3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_urllib_parse_unquote,
14 compat_urllib_request,
16 compat_xml_parse_error,
33 from .brightcove import (
37 from .nbc import NBCSportsVPlayerIE
38 from .ooyala import OoyalaIE
39 from .rutv import RUTVIE
40 from .tvc import TVCIE
41 from .sportbox import SportBoxEmbedIE
42 from .smotri import SmotriIE
43 from .myvi import MyviIE
44 from .condenast import CondeNastIE
45 from .udn import UDNEmbedIE
46 from .senateisvp import SenateISVPIE
47 from .bliptv import BlipTVIE
48 from .svt import SVTIE
49 from .pornhub import PornHubIE
50 from .xhamster import XHamsterEmbedIE
51 from .vimeo import VimeoIE
52 from .dailymotion import DailymotionCloudIE
53 from .onionstudios import OnionStudiosIE
54 from .snagfilms import SnagFilmsEmbedIE
55 from .screenwavemedia import ScreenwaveMediaIE
56 from .mtv import MTVServicesEmbeddedIE
59 class GenericIE(InfoExtractor):
60 IE_DESC = 'Generic downloader that works on some sites'
64 # Direct link to a video
66 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
67 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
72 'upload_date': '20100513',
75 # Direct link to media delivered compressed (until Accept-Encoding is *)
77 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
78 'md5': '128c42e68b13950268b648275386fc74',
80 'id': 'FictionJunction-Parallel_Hearts',
82 'title': 'FictionJunction-Parallel_Hearts',
83 'upload_date': '20140522',
85 'expected_warnings': [
86 'URL could be a direct video link, returning it as such.'
89 # Direct download with broken HEAD
91 'url': 'http://ai-radio.org:8000/radio.opus',
98 'skip_download': True, # infinite live stream
100 'expected_warnings': [
101 r'501.*Not Implemented'
104 # Direct link with incorrect MIME type
106 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
107 'md5': '4ccbebe5f36706d85221f204d7eb5913',
109 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
110 'id': '5_Lennart_Poettering_-_Systemd',
112 'title': '5_Lennart_Poettering_-_Systemd',
113 'upload_date': '20141120',
115 'expected_warnings': [
116 'URL could be a direct video link, returning it as such.'
121 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
123 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
124 'title': 'Zero Punctuation',
125 'description': 're:.*groundbreaking video review series.*'
127 'playlist_mincount': 11,
129 # RSS feed with enclosure
131 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
133 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
135 'upload_date': '20150228',
136 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
139 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
141 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
145 'title': 'Automatics, robotics and biocybernetics',
146 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
147 'upload_date': '20130627',
148 'formats': 'mincount:16',
149 'subtitles': 'mincount:1',
152 'force_generic_extractor': True,
153 'skip_download': True,
156 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
158 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
163 'formats': 'mincount:1',
166 'skip_download': True,
169 # SMIL from https://www.restudy.dk/video/play/id/1637
171 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
175 'title': 'video_1637',
176 'formats': 'mincount:3',
179 'skip_download': True,
182 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
184 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
186 'id': 'smil-service',
188 'title': 'smil-service',
189 'formats': 'mincount:1',
192 'skip_download': True,
195 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
197 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
201 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
202 'formats': 'mincount:3',
205 'skip_download': True,
208 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
210 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
212 'id': 'mZlp2ctYIUEB',
214 'title': 'Tikibad ontruimd wegens brand',
215 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
216 'thumbnail': 're:^https?://.*\.jpg$',
220 'skip_download': True,
225 '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',
229 'upload_date': '20130224',
230 'uploader_id': 'TheVerge',
231 'description': 're:^Chris Ziegler takes a look at the\.*',
232 'uploader': 'The Verge',
233 'title': 'First Firefox OS phones side-by-side',
236 'skip_download': False,
240 # redirect in Refresh HTTP header
241 'url': 'https://www.facebook.com/l.php?u=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DpO8h3EaFRdo&h=TAQHsoToz&enc=AZN16h-b6o4Zq9pZkCCdOLNKMN96BbGMNtcFwHSaazus4JHT_MFYkAA-WARTX2kvsCIdlAIyHZjl6d33ILIJU7Jzwk_K3mcenAXoAzBNoZDI_Q7EXGDJnIhrGkLXo_LJ_pAa2Jzbx17UHMd3jAs--6j2zaeto5w9RTn8T_1kKg3fdC5WPX9Dbb18vzH7YFX0eSJmoa6SP114rvlkw6pkS1-T&s=1',
245 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
246 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
247 'upload_date': '20150917',
248 'uploader_id': 'brtvofficial',
249 'uploader': 'Boiler Room',
252 'skip_download': False,
256 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
257 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
259 'id': '13601338388002',
261 'uploader': 'www.hodiho.fr',
262 'title': 'R\u00e9gis plante sa Jeep',
265 # bandcamp page with custom domain
267 'add_ie': ['Bandcamp'],
268 'url': 'http://bronyrock.com/track/the-pony-mash',
272 'title': 'The Pony Mash',
273 'uploader': 'M_Pallante',
