# Conflicts:
#	youtube_dl/extractor/youtube.py
This commit is contained in:
Khang Nguyen 2017-02-09 17:35:04 +07:00
commit 7bcd1167ac
53 changed files with 1729 additions and 401 deletions

View File

@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.01.29*. 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 Issues with outdated version will be rejected.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 **2017.01.29**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.02.07*. 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 Issues with outdated version will be rejected.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 **2017.02.07**
### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
[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 2017.01.29
[debug] youtube-dl version 2017.02.07
[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: {}

View File

@ -6,6 +6,7 @@ python:
- "3.3"
- "3.4"
- "3.5"
- "3.6"
sudo: false
script: nosetests test --verbose
notifications:

View File

@ -200,3 +200,5 @@ Paul Hartmann
Stephen Chen
Fabian Stahl
Bagira
Odd Stråbø
Philip Herzog

View File

@ -1,3 +1,85 @@
version 2017.02.07
Core
* [extractor/common] Fix audio only with audio group in m3u8 (#11995)
+ [downloader/fragment] Respect --no-part
* [extractor/common] Speed-up HTML5 media entries extraction (#11979)
Extractors
* [pornhub] Fix extraction (#11997)
+ [canalplus] Add support for cstar.fr (#11990)
+ [extractor/generic] Improve RTMP support (#11993)
+ [gaskrank] Add support for gaskrank.tv (#11685)
* [bandcamp] Fix extraction for incomplete albums (#11727)
* [iwara] Fix extraction (#11781)
* [googledrive] Fix extraction on Python 3.6
+ [videopress] Add support for videopress.com
+ [afreecatv] Extract RTMP formats
version 2017.02.04.1
Extractors
+ [twitch:stream] Add support for player.twitch.tv (#11971)
* [radiocanada] Fix extraction for toutv rtmp formats
version 2017.02.04
Core
+ Add --playlist-random to shuffle playlists (#11889, #11901)
* [utils] Improve comments processing in js_to_json (#11947)
* [utils] Handle single-line comments in js_to_json
* [downloader/external:ffmpeg] Minimize the use of aac_adtstoasc filter
Extractors
+ [piksel] Add another app token pattern (#11969)
+ [vk] Capture and output author blocked error message (#11965)
+ [turner] Fix secure HLS formats downloading with ffmpeg (#11358, #11373,
#11800)
+ [drtv] Add support for live and radio sections (#1827, #3427)
* [myspace] Fix extraction and extract HLS and HTTP formats
+ [youtube] Add format info for itag 325 and 328
* [vine] Fix extraction (#11955)
- [sportbox] Remove extractor (#11954)
+ [filmon] Add support for filmon.com (#11187)
+ [infoq] Add audio only formats (#11565)
* [douyutv] Improve room id regular expression (#11931)
* [iprima] Fix extraction (#11920, #11896)
* [youtube] Fix ytsearch when cookies are provided (#11924)
* [go] Relax video id regular expression (#11937)
* [facebook] Fix title extraction (#11941)
+ [youtube:playlist] Recognize TL playlists (#11945)
+ [bilibili] Support new Bangumi URLs (#11845)
+ [cbc:watch] Extract audio codec for audio only formats (#11893)
+ [elpais] Fix extraction for some URLs (#11765)
version 2017.02.01
Extractors
+ [facebook] Add another fallback extraction scenario (#11926)
* [prosiebensat1] Fix extraction of descriptions (#11810, #11929)
- [crunchyroll] Remove ScaledBorderAndShadow settings (#9028)
+ [vimeo] Extract upload timestamp
+ [vimeo] Extract license (#8726, #11880)
+ [nrk:series] Add support for series (#11571, #11711)
version 2017.01.31
Core
+ [compat] Add compat_etree_register_namespace
Extractors
* [youtube] Fix extraction for domainless player URLs (#11890, #11891, #11892,
#11894, #11895, #11897, #11900, #11903, #11904, #11906, #11907, #11909,
#11913, #11914, #11915, #11916, #11917, #11918, #11919)
+ [vimeo] Extract both mixed and separated DASH formats
+ [ruutu] Extract DASH formats
* [itv] Fix extraction for python 2.6
version 2017.01.29
Core

View File

@ -182,6 +182,7 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
automatically resized from an initial value
of SIZE.
--playlist-reverse Download playlist videos in reverse order
--playlist-random Download playlist videos in random order
--xattr-set-filesize Set file xattribute ytdl.filesize with
expected file size (experimental)
--hls-prefer-native Use the native HLS downloader instead of

View File

@ -84,6 +84,7 @@
- **bambuser:channel**
- **Bandcamp**
- **Bandcamp:album**
- **bangumi.bilibili.com**: BiliBili番剧
- **bbc**: BBC
- **bbc.co.uk**: BBC iPlayer
- **bbc.co.uk:article**: BBC articles
@ -211,7 +212,8 @@
- **DRBonanza**
- **Dropbox**
- **DrTuber**
- **DRTV**
- **drtv**
- **drtv:live**
- **Dumpert**
- **dvtv**: http://video.aktualne.cz/
- **dw**
@ -247,6 +249,8 @@
- **fc2:embed**
- **Fczenit**
- **fernsehkritik.tv**
- **filmon**
- **filmon:channel**
- **Firstpost**
- **FiveTV**
- **Flickr**
@ -278,6 +282,7 @@
- **Gamersyde**
- **GameSpot**
- **GameStar**
- **Gaskrank**
- **Gazeta**
- **GDCVault**
- **generic**: Generic downloader that works on some sites
@ -528,6 +533,7 @@
- **NRKTV**: NRK TV and NRK Radio
- **NRKTVDirekte**: NRK TV Direkte and NRK Radio Direkte
- **NRKTVEpisodes**
- **NRKTVSeries**
- **ntv.ru**
- **Nuvid**
- **NYTimes**
@ -702,7 +708,6 @@
- **Spiegeltv**
- **Spike**
- **Sport5**
- **SportBox**
- **SportBoxEmbed**
- **SportDeutschland**
- **Sportschau**
@ -855,6 +860,7 @@
- **videomore:season**
- **videomore:video**
- **VideoPremium**
- **VideoPress**
- **videoweed**: VideoWeed
- **Vidio**
- **vidme**

View File

@ -785,12 +785,27 @@ class TestUtil(unittest.TestCase):
on = js_to_json('["abc", "def",]')
self.assertEqual(json.loads(on), ['abc', 'def'])
on = js_to_json('[/*comment\n*/"abc"/*comment\n*/,/*comment\n*/"def",/*comment\n*/]')
self.assertEqual(json.loads(on), ['abc', 'def'])
on = js_to_json('[//comment\n"abc" //comment\n,//comment\n"def",//comment\n]')
self.assertEqual(json.loads(on), ['abc', 'def'])
on = js_to_json('{"abc": "def",}')
self.assertEqual(json.loads(on), {'abc': 'def'})
on = js_to_json('{/*comment\n*/"abc"/*comment\n*/:/*comment\n*/"def"/*comment\n*/,/*comment\n*/}')
self.assertEqual(json.loads(on), {'abc': 'def'})
on = js_to_json('{ 0: /* " \n */ ",]" , }')
self.assertEqual(json.loads(on), {'0': ',]'})
on = js_to_json('{ /*comment\n*/0/*comment\n*/: /* " \n */ ",]" , }')
self.assertEqual(json.loads(on), {'0': ',]'})
on = js_to_json('{ 0: // comment\n1 }')
self.assertEqual(json.loads(on), {'0': 1})
on = js_to_json(r'["<p>x<\/p>"]')
self.assertEqual(json.loads(on), ['<p>x</p>'])
@ -800,15 +815,27 @@ class TestUtil(unittest.TestCase):
on = js_to_json("['a\\\nb']")
self.assertEqual(json.loads(on), ['ab'])
on = js_to_json("/*comment\n*/[/*comment\n*/'a\\\nb'/*comment\n*/]/*comment\n*/")
self.assertEqual(json.loads(on), ['ab'])
on = js_to_json('{0xff:0xff}')
self.assertEqual(json.loads(on), {'255': 255})
on = js_to_json('{/*comment\n*/0xff/*comment\n*/:/*comment\n*/0xff/*comment\n*/}')
self.assertEqual(json.loads(on), {'255': 255})
on = js_to_json('{077:077}')
self.assertEqual(json.loads(on), {'63': 63})
on = js_to_json('{/*comment\n*/077/*comment\n*/:/*comment\n*/077/*comment\n*/}')
self.assertEqual(json.loads(on), {'63': 63})
on = js_to_json('{42:42}')
self.assertEqual(json.loads(on), {'42': 42})
on = js_to_json('{/*comment\n*/42/*comment\n*/:/*comment\n*/42/*comment\n*/}')
self.assertEqual(json.loads(on), {'42': 42})
def test_extract_attributes(self):
self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
self.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'})

View File

@ -24,6 +24,7 @@ import sys
import time
import tokenize
import traceback
import random
from .compat import (
compat_basestring,
@ -159,6 +160,7 @@ class YoutubeDL(object):
playlistend: Playlist item to end at.
playlist_items: Specific indices of playlist to download.
playlistreverse: Download playlist items in reverse order.
playlistrandom: Download playlist items in random order.
matchtitle: Download only matching titles.
rejecttitle: Reject downloads for matching titles.
logger: Log messages to a logging.Logger instance.
@ -842,6 +844,9 @@ class YoutubeDL(object):
if self.params.get('playlistreverse', False):
entries = entries[::-1]
if self.params.get('playlistrandom', False):
random.shuffle(entries)
for i, entry in enumerate(entries, 1):
self.to_screen('[download] Downloading video %s of %s' % (i, n_entries))
extra = {

View File

@ -344,6 +344,7 @@ def _real_main(argv=None):
'playliststart': opts.playliststart,
'playlistend': opts.playlistend,
'playlistreverse': opts.playlist_reverse,
'playlistrandom': opts.playlist_random,
'noplaylist': opts.noplaylist,
'logtostderr': opts.outtmpl == '-',
'consoletitle': opts.consoletitle,

View File

@ -2883,6 +2883,7 @@ __all__ = [
'compat_cookiejar',
'compat_cookies',
'compat_etree_fromstring',
'compat_etree_register_namespace',
'compat_expanduser',
'compat_get_terminal_size',
'compat_getenv',

View File

@ -17,6 +17,7 @@ from ..utils import (
encodeArgument,
handle_youtubedl_headers,
check_executable,
is_outdated_version,
)
@ -198,6 +199,15 @@ class FFmpegFD(ExternalFD):
args = [ffpp.executable, '-y']
seekable = info_dict.get('_seekable')
if seekable is not None:
# setting -seekable prevents ffmpeg from guessing if the server
# supports seeking(by adding the header `Range: bytes=0-`), which
# can cause problems in some cases
# https://github.com/rg3/youtube-dl/issues/11800#issuecomment-275037127
# http://trac.ffmpeg.org/ticket/6125#comment:10
args += ['-seekable', '1' if seekable else '0']
args += self._configuration_args()
# start_time = info_dict.get('start_time') or 0
@ -264,7 +274,9 @@ class FFmpegFD(ExternalFD):
if self.params.get('hls_use_mpegts', False) or tmpfilename == '-':
args += ['-f', 'mpegts']
else:
args += ['-f', 'mp4', '-bsf:a', 'aac_adtstoasc']
args += ['-f', 'mp4']
if (ffpp.basename == 'ffmpeg' and is_outdated_version(ffpp._versions['ffmpeg'], '3.2')) and (not info_dict.get('acodec') or info_dict['acodec'].split('.')[0] in ('aac', 'mp4a')):
args += ['-bsf:a', 'aac_adtstoasc']
elif protocol == 'rtmp':
args += ['-f', 'flv']
else:

View File

@ -61,6 +61,7 @@ class FragmentFD(FileDownloader):
'noprogress': True,
'ratelimit': self.params.get('ratelimit'),
'retries': self.params.get('retries', 0),
'nopart': self.params.get('nopart', False),
'test': self.params.get('test', False),
}
)

View File

@ -221,10 +221,23 @@ class AfreecaTVGlobalIE(AfreecaTVIE):
s_url = s.get('purl')
if not s_url:
continue
# TODO: extract rtmp formats
if s.get('stype') == 'HLS':
stype = s.get('stype')
if stype == 'HLS':
formats.extend(self._extract_m3u8_formats(
s_url, channel_id, 'mp4', fatal=False))
s_url, channel_id, 'mp4', m3u8_id=stype, fatal=False))
elif stype == 'RTMP':
format_id = [stype]
label = s.get('label')
if label:
format_id.append(label)
formats.append({
'format_id': '-'.join(format_id),
'url': s_url,
'tbr': int_or_none(s.get('bps')),
'height': int_or_none(s.get('brt')),
'ext': 'flv',
'rtmp_live': True,
})
self._sort_formats(formats)
info.update({

View File

@ -209,6 +209,15 @@ class BandcampAlbumIE(InfoExtractor):
'id': 'entropy-ep',
},
'playlist_mincount': 3,
}, {
# not all tracks have songs
'url': 'https://insulters.bandcamp.com/album/we-are-the-plague',
'info_dict': {
'id': 'we-are-the-plague',
'title': 'WE ARE THE PLAGUE',
'uploader_id': 'insulters',
},
'playlist_count': 2,
}]
def _real_extract(self, url):
@ -217,12 +226,16 @@ class BandcampAlbumIE(InfoExtractor):
album_id = mobj.group('album_id')
playlist_id = album_id or uploader_id
webpage = self._download_webpage(url, playlist_id)
tracks_paths = re.findall(r'<a href="(.*?)" itemprop="url">', webpage)
if not tracks_paths:
track_elements = re.findall(
r'(?s)<div[^>]*>(.*?<a[^>]+href="([^"]+?)"[^>]+itemprop="url"[^>]*>.*?)</div>', webpage)
if not track_elements:
raise ExtractorError('The page doesn\'t contain any tracks')
# Only tracks with duration info have songs
entries = [
self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
for t_path in tracks_paths]
for elem_content, t_path in track_elements
if self._html_search_meta('duration', elem_content, default=None)]
title = self._html_search_regex(
r'album_title\s*:\s*"((?:\\.|[^"\\])+?)"',
webpage, 'title', fatal=False)

