knight', + 'description': 'md5:549cd9c70d413adb32ce2a779b53b486', + 'duration': 102, + 'timestamp': 1504291893, + 'upload_date': '20170901', + 'creator': 'FOX', + 'series': 'Gotham', }, - 'add_ie': ['ThePlatform'], - } + 'params': { + 'skip_download': True, + }, + }, { + # episode, geo-restricted + 'url': 'https://www.fox.com/watch/087036ca7f33c8eb79b08152b4dd75c1/', + 'only_matching': True, + }, { + # episode, geo-restricted, tv provided required + 'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - settings = self._parse_json(self._search_regex( - r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', - webpage, 'drupal settings'), video_id) - fox_pdk_player = settings['fox_pdk_player'] - release_url = fox_pdk_player['release_url'] - query = { - 'mbr': 'true', - 'switch': 'http' - } - if fox_pdk_player.get('access') == 'locked': - ap_p = settings['foxAdobePassProvider'] - rating = ap_p.get('videoRating') - if rating == 'n/a': - rating = None - resource = self._get_mvpd_resource('fbc-fox', None, ap_p['videoGUID'], rating) - query['auth'] = self._extract_mvpd_auth(url, video_id, 'fbc-fox', resource) + video = self._download_json( + 'https://api.fox.com/fbc-content/v1_4/video/%s' % video_id, + video_id, headers={ + 'apikey': 'abdcbed02c124d393b39e818a4312055', + 'Content-Type': 'application/json', + 'Referer': url, + }) - info = self._search_json_ld(webpage, video_id, fatal=False) - info.update({ - '_type': 'url_transparent', - 'ie_key': 'ThePlatform', - 'url': smuggle_url(update_url_query(release_url, query), {'force_smil_url': True}), + title = video['name'] + + m3u8_url = self._download_json( + video['videoRelease']['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) + + 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')) + age_limit = parse_age_limit(video.get('contentRating')) + + 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')) + + if data.get('authRequired'): + # TODO: AP + pass + + return { 'id': video_id, - }) - - return info + 'title': title, + 'description': description, + 'duration': duration, + 'timestamp': timestamp, + 'age_limit': age_limit, + 'creator': creator, + 'series': series, + 'season_number': season_number, + 'episode': episode, + 'episode_number': episode_number, + 'release_year': release_year, + 'formats': formats, + } diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index b83c18380..7d0edf09c 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -1879,6 +1879,15 @@ class GenericIE(InfoExtractor): 'title': 'Building A Business Online: Principal Chairs Q & A', }, }, + { + # multiple HTML5 videos on one page + 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html', + 'info_dict': { + 'id': 'keyscenarios', + 'title': 'Rescue Kit 14 Free Edition - Getting started', + }, + 'playlist_count': 4, + } # { # # TODO: find another test # # http://schema.org/VideoObject @@ -2849,13 +2858,20 @@ class GenericIE(InfoExtractor): # Look for HTML5 media entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls') if entries: - for entry in entries: - entry.update({ + if len(entries) == 1: + entries[0].update({ 'id': video_id, 'title': video_title, }) + else: + for num, entry in enumerate(entries, start=1): + entry.update({ + 'id': '%s-%s' % (video_id, num), + 'title': '%s (%d)' % (video_title, num), + }) + for entry in entries: self._sort_formats(entry['formats']) - return self.playlist_result(entries) + return self.playlist_result(entries, video_id, video_title) jwplayer_data = self._find_jwplayer_data( webpage, video_id, transform_source=js_to_json) diff --git a/youtube_dl/extractor/heise.py b/youtube_dl/extractor/heise.py index 382f32771..82e11a7d8 100644 --- a/youtube_dl/extractor/heise.py +++ b/youtube_dl/extractor/heise.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals from .common import InfoExtractor +from .youtube import YoutubeIE from ..utils import ( determine_ext, int_or_none, @@ -25,6 +26,22 @@ class HeiseIE(InfoExtractor): 'description': 'md5:c934cbfb326c669c2bcabcbe3d3fcd20', 'thumbnail': r're:^https?://.*/gallery/$', } + }, { + # YouTube embed + 'url': 'http://www.heise.de/newsticker/meldung/Netflix-In-20-Jahren-vom-Videoverleih-zum-TV-Revolutionaer-3814130.html', + 'md5': 'e403d2b43fea8e405e88e3f8623909f1', + 'info_dict': { + 'id': '6kmWbXleKW4', + 'ext': 'mp4', + 'title': 'NEU IM SEPTEMBER | Netflix', + 'description': 'md5:2131f3c7525e540d5fd841de938bd452', + 'upload_date': '20170830', + 'uploader': 'Netflix Deutschland, Österreich und Schweiz', + 'uploader_id': 'netflixdach', + }, + 'params': { + 'skip_download': True, + }, }, { 'url': 'http://www.heise.de/ct/artikel/c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2403911.html', 'only_matching': True, @@ -40,6 +57,16 @@ class HeiseIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + title = self._html_search_meta('fulltitle', webpage, default=None) + if not title or title == "c't": + title = self._search_regex( + r']+class="videoplayerjw"[^>]+data-title="([^"]+)"', + webpage, 'title') + + yt_urls = YoutubeIE._extract_urls(webpage) + if yt_urls: + return self.playlist_from_matches(yt_urls, video_id, title, ie=YoutubeIE.ie_key()) + container_id = self._search_regex( r'
]+data-container="([0-9]+)"', webpage, 'container ID') @@ -47,12 +74,6 @@ class HeiseIE(InfoExtractor): r'
