3 from __future__ import unicode_literals
8 from .common import InfoExtractor
9 from .youtube import YoutubeIE
10 from ..compat import (
12 compat_urllib_parse_unquote,
13 compat_urllib_request,
15 compat_xml_parse_error,
33 from .brightcove import BrightcoveIE
34 from .nbc import NBCSportsVPlayerIE
35 from .ooyala import OoyalaIE
36 from .rutv import RUTVIE
37 from .sportbox import SportBoxEmbedIE
38 from .smotri import SmotriIE
39 from .condenast import CondeNastIE
40 from .udn import UDNEmbedIE
41 from .senateisvp import SenateISVPIE
42 from .bliptv import BlipTVIE
43 from .svt import SVTIE
46 class GenericIE(InfoExtractor):
47 IE_DESC = 'Generic downloader that works on some sites'
52 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
53 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
55 'id': '13601338388002',
57 'uploader': 'www.hodiho.fr',
58 'title': 'R\u00e9gis plante sa Jeep',
61 # bandcamp page with custom domain
63 'add_ie': ['Bandcamp'],
64 'url': 'http://bronyrock.com/track/the-pony-mash',
68 'title': 'The Pony Mash',
69 'uploader': 'M_Pallante',
71 'skip': 'There is a limit of 200 free downloads / month for the test song',
73 # embedded brightcove video
74 # it also tests brightcove videos that need to set the 'Referer' in the
77 'add_ie': ['Brightcove'],
78 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
80 'id': '2765128793001',
82 'title': 'Le cours de bourse : l’analyse technique',
83 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
84 'uploader': 'BFM BUSINESS',
87 'skip_download': True,
91 # https://github.com/rg3/youtube-dl/issues/2253
92 'url': 'http://bcove.me/i6nfkrc3',
93 'md5': '0ba9446db037002366bab3b3eb30c88c',
95 'id': '3101154703001',
97 'title': 'Still no power',
98 'uploader': 'thestar.com',
99 '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.',
101 'add_ie': ['Brightcove'],
104 'url': 'http://www.championat.com/video/football/v/87/87499.html',
105 'md5': 'fb973ecf6e4a78a67453647444222983',
107 'id': '3414141473001',
109 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
110 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
111 'uploader': 'Championat',
115 # https://github.com/rg3/youtube-dl/issues/3541
116 'add_ie': ['Brightcove'],
117 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
119 'id': '3866516442001',
121 'title': 'Leer mij vrouwen kennen: Aflevering 1',
122 'description': 'Leer mij vrouwen kennen: Aflevering 1',
123 'uploader': 'SBS Broadcasting',
125 'skip': 'Restricted to Netherlands',
127 'skip_download': True, # m3u8 download
130 # Direct link to a video
132 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
133 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
138 'upload_date': '20100513',
143 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
144 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
146 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
148 'title': '2cc213299525360.mov', # that's what we get
150 'add_ie': ['Ooyala'],
152 # multiple ooyala embeds on SBN network websites
154 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
156 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
157 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
159 'playlist_mincount': 3,
161 'skip_download': True,
163 'add_ie': ['Ooyala'],
167 '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',
171 'upload_date': '20130224',
172 'uploader_id': 'TheVerge',
173 'description': 're:^Chris Ziegler takes a look at the\.*',
174 'uploader': 'The Verge',
175 'title': 'First Firefox OS phones side-by-side',
178 'skip_download': False,
183 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
187 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
188 'upload_date': '20140225',
189 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
190 'uploader': 'Tested',
191 'uploader_id': 'testedcom',
193 # No need to test YoutubeIE here
195 'skip_download': True,
200 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
204 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
205 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
210 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER',
212 'title': 'BBC - Blogs - Adam Curtis - BUGGER',
214 'playlist_mincount': 18,
218 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
222 'title': 'Охотское море стало целиком российским',
223 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
227 'skip_download': True,
232 'url': 'http://www.vestifinance.ru/articles/25753',
235 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
240 'title': 'Госзаказ. День 3',
246 'title': 'Госзаказ. День 2',
252 'title': 'Госзаказ. День 1',
258 'skip_download': True,
263 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
264 'md5': '65fdff94098e4a607385a60c5177c638',
268 'title': 'Hidden miracles of the natural world',
269 'uploader': 'Louie Schwartzberg',
270 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
273 # Embeded Ustream video
275 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
276 'md5': '27b99cdb639c9b12a79bca876a073417',