View File

@ -5,19 +5,27 @@ import hashlib
import re
from .common import InfoExtractor
from ..compat import compat_parse_qs
from ..compat import (
compat_parse_qs,
compat_urlparse,
)
from ..utils import (
ExtractorError,
int_or_none,
float_or_none,
parse_iso8601,
smuggle_url,
strip_jsonp,
unified_timestamp,
unsmuggle_url,
urlencode_postdata,
)
class BiliBiliIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.|bangumi\.|)bilibili\.(?:tv|com)/(?:video/av|anime/v/)(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.|bangumi\.|)bilibili\.(?:tv|com)/(?:video/av|anime/(?P<anime_id>\d+)/play#)(?P<id>\d+)'
_TEST = {
_TESTS = [{
'url': 'http://www.bilibili.tv/video/av1074402/',
'md5': '9fa226fe2b8a9a4d5a69b4c6a183417e',
'info_dict': {
@ -32,25 +40,61 @@ class BiliBiliIE(InfoExtractor):
'uploader': '菊子桑',
'uploader_id': '156160',
},
}
}, {
# Tested in BiliBiliBangumiIE
'url': 'http://bangumi.bilibili.com/anime/1869/play#40062',
'only_matching': True,
}, {
'url': 'http://bangumi.bilibili.com/anime/5802/play#100643',
'md5': '3f721ad1e75030cc06faf73587cfec57',
'info_dict': {
'id': '100643',
'ext': 'mp4',
'title': 'CHAOS;CHILD',
'description': '如果你是神明并且能够让妄想成为现实。那你会进行怎么样的妄想是淫靡的世界独裁社会毁灭性的制裁还是……2015年涩谷。从6年前发生的大灾害“涩谷地震”之后复兴了的这个街区里新设立的私立高中...',
},
'skip': 'Geo-restricted to China',
}]
_APP_KEY = '84956560bc028eb7'
_BILIBILI_KEY = '94aba54af9065f71de72f5508f1cd42e'
def _report_error(self, result):
if 'message' in result:
raise ExtractorError('%s said: %s' % (self.IE_NAME, result['message']), expected=True)
elif 'code' in result:
raise ExtractorError('%s returns error %d' % (self.IE_NAME, result['code']), expected=True)
else:
raise ExtractorError('Can\'t extract Bangumi episode ID')
def _real_extract(self, url):
video_id = self._match_id(url)
url, smuggled_data = unsmuggle_url(url, {})
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
anime_id = mobj.group('anime_id')
webpage = self._download_webpage(url, video_id)
if 'anime/v' not in url:
if 'anime/' not in url:
cid = compat_parse_qs(self._search_regex(
[r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
webpage, 'player parameters'))['cid'][0]
else:
if 'no_bangumi_tip' not in smuggled_data:
self.to_screen('Downloading episode %s. To download all videos in anime %s, re-run youtube-dl with %s' % (
video_id, anime_id, compat_urlparse.urljoin(url, '//bangumi.bilibili.com/anime/%s' % anime_id)))
headers = {
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
}
headers.update(self.geo_verification_headers())
js = self._download_json(
'http://bangumi.bilibili.com/web_api/get_source', video_id,
data=urlencode_postdata({'episode_id': video_id}),
headers={'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8'})
headers=headers)
if 'result' not in js:
self._report_error(js)
cid = js['result']['cid']
payload = 'appkey=%s&cid=%s&otype=json&quality=2&type=mp4' % (self._APP_KEY, cid)
@ -58,7 +102,11 @@ class BiliBiliIE(InfoExtractor):
video_info = self._download_json(
'http://interface.bilibili.com/playurl?%s&sign=%s' % (payload, sign),
video_id, note='Downloading video info page')
video_id, note='Downloading video info page',
headers=self.geo_verification_headers())
if 'durl' not in video_info:
self._report_error(video_info)
entries = []
@ -85,7 +133,7 @@ class BiliBiliIE(InfoExtractor):
title = self._html_search_regex('<h1[^>]+title="([^"]+)">', webpage, 'title')
description = self._html_search_meta('description', webpage)
timestamp = unified_timestamp(self._html_search_regex(
r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False))
r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', default=None))
thumbnail = self._html_search_meta(['og:image', 'thumbnailUrl'], webpage)
# TODO 'view_count' requires deobfuscating Javascript
@ -99,7 +147,7 @@ class BiliBiliIE(InfoExtractor):
}
uploader_mobj = re.search(
r'<a[^>]+href="https?://space\.bilibili\.com/(?P<id>\d+)"[^>]+title="(?P<name>[^"]+)"',
r'<a[^>]+href="(?:https?:)?//space\.bilibili\.com/(?P<id>\d+)"[^>]+title="(?P<name>[^"]+)"',
webpage)
if uploader_mobj:
info.update({
@ -123,3 +171,70 @@ class BiliBiliIE(InfoExtractor):
'description': description,
'entries': entries,
}
class BiliBiliBangumiIE(InfoExtractor):
_VALID_URL = r'https?://bangumi\.bilibili\.com/anime/(?P<id>\d+)'
IE_NAME = 'bangumi.bilibili.com'
IE_DESC = 'BiliBili番剧'
_TESTS = [{
'url': 'http://bangumi.bilibili.com/anime/1869',
'info_dict': {
'id': '1869',
'title': '混沌武士',
'description': 'md5:6a9622b911565794c11f25f81d6a97d2',
},
'playlist_count': 26,
}, {
'url': 'http://bangumi.bilibili.com/anime/1869',
'info_dict': {
'id': '1869',
'title': '混沌武士',
'description': 'md5:6a9622b911565794c11f25f81d6a97d2',
},
'playlist': [{
'md5': '91da8621454dd58316851c27c68b0c13',
'info_dict': {
'id': '40062',
'ext': 'mp4',
'title': '混沌武士',
'description': '故事发生在日本的江户时代。风是一个小酒馆的打工女。一日,酒馆里来了一群恶霸,虽然他们的举动令风十分不满,但是毕竟风只是一届女流,无法对他们采取什么行动,只能在心里嘟哝。这时,酒家里又进来了个“不良份子...',
'timestamp': 1414538739,
'upload_date': '20141028',
'episode': '疾风怒涛 Tempestuous Temperaments',
'episode_number': 1,
},
}],
'params': {
'playlist_items': '1',
},
}]
@classmethod
def suitable(cls, url):
return False if BiliBiliIE.suitable(url) else super(BiliBiliBangumiIE, cls).suitable(url)
def _real_extract(self, url):
bangumi_id = self._match_id(url)
# Sometimes this API returns a JSONP response
season_info = self._download_json(
'http://bangumi.bilibili.com/jsonp/seasoninfo/%s.ver' % bangumi_id,
bangumi_id, transform_source=strip_jsonp)['result']
entries = [{
'_type': 'url_transparent',
'url': smuggle_url(episode['webplay_url'], {'no_bangumi_tip': 1}),
'ie_key': BiliBiliIE.ie_key(),
'timestamp': parse_iso8601(episode.get('update_time'), delimiter=' '),
'episode': episode.get('index_title'),
'episode_number': int_or_none(episode.get('index')),
} for episode in season_info['episodes']]
entries = sorted(entries, key=lambda entry: entry.get('episode_number'))
return self.playlist_result(
entries, bangumi_id,
season_info.get('bangumi_title'), season_info.get('evaluate'))

View File

@ -27,6 +27,7 @@ class CanalplusIE(InfoExtractor):
(?:www\.)?d8\.tv|
(?:www\.)?c8\.fr|
(?:www\.)?d17\.tv|
(?:(?:football|www)\.)?cstar\.fr|
(?:www\.)?itele\.fr
)/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
player\.canalplus\.fr/#/(?P<id>\d+)
@ -40,6 +41,7 @@ class CanalplusIE(InfoExtractor):
'd8': 'd8',
'c8': 'd8',
'd17': 'd17',
'cstar': 'd17',
'itele': 'itele',
}
@ -86,6 +88,19 @@ class CanalplusIE(InfoExtractor):
'description': 'Chaque matin du lundi au vendredi, Michaël Darmon reçoit un invité politique à 8h25.',
'upload_date': '20161014',
},
}, {
'url': 'http://football.cstar.fr/cstar-minisite-foot/pid7566-feminines-videos.html?vid=1416769',
'info_dict': {
'id': '1416769',
'display_id': 'pid7566-feminines-videos',
'ext': 'mp4',
'title': 'France - Albanie : les temps forts de la soirée - 20/09/2016',
'description': 'md5:c3f30f2aaac294c1c969b3294de6904e',
'upload_date': '20160921',
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://m.canalplus.fr/?vid=1398231',
'only_matching': True,

View File

@ -296,6 +296,12 @@ class CBCWatchVideoIE(CBCWatchBaseIE):
formats = self._extract_m3u8_formats(re.sub(r'/([^/]+)/[^/?]+\.m3u8', r'/\1/\1.m3u8', m3u8_url), video_id, 'mp4', fatal=False)
if len(formats) < 2:
formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
for f in formats:
format_id = f.get('format_id')
if format_id.startswith('AAC'):
f['acodec'] = 'aac'
elif format_id.startswith('AC3'):
f['acodec'] = 'ac-3'
self._sort_formats(formats)
info = {

View File

@ -1025,13 +1025,13 @@ class InfoExtractor(object):
unique_formats.append(f)
formats[:] = unique_formats
def _is_valid_url(self, url, video_id, item='video'):
def _is_valid_url(self, url, video_id, item='video', headers={}):
url = self._proto_relative_url(url, scheme='http:')
# For now assume non HTTP(S) URLs always valid
if not (url.startswith('http://') or url.startswith('https://')):
return True
try:
self._request_webpage(url, video_id, 'Checking %s URL' % item)
self._request_webpage(url, video_id, 'Checking %s URL' % item, headers=headers)
return True
except ExtractorError as e:
if isinstance(e.cause, compat_urllib_error.URLError):
@ -1315,8 +1315,8 @@ class InfoExtractor(object):
'abr': abr,
})
f.update(parse_codecs(last_info.get('CODECS')))
if audio_in_video_stream.get(last_info.get('AUDIO')) is False:
# TODO: update acodec for for audio only formats with the same GROUP-ID
if audio_in_video_stream.get(last_info.get('AUDIO')) is False and f['vcodec'] != 'none':
# TODO: update acodec for audio only formats with the same GROUP-ID
f['acodec'] = 'none'
formats.append(f)
last_info = {}
@ -1959,7 +1959,12 @@ class InfoExtractor(object):
media_tags = [(media_tag, media_type, '')
for media_tag, media_type
in re.findall(r'(?s)(<(video|audio)[^>]*/>)', webpage)]
media_tags.extend(re.findall(r'(?s)(<(?P<tag>video|audio)[^>]*>)(.*?)</(?P=tag)>', webpage))
media_tags.extend(re.findall(
# We only allow video|audio followed by a whitespace or '>'.
# Allowing more characters may end up in significant slow down (see
# https://github.com/rg3/youtube-dl/issues/11979, example URL:
# http://www.porntrex.com/maps/videositemap.xml).
r'(?s)(<(?P<tag>video|audio)(?:\s+[^>]*)?>)(.*?)</(?P=tag)>', webpage))
for media_tag, media_type, media_content in media_tags:
media_info = {
'formats': [],

View File

@ -255,8 +255,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
output += 'WrapStyle: %s\n' % sub_root.attrib['wrap_style']
output += 'PlayResX: %s\n' % sub_root.attrib['play_res_x']
output += 'PlayResY: %s\n' % sub_root.attrib['play_res_y']
output += """ScaledBorderAndShadow: no
output += """
[V4+ Styles]
Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding
"""

View File

@ -18,7 +18,7 @@ from ..utils import (
class DouyuTVIE(InfoExtractor):
IE_DESC = '斗鱼'
_VALID_URL = r'https?://(?:www\.)?douyu(?:tv)?\.com/(?P<id>[A-Za-z0-9]+)'
_VALID_URL = r'https?://(?:www\.)?douyu(?:tv)?\.com/(?:[^/]+/)*(?P<id>[A-Za-z0-9]+)'
_TESTS = [{
'url': 'http://www.douyutv.com/iseven',
'info_dict': {
@ -68,6 +68,10 @@ class DouyuTVIE(InfoExtractor):
}, {
'url': 'http://www.douyu.com/xiaocang',
'only_matching': True,
}, {
# \"room_id\"
'url': 'http://www.douyu.com/t/lpl',
'only_matching': True,
}]
# Decompile core.swf in webpage by ffdec "Search SWFs in memory". core.swf
@ -82,7 +86,7 @@ class DouyuTVIE(InfoExtractor):
else:
page = self._download_webpage(url, video_id)
room_id = self._html_search_regex(
r'"room_id"\s*:\s*(\d+),', page, 'room id')
r'"room_id\\?"\s*:\s*(\d+),', page, 'room id')
room = self._download_json(
'http://m.douyu.com/html5/live?roomId=%s' % room_id, video_id,

