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,
15 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 .svt import SVTIE
48 from .pornhub import PornHubIE
49 from .xhamster import XHamsterEmbedIE
50 from .tnaflix import TNAFlixNetworkEmbedIE
51 from .vimeo import VimeoIE
52 from .dailymotion import DailymotionCloudIE
53 from .onionstudios import OnionStudiosIE
54 from .viewlift import ViewLiftEmbedIE
55 from .screenwavemedia import ScreenwaveMediaIE
56 from .mtv import MTVServicesEmbeddedIE
57 from .pladform import PladformIE
58 from .videomore import VideomoreIE
59 from .googledrive import GoogleDriveIE
60 from .jwplatform import JWPlatformIE
61 from .digiteka import DigitekaIE
62 from .instagram import InstagramIE
63 from .liveleak import LiveLeakIE
64 from .threeqsdn import ThreeQSDNIE
67 class GenericIE(InfoExtractor):
68 IE_DESC = 'Generic downloader that works on some sites'
72 # Direct link to a video
74 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
75 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
80 'upload_date': '20100513',
83 # Direct link to media delivered compressed (until Accept-Encoding is *)
85 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
86 'md5': '128c42e68b13950268b648275386fc74',
88 'id': 'FictionJunction-Parallel_Hearts',
90 'title': 'FictionJunction-Parallel_Hearts',
91 'upload_date': '20140522',
93 'expected_warnings': [
94 'URL could be a direct video link, returning it as such.'
97 # Direct download with broken HEAD
99 'url': 'http://ai-radio.org:8000/radio.opus',
106 'skip_download': True, # infinite live stream
108 'expected_warnings': [
109 r'501.*Not Implemented',
113 # Direct link with incorrect MIME type
115 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
116 'md5': '4ccbebe5f36706d85221f204d7eb5913',
118 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
119 'id': '5_Lennart_Poettering_-_Systemd',
121 'title': '5_Lennart_Poettering_-_Systemd',
122 'upload_date': '20141120',
124 'expected_warnings': [
125 'URL could be a direct video link, returning it as such.'
130 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
132 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
133 'title': 'Zero Punctuation',
134 'description': 're:.*groundbreaking video review series.*'
136 'playlist_mincount': 11,
138 # RSS feed with enclosure
140 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
142 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
144 'upload_date': '20150228',
145 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
148 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
150 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
154 'title': 'Automatics, robotics and biocybernetics',
155 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
156 'upload_date': '20130627',
157 'formats': 'mincount:16',
158 'subtitles': 'mincount:1',
161 'force_generic_extractor': True,
162 'skip_download': True,
165 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
167 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
172 'formats': 'mincount:1',
175 'skip_download': True,
178 # SMIL from https://www.restudy.dk/video/play/id/1637
180 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
184 'title': 'video_1637',
185 'formats': 'mincount:3',
188 'skip_download': True,
191 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
193 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
195 'id': 'smil-service',
197 'title': 'smil-service',
198 'formats': 'mincount:1',
201 'skip_download': True,
204 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
206 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
210 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
211 'formats': 'mincount:3',
214 'skip_download': True,
217 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
219 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
221 'id': 'mZlp2ctYIUEB',
223 'title': 'Tikibad ontruimd wegens brand',
224 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
225 'thumbnail': 're:^https?://.*\.jpg$',
229 'skip_download': True,
232 # MPD from http://dash-mse-test.appspot.com/media.html
234 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
235 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
237 'id': 'car-20120827-manifest',
239 'title': 'car-20120827-manifest',
240 'formats': 'mincount:9',
241 'upload_date': '20130904',
244 'format': 'bestvideo',
247 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
249 'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
254 'formats': 'mincount:8',
258 'skip_download': True,
261 # m3u8 served with Content-Type: text/plain
263 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
268 'upload_date': '20140720',
269 'formats': 'mincount:11',
273 'skip_download': True,
278 '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',
282 'upload_date': '20130224',
283 'uploader_id': 'TheVerge',
284 'description': 're:^Chris Ziegler takes a look at the\.*',
285 'uploader': 'The Verge',
286 'title': 'First Firefox OS phones side-by-side',
289 'skip_download': False,
293 # redirect in Refresh HTTP header
294 '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',
298 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
299 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
300 'upload_date': '20150917',
301 'uploader_id': 'brtvofficial',
302 'uploader': 'Boiler Room',
305 'skip_download': False,
309 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
310 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
312 'id': '13601338388002',
314 'uploader': 'www.hodiho.fr',
315 'title': 'R\u00e9gis plante sa Jeep',
318 # bandcamp page with custom domain
320 'add_ie': ['Bandcamp'],
321 'url': 'http://bronyrock.com/track/the-pony-mash',
325 'title': 'The Pony Mash',
326 'uploader': 'M_Pallante',
328 'skip': 'There is a limit of 200 free downloads / month for the test song',
330 # embedded brightcove video
331 # it also tests brightcove videos that need to set the 'Referer' in the
334 'add_ie': ['BrightcoveLegacy'],
335 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
337 'id': '2765128793001',
339 'title': 'Le cours de bourse : l’analyse technique',
340 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