280 'uploader': 'AU SPA: The NSA and Privacy',
281 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
284 # nowvideo embed hidden behind percent encoding
286 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
287 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
289 'id': '06e53103ca9aa',
291 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
292 'description': 'No description',
297 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
298 'md5': '7653032cbb25bf6c80d80f217055fa43',
300 'id': '048195-004_PLUS7-F',
303 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
304 'upload_date': '20140320',
307 'skip_download': 'Requires rtmpdump'
312 'url': 'http://www.wired.com/2014/04/honda-asimo/',
313 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
315 'id': '53501be369702d3275860000',
317 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
322 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
323 'md5': '441aeeb82eb72c422c7f14ec533999cd',
325 'id': 'k2mm4bCdJ6CQ2i7c8o2',
327 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
330 'add_ie': ['Dailymotion'],
334 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
338 'title': 'The NBL Auction 2014',
339 'uploader': 'BADMINTON England',
340 'uploader_id': 'BADMINTONEvents',
341 'upload_date': '20140603',
342 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
344 'add_ie': ['Youtube'],
346 'skip_download': True,
351 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
352 'md5': '35727f82f58c76d996fc188f9755b0d5',
354 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
357 'description': 'Mario\'s life in the fast lane has never looked so good.',
360 # YouTube embed via <data-embed-url="">
362 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
366 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
367 'uploader': 'Gameloft',
368 'uploader_id': 'gameloft',
369 'upload_date': '20140828',
370 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
373 'skip_download': True,
378 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
380 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
382 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
383 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
388 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
390 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
391 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
397 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
402 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
403 'md5': '9d65602bf31c6e20014319c7d07fba27',
405 'id': '5123ea6d5e5a7',
408 'uploader': 'www.handjobhub.com',
409 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
414 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
416 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
417 'title': 'Zero Punctuation',
418 'description': 're:.*groundbreaking video review series.*'
420 'playlist_mincount': 11,
422 # Multiple brightcove videos
423 # https://github.com/rg3/youtube-dl/issues/2283
425 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
427 'id': 'always-never',
428 'title': 'Always / Never - The New Yorker',
432 'extract_flat': False,
433 'skip_download': True,
438 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
439 'md5': '96f09a37e44da40dd083e12d9a683327',
443 'title': 'Ump changes call to ball',
444 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
446 'timestamp': 1401537900,
447 'upload_date': '20140531',
448 'thumbnail': 're:^https?://.*\.jpg$',
453 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
454 'md5': '8788b683c777a5cf25621eaf286d0c23',
458 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
460 'filesize': 182808282,
461 'uploader': 'education-portal.com',
465 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
466 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
470 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
472 'uploader': 'thoughtworks.wistia.com',
475 # Direct download with broken HEAD
477 'url': 'http://ai-radio.org:8000/radio.opus',
484 'skip_download': True, # infinite live stream
486 'expected_warnings': [
487 r'501.*Not Implemented'
492 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
496 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
497 'uploader': 'Sophos Security',
498 'title': 'Chet Chat 171 - Oct 29, 2014',
499 'upload_date': '20141029',
504 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
508 'upload_date': '20141112',
509 'title': 'Rosetta #CometLanding webcast HL 10',
514 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
517 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
519 'playlist_mincount': 2,
521 # Direct link with incorrect MIME type
523 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
524 'md5': '4ccbebe5f36706d85221f204d7eb5913',
526 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
527 'id': '5_Lennart_Poettering_-_Systemd',
529 'title': '5_Lennart_Poettering_-_Systemd',
530 'upload_date': '20141120',
532 'expected_warnings': [
533 'URL could be a direct video link, returning it as such.'
