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 .xhamster import XHamsterEmbedIE
47 from .vimeo import VimeoIE
48 from .dailymotion import DailymotionCloudIE
51 class GenericIE(InfoExtractor):
52 IE_DESC = 'Generic downloader that works on some sites'
56 # Direct link to a video
58 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
59 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
64 'upload_date': '20100513',
67 # Direct link to media delivered compressed (until Accept-Encoding is *)
69 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
70 'md5': '128c42e68b13950268b648275386fc74',
72 'id': 'FictionJunction-Parallel_Hearts',
74 'title': 'FictionJunction-Parallel_Hearts',
75 'upload_date': '20140522',
77 'expected_warnings': [
78 'URL could be a direct video link, returning it as such.'
81 # Direct download with broken HEAD
83 'url': 'http://ai-radio.org:8000/radio.opus',
90 'skip_download': True, # infinite live stream
92 'expected_warnings': [
93 r'501.*Not Implemented'
96 # Direct link with incorrect MIME type
98 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
99 'md5': '4ccbebe5f36706d85221f204d7eb5913',
101 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
102 'id': '5_Lennart_Poettering_-_Systemd',
104 'title': '5_Lennart_Poettering_-_Systemd',
105 'upload_date': '20141120',
107 'expected_warnings': [
108 'URL could be a direct video link, returning it as such.'
113 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
115 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
116 'title': 'Zero Punctuation',
117 'description': 're:.*groundbreaking video review series.*'
119 'playlist_mincount': 11,
121 # RSS feed with enclosure
123 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
125 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
127 'upload_date': '20150228',
128 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
133 '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',
137 'upload_date': '20130224',
138 'uploader_id': 'TheVerge',
139 'description': 're:^Chris Ziegler takes a look at the\.*',
140 'uploader': 'The Verge',
141 'title': 'First Firefox OS phones side-by-side',
144 'skip_download': False,
148 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
149 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
151 'id': '13601338388002',
153 'uploader': 'www.hodiho.fr',
154 'title': 'R\u00e9gis plante sa Jeep',
157 # bandcamp page with custom domain
159 'add_ie': ['Bandcamp'],
160 'url': 'http://bronyrock.com/track/the-pony-mash',
164 'title': 'The Pony Mash',
165 'uploader': 'M_Pallante',
167 'skip': 'There is a limit of 200 free downloads / month for the test song',
169 # embedded brightcove video
170 # it also tests brightcove videos that need to set the 'Referer' in the
173 'add_ie': ['Brightcove'],
174 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
176 'id': '2765128793001',
178 'title': 'Le cours de bourse : l’analyse technique',
179 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
180 'uploader': 'BFM BUSINESS',
183 'skip_download': True,
187 # https://github.com/rg3/youtube-dl/issues/2253
188 'url': 'http://bcove.me/i6nfkrc3',
189 'md5': '0ba9446db037002366bab3b3eb30c88c',
191 'id': '3101154703001',
193 'title': 'Still no power',
194 'uploader': 'thestar.com',
195 '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.',
197 'add_ie': ['Brightcove'],
200 'url': 'http://www.championat.com/video/football/v/87/87499.html',
201 'md5': 'fb973ecf6e4a78a67453647444222983',
203 'id': '3414141473001',
205 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
206 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
207 'uploader': 'Championat',
211 # https://github.com/rg3/youtube-dl/issues/3541
212 'add_ie': ['Brightcove'],
213 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
215 'id': '3866516442001',
217 'title': 'Leer mij vrouwen kennen: Aflevering 1',
218 'description': 'Leer mij vrouwen kennen: Aflevering 1',
219 'uploader': 'SBS Broadcasting',
221 'skip': 'Restricted to Netherlands',
223 'skip_download': True, # m3u8 download
228 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
229 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
231 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
233 'title': '2cc213299525360.mov', # that's what we get
235 'add_ie': ['Ooyala'],
237 # multiple ooyala embeds on SBN network websites
239 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
241 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
242 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
244 'playlist_mincount': 3,
246 'skip_download': True,
248 'add_ie': ['Ooyala'],
252 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
256 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
257 'upload_date': '20140225',
258 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
259 'uploader': 'Tested',
260 'uploader_id': 'testedcom',
262 # No need to test YoutubeIE here
264 'skip_download': True,
269 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
273 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
