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 .tvc import TVCIE
38 from .sportbox import SportBoxEmbedIE
39 from .smotri import SmotriIE
40 from .condenast import CondeNastIE
41 from .udn import UDNEmbedIE
42 from .senateisvp import SenateISVPIE
43 from .bliptv import BlipTVIE
44 from .svt import SVTIE
45 from .pornhub import PornHubIE
46 from .vimeo import VimeoIE
47 from .dailymotion import DailymotionCloudIE
50 class GenericIE(InfoExtractor):
51 IE_DESC = 'Generic downloader that works on some sites'
55 # Direct link to a video
57 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
58 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
63 'upload_date': '20100513',
66 # Direct link to media delivered compressed (until Accept-Encoding is *)
68 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
69 'md5': '128c42e68b13950268b648275386fc74',
71 'id': 'FictionJunction-Parallel_Hearts',
73 'title': 'FictionJunction-Parallel_Hearts',
74 'upload_date': '20140522',
76 'expected_warnings': [
77 'URL could be a direct video link, returning it as such.'
80 # Direct download with broken HEAD
82 'url': 'http://ai-radio.org:8000/radio.opus',
89 'skip_download': True, # infinite live stream
91 'expected_warnings': [
92 r'501.*Not Implemented'
95 # Direct link with incorrect MIME type
97 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
98 'md5': '4ccbebe5f36706d85221f204d7eb5913',
100 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
101 'id': '5_Lennart_Poettering_-_Systemd',
103 'title': '5_Lennart_Poettering_-_Systemd',
104 'upload_date': '20141120',
106 'expected_warnings': [
107 'URL could be a direct video link, returning it as such.'
112 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
114 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
115 'title': 'Zero Punctuation',
116 'description': 're:.*groundbreaking video review series.*'
118 'playlist_mincount': 11,
120 # RSS feed with enclosure
122 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
124 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
126 'upload_date': '20150228',
127 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
132 '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',
136 'upload_date': '20130224',
137 'uploader_id': 'TheVerge',
138 'description': 're:^Chris Ziegler takes a look at the\.*',
139 'uploader': 'The Verge',
140 'title': 'First Firefox OS phones side-by-side',
143 'skip_download': False,
147 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
148 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
150 'id': '13601338388002',
152 'uploader': 'www.hodiho.fr',
153 'title': 'R\u00e9gis plante sa Jeep',
156 # bandcamp page with custom domain
158 'add_ie': ['Bandcamp'],
159 'url': 'http://bronyrock.com/track/the-pony-mash',
163 'title': 'The Pony Mash',
164 'uploader': 'M_Pallante',
166 'skip': 'There is a limit of 200 free downloads / month for the test song',
168 # embedded brightcove video
169 # it also tests brightcove videos that need to set the 'Referer' in the
172 'add_ie': ['Brightcove'],
173 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
175 'id': '2765128793001',
177 'title': 'Le cours de bourse : l’analyse technique',
178 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
179 'uploader': 'BFM BUSINESS',
182 'skip_download': True,
186 # https://github.com/rg3/youtube-dl/issues/2253
187 'url': 'http://bcove.me/i6nfkrc3',
188 'md5': '0ba9446db037002366bab3b3eb30c88c',
190 'id': '3101154703001',
192 'title': 'Still no power',
193 'uploader': 'thestar.com',
194 '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.',
196 'add_ie': ['Brightcove'],
199 'url': 'http://www.championat.com/video/football/v/87/87499.html',
200 'md5': 'fb973ecf6e4a78a67453647444222983',
202 'id': '3414141473001',
204 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
205 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
206 'uploader': 'Championat',
210 # https://github.com/rg3/youtube-dl/issues/3541
211 'add_ie': ['Brightcove'],
212 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
214 'id': '3866516442001',
216 'title': 'Leer mij vrouwen kennen: Aflevering 1',
217 'description': 'Leer mij vrouwen kennen: Aflevering 1',
218 'uploader': 'SBS Broadcasting',
220 'skip': 'Restricted to Netherlands',
222 'skip_download': True, # m3u8 download
227 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
228 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
230 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
232 'title': '2cc213299525360.mov', # that's what we get
234 'add_ie': ['Ooyala'],
236 # multiple ooyala embeds on SBN network websites
238 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
240 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
241 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
243 'playlist_mincount': 3,
245 'skip_download': True,
247 'add_ie': ['Ooyala'],
251 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
255 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
256 'upload_date': '20140225',
257 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
258 'uploader': 'Tested',
259 'uploader_id': 'testedcom',
