3 from __future__ import unicode_literals
8 from .common import InfoExtractor
9 from .youtube import YoutubeIE
10 from ..compat import (
13 compat_xml_parse_error,
31 from .brightcove import BrightcoveIE
32 from .nbc import NBCSportsVPlayerIE
33 from .ooyala import OoyalaIE
34 from .rutv import RUTVIE
35 from .smotri import SmotriIE
36 from .condenast import CondeNastIE
37 from .udn import UDNEmbedIE
38 from .senateisvp import SenateISVPIE
39 from .bliptv import BlipTVIE
42 class GenericIE(InfoExtractor):
43 IE_DESC = 'Generic downloader that works on some sites'
48 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
49 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
51 'id': '13601338388002',
53 'uploader': 'www.hodiho.fr',
54 'title': 'R\u00e9gis plante sa Jeep',
57 # bandcamp page with custom domain
59 'add_ie': ['Bandcamp'],
60 'url': 'http://bronyrock.com/track/the-pony-mash',
64 'title': 'The Pony Mash',
65 'uploader': 'M_Pallante',
67 'skip': 'There is a limit of 200 free downloads / month for the test song',
69 # embedded brightcove video
70 # it also tests brightcove videos that need to set the 'Referer' in the
73 'add_ie': ['Brightcove'],
74 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
76 'id': '2765128793001',
78 'title': 'Le cours de bourse : l’analyse technique',
79 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
80 'uploader': 'BFM BUSINESS',
83 'skip_download': True,
87 # https://github.com/rg3/youtube-dl/issues/2253
88 'url': 'http://bcove.me/i6nfkrc3',
89 'md5': '0ba9446db037002366bab3b3eb30c88c',
91 'id': '3101154703001',
93 'title': 'Still no power',
94 'uploader': 'thestar.com',
95 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
97 'add_ie': ['Brightcove'],
100 'url': 'http://www.championat.com/video/football/v/87/87499.html',
101 'md5': 'fb973ecf6e4a78a67453647444222983',
103 'id': '3414141473001',
105 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
106 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
107 'uploader': 'Championat',
111 # https://github.com/rg3/youtube-dl/issues/3541
112 'add_ie': ['Brightcove'],
113 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
115 'id': '3866516442001',
117 'title': 'Leer mij vrouwen kennen: Aflevering 1',
118 'description': 'Leer mij vrouwen kennen: Aflevering 1',
119 'uploader': 'SBS Broadcasting',
121 'skip': 'Restricted to Netherlands',
123 'skip_download': True, # m3u8 download
126 # Direct link to a video
128 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
129 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
134 'upload_date': '20100513',
139 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
140 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
142 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
144 'title': '2cc213299525360.mov', # that's what we get
146 'add_ie': ['Ooyala'],
148 # multiple ooyala embeds on SBN network websites
150 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
152 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
153 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
155 'playlist_mincount': 3,
157 'skip_download': True,
159 'add_ie': ['Ooyala'],
163 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
167 'upload_date': '20130224',
168 'uploader_id': 'TheVerge',
169 'description': 're:^Chris Ziegler takes a look at the\.*',
170 'uploader': 'The Verge',
171 'title': 'First Firefox OS phones side-by-side',
174 'skip_download': False,
179 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
183 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
184 'upload_date': '20140225',
185 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
186 'uploader': 'Tested',
187 'uploader_id': 'testedcom',
189 # No need to test YoutubeIE here
191 'skip_download': True,
196 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
200 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
201 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
206 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER',
208 'title': 'BBC - Blogs - Adam Curtis - BUGGER',
210 'playlist_mincount': 18,
214 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
218 'title': 'Охотское море стало целиком российским',
219 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
223 'skip_download': True,
228 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
229 'md5': '65fdff94098e4a607385a60c5177c638',
233 'title': 'Hidden miracles of the natural world',
234 'uploader': 'Louie Schwartzberg',
235 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
238 # Embeded Ustream video
240 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
241 'md5': '27b99cdb639c9b12a79bca876a073417',
245 'uploader': 'AU SPA: The NSA and Privacy',
246 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
249 # nowvideo embed hidden behind percent encoding
251 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