274 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
279 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER',
281 'title': 'BBC - Blogs - Adam Curtis - BUGGER',
283 'playlist_mincount': 18,
287 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
291 'title': 'Охотское море стало целиком российским',
292 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
296 'skip_download': True,
301 '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/',
305 'title': 'Дошкольное воспитание',
310 'url': 'http://www.vestifinance.ru/articles/25753',
313 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
318 'title': 'Госзаказ. День 3',
324 'title': 'Госзаказ. День 2',
330 'title': 'Госзаказ. День 1',
336 'skip_download': True,
341 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
342 'md5': '65fdff94098e4a607385a60c5177c638',
346 'title': 'Hidden miracles of the natural world',
347 'uploader': 'Louie Schwartzberg',
348 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
351 # Embeded Ustream video
353 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
354 'md5': '27b99cdb639c9b12a79bca876a073417',
358 'uploader': 'AU SPA: The NSA and Privacy',
359 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
362 # nowvideo embed hidden behind percent encoding
364 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
365 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
367 'id': '06e53103ca9aa',
369 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
370 'description': 'No description',
375 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
376 'md5': '7653032cbb25bf6c80d80f217055fa43',
378 'id': '048195-004_PLUS7-F',
381 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
382 'upload_date': '20140320',
385 'skip_download': 'Requires rtmpdump'
390 'url': 'http://www.wired.com/2014/04/honda-asimo/',
391 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
393 'id': '53501be369702d3275860000',
395 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
400 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
401 'md5': '441aeeb82eb72c422c7f14ec533999cd',
403 'id': 'k2mm4bCdJ6CQ2i7c8o2',
405 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
408 'add_ie': ['Dailymotion'],
412 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
416 'title': 'The NBL Auction 2014',
417 'uploader': 'BADMINTON England',
418 'uploader_id': 'BADMINTONEvents',
419 'upload_date': '20140603',
420 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
422 'add_ie': ['Youtube'],
424 'skip_download': True,
429 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
430 'md5': '35727f82f58c76d996fc188f9755b0d5',
432 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
435 'description': 'Mario\'s life in the fast lane has never looked so good.',
438 # YouTube embed via <data-embed-url="">
440 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
444 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
445 'uploader': 'Gameloft',
446 'uploader_id': 'gameloft',
447 'upload_date': '20140828',
448 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
451 'skip_download': True,
456 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
458 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
460 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
461 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
466 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
468 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
469 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
475 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
480 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
481 'md5': '9d65602bf31c6e20014319c7d07fba27',
483 'id': '5123ea6d5e5a7',
486 'uploader': 'www.handjobhub.com',
487 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
490 # Multiple brightcove videos
491 # https://github.com/rg3/youtube-dl/issues/2283
493 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
495 'id': 'always-never',
496 'title': 'Always / Never - The New Yorker',
500 'extract_flat': False,
501 'skip_download': True,
506 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
507 'md5': '96f09a37e44da40dd083e12d9a683327',
511 'title': 'Ump changes call to ball',
512 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
514 'timestamp': 1401537900,
515 'upload_date': '20140531',
516 'thumbnail': 're:^https?://.*\.jpg$',
521 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
522 'md5': '8788b683c777a5cf25621eaf286d0c23',
526 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
528 'filesize': 182808282,
529 'uploader': 'education-portal.com',
533 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
534 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
538 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
540 'uploader': 'thoughtworks.wistia.com',
545 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
549 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
550 'uploader': 'Sophos Security',
551 'title': 'Chet Chat 171 - Oct 29, 2014',
552 'upload_date': '20141029',