]+data-sequenz="([0-9]+)"', webpage, 'sequenz ID') - title = self._html_search_meta('fulltitle', webpage, default=None) - if not title or title == "c't": - title = self._search_regex( - r']+class="videoplayerjw"[^>]+data-title="([^"]+)"', - webpage, 'title') - doc = self._download_xml( 'http://www.heise.de/videout/feed', video_id, query={ 'container': container_id, diff --git a/youtube_dl/extractor/kakao.py b/youtube_dl/extractor/kakao.py new file mode 100644 index 000000000..7fa140b0c --- /dev/null +++ b/youtube_dl/extractor/kakao.py @@ -0,0 +1,149 @@ +# coding: utf-8 + +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + int_or_none, + unified_timestamp, + update_url_query, +) + + +class KakaoIE(InfoExtractor): + _VALID_URL = r'https?://tv\.kakao\.com/channel/(?P\d+)/cliplink/(?P\d+)' + _API_BASE = 'http://tv.kakao.com/api/v1/ft/cliplinks' + + _TESTS = [{ + 'url': 'http://tv.kakao.com/channel/2671005/cliplink/301965083', + 'md5': '702b2fbdeb51ad82f5c904e8c0766340', + 'info_dict': { + 'id': '301965083', + 'ext': 'mp4', + 'title': '乃木坂46 バナナマン 「3期生紹介コーナーが始動！顔高低差GPも！」 『乃木坂工事中』', + 'uploader_id': 2671005, + 'uploader': '그랑그랑이', + 'timestamp': 1488160199, + 'upload_date': '20170227', + } + }, { + 'url': 'http://tv.kakao.com/channel/2653210/cliplink/300103180', + 'md5': 'a8917742069a4dd442516b86e7d66529', + 'info_dict': { + 'id': '300103180', + 'ext': 'mp4', + 'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회', + 'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)', + 'uploader_id': 2653210, + 'uploader': '쇼 음악중심', + 'timestamp': 1485684628, + 'upload_date': '20170129', + } + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + player_header = { + 'Referer': update_url_query( + 'http://tv.kakao.com/embed/player/cliplink/%s' % video_id, { + 'service': 'kakao_tv', + 'autoplay': '1', + 'profile': 'HIGH', + 'wmode': 'transparent', + }) + } + + QUERY_COMMON = { + 'player': 'monet_html5', + 'referer': url, + 'uuid': '', + 'service': 'kakao_tv', + 'section': '', + 'dteType': 'PC', + } + + query = QUERY_COMMON.copy() + query['fields'] = 'clipLink,clip,channel,hasPlusFriend,-service,-tagList' + impress = self._download_json( + '%s/%s/impress' % (self._API_BASE, video_id), + video_id, 'Downloading video info', + query=query, headers=player_header) + + clip_link = impress['clipLink'] + clip = clip_link['clip'] + + title = clip.get('title') or clip_link.get('displayTitle') + + tid = impress.get('tid', '') + + query = QUERY_COMMON.copy() + query.update({ + 'tid': tid, + 'profile': 'HIGH', + }) + raw = self._download_json( + '%s/%s/raw' % (self._API_BASE, video_id), + video_id, 'Downloading video formats info', + query=query, headers=player_header) + + formats = [] + for fmt in raw.get('outputList', []): + try: + profile_name = fmt['profile'] + fmt_url_json = self._download_json( + '%s/%s/raw/videolocation' % (self._API_BASE, video_id), + video_id, + 'Downloading video URL for profile %s' % profile_name, + query={ + 'service': 'kakao_tv', + 'section': '', + 'tid': tid, + 'profile': profile_name + }, headers=player_header, fatal=False) + + if fmt_url_json is None: + continue + + fmt_url = fmt_url_json['url'] + formats.append({ + 'url': fmt_url, + 'format_id': profile_name, + 'width': int_or_none(fmt.get('width')), + 'height': int_or_none(fmt.get('height')), + 'format_note': fmt.get('label'), + 'filesize': int_or_none(fmt.get('filesize')) + }) + except KeyError: + pass + self._sort_formats(formats) + + thumbs = [] + for thumb in clip.get('clipChapterThumbnailList', []): + thumbs.append({ + 'url': thumb.get('thumbnailUrl'), + 'id': compat_str(thumb.get('timeInSec')), + 'preference': -1 if thumb.get('isDefault') else 0 + }) + top_thumbnail = clip.get('thumbnailUrl') + if top_thumbnail: + thumbs.append({ + 'url': top_thumbnail, + 'preference': 10, + }) + + return { + 'id': video_id, + 'title': title, + 'description': clip.get('description'), + 'uploader': clip_link.get('channel', {}).get('name'), + 'uploader_id': clip_link.get('channelId'), + 'thumbnails': thumbs, + 'timestamp': unified_timestamp(clip_link.get('createTime')), + 'duration': int_or_none(clip.get('duration')), + 'view_count': int_or_none(clip.get('playCount')), + 'like_count': int_or_none(clip.get('likeCount')), + 'comment_count': int_or_none(clip.get('commentCount')), + 'formats': formats, + } diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py index d2f75296a..1b6f5091d 100644 --- a/youtube_dl/extractor/lynda.py +++ b/youtube_dl/extractor/lynda.py @@ -94,7 +94,7 @@ class LyndaBaseIE(InfoExtractor): class LyndaIE(LyndaBaseIE): IE_NAME = 'lynda' IE_DESC = 'lynda.com videos' - _VALID_URL = r'https?://(?:www\.)?lynda\.com/(?:[^/]+/[^/]+/(?P\d+)|player/embed)/(?P\d+)' + _VALID_URL = r'https?://(?:www\.)?(?:lynda\.com|educourse\.ga)/(?:[^/]+/[^/]+/(?P\d+)|player/embed)/(?P\d+)' _TIMECODE_REGEX = r'\[(?P\d+:\d+:\d+[\.,]\d+)\]' @@ -110,6 +110,9 @@ class LyndaIE(LyndaBaseIE): }, { 'url': 'https://www.lynda.com/player/embed/133770?tr=foo=1;bar=g;fizz=rt&fs=0', 'only_matching': True, + }, { + 'url': 'https://educourse.ga/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html', + 'only_matching': True, }] def _raise_unavailable(self, video_id): @@ -253,7 +256,7 @@ class LyndaCourseIE(LyndaBaseIE): # Course link equals to welcome/introduction video link of same course # We will recognize it as course link - _VALID_URL = r'https?://(?:www|m)\.lynda\.com/(?P[^/]+/[^/]+/(?P\d+))-\d\.html' + _VALID_URL = r'https?://(?:www|m)\.(?:lynda\.com|educourse\.ga)/(?P[^/]+/[^/]+/(?P\d+))-\d\.html' def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index f6360cce6..f331db890 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -12,12 +12,16 @@ from ..compat import ( compat_str, compat_urllib_parse_unquote, compat_urlparse, + compat_zip ) from ..utils import ( clean_html, ExtractorError, + int_or_none, OnDemandPagedList, str_to_int, + try_get, + urljoin, ) @@ -54,27 +58,12 @@ class MixcloudIE(InfoExtractor): 'only_matching': True, }] - _keys = [ - 'return { requestAnimationFrame: function(callback) { callback(); }, innerHeight: 500 };', - 'pleasedontdownloadourmusictheartistswontgetpaid', - 'window.addEventListener = window.addEventListener || function() {};', - '(function() { return new Date().toLocaleDateString(); })()' - ] - _current_key = None - - # See https://www.mixcloud.com/media/js2/www_js_2.9e23256562c080482435196ca3975ab5.js - def _decrypt_play_info(self, play_info, video_id): - play_info = base64.b64decode(play_info.encode('ascii')) - for num, key in enumerate(self._keys, start=1): - try: - return self._parse_json( - ''.join([ - compat_chr(compat_ord(ch) ^ compat_ord(key[idx % len(key)])) - for idx, ch in enumerate(play_info)]), - video_id) - except ExtractorError: - if num == len(self._keys): - raise + @staticmethod + def _decrypt_xor_cipher(key, ciphertext): + """Encrypt/Decrypt XOR cipher. Both ways are possible because it's XOR.""" + return ''.join([ + compat_chr(compat_ord(ch) ^ compat_ord(k)) + for ch, k in compat_zip(ciphertext, itertools.cycle(key))]) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -84,54 +73,119 @@ class MixcloudIE(InfoExtractor): webpage = self._download_webpage(url, track_id) - if not self._current_key: - js_url = self._search_regex( - r']+\bsrc=["\"](https://(?:www\.)