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 .snagfilms import SnagFilmsEmbedIE
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
65 class GenericIE(InfoExtractor):
66 IE_DESC = 'Generic downloader that works on some sites'
70 # Direct link to a video
72 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
73 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
78 'upload_date': '20100513',
81 # Direct link to media delivered compressed (until Accept-Encoding is *)
83 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
84 'md5': '128c42e68b13950268b648275386fc74',
86 'id': 'FictionJunction-Parallel_Hearts',
88 'title': 'FictionJunction-Parallel_Hearts',
89 'upload_date': '20140522',
91 'expected_warnings': [
92 'URL could be a direct video link, returning it as such.'
95 # Direct download with broken HEAD
97 'url': 'http://ai-radio.org:8000/radio.opus',
104 'skip_download': True, # infinite live stream
106 'expected_warnings': [
107 r'501.*Not Implemented'
110 # Direct link with incorrect MIME type
112 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
113 'md5': '4ccbebe5f36706d85221f204d7eb5913',
115 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
116 'id': '5_Lennart_Poettering_-_Systemd',
118 'title': '5_Lennart_Poettering_-_Systemd',
119 'upload_date': '20141120',
121 'expected_warnings': [
122 'URL could be a direct video link, returning it as such.'
127 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
129 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
130 'title': 'Zero Punctuation',
131 'description': 're:.*groundbreaking video review series.*'
133 'playlist_mincount': 11,
135 # RSS feed with enclosure
137 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
139 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
141 'upload_date': '20150228',
142 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
145 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
147 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
151 'title': 'Automatics, robotics and biocybernetics',
152 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
153 'upload_date': '20130627',
154 'formats': 'mincount:16',
155 'subtitles': 'mincount:1',
158 'force_generic_extractor': True,
159 'skip_download': True,
162 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
164 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
169 'formats': 'mincount:1',
172 'skip_download': True,
175 # SMIL from https://www.restudy.dk/video/play/id/1637
177 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
181 'title': 'video_1637',
182 'formats': 'mincount:3',
185 'skip_download': True,
188 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
190 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
192 'id': 'smil-service',
194 'title': 'smil-service',
195 'formats': 'mincount:1',
198 'skip_download': True,
201 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
203 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
207 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
208 'formats': 'mincount:3',
211 'skip_download': True,
214 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
216 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
218 'id': 'mZlp2ctYIUEB',
220 'title': 'Tikibad ontruimd wegens brand',
221 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
222 'thumbnail': 're:^https?://.*\.jpg$',
226 'skip_download': True,
229 # MPD from http://dash-mse-test.appspot.com/media.html
231 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
232 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
234 'id': 'car-20120827-manifest',
236 'title': 'car-20120827-manifest',
237 'formats': 'mincount:9',
240 'format': 'bestvideo',
243 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
245 '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',
250 'formats': 'mincount:8',
254 'skip_download': True,
257 # m3u8 served with Content-Type: text/plain
259 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
264 'upload_date': '20140720',
265 'formats': 'mincount:11',
269 'skip_download': True,
274 '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',
278 'upload_date': '20130224',
279 'uploader_id': 'TheVerge',
280 'description': 're:^Chris Ziegler takes a look at the\.*',
281 'uploader': 'The Verge',
282 'title': 'First Firefox OS phones side-by-side',
285 'skip_download': False,
289 # redirect in Refresh HTTP header
290 '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',
294 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
295 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
296 'upload_date': '20150917',
297 'uploader_id': 'brtvofficial',
298 'uploader': 'Boiler Room',
301 'skip_download': False,
305 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
306 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
308 'id': '13601338388002',
310 'uploader': 'www.hodiho.fr',
311 'title': 'R\u00e9gis plante sa Jeep',
314 # bandcamp page with custom domain
316 'add_ie': ['Bandcamp'],
317 'url': 'http://bronyrock.com/track/the-pony-mash',
321 'title': 'The Pony Mash',
322 'uploader': 'M_Pallante',
324 'skip': 'There is a limit of 200 free downloads / month for the test song',
326 # embedded brightcove video
327 # it also tests brightcove videos that need to set the 'Referer' in the
330 'add_ie': ['BrightcoveLegacy'],
331 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
333 'id': '2765128793001',
335 'title': 'Le cours de bourse : l’analyse technique',
336 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
337 'uploader': 'BFM BUSINESS',
340 'skip_download': True,
344 # https://github.com/rg3/youtube-dl/issues/2253
345 'url': 'http://bcove.me/i6nfkrc3',
346 'md5': '0ba9446db037002366bab3b3eb30c88c',
348 'id': '3101154703001',
350 'title': 'Still no power',
351 'uploader': 'thestar.com',