557 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
561 'upload_date': '20141112',
562 'title': 'Rosetta #CometLanding webcast HL 10',
567 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
570 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
572 'playlist_mincount': 2,
576 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
580 'upload_date': '20141126',
581 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
586 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
588 'id': '730m_DandD_1901_512k',
590 'uploader': 'www.abc.net.au',
591 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
594 # embedded viddler video
596 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
600 'uploader': 'deadspin',
601 'title': 'WALL-TO-GORTAT',
602 'timestamp': 1422285291,
603 'upload_date': '20150126',
605 'add_ie': ['Viddler'],
609 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
613 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
614 'description': 'md5:601cb790edd05908957dae8aaa866465',
615 'upload_date': '20150220',
620 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
624 'upload_date': '20150212',
625 'uploader': 'The National Archives UK',
626 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
627 'uploader_id': 'NationalArchives08',
628 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
633 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
634 'playlist_mincount': 5,
636 'id': 'aanslagen-kopenhagen',
637 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
642 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
646 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
651 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
655 'upload_date': '20150226',
656 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
658 'title': 'John Carlson Postgame 2/25/15',
661 # Eagle.Platform embed (generic URL)
663 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
667 'title': 'Навальный вышел на свободу',
668 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
669 'thumbnail': 're:^https?://.*\.jpg$',
675 # ClipYou (Eagle.Platform) embed (custom URL)
677 'url': 'http://muz-tv.ru/play/7129/',
681 'title': "'O Sole Mio",
682 'thumbnail': 're:^https?://.*\.jpg$',
689 'url': 'http://muz-tv.ru/kinozal/view/7400/',
693 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
694 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
695 'thumbnail': 're:^https?://.*\.jpg$',
702 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
706 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
707 'thumbnail': 're:^https?://.*\.png$',
713 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
714 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
718 'title': 'Facebook Creates "On This Day" | Crunch Report',
723 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
727 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
732 # Crooks and Liars embed
734 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
738 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
739 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
740 'timestamp': 1428207000,
741 'upload_date': '20150405',
742 'uploader': 'Heather',
745 # Crooks and Liars external embed
747 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
749 'id': 'MTE3MjUtMzQ2MzA',
751 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
752 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
753 'timestamp': 1265032391,
754 'upload_date': '20100201',
755 'uploader': 'Heather',
758 # NBC Sports vplayer embed
760 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
762 'id': 'ln7x1qSThw4k',
764 'title': "PFT Live: New leader in the 'new-look' defense",
765 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
770 'url': 'http://www.udn.com/news/story/7314/822787',
771 'md5': 'fd2060e988c326991037b9aff9df21a6',
775 'title': '中一中男師變性 全校師生力挺',
776 'thumbnail': 're:^https?://.*\.jpg$',
781 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
783 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
785 'description': 'VIDEO: Index/Match versus VLOOKUP.',
786 'title': 'This is what separates the Excel masters from the wannabes',
790 'skip_download': True,
793 # Contains a SMIL manifest
795 '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',
799 'title': '+ Football: Lottery Champions League Europe',
800 'uploader': 'www.telewebion.com',
804 'skip_download': True,
807 # Brightcove URL in single quotes
809 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
810 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
812 'id': '4255764656001',
814 'title': 'SN Presents: Russell Martin, World Citizen',
815 '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.',
816 'uploader': 'Rogers Sportsnet',
819 # Dailymotion Cloud video
821 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
822 'md5': '49444254273501a64675a7e68c502681',
824 'id': '5585de919473990de4bee11b',
827 'thumbnail': 're:^https?://.*\.jpe?g$',
832 def report_following_redirect(self, new_url):
833 """Report information extraction."""