261 # No need to test YoutubeIE here
263 'skip_download': True,
268 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
272 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
273 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
278 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER',
280 'title': 'BBC - Blogs - Adam Curtis - BUGGER',
282 'playlist_mincount': 18,
286 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
290 'title': 'Охотское море стало целиком российским',
291 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
295 'skip_download': True,
300 'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
304 'title': 'Дошкольное воспитание',
309 'url': 'http://www.vestifinance.ru/articles/25753',
312 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
317 'title': 'Госзаказ. День 3',
323 'title': 'Госзаказ. День 2',
329 'title': 'Госзаказ. День 1',
335 'skip_download': True,
340 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
341 'md5': '65fdff94098e4a607385a60c5177c638',
345 'title': 'Hidden miracles of the natural world',
346 'uploader': 'Louie Schwartzberg',
347 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
350 # Embeded Ustream video
352 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
353 'md5': '27b99cdb639c9b12a79bca876a073417',
357 'uploader': 'AU SPA: The NSA and Privacy',
358 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
361 # nowvideo embed hidden behind percent encoding
363 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
364 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
366 'id': '06e53103ca9aa',
368 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
369 'description': 'No description',
374 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
375 'md5': '7653032cbb25bf6c80d80f217055fa43',
377 'id': '048195-004_PLUS7-F',
380 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
381 'upload_date': '20140320',
384 'skip_download': 'Requires rtmpdump'
389 'url': 'http://www.wired.com/2014/04/honda-asimo/',
390 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
392 'id': '53501be369702d3275860000',
394 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
399 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
400 'md5': '441aeeb82eb72c422c7f14ec533999cd',
402 'id': 'k2mm4bCdJ6CQ2i7c8o2',
404 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
407 'add_ie': ['Dailymotion'],
411 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
415 'title': 'The NBL Auction 2014',
416 'uploader': 'BADMINTON England',
417 'uploader_id': 'BADMINTONEvents',
418 'upload_date': '20140603',
419 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
421 'add_ie': ['Youtube'],
423 'skip_download': True,
428 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
429 'md5': '35727f82f58c76d996fc188f9755b0d5',
431 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
434 'description': 'Mario\'s life in the fast lane has never looked so good.',
437 # YouTube embed via <data-embed-url="">
439 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
443 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
444 'uploader': 'Gameloft',
445 'uploader_id': 'gameloft',
446 'upload_date': '20140828',
447 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
450 'skip_download': True,
455 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
457 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
459 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
460 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
465 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
467 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
468 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
474 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
479 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
480 'md5': '9d65602bf31c6e20014319c7d07fba27',
482 'id': '5123ea6d5e5a7',
485 'uploader': 'www.handjobhub.com',
486 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
489 # Multiple brightcove videos
490 # https://github.com/rg3/youtube-dl/issues/2283
492 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
494 'id': 'always-never',
495 'title': 'Always / Never - The New Yorker',
499 'extract_flat': False,
500 'skip_download': True,
505 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
506 'md5': '96f09a37e44da40dd083e12d9a683327',
510 'title': 'Ump changes call to ball',
511 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
513 'timestamp': 1401537900,
514 'upload_date': '20140531',
515 'thumbnail': 're:^https?://.*\.jpg$',
520 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
521 'md5': '8788b683c777a5cf25621eaf286d0c23',
525 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
527 'filesize': 182808282,
528 'uploader': 'education-portal.com',
532 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
533 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
537 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
539 'uploader': 'thoughtworks.wistia.com',
544 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
548 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
549 'uploader': 'Sophos Security',