View File

@ -9,12 +9,13 @@ from ..utils import (
mimetype2ext,
parse_iso8601,
remove_end,
update_url_query,
)
class DRTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
_VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder|radio/ondemand)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
IE_NAME = 'drtv'
_TESTS = [{
'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10',
'md5': '25e659cccc9a2ed956110a299fdf5983',
@ -79,9 +80,10 @@ class DRTVIE(InfoExtractor):
subtitles = {}
for asset in data['Assets']:
if asset.get('Kind') == 'Image':
kind = asset.get('Kind')
if kind == 'Image':
thumbnail = asset.get('Uri')
elif asset.get('Kind') == 'VideoResource':
elif kind in ('VideoResource', 'AudioResource'):
duration = float_or_none(asset.get('DurationInMilliseconds'), 1000)
restricted_to_denmark = asset.get('RestrictedToDenmark')
spoken_subtitles = asset.get('Target') == 'SpokenSubtitles'
@ -96,9 +98,13 @@ class DRTVIE(InfoExtractor):
preference = -1
format_id += '-spoken-subtitles'
if target == 'HDS':
formats.extend(self._extract_f4m_formats(
f4m_formats = self._extract_f4m_formats(
uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',
video_id, preference, f4m_id=format_id))
video_id, preference, f4m_id=format_id)
if kind == 'AudioResource':
for f in f4m_formats:
f['vcodec'] = 'none'
formats.extend(f4m_formats)
elif target == 'HLS':
formats.extend(self._extract_m3u8_formats(
uri, video_id, 'mp4', entry_protocol='m3u8_native',
@ -112,6 +118,7 @@ class DRTVIE(InfoExtractor):
'format_id': format_id,
'tbr': int_or_none(bitrate),
'ext': link.get('FileFormat'),
'vcodec': 'none' if kind == 'AudioResource' else None,
})
subtitles_list = asset.get('SubtitlesList')
if isinstance(subtitles_list, list):
@ -144,3 +151,58 @@ class DRTVIE(InfoExtractor):
'formats': formats,
'subtitles': subtitles,
}
class DRTVLiveIE(InfoExtractor):
IE_NAME = 'drtv:live'
_VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv|TV)/live/(?P<id>[\da-z-]+)'
_TEST = {
'url': 'https://www.dr.dk/tv/live/dr1',
'info_dict': {
'id': 'dr1',
'ext': 'mp4',
'title': 're:^DR1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
},
'params': {
# m3u8 download
'skip_download': True,
},
}
def _real_extract(self, url):
channel_id = self._match_id(url)
channel_data = self._download_json(
'https://www.dr.dk/mu-online/api/1.0/channel/' + channel_id,
channel_id)
title = self._live_title(channel_data['Title'])
formats = []
for streaming_server in channel_data.get('StreamingServers', []):
server = streaming_server.get('Server')
if not server:
continue
link_type = streaming_server.get('LinkType')
for quality in streaming_server.get('Qualities', []):
for stream in quality.get('Streams', []):
stream_path = stream.get('Stream')
if not stream_path:
continue
stream_url = update_url_query(
'%s/%s' % (server, stream_path), {'b': ''})
if link_type == 'HLS':
formats.extend(self._extract_m3u8_formats(
stream_url, channel_id, 'mp4',
m3u8_id=link_type, fatal=False, live=True))
elif link_type == 'HDS':
formats.extend(self._extract_f4m_formats(update_url_query(
'%s/%s' % (server, stream_path), {'hdcore': '3.7.0'}),
channel_id, f4m_id=link_type, fatal=False))
self._sort_formats(formats)
return {
'id': channel_id,
'title': title,
'thumbnail': channel_data.get('PrimaryImageUri'),
'formats': formats,
'is_live': True,
}

View File

@ -2,7 +2,7 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import unified_strdate
from ..utils import strip_jsonp, unified_strdate
class ElPaisIE(InfoExtractor):
@ -29,6 +29,16 @@ class ElPaisIE(InfoExtractor):
'description': 'Que sí, que las cápsulas son cómodas. Pero si le pides algo más a la vida, quizá deberías aprender a usar bien la cafetera italiana. No tienes más que ver este vídeo y seguir sus siete normas básicas.',
'upload_date': '20160303',
}
}, {
'url': 'http://elpais.com/elpais/2017/01/26/ciencia/1485456786_417876.html',
'md5': '9c79923a118a067e1a45789e1e0b0f9c',
'info_dict': {
'id': '1485456786_417876',
'ext': 'mp4',
'title': 'Hallado un barco de la antigua Roma que naufragó en Baleares hace 1.800 años',
'description': 'La nave portaba cientos de ánforas y se hundió cerca de la isla de Cabrera por razones desconocidas',
'upload_date': '20170127',
},
}]
def _real_extract(self, url):
@ -37,8 +47,15 @@ class ElPaisIE(InfoExtractor):
prefix = self._html_search_regex(
r'var\s+url_cache\s*=\s*"([^"]+)";', webpage, 'URL prefix')
video_suffix = self._search_regex(
r"(?:URLMediaFile|urlVideo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'", webpage, 'video URL')
id_multimedia = self._search_regex(
r"id_multimedia\s*=\s*'([^']+)'", webpage, 'ID multimedia', default=None)
if id_multimedia:
url_info = self._download_json(
'http://elpais.com/vdpep/1/?pepid=' + id_multimedia, video_id, transform_source=strip_jsonp)
video_suffix = url_info['mp4']
else:
video_suffix = self._search_regex(
r"(?:URLMediaFile|urlVideo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'", webpage, 'video URL')
video_url = prefix + video_suffix
thumbnail_suffix = self._search_regex(
r"(?:URLMediaStill|urlFotogramaFijo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'",

View File

@ -103,7 +103,10 @@ from .beatport import BeatportIE
from .bet import BetIE
from .bigflix import BigflixIE
from .bild import BildIE
from .bilibili import BiliBiliIE
from .bilibili import (
BiliBiliIE,
BiliBiliBangumiIE,
)
from .biobiochiletv import BioBioChileTVIE
from .biqle import BIQLEIE
from .bleacherreport import (
@ -245,7 +248,10 @@ from .dramafever import (
from .dreisat import DreiSatIE
from .drbonanza import DRBonanzaIE
from .drtuber import DrTuberIE
from .drtv import DRTVIE
from .drtv import (
DRTVIE,
DRTVLiveIE,
)
from .dvtv import DVTVIE
from .dumpert import DumpertIE
from .defense import DefenseGouvFrIE
@ -296,6 +302,10 @@ from .fc2 import (
FC2EmbedIE,
)
from .fczenit import FczenitIE
from .filmon import (
FilmOnIE,
FilmOnChannelIE,
)
from .firstpost import FirstpostIE
from .firsttv import FirstTVIE
from .fivemin import FiveMinIE
@ -339,6 +349,7 @@ from .gameone import (
from .gamersyde import GamersydeIE
from .gamespot import GameSpotIE
from .gamestar import GameStarIE
from .gaskrank import GaskrankIE
from .gazeta import GazetaIE
from .gdcvault import GDCVaultIE
from .generic import GenericIE
@ -668,6 +679,7 @@ from .nrk import (
NRKTVIE,
NRKTVDirekteIE,
NRKTVEpisodesIE,
NRKTVSeriesIE,
)
from .ntvde import NTVDeIE
from .ntvru import NTVRuIE
@ -826,6 +838,7 @@ from .sbs import SBSIE
from .scivee import SciVeeIE
from .screencast import ScreencastIE
from .screencastomatic import ScreencastOMaticIE
from .scrippsnetworks import ScrippsNetworksWatchIE
from .seeker import SeekerIE
from .senateisvp import SenateISVPIE
from .sendtonews import SendtoNewsIE
@ -880,12 +893,10 @@ from .spiegeltv import SpiegeltvIE
from .spike import SpikeIE
from .stitcher import StitcherIE
from .sport5 import Sport5IE
from .sportbox import (
SportBoxIE,
SportBoxEmbedIE,
)
from .sportbox import SportBoxEmbedIE
from .sportdeutschland import SportDeutschlandIE
from .sportschau import SportschauIE
from .sprout import SproutIE
from .srgssr import (
SRGSSRIE,
SRGSSRPlayIE,
@ -1087,6 +1098,7 @@ from .videomore import (
VideomoreSeasonIE,
)
from .videopremium import VideoPremiumIE
from .videopress import VideoPressIE
from .vidio import VidioIE
from .vidme import (
VidmeIE,

View File

@ -12,14 +12,16 @@ from ..compat import (
compat_urllib_parse_unquote_plus,
)
from ..utils import (
clean_html,
error_to_compat_str,
ExtractorError,
get_element_by_id,
int_or_none,
js_to_json,
limit_length,
sanitized_Request,
try_get,
urlencode_postdata,
get_element_by_id,
clean_html,
)
@ -71,7 +73,7 @@ class FacebookIE(InfoExtractor):
'info_dict': {
'id': '274175099429670',
'ext': 'mp4',
'title': 'Facebook video #274175099429670',
'title': 'Asif Nawab Butt posted a video to his Timeline.',
'uploader': 'Asif Nawab Butt',
'upload_date': '20140506',
'timestamp': 1399398998,
@ -243,14 +245,30 @@ class FacebookIE(InfoExtractor):
video_data = None
def extract_video_data(instances):
for item in instances:
if item[1][0] == 'VideoConfig':
video_item = item[2][0]
if video_item.get('video_id') == video_id:
return video_item['videoData']
server_js_data = self._parse_json(self._search_regex(
r'handleServerJS\(({.+})(?:\);|,")', webpage, 'server js data', default='{}'), video_id)
for item in server_js_data.get('instances', []):
if item[1][0] == 'VideoConfig':
video_item = item[2][0]
if video_item.get('video_id') == video_id:
video_data = video_item['videoData']
break
r'handleServerJS\(({.+})(?:\);|,")', webpage,
'server js data', default='{}'), video_id, fatal=False)
if server_js_data:
video_data = extract_video_data(server_js_data.get('instances', []))
if not video_data:
server_js_data = self._parse_json(
self._search_regex(
r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+stream_pagelet',
webpage, 'js data', default='{}'),
video_id, transform_source=js_to_json, fatal=False)
if server_js_data:
video_data = extract_video_data(try_get(
server_js_data, lambda x: x['jsmods']['instances'],
list) or [])
if not video_data:
if not fatal_if_no_video:
@ -300,10 +318,16 @@ class FacebookIE(InfoExtractor):
video_title = self._html_search_regex(
r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
webpage, 'alternative title', default=None)
video_title = limit_length(video_title, 80)
if not video_title:
video_title = self._html_search_meta(
'description', webpage, 'title')
if video_title:
video_title = limit_length(video_title, 80)
else:
video_title = 'Facebook video #%s' % video_id
uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
uploader = clean_html(get_element_by_id(
'fbPhotoPageAuthorName', webpage)) or self._search_regex(
r'ownerName\s*:\s*"([^"]+)"', webpage, 'uploader', fatal=False)
timestamp = int_or_none(self._search_regex(
r'<abbr[^>]+data-utime=["\'](\d+)', webpage,
'timestamp', default=None))

View File

@ -0,0 +1,178 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_HTTPError,
)
from ..utils import (
qualities,
strip_or_none,
int_or_none,
ExtractorError,
)
class FilmOnIE(InfoExtractor):
IE_NAME = 'filmon'
_VALID_URL = r'(?:https?://(?:www\.)?filmon\.com/vod/view/|filmon:)(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.filmon.com/vod/view/24869-0-plan-9-from-outer-space',
'info_dict': {
'id': '24869',
'ext': 'mp4',
'title': 'Plan 9 From Outer Space',
'description': 'Dead human, zombies and vampires',
},
}, {
'url': 'https://www.filmon.com/vod/view/2825-1-popeye-series-1',
'info_dict': {
'id': '2825',
'title': 'Popeye Series 1',
'description': 'The original series of Popeye.',
},
'playlist_mincount': 8,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
try:
response = self._download_json(
'https://www.filmon.com/api/vod/movie?id=%s' % video_id,
video_id)['response']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError):
errmsg = self._parse_json(e.cause.read().decode(), video_id)['reason']
raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True)
raise
title = response['title']
description = strip_or_none(response.get('description'))
if response.get('type_id') == 1:
entries = [self.url_result('filmon:' + episode_id) for episode_id in response.get('episodes', [])]
return self.playlist_result(entries, video_id, title, description)
QUALITY = qualities(('low', 'high'))
formats = []
for format_id, stream in response.get('streams', {}).items():
stream_url = stream.get('url')
if not stream_url:
continue
formats.append({
'format_id': format_id,
'url': stream_url,
'ext': 'mp4',
'quality': QUALITY(stream.get('quality')),
'protocol': 'm3u8_native',
})
self._sort_formats(formats)
thumbnails = []
poster = response.get('poster', {})
thumbs = poster.get('thumbs', {})
thumbs['poster'] = poster
for thumb_id, thumb in thumbs.items():
thumb_url = thumb.get('url')
if not thumb_url:
continue
thumbnails.append({
'id': thumb_id,
'url': thumb_url,
'width': int_or_none(thumb.get('width')),
'height': int_or_none(thumb.get('height')),
})
return {
'id': video_id,
'title': title,
'formats': formats,
'description': description,
'thumbnails': thumbnails,
}
class FilmOnChannelIE(InfoExtractor):
IE_NAME = 'filmon:channel'
_VALID_URL = r'https?://(?:www\.)?filmon\.com/(?:tv|channel)/(?P<id>[a-z0-9-]+)'
_TESTS = [{
# VOD
'url': 'http://www.filmon.com/tv/sports-haters',
'info_dict': {
'id': '4190',
'ext': 'mp4',
'title': 'Sports Haters',
'description': 'md5:dabcb4c1d9cfc77085612f1a85f8275d',
},
}, {
# LIVE
'url': 'https://www.filmon.com/channel/filmon-sports',
'only_matching': True,
}, {
'url': 'https://www.filmon.com/tv/2894',
'only_matching': True,
}]
_THUMBNAIL_RES = [
('logo', 56, 28),
('big_logo', 106, 106),
('extra_big_logo', 300, 300),
]
def _real_extract(self, url):
channel_id = self._match_id(url)
try:
channel_data = self._download_json(
'http://www.filmon.com/api-v2/channel/' + channel_id, channel_id)['data']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError):
errmsg = self._parse_json(e.cause.read().decode(), channel_id)['message']
raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True)
raise
channel_id = compat_str(channel_data['id'])
is_live = not channel_data.get('is_vod') and not channel_data.get('is_vox')
title = channel_data['title']
QUALITY = qualities(('low', 'high'))
formats = []
for stream in channel_data.get('streams', []):
stream_url = stream.get('url')
if not stream_url:
continue
if not is_live:
formats.extend(self._extract_wowza_formats(
stream_url, channel_id, skip_protocols=['dash', 'rtmp', 'rtsp']))
continue
quality = stream.get('quality')
formats.append({
'format_id': quality,
# this is an m3u8 stream, but we are deliberately not using _extract_m3u8_formats
# because it doesn't have bitrate variants anyway
'url': stream_url,
'ext': 'mp4',
'quality': QUALITY(quality),
})
self._sort_formats(formats)
thumbnails = []
for name, width, height in self._THUMBNAIL_RES:
thumbnails.append({
'id': name,
'url': 'http://static.filmon.com/assets/channels/%s/%s.png' % (channel_id, name),
'width': width,
'height': height,
})
return {
'id': channel_id,
'display_id': channel_data.get('alias'),
'title': self._live_title(title) if is_live else title,
'description': channel_data.get('description'),
'thumbnails': thumbnails,
'formats': formats,
'is_live': is_live,
}