352 '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.',
354 'add_ie': ['BrightcoveLegacy'],
357 'url': 'http://www.championat.com/video/football/v/87/87499.html',
358 'md5': 'fb973ecf6e4a78a67453647444222983',
360 'id': '3414141473001',
362 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
363 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
364 'uploader': 'Championat',
368 # https://github.com/rg3/youtube-dl/issues/3541
369 'add_ie': ['BrightcoveLegacy'],
370 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
372 'id': '3866516442001',
374 'title': 'Leer mij vrouwen kennen: Aflevering 1',
375 'description': 'Leer mij vrouwen kennen: Aflevering 1',
376 'uploader': 'SBS Broadcasting',
378 'skip': 'Restricted to Netherlands',
380 'skip_download': True, # m3u8 download
385 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
386 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
388 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
390 'title': '2cc213299525360.mov', # that's what we get
393 'add_ie': ['Ooyala'],
396 # ooyala video embedded with http://player.ooyala.com/iframe.js
397 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
399 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
401 'title': '"Steve Jobs: Man in the Machine" trailer',
402 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
406 'skip_download': True,
411 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
415 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
416 'upload_date': '20140225',
417 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
418 'uploader': 'Tested',
419 'uploader_id': 'testedcom',
421 # No need to test YoutubeIE here
423 'skip_download': True,
428 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
432 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
433 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
438 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
442 'title': 'Охотское море стало целиком российским',
443 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
447 'skip_download': True,
452 '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/',
456 'title': 'Дошкольное воспитание',
461 'url': 'http://www.vestifinance.ru/articles/25753',
464 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
469 'title': 'Госзаказ. День 3',
475 'title': 'Госзаказ. День 2',
481 'title': 'Госзаказ. День 1',
487 'skip_download': True,
492 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
494 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
496 'title': 'Ужастики, русский трейлер (2015)',
497 'thumbnail': 're:^https?://.*\.jpg$',
503 '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',
506 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
508 'playlist_mincount': 7,
512 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
513 'md5': '65fdff94098e4a607385a60c5177c638',
517 'title': 'Hidden miracles of the natural world',
518 'uploader': 'Louie Schwartzberg',
519 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
522 # Embedded Ustream video
524 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
525 'md5': '27b99cdb639c9b12a79bca876a073417',
529 'uploader': 'AU SPA: The NSA and Privacy',
530 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
533 # nowvideo embed hidden behind percent encoding
535 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
536 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
538 'id': '06e53103ca9aa',
540 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
541 'description': 'No description',
546 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
547 'md5': '7653032cbb25bf6c80d80f217055fa43',
549 'id': '048195-004_PLUS7-F',
552 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
553 'upload_date': '20140320',
556 'skip_download': 'Requires rtmpdump'
561 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
565 'title': 'Alcaline, le concert avec Calogero',
566 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
567 'upload_date': '20150226',
568 'timestamp': 1424989860,
573 'skip_download': True,
575 'expected_warnings': [
581 'url': 'http://www.wired.com/2014/04/honda-asimo/',
582 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
584 'id': '53501be369702d3275860000',
586 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
591 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
592 'md5': '441aeeb82eb72c422c7f14ec533999cd',
594 'id': 'k2mm4bCdJ6CQ2i7c8o2',
596 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
599 'add_ie': ['Dailymotion'],
603 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
607 'title': 'The NBL Auction 2014',
608 'uploader': 'BADMINTON England',
609 'uploader_id': 'BADMINTONEvents',
610 'upload_date': '20140603',
611 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
613 'add_ie': ['Youtube'],
615 'skip_download': True,
620 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
621 'md5': '35727f82f58c76d996fc188f9755b0d5',
623 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
626 'description': 'Mario\'s life in the fast lane has never looked so good.',
629 # YouTube embed via <data-embed-url="">
631 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
635 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
636 'uploader': 'Gameloft',
637 'uploader_id': 'gameloft',
638 'upload_date': '20140828',
639 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
642 'skip_download': True,
647 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
649 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
651 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
652 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
657 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
659 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