550 'title': 'Chet Chat 171 - Oct 29, 2014',
551 'upload_date': '20141029',
556 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
560 'upload_date': '20141112',
561 'title': 'Rosetta #CometLanding webcast HL 10',
566 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
569 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
571 'playlist_mincount': 2,
575 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
579 'upload_date': '20141126',
580 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
585 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
587 'id': '730m_DandD_1901_512k',
589 'uploader': 'www.abc.net.au',
590 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
593 # embedded viddler video
595 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
599 'uploader': 'deadspin',
600 'title': 'WALL-TO-GORTAT',
601 'timestamp': 1422285291,
602 'upload_date': '20150126',
604 'add_ie': ['Viddler'],
608 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
612 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
613 'description': 'md5:601cb790edd05908957dae8aaa866465',
614 'upload_date': '20150220',
619 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
623 'upload_date': '20150212',
624 'uploader': 'The National Archives UK',
625 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
626 'uploader_id': 'NationalArchives08',
627 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
632 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
633 'playlist_mincount': 5,
635 'id': 'aanslagen-kopenhagen',
636 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
641 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
645 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
650 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
654 'upload_date': '20150226',
655 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
657 'title': 'John Carlson Postgame 2/25/15',
660 # Eagle.Platform embed (generic URL)
662 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
666 'title': 'Навальный вышел на свободу',
667 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
668 'thumbnail': 're:^https?://.*\.jpg$',
674 # ClipYou (Eagle.Platform) embed (custom URL)
676 'url': 'http://muz-tv.ru/play/7129/',
680 'title': "'O Sole Mio",
681 'thumbnail': 're:^https?://.*\.jpg$',
688 'url': 'http://muz-tv.ru/kinozal/view/7400/',
692 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
693 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
694 'thumbnail': 're:^https?://.*\.jpg$',
701 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
705 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
706 'thumbnail': 're:^https?://.*\.png$',
712 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
713 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
717 'title': 'Facebook Creates "On This Day" | Crunch Report',
722 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
726 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
731 # Crooks and Liars embed
733 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
737 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
738 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
739 'timestamp': 1428207000,
740 'upload_date': '20150405',
741 'uploader': 'Heather',
744 # Crooks and Liars external embed
746 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
748 'id': 'MTE3MjUtMzQ2MzA',
750 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
751 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
752 'timestamp': 1265032391,
753 'upload_date': '20100201',
754 'uploader': 'Heather',
757 # NBC Sports vplayer embed
759 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
761 'id': 'ln7x1qSThw4k',
763 'title': "PFT Live: New leader in the 'new-look' defense",
764 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
769 'url': 'http://www.udn.com/news/story/7314/822787',
770 'md5': 'fd2060e988c326991037b9aff9df21a6',
774 'title': '中一中男師變性 全校師生力挺',
775 'thumbnail': 're:^https?://.*\.jpg$',
780 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
782 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
784 'description': 'VIDEO: Index/Match versus VLOOKUP.',
785 'title': 'This is what separates the Excel masters from the wannabes',
789 'skip_download': True,
792 # Contains a SMIL manifest
794 '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',
798 'title': '+ Football: Lottery Champions League Europe',
799 'uploader': 'www.telewebion.com',
803 'skip_download': True,
806 # Brightcove URL in single quotes
808 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
809 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
811 'id': '4255764656001',
813 'title': 'SN Presents: Russell Martin, World Citizen',
814 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
815 'uploader': 'Rogers Sportsnet',
818 # Dailymotion Cloud video
820 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
821 'md5': '49444254273501a64675a7e68c502681',
823 'id': '5585de919473990de4bee11b',
826 'thumbnail': 're:^https?://.*\.jpe?g$',
831 def report_following_redirect(self, new_url):
832 """Report information extraction."""