341 'uploader': 'BFM BUSINESS',
344 'skip_download': True,
348 # https://github.com/rg3/youtube-dl/issues/2253
349 'url': 'http://bcove.me/i6nfkrc3',
350 'md5': '0ba9446db037002366bab3b3eb30c88c',
352 'id': '3101154703001',
354 'title': 'Still no power',
355 'uploader': 'thestar.com',
356 '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.',
358 'add_ie': ['BrightcoveLegacy'],
361 'url': 'http://www.championat.com/video/football/v/87/87499.html',
362 'md5': 'fb973ecf6e4a78a67453647444222983',
364 'id': '3414141473001',
366 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
367 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
368 'uploader': 'Championat',
372 # https://github.com/rg3/youtube-dl/issues/3541
373 'add_ie': ['BrightcoveLegacy'],
374 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
376 'id': '3866516442001',
378 'title': 'Leer mij vrouwen kennen: Aflevering 1',
379 'description': 'Leer mij vrouwen kennen: Aflevering 1',
380 'uploader': 'SBS Broadcasting',
382 'skip': 'Restricted to Netherlands',
384 'skip_download': True, # m3u8 download
389 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
390 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
392 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
394 'title': '2cc213299525360.mov', # that's what we get
397 'add_ie': ['Ooyala'],
400 # ooyala video embedded with http://player.ooyala.com/iframe.js
401 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
403 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
405 'title': '"Steve Jobs: Man in the Machine" trailer',
406 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
410 'skip_download': True,
415 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
419 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
420 'upload_date': '20140225',
421 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
422 'uploader': 'Tested',
423 'uploader_id': 'testedcom',
425 # No need to test YoutubeIE here
427 'skip_download': True,
432 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
436 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
437 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
442 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
446 'title': 'Охотское море стало целиком российским',
447 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
451 'skip_download': True,
456 '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/',
460 'title': 'Дошкольное воспитание',
465 'url': 'http://www.vestifinance.ru/articles/25753',
468 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
473 'title': 'Госзаказ. День 3',
479 'title': 'Госзаказ. День 2',
485 'title': 'Госзаказ. День 1',
491 'skip_download': True,
496 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
498 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
500 'title': 'Ужастики, русский трейлер (2015)',
501 'thumbnail': 're:^https?://.*\.jpg$',
507 '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',
510 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
512 'playlist_mincount': 7,
516 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
517 'md5': '65fdff94098e4a607385a60c5177c638',
521 'title': 'Hidden miracles of the natural world',
522 'uploader': 'Louie Schwartzberg',
523 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
526 # Embedded Ustream video
528 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
529 'md5': '27b99cdb639c9b12a79bca876a073417',
533 'uploader': 'AU SPA: The NSA and Privacy',
534 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
537 # nowvideo embed hidden behind percent encoding
539 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
540 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
542 'id': '06e53103ca9aa',
544 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
545 'description': 'No description',
550 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
551 'md5': '7653032cbb25bf6c80d80f217055fa43',
553 'id': '048195-004_PLUS7-F',
556 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
557 'upload_date': '20140320',
560 'skip_download': 'Requires rtmpdump'
565 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
569 'title': 'Alcaline, le concert avec Calogero',
570 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
571 'upload_date': '20150226',
572 'timestamp': 1424989860,
577 'skip_download': True,
579 'expected_warnings': [
585 'url': 'http://www.wired.com/2014/04/honda-asimo/',
586 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
588 'id': '53501be369702d3275860000',
590 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
595 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
596 'md5': '441aeeb82eb72c422c7f14ec533999cd',
598 'id': 'k2mm4bCdJ6CQ2i7c8o2',
600 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
601 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
603 'uploader_id': 'xgditw',
604 'upload_date': '20140425',
605 'timestamp': 1398441542,
607 'add_ie': ['Dailymotion'],
611 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
615 'title': 'The NBL Auction 2014',
616 'uploader': 'BADMINTON England',
617 'uploader_id': 'BADMINTONEvents',
618 'upload_date': '20140603',
619 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
621 'add_ie': ['Youtube'],
623 'skip_download': True,
628 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
629 'md5': '35727f82f58c76d996fc188f9755b0d5',
631 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
634 'description': 'Mario\'s life in the fast lane has never looked so good.',
637 # YouTube embed via <data-embed-url="">
639 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
643 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
644 'uploader': 'Gameloft',
645 'uploader_id': 'gameloft',
646 'upload_date': '20140828',
647 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
650 'skip_download': True,
655 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
657 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
659 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
660 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
665 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
667 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
668 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