538 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
542 'upload_date': '20141126',
543 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
548 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
550 'id': '730m_DandD_1901_512k',
552 'uploader': 'www.abc.net.au',
553 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
556 # embedded viddler video
558 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
562 'uploader': 'deadspin',
563 'title': 'WALL-TO-GORTAT',
564 'timestamp': 1422285291,
565 'upload_date': '20150126',
567 'add_ie': ['Viddler'],
571 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
575 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
576 'description': 'md5:601cb790edd05908957dae8aaa866465',
577 'upload_date': '20150220',
582 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
586 'upload_date': '20150212',
587 'uploader': 'The National Archives UK',
588 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
589 'uploader_id': 'NationalArchives08',
590 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
595 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
596 'playlist_mincount': 5,
598 'id': 'aanslagen-kopenhagen',
599 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
604 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
608 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
613 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
617 'upload_date': '20150226',
618 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
620 'title': 'John Carlson Postgame 2/25/15',
623 # Eagle.Platform embed (generic URL)
625 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
629 'title': 'Навальный вышел на свободу',
630 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
631 'thumbnail': 're:^https?://.*\.jpg$',
637 # ClipYou (Eagle.Platform) embed (custom URL)
639 'url': 'http://muz-tv.ru/play/7129/',
643 'title': "'O Sole Mio",
644 'thumbnail': 're:^https?://.*\.jpg$',
651 'url': 'http://muz-tv.ru/kinozal/view/7400/',
655 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
656 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
657 'thumbnail': 're:^https?://.*\.jpg$',
664 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
668 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
669 'thumbnail': 're:^https?://.*\.png$',
675 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
676 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
680 'title': 'Facebook Creates "On This Day" | Crunch Report',
685 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
689 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
694 # RSS feed with enclosure
696 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
698 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
700 'upload_date': '20150228',
701 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
704 # Crooks and Liars embed
706 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
710 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
711 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
712 'timestamp': 1428207000,
713 'upload_date': '20150405',
714 'uploader': 'Heather',
717 # Crooks and Liars external embed
719 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
721 'id': 'MTE3MjUtMzQ2MzA',
723 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
724 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
725 'timestamp': 1265032391,
726 'upload_date': '20100201',
727 'uploader': 'Heather',
730 # NBC Sports vplayer embed
732 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
734 'id': 'ln7x1qSThw4k',
736 'title': "PFT Live: New leader in the 'new-look' defense",
737 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
742 'url': 'http://www.udn.com/news/story/7314/822787',
743 'md5': 'fd2060e988c326991037b9aff9df21a6',
747 'title': '中一中男師變性 全校師生力挺',
748 'thumbnail': 're:^https?://.*\.jpg$',
753 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
755 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
757 'description': 'VIDEO: Index/Match versus VLOOKUP.',
758 'title': 'This is what separates the Excel masters from the wannabes',
762 'skip_download': True,
765 # Contains a SMIL manifest
767 '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',
771 'title': '+ Football: Lottery Champions League Europe',
772 'uploader': 'www.telewebion.com',
776 'skip_download': True,
781 def report_following_redirect(self, new_url):
782 """Report information extraction."""