660 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
666 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
671 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
672 'md5': '9d65602bf31c6e20014319c7d07fba27',
674 'id': '5123ea6d5e5a7',
677 'uploader': 'www.handjobhub.com',
678 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
681 # Multiple brightcove videos
682 # https://github.com/rg3/youtube-dl/issues/2283
684 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
686 'id': 'always-never',
687 'title': 'Always / Never - The New Yorker',
691 'extract_flat': False,
692 'skip_download': True,
697 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
698 'md5': '96f09a37e44da40dd083e12d9a683327',
702 'title': 'Ump changes call to ball',
703 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
705 'timestamp': 1401537900,
706 'upload_date': '20140531',
707 'thumbnail': 're:^https?://.*\.jpg$',
712 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
713 'md5': '8788b683c777a5cf25621eaf286d0c23',
717 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
719 'filesize': 182808282,
720 'uploader': 'education-portal.com',
724 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
725 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
729 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
731 'uploader': 'thoughtworks.wistia.com',
736 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
740 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
741 'uploader': 'Sophos Security',
742 'title': 'Chet Chat 171 - Oct 29, 2014',
743 'upload_date': '20141029',
748 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
752 'upload_date': '20141112',
753 'title': 'Rosetta #CometLanding webcast HL 10',
758 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
761 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
763 'playlist_mincount': 2,
767 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
771 'upload_date': '20141126',
772 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
777 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
779 'id': '730m_DandD_1901_512k',
781 'uploader': 'www.abc.net.au',
782 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
785 # embedded viddler video
787 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
791 'uploader': 'deadspin',
792 'title': 'WALL-TO-GORTAT',
793 'timestamp': 1422285291,
794 'upload_date': '20150126',
796 'add_ie': ['Viddler'],
800 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
804 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
805 'description': 'md5:601cb790edd05908957dae8aaa866465',
806 'upload_date': '20150220',
811 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
815 'upload_date': '20150212',
816 'uploader': 'The National Archives UK',
817 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
818 'uploader_id': 'NationalArchives08',
819 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
824 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
825 'playlist_mincount': 5,
827 'id': 'aanslagen-kopenhagen',
828 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
833 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
837 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
842 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
846 'upload_date': '20150226',
847 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
849 'title': 'John Carlson Postgame 2/25/15',
852 # Kaltura embed (different embed code)
854 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
858 'upload_date': '20150127',
859 'uploader_id': 'PremierMedia',
861 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
864 # Kaltura embed protected with referrer
866 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
870 'title': 'Violetta - Achter De Schermen - Ruggero',
871 'description': 'Achter de schermen met Ruggero',
872 'timestamp': 1435133761,
873 'upload_date': '20150624',
874 'uploader_id': 'echojecka',
877 # Eagle.Platform embed (generic URL)
879 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
883 'title': 'Навальный вышел на свободу',
884 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
885 'thumbnail': 're:^https?://.*\.jpg$',
891 # ClipYou (Eagle.Platform) embed (custom URL)
893 'url': 'http://muz-tv.ru/play/7129/',
897 'title': "'O Sole Mio",
898 'thumbnail': 're:^https?://.*\.jpg$',
905 'url': 'http://muz-tv.ru/kinozal/view/7400/',
909 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
910 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
911 'thumbnail': 're:^https?://.*\.jpg$',
918 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
922 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
923 'thumbnail': 're:^https?://.*\.png$',
929 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
930 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
934 'title': 'Facebook Creates "On This Day" | Crunch Report',
939 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
943 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
948 # Crooks and Liars embed
950 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
954 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
955 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
956 'timestamp': 1428207000,
957 'upload_date': '20150405',
958 'uploader': 'Heather',
961 # Crooks and Liars external embed
963 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
965 'id': 'MTE3MjUtMzQ2MzA',
967 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
968 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
969 'timestamp': 1265032391,
970 'upload_date': '20100201',
971 'uploader': 'Heather',
974 # NBC Sports vplayer embed
976 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
978 'id': 'ln7x1qSThw4k',
980 'title': "PFT Live: New leader in the 'new-look' defense",
981 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
