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
41 class GenericIE(InfoExtractor):
42 IE_DESC = 'Generic downloader that works on some sites'
47 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
48 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
50 'id': '13601338388002',
52 'uploader': 'www.hodiho.fr',
53 'title': 'R\u00e9gis plante sa Jeep',
56 # bandcamp page with custom domain
58 'add_ie': ['Bandcamp'],
59 'url': 'http://bronyrock.com/track/the-pony-mash',
63 'title': 'The Pony Mash',
64 'uploader': 'M_Pallante',
66 'skip': 'There is a limit of 200 free downloads / month for the test song',
68 # embedded brightcove video
69 # it also tests brightcove videos that need to set the 'Referer' in the
72 'add_ie': ['Brightcove'],
73 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
75 'id': '2765128793001',
77 'title': 'Le cours de bourse : l’analyse technique',
78 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
79 'uploader': 'BFM BUSINESS',
82 'skip_download': True,
86 # https://github.com/rg3/youtube-dl/issues/2253
87 'url': 'http://bcove.me/i6nfkrc3',
88 'md5': '0ba9446db037002366bab3b3eb30c88c',
90 'id': '3101154703001',
92 'title': 'Still no power',
93 'uploader': 'thestar.com',
94 '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.',
96 'add_ie': ['Brightcove'],
99 'url': 'http://www.championat.com/video/football/v/87/87499.html',
100 'md5': 'fb973ecf6e4a78a67453647444222983',
102 'id': '3414141473001',
104 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
105 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
106 'uploader': 'Championat',
110 # https://github.com/rg3/youtube-dl/issues/3541
111 'add_ie': ['Brightcove'],
112 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
114 'id': '3866516442001',
116 'title': 'Leer mij vrouwen kennen: Aflevering 1',
117 'description': 'Leer mij vrouwen kennen: Aflevering 1',
118 'uploader': 'SBS Broadcasting',
120 'skip': 'Restricted to Netherlands',
122 'skip_download': True, # m3u8 download
125 # Direct link to a video
127 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
128 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
133 'upload_date': '20100513',
138 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
139 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
141 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
143 'title': '2cc213299525360.mov', # that's what we get
145 'add_ie': ['Ooyala'],
147 # multiple ooyala embeds on SBN network websites
149 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
151 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
152 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
154 'playlist_mincount': 3,
156 'skip_download': True,
158 'add_ie': ['Ooyala'],
162 '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',
166 'upload_date': '20130224',
167 'uploader_id': 'TheVerge',
168 'description': 're:^Chris Ziegler takes a look at the\.*',
169 'uploader': 'The Verge',
170 'title': 'First Firefox OS phones side-by-side',
173 'skip_download': False,
178 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
182 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
183 'upload_date': '20140225',
184 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
185 'uploader': 'Tested',
186 'uploader_id': 'testedcom',
188 # No need to test YoutubeIE here
190 'skip_download': True,
195 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
199 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
200 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
205 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER',
207 'title': 'BBC - Blogs - Adam Curtis - BUGGER',
209 'playlist_mincount': 18,
213 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
217 'title': 'Охотское море стало целиком российским',
218 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
222 'skip_download': True,
227 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
228 'md5': '65fdff94098e4a607385a60c5177c638',
232 'title': 'Hidden miracles of the natural world',
233 'uploader': 'Louie Schwartzberg',
234 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
237 # Embeded Ustream video
239 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
240 'md5': '27b99cdb639c9b12a79bca876a073417',
244 'uploader': 'AU SPA: The NSA and Privacy',
245 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
248 # nowvideo embed hidden behind percent encoding
250 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
251 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
253 'id': '06e53103ca9aa',
255 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
256 'description': 'No description',
261 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
262 'md5': '7653032cbb25bf6c80d80f217055fa43',
264 'id': '048195-004_PLUS7-F',
267 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
268 'upload_date': '20140320',
271 'skip_download': 'Requires rtmpdump'
276 'url': 'http://www.wired.com/2014/04/honda-asimo/',
277 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
279 'id': '53501be369702d3275860000',
281 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
286 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
287 'md5': '441aeeb82eb72c422c7f14ec533999cd',
289 'id': 'k2mm4bCdJ6CQ2i7c8o2',
291 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
294 'add_ie': ['Dailymotion'],
298 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
302 'title': 'The NBL Auction 2014',
303 'uploader': 'BADMINTON England',
304 'uploader_id': 'BADMINTONEvents',
305 'upload_date': '20140603',
306 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
308 'add_ie': ['Youtube'],
310 'skip_download': True,
315 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
316 'md5': '35727f82f58c76d996fc188f9755b0d5',
318 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
321 'description': 'Mario\'s life in the fast lane has never looked so good.',
324 # YouTube embed via <data-embed-url="">
326 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
330 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
331 'uploader': 'Gameloft',
332 'uploader_id': 'gameloft',
333 'upload_date': '20140828',
334 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
337 'skip_download': True,
342 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
344 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
346 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
347 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
352 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
354 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
355 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
361 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
366 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
367 'md5': '9d65602bf31c6e20014319c7d07fba27',