View File

@ -0,0 +1,123 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
js_to_json,
unified_strdate,
)
class GaskrankIE(InfoExtractor):
"""InfoExtractor for gaskrank.tv"""
_VALID_URL = r'https?://(?:www\.)?gaskrank\.tv/tv/(?P<categories>[^/]+)/(?P<id>[^/]+)\.html?'
_TESTS = [
{
'url': 'http://www.gaskrank.tv/tv/motorrad-fun/strike-einparken-durch-anfaenger-crash-mit-groesserem-flurschaden.htm',
'md5': '1ae88dbac97887d85ebd1157a95fc4f9',
'info_dict': {
'id': '201601/26955',
'ext': 'mp4',
'title': 'Strike! Einparken können nur Männer - Flurschaden hält sich in Grenzen *lol*',
'thumbnail': r're:^https?://.*\.jpg$',
'categories': ['motorrad-fun'],
'display_id': 'strike-einparken-durch-anfaenger-crash-mit-groesserem-flurschaden',
'uploader_id': 'Bikefun',
'upload_date': '20170110',
'uploader_url': None,
}
},
{
'url': 'http://www.gaskrank.tv/tv/racing/isle-of-man-tt-2011-michael-du-15920.htm',
'md5': 'c33ee32c711bc6c8224bfcbe62b23095',
'info_dict': {
'id': '201106/15920',
'ext': 'mp4',
'title': 'Isle of Man - Michael Dunlop vs Guy Martin - schwindelig kucken',
'thumbnail': r're:^https?://.*\.jpg$',
'categories': ['racing'],
'display_id': 'isle-of-man-tt-2011-michael-du-15920',
'uploader_id': 'IOM',
'upload_date': '20160506',
'uploader_url': 'www.iomtt.com',
}
}
]
def _real_extract(self, url):
"""extract information from gaskrank.tv"""
def fix_json(code):
"""Removes trailing comma in json: {{},} --> {{}}"""
return re.sub(r',\s*}', r'}', js_to_json(code))
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
categories = [re.match(self._VALID_URL, url).group('categories')]
title = self._search_regex(
r'movieName\s*:\s*\'([^\']*)\'',
webpage, 'title')
thumbnail = self._search_regex(
r'poster\s*:\s*\'([^\']*)\'',
webpage, 'thumbnail', default=None)
mobj = re.search(
r'Video von:\s*(?P<uploader_id>[^|]*?)\s*\|\s*vom:\s*(?P<upload_date>[0-9][0-9]\.[0-9][0-9]\.[0-9][0-9][0-9][0-9])',
webpage)
if mobj is not None:
uploader_id = mobj.groupdict().get('uploader_id')
upload_date = unified_strdate(mobj.groupdict().get('upload_date'))
uploader_url = self._search_regex(
r'Homepage:\s*<[^>]*>(?P<uploader_url>[^<]*)',
webpage, 'uploader_url', default=None)
tags = re.findall(
r'/tv/tags/[^/]+/"\s*>(?P<tag>[^<]*?)<',
webpage)
view_count = self._search_regex(
r'class\s*=\s*"gkRight"(?:[^>]*>\s*<[^>]*)*icon-eye-open(?:[^>]*>\s*<[^>]*)*>\s*(?P<view_count>[0-9\.]*)',
webpage, 'view_count', default=None)
if view_count:
view_count = int_or_none(view_count.replace('.', ''))
average_rating = self._search_regex(
r'itemprop\s*=\s*"ratingValue"[^>]*>\s*(?P<average_rating>[0-9,]+)',
webpage, 'average_rating')
if average_rating:
average_rating = float_or_none(average_rating.replace(',', '.'))
playlist = self._parse_json(
self._search_regex(
r'playlist\s*:\s*\[([^\]]*)\]',
webpage, 'playlist', default='{}'),
display_id, transform_source=fix_json, fatal=False)
video_id = self._search_regex(
r'https?://movies\.gaskrank\.tv/([^-]*?)(-[^\.]*)?\.mp4',
playlist.get('0').get('src'), 'video id')
formats = []
for key in playlist:
formats.append({
'url': playlist[key]['src'],
'format_id': key,
'quality': playlist[key].get('quality')})
self._sort_formats(formats, field_preference=['format_id'])
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'categories': categories,
'display_id': display_id,
'uploader_id': uploader_id,
'upload_date': upload_date,
'uploader_url': uploader_url,
'tags': tags,
'view_count': view_count,
'average_rating': average_rating,
}

View File

@ -29,6 +29,7 @@ from ..utils import (
UnsupportedError,
xpath_text,
)
from .commonprotocols import RtmpIE
from .brightcove import (
BrightcoveLegacyIE,
BrightcoveNewIE,
@ -81,6 +82,7 @@ from .videa import VideaIE
from .twentymin import TwentyMinutenIE
from .ustream import UstreamIE
from .openload import OpenloadIE
from .videopress import VideoPressIE
class GenericIE(InfoExtractor):
@ -946,6 +948,19 @@ class GenericIE(InfoExtractor):
'title': 'Webinar: Using Discovery, The National Archives online catalogue',
},
},
# jwplayer rtmp
{
'url': 'http://www.suffolk.edu/sjc/',
'info_dict': {
'id': 'sjclive',
'ext': 'flv',
'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
'uploader': 'www.suffolk.edu',
},
'params': {
'skip_download': True,
}
},
# rtl.nl embed
{
'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
@ -1473,6 +1488,21 @@ class GenericIE(InfoExtractor):
'skip_download': True,
},
'add_ie': [TwentyMinutenIE.ie_key()],
},
{
# VideoPress embed
'url': 'https://en.support.wordpress.com/videopress/',
'info_dict': {
'id': 'OcobLTqC',
'ext': 'm4v',
'title': 'IMG_5786',
'timestamp': 1435711927,
'upload_date': '20150701',
},
'params': {
'skip_download': True,
},
'add_ie': [VideoPressIE.ie_key()],
}
# {
# # TODO: find another test
@ -2438,6 +2468,12 @@ class GenericIE(InfoExtractor):
return _playlist_from_matches(
openload_urls, ie=OpenloadIE.ie_key())
# Look for VideoPress embeds
videopress_urls = VideoPressIE._extract_urls(webpage)
if videopress_urls:
return _playlist_from_matches(
videopress_urls, ie=VideoPressIE.ie_key())
# Looking for http://schema.org/VideoObject
json_ld = self._search_json_ld(
webpage, video_id, default={}, expected_type='VideoObject')
@ -2465,6 +2501,8 @@ class GenericIE(InfoExtractor):
def check_video(vurl):
if YoutubeIE.suitable(vurl):
return True
if RtmpIE.suitable(vurl):
return True
vpath = compat_urlparse.urlparse(vurl).path
vext = determine_ext(vpath)
return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
@ -2572,6 +2610,15 @@ class GenericIE(InfoExtractor):
'age_limit': age_limit,
}
if RtmpIE.suitable(video_url):
entry_info_dict.update({
'_type': 'url_transparent',
'ie_key': RtmpIE.ie_key(),
'url': video_url,
})
entries.append(entry_info_dict)
continue
ext = determine_ext(video_url)
if ext == 'smil':
entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)

View File

@ -3,7 +3,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .adobepass import AdobePassIE
from ..utils import (
int_or_none,
determine_ext,
@ -13,15 +13,30 @@ from ..utils import (
)
class GoIE(InfoExtractor):
_BRANDS = {
'abc': '001',
'freeform': '002',
'watchdisneychannel': '004',
'watchdisneyjunior': '008',
'watchdisneyxd': '009',
class GoIE(AdobePassIE):
_SITE_INFO = {
'abc': {
'brand': '001',
'requestor_id': 'ABC',
},
'freeform': {
'brand': '002',
'requestor_id': 'ABCFamily',
},
'watchdisneychannel': {
'brand': '004',
'requestor_id': 'Disney',
},
'watchdisneyjunior': {
'brand': '008',
'requestor_id': 'DisneyJunior',
},
'watchdisneyxd': {
'brand': '009',
'requestor_id': 'DisneyXD',
}
}
_VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|season-\d+/\d+-(?P<display_id>[^/?#]+))' % '|'.join(_BRANDS.keys())
_VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|season-\d+/\d+-(?P<display_id>[^/?#]+))' % '|'.join(_SITE_INFO.keys())
_TESTS = [{
'url': 'http://abc.go.com/shows/castle/video/most-recent/vdka0_g86w5onx',
'info_dict': {
@ -43,8 +58,12 @@ class GoIE(InfoExtractor):
sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
if not video_id:
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(r'data-video-id=["\']VDKA(\w+)', webpage, 'video id')
brand = self._BRANDS[sub_domain]
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')
site_info = self._SITE_INFO[sub_domain]
brand = site_info['brand']
video_data = self._download_json(
'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (brand, video_id),
video_id)['video'][0]
@ -60,14 +79,26 @@ class GoIE(InfoExtractor):
if ext == 'm3u8':
video_type = video_data.get('type')
if video_type == 'lf':
data = {
'video_id': video_data['id'],
'video_type': video_type,
'brand': brand,
'device': '001',
}
if video_data.get('accesslevel') == '1':
requestor_id = site_info['requestor_id']
resource = self._get_mvpd_resource(
requestor_id, title, video_id, None)
auth = self._extract_mvpd_auth(
url, video_id, requestor_id, resource)
data.update({
'token': auth,
'token_type': 'ap',
'adobe_requestor_id': requestor_id,
})
entitlement = self._download_json(
'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
video_id, data=urlencode_postdata({
'video_id': video_data['id'],
'video_type': video_type,
'brand': brand,
'device': '001',
}))
video_id, data=urlencode_postdata(data), headers=self.geo_verification_headers())
errors = entitlement.get('errors', {}).get('errors', [])
if errors:
error_message = ', '.join([error['message'] for error in errors])

View File

@ -6,6 +6,7 @@ from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
lowercase_escape,
)
@ -13,12 +14,12 @@ class GoogleDriveIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28,})'
_TESTS = [{
'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
'md5': '881f7700aec4f538571fa1e0eed4a7b6',
'md5': 'd109872761f7e7ecf353fa108c0dbe1e',
'info_dict': {
'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
'ext': 'mp4',
'title': 'Big Buck Bunny.mp4',
'duration': 46,
'duration': 45,
}
}, {
# video id is longer than 28 characters
@ -55,7 +56,7 @@ class GoogleDriveIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'http://docs.google.com/file/d/%s' % video_id, video_id, encoding='unicode_escape')
'http://docs.google.com/file/d/%s' % video_id, video_id)
reason = self._search_regex(r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
if reason:
@ -74,7 +75,7 @@ class GoogleDriveIE(InfoExtractor):
resolution = fmt.split('/')[1]
width, height = resolution.split('x')
formats.append({
'url': fmt_url,
'url': lowercase_escape(fmt_url),
'format_id': fmt_id,
'resolution': resolution,
'width': int_or_none(width),