834 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
836 def _extract_rss(self, url, video_id, doc):
837 playlist_title = doc.find('./channel/title').text
838 playlist_desc_el = doc.find('./channel/description')
839 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
842 for it in doc.findall('./channel/item'):
843 next_url = xpath_text(it, 'link', fatal=False)
845 enclosure_nodes = it.findall('./enclosure')
846 for e in enclosure_nodes:
847 next_url = e.attrib.get('url')
857 'title': it.find('title').text,
863 'title': playlist_title,
864 'description': playlist_desc,
868 def _extract_camtasia(self, url, video_id, webpage):
869 """ Returns None if no camtasia video can be found. """
871 camtasia_cfg = self._search_regex(
872 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
873 webpage, 'camtasia configuration file', default=None)
874 if camtasia_cfg is None:
877 title = self._html_search_meta('DC.title', webpage, fatal=True)
879 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
880 camtasia_cfg = self._download_xml(
881 camtasia_url, video_id,
882 note='Downloading camtasia configuration',
883 errnote='Failed to download camtasia configuration')
884 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
887 for n in fileset_node.getchildren():
888 url_n = n.find('./uri')
893 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
894 'title': '%s - %s' % (title, n.tag),
895 'url': compat_urlparse.urljoin(url, url_n.text),
896 'duration': float_or_none(n.find('./duration').text),
905 def _real_extract(self, url):
906 if url.startswith('//'):
909 'url': self.http_scheme() + url,
912 parsed_url = compat_urlparse.urlparse(url)
913 if not parsed_url.scheme:
914 default_search = self._downloader.params.get('default_search')
915 if default_search is None:
916 default_search = 'fixup_error'
918 if default_search in ('auto', 'auto_warning', 'fixup_error'):
920 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
921 return self.url_result('http://' + url)
922 elif default_search != 'fixup_error':
923 if default_search == 'auto_warning':
924 if re.match(r'^(?:url|URL)$', url):
925 raise ExtractorError(
926 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
929 self._downloader.report_warning(
930 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
931 return self.url_result('ytsearch:' + url)
933 if default_search in ('error', 'fixup_error'):
934 raise ExtractorError(
935 '%r is not a valid URL. '
936 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
937 % (url, url), expected=True)
939 if ':' not in default_search:
940 default_search += ':'
941 return self.url_result(default_search + url)
943 url, smuggled_data = unsmuggle_url(url)
945 is_intentional = smuggled_data and smuggled_data.get('to_generic')
946 if smuggled_data and 'force_videoid' in smuggled_data:
947 force_videoid = smuggled_data['force_videoid']
948 video_id = force_videoid
950 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
952 self.to_screen('%s: Requesting header' % video_id)
954 head_req = HEADRequest(url)
955 head_response = self._request_webpage(
957 note=False, errnote='Could not send HEAD request to %s' % url,
960 if head_response is not False:
962 new_url = head_response.geturl()
964 self.report_following_redirect(new_url)
966 new_url = smuggle_url(
967 new_url, {'force_videoid': force_videoid})
968 return self.url_result(new_url)
971 if head_response is False:
972 request = compat_urllib_request.Request(url)
973 request.add_header('Accept-Encoding', '*')
974 full_response = self._request_webpage(request, video_id)
975 head_response = full_response
977 # Check for direct link to a video
978 content_type = head_response.headers.get('Content-Type', '')
979 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
981 upload_date = unified_strdate(
982 head_response.headers.get('Last-Modified'))
985 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
988 'format_id': m.group('format_id'),
990 'vcodec': 'none' if m.group('type') == 'audio' else None
992 'upload_date': upload_date,
995 if not self._downloader.params.get('test', False) and not is_intentional:
996 self._downloader.report_warning('Falling back on generic information extractor.')
998 if not full_response:
999 request = compat_urllib_request.Request(url)
1000 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1001 # making it impossible to download only chunk of the file (yet we need only 512kB to
1002 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1003 # that will always result in downloading the whole file that is not desirable.
1004 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1005 # to accept raw bytes and being able to download only a chunk.
1006 # It may probably better to solve this by checking Content-Type for application/octet-stream
1007 # after HEAD request finishes, but not sure if we can rely on this.
1008 request.add_header('Accept-Encoding', '*')
1009 full_response = self._request_webpage(request, video_id)
1011 # Maybe it's a direct link to a video?
1012 # Be careful not to download the whole thing!
1013 first_bytes = full_response.read(512)
1014 if not is_html(first_bytes):
1015 self._downloader.report_warning(
1016 'URL could be a direct video link, returning it as such.')
1017 upload_date = unified_strdate(
1018 head_response.headers.get('Last-Modified'))
1021 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1024 'upload_date': upload_date,
1027 webpage = self._webpage_read_content(
1028 full_response, url, video_id, prefix=first_bytes)
1030 self.report_extraction(video_id)
1032 # Is it an RSS feed?
1034 doc = parse_xml(webpage)
1035 if doc.tag == 'rss':
1036 return self._extract_rss(url, video_id, doc)
1037 except compat_xml_parse_error:
1040 # Is it a Camtasia project?
