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,
32 from .brightcove import (
36 from .nbc import NBCSportsVPlayerIE
37 from .ooyala import OoyalaIE
38 from .rutv import RUTVIE
39 from .tvc import TVCIE
40 from .sportbox import SportBoxEmbedIE
41 from .smotri import SmotriIE
42 from .myvi import MyviIE
43 from .condenast import CondeNastIE
44 from .udn import UDNEmbedIE
45 from .senateisvp import SenateISVPIE
46 from .svt import SVTIE
47 from .pornhub import PornHubIE
48 from .xhamster import XHamsterEmbedIE
49 from .tnaflix import TNAFlixNetworkEmbedIE
50 from .drtuber import DrTuberIE
51 from .redtube import RedTubeIE
52 from .vimeo import VimeoIE
53 from .dailymotion import (
57 from .onionstudios import OnionStudiosIE
58 from .viewlift import ViewLiftEmbedIE
59 from .mtv import MTVServicesEmbeddedIE
60 from .pladform import PladformIE
61 from .videomore import VideomoreIE
62 from .webcaster import WebcasterFeedIE
63 from .googledrive import GoogleDriveIE
64 from .jwplatform import JWPlatformIE
65 from .digiteka import DigitekaIE
66 from .arkena import ArkenaIE
67 from .instagram import InstagramIE
68 from .liveleak import LiveLeakIE
69 from .threeqsdn import ThreeQSDNIE
70 from .theplatform import ThePlatformIE
71 from .vessel import VesselIE
72 from .kaltura import KalturaIE
73 from .eagleplatform import EaglePlatformIE
74 from .facebook import FacebookIE
75 from .soundcloud import SoundcloudIE
76 from .vbox7 import Vbox7IE
77 from .dbtv import DBTVIE
78 from .piksel import PikselIE
79 from .videa import VideaIE
82 class GenericIE(InfoExtractor):
83 IE_DESC = 'Generic downloader that works on some sites'
87 # Direct link to a video
89 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
90 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
95 'upload_date': '20100513',
98 # Direct link to media delivered compressed (until Accept-Encoding is *)
100 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
101 'md5': '128c42e68b13950268b648275386fc74',
103 'id': 'FictionJunction-Parallel_Hearts',
105 'title': 'FictionJunction-Parallel_Hearts',
106 'upload_date': '20140522',
108 'expected_warnings': [
109 'URL could be a direct video link, returning it as such.'
111 'skip': 'URL invalid',
113 # Direct download with broken HEAD
115 'url': 'http://ai-radio.org:8000/radio.opus',
122 'skip_download': True, # infinite live stream
124 'expected_warnings': [
125 r'501.*Not Implemented',
129 # Direct link with incorrect MIME type
131 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
132 'md5': '4ccbebe5f36706d85221f204d7eb5913',
134 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
135 'id': '5_Lennart_Poettering_-_Systemd',
137 'title': '5_Lennart_Poettering_-_Systemd',
138 'upload_date': '20141120',
140 'expected_warnings': [
141 'URL could be a direct video link, returning it as such.'
146 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
148 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
149 'title': 'Zero Punctuation',
150 'description': 're:.*groundbreaking video review series.*'
152 'playlist_mincount': 11,
154 # RSS feed with enclosure
156 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
158 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
160 'upload_date': '20150228',
161 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
164 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
166 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
170 'title': 'Automatics, robotics and biocybernetics',
171 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
172 'upload_date': '20130627',
173 'formats': 'mincount:16',
174 'subtitles': 'mincount:1',
177 'force_generic_extractor': True,
178 'skip_download': True,
181 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
183 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
188 'formats': 'mincount:1',
191 'skip_download': True,
194 # SMIL from https://www.restudy.dk/video/play/id/1637
196 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
200 'title': 'video_1637',
201 'formats': 'mincount:3',
204 'skip_download': True,
207 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
209 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
211 'id': 'smil-service',
213 'title': 'smil-service',
214 'formats': 'mincount:1',
217 'skip_download': True,
220 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
222 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
226 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
227 'formats': 'mincount:3',
230 'skip_download': True,
233 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
235 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
237 'id': 'mZlp2ctYIUEB',
239 'title': 'Tikibad ontruimd wegens brand',
240 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
241 'thumbnail': 're:^https?://.*\.jpg$',
245 'skip_download': True,
248 # MPD from http://dash-mse-test.appspot.com/media.html
250 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
251 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
253 'id': 'car-20120827-manifest',
255 'title': 'car-20120827-manifest',
256 'formats': 'mincount:9',
257 'upload_date': '20130904',
260 'format': 'bestvideo',
263 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
265 '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',
270 'formats': 'mincount:8',
274 'skip_download': True,
276 'skip': 'video gone',
278 # m3u8 served with Content-Type: text/plain
280 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
285 'upload_date': '20140720',
286 'formats': 'mincount:11',
290 'skip_download': True,
292 'skip': 'video gone',
296 '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',
300 'upload_date': '20130224',
301 'uploader_id': 'TheVerge',
302 'description': 're:^Chris Ziegler takes a look at the\.*',
303 'uploader': 'The Verge',
304 'title': 'First Firefox OS phones side-by-side',
307 'skip_download': False,
311 # redirect in Refresh HTTP header
312 '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',
316 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
317 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
318 'upload_date': '20150917',
319 'uploader_id': 'brtvofficial',
320 'uploader': 'Boiler Room',
323 'skip_download': False,
327 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
328 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
330 'id': '13601338388002',
332 'uploader': 'www.hodiho.fr',
333 'title': 'R\u00e9gis plante sa Jeep',
336 # bandcamp page with custom domain
338 'add_ie': ['Bandcamp'],
339 'url': 'http://bronyrock.com/track/the-pony-mash',
343 'title': 'The Pony Mash',
344 'uploader': 'M_Pallante',
346 'skip': 'There is a limit of 200 free downloads / month for the test song',
349 # embedded brightcove video
350 # it also tests brightcove videos that need to set the 'Referer'
351 # in the http requests
352 'add_ie': ['BrightcoveLegacy'],
353 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
355 'id': '2765128793001',
357 'title': 'Le cours de bourse : l’analyse technique',
358 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
359 'uploader': 'BFM BUSINESS',
362 'skip_download': True,
366 # embedded with itemprop embedURL and video id spelled as `idVideo`
367 'add_id': ['BrightcoveLegacy'],
368 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
370 'id': '5255628253001',
372 'title': 'md5:37c519b1128915607601e75a87995fc0',