View File

@ -4,7 +4,10 @@ from __future__ import unicode_literals
import base64
from ..compat import compat_urllib_parse_unquote
from ..compat import (
compat_urllib_parse_unquote,
compat_urlparse,
)
from ..utils import determine_ext
from .bokecc import BokeCCBaseIE
@ -33,9 +36,21 @@ class InfoQIE(BokeCCBaseIE):
'ext': 'flv',
'description': 'md5:308d981fb28fa42f49f9568322c683ff',
},
}, {
'url': 'https://www.infoq.com/presentations/Simple-Made-Easy',
'md5': '0e34642d4d9ef44bf86f66f6399672db',
'info_dict': {
'id': 'Simple-Made-Easy',
'title': 'Simple Made Easy',
'ext': 'mp3',
'description': 'md5:3e0e213a8bbd074796ef89ea35ada25b',
},
'params': {
'format': 'bestaudio',
},
}]
def _extract_rtmp_videos(self, webpage):
def _extract_rtmp_video(self, webpage):
# The server URL is hardcoded
video_url = 'rtmpe://video.infoq.com/cfx/st/'
@ -47,28 +62,53 @@ class InfoQIE(BokeCCBaseIE):
playpath = 'mp4:' + real_id
return [{
'format_id': 'rtmp',
'format_id': 'rtmp_video',
'url': video_url,
'ext': determine_ext(playpath),
'play_path': playpath,
}]
def _extract_http_videos(self, webpage):
http_video_url = self._search_regex(r'P\.s\s*=\s*\'([^\']+)\'', webpage, 'video URL')
def _extract_cookies(self, webpage):
policy = self._search_regex(r'InfoQConstants.scp\s*=\s*\'([^\']+)\'', webpage, 'policy')
signature = self._search_regex(r'InfoQConstants.scs\s*=\s*\'([^\']+)\'', webpage, 'signature')
key_pair_id = self._search_regex(r'InfoQConstants.sck\s*=\s*\'([^\']+)\'', webpage, 'key-pair-id')
return 'CloudFront-Policy=%s; CloudFront-Signature=%s; CloudFront-Key-Pair-Id=%s' % (
policy, signature, key_pair_id)
def _extract_http_video(self, webpage):
http_video_url = self._search_regex(r'P\.s\s*=\s*\'([^\']+)\'', webpage, 'video URL')
return [{
'format_id': 'http',
'format_id': 'http_video',
'url': http_video_url,
'http_headers': {
'Cookie': 'CloudFront-Policy=%s; CloudFront-Signature=%s; CloudFront-Key-Pair-Id=%s' % (
policy, signature, key_pair_id),
'Cookie': self._extract_cookies(webpage)
},
}]
def _extract_http_audio(self, webpage, video_id):
fields = self._hidden_inputs(webpage)
http_audio_url = fields['filename']
if http_audio_url is None:
return []
cookies_header = {'Cookie': self._extract_cookies(webpage)}
# base URL is found in the Location header in the response returned by
# GET https://www.infoq.com/mp3download.action?filename=... when logged in.
http_audio_url = compat_urlparse.urljoin('http://res.infoq.com/downloads/mp3downloads/', http_audio_url)
# audio file seem to be missing some times even if there is a download link
# so probe URL to make sure
if not self._is_valid_url(http_audio_url, video_id, headers=cookies_header):
return []
return [{
'format_id': 'http_audio',
'url': http_audio_url,
'vcodec': 'none',
'http_headers': cookies_header,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
@ -80,7 +120,10 @@ class InfoQIE(BokeCCBaseIE):
# for China videos, HTTP video URL exists but always fails with 403
formats = self._extract_bokecc_formats(webpage, video_id)
else:
formats = self._extract_rtmp_videos(webpage) + self._extract_http_videos(webpage)
formats = (
self._extract_rtmp_video(webpage) +
self._extract_http_video(webpage) +
self._extract_http_audio(webpage, video_id))
self._sort_formats(formats)

View File

@ -65,7 +65,7 @@ class IPrimaIE(InfoExtractor):
options = self._parse_json(
self._search_regex(
r'(?s)var\s+playerOptions\s*=\s*({.+?});',
r'(?s)(?:TDIPlayerOptions|playerOptions)\s*=\s*({.+?});\s*\]\]',
playerpage, 'player options', default='{}'),
video_id, transform_source=js_to_json, fatal=False)
if options:

View File

@ -3,14 +3,18 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlparse
from ..utils import remove_end
from ..utils import (
int_or_none,
mimetype2ext,
remove_end,
)
class IwaraIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.|ecchi\.)?iwara\.tv/videos/(?P<id>[a-zA-Z0-9]+)'
_TESTS = [{
'url': 'http://iwara.tv/videos/amVwUl1EHpAD9RD',
'md5': '1d53866b2c514b23ed69e4352fdc9839',
# md5 is unstable
'info_dict': {
'id': 'amVwUl1EHpAD9RD',
'ext': 'mp4',
@ -23,17 +27,17 @@ class IwaraIE(InfoExtractor):
'info_dict': {
'id': '0B1LvuHnL-sRFNXB1WHNqbGw4SXc',
'ext': 'mp4',
'title': '[3D Hentai] Kyonyu Ã\x97 Genkai Ã\x97 Emaki Shinobi Girls.mp4',
'title': '[3D Hentai] Kyonyu × Genkai × Emaki Shinobi Girls.mp4',
'age_limit': 18,
},
'add_ie': ['GoogleDrive'],
}, {
'url': 'http://www.iwara.tv/videos/nawkaumd6ilezzgq',
'md5': '1d85f1e5217d2791626cff5ec83bb189',
# md5 is unstable
'info_dict': {
'id': '6liAP9s2Ojc',
'ext': 'mp4',
'age_limit': 0,
'age_limit': 18,
'title': '[MMD] Do It Again Ver.2 [1080p 60FPS] (Motion,Camera,Wav+DL)',
'description': 'md5:590c12c0df1443d833fbebe05da8c47a',
'upload_date': '20160910',
@ -52,9 +56,9 @@ class IwaraIE(InfoExtractor):
# ecchi is 'sexy' in Japanese
age_limit = 18 if hostname.split('.')[0] == 'ecchi' else 0
entries = self._parse_html5_media_entries(url, webpage, video_id)
video_data = self._download_json('http://www.iwara.tv/api/video/%s' % video_id, video_id)
if not entries:
if not video_data:
iframe_url = self._html_search_regex(
r'<iframe[^>]+src=([\'"])(?P<url>[^\'"]+)\1',
webpage, 'iframe URL', group='url')
@ -67,11 +71,25 @@ class IwaraIE(InfoExtractor):
title = remove_end(self._html_search_regex(
r'<title>([^<]+)</title>', webpage, 'title'), ' | Iwara')
info_dict = entries[0]
info_dict.update({
formats = []
for a_format in video_data:
format_id = a_format.get('resolution')
height = int_or_none(self._search_regex(
r'(\d+)p', format_id, 'height', default=None))
formats.append({
'url': a_format['uri'],
'format_id': format_id,
'ext': mimetype2ext(a_format.get('mime')) or 'mp4',
'height': height,
'width': int_or_none(height / 9.0 * 16.0 if height else None),
'quality': 1 if format_id == 'Source' else 0,
})
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'age_limit': age_limit,
})
return info_dict
'formats': formats,
}

View File

@ -17,9 +17,10 @@ class MySpaceIE(InfoExtractor):
_TESTS = [
{
'url': 'https://myspace.com/fiveminutestothestage/video/little-big-town/109594919',
'md5': '9c1483c106f4a695c47d2911feed50a7',
'info_dict': {
'id': '109594919',
'ext': 'flv',
'ext': 'mp4',
'title': 'Little Big Town',
'description': 'This country quartet was all smiles while playing a sold out show at the Pacific Amphitheatre in Orange County, California.',
'uploader': 'Five Minutes to the Stage',
@ -27,37 +28,30 @@ class MySpaceIE(InfoExtractor):
'timestamp': 1414108751,
'upload_date': '20141023',
},
'params': {
# rtmp download
'skip_download': True,
},
},
# songs
{
'url': 'https://myspace.com/killsorrow/music/song/of-weakened-soul...-93388656-103880681',
'md5': '1d7ee4604a3da226dd69a123f748b262',
'info_dict': {
'id': '93388656',
'ext': 'flv',
'ext': 'm4a',
'title': 'Of weakened soul...',
'uploader': 'Killsorrow',
'uploader_id': 'killsorrow',
},
'params': {
# rtmp download
'skip_download': True,
},
}, {
'add_ie': ['Vevo'],
'add_ie': ['Youtube'],
'url': 'https://myspace.com/threedaysgrace/music/song/animal-i-have-become-28400208-28218041',
'info_dict': {
'id': 'USZM20600099',
'ext': 'mp4',
'title': 'Animal I Have Become',
'uploader': 'Three Days Grace',
'timestamp': int,
'upload_date': '20060502',
'id': 'xqds0B_meys',
'ext': 'webm',
'title': 'Three Days Grace - Animal I Have Become',
'description': 'md5:8bd86b3693e72a077cf863a8530c54bb',
'uploader': 'ThreeDaysGraceVEVO',
'uploader_id': 'ThreeDaysGraceVEVO',
'upload_date': '20091002',
},
'skip': 'VEVO is only available in some countries',
}, {
'add_ie': ['Youtube'],
'url': 'https://myspace.com/starset2/music/song/first-light-95799905-106964426',
@ -76,24 +70,46 @@ class MySpaceIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
is_song = mobj.group('mediatype').startswith('music/song')
webpage = self._download_webpage(url, video_id)
player_url = self._search_regex(
r'playerSwf":"([^"?]*)', webpage, 'player URL')
r'videoSwf":"([^"?]*)', webpage, 'player URL', fatal=False)
def rtmp_format_from_stream_url(stream_url, width=None, height=None):
rtmp_url, play_path = stream_url.split(';', 1)
return {
'format_id': 'rtmp',
'url': rtmp_url,
'play_path': play_path,
'player_url': player_url,
'protocol': 'rtmp',
'ext': 'flv',
'width': width,
'height': height,
}
def formats_from_stream_urls(stream_url, hls_stream_url, http_stream_url, width=None, height=None):
formats = []
vcodec = 'none' if is_song else None
if hls_stream_url:
formats.append({
'format_id': 'hls',
'url': hls_stream_url,
'protocol': 'm3u8_native',
'ext': 'm4a' if is_song else 'mp4',
'vcodec': vcodec,
})
if stream_url and player_url:
rtmp_url, play_path = stream_url.split(';', 1)
formats.append({
'format_id': 'rtmp',
'url': rtmp_url,
'play_path': play_path,
'player_url': player_url,
'protocol': 'rtmp',
'ext': 'flv',
'width': width,
'height': height,
'vcodec': vcodec,
})
if http_stream_url:
formats.append({
'format_id': 'http',
'url': http_stream_url,
'width': width,
'height': height,
'vcodec': vcodec,
})
return formats
if mobj.group('mediatype').startswith('music/song'):
if is_song:
# songs don't store any useful info in the 'context' variable
song_data = self._search_regex(
r'''<button.*data-song-id=(["\'])%s\1.*''' % video_id,
@ -108,8 +124,10 @@ class MySpaceIE(InfoExtractor):
return self._search_regex(
r'''data-%s=([\'"])(?P<data>.*?)\1''' % name,
song_data, name, default='', group='data')
stream_url = search_data('stream-url')
if not stream_url:
formats = formats_from_stream_urls(
search_data('stream-url'), search_data('hls-stream-url'),
search_data('http-stream-url'))
if not formats:
vevo_id = search_data('vevo-id')
youtube_id = search_data('youtube-id')
if vevo_id:
@ -121,6 +139,7 @@ class MySpaceIE(InfoExtractor):
else:
raise ExtractorError(
'Found song but don\'t know how to download it')
self._sort_formats(formats)
return {
'id': video_id,
'title': self._og_search_title(webpage),
@ -128,27 +147,16 @@ class MySpaceIE(InfoExtractor):
'uploader_id': search_data('artist-username'),
'thumbnail': self._og_search_thumbnail(webpage),
'duration': int_or_none(search_data('duration')),
'formats': [rtmp_format_from_stream_url(stream_url)]
'formats': formats,
}
else:
video = self._parse_json(self._search_regex(
r'context = ({.*?});', webpage, 'context'),
video_id)['video']
formats = []
hls_stream_url = video.get('hlsStreamUrl')
if hls_stream_url:
formats.append({
'format_id': 'hls',
'url': hls_stream_url,
'protocol': 'm3u8_native',
'ext': 'mp4',
})
stream_url = video.get('streamUrl')
if stream_url:
formats.append(rtmp_format_from_stream_url(
stream_url,
int_or_none(video.get('width')),
int_or_none(video.get('height'))))
formats = formats_from_stream_urls(
video.get('streamUrl'), video.get('hlsStreamUrl'),
video.get('mp4StreamUrl'), int_or_none(video.get('width')),
int_or_none(video.get('height')))
self._sort_formats(formats)
return {
'id': video_id,

View File

@ -4,23 +4,26 @@ import re
from .common import InfoExtractor
from .theplatform import ThePlatformIE
from .adobepass import AdobePassIE
from ..compat import compat_urllib_parse_urlparse
from ..utils import (
find_xpath_attr,
lowercase_escape,
smuggle_url,
unescapeHTML,
update_url_query,
int_or_none,
)
class NBCIE(InfoExtractor):
class NBCIE(AdobePassIE):
_VALID_URL = r'https?://(?:www\.)?nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'
_TESTS = [
{
'url': 'http://www.nbc.com/the-tonight-show/segments/112966',
'url': 'http://www.nbc.com/the-tonight-show/video/jimmy-fallon-surprises-fans-at-ben-jerrys/2848237',
'info_dict': {
'id': '112966',
'id': '2848237',
'ext': 'mp4',
'title': 'Jimmy Fallon Surprises Fans at Ben & Jerry\'s',
'description': 'Jimmy gives out free scoops of his new "Tonight Dough" ice cream flavor by surprising customers at the Ben & Jerry\'s scoop shop.',
@ -69,7 +72,7 @@ class NBCIE(InfoExtractor):
# HLS streams requires the 'hdnea3' cookie
'url': 'http://www.nbc.com/Kings/video/goliath/n1806',
'info_dict': {
'id': 'n1806',
'id': '101528f5a9e8127b107e98c5e6ce4638',
'ext': 'mp4',
'title': 'Goliath',
'description': 'When an unknown soldier saves the life of the King\'s son in battle, he\'s thrust into the limelight and politics of the kingdom.',
@ -87,21 +90,57 @@ class NBCIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
theplatform_url = unescapeHTML(lowercase_escape(self._html_search_regex(
[
r'(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"',
r'<iframe[^>]+src="((?:https?:)?//player\.theplatform\.com/[^"]+)"',
r'"embedURL"\s*:\s*"([^"]+)"'
],
webpage, 'theplatform url').replace('_no_endcard', '').replace('\\/', '/')))
if theplatform_url.startswith('//'):
theplatform_url = 'http:' + theplatform_url
return {
info = {
'_type': 'url_transparent',
'ie_key': 'ThePlatform',
'url': smuggle_url(theplatform_url, {'source_url': url}),
'id': video_id,
}
video_data = None
preload = self._search_regex(
r'PRELOAD\s*=\s*({.+})', webpage, 'preload data', default=None)
if preload:
preload_data = self._parse_json(preload, video_id)
path = compat_urllib_parse_urlparse(url).path.rstrip('/')
entity_id = preload_data.get('xref', {}).get(path)
video_data = preload_data.get('entities', {}).get(entity_id)
if video_data:
query = {
'mbr': 'true',
'manifest': 'm3u',
}
video_id = video_data['guid']
title = video_data['title']
if video_data.get('entitlement') == 'auth':
resource = self._get_mvpd_resource(
'nbcentertainment', title, video_id,
video_data.get('vChipRating'))
query['auth'] = self._extract_mvpd_auth(
url, video_id, 'nbcentertainment', resource)
theplatform_url = smuggle_url(update_url_query(
'http://link.theplatform.com/s/NnzsPC/media/guid/2410887629/' + video_id,
query), {'force_smil_url': True})
info.update({
'id': video_id,
'title': title,
'url': theplatform_url,
'description': video_data.get('description'),
'keywords': video_data.get('keywords'),
'season_number': int_or_none(video_data.get('seasonNumber')),
'episode_number': int_or_none(video_data.get('episodeNumber')),
'series': video_data.get('showName'),
})
else:
theplatform_url = unescapeHTML(lowercase_escape(self._html_search_regex(
[
r'(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"',
r'<iframe[^>]+src="((?:https?:)?//player\.theplatform\.com/[^"]+)"',
r'"embedURL"\s*:\s*"([^"]+)"'
],
webpage, 'theplatform url').replace('_no_endcard', '').replace('\\/', '/')))
if theplatform_url.startswith('//'):
theplatform_url = 'http:' + theplatform_url
info['url'] = smuggle_url(theplatform_url, {'source_url': url})
return info
class NBCSportsVPlayerIE(InfoExtractor):