275 'skip': 'There is a limit of 200 free downloads / month for the test song',
277 # embedded brightcove video
278 # it also tests brightcove videos that need to set the 'Referer' in the
281 'add_ie': ['BrightcoveLegacy'],
282 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
284 'id': '2765128793001',
286 'title': 'Le cours de bourse : l’analyse technique',
287 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
288 'uploader': 'BFM BUSINESS',
291 'skip_download': True,
295 # https://github.com/rg3/youtube-dl/issues/2253
296 'url': 'http://bcove.me/i6nfkrc3',
297 'md5': '0ba9446db037002366bab3b3eb30c88c',
299 'id': '3101154703001',
301 'title': 'Still no power',
302 'uploader': 'thestar.com',
303 '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.',
305 'add_ie': ['BrightcoveLegacy'],
308 'url': 'http://www.championat.com/video/football/v/87/87499.html',
309 'md5': 'fb973ecf6e4a78a67453647444222983',
311 'id': '3414141473001',
313 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
314 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
315 'uploader': 'Championat',
319 # https://github.com/rg3/youtube-dl/issues/3541
320 'add_ie': ['BrightcoveLegacy'],
321 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
323 'id': '3866516442001',
325 'title': 'Leer mij vrouwen kennen: Aflevering 1',
326 'description': 'Leer mij vrouwen kennen: Aflevering 1',
327 'uploader': 'SBS Broadcasting',
329 'skip': 'Restricted to Netherlands',
331 'skip_download': True, # m3u8 download
336 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
337 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
339 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
341 'title': '2cc213299525360.mov', # that's what we get
343 'add_ie': ['Ooyala'],
346 # ooyala video embedded with http://player.ooyala.com/iframe.js
347 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
349 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
351 'title': '"Steve Jobs: Man in the Machine" trailer',
352 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
355 'skip_download': True,
358 # multiple ooyala embeds on SBN network websites
360 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
362 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
363 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
365 'playlist_mincount': 3,
367 'skip_download': True,
369 'add_ie': ['Ooyala'],
373 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
377 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
378 'upload_date': '20140225',
379 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
380 'uploader': 'Tested',
381 'uploader_id': 'testedcom',
383 # No need to test YoutubeIE here
385 'skip_download': True,
390 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
394 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
395 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
400 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
404 'title': 'Охотское море стало целиком российским',
405 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
409 'skip_download': True,
414 '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/',
418 'title': 'Дошкольное воспитание',
423 'url': 'http://www.vestifinance.ru/articles/25753',
426 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
431 'title': 'Госзаказ. День 3',
437 'title': 'Госзаказ. День 2',
443 'title': 'Госзаказ. День 1',
449 'skip_download': True,
454 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
456 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
458 'title': 'Ужастики, русский трейлер (2015)',
459 'thumbnail': 're:^https?://.*\.jpg$',
465 'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
468 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
470 'playlist_mincount': 7,
474 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
475 'md5': '65fdff94098e4a607385a60c5177c638',
479 'title': 'Hidden miracles of the natural world',
480 'uploader': 'Louie Schwartzberg',
481 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
484 # Embeded Ustream video
486 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
487 'md5': '27b99cdb639c9b12a79bca876a073417',
491 'uploader': 'AU SPA: The NSA and Privacy',
492 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
495 # nowvideo embed hidden behind percent encoding
497 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
498 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
500 'id': '06e53103ca9aa',
502 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
503 'description': 'No description',
508 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
509 'md5': '7653032cbb25bf6c80d80f217055fa43',
511 'id': '048195-004_PLUS7-F',
514 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
515 'upload_date': '20140320',
518 'skip_download': 'Requires rtmpdump'
523 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
527 'title': 'Alcaline, le concert avec Calogero',
528 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
529 'upload_date': '20150226',
530 'timestamp': 1424989860,
535 'skip_download': True,
537 'expected_warnings': [
543 'url': 'http://www.wired.com/2014/04/honda-asimo/',
544 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
546 'id': '53501be369702d3275860000',
548 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
553 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
554 'md5': '441aeeb82eb72c422c7f14ec533999cd',
556 'id': 'k2mm4bCdJ6CQ2i7c8o2',
558 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