674 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
679 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
680 'md5': '9d65602bf31c6e20014319c7d07fba27',
682 'id': '5123ea6d5e5a7',
685 'uploader': 'www.handjobhub.com',
686 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
689 # Multiple brightcove videos
690 # https://github.com/rg3/youtube-dl/issues/2283
692 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
694 'id': 'always-never',
695 'title': 'Always / Never - The New Yorker',
699 'extract_flat': False,
700 'skip_download': True,
705 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
706 'md5': '96f09a37e44da40dd083e12d9a683327',
710 'title': 'Ump changes call to ball',
711 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
713 'timestamp': 1401537900,
714 'upload_date': '20140531',
715 'thumbnail': 're:^https?://.*\.jpg$',
720 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
721 'md5': '8788b683c777a5cf25621eaf286d0c23',
725 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
727 'filesize': 182808282,
728 'uploader': 'education-portal.com',
732 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
733 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
737 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
738 'description': 'a Martin Fowler video from ThoughtWorks',
740 'uploader': 'thoughtworks.wistia.com',
741 'upload_date': '20140603',
742 'timestamp': 1401832161,
747 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
751 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
752 'uploader': 'Sophos Security',
753 'title': 'Chet Chat 171 - Oct 29, 2014',
754 'upload_date': '20141029',
759 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
763 'upload_date': '20141112',
764 'title': 'Rosetta #CometLanding webcast HL 10',
769 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
772 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
774 'playlist_mincount': 2,
778 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
782 'upload_date': '20141126',
783 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
788 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
790 'id': '730m_DandD_1901_512k',
792 'uploader': 'www.abc.net.au',
793 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
796 # embedded viddler video
798 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
802 'uploader': 'deadspin',
803 'title': 'WALL-TO-GORTAT',
804 'timestamp': 1422285291,
805 'upload_date': '20150126',
807 'add_ie': ['Viddler'],
811 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
815 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
816 'description': 'md5:601cb790edd05908957dae8aaa866465',
817 'upload_date': '20150220',
822 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
826 'upload_date': '20150212',
827 'uploader': 'The National Archives UK',
828 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
829 'uploader_id': 'NationalArchives08',
830 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
835 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
836 'playlist_mincount': 5,
838 'id': 'aanslagen-kopenhagen',
839 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
844 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
848 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
853 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
857 'upload_date': '20150226',
858 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
860 'title': 'John Carlson Postgame 2/25/15',
863 # Kaltura embed (different embed code)
865 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
869 'upload_date': '20150127',
870 'uploader_id': 'PremierMedia',
872 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
875 # Kaltura embed protected with referrer
877 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
881 'title': 'Violetta - Achter De Schermen - Ruggero',
882 'description': 'Achter de schermen met Ruggero',
883 'timestamp': 1435133761,
884 'upload_date': '20150624',
885 'uploader_id': 'echojecka',
888 # Eagle.Platform embed (generic URL)
890 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
891 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
895 'title': 'Навальный вышел на свободу',
896 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
897 'thumbnail': 're:^https?://.*\.jpg$',
903 # ClipYou (Eagle.Platform) embed (custom URL)
905 'url': 'http://muz-tv.ru/play/7129/',
906 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
910 'title': "'O Sole Mio",
911 'thumbnail': 're:^https?://.*\.jpg$',
918 'url': 'http://muz-tv.ru/kinozal/view/7400/',
922 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
923 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
924 'thumbnail': 're:^https?://.*\.jpg$',
931 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
935 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
936 'thumbnail': 're:^https?://.*\.png$',
942 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
943 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
947 'title': 'Facebook Creates "On This Day" | Crunch Report',
952 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
956 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
961 # Crooks and Liars embed
963 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
967 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
968 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
969 'timestamp': 1428207000,
970 'upload_date': '20150405',
971 'uploader': 'Heather',
974 # Crooks and Liars external embed
976 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
978 'id': 'MTE3MjUtMzQ2MzA',
980 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
981 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
982 'timestamp': 1265032391,
983 'upload_date': '20100201',
984 'uploader': 'Heather',
987 # NBC Sports vplayer embed
989 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
991 'id': 'ln7x1qSThw4k',
993 'title': "PFT Live: New leader in the 'new-look' defense",
994 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
995 'uploader': 'NBCU-SPORTS',
996 'upload_date': '20140107',
997 'timestamp': 1389118457,
1002 'url': 'http://www.udn.com/news/story/7314/822787',
1003 'md5': 'fd2060e988c326991037b9aff9df21a6',