View File

@ -128,6 +128,22 @@ class NRKBaseIE(InfoExtractor):
series = conviva.get('seriesName') or data.get('seriesTitle')
episode = conviva.get('episodeName') or data.get('episodeNumberOrDate')
season_number = None
episode_number = None
if data.get('mediaElementType') == 'Episode':
_season_episode = data.get('scoresStatistics', {}).get('springStreamStream') or \
data.get('relativeOriginUrl', '')
EPISODENUM_RE = [
r'/s(?P<season>\d{,2})e(?P<episode>\d{,2})\.',
r'/sesong-(?P<season>\d{,2})/episode-(?P<episode>\d{,2})',
]
season_number = int_or_none(self._search_regex(
EPISODENUM_RE, _season_episode, 'season number',
default=None, group='season'))
episode_number = int_or_none(self._search_regex(
EPISODENUM_RE, _season_episode, 'episode number',
default=None, group='episode'))
thumbnails = None
images = data.get('images')
if images and isinstance(images, dict):
@ -140,11 +156,15 @@ class NRKBaseIE(InfoExtractor):
} for image in web_images if image.get('imageUrl')]
description = data.get('description')
category = data.get('mediaAnalytics', {}).get('category')
common_info = {
'description': description,
'series': series,
'episode': episode,
'season_number': season_number,
'episode_number': episode_number,
'categories': [category] if category else None,
'age_limit': parse_age_limit(data.get('legalAge')),
'thumbnails': thumbnails,
}
@ -227,54 +247,102 @@ class NRKTVIE(NRKBaseIE):
'title': '20 spørsmål 23.05.2014',
'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
'duration': 1741,
'series': '20 spørsmål - TV',
'episode': '23.05.2014',
},
}, {
'url': 'https://tv.nrk.no/program/mdfp15000514',
'md5': '43d0be26663d380603a9cf0c24366531',
'info_dict': {
'id': 'MDFP15000514CA',
'ext': 'mp4',
'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting 24.05.2014',
'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db',
'duration': 4605,
'series': 'Kunnskapskanalen',
'episode': '24.05.2014',
},
'params': {
'skip_download': True,
},
}, {
# single playlist video
'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
'md5': 'adbd1dbd813edaf532b0a253780719c2',
'info_dict': {
'id': 'MSPO40010515-part2',
'ext': 'flv',
'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
},
'skip': 'Only works from Norway',
'params': {
'skip_download': True,
},
'expected_warnings': ['Video is geo restricted'],
'skip': 'particular part is not supported currently',
}, {
'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
'playlist': [{
'md5': '9480285eff92d64f06e02a5367970a7a',
'info_dict': {
'id': 'MSPO40010515-part1',
'ext': 'flv',
'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)',
'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
'id': 'MSPO40010515AH',
'ext': 'mp4',
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 1)',
'description': 'md5:c03aba1e917561eface5214020551b7a',
'duration': 772,
'series': 'Tour de Ski',
'episode': '06.01.2015',
},
'params': {
'skip_download': True,
},
}, {
'md5': 'adbd1dbd813edaf532b0a253780719c2',
'info_dict': {
'id': 'MSPO40010515-part2',
'ext': 'flv',
'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
'id': 'MSPO40010515BH',
'ext': 'mp4',
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 2)',
'description': 'md5:c03aba1e917561eface5214020551b7a',
'duration': 6175,
'series': 'Tour de Ski',
'episode': '06.01.2015',
},
'params': {
'skip_download': True,
},
}],
'info_dict': {
'id': 'MSPO40010515',
'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn',
'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
'duration': 6947.52,
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
'description': 'md5:c03aba1e917561eface5214020551b7a',
},
'expected_warnings': ['Video is geo restricted'],
}, {
'url': 'https://tv.nrk.no/serie/anno/KMTE50001317/sesong-3/episode-13',
'info_dict': {
'id': 'KMTE50001317AA',
'ext': 'mp4',
'title': 'Anno 13:30',
'description': 'md5:11d9613661a8dbe6f9bef54e3a4cbbfa',
'duration': 2340,
'series': 'Anno',
'episode': '13:30',
'season_number': 3,
'episode_number': 13,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://tv.nrk.no/serie/nytt-paa-nytt/MUHH46000317/27-01-2017',
'info_dict': {
'id': 'MUHH46000317AA',
'ext': 'mp4',
'title': 'Nytt på Nytt 27.01.2017',
'description': 'md5:5358d6388fba0ea6f0b6d11c48b9eb4b',
'duration': 1796,
'series': 'Nytt på nytt',
'episode': '27.01.2017',
},
'params': {
'skip_download': True,
},
'skip': 'Only works from Norway',
}, {
'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
'only_matching': True,
@ -360,6 +428,64 @@ 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) 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+)'

View File

@ -16,18 +16,33 @@ from ..utils import (
class PikselIE(InfoExtractor):
_VALID_URL = r'https?://player\.piksel\.com/v/(?P<id>[a-z0-9]+)'
_TEST = {
'url': 'http://player.piksel.com/v/nv60p12f',
'md5': 'd9c17bbe9c3386344f9cfd32fad8d235',
'info_dict': {
'id': 'nv60p12f',
'ext': 'mp4',
'title': 'فن الحياة - الحلقة 1',
'description': 'احدث برامج الداعية الاسلامي " مصطفي حسني " فى رمضان 2016علي النهار نور',
'timestamp': 1465231790,
'upload_date': '20160606',
_TESTS = [
{
'url': 'http://player.piksel.com/v/nv60p12f',
'md5': 'd9c17bbe9c3386344f9cfd32fad8d235',
'info_dict': {
'id': 'nv60p12f',
'ext': 'mp4',
'title': 'فن الحياة - الحلقة 1',
'description': 'احدث برامج الداعية الاسلامي " مصطفي حسني " فى رمضان 2016علي النهار نور',
'timestamp': 1465231790,
'upload_date': '20160606',
}
},
{
# Original source: http://www.uscourts.gov/cameras-courts/state-washington-vs-donald-j-trump-et-al
'url': 'https://player.piksel.com/v/v80kqp41',
'md5': '753ddcd8cc8e4fa2dda4b7be0e77744d',
'info_dict': {
'id': 'v80kqp41',
'ext': 'mp4',
'title': 'WAW- State of Washington vs. Donald J. Trump, et al',
'description': 'State of Washington vs. Donald J. Trump, et al, Case Number 17-CV-00141-JLR, TRO Hearing, Civil Rights Case, 02/3/2017, 1:00 PM (PST), Seattle Federal Courthouse, Seattle, WA, Judge James L. Robart presiding.',
'timestamp': 1486171129,
'upload_date': '20170204',
}
}
}
]
@staticmethod
def _extract_url(webpage):
@ -40,8 +55,10 @@ class PikselIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
app_token = self._search_regex(
r'clientAPI\s*:\s*"([^"]+)"', webpage, 'app token')
app_token = self._search_regex([
r'clientAPI\s*:\s*"([^"]+)"',
r'data-de-api-key\s*=\s*"([^"]+)"'
], webpage, 'app token')
response = self._download_json(
'http://player.piksel.com/ws/ws_program/api/%s/mode/json/apiv/5' % app_token,
video_id, query={

View File

@ -156,7 +156,12 @@ class PornHubIE(InfoExtractor):
comment_count = self._extract_count(
r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
video_urls = list(map(compat_urllib_parse_unquote, re.findall(r"player_quality_[0-9]{3}p\s*=\s*'([^']+)'", webpage)))
video_urls = []
for quote, video_url in re.findall(
r'player_quality_[0-9]{3,4}p\s*=\s*(["\'])(.+?)\1;', webpage):
video_urls.append(compat_urllib_parse_unquote(re.sub(
r'{0}\s*\+\s*{0}'.format(quote), '', video_url)))
if webpage.find('"encrypted":true') != -1:
password = compat_urllib_parse_unquote_plus(
self._search_regex(r'"video_title":"([^"]+)', webpage, 'password'))

View File

@ -147,16 +147,12 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
'url': 'http://www.prosieben.de/tv/circus-halligalli/videos/218-staffel-2-episode-18-jahresrueckblick-ganze-folge',
'info_dict': {
'id': '2104602',
'ext': 'flv',
'ext': 'mp4',
'title': 'Episode 18 - Staffel 2',
'description': 'md5:8733c81b702ea472e069bc48bb658fc1',
'upload_date': '20131231',
'duration': 5845.04,
},
'params': {
# rtmp download
'skip_download': True,
},
},
{
'url': 'http://www.prosieben.de/videokatalog/Gesellschaft/Leben/Trends/video-Lady-Umstyling-f%C3%BCr-Audrina-Rebekka-Audrina-Fergen-billig-aussehen-Battal-Modica-700544.html',
@ -258,7 +254,7 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
'url': 'http://www.the-voice-of-germany.de/video/31-andreas-kuemmert-rocket-man-clip',
'info_dict': {
'id': '2572814',
'ext': 'flv',
'ext': 'mp4',
'title': 'Andreas Kümmert: Rocket Man',
'description': 'md5:6ddb02b0781c6adf778afea606652e38',
'upload_date': '20131017',
@ -272,7 +268,7 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
'url': 'http://www.fem.com/wellness/videos/wellness-video-clip-kurztripps-zum-valentinstag.html',
'info_dict': {
'id': '2156342',
'ext': 'flv',
'ext': 'mp4',
'title': 'Kurztrips zum Valentinstag',
'description': 'Romantischer Kurztrip zum Valentinstag? Nina Heinemann verrät, was sich hier wirklich lohnt.',
'duration': 307.24,
@ -289,12 +285,13 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
'description': 'md5:63b8963e71f481782aeea877658dec84',
},
'playlist_count': 2,
'skip': 'This video is unavailable',
},
{
'url': 'http://www.7tv.de/circus-halligalli/615-best-of-circus-halligalli-ganze-folge',
'info_dict': {
'id': '4187506',
'ext': 'flv',
'ext': 'mp4',
'title': 'Best of Circus HalliGalli',
'description': 'md5:8849752efd90b9772c9db6fdf87fb9e9',
'upload_date': '20151229',
@ -375,7 +372,9 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
title = self._html_search_regex(self._TITLE_REGEXES, webpage, 'title')
info = self._extract_video_info(url, clip_id)
description = self._html_search_regex(
self._DESCRIPTION_REGEXES, webpage, 'description', fatal=False)
self._DESCRIPTION_REGEXES, webpage, 'description', default=None)
if description is None:
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(self._html_search_regex(
self._UPLOAD_DATE_REGEXES, webpage, 'upload date', default=None))

View File

@ -54,9 +54,8 @@ class RadioCanadaIE(InfoExtractor):
raise ExtractorError('This video is DRM protected.', expected=True)
device_types = ['ipad']
if app_code != 'toutv':
device_types.append('flash')
if not smuggled_data:
device_types.append('flash')
device_types.append('android')
formats = []
@ -103,7 +102,7 @@ class RadioCanadaIE(InfoExtractor):
continue
f_url = re.sub(r'\d+\.%s' % ext, '%d.%s' % (tbr, ext), v_url)
protocol = determine_protocol({'url': f_url})
formats.append({
f = {
'format_id': '%s-%d' % (protocol, tbr),
'url': f_url,
'ext': 'flv' if protocol == 'rtmp' else ext,
@ -111,7 +110,14 @@ class RadioCanadaIE(InfoExtractor):
'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)