986 'url': 'http://www.udn.com/news/story/7314/822787',
987 'md5': 'fd2060e988c326991037b9aff9df21a6',
991 'title': '中一中男師變性 全校師生力挺',
992 'thumbnail': 're:^https?://.*\.jpg$',
997 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
999 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1001 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1002 'title': 'This is what separates the Excel masters from the wannabes',
1003 'duration': 191.933,
1007 'skip_download': True,
1010 # Contains a SMIL manifest
1012 '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',
1016 'title': '+ Football: Lottery Champions League Europe',
1017 'uploader': 'www.telewebion.com',
1021 'skip_download': True,
1024 # Brightcove URL in single quotes
1026 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1027 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1029 'id': '4255764656001',
1031 'title': 'SN Presents: Russell Martin, World Citizen',
1032 '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.',
1033 'uploader': 'Rogers Sportsnet',
1036 # Dailymotion Cloud video
1038 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1039 'md5': '49444254273501a64675a7e68c502681',
1041 'id': '5585de919473990de4bee11b',
1043 'title': 'Le débat',
1044 'thumbnail': 're:^https?://.*\.jpe?g$',
1047 # OnionStudios embed
1049 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1053 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1054 'thumbnail': 're:^https?://.*\.jpe?g$',
1055 'uploader': 'ClickHole',
1056 'uploader_id': 'clickhole',
1061 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1063 'id': '74849a00-85a9-11e1-9660-123139220831',
1065 'title': '#whilewewatch',
1068 # AdobeTVVideo embed
1070 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1071 'md5': '43662b577c018ad707a63766462b1e87',
1075 'title': 'New experience with Acrobat DC',
1076 'description': 'New experience with Acrobat DC',
1077 'duration': 248.667,
1080 # ScreenwaveMedia embed
1082 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1083 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1085 'id': 'cinemasnob-55d26273809dd',
1087 'title': 'cinemasnob',
1090 # BrightcoveInPageEmbed embed
1092 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1094 'id': '4238694884001',
1096 'title': 'Tabletop: Dread, Last Thoughts',
1097 'description': 'Tabletop: Dread, Last Thoughts',
1101 # JWPlayer with M3U8
1103 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1107 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1108 'uploader': 'ren.tv',
1112 'skip_download': True,
1115 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1116 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1118 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1120 'id': '4785848093001',
1122 'title': 'The Cardinal Pell Interview',
1123 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1124 'uploader': 'GlobeCast Australia - GlobeStream',
1128 'skip_download': True,
1133 def report_following_redirect(self, new_url):
1134 """Report information extraction."""
1135 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1137 def _extract_rss(self, url, video_id, doc):
1138 playlist_title = doc.find('./channel/title').text
1139 playlist_desc_el = doc.find('./channel/description')
1140 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1143 for it in doc.findall('./channel/item'):
1144 next_url = xpath_text(it, 'link', fatal=False)
1146 enclosure_nodes = it.findall('./enclosure')
1147 for e in enclosure_nodes:
1148 next_url = e.attrib.get('url')
1158 'title': it.find('title').text,
1162 '_type': 'playlist',
1164 'title': playlist_title,
1165 'description': playlist_desc,
1169 def _extract_camtasia(self, url, video_id, webpage):
1170 """ Returns None if no camtasia video can be found. """
1172 camtasia_cfg = self._search_regex(
1173 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1174 webpage, 'camtasia configuration file', default=None)
1175 if camtasia_cfg is None:
1178 title = self._html_search_meta('DC.title', webpage, fatal=True)
1180 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1181 camtasia_cfg = self._download_xml(
1182 camtasia_url, video_id,
1183 note='Downloading camtasia configuration',
1184 errnote='Failed to download camtasia configuration')
1185 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1188 for n in fileset_node.getchildren():
1189 url_n = n.find('./uri')
1194 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1195 'title': '%s - %s' % (title, n.tag),
1196 'url': compat_urlparse.urljoin(url, url_n.text),
1197 'duration': float_or_none(n.find('./duration').text),
1201 '_type': 'playlist',
1206 def _real_extract(self, url):
1207 if url.startswith('//'):
1210 'url': self.http_scheme() + url,
1213 parsed_url = compat_urlparse.urlparse(url)
1214 if not parsed_url.scheme:
1215 default_search = self._downloader.params.get('default_search')
1216 if default_search is None:
1217 default_search = 'fixup_error'
1219 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1221 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1222 return self.url_result('http://' + url)
1223 elif default_search != 'fixup_error':
1224 if default_search == 'auto_warning':
1225 if re.match(r'^(?:url|URL)$', url):
1226 raise ExtractorError(
1227 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1230 self._downloader.report_warning(
1231 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1232 return self.url_result('ytsearch:' + url)
1234 if default_search in ('error', 'fixup_error'):
1235 raise ExtractorError(
1236 '%r is not a valid URL. '
1237 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1238 % (url, url), expected=True)
1240 if ':' not in default_search:
1241 default_search += ':'
1242 return self.url_result(default_search + url)