833 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
835 def _extract_rss(self, url, video_id, doc):
836 playlist_title = doc.find('./channel/title').text
837 playlist_desc_el = doc.find('./channel/description')
838 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
841 for it in doc.findall('./channel/item'):
842 next_url = xpath_text(it, 'link', fatal=False)
844 enclosure_nodes = it.findall('./enclosure')
845 for e in enclosure_nodes:
846 next_url = e.attrib.get('url')
856 'title': it.find('title').text,
862 'title': playlist_title,
863 'description': playlist_desc,
867 def _extract_camtasia(self, url, video_id, webpage):
868 """ Returns None if no camtasia video can be found. """
870 camtasia_cfg = self._search_regex(
871 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
872 webpage, 'camtasia configuration file', default=None)
873 if camtasia_cfg is None:
876 title = self._html_search_meta('DC.title', webpage, fatal=True)
878 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
879 camtasia_cfg = self._download_xml(
880 camtasia_url, video_id,
881 note='Downloading camtasia configuration',
882 errnote='Failed to download camtasia configuration')
883 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
886 for n in fileset_node.getchildren():
887 url_n = n.find('./uri')
892 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
893 'title': '%s - %s' % (title, n.tag),
894 'url': compat_urlparse.urljoin(url, url_n.text),
895 'duration': float_or_none(n.find('./duration').text),
904 def _real_extract(self, url):
905 if url.startswith('//'):
908 'url': self.http_scheme() + url,
911 parsed_url = compat_urlparse.urlparse(url)
912 if not parsed_url.scheme:
913 default_search = self._downloader.params.get('default_search')
914 if default_search is None:
915 default_search = 'fixup_error'
917 if default_search in ('auto', 'auto_warning', 'fixup_error'):
919 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
920 return self.url_result('http://' + url)
921 elif default_search != 'fixup_error':
922 if default_search == 'auto_warning':
923 if re.match(r'^(?:url|URL)$', url):
924 raise ExtractorError(
925 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
928 self._downloader.report_warning(
929 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
930 return self.url_result('ytsearch:' + url)
932 if default_search in ('error', 'fixup_error'):
933 raise ExtractorError(
934 '%r is not a valid URL. '
935 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
936 % (url, url), expected=True)
938 if ':' not in default_search:
939 default_search += ':'
940 return self.url_result(default_search + url)
942 url, smuggled_data = unsmuggle_url(url)
944 is_intentional = smuggled_data and smuggled_data.get('to_generic')
945 if smuggled_data and 'force_videoid' in smuggled_data:
946 force_videoid = smuggled_data['force_videoid']
947 video_id = force_videoid
949 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
951 self.to_screen('%s: Requesting header' % video_id)
953 head_req = HEADRequest(url)
954 head_response = self._request_webpage(
956 note=False, errnote='Could not send HEAD request to %s' % url,
959 if head_response is not False:
961 new_url = head_response.geturl()
963 self.report_following_redirect(new_url)
965 new_url = smuggle_url(
966 new_url, {'force_videoid': force_videoid})
967 return self.url_result(new_url)
970 if head_response is False:
971 request = compat_urllib_request.Request(url)
972 request.add_header('Accept-Encoding', '*')
973 full_response = self._request_webpage(request, video_id)
974 head_response = full_response
976 # Check for direct link to a video
977 content_type = head_response.headers.get('Content-Type', '')
978 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
980 upload_date = unified_strdate(
981 head_response.headers.get('Last-Modified'))
984 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
987 'format_id': m.group('format_id'),
989 'vcodec': 'none' if m.group('type') == 'audio' else None
991 'upload_date': upload_date,
994 if not self._downloader.params.get('test', False) and not is_intentional:
995 self._downloader.report_warning('Falling back on generic information extractor.')
997 if not full_response:
998 request = compat_urllib_request.Request(url)
999 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1000 # making it impossible to download only chunk of the file (yet we need only 512kB to
1001 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1002 # that will always result in downloading the whole file that is not desirable.
1003 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1004 # to accept raw bytes and being able to download only a chunk.
1005 # It may probably better to solve this by checking Content-Type for application/octet-stream
1006 # after HEAD request finishes, but not sure if we can rely on this.
1007 request.add_header('Accept-Encoding', '*')
1008 full_response = self._request_webpage(request, video_id)
1010 # Maybe it's a direct link to a video?
1011 # Be careful not to download the whole thing!
1012 first_bytes = full_response.read(512)
1013 if not is_html(first_bytes):
1014 self._downloader.report_warning(
1015 'URL could be a direct video link, returning it as such.')
1016 upload_date = unified_strdate(
1017 head_response.headers.get('Last-Modified'))
1020 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1023 'upload_date': upload_date,
1026 webpage = self._webpage_read_content(
1027 full_response, url, video_id, prefix=first_bytes)
1029 self.report_extraction(video_id)
1031 # Is it an RSS feed?
1033 doc = parse_xml(webpage)
1034 if doc.tag == 'rss':
1035 return self._extract_rss(url, video_id, doc)
1036 except compat_xml_parse_error:
1039 # Is it a Camtasia project?