View File

@ -0,0 +1,60 @@
# coding: utf-8
from __future__ import unicode_literals
from .adobepass import AdobePassIE
from ..utils import (
int_or_none,
smuggle_url,
update_url_query,
)
class ScrippsNetworksWatchIE(AdobePassIE):
IE_NAME = 'scrippsnetworks:watch'
_VALID_URL = r'https?://watch\.(?:hgtv|foodnetwork|travelchannel|diynetwork|cookingchanneltv)\.com/player\.[A-Z0-9]+\.html#(?P<id>\d+)'
_TEST = {
'url': 'http://watch.hgtv.com/player.HNT.html#0256538',
'md5': '26545fd676d939954c6808274bdb905a',
'info_dict': {
'id': '0256538',
'ext': 'mp4',
'title': 'Seeking a Wow House',
'description': 'Buyers retiring in Palm Springs, California, want a modern house with major wow factor. They\'re also looking for a pool and a large, open floorplan with tall windows looking out at the views.',
'uploader': 'SCNI',
'upload_date': '20170207',
'timestamp': 1486450493,
},
'skip': 'requires TV provider authentication',
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
channel = self._parse_json(self._search_regex(
r'"channels"\s*:\s*(\[.+\])',
webpage, 'channels'), video_id)[0]
video_data = next(v for v in channel['videos'] if v.get('nlvid') == video_id)
title = video_data['title']
release_url = video_data['releaseUrl']
if video_data.get('restricted'):
requestor_id = self._search_regex(
r'requestorId\s*=\s*"([^"]+)";', webpage, 'requestor id')
resource = self._get_mvpd_resource(
requestor_id, title, video_id,
video_data.get('ratings', [{}])[0].get('rating'))
auth = self._extract_mvpd_auth(
url, video_id, requestor_id, resource)
release_url = update_url_query(release_url, {'auth': auth})
return {
'_type': 'url_transparent',
'id': video_id,
'title': title,
'url': smuggle_url(release_url, {'force_smil_url': True}),
'description': video_data.get('description'),
'thumbnail': video_data.get('thumbnailUrl'),
'series': video_data.get('showTitle'),
'season_number': int_or_none(video_data.get('season')),
'episode_number': int_or_none(video_data.get('episodeNumber')),
'ie_key': 'ThePlatform',
}

View File

@ -1,64 +1,101 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
qualities,
int_or_none,
mimetype2ext,
determine_ext,
int_or_none,
try_get,
qualities,
)
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/jamel-et-ses-amis-au-marrakech-du-rire-p_1316/jamel-et-ses-amis-au-marrakech-du-rire-2015-c_11495320',
'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',
'info_dict': {
'id': '11495320',
'id': '11638450',
'ext': 'mp4',
'title': 'Jamel et ses amis au Marrakech du rire 2015',
'description': 'md5:ba2149d5c321d5201b78070ee839d872',
'title': 'Le Meilleur Pâtissier, spécial fêtes mercredi à 21:00 sur M6',
'description': 'md5:308853f6a5f9e2d55a30fc0654de415f',
'duration': 39,
'series': 'Le meilleur pâtissier',
},
'params': {
'skip_download': True,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
clip_data = self._download_json(
'https://player.m6web.fr/v2/video/config/6play-auth/FR/%s.json' % video_id,
video_id)
video_data = clip_data['videoInfo']
data = self._download_json(
'https://pc.middleware.6play.fr/6play/v2/platforms/m6group_web/services/6play/videos/clip_%s' % video_id,
video_id, query={
'csa': 5,
'with': 'clips',
})
clip_data = data['clips'][0]
title = clip_data['title']
urls = []
quality_key = qualities(['lq', 'sd', 'hq', 'hd'])
formats = []
for source in clip_data['sources']:
source_type, source_url = source.get('type'), source.get('src')
if not source_url or source_type == 'hls/primetime':
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:
continue
ext = mimetype2ext(source_type) or determine_ext(source_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
formats.extend(self._extract_f4m_formats(
source_url.replace('.m3u8', '.f4m'),
video_id, f4m_id='hds', fatal=False))
elif ext == 'mp4':
quality = source.get('quality')
urls.append(asset_url)
container = asset.get('video_container')
ext = determine_ext(asset_url)
if container == 'm3u8' or ext == 'm3u8':
if protocol == 'usp':
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('/[^/]+\.m3u8', '/Manifest', asset_url),
video_id, ism_id='mss', fatal=False))
else:
formats.extend(self._extract_m3u8_formats(
asset_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
elif container == 'mp4' or ext == 'mp4':
quality = asset.get('video_quality')
formats.append({
'url': source_url,
'url': asset_url,
'format_id': quality,
'quality': quality_key(quality),
'ext': ext,
})
self._sort_formats(formats)
def get(getter):
for src in (data, clip_data):
v = try_get(src, getter, compat_str)
if v:
return v
return {
'id': video_id,
'title': video_data['title'].strip(),
'description': video_data.get('description'),
'duration': int_or_none(video_data.get('duration')),
'series': video_data.get('titlePgm'),
'title': title,
'description': get(lambda x: x['description']),
'duration': int_or_none(clip_data.get('duration')),
'series': get(lambda x: x['program']['title']),
'formats': formats,
}

View File

@ -4,65 +4,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
js_to_json,
unified_strdate,
)
class SportBoxIE(InfoExtractor):
_VALID_URL = r'https?://news\.sportbox\.ru/(?:[^/]+/)+spbvideo_NI\d+_(?P<display_id>.+)'
_TESTS = [{
'url': 'http://news.sportbox.ru/Vidy_sporta/Avtosport/Rossijskij/spbvideo_NI483529_Gonka-2-zaezd-Obyedinenniy-2000-klassi-Turing-i-S',
'md5': 'ff56a598c2cf411a9a38a69709e97079',
'info_dict': {
'id': '80822',
'ext': 'mp4',
'title': 'Гонка 2 заезд ««Объединенный 2000»: классы Туринг и Супер-продакшн',
'description': 'md5:3d72dc4a006ab6805d82f037fdc637ad',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20140928',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://news.sportbox.ru/Vidy_sporta/billiard/spbvideo_NI486287_CHempionat-mira-po-dinamichnoy-piramide-4',
'only_matching': True,
}, {
'url': 'http://news.sportbox.ru/video/no_ads/spbvideo_NI536574_V_Novorossijske_proshel_detskij_turnir_Pole_slavy_bojevoj?ci=211355',
'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)
player = self._search_regex(
r'src="/?(vdl/player/[^"]+)"', webpage, 'player')
title = self._html_search_regex(
[r'"nodetitle"\s*:\s*"([^"]+)"', r'class="node-header_{1,2}title">([^<]+)'],
webpage, 'title')
description = self._og_search_description(webpage) or self._html_search_meta(
'description', webpage, 'description')
thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(self._html_search_meta(
'dateCreated', webpage, 'upload date'))
return {
'_type': 'url_transparent',
'url': compat_urlparse.urljoin(url, '/%s' % player),
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'upload_date': upload_date,
}
from ..utils import js_to_json
class SportBoxEmbedIE(InfoExtractor):

View File

@ -0,0 +1,52 @@
# coding: utf-8
from __future__ import unicode_literals
from .adobepass import AdobePassIE
from ..utils import (
extract_attributes,
update_url_query,
smuggle_url,
)
class SproutIE(AdobePassIE):
_VALID_URL = r'https?://(?:www\.)?sproutonline\.com/watch/(?P<id>[^/?#]+)'
_TEST = {
'url': 'http://www.sproutonline.com/watch/cowboy-adventure',
'md5': '74bf14128578d1e040c3ebc82088f45f',
'info_dict': {
'id': '9dexnwtmh8_X',
'ext': 'mp4',
'title': 'A Cowboy Adventure',
'description': 'Ruff-Ruff, Tweet and Dave get to be cowboys for the day at Six Cow Corral.',
'timestamp': 1437758640,
'upload_date': '20150724',
'uploader': 'NBCU-SPROUT-NEW',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_component = self._search_regex(
r'(?s)(<div[^>]+data-component="video"[^>]*?>)',
webpage, 'video component', default=None)
if video_component:
options = self._parse_json(extract_attributes(
video_component)['data-options'], video_id)
theplatform_url = options['video']
query = {
'mbr': 'true',
'manifest': 'm3u',
}
if options.get('protected'):
query['auth'] = self._extract_mvpd_auth(url, options['pid'], 'sprout', 'sprout')
theplatform_url = smuggle_url(update_url_query(
theplatform_url, query), {'force_smil_url': True})
else:
iframe = self._search_regex(
r'(<iframe[^>]+id="sproutVideoIframe"[^>]*?>)',
webpage, 'iframe')
theplatform_url = extract_attributes(iframe)['src']
return self.url_result(theplatform_url, 'ThePlatform')

View File

@ -100,9 +100,13 @@ class TurnerBaseIE(AdobePassIE):
formats.extend(self._extract_smil_formats(
video_url, video_id, fatal=False))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
m3u8_formats = self._extract_m3u8_formats(
video_url, video_id, 'mp4',
m3u8_id=format_id or 'hls', fatal=False))
m3u8_id=format_id or 'hls', fatal=False)
if '/secure/' in video_url and '?hdnea=' in video_url:
for f in m3u8_formats:
f['_seekable'] = False
formats.extend(m3u8_formats)
elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(
update_url_query(video_url, {'hdcore': '3.7.0'}),

View File

@ -447,7 +447,14 @@ class TwitchHighlightsIE(TwitchVideosBaseIE):
class TwitchStreamIE(TwitchBaseIE):
IE_NAME = 'twitch:stream'
_VALID_URL = r'%s/(?P<id>[^/#?]+)/?(?:\#.*)?$' % TwitchBaseIE._VALID_URL_BASE
_VALID_URL = r'''(?x)
https?://
(?:
(?:www\.)?twitch\.tv/|
player\.twitch\.tv/\?.*?\bchannel=
)
(?P<id>[^/#?]+)
'''
_TESTS = [{
'url': 'http://www.twitch.tv/shroomztv',
@ -471,8 +478,25 @@ class TwitchStreamIE(TwitchBaseIE):
}, {
'url': 'http://www.twitch.tv/miracle_doto#profile-0',
'only_matching': True,
}, {
'url': 'https://player.twitch.tv/?channel=lotsofs',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return (False
if any(ie.suitable(url) for ie in (
TwitchVideoIE,
TwitchChapterIE,
TwitchVodIE,
TwitchProfileIE,
TwitchAllVideosIE,
TwitchUploadsIE,
TwitchPastBroadcastsIE,
TwitchHighlightsIE))
else super(TwitchStreamIE, cls).suitable(url))
def _real_extract(self, url):
channel_id = self._match_id(url)

View File

@ -0,0 +1,99 @@
# coding: utf-8
from __future__ import unicode_literals
import random
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
float_or_none,
parse_age_limit,
qualities,
try_get,
unified_timestamp,
urljoin,
)
class VideoPressIE(InfoExtractor):
_VALID_URL = r'https?://videopress\.com/embed/(?P<id>[\da-zA-Z]+)'
_TESTS = [{
'url': 'https://videopress.com/embed/kUJmAcSf',
'md5': '706956a6c875873d51010921310e4bc6',
'info_dict': {
'id': 'kUJmAcSf',
'ext': 'mp4',
'title': 'VideoPress Demo',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 634.6,
'timestamp': 1434983935,
'upload_date': '20150622',
'age_limit': 0,
},
}, {
# 17+, requires birth_* params
'url': 'https://videopress.com/embed/iH3gstfZ',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe[^>]+src=["\']((?:https?://)?videopress\.com/embed/[\da-zA-Z]+)',
webpage)
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._download_json(
'https://public-api.wordpress.com/rest/v1.1/videos/%s' % video_id,
video_id, query={
'birth_month': random.randint(1, 12),
'birth_day': random.randint(1, 31),
'birth_year': random.randint(1950, 1995),
})
title = video['title']
def base_url(scheme):
return try_get(
video, lambda x: x['file_url_base'][scheme], compat_str)
base_url = base_url('https') or base_url('http')
QUALITIES = ('std', 'dvd', 'hd')
quality = qualities(QUALITIES)
formats = []
for format_id, f in video['files'].items():
if not isinstance(f, dict):
continue
for ext, path in f.items():
if ext in ('mp4', 'ogg'):
formats.append({
'url': urljoin(base_url, path),
'format_id': '%s-%s' % (format_id, ext),
'ext': determine_ext(path, ext),
'quality': quality(format_id),
})
original_url = try_get(video, lambda x: x['original'], compat_str)
if original_url:
formats.append({
'url': original_url,
'format_id': 'original',
'quality': len(QUALITIES),
})
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': video.get('description'),
'thumbnail': video.get('poster'),
'duration': float_or_none(video.get('duration'), 1000),
'timestamp': unified_timestamp(video.get('upload_date')),
'age_limit': parse_age_limit(video.get('rating')),
'formats': formats,
}