1041 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1042 if camtasia_res is not None:
1045 # Sometimes embedded video player is hidden behind percent encoding
1046 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1047 # Unescaping the whole page allows to handle those cases in a generic way
1048 webpage = compat_urllib_parse.unquote(webpage)
1050 # it's tempting to parse this further, but you would
1051 # have to take into account all the variations like
1052 # Video Title - Site Name
1053 # Site Name | Video Title
1054 # Video Title - Tagline | Site Name
1055 # and so on and so forth; it's just not practical
1056 video_title = self._html_search_regex(
1057 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1060 # Try to detect age limit automatically
1061 age_limit = self._rta_search(webpage)
1062 # And then there are the jokers who advertise that they use RTA,
1063 # but actually don't.
1064 AGE_LIMIT_MARKERS = [
1065 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1067 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1070 # video uploader is domain name
1071 video_uploader = self._search_regex(
1072 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1075 def _playlist_from_matches(matches, getter=None, ie=None):
1077 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1079 return self.playlist_result(
1080 urlrs, playlist_id=video_id, playlist_title=video_title)
1082 # Look for BrightCove:
1083 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1085 self.to_screen('Brightcove video detected.')
1088 'url': smuggle_url(bc_url, {'Referer': url}),
1089 'ie_key': 'Brightcove'
1090 } for bc_url in bc_urls]
1093 '_type': 'playlist',
1094 'title': video_title,
1099 # Look for embedded rtl.nl player
1100 matches = re.findall(
1101 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1104 return _playlist_from_matches(matches, ie='RtlNl')
1106 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1107 if vimeo_url is not None:
1108 return self.url_result(vimeo_url)
1110 # Look for embedded YouTube player
1111 matches = re.findall(r'''(?x)
1120 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1124 return _playlist_from_matches(
1125 matches, lambda m: unescapeHTML(m[1]))
1127 # Look for lazyYT YouTube embed
1128 matches = re.findall(
1129 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1131 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1133 # Look for embedded Dailymotion player
1134 matches = re.findall(
1135 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1137 return _playlist_from_matches(
1138 matches, lambda m: unescapeHTML(m[1]))
1140 # Look for embedded Dailymotion playlist player (#3822)
1142 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1144 playlists = re.findall(
1145 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1147 return _playlist_from_matches(
1148 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1150 # Look for embedded Wistia player
1152 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1154 embed_url = self._proto_relative_url(
1155 unescapeHTML(match.group('url')))
1157 '_type': 'url_transparent',
1160 'uploader': video_uploader,
1161 'title': video_title,
1165 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1168 '_type': 'url_transparent',
1169 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1171 'uploader': video_uploader,
1172 'title': video_title,
1173 'id': match.group('id')
1176 # Look for embedded blip.tv player
1177 bliptv_url = BlipTVIE._extract_url(webpage)
1179 return self.url_result(bliptv_url, 'BlipTV')
1181 # Look for SVT player
1182 svt_url = SVTIE._extract_url(webpage)
1184 return self.url_result(svt_url, 'SVT')
1186 # Look for embedded condenast player
1187 matches = re.findall(
1188 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1192 '_type': 'playlist',
1195 'ie_key': 'CondeNast',
1197 } for ma in matches],
1198 'title': video_title,
1202 # Look for Bandcamp pages with custom domain
1203 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1204 if mobj is not None:
1205 burl = unescapeHTML(mobj.group(1))
1206 # Don't set the extractor because it can be a track url or an album
1207 return self.url_result(burl)
1209 # Look for embedded Vevo player
1211 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1212 if mobj is not None:
1213 return self.url_result(mobj.group('url'))
1215 # Look for embedded Viddler player
1217 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1219 if mobj is not None:
1220 return self.url_result(mobj.group('url'))
1222 # Look for NYTimes player
1224 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1226 if mobj is not None:
1227 return self.url_result(mobj.group('url'))
1229 # Look for Libsyn player
1231 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1232 if mobj is not None:
1233 return self.url_result(mobj.group('url'))
1235 # Look for Ooyala videos
1236 mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1237 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1238 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1239 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1240 if mobj is not None:
1241 return OoyalaIE._build_url_result(mobj.group('ec'))
1243 # Look for multiple Ooyala embeds on SBN network websites
1244 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1245 if mobj is not None:
1246 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1248 return _playlist_from_matches(
1249 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1251 # Look for Aparat videos
1252 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1253 if mobj is not None:
1254 return self.url_result(mobj.group(1), 'Aparat')
1256 # Look for MPORA videos
1257 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1258 if mobj is not None:
1259 return self.url_result(mobj.group(1), 'Mpora')
1261 # Look for embedded NovaMov-based player
1263 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1264 (?P<url>http://(?:(?:embed|www)\.)?