561 'add_ie': ['Dailymotion'],
565 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
569 'title': 'The NBL Auction 2014',
570 'uploader': 'BADMINTON England',
571 'uploader_id': 'BADMINTONEvents',
572 'upload_date': '20140603',
573 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
575 'add_ie': ['Youtube'],
577 'skip_download': True,
582 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
583 'md5': '35727f82f58c76d996fc188f9755b0d5',
585 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
588 'description': 'Mario\'s life in the fast lane has never looked so good.',
591 # YouTube embed via <data-embed-url="">
593 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
597 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
598 'uploader': 'Gameloft',
599 'uploader_id': 'gameloft',
600 'upload_date': '20140828',
601 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
604 'skip_download': True,
609 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
611 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
613 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
614 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
619 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
621 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
622 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
628 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
633 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
634 'md5': '9d65602bf31c6e20014319c7d07fba27',
636 'id': '5123ea6d5e5a7',
639 'uploader': 'www.handjobhub.com',
640 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
643 # Multiple brightcove videos
644 # https://github.com/rg3/youtube-dl/issues/2283
646 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
648 'id': 'always-never',
649 'title': 'Always / Never - The New Yorker',
653 'extract_flat': False,
654 'skip_download': True,
659 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
660 'md5': '96f09a37e44da40dd083e12d9a683327',
664 'title': 'Ump changes call to ball',
665 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
667 'timestamp': 1401537900,
668 'upload_date': '20140531',
669 'thumbnail': 're:^https?://.*\.jpg$',
674 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
675 'md5': '8788b683c777a5cf25621eaf286d0c23',
679 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
681 'filesize': 182808282,
682 'uploader': 'education-portal.com',
686 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
687 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
691 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
693 'uploader': 'thoughtworks.wistia.com',
698 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
702 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
703 'uploader': 'Sophos Security',
704 'title': 'Chet Chat 171 - Oct 29, 2014',
705 'upload_date': '20141029',
710 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
714 'upload_date': '20141112',
715 'title': 'Rosetta #CometLanding webcast HL 10',
720 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
723 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
725 'playlist_mincount': 2,
729 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
733 'upload_date': '20141126',
734 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
739 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
741 'id': '730m_DandD_1901_512k',
743 'uploader': 'www.abc.net.au',
744 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
747 # embedded viddler video
749 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
753 'uploader': 'deadspin',
754 'title': 'WALL-TO-GORTAT',
755 'timestamp': 1422285291,
756 'upload_date': '20150126',
758 'add_ie': ['Viddler'],
762 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
766 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
767 'description': 'md5:601cb790edd05908957dae8aaa866465',
768 'upload_date': '20150220',
773 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
777 'upload_date': '20150212',
778 'uploader': 'The National Archives UK',
779 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
780 'uploader_id': 'NationalArchives08',
781 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
786 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
787 'playlist_mincount': 5,
789 'id': 'aanslagen-kopenhagen',
790 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
795 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
799 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
804 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
808 'upload_date': '20150226',
809 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
811 'title': 'John Carlson Postgame 2/25/15',
814 # Kaltura embed (different embed code)
816 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
820 'upload_date': '20150127',
821 'uploader_id': 'PremierMedia',
823 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
826 # Eagle.Platform embed (generic URL)
828 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
832 'title': 'Навальный вышел на свободу',
833 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
834 'thumbnail': 're:^https?://.*\.jpg$',
840 # ClipYou (Eagle.Platform) embed (custom URL)
842 'url': 'http://muz-tv.ru/play/7129/',
846 'title': "'O Sole Mio",
847 'thumbnail': 're:^https?://.*\.jpg$',
854 'url': 'http://muz-tv.ru/kinozal/view/7400/',
858 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
859 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