252 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
254 'id': '06e53103ca9aa',
256 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
257 'description': 'No description',
262 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
263 'md5': '7653032cbb25bf6c80d80f217055fa43',
265 'id': '048195-004_PLUS7-F',
268 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
269 'upload_date': '20140320',
272 'skip_download': 'Requires rtmpdump'
277 'url': 'http://www.wired.com/2014/04/honda-asimo/',
278 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
280 'id': '53501be369702d3275860000',
282 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
287 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
288 'md5': '441aeeb82eb72c422c7f14ec533999cd',
290 'id': 'k2mm4bCdJ6CQ2i7c8o2',
292 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
295 'add_ie': ['Dailymotion'],
299 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
303 'title': 'The NBL Auction 2014',
304 'uploader': 'BADMINTON England',
305 'uploader_id': 'BADMINTONEvents',
306 'upload_date': '20140603',
307 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
309 'add_ie': ['Youtube'],
311 'skip_download': True,
316 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
317 'md5': '35727f82f58c76d996fc188f9755b0d5',
319 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
322 'description': 'Mario\'s life in the fast lane has never looked so good.',
325 # YouTube embed via <data-embed-url="">
327 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
331 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
332 'uploader': 'Gameloft',
333 'uploader_id': 'gameloft',
334 'upload_date': '20140828',
335 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
338 'skip_download': True,
343 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
345 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
347 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
348 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
353 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
355 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
356 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
362 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
367 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
368 'md5': '9d65602bf31c6e20014319c7d07fba27',
370 'id': '5123ea6d5e5a7',
373 'uploader': 'www.handjobhub.com',
374 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
379 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
381 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
382 'title': 'Zero Punctuation',
383 'description': 're:.*groundbreaking video review series.*'
385 'playlist_mincount': 11,
387 # Multiple brightcove videos
388 # https://github.com/rg3/youtube-dl/issues/2283
390 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
392 'id': 'always-never',
393 'title': 'Always / Never - The New Yorker',
397 'extract_flat': False,
398 'skip_download': True,
403 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
404 'md5': '96f09a37e44da40dd083e12d9a683327',
408 'title': 'Ump changes call to ball',
409 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
411 'timestamp': 1401537900,
412 'upload_date': '20140531',
413 'thumbnail': 're:^https?://.*\.jpg$',
418 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
419 'md5': '8788b683c777a5cf25621eaf286d0c23',
423 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
425 'filesize': 182808282,
426 'uploader': 'education-portal.com',
430 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
431 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
435 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
437 'uploader': 'thoughtworks.wistia.com',
440 # Direct download with broken HEAD
442 'url': 'http://ai-radio.org:8000/radio.opus',
449 'skip_download': True, # infinite live stream
451 'expected_warnings': [
452 r'501.*Not Implemented'
457 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
461 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
462 'uploader': 'Sophos Security',
463 'title': 'Chet Chat 171 - Oct 29, 2014',
464 'upload_date': '20141029',
469 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
473 'upload_date': '20141112',
474 'title': 'Rosetta #CometLanding webcast HL 10',
479 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
482 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
484 'playlist_mincount': 2,
486 # Direct link with incorrect MIME type
488 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
489 'md5': '4ccbebe5f36706d85221f204d7eb5913',
491 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
492 'id': '5_Lennart_Poettering_-_Systemd',
494 'title': '5_Lennart_Poettering_-_Systemd',
495 'upload_date': '20141120',
497 'expected_warnings': [
498 'URL could be a direct video link, returning it as such.'