1007 'title': '中一中男師變性 全校師生力挺',
1008 'thumbnail': 're:^https?://.*\.jpg$',
1013 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1015 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1017 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1018 'title': 'This is what separates the Excel masters from the wannabes',
1019 'duration': 191.933,
1023 'skip_download': True,
1026 # Contains a SMIL manifest
1028 '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',
1032 'title': '+ Football: Lottery Champions League Europe',
1033 'uploader': 'www.telewebion.com',
1037 'skip_download': True,
1040 # Brightcove URL in single quotes
1042 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1043 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1045 'id': '4255764656001',
1047 'title': 'SN Presents: Russell Martin, World Citizen',
1048 '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.',
1049 'uploader': 'Rogers Sportsnet',
1050 'uploader_id': '1704050871',
1051 'upload_date': '20150525',
1052 'timestamp': 1432570283,
1055 # Dailymotion Cloud video
1057 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1058 'md5': '49444254273501a64675a7e68c502681',
1060 'id': '5585de919473990de4bee11b',
1062 'title': 'Le débat',
1063 'thumbnail': 're:^https?://.*\.jpe?g$',
1066 # OnionStudios embed
1068 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1072 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1073 'thumbnail': 're:^https?://.*\.jpe?g$',
1074 'uploader': 'ClickHole',
1075 'uploader_id': 'clickhole',
1080 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1082 'id': '74849a00-85a9-11e1-9660-123139220831',
1084 'title': '#whilewewatch',
1087 # AdobeTVVideo embed
1089 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1090 'md5': '43662b577c018ad707a63766462b1e87',
1094 'title': 'New experience with Acrobat DC',
1095 'description': 'New experience with Acrobat DC',
1096 'duration': 248.667,
1099 # ScreenwaveMedia embed
1101 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1102 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1104 'id': 'cinemasnob-55d26273809dd',
1106 'title': 'cinemasnob',
1109 # BrightcoveInPageEmbed embed
1111 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1113 'id': '4238694884001',
1115 'title': 'Tabletop: Dread, Last Thoughts',
1116 'description': 'Tabletop: Dread, Last Thoughts',
1120 # JWPlayer with M3U8
1122 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1126 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1127 'uploader': 'ren.tv',
1131 'skip_download': True,
1134 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1135 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1137 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1139 'id': '4785848093001',
1141 'title': 'The Cardinal Pell Interview',
1142 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1143 'uploader': 'GlobeCast Australia - GlobeStream',
1144 'uploader_id': '2733773828001',
1145 'upload_date': '20160304',
1146 'timestamp': 1457083087,
1150 'skip_download': True,
1153 # Another form of arte.tv embed
1155 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1156 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1158 'id': '030273-562_PLUS7-F',
1160 'title': 'ARTE Reportage - Nulle part, en France',
1161 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1162 'upload_date': '20160409',
1167 'url': 'http://www.wykop.pl/link/3088787/',
1168 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1170 'id': '874_1459135191',
1172 'title': 'Man shows poor quality of new apartment building',
1173 'description': 'The wall is like a sand pile.',
1174 'uploader': 'Lake8737',
1179 def report_following_redirect(self, new_url):
1180 """Report information extraction."""
1181 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1183 def _extract_rss(self, url, video_id, doc):
1184 playlist_title = doc.find('./channel/title').text
1185 playlist_desc_el = doc.find('./channel/description')
1186 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1189 for it in doc.findall('./channel/item'):
1190 next_url = xpath_text(it, 'link', fatal=False)
1192 enclosure_nodes = it.findall('./enclosure')
1193 for e in enclosure_nodes:
1194 next_url = e.attrib.get('url')
1204 'title': it.find('title').text,
1208 '_type': 'playlist',
1210 'title': playlist_title,
1211 'description': playlist_desc,
1215 def _extract_camtasia(self, url, video_id, webpage):
1216 """ Returns None if no camtasia video can be found. """
1218 camtasia_cfg = self._search_regex(
1219 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1220 webpage, 'camtasia configuration file', default=None)
1221 if camtasia_cfg is None:
1224 title = self._html_search_meta('DC.title', webpage, fatal=True)
1226 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1227 camtasia_cfg = self._download_xml(
1228 camtasia_url, video_id,
1229 note='Downloading camtasia configuration',
1230 errnote='Failed to download camtasia configuration')
1231 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1234 for n in fileset_node.getchildren():
1235 url_n = n.find('./uri')
1240 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1241 'title': '%s - %s' % (title, n.tag),
1242 'url': compat_urlparse.urljoin(url, url_n.text),
1243 'duration': float_or_none(n.find('./duration').text),
1247 '_type': 'playlist',
1252 def _real_extract(self, url):
1253 if url.startswith('//'):
1256 'url': self.http_scheme() + url,
1259 parsed_url = compat_urlparse.urlparse(url)
1260 if not parsed_url.scheme:
1261 default_search = self._downloader.params.get('default_search')
1262 if default_search is None:
1263 default_search = 'fixup_error'
1265 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1267 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1268 return self.url_result('http://' + url)
1269 elif default_search != 'fixup_error':
1270 if default_search == 'auto_warning':
1271 if re.match(r'^(?:url|URL)$', url):
1272 raise ExtractorError(
1273 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1276 self._downloader.report_warning(
1277 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1278 return self.url_result('ytsearch:' + url)
1280 if default_search in ('error', 'fixup_error'):