1266 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1267 videoweed\.(?:es|com)|
1268 movshare\.(?:net|sx|ag)|
1269 divxstage\.(?:eu|net|ch|co|at|ag))
1270 /embed\.php.+?)\1''', webpage)
1271 if mobj is not None:
1272 return self.url_result(mobj.group('url'))
1274 # Look for embedded Facebook player
1276 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1277 if mobj is not None:
1278 return self.url_result(mobj.group('url'), 'Facebook')
1280 # Look for embedded VK player
1281 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1282 if mobj is not None:
1283 return self.url_result(mobj.group('url'), 'VK')
1285 # Look for embedded ivi player
1286 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1287 if mobj is not None:
1288 return self.url_result(mobj.group('url'), 'Ivi')
1290 # Look for embedded Huffington Post player
1292 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1293 if mobj is not None:
1294 return self.url_result(mobj.group('url'), 'HuffPost')
1297 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1298 if mobj is not None:
1299 return self.url_result(mobj.group('url'))
1300 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1301 if mobj is not None:
1302 return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
1304 # Look for funnyordie embed
1305 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1307 return _playlist_from_matches(
1308 matches, getter=unescapeHTML, ie='FunnyOrDie')
1310 # Look for BBC iPlayer embed
1311 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1313 return _playlist_from_matches(matches, ie='BBCCoUk')
1315 # Look for embedded RUTV player
1316 rutv_url = RUTVIE._extract_url(webpage)
1318 return self.url_result(rutv_url, 'RUTV')
1320 # Look for embedded TVC player
1321 tvc_url = TVCIE._extract_url(webpage)
1323 return self.url_result(tvc_url, 'TVC')
1325 # Look for embedded SportBox player
1326 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1328 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1330 # Look for embedded PornHub player
1331 pornhub_url = PornHubIE._extract_url(webpage)
1333 return self.url_result(pornhub_url, 'PornHub')
1335 # Look for embedded XHamster player
1336 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1338 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1340 # Look for embedded Tvigle player
1342 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1343 if mobj is not None:
1344 return self.url_result(mobj.group('url'), 'Tvigle')
1346 # Look for embedded TED player
1348 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1349 if mobj is not None:
1350 return self.url_result(mobj.group('url'), 'TED')
1352 # Look for embedded Ustream videos
1354 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1355 if mobj is not None:
1356 return self.url_result(mobj.group('url'), 'Ustream')
1358 # Look for embedded arte.tv player
1360 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1362 if mobj is not None:
1363 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1365 # Look for embedded smotri.com player
1366 smotri_url = SmotriIE._extract_url(webpage)
1368 return self.url_result(smotri_url, 'Smotri')
1370 # Look for embeded soundcloud player
1372 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1374 if mobj is not None:
1375 url = unescapeHTML(mobj.group('url'))
1376 return self.url_result(url)
1378 # Look for embedded vulture.com player
1380 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1382 if mobj is not None:
1383 url = unescapeHTML(mobj.group('url'))
1384 return self.url_result(url, ie='Vulture')
1386 # Look for embedded mtvservices player
1388 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1390 if mobj is not None:
1391 url = unescapeHTML(mobj.group('url'))
1392 return self.url_result(url, ie='MTVServicesEmbedded')
1394 # Look for embedded yahoo player
1396 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1398 if mobj is not None:
1399 return self.url_result(mobj.group('url'), 'Yahoo')
1401 # Look for embedded sbs.com.au player
1405 <meta\s+property="og:video"\s+content=|
1408 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1410 if mobj is not None:
1411 return self.url_result(mobj.group('url'), 'SBS')
1413 # Look for embedded Cinchcast player
1415 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1417 if mobj is not None:
1418 return self.url_result(mobj.group('url'), 'Cinchcast')
1421 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1425 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1427 if mobj is not None:
1428 return self.url_result(mobj.group('url'), 'MLB')
1431 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1433 if mobj is not None:
1434 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1437 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1439 if mobj is not None:
1440 return self.url_result(mobj.group('url'), 'Livestream')
1442 # Look for Zapiks embed
1444 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1445 if mobj is not None:
1446 return self.url_result(mobj.group('url'), 'Zapiks')
1448 # Look for Kaltura embeds
1450 r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage)
1451 if mobj is not None:
1452 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1454 # Look for Eagle.Platform embeds
1456 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1457 if mobj is not None:
1458 return self.url_result(mobj.group('url'), 'EaglePlatform')
1460 # Look for ClipYou (uses Eagle.Platform) embeds
1462 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1463 if mobj is not None:
1464 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1466 # Look for Pladform embeds
1468 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1469 if mobj is not None:
1470 return self.url_result(mobj.group('url'), 'Pladform')
1472 # Look for Playwire embeds
1474 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1475 if mobj is not None:
1476 return self.url_result(mobj.group('url'))
1478 # Look for 5min embeds
1480 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1481 if mobj is not None:
1482 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1484 # Look for Crooks and Liars embeds
1486 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1487 if mobj is not None:
1488 return self.url_result(mobj.group('url'))
1490 # Look for NBC Sports VPlayer embeds
1491 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1493 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1495 # Look for UDN embeds
1497 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1498 if mobj is not None:
1499 return self.url_result(
1500 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1502 # Look for Senate ISVP iframe
1503 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1505 return self.url_result(senate_isvp_url, 'SenateISVP')
1507 # Look for Dailymotion Cloud videos
1508 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1510 return self.url_result(dmcloud_url, 'DailymotionCloud')
1512 def check_video(vurl):
1513 if YoutubeIE.suitable(vurl):
1515 vpath = compat_urlparse.urlparse(vurl).path
1516 vext = determine_ext(vpath)
1517 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1519 def filter_video(urls):
1520 return list(filter(check_video, urls))
1522 # Start with something easy: JW Player in SWFObject
1523 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1525 # Look for gorilla-vid style embedding
1526 found = filter_video(re.findall(r'''(?sx)
1530 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1533 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1535 # Broaden the search a little bit
1536 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1538 # Broaden the findall a little bit: JWPlayer JS loader
1539 found = filter_video(re.findall(
1540 r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1543 found = filter_video(re.findall(r'''(?xs)
1544 flowplayer\("[^"]+",\s*
1546 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1547 ["']?url["']?\s*:\s*["']([^"']+)["']
1552 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1554 # Try to find twitter cards info
1555 found = filter_video(re.findall(
1556 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1558 # We look for Open Graph info:
1559 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1560 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1561 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1562 if m_video_type is not None:
1563 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1566 found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1568 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1570 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1571 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1574 # Look also in Refresh HTTP header
1575 refresh_header = head_response.headers.get('Refresh')
1577 found = re.search(REDIRECT_REGEX, refresh_header)
1579 new_url = compat_urlparse.urljoin(url, found.group(1))
1580 self.report_following_redirect(new_url)
1586 raise UnsupportedError(url)
1589 for video_url in found:
1590 video_url = compat_urlparse.urljoin(url, video_url)
1591 video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
1593 # Sometimes, jwplayer extraction will result in a YouTube URL
1594 if YoutubeIE.suitable(video_url):
1595 entries.append(self.url_result(video_url, 'Youtube'))
1598 # here's a fun little line of code for you:
1599 video_id = os.path.splitext(video_id)[0]
1601 if determine_ext(video_url) == 'smil':
1604 'formats': self._extract_smil_formats(video_url, video_id),
1605 'uploader': video_uploader,
1606 'title': video_title,
1607 'age_limit': age_limit,
1613 'uploader': video_uploader,
1614 'title': video_title,
1615 'age_limit': age_limit,
1618 if len(entries) == 1:
1621 for num, e in enumerate(entries, start=1):
1622 # 'url' results don't have a title
1623 if e.get('title') is not None:
1624 e['title'] = '%s (%d)' % (e['title'], num)
1626 '_type': 'playlist',