1244 url, smuggled_data = unsmuggle_url(url)
1245 force_videoid = None
1246 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1247 if smuggled_data and 'force_videoid' in smuggled_data:
1248 force_videoid = smuggled_data['force_videoid']
1249 video_id = force_videoid
1251 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1253 self.to_screen('%s: Requesting header' % video_id)
1255 head_req = HEADRequest(url)
1256 head_response = self._request_webpage(
1258 note=False, errnote='Could not send HEAD request to %s' % url,
1261 if head_response is not False:
1262 # Check for redirect
1263 new_url = head_response.geturl()
1265 self.report_following_redirect(new_url)
1267 new_url = smuggle_url(
1268 new_url, {'force_videoid': force_videoid})
1269 return self.url_result(new_url)
1271 full_response = None
1272 if head_response is False:
1273 request = sanitized_Request(url)
1274 request.add_header('Accept-Encoding', '*')
1275 full_response = self._request_webpage(request, video_id)
1276 head_response = full_response
1280 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1281 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1284 # Check for direct link to a video
1285 content_type = head_response.headers.get('Content-Type', '').lower()
1286 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1288 format_id = m.group('format_id')
1289 if format_id.endswith('mpegurl'):
1290 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1291 elif format_id == 'f4m':
1292 formats = self._extract_f4m_formats(url, video_id)
1295 'format_id': m.group('format_id'),
1297 'vcodec': 'none' if m.group('type') == 'audio' else None
1299 info_dict['direct'] = True
1300 self._sort_formats(formats)
1301 info_dict['formats'] = formats
1304 if not self._downloader.params.get('test', False) and not is_intentional:
1305 force = self._downloader.params.get('force_generic_extractor', False)
1306 self._downloader.report_warning(
1307 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1309 if not full_response:
1310 request = sanitized_Request(url)
1311 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1312 # making it impossible to download only chunk of the file (yet we need only 512kB to
1313 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1314 # that will always result in downloading the whole file that is not desirable.
1315 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1316 # to accept raw bytes and being able to download only a chunk.
1317 # It may probably better to solve this by checking Content-Type for application/octet-stream
1318 # after HEAD request finishes, but not sure if we can rely on this.
1319 request.add_header('Accept-Encoding', '*')
1320 full_response = self._request_webpage(request, video_id)
1322 first_bytes = full_response.read(512)
1324 # Is it an M3U playlist?
1325 if first_bytes.startswith(b'#EXTM3U'):
1326 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1327 self._sort_formats(info_dict['formats'])
1330 # Maybe it's a direct link to a video?
1331 # Be careful not to download the whole thing!
1332 if not is_html(first_bytes):
1333 self._downloader.report_warning(
1334 'URL could be a direct video link, returning it as such.')
1341 webpage = self._webpage_read_content(
1342 full_response, url, video_id, prefix=first_bytes)
1344 self.report_extraction(video_id)
1346 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1348 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1349 if doc.tag == 'rss':
1350 return self._extract_rss(url, video_id, doc)
1351 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1352 smil = self._parse_smil(doc, url, video_id)
1353 self._sort_formats(smil['formats'])
1355 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1356 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1357 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1358 info_dict['formats'] = self._parse_mpd_formats(
1359 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1360 self._sort_formats(info_dict['formats'])
1362 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1363 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1364 self._sort_formats(info_dict['formats'])
1366 except compat_xml_parse_error:
1369 # Is it a Camtasia project?
1370 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1371 if camtasia_res is not None:
1374 # Sometimes embedded video player is hidden behind percent encoding
1375 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1376 # Unescaping the whole page allows to handle those cases in a generic way
1377 webpage = compat_urllib_parse_unquote(webpage)
1379 # it's tempting to parse this further, but you would
1380 # have to take into account all the variations like
1381 # Video Title - Site Name
1382 # Site Name | Video Title
1383 # Video Title - Tagline | Site Name
1384 # and so on and so forth; it's just not practical
1385 video_title = self._html_search_regex(
1386 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1389 # Try to detect age limit automatically
1390 age_limit = self._rta_search(webpage)
1391 # And then there are the jokers who advertise that they use RTA,
1392 # but actually don't.
1393 AGE_LIMIT_MARKERS = [
1394 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1396 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1399 # video uploader is domain name
1400 video_uploader = self._search_regex(
1401 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1404 def _playlist_from_matches(matches, getter=None, ie=None):
1406 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1408 return self.playlist_result(
1409 urlrs, playlist_id=video_id, playlist_title=video_title)
1411 # Look for Brightcove Legacy Studio embeds
1412 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1414 self.to_screen('Brightcove video detected.')