860 'thumbnail': 're:^https?://.*\.jpg$',
867 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
871 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
872 'thumbnail': 're:^https?://.*\.png$',
878 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
879 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
883 'title': 'Facebook Creates "On This Day" | Crunch Report',
888 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
892 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
897 # Crooks and Liars embed
899 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
903 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
904 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
905 'timestamp': 1428207000,
906 'upload_date': '20150405',
907 'uploader': 'Heather',
910 # Crooks and Liars external embed
912 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
914 'id': 'MTE3MjUtMzQ2MzA',
916 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
917 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
918 'timestamp': 1265032391,
919 'upload_date': '20100201',
920 'uploader': 'Heather',
923 # NBC Sports vplayer embed
925 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
927 'id': 'ln7x1qSThw4k',
929 'title': "PFT Live: New leader in the 'new-look' defense",
930 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
935 'url': 'http://www.udn.com/news/story/7314/822787',
936 'md5': 'fd2060e988c326991037b9aff9df21a6',
940 'title': '中一中男師變性 全校師生力挺',
941 'thumbnail': 're:^https?://.*\.jpg$',
946 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
948 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
950 'description': 'VIDEO: Index/Match versus VLOOKUP.',
951 'title': 'This is what separates the Excel masters from the wannabes',
955 'skip_download': True,
958 # Contains a SMIL manifest
960 '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',
964 'title': '+ Football: Lottery Champions League Europe',
965 'uploader': 'www.telewebion.com',
969 'skip_download': True,
972 # Brightcove URL in single quotes
974 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
975 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
977 'id': '4255764656001',
979 'title': 'SN Presents: Russell Martin, World Citizen',
980 '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.',
981 'uploader': 'Rogers Sportsnet',
984 # Dailymotion Cloud video
986 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
987 'md5': '49444254273501a64675a7e68c502681',
989 'id': '5585de919473990de4bee11b',
992 'thumbnail': 're:^https?://.*\.jpe?g$',
997 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1001 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1002 'thumbnail': 're:^https?://.*\.jpe?g$',
1003 'uploader': 'ClickHole',
1004 'uploader_id': 'clickhole',
1009 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1011 'id': '74849a00-85a9-11e1-9660-123139220831',
1013 'title': '#whilewewatch',
1016 # AdobeTVVideo embed
1018 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1019 'md5': '43662b577c018ad707a63766462b1e87',
1023 'title': 'New experience with Acrobat DC',
1024 'description': 'New experience with Acrobat DC',
1025 'duration': 248.667,
1028 # ScreenwaveMedia embed
1030 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1031 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1033 'id': 'cinemasnob-55d26273809dd',
1035 'title': 'cinemasnob',
1038 # BrightcoveInPageEmbed embed
1040 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1042 'id': '4238694884001',
1044 'title': 'Tabletop: Dread, Last Thoughts',
1045 'description': 'Tabletop: Dread, Last Thoughts',
1051 def report_following_redirect(self, new_url):
1052 """Report information extraction."""
1053 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1055 def _extract_rss(self, url, video_id, doc):
1056 playlist_title = doc.find('./channel/title').text
1057 playlist_desc_el = doc.find('./channel/description')
1058 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1061 for it in doc.findall('./channel/item'):
1062 next_url = xpath_text(it, 'link', fatal=False)
1064 enclosure_nodes = it.findall('./enclosure')
1065 for e in enclosure_nodes:
1066 next_url = e.attrib.get('url')
1076 'title': it.find('title').text,
1080 '_type': 'playlist',
1082 'title': playlist_title,
1083 'description': playlist_desc,
1087 def _extract_camtasia(self, url, video_id, webpage):
1088 """ Returns None if no camtasia video can be found. """
1090 camtasia_cfg = self._search_regex(
1091 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1092 webpage, 'camtasia configuration file', default=None)
1093 if camtasia_cfg is None:
1096 title = self._html_search_meta('DC.title', webpage, fatal=True)
1098 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1099 camtasia_cfg = self._download_xml(
1100 camtasia_url, video_id,
1101 note='Downloading camtasia configuration',
1102 errnote='Failed to download camtasia configuration')
1103 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1106 for n in fileset_node.getchildren():
1107 url_n = n.find('./uri')
1112 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1113 'title': '%s - %s' % (title, n.tag),
1114 'url': compat_urlparse.urljoin(url, url_n.text),
1115 'duration': float_or_none(n.find('./duration').text),
1119 '_type': 'playlist',
1124 def _real_extract(self, url):
1125 if url.startswith('//'):
1128 'url': self.http_scheme() + url,
1131 parsed_url = compat_urlparse.urlparse(url)