?mixcloud\.com/media/js2/www_js_4\.[^>]+\.js)', - webpage, 'js url', default=None) - if js_url: - js = self._download_webpage(js_url, track_id, fatal=False) - if js: - KEY_RE_TEMPLATE = r'player\s*:\s*{.*?\b%s\s*:\s*(["\'])(?P(?:(?!\1).)+)\1' - for key_name in ('value', 'key_value', 'key_value.*?', '.*?value.*?'): - key = self._search_regex( - KEY_RE_TEMPLATE % key_name, js, 'key', - default=None, group='key') - if key and isinstance(key, compat_str): - self._keys.insert(0, key) - self._current_key = key + # Legacy path + encrypted_play_info = self._search_regex( + r'm-play-info="([^"]+)"', webpage, 'play info', default=None) + + if encrypted_play_info is not None: + # Decode + encrypted_play_info = base64.b64decode(encrypted_play_info) + else: + # New path + full_info_json = self._parse_json(self._html_search_regex( + r'', + webpage, 'play info'), 'play info') + for item in full_info_json: + item_data = try_get( + item, lambda x: x['cloudcast']['data']['cloudcastLookup'], + dict) + if try_get(item_data, lambda x: x['streamInfo']['url']): + info_json = item_data + break + else: + raise ExtractorError('Failed to extract matching stream info') message = self._html_search_regex( r'(?s)]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)', webpage, 'error message', default=None) - encrypted_play_info = self._search_regex( - r'm-play-info="([^"]+)"', webpage, 'play info') + js_url = self._search_regex( + r']+\bsrc=["\"](https://(?:www\.)?mixcloud\.com/media/(?:js2/www_js_4|js/www)\.[^>]+\.js)', + webpage, 'js url') + js = self._download_webpage(js_url, track_id, 'Downloading JS') + # Known plaintext attack + if encrypted_play_info: + kps = ['{"stream_url":'] + kpa_target = encrypted_play_info + else: + kps = ['https://', 'http://'] + kpa_target = base64.b64decode(info_json['streamInfo']['url']) + for kp in kps: + partial_key = self._decrypt_xor_cipher(kpa_target, kp) + for quote in ["'", '"']: + key = self._search_regex( + r'{0}({1}[^{0}]*){0}'.format(quote, re.escape(partial_key)), + js, 'encryption key', default=None) + if key is not None: + break + else: + continue + break + else: + raise ExtractorError('Failed to extract encryption key') - play_info = self._decrypt_play_info(encrypted_play_info, track_id) + if encrypted_play_info is not None: + play_info = self._parse_json(self._decrypt_xor_cipher(key, encrypted_play_info), 'play info') + if message and 'stream_url' not in play_info: + raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True) + song_url = play_info['stream_url'] + formats = [{ + 'format_id': 'normal', + 'url': song_url + }] - if message and 'stream_url' not in play_info: - raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True) + title = self._html_search_regex(r'm-title="([^"]+)"', webpage, 'title') + thumbnail = self._proto_relative_url(self._html_search_regex( + r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail', fatal=False)) + uploader = self._html_search_regex( + r'm-owner-name="([^"]+)"', webpage, 'uploader', fatal=False) + uploader_id = self._search_regex( + r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False) + description = self._og_search_description(webpage) + view_count = str_to_int(self._search_regex( + [r'([0-9,.]+)', + r'(?:m|data)-tooltip=["\']([\d,.]+) plays'], + webpage, 'play count', default=None)) - song_url = play_info['stream_url'] + else: + title = info_json['name'] + thumbnail = urljoin( + 'https://thumbnailer.mixcloud.com/unsafe/600x600/', + try_get(info_json, lambda x: x['picture']['urlRoot'], compat_str)) + uploader = try_get(info_json, lambda x: x['owner']['displayName']) + uploader_id = try_get(info_json, lambda x: x['owner']['username']) + description = try_get(info_json, lambda x: x['description']) + view_count = int_or_none(try_get(info_json, lambda x: x['plays'])) - title = self._html_search_regex(r'm-title="([^"]+)"', webpage, 'title') - thumbnail = self._proto_relative_url(self._html_search_regex( - r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail', fatal=False)) - uploader = self._html_search_regex( - r'm-owner-name="([^"]+)"', webpage, 'uploader', fatal=False) - uploader_id = self._search_regex( - r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False) - description = self._og_search_description(webpage) - view_count = str_to_int(self._search_regex( - [r'([0-9,.]+)', - r'(?:m|data)-tooltip=["\']([\d,.]+) plays'], - webpage, 'play count', default=None)) + stream_info = info_json['streamInfo'] + formats = [] + + 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, base64.b64decode(format_url)) + if not decrypted: + continue + if url_key == 'hlsUrl': + formats.extend(self._extract_m3u8_formats( + decrypted, track_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + elif url_key == 'dashUrl': + formats.extend(self._extract_mpd_formats( + decrypted, track_id, mpd_id='dash', fatal=False)) + else: + formats.append({ + 'format_id': 'http', + 'url': decrypted, + }) + self._sort_formats(formats) return { 'id': track_id, 'title': title, - 'url': song_url, + 'formats': formats, 'description': description, 'thumbnail': thumbnail, 'uploader': uploader, diff --git a/youtube_dl/extractor/morningstar.py b/youtube_dl/extractor/morningstar.py index 320d27bdd..0093bcd6c 100644 --- a/youtube_dl/extractor/morningstar.py +++ b/youtube_dl/extractor/morningstar.py @@ -8,8 +8,8 @@ from .common import InfoExtractor class MorningstarIE(InfoExtractor): IE_DESC = 'morningstar.com' - _VALID_URL = r'https?://(?:www\.)