503 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
507 'upload_date': '20141126',
508 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
513 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
515 'id': '730m_DandD_1901_512k',
517 'uploader': 'www.abc.net.au',
518 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
521 # embedded viddler video
523 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
527 'uploader': 'deadspin',
528 'title': 'WALL-TO-GORTAT',
529 'timestamp': 1422285291,
530 'upload_date': '20150126',
532 'add_ie': ['Viddler'],
536 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
540 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
541 'description': 'md5:601cb790edd05908957dae8aaa866465',
542 'upload_date': '20150220',
547 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
551 'upload_date': '20150212',
552 'uploader': 'The National Archives UK',
553 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
554 'uploader_id': 'NationalArchives08',
555 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
560 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
561 'playlist_mincount': 5,
563 'id': 'aanslagen-kopenhagen',
564 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
569 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
573 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
578 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
582 'upload_date': '20150226',
583 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
585 'title': 'John Carlson Postgame 2/25/15',
588 # Eagle.Platform embed (generic URL)
590 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
594 'title': 'Навальный вышел на свободу',
595 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
596 'thumbnail': 're:^https?://.*\.jpg$',
602 # ClipYou (Eagle.Platform) embed (custom URL)
604 'url': 'http://muz-tv.ru/play/7129/',
608 'title': "'O Sole Mio",
609 'thumbnail': 're:^https?://.*\.jpg$',
616 'url': 'http://muz-tv.ru/kinozal/view/7400/',
620 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
621 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
622 'thumbnail': 're:^https?://.*\.jpg$',
629 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
633 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
634 'thumbnail': 're:^https?://.*\.png$',
640 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
641 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
645 'title': 'Facebook Creates "On This Day" | Crunch Report',
648 # RSS feed with enclosure
650 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
652 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
654 'upload_date': '20150228',
655 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
658 # Crooks and Liars embed
660 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
664 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
665 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
666 'timestamp': 1428207000,
667 'upload_date': '20150405',
668 'uploader': 'Heather',
671 # Crooks and Liars external embed
673 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
675 'id': 'MTE3MjUtMzQ2MzA',
677 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
678 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
679 'timestamp': 1265032391,
680 'upload_date': '20100201',
681 'uploader': 'Heather',
684 # NBC Sports vplayer embed
686 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
688 'id': 'ln7x1qSThw4k',
690 'title': "PFT Live: New leader in the 'new-look' defense",
691 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
696 'url': 'http://www.udn.com/news/story/7314/822787',
697 'md5': 'fd2060e988c326991037b9aff9df21a6',
701 'title': '中一中男師變性 全校師生力挺',
702 'thumbnail': 're:^https?://.*\.jpg$',
707 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
709 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
711 'description': 'VIDEO: Index/Match versus VLOOKUP.',
712 'title': 'This is what separates the Excel masters from the wannabes',
716 'skip_download': True,
719 # Contains a SMIL manifest
721 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
725 'title': '+ Football: Lottery Champions League Europe',
726 'uploader': 'www.telewebion.com',
730 'skip_download': True,
735 def report_following_redirect(self, new_url):
736 """Report information extraction."""