373 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
374 'uploader': 'BFM BUSINESS',
375 'uploader_id': '876450612001',
376 'timestamp': 1482255315,
377 'upload_date': '20161220',
380 'skip_download': True,
384 # https://github.com/rg3/youtube-dl/issues/2253
385 'url': 'http://bcove.me/i6nfkrc3',
386 'md5': '0ba9446db037002366bab3b3eb30c88c',
388 'id': '3101154703001',
390 'title': 'Still no power',
391 'uploader': 'thestar.com',
392 '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.',
394 'add_ie': ['BrightcoveLegacy'],
395 'skip': 'video gone',
398 'url': 'http://www.championat.com/video/football/v/87/87499.html',
399 'md5': 'fb973ecf6e4a78a67453647444222983',
401 'id': '3414141473001',
403 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
404 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
405 'uploader': 'Championat',
409 # https://github.com/rg3/youtube-dl/issues/3541
410 'add_ie': ['BrightcoveLegacy'],
411 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
413 'id': '3866516442001',
415 'title': 'Leer mij vrouwen kennen: Aflevering 1',
416 'description': 'Leer mij vrouwen kennen: Aflevering 1',
417 'uploader': 'SBS Broadcasting',
419 'skip': 'Restricted to Netherlands',
421 'skip_download': True, # m3u8 download
426 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
427 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
429 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
431 'title': '2cc213299525360.mov', # that's what we get
434 'add_ie': ['Ooyala'],
437 # ooyala video embedded with http://player.ooyala.com/iframe.js
438 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
440 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
442 'title': '"Steve Jobs: Man in the Machine" trailer',
443 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
447 'skip_download': True,
449 'skip': 'movie expired',
453 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
457 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
458 'upload_date': '20140225',
459 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
460 'uploader': 'Tested',
461 'uploader_id': 'testedcom',
463 # No need to test YoutubeIE here
465 'skip_download': True,
470 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
474 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
475 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
477 # HEAD requests lead to endless 301, while GET is OK
478 'expected_warnings': ['301'],
482 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
486 'title': 'Охотское море стало целиком российским',
487 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
491 'skip_download': True,
496 '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/',
500 'title': 'Дошкольное воспитание',
505 'url': 'http://www.vestifinance.ru/articles/25753',
508 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
513 'title': 'Госзаказ. День 3',
519 'title': 'Госзаказ. День 2',
525 'title': 'Госзаказ. День 1',
531 'skip_download': True,
536 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
538 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
540 'title': 'Ужастики, русский трейлер (2015)',
541 'thumbnail': 're:^https?://.*\.jpg$',
547 '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',
550 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
552 'playlist_mincount': 7,
553 # This forum does not allow <iframe> syntaxes anymore
554 # Now HTML tags are displayed as-is
555 'skip': 'No videos on this page',
559 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
560 'md5': '65fdff94098e4a607385a60c5177c638',
564 'title': 'Hidden miracles of the natural world',
565 'uploader': 'Louie Schwartzberg',
566 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
569 # Embedded Ustream video
571 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
572 'md5': '27b99cdb639c9b12a79bca876a073417',
576 'uploader': 'AU SPA: The NSA and Privacy',
577 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
580 # nowvideo embed hidden behind percent encoding
582 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
583 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
585 'id': '06e53103ca9aa',
587 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
588 'description': 'No description',
593 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
594 'md5': '7653032cbb25bf6c80d80f217055fa43',
596 'id': '048195-004_PLUS7-F',
599 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
600 'upload_date': '20140320',
603 'skip_download': 'Requires rtmpdump'
605 'skip': 'video gone',
609 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
613 'title': 'Alcaline, le concert avec Calogero',
614 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
615 'upload_date': '20150226',
616 'timestamp': 1424989860,
621 'skip_download': True,
623 'expected_warnings': [
629 'url': 'http://www.wired.com/2014/04/honda-asimo/',
630 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
632 'id': '53501be369702d3275860000',
634 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
639 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
640 'md5': '441aeeb82eb72c422c7f14ec533999cd',
642 'id': 'k2mm4bCdJ6CQ2i7c8o2',
644 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
645 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
647 'uploader_id': 'xgditw',
648 'upload_date': '20140425',
649 'timestamp': 1398441542,
651 'add_ie': ['Dailymotion'],
655 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
659 'title': 'The NBL Auction 2014',
660 'uploader': 'BADMINTON England',
661 'uploader_id': 'BADMINTONEvents',
662 'upload_date': '20140603',
663 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
665 'add_ie': ['Youtube'],
667 'skip_download': True,
672 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
673 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
675 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
677 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
678 'description': 'Two valets share their love for movie star Liam Neesons.',
679 'timestamp': 1349922600,
680 'upload_date': '20121011',
683 # YouTube embed via <data-embed-url="">
685 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
689 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
690 'uploader': 'Gameloft',
691 'uploader_id': 'gameloft',
692 'upload_date': '20140828',
693 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
696 'skip_download': True,
701 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
703 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
705 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
706 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
711 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
713 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
714 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
720 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
725 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
726 'md5': '9d65602bf31c6e20014319c7d07fba27',
728 'id': '5123ea6d5e5a7',
731 'uploader': 'www.handjobhub.com',
732 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
735 # Multiple brightcove videos
736 # https://github.com/rg3/youtube-dl/issues/2283
738 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
740 'id': 'always-never',
741 'title': 'Always / Never - The New Yorker',