1040 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1041 if camtasia_res is not None:
1044 # Sometimes embedded video player is hidden behind percent encoding
1045 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1046 # Unescaping the whole page allows to handle those cases in a generic way
1047 webpage = compat_urllib_parse.unquote(webpage)
1049 # it's tempting to parse this further, but you would
1050 # have to take into account all the variations like
1051 # Video Title - Site Name
1052 # Site Name | Video Title
1053 # Video Title - Tagline | Site Name
1054 # and so on and so forth; it's just not practical
1055 video_title = self._html_search_regex(
1056 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1059 # Try to detect age limit automatically
1060 age_limit = self._rta_search(webpage)
1061 # And then there are the jokers who advertise that they use RTA,
1062 # but actually don't.
1063 AGE_LIMIT_MARKERS = [
1064 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1066 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1069 # video uploader is domain name
1070 video_uploader = self._search_regex(
1071 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1074 def _playlist_from_matches(matches, getter=None, ie=None):
1076 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1078 return self.playlist_result(
1079 urlrs, playlist_id=video_id, playlist_title=video_title)
1081 # Look for BrightCove:
1082 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1084 self.to_screen('Brightcove video detected.')
1087 'url': smuggle_url(bc_url, {'Referer': url}),
1088 'ie_key': 'Brightcove'
1089 } for bc_url in bc_urls]
1092 '_type': 'playlist',
1093 'title': video_title,
1098 # Look for embedded rtl.nl player
1099 matches = re.findall(
1100 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1103 return _playlist_from_matches(matches, ie='RtlNl')
1105 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1106 if vimeo_url is not None:
1107 return self.url_result(vimeo_url)
1109 # Look for embedded YouTube player
1110 matches = re.findall(r'''(?x)
1119 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1123 return _playlist_from_matches(
1124 matches, lambda m: unescapeHTML(m[1]))
1126 # Look for lazyYT YouTube embed
1127 matches = re.findall(
1128 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1130 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1132 # Look for embedded Dailymotion player
1133 matches = re.findall(
1134 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1136 return _playlist_from_matches(
1137 matches, lambda m: unescapeHTML(m[1]))
1139 # Look for embedded Dailymotion playlist player (#3822)
1141 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1143 playlists = re.findall(
1144 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1146 return _playlist_from_matches(
1147 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1149 # Look for embedded Wistia player
1151 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1153 embed_url = self._proto_relative_url(
1154 unescapeHTML(match.group('url')))
1156 '_type': 'url_transparent',
1159 'uploader': video_uploader,
1160 'title': video_title,
1164 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1167 '_type': 'url_transparent',
1168 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1170 'uploader': video_uploader,
1171 'title': video_title,
1172 'id': match.group('id')
1175 # Look for embedded blip.tv player
1176 bliptv_url = BlipTVIE._extract_url(webpage)
1178 return self.url_result(bliptv_url, 'BlipTV')
1180 # Look for SVT player
1181 svt_url = SVTIE._extract_url(webpage)
1183 return self.url_result(svt_url, 'SVT')
1185 # Look for embedded condenast player
1186 matches = re.findall(
1187 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1191 '_type': 'playlist',
1194 'ie_key': 'CondeNast',
1196 } for ma in matches],
1197 'title': video_title,
1201 # Look for Bandcamp pages with custom domain
1202 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1203 if mobj is not None:
1204 burl = unescapeHTML(mobj.group(1))
1205 # Don't set the extractor because it can be a track url or an album
1206 return self.url_result(burl)
1208 # Look for embedded Vevo player
1210 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1211 if mobj is not None:
1212 return self.url_result(mobj.group('url'))
1214 # Look for embedded Viddler player
1216 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1218 if mobj is not None:
1219 return self.url_result(mobj.group('url'))
1221 # Look for NYTimes player
1223 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1225 if mobj is not None:
1226 return self.url_result(mobj.group('url'))
1228 # Look for Libsyn player
1230 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1231 if mobj is not None:
1232 return self.url_result(mobj.group('url'))
1234 # Look for Ooyala videos
1235 mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1236 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1237 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1238 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1239 if mobj is not None:
1240 return OoyalaIE._build_url_result(mobj.group('ec'))
1242 # Look for multiple Ooyala embeds on SBN network websites
1243 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1244 if mobj is not None:
1245 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1247 return _playlist_from_matches(
1248 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1250 # Look for Aparat videos
1251 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1252 if mobj is not None:
1253 return self.url_result(mobj.group(1), 'Aparat')
1255 # Look for MPORA videos
1256 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1257 if mobj is not None:
1258 return self.url_result(mobj.group(1), 'Mpora')
1260 # Look for embedded NovaMov-based player
1262 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1263 (?P<url>http://(?:(?:embed|www)\.)?