1417 'url': smuggle_url(bc_url, {'Referer': url}),
1418 'ie_key': 'BrightcoveLegacy'
1419 } for bc_url in bc_urls]
1422 '_type': 'playlist',
1423 'title': video_title,
1428 # Look for Brightcove New Studio embeds
1429 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1431 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1433 # Look for embedded rtl.nl player
1434 matches = re.findall(
1435 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1438 return _playlist_from_matches(matches, ie='RtlNl')
1440 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1441 if vimeo_url is not None:
1442 return self.url_result(vimeo_url)
1444 vid_me_embed_url = self._search_regex(
1445 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1446 webpage, 'vid.me embed', default=None)
1447 if vid_me_embed_url is not None:
1448 return self.url_result(vid_me_embed_url, 'Vidme')
1450 # Look for embedded YouTube player
1451 matches = re.findall(r'''(?x)
1460 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1464 return _playlist_from_matches(
1465 matches, lambda m: unescapeHTML(m[1]))
1467 # Look for lazyYT YouTube embed
1468 matches = re.findall(
1469 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1471 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1473 # Look for embedded Dailymotion player
1474 matches = re.findall(
1475 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1477 return _playlist_from_matches(
1478 matches, lambda m: unescapeHTML(m[1]))
1480 # Look for embedded Dailymotion playlist player (#3822)
1482 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1484 playlists = re.findall(
1485 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1487 return _playlist_from_matches(
1488 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1490 # Look for embedded Wistia player
1492 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1494 embed_url = self._proto_relative_url(
1495 unescapeHTML(match.group('url')))
1497 '_type': 'url_transparent',
1500 'uploader': video_uploader,
1501 'title': video_title,
1505 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1508 '_type': 'url_transparent',
1509 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1511 'uploader': video_uploader,
1512 'title': video_title,
1513 'id': match.group('id')
1516 # Look for SVT player
1517 svt_url = SVTIE._extract_url(webpage)
1519 return self.url_result(svt_url, 'SVT')
1521 # Look for embedded condenast player
1522 matches = re.findall(
1523 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1527 '_type': 'playlist',
1530 'ie_key': 'CondeNast',
1532 } for ma in matches],
1533 'title': video_title,
1537 # Look for Bandcamp pages with custom domain
1538 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1539 if mobj is not None:
1540 burl = unescapeHTML(mobj.group(1))
1541 # Don't set the extractor because it can be a track url or an album
1542 return self.url_result(burl)
1544 # Look for embedded Vevo player
1546 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1547 if mobj is not None:
1548 return self.url_result(mobj.group('url'))
1550 # Look for embedded Viddler player
1552 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1554 if mobj is not None:
1555 return self.url_result(mobj.group('url'))
1557 # Look for NYTimes player
1559 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1561 if mobj is not None:
1562 return self.url_result(mobj.group('url'))
1564 # Look for Libsyn player
1566 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1567 if mobj is not None:
1568 return self.url_result(mobj.group('url'))
1570 # Look for Ooyala videos
1571 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1572 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1573 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1574 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1575 if mobj is not None:
1576 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1578 # Look for multiple Ooyala embeds on SBN network websites
1579 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1580 if mobj is not None:
1581 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1583 return _playlist_from_matches(
1584 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1586 # Look for Aparat videos
1587 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1588 if mobj is not None:
1589 return self.url_result(mobj.group(1), 'Aparat')
1591 # Look for MPORA videos
1592 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1593 if mobj is not None:
1594 return self.url_result(mobj.group(1), 'Mpora')
1596 # Look for embedded NovaMov-based player
1598 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1599 (?P<url>http://(?:(?:embed|www)\.)?