745 'extract_flat': False,
746 'skip_download': True,
751 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
752 'md5': '96f09a37e44da40dd083e12d9a683327',
756 'title': 'Ump changes call to ball',
757 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
759 'timestamp': 1401537900,
760 'upload_date': '20140531',
761 'thumbnail': 're:^https?://.*\.jpg$',
766 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
767 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
771 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
772 'description': 'a Paywall Videos video from Remilon',
774 'uploader': 'study.com',
775 'timestamp': 1459678540,
776 'upload_date': '20160403',
777 'filesize': 24687186,
781 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
782 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
786 'title': 'Conversation about Hexagonal Rails Part 1',
787 'description': 'a Martin Fowler video from ThoughtWorks',
789 'uploader': 'thoughtworks.wistia.com',
790 'timestamp': 1401832161,
791 'upload_date': '20140603',
794 # Wistia standard embed (async)
796 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
800 'title': 'Drip Brennan Dunn Workshop',
801 'description': 'a JV Webinars video from getdrip-1',
803 'timestamp': 1463607249,
804 'upload_date': '20160518',
807 'skip_download': True,
812 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
816 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
817 'uploader': 'Sophos Security',
818 'title': 'Chet Chat 171 - Oct 29, 2014',
819 'upload_date': '20141029',
822 # Soundcloud multiple embeds
824 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
827 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
829 'playlist_mincount': 7,
833 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
837 'upload_date': '20141112',
838 'title': 'Rosetta #CometLanding webcast HL 10',
841 # Another Livestream embed, without 'new.' in URL
843 'url': 'https://www.freespeech.org/',
847 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
851 'skip_download': True,
856 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
859 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
861 'playlist_mincount': 2,
865 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
869 'upload_date': '20141126',
870 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
875 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
877 'id': '730m_DandD_1901_512k',
879 'uploader': 'www.abc.net.au',
880 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
883 # embedded viddler video
885 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
889 'uploader': 'deadspin',
890 'title': 'WALL-TO-GORTAT',
891 'timestamp': 1422285291,
892 'upload_date': '20150126',
894 'add_ie': ['Viddler'],
898 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
902 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
903 'description': 'md5:601cb790edd05908957dae8aaa866465',
904 'upload_date': '20150220',
906 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
910 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
914 'upload_date': '20150212',
915 'uploader': 'The National Archives UK',
916 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
917 'uploader_id': 'NationalArchives08',
918 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
923 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
924 'playlist_mincount': 5,
926 'id': 'aanslagen-kopenhagen',
927 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
932 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
936 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
939 # Kaltura embed (different embed code)
941 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
945 'upload_date': '20150127',
946 'uploader_id': 'PremierMedia',
948 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
951 # Kaltura embed protected with referrer
953 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
957 'title': 'Violetta - Achter De Schermen - Ruggero',
958 'description': 'Achter de schermen met Ruggero',
959 'timestamp': 1435133761,
960 'upload_date': '20150624',
961 'uploader_id': 'echojecka',
964 # Kaltura embed with single quotes
966 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
971 'timestamp': 1355743100,
972 'upload_date': '20121217',
973 'uploader_id': 'batchUser',
975 'add_ie': ['Kaltura'],
978 # Kaltura embedded via quoted entry_id
979 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
983 'title': '06_matthew_brender_raj_dutt',
984 'timestamp': 1466638791,
985 'upload_date': '20160622',
987 'add_ie': ['Kaltura'],
988 'expected_warnings': [
989 'Could not send HEAD request'
992 'skip_download': True,
996 # Kaltura embedded, some fileExt broken (#11480)
997 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1001 'title': 'Our "Standard Models" of particle physics and cosmology',
1002 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1003 'timestamp': 1321158993,
1004 'upload_date': '20111113',
1005 'uploader_id': 'kps1',
1007 'add_ie': ['Kaltura'],
1009 # Eagle.Platform embed (generic URL)
1011 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1012 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1016 'title': 'Навальный вышел на свободу',
1017 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1018 'thumbnail': 're:^https?://.*\.jpg$',
1024 # ClipYou (Eagle.Platform) embed (custom URL)
1026 'url': 'http://muz-tv.ru/play/7129/',
1027 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1031 'title': "'O Sole Mio",
1032 'thumbnail': 're:^https?://.*\.jpg$',
1039 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1043 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1044 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1045 'thumbnail': 're:^https?://.*\.jpg$',
1052 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1056 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1057 'thumbnail': 're:^https?://.*\.png$',
1063 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1064 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1068 'title': 'Facebook Creates "On This Day" | Crunch Report',
1073 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1077 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1082 # Crooks and Liars embed
1084 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1088 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1089 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1090 'timestamp': 1428207000,
1091 'upload_date': '20150405',
1092 'uploader': 'Heather',
1095 # Crooks and Liars external embed
1097 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1099 'id': 'MTE3MjUtMzQ2MzA',
1101 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1102 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1103 'timestamp': 1265032391,
1104 'upload_date': '20100201',
1105 'uploader': 'Heather',
1108 # NBC Sports vplayer embed
1110 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1112 'id': 'ln7x1qSThw4k',
1114 'title': "PFT Live: New leader in the 'new-look' defense",
1115 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1116 'uploader': 'NBCU-SPORTS',
1117 'upload_date': '20140107',
1118 'timestamp': 1389118457,
1123 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1124 'md5': '1aa589c675898ae6d37a17913cf68d66',
1126 'id': '701714499682',
1128 'title': 'PREVIEW: On Assignment: David Letterman',