369 'id': '5123ea6d5e5a7',
372 'uploader': 'www.handjobhub.com',
373 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
378 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
380 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
381 'title': 'Zero Punctuation',
382 'description': 're:.*groundbreaking video review series.*'
384 'playlist_mincount': 11,
386 # Multiple brightcove videos
387 # https://github.com/rg3/youtube-dl/issues/2283
389 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
391 'id': 'always-never',
392 'title': 'Always / Never - The New Yorker',
396 'extract_flat': False,
397 'skip_download': True,
402 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
403 'md5': '96f09a37e44da40dd083e12d9a683327',
407 'title': 'Ump changes call to ball',
408 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
410 'timestamp': 1401537900,
411 'upload_date': '20140531',
412 'thumbnail': 're:^https?://.*\.jpg$',
417 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
418 'md5': '8788b683c777a5cf25621eaf286d0c23',
422 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
424 'filesize': 182808282,
425 'uploader': 'education-portal.com',
429 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
430 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
434 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
436 'uploader': 'thoughtworks.wistia.com',
439 # Direct download with broken HEAD
441 'url': 'http://ai-radio.org:8000/radio.opus',
448 'skip_download': True, # infinite live stream
450 'expected_warnings': [
451 r'501.*Not Implemented'
456 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
460 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
461 'uploader': 'Sophos Security',
462 'title': 'Chet Chat 171 - Oct 29, 2014',
463 'upload_date': '20141029',
468 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
472 'upload_date': '20141112',
473 'title': 'Rosetta #CometLanding webcast HL 10',
478 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
481 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
483 'playlist_mincount': 2,
485 # Direct link with incorrect MIME type
487 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
488 'md5': '4ccbebe5f36706d85221f204d7eb5913',
490 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
491 'id': '5_Lennart_Poettering_-_Systemd',
493 'title': '5_Lennart_Poettering_-_Systemd',
494 'upload_date': '20141120',
496 'expected_warnings': [
497 'URL could be a direct video link, returning it as such.'
502 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
506 'upload_date': '20141126',
507 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
512 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
514 'id': '730m_DandD_1901_512k',
516 'uploader': 'www.abc.net.au',
517 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
520 # embedded viddler video
522 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
526 'uploader': 'deadspin',
527 'title': 'WALL-TO-GORTAT',
528 'timestamp': 1422285291,
529 'upload_date': '20150126',
531 'add_ie': ['Viddler'],
535 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
539 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
540 'description': 'md5:601cb790edd05908957dae8aaa866465',
541 'upload_date': '20150220',
546 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
550 'upload_date': '20150212',
551 'uploader': 'The National Archives UK',
552 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
553 'uploader_id': 'NationalArchives08',
554 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
559 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
560 'playlist_mincount': 5,
562 'id': 'aanslagen-kopenhagen',
563 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
568 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
572 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
577 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
581 'upload_date': '20150226',
582 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
584 'title': 'John Carlson Postgame 2/25/15',
587 # Eagle.Platform embed (generic URL)
589 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
593 'title': 'Навальный вышел на свободу',
594 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
595 'thumbnail': 're:^https?://.*\.jpg$',
601 # ClipYou (Eagle.Platform) embed (custom URL)
603 'url': 'http://muz-tv.ru/play/7129/',
607 'title': "'O Sole Mio",
608 'thumbnail': 're:^https?://.*\.jpg$',
615 'url': 'http://muz-tv.ru/kinozal/view/7400/',
619 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
620 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
621 'thumbnail': 're:^https?://.*\.jpg$',
628 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
632 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
633 'thumbnail': 're:^https?://.*\.png$',
639 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
640 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
644 'title': 'Facebook Creates "On This Day" | Crunch Report',
647 # RSS feed with enclosure
649 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
651 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
653 'upload_date': '20150228',
654 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
657 # Crooks and Liars embed
659 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
663 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
664 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
665 'timestamp': 1428207000,
666 'upload_date': '20150405',
667 'uploader': 'Heather',
670 # Crooks and Liars external embed
672 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
674 'id': 'MTE3MjUtMzQ2MzA',
676 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
677 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
678 'timestamp': 1265032391,
679 'upload_date': '20100201',
680 'uploader': 'Heather',
683 # NBC Sports vplayer embed
685 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
687 'id': 'ln7x1qSThw4k',
689 'title': "PFT Live: New leader in the 'new-look' defense",
690 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
695 'url': 'http://www.udn.com/news/story/7314/822787',
696 'md5': 'fd2060e988c326991037b9aff9df21a6',
700 'title': '中一中男師變性 全校師生力挺',
701 'thumbnail': 're:^https?://.*\.jpg$',
706 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
708 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
710 'description': 'VIDEO: Index/Match versus VLOOKUP.',
711 'title': 'This is what separates the Excel masters from the wannabes',
715 'skip_download': True,
718 # Contains a SMIL manifest
720 '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',
724 'title': '+ Football: Lottery Champions League Europe',
725 'uploader': 'www.telewebion.com',
729 'skip_download': True,
734 def report_following_redirect(self, new_url):
735 """Report information extraction."""