737 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
739 def _extract_rss(self, url, video_id, doc):
740 playlist_title = doc.find('./channel/title').text
741 playlist_desc_el = doc.find('./channel/description')
742 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
745 for it in doc.findall('./channel/item'):
746 next_url = xpath_text(it, 'link', fatal=False)
748 enclosure_nodes = it.findall('./enclosure')
749 for e in enclosure_nodes:
750 next_url = e.attrib.get('url')
760 'title': it.find('title').text,
766 'title': playlist_title,
767 'description': playlist_desc,
771 def _extract_camtasia(self, url, video_id, webpage):
772 """ Returns None if no camtasia video can be found. """
774 camtasia_cfg = self._search_regex(
775 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
776 webpage, 'camtasia configuration file', default=None)
777 if camtasia_cfg is None:
780 title = self._html_search_meta('DC.title', webpage, fatal=True)
782 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
783 camtasia_cfg = self._download_xml(
784 camtasia_url, video_id,
785 note='Downloading camtasia configuration',
786 errnote='Failed to download camtasia configuration')
787 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
790 for n in fileset_node.getchildren():
791 url_n = n.find('./uri')
796 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
797 'title': '%s - %s' % (title, n.tag),
798 'url': compat_urlparse.urljoin(url, url_n.text),
799 'duration': float_or_none(n.find('./duration').text),
808 def _real_extract(self, url):
809 if url.startswith('//'):
812 'url': self.http_scheme() + url,
815 parsed_url = compat_urlparse.urlparse(url)
816 if not parsed_url.scheme:
817 default_search = self._downloader.params.get('default_search')
818 if default_search is None:
819 default_search = 'fixup_error'
821 if default_search in ('auto', 'auto_warning', 'fixup_error'):
823 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
824 return self.url_result('http://' + url)
825 elif default_search != 'fixup_error':
826 if default_search == 'auto_warning':
827 if re.match(r'^(?:url|URL)$', url):
828 raise ExtractorError(
829 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
832 self._downloader.report_warning(
833 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
834 return self.url_result('ytsearch:' + url)
836 if default_search in ('error', 'fixup_error'):
837 raise ExtractorError(
838 '%r is not a valid URL. '
839 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
840 % (url, url), expected=True)
842 if ':' not in default_search:
843 default_search += ':'
844 return self.url_result(default_search + url)
846 url, smuggled_data = unsmuggle_url(url)
848 is_intentional = smuggled_data and smuggled_data.get('to_generic')
849 if smuggled_data and 'force_videoid' in smuggled_data:
850 force_videoid = smuggled_data['force_videoid']
851 video_id = force_videoid
853 video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0]
855 self.to_screen('%s: Requesting header' % video_id)
857 head_req = HEADRequest(url)
858 head_response = self._request_webpage(
860 note=False, errnote='Could not send HEAD request to %s' % url,
863 if head_response is not False:
865 new_url = head_response.geturl()
867 self.report_following_redirect(new_url)
869 new_url = smuggle_url(
870 new_url, {'force_videoid': force_videoid})
871 return self.url_result(new_url)
874 if head_response is False:
875 full_response = self._request_webpage(url, video_id)
876 head_response = full_response
878 # Check for direct link to a video
879 content_type = head_response.headers.get('Content-Type', '')
880 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
882 upload_date = unified_strdate(
883 head_response.headers.get('Last-Modified'))
886 'title': os.path.splitext(url_basename(url))[0],
889 'format_id': m.group('format_id'),
891 'vcodec': 'none' if m.group('type') == 'audio' else None
893 'upload_date': upload_date,
896 if not self._downloader.params.get('test', False) and not is_intentional:
897 self._downloader.report_warning('Falling back on generic information extractor.')
899 if not full_response:
900 full_response = self._request_webpage(url, video_id)
902 # Maybe it's a direct link to a video?
903 # Be careful not to download the whole thing!
904 first_bytes = full_response.read(512)
905 if not is_html(first_bytes):
906 self._downloader.report_warning(
907 'URL could be a direct video link, returning it as such.')
908 upload_date = unified_strdate(
909 head_response.headers.get('Last-Modified'))
912 'title': os.path.splitext(url_basename(url))[0],
915 'upload_date': upload_date,
918 webpage = self._webpage_read_content(
919 full_response, url, video_id, prefix=first_bytes)
921 self.report_extraction(video_id)
925 doc = parse_xml(webpage)
927 return self._extract_rss(url, video_id, doc)
928 except compat_xml_parse_error:
931 # Is it a Camtasia project?