783 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
785 def _extract_rss(self, url, video_id, doc):
786 playlist_title = doc.find('./channel/title').text
787 playlist_desc_el = doc.find('./channel/description')
788 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
791 for it in doc.findall('./channel/item'):
792 next_url = xpath_text(it, 'link', fatal=False)
794 enclosure_nodes = it.findall('./enclosure')
795 for e in enclosure_nodes:
796 next_url = e.attrib.get('url')
806 'title': it.find('title').text,
812 'title': playlist_title,
813 'description': playlist_desc,
817 def _extract_camtasia(self, url, video_id, webpage):
818 """ Returns None if no camtasia video can be found. """
820 camtasia_cfg = self._search_regex(
821 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
822 webpage, 'camtasia configuration file', default=None)
823 if camtasia_cfg is None:
826 title = self._html_search_meta('DC.title', webpage, fatal=True)
828 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
829 camtasia_cfg = self._download_xml(
830 camtasia_url, video_id,
831 note='Downloading camtasia configuration',
832 errnote='Failed to download camtasia configuration')
833 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
836 for n in fileset_node.getchildren():
837 url_n = n.find('./uri')
842 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
843 'title': '%s - %s' % (title, n.tag),
844 'url': compat_urlparse.urljoin(url, url_n.text),
845 'duration': float_or_none(n.find('./duration').text),
854 def _real_extract(self, url):
855 if url.startswith('//'):
858 'url': self.http_scheme() + url,
861 parsed_url = compat_urlparse.urlparse(url)
862 if not parsed_url.scheme:
863 default_search = self._downloader.params.get('default_search')
864 if default_search is None:
865 default_search = 'fixup_error'
867 if default_search in ('auto', 'auto_warning', 'fixup_error'):
869 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
870 return self.url_result('http://' + url)
871 elif default_search != 'fixup_error':
872 if default_search == 'auto_warning':
873 if re.match(r'^(?:url|URL)$', url):
874 raise ExtractorError(
875 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
878 self._downloader.report_warning(
879 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
880 return self.url_result('ytsearch:' + url)
882 if default_search in ('error', 'fixup_error'):
883 raise ExtractorError(
884 '%r is not a valid URL. '
885 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
886 % (url, url), expected=True)
888 if ':' not in default_search:
889 default_search += ':'
890 return self.url_result(default_search + url)
892 url, smuggled_data = unsmuggle_url(url)
894 is_intentional = smuggled_data and smuggled_data.get('to_generic')
895 if smuggled_data and 'force_videoid' in smuggled_data:
896 force_videoid = smuggled_data['force_videoid']
897 video_id = force_videoid
899 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
901 self.to_screen('%s: Requesting header' % video_id)
903 head_req = HEADRequest(url)
904 head_response = self._request_webpage(
906 note=False, errnote='Could not send HEAD request to %s' % url,
909 if head_response is not False:
911 new_url = head_response.geturl()
913 self.report_following_redirect(new_url)
915 new_url = smuggle_url(
916 new_url, {'force_videoid': force_videoid})
917 return self.url_result(new_url)
920 if head_response is False:
921 request = compat_urllib_request.Request(url)
922 request.add_header('Accept-Encoding', '*')
923 full_response = self._request_webpage(request, video_id)
924 head_response = full_response
926 # Check for direct link to a video
927 content_type = head_response.headers.get('Content-Type', '')
928 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
930 upload_date = unified_strdate(
931 head_response.headers.get('Last-Modified'))
934 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
937 'format_id': m.group('format_id'),
939 'vcodec': 'none' if m.group('type') == 'audio' else None
941 'upload_date': upload_date,
944 if not self._downloader.params.get('test', False) and not is_intentional:
945 self._downloader.report_warning('Falling back on generic information extractor.')
947 if not full_response:
948 request = compat_urllib_request.Request(url)
949 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
950 # making it impossible to download only chunk of the file (yet we need only 512kB to
951 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
952 # that will always result in downloading the whole file that is not desirable.
953 # Therefore for extraction pass we have to override Accept-Encoding to any in order
954 # to accept raw bytes and being able to download only a chunk.
955 # It may probably better to solve this by checking Content-Type for application/octet-stream
956 # after HEAD request finishes, but not sure if we can rely on this.
957 request.add_header('Accept-Encoding', '*')
958 full_response = self._request_webpage(request, video_id)
960 # Maybe it's a direct link to a video?
961 # Be careful not to download the whole thing!
962 first_bytes = full_response.read(512)
963 if not is_html(first_bytes):
964 self._downloader.report_warning(
965 'URL could be a direct video link, returning it as such.')
966 upload_date = unified_strdate(
967 head_response.headers.get('Last-Modified'))
970 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
973 'upload_date': upload_date,
976 webpage = self._webpage_read_content(
977 full_response, url, video_id, prefix=first_bytes)
979 self.report_extraction(video_id)
983 doc = parse_xml(webpage)
985 return self._extract_rss(url, video_id, doc)
986 except compat_xml_parse_error:
989 # Is it a Camtasia project?