736 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
738 def _extract_rss(self, url, video_id, doc):
739 playlist_title = doc.find('./channel/title').text
740 playlist_desc_el = doc.find('./channel/description')
741 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
744 for it in doc.findall('./channel/item'):
745 next_url = xpath_text(it, 'link', fatal=False)
747 enclosure_nodes = it.findall('./enclosure')
748 for e in enclosure_nodes:
749 next_url = e.attrib.get('url')
759 'title': it.find('title').text,
765 'title': playlist_title,
766 'description': playlist_desc,
770 def _extract_camtasia(self, url, video_id, webpage):
771 """ Returns None if no camtasia video can be found. """
773 camtasia_cfg = self._search_regex(
774 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
775 webpage, 'camtasia configuration file', default=None)
776 if camtasia_cfg is None:
779 title = self._html_search_meta('DC.title', webpage, fatal=True)
781 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
782 camtasia_cfg = self._download_xml(
783 camtasia_url, video_id,
784 note='Downloading camtasia configuration',
785 errnote='Failed to download camtasia configuration')
786 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
789 for n in fileset_node.getchildren():
790 url_n = n.find('./uri')
795 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
796 'title': '%s - %s' % (title, n.tag),
797 'url': compat_urlparse.urljoin(url, url_n.text),
798 'duration': float_or_none(n.find('./duration').text),
807 def _real_extract(self, url):
808 if url.startswith('//'):
811 'url': self.http_scheme() + url,
814 parsed_url = compat_urlparse.urlparse(url)
815 if not parsed_url.scheme:
816 default_search = self._downloader.params.get('default_search')
817 if default_search is None:
818 default_search = 'fixup_error'
820 if default_search in ('auto', 'auto_warning', 'fixup_error'):
822 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
823 return self.url_result('http://' + url)
824 elif default_search != 'fixup_error':
825 if default_search == 'auto_warning':
826 if re.match(r'^(?:url|URL)$', url):
827 raise ExtractorError(
828 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
831 self._downloader.report_warning(
832 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
833 return self.url_result('ytsearch:' + url)
835 if default_search in ('error', 'fixup_error'):
836 raise ExtractorError(
837 '%r is not a valid URL. '
838 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
839 % (url, url), expected=True)
841 if ':' not in default_search:
842 default_search += ':'
843 return self.url_result(default_search + url)
845 url, smuggled_data = unsmuggle_url(url)
847 is_intentional = smuggled_data and smuggled_data.get('to_generic')
848 if smuggled_data and 'force_videoid' in smuggled_data:
849 force_videoid = smuggled_data['force_videoid']
850 video_id = force_videoid
852 video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0]
854 self.to_screen('%s: Requesting header' % video_id)
856 head_req = HEADRequest(url)
857 head_response = self._request_webpage(
859 note=False, errnote='Could not send HEAD request to %s' % url,
862 if head_response is not False:
864 new_url = head_response.geturl()
866 self.report_following_redirect(new_url)
868 new_url = smuggle_url(
869 new_url, {'force_videoid': force_videoid})
870 return self.url_result(new_url)
873 if head_response is False:
874 full_response = self._request_webpage(url, video_id)
875 head_response = full_response
877 # Check for direct link to a video
878 content_type = head_response.headers.get('Content-Type', '')
879 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
881 upload_date = unified_strdate(
882 head_response.headers.get('Last-Modified'))
885 'title': os.path.splitext(url_basename(url))[0],
888 'format_id': m.group('format_id'),
890 'vcodec': 'none' if m.group('type') == 'audio' else None
892 'upload_date': upload_date,
895 if not self._downloader.params.get('test', False) and not is_intentional:
896 self._downloader.report_warning('Falling back on generic information extractor.')