932 camtasia_res = self._extract_camtasia(url, video_id, webpage)
933 if camtasia_res is not None:
936 # Sometimes embedded video player is hidden behind percent encoding
937 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
938 # Unescaping the whole page allows to handle those cases in a generic way
939 webpage = compat_urllib_parse.unquote(webpage)
941 # it's tempting to parse this further, but you would
942 # have to take into account all the variations like
943 # Video Title - Site Name
944 # Site Name | Video Title
945 # Video Title - Tagline | Site Name
946 # and so on and so forth; it's just not practical
947 video_title = self._html_search_regex(
948 r'(?s)<title>(.*?)</title>', webpage, 'video title',
951 # Try to detect age limit automatically
952 age_limit = self._rta_search(webpage)
953 # And then there are the jokers who advertise that they use RTA,
954 # but actually don't.
955 AGE_LIMIT_MARKERS = [
956 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
958 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
961 # video uploader is domain name
962 video_uploader = self._search_regex(
963 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
966 def _playlist_from_matches(matches, getter=None, ie=None):
968 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
970 return self.playlist_result(
971 urlrs, playlist_id=video_id, playlist_title=video_title)
973 # Look for BrightCove:
974 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
976 self.to_screen('Brightcove video detected.')
979 'url': smuggle_url(bc_url, {'Referer': url}),
980 'ie_key': 'Brightcove'
981 } for bc_url in bc_urls]
985 'title': video_title,
990 # Look for embedded rtl.nl player
991 matches = re.findall(
992 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+video_embed[^"]+)"',
995 return _playlist_from_matches(matches, ie='RtlNl')
997 # Look for embedded (iframe) Vimeo player
999 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
1001 player_url = unescapeHTML(mobj.group('url'))
1002 surl = smuggle_url(player_url, {'Referer': url})
1003 return self.url_result(surl)
1004 # Look for embedded (swf embed) Vimeo player
1006 r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
1008 return self.url_result(mobj.group(1))
1010 # Look for embedded YouTube player
1011 matches = re.findall(r'''(?x)
1020 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1024 return _playlist_from_matches(
1025 matches, lambda m: unescapeHTML(m[1]))
1027 # Look for lazyYT YouTube embed
1028 matches = re.findall(
1029 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1031 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1033 # Look for embedded Dailymotion player
1034 matches = re.findall(
1035 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1037 return _playlist_from_matches(
1038 matches, lambda m: unescapeHTML(m[1]))
1040 # Look for embedded Dailymotion playlist player (#3822)
1042 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1044 playlists = re.findall(
1045 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1047 return _playlist_from_matches(
1048 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1050 # Look for embedded Wistia player
1052 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1054 embed_url = self._proto_relative_url(
1055 unescapeHTML(match.group('url')))
1057 '_type': 'url_transparent',
1060 'uploader': video_uploader,
1061 'title': video_title,
1065 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1068 '_type': 'url_transparent',
1069 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1071 'uploader': video_uploader,
1072 'title': video_title,
1073 'id': match.group('id')
1076 # Look for embedded blip.tv player
1077 bliptv_url = BlipTVIE._extract_url(webpage)
1079 return self.url_result(bliptv_url, 'BlipTV')
1081 # Look for embedded condenast player
1082 matches = re.findall(
1083 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1087 '_type': 'playlist',
1090 'ie_key': 'CondeNast',
1092 } for ma in matches],
1093 'title': video_title,
1097 # Look for Bandcamp pages with custom domain
1098 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1099 if mobj is not None:
1100 burl = unescapeHTML(mobj.group(1))
1101 # Don't set the extractor because it can be a track url or an album
1102 return self.url_result(burl)
1104 # Look for embedded Vevo player
1106 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1107 if mobj is not None:
1108 return self.url_result(mobj.group('url'))
1110 # Look for embedded Viddler player
1112 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1114 if mobj is not None:
1115 return self.url_result(mobj.group('url'))
1117 # Look for NYTimes player
1119 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1121 if mobj is not None:
1122 return self.url_result(mobj.group('url'))
1124 # Look for Libsyn player
1126 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1127 if mobj is not None:
1128 return self.url_result(mobj.group('url'))
1130 # Look for Ooyala videos
1131 mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1132 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1133 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1134 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1135 if mobj is not None:
1136 return OoyalaIE._build_url_result(mobj.group('ec'))
1138 # Look for multiple Ooyala embeds on SBN network websites
1139 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1140 if mobj is not None:
1141 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1143 return _playlist_from_matches(
1144 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1146 # Look for Aparat videos
1147 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1148 if mobj is not None:
1149 return self.url_result(mobj.group(1), 'Aparat')
1151 # Look for MPORA videos
1152 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1153 if mobj is not None:
1154 return self.url_result(mobj.group(1), 'Mpora')
1156 # Look for embedded NovaMov-based player
1158 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1159 (?P<url>http://(?:(?:embed|www)\.)?