View File

@ -21,12 +21,12 @@ from ..utils import (
sanitized_Request,
smuggle_url,
std_headers,
unified_strdate,
try_get,
unified_timestamp,
unsmuggle_url,
urlencode_postdata,
unescapeHTML,
parse_filesize,
try_get,
)
@ -142,10 +142,19 @@ class VimeoBaseInfoExtractor(InfoExtractor):
note='Downloading %s m3u8 information' % cdn_name,
fatal=False))
elif files_type == 'dash':
formats.extend(self._extract_mpd_formats(
manifest_url.replace('/master.json', '/master.mpd'), video_id, format_id,
'Downloading %s MPD information' % cdn_name,
fatal=False))
mpd_pattern = r'/%s/(?:sep/)?video/' % video_id
mpd_manifest_urls = []
if re.search(mpd_pattern, manifest_url):
for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
mpd_manifest_urls.append((format_id + suffix, re.sub(
mpd_pattern, '/%s/%s/' % (video_id, repl), manifest_url)))
else:
mpd_manifest_urls = [(format_id, manifest_url)]
for f_id, m_url in mpd_manifest_urls:
formats.extend(self._extract_mpd_formats(
m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
'Downloading %s MPD information' % cdn_name,
fatal=False))
subtitles = {}
text_tracks = config['request'].get('text_tracks')
@ -204,11 +213,13 @@ class VimeoIE(VimeoBaseInfoExtractor):
'ext': 'mp4',
'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
'description': 'md5:2d3305bad981a06ff79f027f19865021',
'timestamp': 1355990239,
'upload_date': '20121220',
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
'uploader_id': 'user7108434',
'uploader': 'Filippo Valsorda',
'duration': 10,
'license': 'by-sa',
},
},
{
@ -249,6 +260,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'id': '68375962',
'ext': 'mp4',
'title': 'youtube-dl password protected test video',
'timestamp': 1371200155,
'upload_date': '20130614',
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
'uploader_id': 'user18948128',
@ -271,7 +283,8 @@ class VimeoIE(VimeoBaseInfoExtractor):
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
'uploader_id': 'atencio',
'uploader': 'Peter Atencio',
'upload_date': '20130927',
'timestamp': 1380339469,
'upload_date': '20130928',
'duration': 187,
},
},
@ -283,6 +296,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'ext': 'mp4',
'title': 'The New Vimeo Player (You Know, For Videos)',
'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
'timestamp': 1381846109,
'upload_date': '20131015',
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
'uploader_id': 'staff',
@ -314,6 +328,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'uploader': 'The DMCI',
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
'uploader_id': 'dmci',
'timestamp': 1324343742,
'upload_date': '20111220',
'description': 'md5:ae23671e82d05415868f7ad1aec21147',
},
@ -329,6 +344,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'uploader': 'Casey Donahue',
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
'uploader_id': 'caseydonahue',
'timestamp': 1250886430,
'upload_date': '20090821',
'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
},
@ -477,6 +493,9 @@ class VimeoIE(VimeoBaseInfoExtractor):
'%s said: %s' % (self.IE_NAME, seed_status['title']),
expected=True)
cc_license = None
timestamp = None
# Extract the config JSON
try:
try:
@ -490,8 +509,12 @@ class VimeoIE(VimeoBaseInfoExtractor):
vimeo_clip_page_config = self._search_regex(
r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
'vimeo clip page config')
config_url = self._parse_json(
vimeo_clip_page_config, video_id)['player']['config_url']
page_config = self._parse_json(vimeo_clip_page_config, video_id)
config_url = page_config['player']['config_url']
cc_license = page_config.get('cc_license')
timestamp = try_get(
page_config, lambda x: x['clip']['uploaded_on'],
compat_str)
config_json = self._download_webpage(config_url, video_id)
config = json.loads(config_json)
except RegexNotFoundError:
@ -560,10 +583,10 @@ class VimeoIE(VimeoBaseInfoExtractor):
self._downloader.report_warning('Cannot find video description')
# Extract upload date
video_upload_date = None
mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
if mobj is not None:
video_upload_date = unified_strdate(mobj.group(1))
if not timestamp:
timestamp = self._search_regex(
r'<time[^>]+datetime="([^"]+)"', webpage,
'timestamp', default=None)
try:
view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
@ -600,15 +623,22 @@ class VimeoIE(VimeoBaseInfoExtractor):
info_dict = self._parse_config(config, video_id)
formats.extend(info_dict['formats'])
self._vimeo_sort_formats(formats)
if not cc_license:
cc_license = self._search_regex(
r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
webpage, 'license', default=None, group='license')
info_dict.update({
'id': video_id,
'formats': formats,
'upload_date': video_upload_date,
'timestamp': unified_timestamp(timestamp),
'description': video_description,
'webpage_url': url,
'view_count': view_count,
'like_count': like_count,
'comment_count': comment_count,
'license': cc_license,
})
return info_dict

View File

@ -6,8 +6,9 @@ import itertools
from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
unified_strdate,
unified_timestamp,
)
@ -20,50 +21,16 @@ class VineIE(InfoExtractor):
'id': 'b9KOOWX7HUx',
'ext': 'mp4',
'title': 'Chicken.',
'alt_title': 'Vine by Jack Dorsey',
'alt_title': 'Vine by Jack',
'timestamp': 1368997951,
'upload_date': '20130519',
'uploader': 'Jack Dorsey',
'uploader': 'Jack',
'uploader_id': '76',
'view_count': int,
'like_count': int,
'comment_count': int,
'repost_count': int,
},
}, {
'url': 'https://vine.co/v/MYxVapFvz2z',
'md5': '7b9a7cbc76734424ff942eb52c8f1065',
'info_dict': {
'id': 'MYxVapFvz2z',
'ext': 'mp4',
'title': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14',
'alt_title': 'Vine by Mars Ruiz',
'upload_date': '20140815',
'uploader': 'Mars Ruiz',
'uploader_id': '1102363502380728320',
'view_count': int,
'like_count': int,
'comment_count': int,
'repost_count': int,
},
}, {
'url': 'https://vine.co/v/bxVjBbZlPUH',
'md5': 'ea27decea3fa670625aac92771a96b73',
'info_dict': {
'id': 'bxVjBbZlPUH',
'ext': 'mp4',
'title': '#mw3 #ac130 #killcam #angelofdeath',
'alt_title': 'Vine by Z3k3',
'upload_date': '20130430',
'uploader': 'Z3k3',
'uploader_id': '936470460173008896',
'view_count': int,
'like_count': int,
'comment_count': int,
'repost_count': int,
},
}, {
'url': 'https://vine.co/oembed/MYxVapFvz2z.json',
'only_matching': True,
}, {
'url': 'https://vine.co/v/e192BnZnZ9V',
'info_dict': {
@ -71,6 +38,7 @@ class VineIE(InfoExtractor):
'ext': 'mp4',
'title': 'ยิ้ม~ เขิน~ อาย~ น่าร้ากอ้ะ >//< @n_whitewo @orlameena #lovesicktheseries #lovesickseason2',
'alt_title': 'Vine by Pimry_zaa',
'timestamp': 1436057405,
'upload_date': '20150705',
'uploader': 'Pimry_zaa',
'uploader_id': '1135760698325307392',
@ -82,43 +50,60 @@ class VineIE(InfoExtractor):
'params': {
'skip_download': True,
},
}, {
'url': 'https://vine.co/v/MYxVapFvz2z',
'only_matching': True,
}, {
'url': 'https://vine.co/v/bxVjBbZlPUH',
'only_matching': True,
}, {
'url': 'https://vine.co/oembed/MYxVapFvz2z.json',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage('https://vine.co/v/' + video_id, video_id)
data = self._parse_json(
self._search_regex(
r'window\.POST_DATA\s*=\s*({.+?});\s*</script>',
webpage, 'vine data'),
video_id)
data = self._download_json(
'https://archive.vine.co/posts/%s.json' % video_id, video_id)
data = data[list(data.keys())[0]]
formats = [{
'format_id': '%(format)s-%(rate)s' % f,
'vcodec': f.get('format'),
'quality': f.get('rate'),
'url': f['videoUrl'],
} for f in data['videoUrls'] if f.get('videoUrl')]
def video_url(kind):
for url_suffix in ('Url', 'URL'):
format_url = data.get('video%s%s' % (kind, url_suffix))
if format_url:
return format_url
formats = []
for quality, format_id in enumerate(('low', '', 'dash')):
format_url = video_url(format_id.capitalize())
if not format_url:
continue
# DASH link returns plain mp4
if format_id == 'dash' and determine_ext(format_url) == 'mpd':
formats.extend(self._extract_mpd_formats(
format_url, video_id, mpd_id='dash', fatal=False))
else:
formats.append({
'url': format_url,
'format_id': format_id or 'standard',
'quality': quality,
})
self._sort_formats(formats)
username = data.get('username')
return {
'id': video_id,
'title': data.get('description') or self._og_search_title(webpage),
'alt_title': 'Vine by %s' % username if username else self._og_search_description(webpage, default=None),
'title': data.get('description'),
'alt_title': 'Vine by %s' % username if username else None,
'thumbnail': data.get('thumbnailUrl'),
'upload_date': unified_strdate(data.get('created')),
'timestamp': unified_timestamp(data.get('created')),
'uploader': username,
'uploader_id': data.get('userIdStr'),
'view_count': int_or_none(data.get('loops', {}).get('count')),
'like_count': int_or_none(data.get('likes', {}).get('count')),
'comment_count': int_or_none(data.get('comments', {}).get('count')),
'repost_count': int_or_none(data.get('reposts', {}).get('count')),
'view_count': int_or_none(data.get('loops')),
'like_count': int_or_none(data.get('likes')),
'comment_count': int_or_none(data.get('comments')),
'repost_count': int_or_none(data.get('reposts')),
'formats': formats,
}

View File

@ -281,6 +281,11 @@ class VKIE(VKBaseIE):
{
'url': 'http://new.vk.com/video205387401_165548505',
'only_matching': True,
},
{
# This video is no longer available, because its author has been blocked.
'url': 'https://vk.com/video-10639516_456240611',
'only_matching': True,
}
]
@ -328,6 +333,12 @@ class VKIE(VKBaseIE):
r'<!>Access denied':
'Access denied to video %s.',
r'<!>Видеозапись недоступна, так как её автор был заблокирован.':
'Video %s is no longer available, because its author has been blocked.',
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.',
}
for error_re, error_msg in ERRORS.items():

View File

@ -329,6 +329,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'},
'256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
'258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
'325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'preference': -50, 'container': 'm4a_dash'},
'328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'preference': -50, 'container': 'm4a_dash'},
# Dash webm
'167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
@ -1028,8 +1030,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def _parse_sig_js(self, jscode):
funcname = self._search_regex(
r'"signature",\s?([a-zA-Z0-9$]+)\(', jscode,
'Initial JS player signature function name')
(r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\('),
jscode, 'Initial JS player signature function name', group='sig')
jsi = JSInterpreter(jscode)
initial_function = jsi.extract_function(funcname)
@ -1050,9 +1054,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if player_url.startswith('//'):
player_url = 'https:' + player_url
elif player_url.startswith('/'):
player_url = 'https://youtube.com' + player_url
elif not re.match(r'https?://', player_url):
player_url = compat_urlparse.urljoin(
'https://www.youtube.com', player_url)
try:
player_id = (player_url, self._signature_cache_id(s))
if player_id not in self._player_cache:
@ -1856,13 +1860,13 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
)
(
(?:PL|LL|EC|UU|FL|RD|UL)?[0-9A-Za-z-_]{10,}
(?:PL|LL|EC|UU|FL|RD|UL|TL)?[0-9A-Za-z-_]{10,}
# Top tracks, they can also include dots
|(?:MC)[\w\.]*
)
.*
|
((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,})
((?:PL|LL|EC|UU|FL|RD|UL|TL)[0-9A-Za-z-_]{10,})
)"""
_TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&disable_polymer=true'
_VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
@ -1984,6 +1988,9 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
}, {
'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
'only_matching': True,
}, {
'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
'only_matching': True,
}]
def _real_initialize(self):
@ -2344,18 +2351,18 @@ class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE):
videos = []
limit = n
url_query = {
'search_query': query.encode('utf-8'),
}
url_query.update(self._EXTRA_QUERY_ARGS)
result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
for pagenum in itertools.count(1):
url_query = {
'search_query': query.encode('utf-8'),
'page': pagenum,
'spf': 'navigate',
}
url_query.update(self._EXTRA_QUERY_ARGS)
result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
data = self._download_json(
result_url, video_id='query "%s"' % query,
note='Downloading page %s' % pagenum,
errnote='Unable to download API page')
errnote='Unable to download API page',
query={'spf': 'navigate'})
html_content = data[1]['body']['content']
if 'class="search-message' in html_content:
@ -2367,6 +2374,12 @@ class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE):
videos += new_videos
if not new_videos or len(videos) > limit:
break
next_link = self._html_search_regex(
r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
html_content, 'next link', default=None)
if next_link is None:
break
result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
if len(videos) > n:
videos = videos[:n]

View File

@ -470,6 +470,10 @@ def parseOpts(overrideArguments=None):
'--playlist-reverse',
action='store_true',
help='Download playlist videos in reverse order')
downloader.add_option(
'--playlist-random',
action='store_true',
help='Download playlist videos in random order')
downloader.add_option(
'--xattr-set-filesize',
dest='xattr_set_filesize', action='store_true',

View File

@ -2103,11 +2103,18 @@ def strip_jsonp(code):
def js_to_json(code):
COMMENT_RE = r'/\*(?:(?!\*/).)*?\*/|//[^\n]*'
SKIP_RE = r'\s*(?:{comment})?\s*'.format(comment=COMMENT_RE)
INTEGER_TABLE = (
(r'(?s)^(0[xX][0-9a-fA-F]+){skip}:?$'.format(skip=SKIP_RE), 16),
(r'(?s)^(0+[0-7]+){skip}:?$'.format(skip=SKIP_RE), 8),
)
def fix_kv(m):
v = m.group(0)
if v in ('true', 'false', 'null'):
return v
elif v.startswith('/*') or v == ',':
elif v.startswith('/*') or v.startswith('//') or v == ',':
return ""
if v[0] in ("'", '"'):
@ -2118,11 +2125,6 @@ def js_to_json(code):
'\\x': '\\u00',
}.get(m.group(0), m.group(0)), v[1:-1])
INTEGER_TABLE = (
(r'^(0[xX][0-9a-fA-F]+)\s*:?$', 16),
(r'^(0+[0-7]+)\s*:?$', 8),
)
for regex, base in INTEGER_TABLE:
im = re.match(regex, v)
if im:
@ -2134,11 +2136,11 @@ def js_to_json(code):
return re.sub(r'''(?sx)
"(?:[^"\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^"\\]*"|
'(?:[^'\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^'\\]*'|
/\*.*?\*/|,(?=\s*[\]}])|
{comment}|,(?={skip}[\]}}])|
[a-zA-Z_][.a-zA-Z_0-9]*|
\b(?:0[xX][0-9a-fA-F]+|0+[0-7]+)(?:\s*:)?|
[0-9]+(?=\s*:)
''', fix_kv, code)
\b(?:0[xX][0-9a-fA-F]+|0+[0-7]+)(?:{skip}:)?|
[0-9]+(?={skip}:)
'''.format(comment=COMMENT_RE, skip=SKIP_RE), fix_kv, code)
def qualities(quality_ids):

View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2017.01.29'
__version__ = '2017.02.07'