?morningstar\.com/[cC]over/video[cC]enter\.aspx\?id=(?P[0-9]+)' - _TEST = { + _VALID_URL = r'https?://(?:(?:www|news)\.)morningstar\.com/[cC]over/video[cC]enter\.aspx\?id=(?P[0-9]+)' + _TESTS = [{ 'url': 'http://www.morningstar.com/cover/videocenter.aspx?id=615869', 'md5': '6c0acface7a787aadc8391e4bbf7b0f5', 'info_dict': { @@ -19,7 +19,10 @@ class MorningstarIE(InfoExtractor): 'description': "Vanguard's Joel Dickson on managing higher tax rates for high-income earners and fund capital-gain distributions in 2013.", 'thumbnail': r're:^https?://.*m(?:orning)?star\.com/.+thumb\.jpg$' } - } + }, { + 'url': 'http://news.morningstar.com/cover/videocenter.aspx?id=825556', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index 62db70b43..836a41f06 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -109,10 +109,10 @@ class NBCSportsVPlayerIE(InfoExtractor): _VALID_URL = r'https?://vplayer\.nbcsports\.com/(?:[^/]+/)+(?P[0-9a-zA-Z_]+)' _TESTS = [{ - 'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_share/select/9CsDKds0kvHI', + 'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/9CsDKds0kvHI', 'info_dict': { 'id': '9CsDKds0kvHI', - 'ext': 'flv', + 'ext': 'mp4', 'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d', 'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson', 'timestamp': 1426270238, @@ -120,7 +120,7 @@ class NBCSportsVPlayerIE(InfoExtractor): 'uploader': 'NBCU-SPORTS', } }, { - 'url': 'http://vplayer.nbcsports.com/p/BxmELC/nbc_embedshare/select/_hqLjQ95yx8Z', + 'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/media/_hqLjQ95yx8Z', 'only_matching': True, }] @@ -134,7 +134,8 @@ class NBCSportsVPlayerIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - theplatform_url = self._og_search_video_url(webpage) + theplatform_url = self._og_search_video_url(webpage).replace( + 'vplayer.nbcsports.com', 'player.theplatform.com') return self.url_result(theplatform_url, 'ThePlatform') diff --git a/youtube_dl/extractor/noovo.py b/youtube_dl/extractor/noovo.py index f7fa098a5..974de3c3e 100644 --- a/youtube_dl/extractor/noovo.py +++ b/youtube_dl/extractor/noovo.py @@ -6,6 +6,7 @@ from .common import InfoExtractor from ..compat import compat_str from ..utils import ( int_or_none, + js_to_json, smuggle_url, try_get, ) @@ -24,8 +25,6 @@ class NoovoIE(InfoExtractor): 'timestamp': 1491399228, 'upload_date': '20170405', 'uploader_id': '618566855001', - 'creator': 'vtele', - 'view_count': int, 'series': 'RPM+', }, 'params': { @@ -37,13 +36,11 @@ class NoovoIE(InfoExtractor): 'info_dict': { 'id': '5395865725001', 'title': 'Épisode 13 : Les retrouvailles', - 'description': 'md5:336d5ebc5436534e61d16e63ddfca327', + 'description': 'md5:888c3330f0c1b4476c5bc99a1c040473', 'ext': 'mp4', 'timestamp': 1492019320, 'upload_date': '20170412', 'uploader_id': '618566855001', - 'creator': 'vtele', - 'view_count': int, 'series': "L'amour est dans le pré", 'season_number': 5, 'episode': 'Épisode 13', @@ -58,40 +55,46 @@ class NoovoIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - data = self._download_json( - 'http://api.noovo.ca/api/v1/pages/single-episode/%s' % video_id, - video_id)['data'] + webpage = self._download_webpage(url, video_id) - content = try_get(data, lambda x: x['contents'][0]) + bc_url = BrightcoveNewIE._extract_url(self, webpage) - brightcove_id = data.get('brightcoveId') or content['brightcoveId'] + data = self._parse_json( + self._search_regex( + r'(?s)dataLayer\.push\(\s*({.+?})\s*\);', webpage, 'data', + default='{}'), + video_id, transform_source=js_to_json, fatal=False) + + title = try_get( + data, lambda x: x['video']['nom'], + compat_str) or self._html_search_meta( + 'dcterms.Title', webpage, 'title', fatal=True) + + description = self._html_search_meta( + ('dcterms.Description', 'description'), webpage, 'description') series = try_get( - data, ( - lambda x: x['show']['title'], - lambda x: x['season']['show']['title']), - compat_str) + data, lambda x: x['emission']['nom']) or self._search_regex( + r']+class="banner-card__subtitle h4"[^>]*>([^<]+)', + webpage, 'series', default=None) - episode = None - og = data.get('og') - if isinstance(og, dict) and og.get('type') == 'video.episode': - episode = og.get('title') + season_el = try_get(data, lambda x: x['emission']['saison'], dict) or {} + season = try_get(season_el, lambda x: x['nom'], compat_str) + season_number = int_or_none(try_get(season_el, lambda x: x['numero'])) - video = content or data + episode_el = try_get(season_el, lambda x: x['episode'], dict) or {} + episode = try_get(episode_el, lambda x: x['nom'], compat_str) + episode_number = int_or_none(try_get(episode_el, lambda x: x['numero'])) return { '_type': 'url_transparent', 'ie_key': BrightcoveNewIE.ie_key(), - 'url': smuggle_url( - self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, - {'geo_countries': ['CA']}), - 'id': brightcove_id, - 'title': video.get('title'), - 'creator': video.get('source'), - 'view_count': int_or_none(video.get('viewsCount')), + 'url': smuggle_url(bc_url, {'geo_countries': ['CA']}), + 'title': title, + 'description': description, 'series': series, - 'season_number': int_or_none(try_get( - data, lambda x: x['season']['seasonNumber'])), + 'season': season, + 'season_number': season_number, 'episode': episode, - 'episode_number': int_or_none(data.get('episodeNumber')), + 'episode_number': episode_number, } diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index d8036b54a..b50d6c77b 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -1,14 +1,244 @@ # coding: utf-8 from __future__ import unicode_literals +import json +import os import re +import subprocess +import tempfile from .common import InfoExtractor -from ..compat import compat_chr -from ..utils import ( - determine_ext, - ExtractorError, +from ..compat import ( + compat_urlparse, + compat_kwargs, ) +from ..utils import ( + check_executable, + determine_ext, + encodeArgument, + ExtractorError, + get_element_by_id, + get_exe_version, + is_outdated_version, + std_headers, +) + + +def cookie_to_dict(cookie): + cookie_dict = { + 'name': cookie.name, + 'value': cookie.value, + } + if cookie.port_specified: + cookie_dict['port'] = cookie.port + if cookie.domain_specified: + cookie_dict['domain'] = cookie.domain + if cookie.path_specified: + cookie_dict['path'] = cookie.path + if cookie.expires is not None: + cookie_dict['expires'] = cookie.expires + if cookie.secure is not None: + cookie_dict['secure'] = cookie.secure + if cookie.discard is not None: + cookie_dict['discard'] = cookie.discard + try: + if (cookie.has_nonstandard_attr('httpOnly') or + cookie.has_nonstandard_attr('httponly') or + cookie.has_nonstandard_attr('HttpOnly')): + cookie_dict['httponly'] = True + except TypeError: + pass + return cookie_dict + + +def cookie_jar_to_list(cookie_jar): + return [cookie_to_dict(cookie) for cookie in cookie_jar] + + +class PhantomJSwrapper(object): + """PhantomJS wrapper class + + This class is experimental. + """ + + _TEMPLATE = r''' + phantom.onError = function(msg, trace) {{ + var msgStack = ['PHANTOM ERROR: ' + msg]; + if(trace && trace.length) {{ + msgStack.push('TRACE:'); + trace.forEach(function(t) {{ + msgStack.push(' -> ' + (t.file || t.sourceURL) + ': ' + t.line + + (t.function ? ' (in function ' + t.function +')' : '')); + }}); + }} + console.error(msgStack.join('\n')); + phantom.exit(1); + }}; + var page = require('webpage').create(); + var fs = require('fs'); + var read = {{ mode: 'r', charset: 'utf-8' }}; + var write = {{ mode: 'w', charset: 'utf-8' }}; + JSON.parse(fs.read("{cookies}", read)).forEach(function(x) {{ + phantom.addCookie(x); + }}); + page.settings.resourceTimeout = {timeout}; + page.settings.userAgent = "{ua}"; + page.onLoadStarted = function() {{ + page.evaluate(function() {{ + delete window._phantom; + delete window.callPhantom; + }}); + }}; + var saveAndExit = function() {{ + fs.write("{html}", page.content, write); + fs.write("{cookies}", JSON.stringify(phantom.cookies), write); + phantom.exit(); + }}; + page.onLoadFinished = function(status) {{ + if(page.url === "") {{ + page.setContent(fs.read("{html}", read), "{url}"); + }} + else {{ + {jscode} + }} + }}; + page.open(""); + ''' + + _TMP_FILE_NAMES = ['script', 'html', 'cookies'] + + @staticmethod + def _version(): + return get_exe_version('phantomjs', version_re=r'([0-9.]+)') + + def __init__(self, extractor, required_version=None, timeout=10000): + self.exe = check_executable('phantomjs', ['-v']) + if not self.exe: + raise ExtractorError('PhantomJS executable not found in PATH, ' + 'download it from http://phantomjs.org', + expected=True) + + self.extractor = extractor + + if required_version: + version = self._version() + if is_outdated_version(version, required_version): + self.extractor._downloader.report_warning( + 'Your copy of PhantomJS is outdated, update it to version ' + '%s or newer if you encounter any errors.' % required_version) + + self.options = { + 'timeout': timeout, + } + self._TMP_FILES = {} + for name in self._TMP_FILE_NAMES: + tmp = tempfile.NamedTemporaryFile(delete=False) + tmp.close() + self._TMP_FILES[name] = tmp + + def __del__(self): + for name in self._TMP_FILE_NAMES: + try: + os.remove(self._TMP_FILES[name].name) + except: + pass + + def _save_cookies(self, url): + cookies = cookie_jar_to_list(self.extractor._downloader.cookiejar) + for cookie in cookies: + if 'path' not in cookie: + cookie['path'] = '/' + if 'domain' not in cookie: + cookie['domain'] = compat_urlparse.urlparse(url).netloc + with open(self._TMP_FILES['cookies'].name, 'wb') as f: + f.write(json.dumps(cookies).encode('utf-8')) + + def _load_cookies(self): + with open(self._TMP_FILES['cookies'].name, 'rb') as f: + cookies = json.loads(f.read().decode('utf-8')) + for cookie in cookies: + if cookie['httponly'] is True: + cookie['rest'] = {'httpOnly': None} + if 'expiry' in cookie: + cookie['expire_time'] = cookie['expiry'] + self.extractor._set_cookie(**compat_kwargs(cookie)) + + def get(self, url, html=None, video_id=None, note=None, note2='Executing JS on webpage', headers={}, jscode='saveAndExit();'): + """ + Downloads webpage (if needed) and executes JS + + Params: + url: website url + html: optional, html code of website + video_id: video id + note: optional, displayed when downloading webpage + note2: optional, displayed when executing JS + headers: custom http headers + jscode: code to be executed when page is loaded + + Returns tuple with: + * downloaded website (after JS execution) + * anything you print with `console.log` (but not inside `page.execute`!) + + In most cases you don't need to add any `jscode`. + It is executed in `page.onLoadFinished`. + `saveAndExit();` is mandatory, use it instead of `phantom.exit()` + It is possible to wait for some element on the webpage, for example: + var check = function() { + var elementFound = page.evaluate(function() { + return document.querySelector('#b.done') !