1161 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1162 videoweed\.(?:es|com)|
1163 movshare\.(?:net|sx|ag)|
1164 divxstage\.(?:eu|net|ch|co|at|ag))
1165 /embed\.php.+?)\1''', webpage)
1166 if mobj is not None:
1167 return self.url_result(mobj.group('url'))
1169 # Look for embedded Facebook player
1171 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1172 if mobj is not None:
1173 return self.url_result(mobj.group('url'), 'Facebook')
1175 # Look for embedded VK player
1176 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1177 if mobj is not None:
1178 return self.url_result(mobj.group('url'), 'VK')
1180 # Look for embedded ivi player
1181 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1182 if mobj is not None:
1183 return self.url_result(mobj.group('url'), 'Ivi')
1185 # Look for embedded Huffington Post player
1187 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1188 if mobj is not None:
1189 return self.url_result(mobj.group('url'), 'HuffPost')
1192 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1193 if mobj is not None:
1194 return self.url_result(mobj.group('url'))
1195 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1196 if mobj is not None:
1197 return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
1199 # Look for funnyordie embed
1200 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1202 return _playlist_from_matches(
1203 matches, getter=unescapeHTML, ie='FunnyOrDie')
1205 # Look for BBC iPlayer embed
1206 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1208 return _playlist_from_matches(matches, ie='BBCCoUk')
1210 # Look for embedded RUTV player
1211 rutv_url = RUTVIE._extract_url(webpage)
1213 return self.url_result(rutv_url, 'RUTV')
1215 # Look for embedded TED player
1217 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1218 if mobj is not None:
1219 return self.url_result(mobj.group('url'), 'TED')
1221 # Look for embedded Ustream videos
1223 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1224 if mobj is not None:
1225 return self.url_result(mobj.group('url'), 'Ustream')
1227 # Look for embedded arte.tv player
1229 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1231 if mobj is not None:
1232 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1234 # Look for embedded smotri.com player
1235 smotri_url = SmotriIE._extract_url(webpage)
1237 return self.url_result(smotri_url, 'Smotri')
1239 # Look for embeded soundcloud player
1241 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1243 if mobj is not None:
1244 url = unescapeHTML(mobj.group('url'))
1245 return self.url_result(url)
1247 # Look for embedded vulture.com player
1249 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1251 if mobj is not None:
1252 url = unescapeHTML(mobj.group('url'))
1253 return self.url_result(url, ie='Vulture')
1255 # Look for embedded mtvservices player
1257 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1259 if mobj is not None:
1260 url = unescapeHTML(mobj.group('url'))
1261 return self.url_result(url, ie='MTVServicesEmbedded')
1263 # Look for embedded yahoo player
1265 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1267 if mobj is not None:
1268 return self.url_result(mobj.group('url'), 'Yahoo')
1270 # Look for embedded sbs.com.au player
1274 <meta\s+property="og:video"\s+content=|
1277 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1279 if mobj is not None:
1280 return self.url_result(mobj.group('url'), 'SBS')
1282 # Look for embedded Cinchcast player
1284 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1286 if mobj is not None:
1287 return self.url_result(mobj.group('url'), 'Cinchcast')
1290 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1292 if mobj is not None:
1293 return self.url_result(mobj.group('url'), 'MLB')
1296 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1298 if mobj is not None:
1299 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1302 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1304 if mobj is not None:
1305 return self.url_result(mobj.group('url'), 'Livestream')
1307 # Look for Zapiks embed
1309 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1310 if mobj is not None:
1311 return self.url_result(mobj.group('url'), 'Zapiks')
1313 # Look for Kaltura embeds
1315 r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage)
1316 if mobj is not None:
1317 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1319 # Look for Eagle.Platform embeds