1281 raise ExtractorError(
1282 '%r is not a valid URL. '
1283 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1284 % (url, url), expected=True)
1286 if ':' not in default_search:
1287 default_search += ':'
1288 return self.url_result(default_search + url)
1290 url, smuggled_data = unsmuggle_url(url)
1291 force_videoid = None
1292 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1293 if smuggled_data and 'force_videoid' in smuggled_data:
1294 force_videoid = smuggled_data['force_videoid']
1295 video_id = force_videoid
1297 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1299 self.to_screen('%s: Requesting header' % video_id)
1301 head_req = HEADRequest(url)
1302 head_response = self._request_webpage(
1304 note=False, errnote='Could not send HEAD request to %s' % url,
1307 if head_response is not False:
1308 # Check for redirect
1309 new_url = head_response.geturl()
1311 self.report_following_redirect(new_url)
1313 new_url = smuggle_url(
1314 new_url, {'force_videoid': force_videoid})
1315 return self.url_result(new_url)
1317 full_response = None
1318 if head_response is False:
1319 request = sanitized_Request(url)
1320 request.add_header('Accept-Encoding', '*')
1321 full_response = self._request_webpage(request, video_id)
1322 head_response = full_response
1326 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1327 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1330 # Check for direct link to a video
1331 content_type = head_response.headers.get('Content-Type', '').lower()
1332 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1334 format_id = m.group('format_id')
1335 if format_id.endswith('mpegurl'):
1336 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1337 elif format_id == 'f4m':
1338 formats = self._extract_f4m_formats(url, video_id)
1341 'format_id': m.group('format_id'),
1343 'vcodec': 'none' if m.group('type') == 'audio' else None
1345 info_dict['direct'] = True
1346 self._sort_formats(formats)
1347 info_dict['formats'] = formats
1350 if not self._downloader.params.get('test', False) and not is_intentional:
1351 force = self._downloader.params.get('force_generic_extractor', False)
1352 self._downloader.report_warning(
1353 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1355 if not full_response:
1356 request = sanitized_Request(url)
1357 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1358 # making it impossible to download only chunk of the file (yet we need only 512kB to
1359 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1360 # that will always result in downloading the whole file that is not desirable.
1361 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1362 # to accept raw bytes and being able to download only a chunk.
1363 # It may probably better to solve this by checking Content-Type for application/octet-stream
1364 # after HEAD request finishes, but not sure if we can rely on this.
1365 request.add_header('Accept-Encoding', '*')
1366 full_response = self._request_webpage(request, video_id)
1368 first_bytes = full_response.read(512)
1370 # Is it an M3U playlist?
1371 if first_bytes.startswith(b'#EXTM3U'):
1372 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1373 self._sort_formats(info_dict['formats'])
1376 # Maybe it's a direct link to a video?
1377 # Be careful not to download the whole thing!
1378 if not is_html(first_bytes):
1379 self._downloader.report_warning(
1380 'URL could be a direct video link, returning it as such.')
1387 webpage = self._webpage_read_content(
1388 full_response, url, video_id, prefix=first_bytes)
1390 self.report_extraction(video_id)
1392 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1394 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1395 if doc.tag == 'rss':
1396 return self._extract_rss(url, video_id, doc)
1397 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1398 smil = self._parse_smil(doc, url, video_id)
1399 self._sort_formats(smil['formats'])
1401 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1402 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1403 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1404 info_dict['formats'] = self._parse_mpd_formats(
1405 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1406 self._sort_formats(info_dict['formats'])
1408 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1409 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1410 self._sort_formats(info_dict['formats'])
1412 except compat_xml_parse_error:
1415 # Is it a Camtasia project?
1416 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1417 if camtasia_res is not None:
1420 # Sometimes embedded video player is hidden behind percent encoding
1421 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1422 # Unescaping the whole page allows to handle those cases in a generic way
1423 webpage = compat_urllib_parse_unquote(webpage)
1425 # it's tempting to parse this further, but you would
1426 # have to take into account all the variations like
1427 # Video Title - Site Name
1428 # Site Name | Video Title
1429 # Video Title - Tagline | Site Name
1430 # and so on and so forth; it's just not practical
1431 video_title = self._og_search_title(
1432 webpage, default=None) or self._html_search_regex(
1433 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1436 # Try to detect age limit automatically
1437 age_limit = self._rta_search(webpage)
1438 # And then there are the jokers who advertise that they use RTA,
1439 # but actually don't.
1440 AGE_LIMIT_MARKERS = [
1441 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1443 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1446 # video uploader is domain name
1447 video_uploader = self._search_regex(
1448 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1450 video_description = self._og_search_description(webpage, default=None)
1451 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1454 def _playlist_from_matches(matches, getter=None, ie=None):
1456 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1458 return self.playlist_result(
1459 urlrs, playlist_id=video_id, playlist_title=video_title)
1461 # Look for Brightcove Legacy Studio embeds
1462 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1464 self.to_screen('Brightcove video detected.')