1129 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
1134 'url': 'https://video.udn.com/news/300346',
1135 'md5': 'fd2060e988c326991037b9aff9df21a6',
1139 'title': '中一中男師變性 全校師生力挺',
1140 'thumbnail': 're:^https?://.*\.jpg$',
1144 'skip_download': True,
1149 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1151 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1153 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1154 'title': 'This is what separates the Excel masters from the wannabes',
1155 'duration': 191.933,
1159 'skip_download': True,
1162 # Brightcove URL in single quotes
1164 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1165 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1167 'id': '4255764656001',
1169 'title': 'SN Presents: Russell Martin, World Citizen',
1170 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1171 'uploader': 'Rogers Sportsnet',
1172 'uploader_id': '1704050871',
1173 'upload_date': '20150525',
1174 'timestamp': 1432570283,
1177 # Dailymotion Cloud video
1179 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1180 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1184 'title': 'Sauvons les abeilles ! - Le débat',
1185 'description': 'md5:d9082128b1c5277987825d684939ca26',
1186 'thumbnail': 're:^https?://.*\.jpe?g$',
1187 'timestamp': 1434970506,
1188 'upload_date': '20150622',
1189 'uploader': 'Public Sénat',
1190 'uploader_id': 'xa9gza',
1193 # OnionStudios embed
1195 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1199 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1200 'thumbnail': 're:^https?://.*\.jpe?g$',
1201 'uploader': 'ClickHole',
1202 'uploader_id': 'clickhole',
1207 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1209 'id': '74849a00-85a9-11e1-9660-123139220831',
1211 'title': '#whilewewatch',
1214 # AdobeTVVideo embed
1216 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1217 'md5': '43662b577c018ad707a63766462b1e87',
1221 'title': 'New experience with Acrobat DC',
1222 'description': 'New experience with Acrobat DC',
1223 'duration': 248.667,
1226 # BrightcoveInPageEmbed embed
1228 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1230 'id': '4238694884001',
1232 'title': 'Tabletop: Dread, Last Thoughts',
1233 'description': 'Tabletop: Dread, Last Thoughts',
1237 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1238 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1240 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1242 'id': '4785848093001',
1244 'title': 'The Cardinal Pell Interview',
1245 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1246 'uploader': 'GlobeCast Australia - GlobeStream',
1247 'uploader_id': '2733773828001',
1248 'upload_date': '20160304',
1249 'timestamp': 1457083087,
1253 'skip_download': True,
1256 # Another form of arte.tv embed
1258 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1259 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1261 'id': '030273-562_PLUS7-F',
1263 'title': 'ARTE Reportage - Nulle part, en France',
1264 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1265 'upload_date': '20160409',
1270 'url': 'http://www.wykop.pl/link/3088787/',
1271 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1273 'id': '874_1459135191',
1275 'title': 'Man shows poor quality of new apartment building',
1276 'description': 'The wall is like a sand pile.',
1277 'uploader': 'Lake8737',
1280 # Duplicated embedded video URLs
1282 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1284 'id': '149298443_480_16c25b74_2',
1286 'title': 'vs. Blue Orange Spring Game',
1287 'uploader': 'www.hudl.com',
1290 # twitter:player:stream embed
1292 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1296 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1297 'uploader': 'www.rtl.be',
1301 'skip_download': True,
1304 # twitter:player embed
1306 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1307 'md5': 'a3e0df96369831de324f0778e126653c',
1309 'id': '4909620399001',
1311 'title': 'What Do Black Holes Sound Like?',
1312 'description': 'what do black holes sound like',
1313 'upload_date': '20160524',
1314 'uploader_id': '29913724001',
1315 'timestamp': 1464107587,
1316 'uploader': 'TheAtlantic',
1318 'add_ie': ['BrightcoveLegacy'],
1320 # Facebook <iframe> embed
1322 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1323 'md5': 'fbcde74f534176ecb015849146dd3aee',
1325 'id': '599637780109885',
1327 'title': 'Facebook video #599637780109885',
1330 # Facebook API embed
1332 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1333 'md5': 'a47372ee61b39a7b90287094d447d94e',
1335 'id': '10153467542406923',
1337 'title': 'Facebook video #10153467542406923',
1340 # Wordpress "YouTube Video Importer" plugin
1342 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1343 'md5': 'd16797741b560b485194eddda8121b48',
1345 'id': 'HNTXWDXV9Is',
1347 'title': 'Blue Devils Drumline Stanford lot 2016',
1348 'upload_date': '20160627',
1349 'uploader_id': 'GENOCIDE8GENERAL10',
1350 'uploader': 'cylus cyrus',
1354 # video stored on custom kaltura server
1355 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1356 'md5': '537617d06e64dfed891fa1593c4b30cc',
1360 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1361 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1362 'uploader_id': 'videos.expansion@el-mundo.net',
1363 'upload_date': '20150429',
1364 'timestamp': 1430303472,
1366 'add_ie': ['Kaltura'],
1369 # Non-standard Vimeo embed
1370 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1371 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1375 'title': 'Understanding the web - Teaser',
1376 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1377 'upload_date': '20151214',
1378 'uploader': 'OpenClassrooms',
1379 'uploader_id': 'openclassrooms',
1381 'add_ie': ['Vimeo'],
1384 # generic vimeo embed that requires original URL passed as Referer
1385 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1386 'only_matching': True,
1389 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1390 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1392 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1394 'title': 'Big Buck Bunny',
1395 'description': 'Royalty free test video',
1396 'timestamp': 1432816365,
1397 'upload_date': '20150528',
1401 'skip_download': True,
1403 'add_ie': [ArkenaIE.ie_key()],
1406 'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
1410 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1413 'skip_download': True,
1415 'add_ie': [Vbox7IE.ie_key()],
1419 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1422 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1424 'playlist_mincount': 3,
1428 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1430 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1431 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1433 'playlist_mincount': 2,
1436 # # TODO: find another test
1437 # # http://schema.org/VideoObject
1438 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1439 # 'md5': '888dcf08b7ea671381f00fab74692755',
1441 # 'id': 'nyvTSJMKId',
1443 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1444 # 'description': '#love for cats.',
1445 # 'timestamp': 1461244995,
1446 # 'upload_date': '20160421',
1449 # 'force_generic_extractor': True,
1454 def report_following_redirect(self, new_url):
1455 """Report information extraction."""