== null; + }); + if(elementFound) + saveAndExit(); + else + window.setTimeout(check, 500); + } + + page.evaluate(function(){ + document.querySelector('#a').click(); + }); + check(); + """ + if 'saveAndExit();' not in jscode: + raise ExtractorError('`saveAndExit();` not found in `jscode`') + if not html: + html = self.extractor._download_webpage(url, video_id, note=note, headers=headers) + with open(self._TMP_FILES['html'].name, 'wb') as f: + f.write(html.encode('utf-8')) + + self._save_cookies(url) + + replaces = self.options + replaces['url'] = url + user_agent = headers.get('User-Agent') or std_headers['User-Agent'] + replaces['ua'] = user_agent.replace('"', '\\"') + replaces['jscode'] = jscode + + for x in self._TMP_FILE_NAMES: + replaces[x] = self._TMP_FILES[x].name.replace('\\', '\\\\').replace('"', '\\"') + + with open(self._TMP_FILES['script'].name, 'wb') as f: + f.write(self._TEMPLATE.format(**replaces).encode('utf-8')) + + if video_id is None: + self.extractor.to_screen('%s' % (note2,)) + else: + self.extractor.to_screen('%s: %s' % (video_id, note2)) + + p = subprocess.Popen([ + self.exe, '--ssl-protocol=any', + self._TMP_FILES['script'].name + ], stdout=subprocess.PIPE, stderr=subprocess.PIPE) + out, err = p.communicate() + if p.returncode != 0: + raise ExtractorError( + 'Executing JS failed\n:' + encodeArgument(err)) + with open(self._TMP_FILES['html'].name, 'rb') as f: + html = f.read().decode('utf-8') + + self._load_cookies() + + return (html, encodeArgument(out)) class OpenloadIE(InfoExtractor): @@ -58,6 +288,8 @@ class OpenloadIE(InfoExtractor): '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' + @staticmethod def _extract_urls(webpage): return re.findall( @@ -66,47 +298,22 @@ class OpenloadIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id) + url = 'https://openload.co/embed/%s/' % video_id + headers = { + 'User-Agent': self._USER_AGENT, + } + + webpage = self._download_webpage(url, video_id, headers=headers) if 'File not found' in webpage or 'deleted by the owner' in webpage: - raise ExtractorError('File not found', expected=True) + raise ExtractorError('File not found', expected=True, video_id=video_id) - ol_id = self._search_regex( - ']+id="[^"]+"[^>]*>([0-9A-Za-z]+)', - webpage, 'openload ID') + phantom = PhantomJSwrapper(self, required_version='2.0') + webpage, _ = phantom.get(url, html=webpage, video_id=video_id, headers=headers) - decoded = '' - a = ol_id[0:24] - b = [] - for i in range(0, len(a), 8): - b.append(int(a[i:i + 8] or '0', 16)) - ol_id = ol_id[24:] - j = 0 - k = 0 - while j < len(ol_id): - c = 128 - d = 0 - e = 0 - f = 0 - _more = True - while _more: - if j + 1 >= len(ol_id): - c = 143 - f = int(ol_id[j:j + 2] or '0', 16) - j += 2 - d += (f & 127) << e - e += 7 - _more = f >= c - g = d ^ b[k % 3] - for i in range(4): - char_dec = (g >> 8 * i) & (c + 127) - char = compat_chr(char_dec) - if char != '#': - decoded += char - k += 1 + decoded_id = get_element_by_id('streamurl', webpage) - video_url = 'https://openload.co/stream/%s?mime=true' - video_url = video_url % decoded + video_url = 'https://openload.co/stream/%s?mime=true' % decoded_id title = self._og_search_title(webpage, default=None) or self._search_regex( r']+class=["\']title["\'][^>]*>([^<]+)', webpage, @@ -114,15 +321,17 @@ class OpenloadIE(InfoExtractor): 'description', webpage, 'title', fatal=True) entries = self._parse_html5_media_entries(url, webpage, video_id) - subtitles = entries[0]['subtitles'] if entries else None + entry = entries[0] if entries else {} + subtitles = entry.get('subtitles') info_dict = { 'id': video_id, 'title': title, - 'thumbnail': self._og_search_thumbnail(webpage, default=None), + 'thumbnail': entry.get('thumbnail') or self._og_search_thumbnail(webpage, default=None), 'url': video_url, # Seems all videos have extensions in their titles 'ext': determine_ext(title, 'mp4'), 'subtitles': subtitles, + 'http_headers': headers, } return info_dict diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index cc296eabd..74fe8017e 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -6,14 +6,15 @@ import re from .common import InfoExtractor from ..compat import compat_str from ..utils import ( - HEADRequest, - unified_strdate, - strip_jsonp, - int_or_none, - float_or_none, determine_ext, + float_or_none, + HEADRequest, + int_or_none, + orderedSet, remove_end, + strip_jsonp, unescapeHTML, + unified_strdate, ) @@ -307,3 +308,108 @@ class ORFIPTVIE(InfoExtractor): 'upload_date': upload_date, 'formats': formats, } + + +class ORFFM4StoryIE(InfoExtractor): + IE_NAME = 'orf:fm4:story' + IE_DESC = 'fm4.orf.at stories' + _VALID_URL = r'https?://fm4\.orf\.at/stories/(?P\d+)' + + _TEST = { + 'url': 'http://fm4.orf.at/stories/2865738/', + 'playlist': [{ + 'md5': 'e1c2c706c45c7b34cf478bbf409907ca', + 'info_dict': { + 'id': '547792', + 'ext': 'flv', + 'title': 'Manu Delago und Inner Tongue live', + 'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.', + 'duration': 1748.52, + 'thumbnail': r're:^https?://.*\.jpg$', + 'upload_date': '20170913', + }, + }, { + 'md5': 'c6dd2179731f86f4f55a7b49899d515f', + 'info_dict': { + 'id': '547798', + 'ext': 'flv', + 'title': 'Manu Delago und Inner Tongue live (2)', + 'duration': 1504.08, + 'thumbnail': r're:^https?://.*\.jpg$', + 'upload_date': '20170913', + 'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.', + }, + }], + } + + def _real_extract(self, url): + story_id = self._match_id(url) + webpage = self._download_webpage(url, story_id) + + entries = [] + all_ids = orderedSet(re.findall(r'data-video(?:id)?="(\d+)"', webpage)) + for idx, video_id in enumerate(all_ids): + data = self._download_json( + 'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id, + video_id)[0] + + duration = float_or_none(data['duration'], 1000) + + video = data['sources']['q8c'] + load_balancer_url = video['loadBalancerUrl'] + abr = int_or_none(video.get('audioBitrate')) + vbr = int_or_none(video.get('bitrate')) + fps = int_or_none(video.get('videoFps')) + width = int_or_none(video.get('videoWidth')) + height = int_or_none(video.get('videoHeight')) + thumbnail = video.get('preview') + + rendition = self._download_json( + load_balancer_url, video_id, transform_source=strip_jsonp) + + f = { + 'abr': abr, + 'vbr': vbr, + 'fps': fps, + 'width': width, + 'height': height, + } + + formats = [] + for format_id, format_url in rendition['redirect'].items(): + if format_id == 'rtmp': + ff = f.copy() + ff.update({ + 'url': format_url, + 'format_id': format_id, + }) + formats.append(ff) + elif determine_ext(format_url) == 'f4m': + formats.extend(self._extract_f4m_formats( + format_url, video_id, f4m_id=format_id)) + elif determine_ext(format_url) == 'm3u8': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', m3u8_id=format_id)) + else: + continue + self._sort_formats(formats) + + title = remove_end(self._og_search_title(webpage), ' - fm4.ORF.at') + if idx >= 1: + # Titles are duplicates, make them unique + title += ' (' + str(idx + 1) + ')' + description = self._og_search_description(webpage) + upload_date = unified_strdate(self._html_search_meta( + 'dc.date', webpage, 'upload date')) + + entries.append({ + 'id': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'formats': formats, + }) + + return self.playlist_result(entries) diff --git a/youtube_dl/extractor/popcorntv.py b/youtube_dl/extractor/popcorntv.py new file mode 100644 index 000000000..ac901f426 --- /dev/null +++ b/youtube_dl/extractor/popcorntv.py @@ -0,0 +1,78 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + extract_attributes, + int_or_none, + unified_timestamp, +) + + +class PopcornTVIE(InfoExtractor): + _VALID_URL = r'https?://[^/]+\.popcorntv\.it/guarda/(?P[^/]+)/(?P\d+)' + _TESTS = [{ + 'url': 'https://animemanga.popcorntv.it/guarda/food-wars-battaglie-culinarie-episodio-01/9183', + 'md5': '47d65a48d147caf692ab8562fe630b45', + 'info_dict': { + 'id': '9183', + 'display_id': 'food-wars-battaglie-culinarie-episodio-01', + 'ext': 'mp4', + 'title': 'Food Wars, Battaglie Culinarie | Episodio 01', + 'description': 'md5:b8bea378faae4651d3b34c6e112463d0', + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1497610857, + 'upload_date': '20170616', + 'duration': 1440, + 'view_count': int, + }, + }, { + 'url': 'https://cinema.popcorntv.it/guarda/smash-cut/10433', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id, video_id = mobj.group('display_id', 'id') + + webpage = self._download_webpage(url, display_id) + + m3u8_url = extract_attributes( + self._search_regex( + r'(]+itemprop=["\'](?:content|embed)Url[^>]*>)', + webpage, 'content' + ))['href'] + + formats = self._extract_m3u8_formats( + m3u8_url, display_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + + title = self._search_regex( + r']+itemprop=["\']name[^>]*>([^<]+)', webpage, + 'title', default=None) or self._og_search_title(webpage) + + description = self._html_search_regex( + r'(?s)]+itemprop=["\']description[^>]*>(.+?)', + webpage, 'description', fatal=False) + 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( + 'interactionCount', webpage, 'view count')) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'view_count': view_count, + 'formats': formats, + } diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index 889fa7628..89d89b65a 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -7,43 +7,84 @@ import itertools from .common import InfoExtractor from ..compat import ( compat_str, + compat_parse_qs, + compat_urllib_parse_urlparse, ) from ..utils import ( determine_ext, - unified_strdate, + bool_or_none, + int_or_none, + try_get, + unified_timestamp, ) -class RutubeIE(InfoExtractor): +class RutubeBaseIE(InfoExtractor): + def _extract_video(self, video, video_id=None, require_title=True): + title = video['title'] if require_title else video.get('title') + + age_limit = video.get('is_adult') + if age_limit is not None: + age_limit = 18 if age_limit is True else 0 + + uploader_id = try_get(video, lambda x: x['author']['id']) + category = try_get(video, lambda x: x['category']['name']) + + return { + 'id': video.get('id') or video_id, + 'title': title, + 'description': video.get('description'), + 'thumbnail': video.get('thumbnail_url'), + 'duration': int_or_none(video.get('duration')), + 'uploader': try_get(video, lambda x: x['author']['name']), + 'uploader_id': compat_str(uploader_id) if uploader_id else None, + 'timestamp': unified_timestamp(video.get('created_ts')), + 'category': [category] if category else None, + 'age_limit': age_limit, + 'view_count': int_or_none(video.get('hits')), + 'comment_count': int_or_none(video.get('comments_count')), + 'is_live': bool_or_none(video.get('is_livestream')), + } + + +class RutubeIE(RutubeBaseIE): IE_NAME = 'rutube' IE_DESC = 'Rutube videos' _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/(?P[\da-z]{32})' _TESTS = [{ 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/', + 'md5': '79938ade01294ef7e27574890d0d3769', 'info_dict': { 'id': '3eac3b4561676c17df9132a9a1e62e3e', - 'ext': 'mp4', + 'ext': 'flv', 'title': 'Раненный кенгуру забежал в аптеку', 'description': 'http://www.ntdtv.ru ', 'duration': 80, 'uploader': 'NTDRussian', 'uploader_id': '29790', + 'timestamp': 1381943602, 'upload_date': '20131016', 'age_limit': 0, }, - 'params': { - # It requires ffmpeg (m3u8 download) - 'skip_download': True, - }, }, { 'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661', 'only_matching': True, }, { 'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661', 'only_matching': True, + }, { + 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252', + 'only_matching': True, + }, { + 'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source', + 'only_matching': True, }] + @classmethod + def suitable(cls, url): + return False if RutubePlaylistIE.suitable(url) else super(RutubeIE, cls).suitable(url) + @staticmethod def _extract_urls(webpage): return [mobj.group('url') for mobj in re.finditer( @@ -52,12 +93,12 @@ class RutubeIE(InfoExtractor): 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') - # Some videos don't have the author field - author = video.get('author') or {} + info = self._extract_video(video, video_id) options = self._download_json( 'http://rutube.ru/api/play/options/%s/?format=json' % video_id, @@ -79,19 +120,8 @@ class RutubeIE(InfoExtractor): }) self._sort_formats(formats) - return { - 'id': video['id'], - 'title': video['title'], - 'description': video['description'], - 'duration': video['duration'], - 'view_count': video['hits'], - 'formats': formats, - 'thumbnail': video['thumbnail_url'], - 'uploader': author.get('name'), - 'uploader_id': compat_str(author['id']) if author else None, - 'upload_date': unified_strdate(video['created_ts']), - 'age_limit': 18 if video['is_adult'] else 0, - } + info['formats'] = formats + return info class RutubeEmbedIE(InfoExtractor): @@ -103,7 +133,8 @@ class RutubeEmbedIE(InfoExtractor): 'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=', 'info_dict': { 'id': 'a10e53b86e8f349080f718582ce4c661', - 'ext': 'mp4', + 'ext': 'flv', + 'timestamp': 1387830582, 'upload_date': '20131223', 'uploader_id': '297833', 'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix

восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89', @@ -111,7 +142,7 @@ class RutubeEmbedIE(InfoExtractor): 'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89', }, 'params': { - 'skip_download': 'Requires ffmpeg', + 'skip_download': True, }, }, { 'url': 'http://rutube.ru/play/embed/8083783', @@ -125,10 +156,51 @@ class RutubeEmbedIE(InfoExtractor): canonical_url = self._html_search_regex( r'\d+)' @@ -142,27 +214,8 @@ class RutubeChannelIE(InfoExtractor): _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json' - def _extract_videos(self, channel_id, channel_title=None): - entries = [] - for pagenum in itertools.count(1): - page = self._download_json( - self._PAGE_TEMPLATE % (channel_id, pagenum), - channel_id, 'Downloading page %s' % pagenum) - results = page['results'] - if not results: - break - entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results) - if not page['has_next']: - break - return self.playlist_result(entries, channel_id, channel_title) - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - channel_id = mobj.group('id') - return self._extract_videos(channel_id) - - -class RutubeMovieIE(RutubeChannelIE): +class RutubeMovieIE(RutubePlaylistBaseIE): IE_NAME = 'rutube:movie' IE_DESC = 'Rutube movies' _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P\d+)' @@ -176,11 +229,11 @@ class RutubeMovieIE(RutubeChannelIE): movie = self._download_json( self._MOVIE_TEMPLATE % movie_id, movie_id, 'Downloading movie JSON') - movie_name = movie['name'] - return self._extract_videos(movie_id, movie_name) + return self._extract_playlist( + movie_id, playlist_name=movie.get('name')) -class RutubePersonIE(RutubeChannelIE): +class RutubePersonIE(RutubePlaylistBaseIE): IE_NAME = 'rutube:person' IE_DESC = 'Rutube person videos' _VALID_URL = r'https?://rutube\.ru/video/person/(?P\d+)' @@ -193,3 +246,37 @@ class RutubePersonIE(RutubeChannelIE): }] _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json' + + +class RutubePlaylistIE(RutubePlaylistBaseIE): + IE_NAME = 'rutube:playlist' + IE_DESC = 'Rutube playlists' + _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P\d+)' + _TESTS = [{ + 'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag', + 'info_dict': { + 'id': '3097', + }, + 'playlist_count': 27, + }, { + 'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source', + 'only_matching': True, + }] + + _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json' + + @classmethod + def suitable(cls, url): + if not super(RutubePlaylistIE, cls).suitable(url): + return False + params = compat_parse_qs(compat_urllib_parse_urlparse(url).query) + return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0]) + + def _next_page_url(self, page_num, playlist_id, item_kind): + return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num) + + def _real_extract(self, url): + qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query) + playlist_kind = qs['pl_type'][0] + playlist_id = qs['pl_id'][0] + return self._extract_playlist(playlist_id, item_kind=playlist_kind) diff --git a/youtube_dl/extractor/tv4.py b/youtube_dl/extractor/tv4.py index 7aeb2c620..cfcce020a 100644 --- a/youtube_dl/extractor/tv4.py +++ b/youtube_dl/extractor/tv4.py @@ -18,7 +18,7 @@ class TV4IE(InfoExtractor): tv4\.se/(?:[^/]+)/klipp/(?:.*)-| tv4play\.se/ (?: - (?:program|barn)/(?:[^\?]+)\?video_id=| + (?:program|barn)/(?:[^/]+/|(?:[^\?]+)\?video_id=)| iframe/video/| film/| sport/| @@ -63,6 +63,10 @@ class TV4IE(InfoExtractor): 'url': 'http://www.tv4play.se/barn/looney-tunes?video_id=3062412', 'only_matching': True, }, + { + 'url': 'http://www.tv4play.se/program/farang/3922081', + 'only_matching': True, + } ] def _real_extract(self, url): diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py index 99ff82a5d..46132eda1 100644 --- a/youtube_dl/extractor/tvplay.py +++ b/youtube_dl/extractor/tvplay.py @@ -15,7 +15,9 @@ from ..utils import ( int_or_none, parse_iso8601, qualities, + smuggle_url, try_get, + unsmuggle_url, update_url_query, ) @@ -224,6 +226,9 @@ class TVPlayIE(InfoExtractor): ] def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url, {}) + self._initialize_geo_bypass(smuggled_data.get('geo_countries')) + video_id = self._match_id(url) geo_country = self._search_regex( r'https?://[^/]+\.([a-z]{2})', url, @@ -426,4 +431,9 @@ class ViafreeIE(InfoExtractor): r'currentVideo["\']\s*:\s*.+?["\']id["\']\s*:\s*["\'](\d{6,})', webpage, 'video id') - return self.url_result('mtg:%s' % video_id, TVPlayIE.ie_key()) + return self.url_result( + smuggle_url( + 'mtg:%s' % video_id, + {'geo_countries': [ + compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1]]}), + ie=TVPlayIE.ie_key(), video_id=video_id) diff --git a/youtube_dl/extractor/twentyfourvideo.py b/youtube_dl/extractor/twentyfourvideo.py index 7af11659f..96e0b96e3 100644 --- a/youtube_dl/extractor/twentyfourvideo.py +++ b/youtube_dl/extractor/twentyfourvideo.py @@ -14,7 +14,7 @@ from ..utils import ( class TwentyFourVideoIE(InfoExtractor): IE_NAME = '24video' - _VALID_URL = r'https?://(?P(?:www\.)?24video\.(?:net|me|xxx|sex|tube))/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P\d+)' + _VALID_URL = r'https?://(?P(?:www\.)?24video\.(?:net|me|xxx|sex|tube|adult))/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P\d+)' _TESTS = [{ 'url': 'http://www.24video.net/video/view/1044982', @@ -60,8 +60,8 @@ class TwentyFourVideoIE(InfoExtractor): duration = int_or_none(self._og_search_property( 'duration', webpage, 'duration', fatal=False)) timestamp = parse_iso8601(self._search_regex( - r'