990 camtasia_res = self._extract_camtasia(url, video_id, webpage)
991 if camtasia_res is not None:
994 # Sometimes embedded video player is hidden behind percent encoding
995 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
996 # Unescaping the whole page allows to handle those cases in a generic way
997 webpage = compat_urllib_parse.unquote(webpage)
999 # it's tempting to parse this further, but you would
1000 # have to take into account all the variations like
1001 # Video Title - Site Name
1002 # Site Name | Video Title
1003 # Video Title - Tagline | Site Name
1004 # and so on and so forth; it's just not practical
1005 video_title = self._html_search_regex(
1006 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1009 # Try to detect age limit automatically
1010 age_limit = self._rta_search(webpage)
1011 # And then there are the jokers who advertise that they use RTA,
1012 # but actually don't.
1013 AGE_LIMIT_MARKERS = [
1014 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1016 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1019 # video uploader is domain name
1020 video_uploader = self._search_regex(
1021 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1024 def _playlist_from_matches(matches, getter=None, ie=None):
1026 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1028 return self.playlist_result(
1029 urlrs, playlist_id=video_id, playlist_title=video_title)
1031 # Look for BrightCove:
1032 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1034 self.to_screen('Brightcove video detected.')
1037 'url': smuggle_url(bc_url, {'Referer': url}),
1038 'ie_key': 'Brightcove'
1039 } for bc_url in bc_urls]
1042 '_type': 'playlist',
1043 'title': video_title,
1048 # Look for embedded rtl.nl player
1049 matches = re.findall(
1050 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+video_embed[^"]+)"',
1053 return _playlist_from_matches(matches, ie='RtlNl')
1055 # Look for embedded (iframe) Vimeo player
1057 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
1059 player_url = unescapeHTML(mobj.group('url'))
1060 surl = smuggle_url(player_url, {'Referer': url})
1061 return self.url_result(surl)
1062 # Look for embedded (swf embed) Vimeo player
1064 r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
1066 return self.url_result(mobj.group(1))
1068 # Look for embedded YouTube player
1069 matches = re.findall(r'''(?x)
1078 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1082 return _playlist_from_matches(
1083 matches, lambda m: unescapeHTML(m[1]))
1085 # Look for lazyYT YouTube embed
1086 matches = re.findall(
1087 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1089 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1091 # Look for embedded Dailymotion player
1092 matches = re.findall(
1093 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1095 return _playlist_from_matches(
1096 matches, lambda m: unescapeHTML(m[1]))
1098 # Look for embedded Dailymotion playlist player (#3822)
1100 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1102 playlists = re.findall(
1103 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1105 return _playlist_from_matches(
1106 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1108 # Look for embedded Wistia player
1110 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1112 embed_url = self._proto_relative_url(
1113 unescapeHTML(match.group('url')))
1115 '_type': 'url_transparent',
1118 'uploader': video_uploader,
1119 'title': video_title,
1123 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1126 '_type': 'url_transparent',
1127 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1129 'uploader': video_uploader,
1130 'title': video_title,
1131 'id': match.group('id')
1134 # Look for embedded blip.tv player
1135 bliptv_url = BlipTVIE._extract_url(webpage)
1137 return self.url_result(bliptv_url, 'BlipTV')
1139 # Look for SVT player
1140 svt_url = SVTIE._extract_url(webpage)
1142 return self.url_result(svt_url, 'SVT')
1144 # Look for embedded condenast player
1145 matches = re.findall(
1146 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1150 '_type': 'playlist',
1153 'ie_key': 'CondeNast',
1155 } for ma in matches],
1156 'title': video_title,
1160 # Look for Bandcamp pages with custom domain
1161 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1162 if mobj is not None:
1163 burl = unescapeHTML(mobj.group(1))
1164 # Don't set the extractor because it can be a track url or an album
1165 return self.url_result(burl)
1167 # Look for embedded Vevo player
1169 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1170 if mobj is not None:
1171 return self.url_result(mobj.group('url'))
1173 # Look for embedded Viddler player
1175 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1177 if mobj is not None:
1178 return self.url_result(mobj.group('url'))
1180 # Look for NYTimes player
1182 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1184 if mobj is not None:
1185 return self.url_result(mobj.group('url'))
1187 # Look for Libsyn player
1189 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1190 if mobj is not None:
1191 return self.url_result(mobj.group('url'))
1193 # Look for Ooyala videos
1194 mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1195 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1196 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1197 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1198 if mobj is not None:
1199 return OoyalaIE._build_url_result(mobj.group('ec'))
1201 # Look for multiple Ooyala embeds on SBN network websites
1202 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1203 if mobj is not None:
1204 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1206 return _playlist_from_matches(
1207 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1209 # Look for Aparat videos
1210 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1211 if mobj is not None:
1212 return self.url_result(mobj.group(1), 'Aparat')
1214 # Look for MPORA videos
1215 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1216 if mobj is not None:
1217 return self.url_result(mobj.group(1), 'Mpora')
1219 # Look for embedded NovaMov-based player
1221 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1222 (?P<url>http://(?:(?:embed|www)\.)?