1456 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1458 def _extract_rss(self, url, video_id, doc):
1459 playlist_title = doc.find('./channel/title').text
1460 playlist_desc_el = doc.find('./channel/description')
1461 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1464 for it in doc.findall('./channel/item'):
1465 next_url = xpath_text(it, 'link', fatal=False)
1467 enclosure_nodes = it.findall('./enclosure')
1468 for e in enclosure_nodes:
1469 next_url = e.attrib.get('url')
1479 'title': it.find('title').text,
1483 '_type': 'playlist',
1485 'title': playlist_title,
1486 'description': playlist_desc,
1490 def _extract_camtasia(self, url, video_id, webpage):
1491 """ Returns None if no camtasia video can be found. """
1493 camtasia_cfg = self._search_regex(
1494 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1495 webpage, 'camtasia configuration file', default=None)
1496 if camtasia_cfg is None:
1499 title = self._html_search_meta('DC.title', webpage, fatal=True)
1501 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1502 camtasia_cfg = self._download_xml(
1503 camtasia_url, video_id,
1504 note='Downloading camtasia configuration',
1505 errnote='Failed to download camtasia configuration')
1506 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1509 for n in fileset_node.getchildren():
1510 url_n = n.find('./uri')
1515 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1516 'title': '%s - %s' % (title, n.tag),
1517 'url': compat_urlparse.urljoin(url, url_n.text),
1518 'duration': float_or_none(n.find('./duration').text),
1522 '_type': 'playlist',
1527 def _real_extract(self, url):
1528 if url.startswith('//'):
1531 'url': self.http_scheme() + url,
1534 parsed_url = compat_urlparse.urlparse(url)
1535 if not parsed_url.scheme:
1536 default_search = self._downloader.params.get('default_search')
1537 if default_search is None:
1538 default_search = 'fixup_error'
1540 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1542 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1543 return self.url_result('http://' + url)
1544 elif default_search != 'fixup_error':
1545 if default_search == 'auto_warning':
1546 if re.match(r'^(?:url|URL)$', url):
1547 raise ExtractorError(
1548 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1551 self._downloader.report_warning(
1552 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1553 return self.url_result('ytsearch:' + url)
1555 if default_search in ('error', 'fixup_error'):
1556 raise ExtractorError(
1557 '%r is not a valid URL. '
1558 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1559 % (url, url), expected=True)
1561 if ':' not in default_search:
1562 default_search += ':'
1563 return self.url_result(default_search + url)
1565 url, smuggled_data = unsmuggle_url(url)
1566 force_videoid = None
1567 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1568 if smuggled_data and 'force_videoid' in smuggled_data:
1569 force_videoid = smuggled_data['force_videoid']
1570 video_id = force_videoid
1572 video_id = self._generic_id(url)
1574 self.to_screen('%s: Requesting header' % video_id)
1576 head_req = HEADRequest(url)
1577 head_response = self._request_webpage(
1579 note=False, errnote='Could not send HEAD request to %s' % url,
1582 if head_response is not False:
1583 # Check for redirect
1584 new_url = head_response.geturl()
1586 self.report_following_redirect(new_url)
1588 new_url = smuggle_url(
1589 new_url, {'force_videoid': force_videoid})
1590 return self.url_result(new_url)
1592 full_response = None
1593 if head_response is False:
1594 request = sanitized_Request(url)
1595 request.add_header('Accept-Encoding', '*')
1596 full_response = self._request_webpage(request, video_id)
1597 head_response = full_response
1601 'title': self._generic_title(url),
1602 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1605 # Check for direct link to a video
1606 content_type = head_response.headers.get('Content-Type', '').lower()
1607 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1609 format_id = m.group('format_id')
1610 if format_id.endswith('mpegurl'):
1611 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1612 elif format_id == 'f4m':
1613 formats = self._extract_f4m_formats(url, video_id)
1616 'format_id': m.group('format_id'),
1618 'vcodec': 'none' if m.group('type') == 'audio' else None
1620 info_dict['direct'] = True
1621 self._sort_formats(formats)
1622 info_dict['formats'] = formats
1625 if not self._downloader.params.get('test', False) and not is_intentional:
1626 force = self._downloader.params.get('force_generic_extractor', False)
1627 self._downloader.report_warning(
1628 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1630 if not full_response:
1631 request = sanitized_Request(url)
1632 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1633 # making it impossible to download only chunk of the file (yet we need only 512kB to
1634 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1635 # that will always result in downloading the whole file that is not desirable.
1636 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1637 # to accept raw bytes and being able to download only a chunk.
1638 # It may probably better to solve this by checking Content-Type for application/octet-stream
1639 # after HEAD request finishes, but not sure if we can rely on this.
1640 request.add_header('Accept-Encoding', '*')
1641 full_response = self._request_webpage(request, video_id)
1643 first_bytes = full_response.read(512)
1645 # Is it an M3U playlist?
1646 if first_bytes.startswith(b'#EXTM3U'):
1647 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1648 self._sort_formats(info_dict['formats'])
1651 # Maybe it's a direct link to a video?
1652 # Be careful not to download the whole thing!
1653 if not is_html(first_bytes):
1654 self._downloader.report_warning(
1655 'URL could be a direct video link, returning it as such.')
1662 webpage = self._webpage_read_content(
1663 full_response, url, video_id, prefix=first_bytes)
1665 self.report_extraction(video_id)
1667 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1669 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1670 if doc.tag == 'rss':
1671 return self._extract_rss(url, video_id, doc)
1672 elif doc.tag == 'SmoothStreamingMedia':
1673 info_dict['formats'] = self._parse_ism_formats(doc, url)
1674 self._sort_formats(info_dict['formats'])
1676 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1677 smil = self._parse_smil(doc, url, video_id)
1678 self._sort_formats(smil['formats'])
1680 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1681 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1682 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1683 info_dict['formats'] = self._parse_mpd_formats(
1685 mpd_base_url=full_response.geturl().rpartition('/')[0],
1687 self._sort_formats(info_dict['formats'])
1689 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1690 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1691 self._sort_formats(info_dict['formats'])
1693 except compat_xml_parse_error:
1696 # Is it a Camtasia project?
1697 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1698 if camtasia_res is not None:
1701 # Sometimes embedded video player is hidden behind percent encoding
1702 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1703 # Unescaping the whole page allows to handle those cases in a generic way
1704 webpage = compat_urllib_parse_unquote(webpage)
1706 # it's tempting to parse this further, but you would
1707 # have to take into account all the variations like
1708 # Video Title - Site Name
1709 # Site Name | Video Title
1710 # Video Title - Tagline | Site Name
1711 # and so on and so forth; it's just not practical
1712 video_title = self._og_search_title(
1713 webpage, default=None) or self._html_search_regex(
1714 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1717 # Try to detect age limit automatically
1718 age_limit = self._rta_search(webpage)
1719 # And then there are the jokers who advertise that they use RTA,
1720 # but actually don't.