1132 if not parsed_url.scheme:
1133 default_search = self._downloader.params.get('default_search')
1134 if default_search is None:
1135 default_search = 'fixup_error'
1137 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1139 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1140 return self.url_result('http://' + url)
1141 elif default_search != 'fixup_error':
1142 if default_search == 'auto_warning':
1143 if re.match(r'^(?:url|URL)$', url):
1144 raise ExtractorError(
1145 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1148 self._downloader.report_warning(
1149 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1150 return self.url_result('ytsearch:' + url)
1152 if default_search in ('error', 'fixup_error'):
1153 raise ExtractorError(
1154 '%r is not a valid URL. '
1155 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1156 % (url, url), expected=True)
1158 if ':' not in default_search:
1159 default_search += ':'
1160 return self.url_result(default_search + url)
1162 url, smuggled_data = unsmuggle_url(url)
1163 force_videoid = None
1164 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1165 if smuggled_data and 'force_videoid' in smuggled_data:
1166 force_videoid = smuggled_data['force_videoid']
1167 video_id = force_videoid
1169 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1171 self.to_screen('%s: Requesting header' % video_id)
1173 head_req = HEADRequest(url)
1174 head_response = self._request_webpage(
1176 note=False, errnote='Could not send HEAD request to %s' % url,
1179 if head_response is not False:
1180 # Check for redirect
1181 new_url = head_response.geturl()
1183 self.report_following_redirect(new_url)
1185 new_url = smuggle_url(
1186 new_url, {'force_videoid': force_videoid})
1187 return self.url_result(new_url)
1189 full_response = None
1190 if head_response is False:
1191 request = compat_urllib_request.Request(url)
1192 request.add_header('Accept-Encoding', '*')
1193 full_response = self._request_webpage(request, video_id)
1194 head_response = full_response
1196 # Check for direct link to a video
1197 content_type = head_response.headers.get('Content-Type', '')
1198 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1200 upload_date = unified_strdate(
1201 head_response.headers.get('Last-Modified'))
1204 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1207 'format_id': m.group('format_id'),
1209 'vcodec': 'none' if m.group('type') == 'audio' else None
1211 'upload_date': upload_date,
1214 if not self._downloader.params.get('test', False) and not is_intentional:
1215 force = self._downloader.params.get('force_generic_extractor', False)
1216 self._downloader.report_warning(
1217 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1219 if not full_response:
1220 request = compat_urllib_request.Request(url)
1221 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1222 # making it impossible to download only chunk of the file (yet we need only 512kB to
1223 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1224 # that will always result in downloading the whole file that is not desirable.
1225 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1226 # to accept raw bytes and being able to download only a chunk.
1227 # It may probably better to solve this by checking Content-Type for application/octet-stream
1228 # after HEAD request finishes, but not sure if we can rely on this.
1229 request.add_header('Accept-Encoding', '*')
1230 full_response = self._request_webpage(request, video_id)
1232 # Maybe it's a direct link to a video?
1233 # Be careful not to download the whole thing!
1234 first_bytes = full_response.read(512)
1235 if not is_html(first_bytes):
1236 self._downloader.report_warning(
1237 'URL could be a direct video link, returning it as such.')
1238 upload_date = unified_strdate(
1239 head_response.headers.get('Last-Modified'))
1242 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1245 'upload_date': upload_date,
1248 webpage = self._webpage_read_content(
1249 full_response, url, video_id, prefix=first_bytes)
1251 self.report_extraction(video_id)
1253 # Is it an RSS feed, a SMIL file or a XSPF playlist?
1255 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1256 if doc.tag == 'rss':
1257 return self._extract_rss(url, video_id, doc)
1258 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1259 return self._parse_smil(doc, url, video_id)
1260 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1261 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1262 except compat_xml_parse_error:
1265 # Is it a Camtasia project?
1266 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1267 if camtasia_res is not None:
1270 # Sometimes embedded video player is hidden behind percent encoding
1271 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1272 # Unescaping the whole page allows to handle those cases in a generic way
1273 webpage = compat_urllib_parse_unquote(webpage)
1275 # it's tempting to parse this further, but you would
1276 # have to take into account all the variations like
1277 # Video Title - Site Name
1278 # Site Name | Video Title
1279 # Video Title - Tagline | Site Name
1280 # and so on and so forth; it's just not practical
1281 video_title = self._html_search_regex(
1282 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1285 # Try to detect age limit automatically
1286 age_limit = self._rta_search(webpage)
1287 # And then there are the jokers who advertise that they use RTA,
1288 # but actually don't.