1224 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1225 videoweed\.(?:es|com)|
1226 movshare\.(?:net|sx|ag)|
1227 divxstage\.(?:eu|net|ch|co|at|ag))
1228 /embed\.php.+?)\1''', webpage)
1229 if mobj is not None:
1230 return self.url_result(mobj.group('url'))
1232 # Look for embedded Facebook player
1234 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1235 if mobj is not None:
1236 return self.url_result(mobj.group('url'), 'Facebook')
1238 # Look for embedded VK player
1239 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1240 if mobj is not None:
1241 return self.url_result(mobj.group('url'), 'VK')
1243 # Look for embedded ivi player
1244 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1245 if mobj is not None:
1246 return self.url_result(mobj.group('url'), 'Ivi')
1248 # Look for embedded Huffington Post player
1250 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1251 if mobj is not None:
1252 return self.url_result(mobj.group('url'), 'HuffPost')
1255 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1256 if mobj is not None:
1257 return self.url_result(mobj.group('url'))
1258 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1259 if mobj is not None:
1260 return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
1262 # Look for funnyordie embed
1263 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1265 return _playlist_from_matches(
1266 matches, getter=unescapeHTML, ie='FunnyOrDie')
1268 # Look for BBC iPlayer embed
1269 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1271 return _playlist_from_matches(matches, ie='BBCCoUk')
1273 # Look for embedded RUTV player
1274 rutv_url = RUTVIE._extract_url(webpage)
1276 return self.url_result(rutv_url, 'RUTV')
1278 # Look for embedded SportBox player
1279 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1281 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1283 # Look for embedded TED player
1285 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1286 if mobj is not None:
1287 return self.url_result(mobj.group('url'), 'TED')
1289 # Look for embedded Ustream videos
1291 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1292 if mobj is not None:
1293 return self.url_result(mobj.group('url'), 'Ustream')
1295 # Look for embedded arte.tv player
1297 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1299 if mobj is not None:
1300 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1302 # Look for embedded smotri.com player
1303 smotri_url = SmotriIE._extract_url(webpage)
1305 return self.url_result(smotri_url, 'Smotri')
1307 # Look for embeded soundcloud player
1309 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1311 if mobj is not None:
1312 url = unescapeHTML(mobj.group('url'))
1313 return self.url_result(url)
1315 # Look for embedded vulture.com player
1317 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1319 if mobj is not None:
1320 url = unescapeHTML(mobj.group('url'))
1321 return self.url_result(url, ie='Vulture')
1323 # Look for embedded mtvservices player
1325 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1327 if mobj is not None:
1328 url = unescapeHTML(mobj.group('url'))
1329 return self.url_result(url, ie='MTVServicesEmbedded')
1331 # Look for embedded yahoo player
1333 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1335 if mobj is not None:
1336 return self.url_result(mobj.group('url'), 'Yahoo')
1338 # Look for embedded sbs.com.au player
1342 <meta\s+property="og:video"\s+content=|
1345 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1347 if mobj is not None:
1348 return self.url_result(mobj.group('url'), 'SBS')
1350 # Look for embedded Cinchcast player
1352 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1354 if mobj is not None:
1355 return self.url_result(mobj.group('url'), 'Cinchcast')
1358 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1362 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1364 if mobj is not None:
1365 return self.url_result(mobj.group('url'), 'MLB')
1368 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1370 if mobj is not None:
1371 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1374 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1376 if mobj is not None:
1377 return self.url_result(mobj.group('url'), 'Livestream')
1379 # Look for Zapiks embed
1381 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1382 if mobj is not None:
1383 return self.url_result(mobj.group('url'), 'Zapiks')
1385 # Look for Kaltura embeds
1387 r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage)
1388 if mobj is not None:
1389 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1391 # Look for Eagle.Platform embeds
1393 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1394 if mobj is not None:
1395 return self.url_result(mobj.group('url'), 'EaglePlatform')
1397 # Look for ClipYou (uses Eagle.Platform) embeds
1399 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1400 if mobj is not None:
1401 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1403 # Look for Pladform embeds
1405 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1406 if mobj is not None:
1407 return self.url_result(mobj.group('url'), 'Pladform')
1409 # Look for Playwire embeds
1411 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1412 if mobj is not None:
1413 return self.url_result(mobj.group('url'))
1415 # Look for 5min embeds
1417 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1418 if mobj is not None:
1419 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1421 # Look for Crooks and Liars embeds
1423 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1424 if mobj is not None:
1425 return self.url_result(mobj.group('url'))
1427 # Look for NBC Sports VPlayer embeds
1428 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1430 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1432 # Look for UDN embeds
1434 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1435 if mobj is not None:
1436 return self.url_result(
1437 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1439 # Look for Senate ISVP iframe
1440 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1442 return self.url_result(senate_isvp_url, 'SenateISVP')
1444 def check_video(vurl):
1445 if YoutubeIE.suitable(vurl):
1447 vpath = compat_urlparse.urlparse(vurl).path
1448 vext = determine_ext(vpath)
1449 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1451 def filter_video(urls):
1452 return list(filter(check_video, urls))
1454 # Start with something easy: JW Player in SWFObject
1455 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1457 # Look for gorilla-vid style embedding
1458 found = filter_video(re.findall(r'''(?sx)
1462 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1465 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1467 # Broaden the search a little bit
1468 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1470 # Broaden the findall a little bit: JWPlayer JS loader
1471 found = filter_video(re.findall(
1472 r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1475 found = filter_video(re.findall(r'''(?xs)
1476 flowplayer\("[^"]+",\s*
1478 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1479 ["']?url["']?\s*:\s*["']([^"']+)["']
1484 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1486 # Try to find twitter cards info
1487 found = filter_video(re.findall(
1488 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1490 # We look for Open Graph info:
1491 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1492 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1493 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1494 if m_video_type is not None:
1495 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1498 found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1500 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1502 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1503 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1506 # Look also in Refresh HTTP header
1507 refresh_header = head_response.headers.get('Refresh')
1509 found = re.search(REDIRECT_REGEX, refresh_header)
1511 new_url = compat_urlparse.urljoin(url, found.group(1))
1512 self.report_following_redirect(new_url)
1518 raise UnsupportedError(url)
1521 for video_url in found:
1522 video_url = compat_urlparse.urljoin(url, video_url)
1523 video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
1525 # Sometimes, jwplayer extraction will result in a YouTube URL
1526 if YoutubeIE.suitable(video_url):
1527 entries.append(self.url_result(video_url, 'Youtube'))
1530 # here's a fun little line of code for you:
1531 video_id = os.path.splitext(video_id)[0]
1533 if determine_ext(video_url) == 'smil':
1536 'formats': self._extract_smil_formats(video_url, video_id),
1537 'uploader': video_uploader,
1538 'title': video_title,
1539 'age_limit': age_limit,
1545 'uploader': video_uploader,
1546 'title': video_title,
1547 'age_limit': age_limit,
1550 if len(entries) == 1:
1553 for num, e in enumerate(entries, start=1):
1554 # 'url' results don't have a title
1555 if e.get('title') is not None:
1556 e['title'] = '%s (%d)' % (e['title'], num)
1558 '_type': 'playlist',