1721 AGE_LIMIT_MARKERS = [
1722 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1724 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1727 # video uploader is domain name
1728 video_uploader = self._search_regex(
1729 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1731 video_description = self._og_search_description(webpage, default=None)
1732 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1735 def _playlist_from_matches(matches, getter=None, ie=None):
1737 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1739 return self.playlist_result(
1740 urlrs, playlist_id=video_id, playlist_title=video_title)
1742 # Look for Brightcove Legacy Studio embeds
1743 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1745 self.to_screen('Brightcove video detected.')
1748 'url': smuggle_url(bc_url, {'Referer': url}),
1749 'ie_key': 'BrightcoveLegacy'
1750 } for bc_url in bc_urls]
1753 '_type': 'playlist',
1754 'title': video_title,
1759 # Look for Brightcove New Studio embeds
1760 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1762 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1764 # Look for ThePlatform embeds
1765 tp_urls = ThePlatformIE._extract_urls(webpage)
1767 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1769 # Look for Vessel embeds
1770 vessel_urls = VesselIE._extract_urls(webpage)
1772 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1774 # Look for embedded rtl.nl player
1775 matches = re.findall(
1776 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1779 return _playlist_from_matches(matches, ie='RtlNl')
1781 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1783 return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
1785 vid_me_embed_url = self._search_regex(
1786 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1787 webpage, 'vid.me embed', default=None)
1788 if vid_me_embed_url is not None:
1789 return self.url_result(vid_me_embed_url, 'Vidme')
1791 # Look for embedded YouTube player
1792 matches = re.findall(r'''(?x)
1801 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1805 return _playlist_from_matches(
1806 matches, lambda m: unescapeHTML(m[1]))
1808 # Look for lazyYT YouTube embed
1809 matches = re.findall(
1810 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1812 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1814 # Look for Wordpress "YouTube Video Importer" plugin
1815 matches = re.findall(r'''(?x)<div[^>]+
1816 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1817 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1819 return _playlist_from_matches(matches, lambda m: m[-1])
1821 matches = DailymotionIE._extract_urls(webpage)
1823 return _playlist_from_matches(matches)
1825 # Look for embedded Dailymotion playlist player (#3822)
1827 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1829 playlists = re.findall(
1830 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1832 return _playlist_from_matches(
1833 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1835 # Look for embedded Wistia player
1837 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1839 embed_url = self._proto_relative_url(
1840 unescapeHTML(match.group('url')))
1842 '_type': 'url_transparent',
1845 'uploader': video_uploader,
1848 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1851 '_type': 'url_transparent',
1852 'url': 'wistia:%s' % match.group('id'),
1854 'uploader': video_uploader,
1859 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1860 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1863 return self.url_result(self._proto_relative_url(
1864 'wistia:%s' % match.group('id')), 'Wistia')
1866 # Look for SVT player
1867 svt_url = SVTIE._extract_url(webpage)
1869 return self.url_result(svt_url, 'SVT')
1871 # Look for embedded condenast player
1872 matches = re.findall(
1873 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1877 '_type': 'playlist',
1880 'ie_key': 'CondeNast',
1882 } for ma in matches],
1883 'title': video_title,
1887 # Look for Bandcamp pages with custom domain
1888 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1889 if mobj is not None:
1890 burl = unescapeHTML(mobj.group(1))
1891 # Don't set the extractor because it can be a track url or an album
1892 return self.url_result(burl)
1894 # Look for embedded Vevo player
1896 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1897 if mobj is not None:
1898 return self.url_result(mobj.group('url'))
1900 # Look for embedded Viddler player
1902 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1904 if mobj is not None:
1905 return self.url_result(mobj.group('url'))
1907 # Look for NYTimes player
1909 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1911 if mobj is not None:
1912 return self.url_result(mobj.group('url'))
1914 # Look for Libsyn player
1916 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1917 if mobj is not None:
1918 return self.url_result(mobj.group('url'))
1920 # Look for Ooyala videos
1921 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1922 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1923 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1924 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1925 if mobj is not None:
1926 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1928 # Look for multiple Ooyala embeds on SBN network websites
1929 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1930 if mobj is not None:
1931 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1933 return _playlist_from_matches(
1934 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1936 # Look for Aparat videos
1937 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1938 if mobj is not None:
1939 return self.url_result(mobj.group(1), 'Aparat')
1941 # Look for MPORA videos
1942 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1943 if mobj is not None:
1944 return self.url_result(mobj.group(1), 'Mpora')
1946 # Look for embedded NovaMov-based player
1948 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1949 (?P<url>http://(?:(?:embed|www)\.)?