1265 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1266 videoweed\.(?:es|com)|
1267 movshare\.(?:net|sx|ag)|
1268 divxstage\.(?:eu|net|ch|co|at|ag))
1269 /embed\.php.+?)\1''', webpage)
1270 if mobj is not None:
1271 return self.url_result(mobj.group('url'))
1273 # Look for embedded Facebook player
1275 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1276 if mobj is not None:
1277 return self.url_result(mobj.group('url'), 'Facebook')
1279 # Look for embedded VK player
1280 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1281 if mobj is not None:
1282 return self.url_result(mobj.group('url'), 'VK')
1284 # Look for embedded ivi player
1285 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1286 if mobj is not None:
1287 return self.url_result(mobj.group('url'), 'Ivi')
1289 # Look for embedded Huffington Post player
1291 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1292 if mobj is not None:
1293 return self.url_result(mobj.group('url'), 'HuffPost')
1296 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1297 if mobj is not None:
1298 return self.url_result(mobj.group('url'))
1299 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1300 if mobj is not None:
1301 return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
1303 # Look for funnyordie embed
1304 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1306 return _playlist_from_matches(
1307 matches, getter=unescapeHTML, ie='FunnyOrDie')
1309 # Look for BBC iPlayer embed
1310 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1312 return _playlist_from_matches(matches, ie='BBCCoUk')
1314 # Look for embedded RUTV player
1315 rutv_url = RUTVIE._extract_url(webpage)
1317 return self.url_result(rutv_url, 'RUTV')
1319 # Look for embedded TVC player
1320 tvc_url = TVCIE._extract_url(webpage)
1322 return self.url_result(tvc_url, 'TVC')
1324 # Look for embedded SportBox player
1325 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1327 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1329 # Look for embedded PornHub player
1330 pornhub_url = PornHubIE._extract_url(webpage)
1332 return self.url_result(pornhub_url, 'PornHub')
1334 # Look for embedded Tvigle player
1336 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1337 if mobj is not None:
1338 return self.url_result(mobj.group('url'), 'Tvigle')
1340 # Look for embedded TED player
1342 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1343 if mobj is not None:
1344 return self.url_result(mobj.group('url'), 'TED')
1346 # Look for embedded Ustream videos
1348 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1349 if mobj is not None:
1350 return self.url_result(mobj.group('url'), 'Ustream')
1352 # Look for embedded arte.tv player
1354 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1356 if mobj is not None:
1357 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1359 # Look for embedded smotri.com player
1360 smotri_url = SmotriIE._extract_url(webpage)
1362 return self.url_result(smotri_url, 'Smotri')
1364 # Look for embeded soundcloud player
1366 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1368 if mobj is not None:
1369 url = unescapeHTML(mobj.group('url'))
1370 return self.url_result(url)
1372 # Look for embedded vulture.com player
1374 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1376 if mobj is not None:
1377 url = unescapeHTML(mobj.group('url'))
1378 return self.url_result(url, ie='Vulture')
1380 # Look for embedded mtvservices player
1382 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1384 if mobj is not None:
1385 url = unescapeHTML(mobj.group('url'))
1386 return self.url_result(url, ie='MTVServicesEmbedded')
1388 # Look for embedded yahoo player
1390 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1392 if mobj is not None:
1393 return self.url_result(mobj.group('url'), 'Yahoo')
1395 # Look for embedded sbs.com.au player
1399 <meta\s+property="og:video"\s+content=|
1402 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1404 if mobj is not None:
1405 return self.url_result(mobj.group('url'), 'SBS')
1407 # Look for embedded Cinchcast player
1409 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1411 if mobj is not None:
1412 return self.url_result(mobj.group('url'), 'Cinchcast')
1415 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1419 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1421 if mobj is not None:
1422 return self.url_result(mobj.group('url'), 'MLB')
1425 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1427 if mobj is not None:
1428 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1431 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1433 if mobj is not None:
1434 return self.url_result(mobj.group('url'), 'Livestream')
1436 # Look for Zapiks embed
1438 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1439 if mobj is not None:
1440 return self.url_result(mobj.group('url'), 'Zapiks')