1467 'url': smuggle_url(bc_url, {'Referer': url}),
1468 'ie_key': 'BrightcoveLegacy'
1469 } for bc_url in bc_urls]
1472 '_type': 'playlist',
1473 'title': video_title,
1478 # Look for Brightcove New Studio embeds
1479 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1481 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1483 # Look for embedded rtl.nl player
1484 matches = re.findall(
1485 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1488 return _playlist_from_matches(matches, ie='RtlNl')
1490 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1491 if vimeo_url is not None:
1492 return self.url_result(vimeo_url)
1494 vid_me_embed_url = self._search_regex(
1495 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1496 webpage, 'vid.me embed', default=None)
1497 if vid_me_embed_url is not None:
1498 return self.url_result(vid_me_embed_url, 'Vidme')
1500 # Look for embedded YouTube player
1501 matches = re.findall(r'''(?x)
1510 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1514 return _playlist_from_matches(
1515 matches, lambda m: unescapeHTML(m[1]))
1517 # Look for lazyYT YouTube embed
1518 matches = re.findall(
1519 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1521 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1523 # Look for embedded Dailymotion player
1524 matches = re.findall(
1525 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1527 return _playlist_from_matches(
1528 matches, lambda m: unescapeHTML(m[1]))
1530 # Look for embedded Dailymotion playlist player (#3822)
1532 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1534 playlists = re.findall(
1535 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1537 return _playlist_from_matches(
1538 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1540 # Look for embedded Wistia player
1542 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1544 embed_url = self._proto_relative_url(
1545 unescapeHTML(match.group('url')))
1547 '_type': 'url_transparent',
1550 'uploader': video_uploader,
1551 'title': video_title,
1555 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1558 '_type': 'url_transparent',
1559 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1561 'uploader': video_uploader,
1562 'title': video_title,
1563 'id': match.group('id')
1566 # Look for SVT player
1567 svt_url = SVTIE._extract_url(webpage)
1569 return self.url_result(svt_url, 'SVT')
1571 # Look for embedded condenast player
1572 matches = re.findall(
1573 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1577 '_type': 'playlist',
1580 'ie_key': 'CondeNast',
1582 } for ma in matches],
1583 'title': video_title,
1587 # Look for Bandcamp pages with custom domain
1588 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1589 if mobj is not None:
1590 burl = unescapeHTML(mobj.group(1))
1591 # Don't set the extractor because it can be a track url or an album
1592 return self.url_result(burl)
1594 # Look for embedded Vevo player
1596 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1597 if mobj is not None:
1598 return self.url_result(mobj.group('url'))
1600 # Look for embedded Viddler player
1602 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1604 if mobj is not None:
1605 return self.url_result(mobj.group('url'))
1607 # Look for NYTimes player
1609 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1611 if mobj is not None:
1612 return self.url_result(mobj.group('url'))
1614 # Look for Libsyn player
1616 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1617 if mobj is not None:
1618 return self.url_result(mobj.group('url'))
1620 # Look for Ooyala videos
1621 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1622 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1623 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1624 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1625 if mobj is not None:
1626 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1628 # Look for multiple Ooyala embeds on SBN network websites
1629 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1630 if mobj is not None:
1631 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1633 return _playlist_from_matches(
1634 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1636 # Look for Aparat videos
1637 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1638 if mobj is not None:
1639 return self.url_result(mobj.group(1), 'Aparat')
1641 # Look for MPORA videos
1642 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1643 if mobj is not None:
1644 return self.url_result(mobj.group(1), 'Mpora')
1646 # Look for embedded NovaMov-based player
1648 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1649 (?P<url>http://(?:(?:embed|www)\.)?