898 if not full_response:
899 full_response = self._request_webpage(url, video_id)
901 # Maybe it's a direct link to a video?
902 # Be careful not to download the whole thing!
903 first_bytes = full_response.read(512)
904 if not is_html(first_bytes):
905 self._downloader.report_warning(
906 'URL could be a direct video link, returning it as such.')
907 upload_date = unified_strdate(
908 head_response.headers.get('Last-Modified'))
911 'title': os.path.splitext(url_basename(url))[0],
914 'upload_date': upload_date,
917 webpage = self._webpage_read_content(
918 full_response, url, video_id, prefix=first_bytes)
920 self.report_extraction(video_id)
924 doc = parse_xml(webpage)
926 return self._extract_rss(url, video_id, doc)
927 except compat_xml_parse_error:
930 # Is it a Camtasia project?
931 camtasia_res = self._extract_camtasia(url, video_id, webpage)
932 if camtasia_res is not None:
935 # Sometimes embedded video player is hidden behind percent encoding
936 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
937 # Unescaping the whole page allows to handle those cases in a generic way
938 webpage = compat_urllib_parse.unquote(webpage)
940 # it's tempting to parse this further, but you would
941 # have to take into account all the variations like
942 # Video Title - Site Name
943 # Site Name | Video Title
944 # Video Title - Tagline | Site Name
945 # and so on and so forth; it's just not practical
946 video_title = self._html_search_regex(
947 r'(?s)<title>(.*?)</title>', webpage, 'video title',
950 # Try to detect age limit automatically
951 age_limit = self._rta_search(webpage)
952 # And then there are the jokers who advertise that they use RTA,
953 # but actually don't.
954 AGE_LIMIT_MARKERS = [
955 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
957 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
960 # video uploader is domain name
961 video_uploader = self._search_regex(
962 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
965 def _playlist_from_matches(matches, getter=None, ie=None):
967 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
969 return self.playlist_result(
970 urlrs, playlist_id=video_id, playlist_title=video_title)
972 # Look for BrightCove:
973 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
975 self.to_screen('Brightcove video detected.')
978 'url': smuggle_url(bc_url, {'Referer': url}),
979 'ie_key': 'Brightcove'
980 } for bc_url in bc_urls]
984 'title': video_title,
989 # Look for embedded rtl.nl player
990 matches = re.findall(
991 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+video_embed[^"]+)"',
994 return _playlist_from_matches(matches, ie='RtlNl')
996 # Look for embedded (iframe) Vimeo player
998 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
1000 player_url = unescapeHTML(mobj.group('url'))
1001 surl = smuggle_url(player_url, {'Referer': url})
1002 return self.url_result(surl)
1003 # Look for embedded (swf embed) Vimeo player
1005 r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
1007 return self.url_result(mobj.group(1))
1009 # Look for embedded YouTube player
1010 matches = re.findall(r'''(?x)
1019 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1023 return _playlist_from_matches(
1024 matches, lambda m: unescapeHTML(m[1]))
1026 # Look for lazyYT YouTube embed
1027 matches = re.findall(
1028 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1030 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1032 # Look for embedded Dailymotion player
1033 matches = re.findall(
1034 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1036 return _playlist_from_matches(
1037 matches, lambda m: unescapeHTML(m[1]))
1039 # Look for embedded Dailymotion playlist player (#3822)
1041 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1043 playlists = re.findall(
1044 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1046 return _playlist_from_matches(
1047 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1049 # Look for embedded Wistia player
1051 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1053 embed_url = self._proto_relative_url(
1054 unescapeHTML(match.group('url')))
1056 '_type': 'url_transparent',
1059 'uploader': video_uploader,
1060 'title': video_title,
1064 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1067 '_type': 'url_transparent',
1068 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1070 'uploader': video_uploader,
1071 'title': video_title,
1072 'id': match.group('id')
1075 # Look for embedded blip.tv player
1076 mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
1078 return self.url_result('http://blip.tv/a/a-' + mobj.group(1), 'BlipTV')
1079 mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage)
1081 return self.url_result(mobj.group(1), 'BlipTV')
1083 # Look for embedded condenast player
1084 matches = re.findall(
1085 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1089 '_type': 'playlist',
1092 'ie_key': 'CondeNast',
1094 } for ma in matches],
1095 'title': video_title,
1099 # Look for Bandcamp pages with custom domain
1100 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1101 if mobj is not None:
1102 burl = unescapeHTML(mobj.group(1))
1103 # Don't set the extractor because it can be a track url or an album
1104 return self.url_result(burl)
1106 # Look for embedded Vevo player