1442 # Look for Kaltura embeds
1444 r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage)
1445 if mobj is not None:
1446 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1448 # Look for Eagle.Platform embeds
1450 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1451 if mobj is not None:
1452 return self.url_result(mobj.group('url'), 'EaglePlatform')
1454 # Look for ClipYou (uses Eagle.Platform) embeds
1456 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1457 if mobj is not None:
1458 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1460 # Look for Pladform embeds
1462 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1463 if mobj is not None:
1464 return self.url_result(mobj.group('url'), 'Pladform')
1466 # Look for Playwire embeds
1468 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1469 if mobj is not None:
1470 return self.url_result(mobj.group('url'))
1472 # Look for 5min embeds
1474 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1475 if mobj is not None:
1476 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1478 # Look for Crooks and Liars embeds
1480 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1481 if mobj is not None:
1482 return self.url_result(mobj.group('url'))
1484 # Look for NBC Sports VPlayer embeds
1485 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1487 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1489 # Look for UDN embeds
1491 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1492 if mobj is not None:
1493 return self.url_result(
1494 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1496 # Look for Senate ISVP iframe
1497 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1499 return self.url_result(senate_isvp_url, 'SenateISVP')
1501 # Look for Dailymotion Cloud videos
1502 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1504 return self.url_result(dmcloud_url, 'DailymotionCloud')
1506 def check_video(vurl):
1507 if YoutubeIE.suitable(vurl):
1509 vpath = compat_urlparse.urlparse(vurl).path
1510 vext = determine_ext(vpath)
1511 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1513 def filter_video(urls):
1514 return list(filter(check_video, urls))
1516 # Start with something easy: JW Player in SWFObject
1517 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1519 # Look for gorilla-vid style embedding
1520 found = filter_video(re.findall(r'''(?sx)
1524 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1527 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1529 # Broaden the search a little bit
1530 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1532 # Broaden the findall a little bit: JWPlayer JS loader
1533 found = filter_video(re.findall(
1534 r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1537 found = filter_video(re.findall(r'''(?xs)
1538 flowplayer\("[^"]+",\s*
1540 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1541 ["']?url["']?\s*:\s*["']([^"']+)["']
1546 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1548 # Try to find twitter cards info
1549 found = filter_video(re.findall(
1550 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1552 # We look for Open Graph info:
1553 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1554 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1555 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1556 if m_video_type is not None:
1557 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1560 found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1562 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1564 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1565 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1568 # Look also in Refresh HTTP header
1569 refresh_header = head_response.headers.get('Refresh')
1571 found = re.search(REDIRECT_REGEX, refresh_header)
1573 new_url = compat_urlparse.urljoin(url, found.group(1))
1574 self.report_following_redirect(new_url)
1580 raise UnsupportedError(url)
1583 for video_url in found:
1584 video_url = compat_urlparse.urljoin(url, video_url)
1585 video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
1587 # Sometimes, jwplayer extraction will result in a YouTube URL
1588 if YoutubeIE.suitable(video_url):
1589 entries.append(self.url_result(video_url, 'Youtube'))
1592 # here's a fun little line of code for you:
1593 video_id = os.path.splitext(video_id)[0]
1595 if determine_ext(video_url) == 'smil':
1598 'formats': self._extract_smil_formats(video_url, video_id),
1599 'uploader': video_uploader,
1600 'title': video_title,
1601 'age_limit': age_limit,
1607 'uploader': video_uploader,
1608 'title': video_title,
1609 'age_limit': age_limit,
1612 if len(entries) == 1:
1615 for num, e in enumerate(entries, start=1):
1616 # 'url' results don't have a title
1617 if e.get('title') is not None:
1618 e['title'] = '%s (%d)' % (e['title'], num)
1620 '_type': 'playlist',