1651 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1652 videoweed\.(?:es|com)|
1653 movshare\.(?:net|sx|ag)|
1654 divxstage\.(?:eu|net|ch|co|at|ag))
1655 /embed\.php.+?)\1''', webpage)
1656 if mobj is not None:
1657 return self.url_result(mobj.group('url'))
1659 # Look for embedded Facebook player
1661 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1662 if mobj is not None:
1663 return self.url_result(mobj.group('url'), 'Facebook')
1665 # Look for embedded VK player
1666 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1667 if mobj is not None:
1668 return self.url_result(mobj.group('url'), 'VK')
1670 # Look for embedded Odnoklassniki player
1671 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1672 if mobj is not None:
1673 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1675 # Look for embedded ivi player
1676 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1677 if mobj is not None:
1678 return self.url_result(mobj.group('url'), 'Ivi')
1680 # Look for embedded Huffington Post player
1682 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1683 if mobj is not None:
1684 return self.url_result(mobj.group('url'), 'HuffPost')
1687 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1688 if mobj is not None:
1689 return self.url_result(mobj.group('url'))
1690 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1691 if mobj is not None:
1692 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1694 # Look for funnyordie embed
1695 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1697 return _playlist_from_matches(
1698 matches, getter=unescapeHTML, ie='FunnyOrDie')
1700 # Look for BBC iPlayer embed
1701 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1703 return _playlist_from_matches(matches, ie='BBCCoUk')
1705 # Look for embedded RUTV player
1706 rutv_url = RUTVIE._extract_url(webpage)
1708 return self.url_result(rutv_url, 'RUTV')
1710 # Look for embedded TVC player
1711 tvc_url = TVCIE._extract_url(webpage)
1713 return self.url_result(tvc_url, 'TVC')
1715 # Look for embedded SportBox player
1716 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1718 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1720 # Look for embedded PornHub player
1721 pornhub_url = PornHubIE._extract_url(webpage)
1723 return self.url_result(pornhub_url, 'PornHub')
1725 # Look for embedded XHamster player
1726 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1728 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1730 # Look for embedded TNAFlixNetwork player
1731 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1733 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1735 # Look for embedded Tvigle player
1737 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1738 if mobj is not None:
1739 return self.url_result(mobj.group('url'), 'Tvigle')
1741 # Look for embedded TED player
1743 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1744 if mobj is not None:
1745 return self.url_result(mobj.group('url'), 'TED')
1747 # Look for embedded Ustream videos
1749 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1750 if mobj is not None:
1751 return self.url_result(mobj.group('url'), 'Ustream')
1753 # Look for embedded arte.tv player
1755 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1757 if mobj is not None:
1758 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1760 # Look for embedded francetv player
1762 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1764 if mobj is not None:
1765 return self.url_result(mobj.group('url'))
1767 # Look for embedded smotri.com player
1768 smotri_url = SmotriIE._extract_url(webpage)
1770 return self.url_result(smotri_url, 'Smotri')
1772 # Look for embedded Myvi.ru player
1773 myvi_url = MyviIE._extract_url(webpage)
1775 return self.url_result(myvi_url)
1777 # Look for embedded soundcloud player
1779 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1781 if mobj is not None:
1782 url = unescapeHTML(mobj.group('url'))
1783 return self.url_result(url)
1785 # Look for embedded vulture.com player
1787 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1789 if mobj is not None:
1790 url = unescapeHTML(mobj.group('url'))
1791 return self.url_result(url, ie='Vulture')
1793 # Look for embedded mtvservices player
1794 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1796 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1798 # Look for embedded yahoo player
1800 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1802 if mobj is not None:
1803 return self.url_result(mobj.group('url'), 'Yahoo')
1805 # Look for embedded sbs.com.au player
1809 <meta\s+property="og:video"\s+content=|
1812 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1814 if mobj is not None:
1815 return self.url_result(mobj.group('url'), 'SBS')
1817 # Look for embedded Cinchcast player
1819 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1821 if mobj is not None:
1822 return self.url_result(mobj.group('url'), 'Cinchcast')
1825 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1829 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1831 if mobj is not None:
1832 return self.url_result(mobj.group('url'), 'MLB')
1835 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1837 if mobj is not None:
1838 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1841 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1843 if mobj is not None:
1844 return self.url_result(mobj.group('url'), 'Livestream')
1846 # Look for Zapiks embed
1848 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1849 if mobj is not None:
1850 return self.url_result(mobj.group('url'), 'Zapiks')
1852 # Look for Kaltura embeds
1853 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1854 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))
1855 if mobj is not None:
1856 return self.url_result(smuggle_url(
1857 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1858 {'source_url': url}), 'Kaltura')
1860 # Look for Eagle.Platform embeds
1862 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1863 if mobj is not None:
1864 return self.url_result(mobj.group('url'), 'EaglePlatform')
1866 # Look for ClipYou (uses Eagle.Platform) embeds
1868 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1869 if mobj is not None:
1870 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1872 # Look for Pladform embeds
1873 pladform_url = PladformIE._extract_url(webpage)
1875 return self.url_result(pladform_url)
1877 # Look for Videomore embeds
1878 videomore_url = VideomoreIE._extract_url(webpage)
1880 return self.url_result(videomore_url)
1882 # Look for Playwire embeds
1884 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1885 if mobj is not None:
1886 return self.url_result(mobj.group('url'))
1888 # Look for 5min embeds