1289 AGE_LIMIT_MARKERS = [
1290 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1292 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1295 # video uploader is domain name
1296 video_uploader = self._search_regex(
1297 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1300 def _playlist_from_matches(matches, getter=None, ie=None):
1302 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1304 return self.playlist_result(
1305 urlrs, playlist_id=video_id, playlist_title=video_title)
1307 # Look for Brightcove Legacy Studio embeds
1308 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1310 self.to_screen('Brightcove video detected.')
1313 'url': smuggle_url(bc_url, {'Referer': url}),
1314 'ie_key': 'BrightcoveLegacy'
1315 } for bc_url in bc_urls]
1318 '_type': 'playlist',
1319 'title': video_title,
1324 # Look for Brightcove New Studio embeds
1325 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1327 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1329 # Look for embedded rtl.nl player
1330 matches = re.findall(
1331 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1334 return _playlist_from_matches(matches, ie='RtlNl')
1336 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1337 if vimeo_url is not None:
1338 return self.url_result(vimeo_url)
1340 vid_me_embed_url = self._search_regex(
1341 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1342 webpage, 'vid.me embed', default=None)
1343 if vid_me_embed_url is not None:
1344 return self.url_result(vid_me_embed_url, 'Vidme')
1346 # Look for embedded YouTube player
1347 matches = re.findall(r'''(?x)
1356 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1360 return _playlist_from_matches(
1361 matches, lambda m: unescapeHTML(m[1]))
1363 # Look for lazyYT YouTube embed
1364 matches = re.findall(
1365 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1367 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1369 # Look for embedded Dailymotion player
1370 matches = re.findall(
1371 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1373 return _playlist_from_matches(
1374 matches, lambda m: unescapeHTML(m[1]))
1376 # Look for embedded Dailymotion playlist player (#3822)
1378 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1380 playlists = re.findall(
1381 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1383 return _playlist_from_matches(
1384 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1386 # Look for embedded Wistia player
1388 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1390 embed_url = self._proto_relative_url(
1391 unescapeHTML(match.group('url')))
1393 '_type': 'url_transparent',
1396 'uploader': video_uploader,
1397 'title': video_title,
1401 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1404 '_type': 'url_transparent',
1405 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1407 'uploader': video_uploader,
1408 'title': video_title,
1409 'id': match.group('id')
1412 # Look for embedded blip.tv player
1413 bliptv_url = BlipTVIE._extract_url(webpage)
1415 return self.url_result(bliptv_url, 'BlipTV')
1417 # Look for SVT player
1418 svt_url = SVTIE._extract_url(webpage)
1420 return self.url_result(svt_url, 'SVT')
1422 # Look for embedded condenast player
1423 matches = re.findall(
1424 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1428 '_type': 'playlist',
1431 'ie_key': 'CondeNast',
1433 } for ma in matches],
1434 'title': video_title,
1438 # Look for Bandcamp pages with custom domain
1439 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1440 if mobj is not None:
1441 burl = unescapeHTML(mobj.group(1))
1442 # Don't set the extractor because it can be a track url or an album
1443 return self.url_result(burl)
1445 # Look for embedded Vevo player
1447 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1448 if mobj is not None:
1449 return self.url_result(mobj.group('url'))
1451 # Look for embedded Viddler player
1453 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1455 if mobj is not None:
1456 return self.url_result(mobj.group('url'))
1458 # Look for NYTimes player
1460 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1462 if mobj is not None:
1463 return self.url_result(mobj.group('url'))
1465 # Look for Libsyn player
1467 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1468 if mobj is not None:
1469 return self.url_result(mobj.group('url'))
1471 # Look for Ooyala videos
1472 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1473 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1474 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1475 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1476 if mobj is not None:
1477 return OoyalaIE._build_url_result(mobj.group('ec'))
1479 # Look for multiple Ooyala embeds on SBN network websites
1480 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1481 if mobj is not None:
1482 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1484 return _playlist_from_matches(
1485 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1487 # Look for Aparat videos
1488 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1489 if mobj is not None:
1490 return self.url_result(mobj.group(1), 'Aparat')
1492 # Look for MPORA videos
1493 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1494 if mobj is not None:
1495 return self.url_result(mobj.group(1), 'Mpora')
1497 # Look for embedded NovaMov-based player
1499 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1500 (?P<url>http://(?:(?:embed|www)\.)?