1601 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1602 videoweed\.(?:es|com)|
1603 movshare\.(?:net|sx|ag)|
1604 divxstage\.(?:eu|net|ch|co|at|ag))
1605 /embed\.php.+?)\1''', webpage)
1606 if mobj is not None:
1607 return self.url_result(mobj.group('url'))
1609 # Look for embedded Facebook player
1611 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1612 if mobj is not None:
1613 return self.url_result(mobj.group('url'), 'Facebook')
1615 # Look for embedded VK player
1616 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1617 if mobj is not None:
1618 return self.url_result(mobj.group('url'), 'VK')
1620 # Look for embedded Odnoklassniki player
1621 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1622 if mobj is not None:
1623 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1625 # Look for embedded ivi player
1626 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1627 if mobj is not None:
1628 return self.url_result(mobj.group('url'), 'Ivi')
1630 # Look for embedded Huffington Post player
1632 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1633 if mobj is not None:
1634 return self.url_result(mobj.group('url'), 'HuffPost')
1637 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1638 if mobj is not None:
1639 return self.url_result(mobj.group('url'))
1640 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1641 if mobj is not None:
1642 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1644 # Look for funnyordie embed
1645 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1647 return _playlist_from_matches(
1648 matches, getter=unescapeHTML, ie='FunnyOrDie')
1650 # Look for BBC iPlayer embed
1651 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1653 return _playlist_from_matches(matches, ie='BBCCoUk')
1655 # Look for embedded RUTV player
1656 rutv_url = RUTVIE._extract_url(webpage)
1658 return self.url_result(rutv_url, 'RUTV')
1660 # Look for embedded TVC player
1661 tvc_url = TVCIE._extract_url(webpage)
1663 return self.url_result(tvc_url, 'TVC')
1665 # Look for embedded SportBox player
1666 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1668 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1670 # Look for embedded PornHub player
1671 pornhub_url = PornHubIE._extract_url(webpage)
1673 return self.url_result(pornhub_url, 'PornHub')
1675 # Look for embedded XHamster player
1676 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1678 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1680 # Look for embedded TNAFlixNetwork player
1681 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1683 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1685 # Look for embedded Tvigle player
1687 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1688 if mobj is not None:
1689 return self.url_result(mobj.group('url'), 'Tvigle')
1691 # Look for embedded TED player
1693 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1694 if mobj is not None:
1695 return self.url_result(mobj.group('url'), 'TED')
1697 # Look for embedded Ustream videos
1699 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1700 if mobj is not None:
1701 return self.url_result(mobj.group('url'), 'Ustream')
1703 # Look for embedded arte.tv player
1705 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1707 if mobj is not None:
1708 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1710 # Look for embedded francetv player
1712 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1714 if mobj is not None:
1715 return self.url_result(mobj.group('url'))
1717 # Look for embedded smotri.com player
1718 smotri_url = SmotriIE._extract_url(webpage)
1720 return self.url_result(smotri_url, 'Smotri')
1722 # Look for embedded Myvi.ru player
1723 myvi_url = MyviIE._extract_url(webpage)
1725 return self.url_result(myvi_url)
1727 # Look for embedded soundcloud player
1729 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1731 if mobj is not None:
1732 url = unescapeHTML(mobj.group('url'))
1733 return self.url_result(url)
1735 # Look for embedded vulture.com player
1737 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1739 if mobj is not None:
1740 url = unescapeHTML(mobj.group('url'))
1741 return self.url_result(url, ie='Vulture')
1743 # Look for embedded mtvservices player
1744 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1746 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1748 # Look for embedded yahoo player
1750 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1752 if mobj is not None:
1753 return self.url_result(mobj.group('url'), 'Yahoo')
1755 # Look for embedded sbs.com.au player
1759 <meta\s+property="og:video"\s+content=|
1762 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1764 if mobj is not None:
1765 return self.url_result(mobj.group('url'), 'SBS')
1767 # Look for embedded Cinchcast player
1769 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1771 if mobj is not None:
1772 return self.url_result(mobj.group('url'), 'Cinchcast')
1775 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1779 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1781 if mobj is not None:
1782 return self.url_result(mobj.group('url'), 'MLB')
1785 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1787 if mobj is not None:
1788 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1791 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1793 if mobj is not None:
1794 return self.url_result(mobj.group('url'), 'Livestream')
1796 # Look for Zapiks embed
1798 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1799 if mobj is not None:
1800 return self.url_result(mobj.group('url'), 'Zapiks')
1802 # Look for Kaltura embeds
1803 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1804 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))
1805 if mobj is not None:
1806 return self.url_result(smuggle_url(
1807 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1808 {'source_url': url}), 'Kaltura')
1810 # Look for Eagle.Platform embeds
1812 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1813 if mobj is not None:
1814 return self.url_result(mobj.group('url'), 'EaglePlatform')
1816 # Look for ClipYou (uses Eagle.Platform) embeds
1818 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1819 if mobj is not None:
1820 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1822 # Look for Pladform embeds
1823 pladform_url = PladformIE._extract_url(webpage)
1825 return self.url_result(pladform_url)
1827 # Look for Videomore embeds
1828 videomore_url = VideomoreIE._extract_url(webpage)