1890 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1891 if mobj is not None:
1892 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1894 # Look for Crooks and Liars embeds
1896 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1897 if mobj is not None:
1898 return self.url_result(mobj.group('url'))
1900 # Look for NBC Sports VPlayer embeds
1901 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1903 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1905 # Look for Google Drive embeds
1906 google_drive_url = GoogleDriveIE._extract_url(webpage)
1907 if google_drive_url:
1908 return self.url_result(google_drive_url, 'GoogleDrive')
1910 # Look for UDN embeds
1912 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1913 if mobj is not None:
1914 return self.url_result(
1915 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1917 # Look for Senate ISVP iframe
1918 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1920 return self.url_result(senate_isvp_url, 'SenateISVP')
1922 # Look for Dailymotion Cloud videos
1923 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1925 return self.url_result(dmcloud_url, 'DailymotionCloud')
1927 # Look for OnionStudios embeds
1928 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1929 if onionstudios_url:
1930 return self.url_result(onionstudios_url)
1932 # Look for ViewLift embeds
1933 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
1935 return self.url_result(viewlift_url)
1937 # Look for JWPlatform embeds
1938 jwplatform_url = JWPlatformIE._extract_url(webpage)
1940 return self.url_result(jwplatform_url, 'JWPlatform')
1942 # Look for ScreenwaveMedia embeds
1943 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1944 if mobj is not None:
1945 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1947 # Look for Digiteka embeds
1948 digiteka_url = DigitekaIE._extract_url(webpage)
1950 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
1952 # Look for Limelight embeds
1953 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
1957 'Channel': 'channel',
1958 'ChannelList': 'channel_list',
1960 return self.url_result('limelight:%s:%s' % (
1961 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
1963 # Look for AdobeTVVideo embeds
1965 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1967 if mobj is not None:
1968 return self.url_result(
1969 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1972 # Look for Vine embeds
1974 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
1976 if mobj is not None:
1977 return self.url_result(
1978 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
1980 # Look for Instagram embeds
1981 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
1982 if instagram_embed_url is not None:
1983 return self.url_result(
1984 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
1986 # Look for LiveLeak embeds
1987 liveleak_url = LiveLeakIE._extract_url(webpage)
1989 return self.url_result(liveleak_url, 'LiveLeak')
1991 # Look for 3Q SDN embeds
1992 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
1995 '_type': 'url_transparent',
1996 'ie_key': ThreeQSDNIE.ie_key(),
1997 'url': self._proto_relative_url(threeqsdn_url),
1998 'title': video_title,
1999 'description': video_description,
2000 'thumbnail': video_thumbnail,
2001 'uploader': video_uploader,
2004 def check_video(vurl):
2005 if YoutubeIE.suitable(vurl):
2007 vpath = compat_urlparse.urlparse(vurl).path
2008 vext = determine_ext(vpath)
2009 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2011 def filter_video(urls):
2012 return list(filter(check_video, urls))
2014 # Start with something easy: JW Player in SWFObject
2015 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2017 # Look for gorilla-vid style embedding
2018 found = filter_video(re.findall(r'''(?sx)
2022 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2025 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2027 # Broaden the search a little bit
2028 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2030 # Broaden the findall a little bit: JWPlayer JS loader
2031 found = filter_video(re.findall(
2032 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2035 found = filter_video(re.findall(r'''(?xs)
2036 flowplayer\("[^"]+",\s*
2038 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2039 ["']?url["']?\s*:\s*["']([^"']+)["']
2044 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2046 # Try to find twitter cards info
2047 found = filter_video(re.findall(
2048 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2050 # We look for Open Graph info:
2051 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2052 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2053 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2054 if m_video_type is not None:
2055 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2058 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2060 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2062 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2063 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2066 # Look also in Refresh HTTP header
2067 refresh_header = head_response.headers.get('Refresh')
2069 # In python 2 response HTTP headers are bytestrings
2070 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2071 refresh_header = refresh_header.decode('iso-8859-1')
2072 found = re.search(REDIRECT_REGEX, refresh_header)
2074 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2075 self.report_following_redirect(new_url)
2081 raise UnsupportedError(url)
2084 for video_url in found:
2085 video_url = unescapeHTML(video_url)
2086 video_url = video_url.replace('\\/', '/')
2087 video_url = compat_urlparse.urljoin(url, video_url)
2088 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2090 # Sometimes, jwplayer extraction will result in a YouTube URL
2091 if YoutubeIE.suitable(video_url):
2092 entries.append(self.url_result(video_url, 'Youtube'))
2095 # here's a fun little line of code for you:
2096 video_id = os.path.splitext(video_id)[0]
2100 'uploader': video_uploader,
2101 'title': video_title,
2102 'age_limit': age_limit,
2105 ext = determine_ext(video_url)
2107 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2109 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2111 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2113 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2115 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2117 entry_info_dict['url'] = video_url
2119 if entry_info_dict.get('formats'):
2120 self._sort_formats(entry_info_dict['formats'])
2122 entries.append(entry_info_dict)
2124 if len(entries) == 1:
2127 for num, e in enumerate(entries, start=1):
2128 # 'url' results don't have a title
2129 if e.get('title') is not None:
2130 e['title'] = '%s (%d)' % (e['title'], num)
2132 '_type': 'playlist',