1502 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1503 videoweed\.(?:es|com)|
1504 movshare\.(?:net|sx|ag)|
1505 divxstage\.(?:eu|net|ch|co|at|ag))
1506 /embed\.php.+?)\1''', webpage)
1507 if mobj is not None:
1508 return self.url_result(mobj.group('url'))
1510 # Look for embedded Facebook player
1512 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1513 if mobj is not None:
1514 return self.url_result(mobj.group('url'), 'Facebook')
1516 # Look for embedded VK player
1517 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1518 if mobj is not None:
1519 return self.url_result(mobj.group('url'), 'VK')
1521 # Look for embedded ivi player
1522 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1523 if mobj is not None:
1524 return self.url_result(mobj.group('url'), 'Ivi')
1526 # Look for embedded Huffington Post player
1528 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1529 if mobj is not None:
1530 return self.url_result(mobj.group('url'), 'HuffPost')
1533 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1534 if mobj is not None:
1535 return self.url_result(mobj.group('url'))
1536 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1537 if mobj is not None:
1538 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1540 # Look for funnyordie embed
1541 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1543 return _playlist_from_matches(
1544 matches, getter=unescapeHTML, ie='FunnyOrDie')
1546 # Look for BBC iPlayer embed
1547 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1549 return _playlist_from_matches(matches, ie='BBCCoUk')
1551 # Look for embedded RUTV player
1552 rutv_url = RUTVIE._extract_url(webpage)
1554 return self.url_result(rutv_url, 'RUTV')
1556 # Look for embedded TVC player
1557 tvc_url = TVCIE._extract_url(webpage)
1559 return self.url_result(tvc_url, 'TVC')
1561 # Look for embedded SportBox player
1562 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1564 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1566 # Look for embedded PornHub player
1567 pornhub_url = PornHubIE._extract_url(webpage)
1569 return self.url_result(pornhub_url, 'PornHub')
1571 # Look for embedded XHamster player
1572 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1574 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1576 # Look for embedded Tvigle player
1578 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1579 if mobj is not None:
1580 return self.url_result(mobj.group('url'), 'Tvigle')
1582 # Look for embedded TED player
1584 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1585 if mobj is not None:
1586 return self.url_result(mobj.group('url'), 'TED')
1588 # Look for embedded Ustream videos
1590 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1591 if mobj is not None:
1592 return self.url_result(mobj.group('url'), 'Ustream')
1594 # Look for embedded arte.tv player
1596 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1598 if mobj is not None:
1599 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1601 # Look for embedded francetv player
1603 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1605 if mobj is not None:
1606 return self.url_result(mobj.group('url'))
1608 # Look for embedded smotri.com player
1609 smotri_url = SmotriIE._extract_url(webpage)
1611 return self.url_result(smotri_url, 'Smotri')
1613 # Look for embedded Myvi.ru player
1614 myvi_url = MyviIE._extract_url(webpage)
1616 return self.url_result(myvi_url)
1618 # Look for embeded soundcloud player
1620 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1622 if mobj is not None:
1623 url = unescapeHTML(mobj.group('url'))
1624 return self.url_result(url)
1626 # Look for embedded vulture.com player
1628 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1630 if mobj is not None:
1631 url = unescapeHTML(mobj.group('url'))
1632 return self.url_result(url, ie='Vulture')
1634 # Look for embedded mtvservices player
1635 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1637 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1639 # Look for embedded yahoo player
1641 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1643 if mobj is not None:
1644 return self.url_result(mobj.group('url'), 'Yahoo')
1646 # Look for embedded sbs.com.au player
1650 <meta\s+property="og:video"\s+content=|
1653 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1655 if mobj is not None:
1656 return self.url_result(mobj.group('url'), 'SBS')
1658 # Look for embedded Cinchcast player
1660 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1662 if mobj is not None:
1663 return self.url_result(mobj.group('url'), 'Cinchcast')
1666 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1670 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1672 if mobj is not None:
1673 return self.url_result(mobj.group('url'), 'MLB')
1676 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1678 if mobj is not None:
1679 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1682 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1684 if mobj is not None:
1685 return self.url_result(mobj.group('url'), 'Livestream')
1687 # Look for Zapiks embed
1689 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1690 if mobj is not None:
1691 return self.url_result(mobj.group('url'), 'Zapiks')
1693 # Look for Kaltura embeds
1694 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1695 re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
1696 if mobj is not None:
1697 return self.url_result(smuggle_url(
1698 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1699 {'source_url': url}), 'Kaltura')