1830 return self.url_result(videomore_url)
1832 # Look for Playwire embeds
1834 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1835 if mobj is not None:
1836 return self.url_result(mobj.group('url'))
1838 # Look for 5min embeds
1840 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1841 if mobj is not None:
1842 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1844 # Look for Crooks and Liars embeds
1846 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1847 if mobj is not None:
1848 return self.url_result(mobj.group('url'))
1850 # Look for NBC Sports VPlayer embeds
1851 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1853 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1855 # Look for Google Drive embeds
1856 google_drive_url = GoogleDriveIE._extract_url(webpage)
1857 if google_drive_url:
1858 return self.url_result(google_drive_url, 'GoogleDrive')
1860 # Look for UDN embeds
1862 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1863 if mobj is not None:
1864 return self.url_result(
1865 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1867 # Look for Senate ISVP iframe
1868 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1870 return self.url_result(senate_isvp_url, 'SenateISVP')
1872 # Look for Dailymotion Cloud videos
1873 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1875 return self.url_result(dmcloud_url, 'DailymotionCloud')
1877 # Look for OnionStudios embeds
1878 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1879 if onionstudios_url:
1880 return self.url_result(onionstudios_url)
1882 # Look for SnagFilms embeds
1883 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1885 return self.url_result(snagfilms_url)
1887 # Look for JWPlatform embeds
1888 jwplatform_url = JWPlatformIE._extract_url(webpage)
1890 return self.url_result(jwplatform_url, 'JWPlatform')
1892 # Look for ScreenwaveMedia embeds
1893 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1894 if mobj is not None:
1895 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1897 # Look for Digiteka embeds
1898 digiteka_url = DigitekaIE._extract_url(webpage)
1900 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
1902 # Look for Limelight embeds
1903 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
1907 'Channel': 'channel',
1908 'ChannelList': 'channel_list',
1910 return self.url_result('limelight:%s:%s' % (
1911 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
1913 # Look for AdobeTVVideo embeds
1915 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1917 if mobj is not None:
1918 return self.url_result(
1919 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1922 # Look for Vine embeds
1924 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
1926 if mobj is not None:
1927 return self.url_result(
1928 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
1930 # Look for Instagram embeds
1931 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
1932 if instagram_embed_url is not None:
1933 return self.url_result(instagram_embed_url, InstagramIE.ie_key())
1935 def check_video(vurl):
1936 if YoutubeIE.suitable(vurl):
1938 vpath = compat_urlparse.urlparse(vurl).path
1939 vext = determine_ext(vpath)
1940 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1942 def filter_video(urls):
1943 return list(filter(check_video, urls))
1945 # Start with something easy: JW Player in SWFObject
1946 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1948 # Look for gorilla-vid style embedding
1949 found = filter_video(re.findall(r'''(?sx)
1953 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1956 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1958 # Broaden the search a little bit
1959 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1961 # Broaden the findall a little bit: JWPlayer JS loader
1962 found = filter_video(re.findall(
1963 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1966 found = filter_video(re.findall(r'''(?xs)
1967 flowplayer\("[^"]+",\s*
1969 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1970 ["']?url["']?\s*:\s*["']([^"']+)["']
1975 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1977 # Try to find twitter cards info
1978 found = filter_video(re.findall(
1979 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1981 # We look for Open Graph info:
1982 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1983 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1984 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1985 if m_video_type is not None:
1986 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1989 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1991 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1993 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1994 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1997 # Look also in Refresh HTTP header
1998 refresh_header = head_response.headers.get('Refresh')
2000 # In python 2 response HTTP headers are bytestrings
2001 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2002 refresh_header = refresh_header.decode('iso-8859-1')
2003 found = re.search(REDIRECT_REGEX, refresh_header)
2005 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2006 self.report_following_redirect(new_url)
2012 raise UnsupportedError(url)
2015 for video_url in found:
2016 video_url = video_url.replace('\\/', '/')
2017 video_url = compat_urlparse.urljoin(url, video_url)
2018 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2020 # Sometimes, jwplayer extraction will result in a YouTube URL
2021 if YoutubeIE.suitable(video_url):
2022 entries.append(self.url_result(video_url, 'Youtube'))
2025 # here's a fun little line of code for you:
2026 video_id = os.path.splitext(video_id)[0]
2030 'uploader': video_uploader,
2031 'title': video_title,
2032 'age_limit': age_limit,
2035 ext = determine_ext(video_url)
2037 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2039 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2041 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2043 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2045 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2047 entry_info_dict['url'] = video_url
2049 if entry_info_dict.get('formats'):
2050 self._sort_formats(entry_info_dict['formats'])
2052 entries.append(entry_info_dict)
2054 if len(entries) == 1:
2057 for num, e in enumerate(entries, start=1):
2058 # 'url' results don't have a title
2059 if e.get('title') is not None:
2060 e['title'] = '%s (%d)' % (e['title'], num)
2062 '_type': 'playlist',