1108 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1109 if mobj is not None:
1110 return self.url_result(mobj.group('url'))
1112 # Look for embedded Viddler player
1114 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1116 if mobj is not None:
1117 return self.url_result(mobj.group('url'))
1119 # Look for NYTimes player
1121 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1123 if mobj is not None:
1124 return self.url_result(mobj.group('url'))
1126 # Look for Libsyn player
1128 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1129 if mobj is not None:
1130 return self.url_result(mobj.group('url'))
1132 # Look for Ooyala videos
1133 mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1134 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1135 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1136 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1137 if mobj is not None:
1138 return OoyalaIE._build_url_result(mobj.group('ec'))
1140 # Look for multiple Ooyala embeds on SBN network websites
1141 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1142 if mobj is not None:
1143 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1145 return _playlist_from_matches(
1146 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1148 # Look for Aparat videos
1149 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1150 if mobj is not None:
1151 return self.url_result(mobj.group(1), 'Aparat')
1153 # Look for MPORA videos
1154 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1155 if mobj is not None:
1156 return self.url_result(mobj.group(1), 'Mpora')
1158 # Look for embedded NovaMov-based player
1160 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1161 (?P<url>http://(?:(?:embed|www)\.)?
1163 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1164 videoweed\.(?:es|com)|
1165 movshare\.(?:net|sx|ag)|
1166 divxstage\.(?:eu|net|ch|co|at|ag))
1167 /embed\.php.+?)\1''', webpage)
1168 if mobj is not None:
1169 return self.url_result(mobj.group('url'))
1171 # Look for embedded Facebook player
1173 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1174 if mobj is not None:
1175 return self.url_result(mobj.group('url'), 'Facebook')
1177 # Look for embedded VK player
1178 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1179 if mobj is not None:
1180 return self.url_result(mobj.group('url'), 'VK')
1182 # Look for embedded ivi player
1183 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1184 if mobj is not None:
1185 return self.url_result(mobj.group('url'), 'Ivi')
1187 # Look for embedded Huffington Post player
1189 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1190 if mobj is not None:
1191 return self.url_result(mobj.group('url'), 'HuffPost')
1194 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1195 if mobj is not None:
1196 return self.url_result(mobj.group('url'))
1197 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1198 if mobj is not None:
1199 return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
1201 # Look for funnyordie embed
1202 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1204 return _playlist_from_matches(
1205 matches, getter=unescapeHTML, ie='FunnyOrDie')
1207 # Look for BBC iPlayer embed
1208 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1210 return _playlist_from_matches(matches, ie='BBCCoUk')
1212 # Look for embedded RUTV player
1213 rutv_url = RUTVIE._extract_url(webpage)
1215 return self.url_result(rutv_url, 'RUTV')
1217 # Look for embedded TED player
1219 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1220 if mobj is not None:
1221 return self.url_result(mobj.group('url'), 'TED')
1223 # Look for embedded Ustream videos
1225 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1226 if mobj is not None:
1227 return self.url_result(mobj.group('url'), 'Ustream')
1229 # Look for embedded arte.tv player
1231 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1233 if mobj is not None:
1234 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1236 # Look for embedded smotri.com player
1237 smotri_url = SmotriIE._extract_url(webpage)
1239 return self.url_result(smotri_url, 'Smotri')
1241 # Look for embeded soundcloud player
1243 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1245 if mobj is not None:
1246 url = unescapeHTML(mobj.group('url'))
1247 return self.url_result(url)
1249 # Look for embedded vulture.com player
1251 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1253 if mobj is not None:
1254 url = unescapeHTML(mobj.group('url'))
1255 return self.url_result(url, ie='Vulture')
1257 # Look for embedded mtvservices player
1259 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1261 if mobj is not None:
1262 url = unescapeHTML(mobj.group('url'))
1263 return self.url_result(url, ie='MTVServicesEmbedded')
1265 # Look for embedded yahoo player
1267 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1269 if mobj is not None:
1270 return self.url_result(mobj.group('url'), 'Yahoo')
1272 # Look for embedded sbs.com.au player
1276 <meta\s+property="og:video"\s+content=|
1279 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1281 if mobj is not None:
1282 return self.url_result(mobj.group('url'), 'SBS')
1284 # Look for embedded Cinchcast player
1286 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1288 if mobj is not None:
1289 return self.url_result(mobj.group('url'), 'Cinchcast')
1292 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1294 if mobj is not None:
1295 return self.url_result(mobj.group('url'), 'MLB')
1298 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1300 if mobj is not None:
1301 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1304 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1306 if mobj is not None:
1307 return self.url_result(mobj.group('url'), 'Livestream')
1309 # Look for Zapiks embed
1311 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1312 if mobj is not None:
1313 return self.url_result(mobj.group('url'), 'Zapiks')
1315 # Look for Kaltura embeds
1317 r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage)
1318 if mobj is not None:
1319 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1321 # Look for Eagle.Platform embeds
1323 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1324 if mobj is not None:
1325 return self.url_result(mobj.group('url'), 'EaglePlatform')
1327 # Look for ClipYou (uses Eagle.Platform) embeds
1329 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1330 if mobj is not None:
1331 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1333 # Look for Pladform embeds
1335 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1336 if mobj is not None:
1337 return self.url_result(mobj.group('url'), 'Pladform')
1339 # Look for Playwire embeds
1341 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1342 if mobj is not None:
1343 return self.url_result(mobj.group('url'))
1345 # Look for 5min embeds
1347 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1348 if mobj is not None:
1349 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1351 # Look for Crooks and Liars embeds
1353 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1354 if mobj is not None:
1355 return self.url_result(mobj.group('url'))
1357 # Look for NBC Sports VPlayer embeds
1358 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1360 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1362 # Look for UDN embeds
1364 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1365 if mobj is not None:
1366 return self.url_result(
1367 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1369 # Look for Senate ISVP iframe
1370 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1372 return self.url_result(surl, 'SenateISVP')
1374 def check_video(vurl):
1375 if YoutubeIE.suitable(vurl):
1377 vpath = compat_urlparse.urlparse(vurl).path
1378 vext = determine_ext(vpath)
1379 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1381 def filter_video(urls):
1382 return list(filter(check_video, urls))
1384 # Start with something easy: JW Player in SWFObject
1385 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1387 # Look for gorilla-vid style embedding
1388 found = filter_video(re.findall(r'''(?sx)
1392 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1395 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1397 # Broaden the search a little bit
1398 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1400 # Broaden the findall a little bit: JWPlayer JS loader
1401 found = filter_video(re.findall(
1402 r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1405 found = filter_video(re.findall(r'''(?xs)
1406 flowplayer\("[^"]+",\s*
1408 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1409 ["']?url["']?\s*:\s*["']([^"']+)["']
1414 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1416 # Try to find twitter cards info
1417 found = filter_video(re.findall(
1418 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1420 # We look for Open Graph info:
1421 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1422 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1423 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1424 if m_video_type is not None:
1425 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1428 found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1430 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1432 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1433 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1436 # Look also in Refresh HTTP header
1437 refresh_header = head_response.headers.get('Refresh')
1439 found = re.search(REDIRECT_REGEX, refresh_header)
1441 new_url = found.group(1)
1442 self.report_following_redirect(new_url)
1448 raise UnsupportedError(url)
1451 for video_url in found:
1452 video_url = compat_urlparse.urljoin(url, video_url)
1453 video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
1455 # Sometimes, jwplayer extraction will result in a YouTube URL
1456 if YoutubeIE.suitable(video_url):
1457 entries.append(self.url_result(video_url, 'Youtube'))
1460 # here's a fun little line of code for you:
1461 video_id = os.path.splitext(video_id)[0]
1463 if determine_ext(video_url) == 'smil':
1466 'formats': self._extract_smil_formats(video_url, video_id),
1467 'uploader': video_uploader,
1468 'title': video_title,
1469 'age_limit': age_limit,
1475 'uploader': video_uploader,
1476 'title': video_title,
1477 'age_limit': age_limit,
1480 if len(entries) == 1:
1483 for num, e in enumerate(entries, start=1):
1484 # 'url' results don't have a title
1485 if e.get('title') is not None:
1486 e['title'] = '%s (%d)' % (e['title'], num)
1488 '_type': 'playlist',