1701 # Look for Eagle.Platform embeds
1703 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1704 if mobj is not None:
1705 return self.url_result(mobj.group('url'), 'EaglePlatform')
1707 # Look for ClipYou (uses Eagle.Platform) embeds
1709 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1710 if mobj is not None:
1711 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1713 # Look for Pladform embeds
1715 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1716 if mobj is not None:
1717 return self.url_result(mobj.group('url'), 'Pladform')
1719 # Look for Playwire embeds
1721 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1722 if mobj is not None:
1723 return self.url_result(mobj.group('url'))
1725 # Look for 5min embeds
1727 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1728 if mobj is not None:
1729 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1731 # Look for Crooks and Liars embeds
1733 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1734 if mobj is not None:
1735 return self.url_result(mobj.group('url'))
1737 # Look for NBC Sports VPlayer embeds
1738 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1740 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1742 # Look for UDN embeds
1744 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1745 if mobj is not None:
1746 return self.url_result(
1747 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1749 # Look for Senate ISVP iframe
1750 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1752 return self.url_result(senate_isvp_url, 'SenateISVP')
1754 # Look for Dailymotion Cloud videos
1755 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1757 return self.url_result(dmcloud_url, 'DailymotionCloud')
1759 # Look for OnionStudios embeds
1760 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1761 if onionstudios_url:
1762 return self.url_result(onionstudios_url)
1764 # Look for SnagFilms embeds
1765 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1767 return self.url_result(snagfilms_url)
1769 # Look for ScreenwaveMedia embeds
1770 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1771 if mobj is not None:
1772 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1774 # Look for AdobeTVVideo embeds
1776 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1778 if mobj is not None:
1779 return self.url_result(
1780 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1783 def check_video(vurl):
1784 if YoutubeIE.suitable(vurl):
1786 vpath = compat_urlparse.urlparse(vurl).path
1787 vext = determine_ext(vpath)
1788 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1790 def filter_video(urls):
1791 return list(filter(check_video, urls))
1793 # Start with something easy: JW Player in SWFObject
1794 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1796 # Look for gorilla-vid style embedding
1797 found = filter_video(re.findall(r'''(?sx)
1801 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1804 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1806 # Broaden the search a little bit
1807 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1809 # Broaden the findall a little bit: JWPlayer JS loader
1810 found = filter_video(re.findall(
1811 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1814 found = filter_video(re.findall(r'''(?xs)
1815 flowplayer\("[^"]+",\s*
1817 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1818 ["']?url["']?\s*:\s*["']([^"']+)["']
1823 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1825 # Try to find twitter cards info
1826 found = filter_video(re.findall(
1827 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1829 # We look for Open Graph info:
1830 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1831 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1832 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1833 if m_video_type is not None:
1834 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1837 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1839 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1841 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1842 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1845 # Look also in Refresh HTTP header
1846 refresh_header = head_response.headers.get('Refresh')
1848 # In python 2 response HTTP headers are bytestrings
1849 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
1850 refresh_header = refresh_header.decode('iso-8859-1')
1851 found = re.search(REDIRECT_REGEX, refresh_header)
1853 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1854 self.report_following_redirect(new_url)
1860 raise UnsupportedError(url)
1863 for video_url in found:
1864 video_url = compat_urlparse.urljoin(url, video_url)
1865 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1867 # Sometimes, jwplayer extraction will result in a YouTube URL
1868 if YoutubeIE.suitable(video_url):
1869 entries.append(self.url_result(video_url, 'Youtube'))
1872 # here's a fun little line of code for you:
1873 video_id = os.path.splitext(video_id)[0]
1875 ext = determine_ext(video_url)
1879 'formats': self._extract_smil_formats(video_url, video_id),
1880 'uploader': video_uploader,
1881 'title': video_title,
1882 'age_limit': age_limit,
1885 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
1890 'uploader': video_uploader,
1891 'title': video_title,
1892 'age_limit': age_limit,
1895 if len(entries) == 1:
1898 for num, e in enumerate(entries, start=1):
1899 # 'url' results don't have a title
1900 if e.get('title') is not None:
1901 e['title'] = '%s (%d)' % (e['title'], num)
1903 '_type': 'playlist',