1951 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1952 videoweed\.(?:es|com)|
1953 movshare\.(?:net|sx|ag)|
1954 divxstage\.(?:eu|net|ch|co|at|ag))
1955 /embed\.php.+?)\1''', webpage)
1956 if mobj is not None:
1957 return self.url_result(mobj.group('url'))
1959 # Look for embedded Facebook player
1960 facebook_url = FacebookIE._extract_url(webpage)
1961 if facebook_url is not None:
1962 return self.url_result(facebook_url, 'Facebook')
1964 # Look for embedded VK player
1965 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1966 if mobj is not None:
1967 return self.url_result(mobj.group('url'), 'VK')
1969 # Look for embedded Odnoklassniki player
1970 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1971 if mobj is not None:
1972 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1974 # Look for embedded ivi player
1975 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1976 if mobj is not None:
1977 return self.url_result(mobj.group('url'), 'Ivi')
1979 # Look for embedded Huffington Post player
1981 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1982 if mobj is not None:
1983 return self.url_result(mobj.group('url'), 'HuffPost')
1986 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1987 if mobj is not None:
1988 return self.url_result(mobj.group('url'))
1989 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1990 if mobj is not None:
1991 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1993 # Look for funnyordie embed
1994 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1996 return _playlist_from_matches(
1997 matches, getter=unescapeHTML, ie='FunnyOrDie')
1999 # Look for BBC iPlayer embed
2000 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2002 return _playlist_from_matches(matches, ie='BBCCoUk')
2004 # Look for embedded RUTV player
2005 rutv_url = RUTVIE._extract_url(webpage)
2007 return self.url_result(rutv_url, 'RUTV')
2009 # Look for embedded TVC player
2010 tvc_url = TVCIE._extract_url(webpage)
2012 return self.url_result(tvc_url, 'TVC')
2014 # Look for embedded SportBox player
2015 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2017 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
2019 # Look for embedded XHamster player
2020 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2022 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
2024 # Look for embedded TNAFlixNetwork player
2025 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2027 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
2029 # Look for embedded PornHub player
2030 pornhub_urls = PornHubIE._extract_urls(webpage)
2032 return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
2034 # Look for embedded DrTuber player
2035 drtuber_urls = DrTuberIE._extract_urls(webpage)
2037 return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
2039 # Look for embedded RedTube player
2040 redtube_urls = RedTubeIE._extract_urls(webpage)
2042 return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
2044 # Look for embedded Tvigle player
2046 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2047 if mobj is not None:
2048 return self.url_result(mobj.group('url'), 'Tvigle')
2050 # Look for embedded TED player
2052 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2053 if mobj is not None:
2054 return self.url_result(mobj.group('url'), 'TED')
2056 # Look for embedded Ustream videos
2058 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
2059 if mobj is not None:
2060 return self.url_result(mobj.group('url'), 'Ustream')
2062 # Look for embedded arte.tv player
2064 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2066 if mobj is not None:
2067 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2069 # Look for embedded francetv player
2071 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2073 if mobj is not None:
2074 return self.url_result(mobj.group('url'))
2076 # Look for embedded smotri.com player
2077 smotri_url = SmotriIE._extract_url(webpage)
2079 return self.url_result(smotri_url, 'Smotri')
2081 # Look for embedded Myvi.ru player
2082 myvi_url = MyviIE._extract_url(webpage)
2084 return self.url_result(myvi_url)
2086 # Look for embedded soundcloud player
2087 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2089 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2091 # Look for embedded mtvservices player
2092 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2094 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2096 # Look for embedded yahoo player
2098 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2100 if mobj is not None:
2101 return self.url_result(mobj.group('url'), 'Yahoo')
2103 # Look for embedded sbs.com.au player
2107 <meta\s+property="og:video"\s+content=|
2110 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2112 if mobj is not None:
2113 return self.url_result(mobj.group('url'), 'SBS')
2115 # Look for embedded Cinchcast player
2117 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2119 if mobj is not None:
2120 return self.url_result(mobj.group('url'), 'Cinchcast')
2123 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2127 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2129 if mobj is not None:
2130 return self.url_result(mobj.group('url'), 'MLB')
2133 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2135 if mobj is not None:
2136 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2139 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2141 if mobj is not None:
2142 return self.url_result(mobj.group('url'), 'Livestream')
2144 # Look for Zapiks embed
2146 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2147 if mobj is not None:
2148 return self.url_result(mobj.group('url'), 'Zapiks')
2150 # Look for Kaltura embeds
2151 kaltura_url = KalturaIE._extract_url(webpage)
2153 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2155 # Look for Eagle.Platform embeds
2156 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2157 if eagleplatform_url:
2158 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2160 # Look for ClipYou (uses Eagle.Platform) embeds
2162 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2163 if mobj is not None:
2164 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2166 # Look for Pladform embeds
2167 pladform_url = PladformIE._extract_url(webpage)
2169 return self.url_result(pladform_url)
2171 # Look for Videomore embeds
2172 videomore_url = VideomoreIE._extract_url(webpage)
2174 return self.url_result(videomore_url)
2176 # Look for Webcaster embeds
2177 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2179 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2181 # Look for Playwire embeds
2183 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2184 if mobj is not None:
2185 return self.url_result(mobj.group('url'))
2187 # Look for 5min embeds
2189 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2190 if mobj is not None:
2191 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2193 # Look for Crooks and Liars embeds
2195 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2196 if mobj is not None:
2197 return self.url_result(mobj.group('url'))
2199 # Look for NBC Sports VPlayer embeds
2200 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2202 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2204 # Look for NBC News embeds
2205 nbc_news_embed_url = re.search(
2206 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2207 if nbc_news_embed_url:
2208 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2210 # Look for Google Drive embeds
2211 google_drive_url = GoogleDriveIE._extract_url(webpage)
2212 if google_drive_url:
2213 return self.url_result(google_drive_url, 'GoogleDrive')
2215 # Look for UDN embeds
2217 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2218 if mobj is not None:
2219 return self.url_result(
2220 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2222 # Look for Senate ISVP iframe
2223 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2225 return self.url_result(senate_isvp_url, 'SenateISVP')
2227 # Look for Dailymotion Cloud videos
2228 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2230 return self.url_result(dmcloud_url, 'DailymotionCloud')
2232 # Look for OnionStudios embeds
2233 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2234 if onionstudios_url:
2235 return self.url_result(onionstudios_url)
2237 # Look for ViewLift embeds
2238 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2240 return self.url_result(viewlift_url)
2242 # Look for JWPlatform embeds
2243 jwplatform_url = JWPlatformIE._extract_url(webpage)