1321 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1322 if mobj is not None:
1323 return self.url_result(mobj.group('url'), 'EaglePlatform')
1325 # Look for ClipYou (uses Eagle.Platform) embeds
1327 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1328 if mobj is not None:
1329 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1331 # Look for Pladform embeds
1333 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1334 if mobj is not None:
1335 return self.url_result(mobj.group('url'), 'Pladform')
1337 # Look for Playwire embeds
1339 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1340 if mobj is not None:
1341 return self.url_result(mobj.group('url'))
1343 # Look for 5min embeds
1345 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1346 if mobj is not None:
1347 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1349 # Look for Crooks and Liars embeds
1351 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1352 if mobj is not None:
1353 return self.url_result(mobj.group('url'))
1355 # Look for NBC Sports VPlayer embeds
1356 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1358 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1360 # Look for UDN embeds
1362 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1363 if mobj is not None:
1364 return self.url_result(
1365 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1367 # Look for Senate ISVP iframe
1368 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1370 return self.url_result(surl, 'SenateISVP')
1372 def check_video(vurl):
1373 if YoutubeIE.suitable(vurl):
1375 vpath = compat_urlparse.urlparse(vurl).path
1376 vext = determine_ext(vpath)
1377 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1379 def filter_video(urls):
1380 return list(filter(check_video, urls))
1382 # Start with something easy: JW Player in SWFObject
1383 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1385 # Look for gorilla-vid style embedding
1386 found = filter_video(re.findall(r'''(?sx)
1390 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1393 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1395 # Broaden the search a little bit
1396 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1398 # Broaden the findall a little bit: JWPlayer JS loader
1399 found = filter_video(re.findall(
1400 r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1403 found = filter_video(re.findall(r'''(?xs)
1404 flowplayer\("[^"]+",\s*
1406 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1407 ["']?url["']?\s*:\s*["']([^"']+)["']
1412 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1414 # Try to find twitter cards info
1415 found = filter_video(re.findall(
1416 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1418 # We look for Open Graph info:
1419 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1420 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1421 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1422 if m_video_type is not None:
1423 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1426 found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1428 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1430 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1431 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1434 # Look also in Refresh HTTP header
1435 refresh_header = head_response.headers.get('Refresh')
1437 found = re.search(REDIRECT_REGEX, refresh_header)
1439 new_url = found.group(1)
1440 self.report_following_redirect(new_url)
1446 raise UnsupportedError(url)
1449 for video_url in found:
1450 video_url = compat_urlparse.urljoin(url, video_url)
1451 video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
1453 # Sometimes, jwplayer extraction will result in a YouTube URL
1454 if YoutubeIE.suitable(video_url):
1455 entries.append(self.url_result(video_url, 'Youtube'))
1458 # here's a fun little line of code for you:
1459 video_id = os.path.splitext(video_id)[0]
1461 if determine_ext(video_url) == 'smil':
1464 'formats': self._extract_smil_formats(video_url, video_id),
1465 'uploader': video_uploader,
1466 'title': video_title,
1467 'age_limit': age_limit,
1473 'uploader': video_uploader,
1474 'title': video_title,
1475 'age_limit': age_limit,
1478 if len(entries) == 1:
1481 for num, e in enumerate(entries, start=1):
1482 # 'url' results don't have a title
1483 if e.get('title') is not None:
1484 e['title'] = '%s (%d)' % (e['title'], num)
1486 '_type': 'playlist',