2245 return self.url_result(jwplatform_url, 'JWPlatform')
2247 # Look for Digiteka embeds
2248 digiteka_url = DigitekaIE._extract_url(webpage)
2250 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2252 # Look for Arkena embeds
2253 arkena_url = ArkenaIE._extract_url(webpage)
2255 return self.url_result(arkena_url, ArkenaIE.ie_key())
2257 # Look for Piksel embeds
2258 piksel_url = PikselIE._extract_url(webpage)
2260 return self.url_result(piksel_url, PikselIE.ie_key())
2262 # Look for Limelight embeds
2263 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2267 'Channel': 'channel',
2268 'ChannelList': 'channel_list',
2270 return self.url_result('limelight:%s:%s' % (
2271 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2275 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2277 name=(["\'])flashVars\2[^>]+
2278 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2281 return self.url_result('limelight:media:%s' % mobj.group('id'))
2283 # Look for AdobeTVVideo embeds
2285 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2287 if mobj is not None:
2288 return self.url_result(
2289 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2292 # Look for Vine embeds
2294 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2296 if mobj is not None:
2297 return self.url_result(
2298 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2300 # Look for VODPlatform embeds
2302 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2304 if mobj is not None:
2305 return self.url_result(
2306 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2308 # Look for Mangomolo embeds
2310 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2312 video\?.*?\bid=(?P<video_id>\d+)|
2313 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2314 ).+?)\1''', webpage)
2315 if mobj is not None:
2317 '_type': 'url_transparent',
2318 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2319 'title': video_title,
2320 'description': video_description,
2321 'thumbnail': video_thumbnail,
2322 'uploader': video_uploader,
2324 video_id = mobj.group('video_id')
2327 'ie_key': 'MangomoloVideo',
2332 'ie_key': 'MangomoloLive',
2333 'id': mobj.group('channel_id'),
2337 # Look for Instagram embeds
2338 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2339 if instagram_embed_url is not None:
2340 return self.url_result(
2341 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2343 # Look for LiveLeak embeds
2344 liveleak_url = LiveLeakIE._extract_url(webpage)
2346 return self.url_result(liveleak_url, 'LiveLeak')
2348 # Look for 3Q SDN embeds
2349 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2352 '_type': 'url_transparent',
2353 'ie_key': ThreeQSDNIE.ie_key(),
2354 'url': self._proto_relative_url(threeqsdn_url),
2355 'title': video_title,
2356 'description': video_description,
2357 'thumbnail': video_thumbnail,
2358 'uploader': video_uploader,
2361 # Look for VBOX7 embeds
2362 vbox7_url = Vbox7IE._extract_url(webpage)
2364 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2366 # Look for DBTV embeds
2367 dbtv_urls = DBTVIE._extract_urls(webpage)
2369 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2371 # Look for Videa embeds
2372 videa_urls = VideaIE._extract_urls(webpage)
2374 return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
2376 # Looking for http://schema.org/VideoObject
2377 json_ld = self._search_json_ld(
2378 webpage, video_id, default={}, expected_type='VideoObject')
2379 if json_ld.get('url'):
2381 'title': video_title or info_dict['title'],
2382 'description': video_description,
2383 'thumbnail': video_thumbnail,
2384 'age_limit': age_limit
2386 info_dict.update(json_ld)
2389 # Look for HTML5 media
2390 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2392 for entry in entries:
2395 'title': video_title,
2397 self._sort_formats(entry['formats'])
2398 return self.playlist_result(entries)
2400 def check_video(vurl):
2401 if YoutubeIE.suitable(vurl):
2403 vpath = compat_urlparse.urlparse(vurl).path
2404 vext = determine_ext(vpath)
2405 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2407 def filter_video(urls):
2408 return list(filter(check_video, urls))
2410 # Start with something easy: JW Player in SWFObject
2411 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2413 # Look for gorilla-vid style embedding
2414 found = filter_video(re.findall(r'''(?sx)
2418 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2421 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2423 # Broaden the search a little bit
2424 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2426 # Broaden the findall a little bit: JWPlayer JS loader
2427 found = filter_video(re.findall(
2428 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2431 found = filter_video(re.findall(r'''(?xs)
2432 flowplayer\("[^"]+",\s*
2434 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2435 ["']?url["']?\s*:\s*["']([^"']+)["']
2440 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2442 # Try to find twitter cards info
2443 # twitter:player:stream should be checked before twitter:player since
2444 # it is expected to contain a raw stream (see
2445 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2446 found = filter_video(re.findall(
2447 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2449 # We look for Open Graph info:
2450 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2451 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2452 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2453 if m_video_type is not None:
2454 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2456 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2458 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2459 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2462 # Look also in Refresh HTTP header
2463 refresh_header = head_response.headers.get('Refresh')
2465 # In python 2 response HTTP headers are bytestrings
2466 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2467 refresh_header = refresh_header.decode('iso-8859-1')
2468 found = re.search(REDIRECT_REGEX, refresh_header)
2470 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2471 self.report_following_redirect(new_url)
2478 # twitter:player is a https URL to iframe player that may or may not
2479 # be supported by youtube-dl thus this is checked the very last (see
2480 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2481 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2483 return self.url_result(embed_url)
2486 raise UnsupportedError(url)
2489 for video_url in orderedSet(found):
2490 video_url = unescapeHTML(video_url)
2491 video_url = video_url.replace('\\/', '/')
2492 video_url = compat_urlparse.urljoin(url, video_url)
2493 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2495 # Sometimes, jwplayer extraction will result in a YouTube URL
2496 if YoutubeIE.suitable(video_url):
2497 entries.append(self.url_result(video_url, 'Youtube'))
2500 # here's a fun little line of code for you:
2501 video_id = os.path.splitext(video_id)[0]
2505 'uploader': video_uploader,
2506 'title': video_title,
2507 'age_limit': age_limit,
2510 ext = determine_ext(video_url)
2512 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2514 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2516 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2518 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2520 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2521 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2522 # Just matching .ism/manifest is not enough to be reliably sure
2523 # whether it's actually an ISM manifest or some other streaming
2524 # manifest since there are various streaming URL formats
2525 # possible (see [1]) as well as some other shenanigans like
2526 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2528 # Thus the most reasonable way to solve this is to delegate
2529 # to generic extractor in order to look into the contents of
2530 # the manifest itself.
2531 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2532 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2533 entry_info_dict = self.url_result(
2534 smuggle_url(video_url, {'to_generic': True}),
2537 entry_info_dict['url'] = video_url
2539 if entry_info_dict.get('formats'):
2540 self._sort_formats(entry_info_dict['formats'])
2542 entries.append(entry_info_dict)
2544 if len(entries) == 1:
2547 for num, e in enumerate(entries, start=1):
2548 # 'url' results don't have a title
2549 if e.get('title') is not None:
2550 e['title'] = '%s (%d)' % (e['title'], num)
2552 '_type': 'playlist',