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 .tunein import TuneInBaseIE
77 from .vbox7 import Vbox7IE
78 from .dbtv import DBTVIE
79 from .piksel import PikselIE
80 from .videa import VideaIE
83 class GenericIE(InfoExtractor):
84 IE_DESC = 'Generic downloader that works on some sites'
88 # Direct link to a video
90 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
91 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
96 'upload_date': '20100513',
99 # Direct link to media delivered compressed (until Accept-Encoding is *)
101 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
102 'md5': '128c42e68b13950268b648275386fc74',
104 'id': 'FictionJunction-Parallel_Hearts',
106 'title': 'FictionJunction-Parallel_Hearts',
107 'upload_date': '20140522',
109 'expected_warnings': [
110 'URL could be a direct video link, returning it as such.'
112 'skip': 'URL invalid',
114 # Direct download with broken HEAD
116 'url': 'http://ai-radio.org:8000/radio.opus',
123 'skip_download': True, # infinite live stream
125 'expected_warnings': [
126 r'501.*Not Implemented',
130 # Direct link with incorrect MIME type
132 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
133 'md5': '4ccbebe5f36706d85221f204d7eb5913',
135 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
136 'id': '5_Lennart_Poettering_-_Systemd',
138 'title': '5_Lennart_Poettering_-_Systemd',
139 'upload_date': '20141120',
141 'expected_warnings': [
142 'URL could be a direct video link, returning it as such.'
147 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
149 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
150 'title': 'Zero Punctuation',
151 'description': 're:.*groundbreaking video review series.*'
153 'playlist_mincount': 11,
155 # RSS feed with enclosure
157 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
159 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
161 'upload_date': '20150228',
162 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
165 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
167 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
171 'title': 'Automatics, robotics and biocybernetics',
172 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
173 'upload_date': '20130627',
174 'formats': 'mincount:16',
175 'subtitles': 'mincount:1',
178 'force_generic_extractor': True,
179 'skip_download': True,
182 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
184 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
189 'formats': 'mincount:1',
192 'skip_download': True,
195 # SMIL from https://www.restudy.dk/video/play/id/1637
197 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
201 'title': 'video_1637',
202 'formats': 'mincount:3',
205 'skip_download': True,
208 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
210 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
212 'id': 'smil-service',
214 'title': 'smil-service',
215 'formats': 'mincount:1',
218 'skip_download': True,
221 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
223 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
227 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
228 'formats': 'mincount:3',
231 'skip_download': True,
234 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
236 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
238 'id': 'mZlp2ctYIUEB',
240 'title': 'Tikibad ontruimd wegens brand',
241 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
242 'thumbnail': r're:^https?://.*\.jpg$',
246 'skip_download': True,
249 # MPD from http://dash-mse-test.appspot.com/media.html
251 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
252 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
254 'id': 'car-20120827-manifest',
256 'title': 'car-20120827-manifest',
257 'formats': 'mincount:9',
258 'upload_date': '20130904',
261 'format': 'bestvideo',
264 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
266 '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',
271 'formats': 'mincount:8',
275 'skip_download': True,
277 'skip': 'video gone',
279 # m3u8 served with Content-Type: text/plain
281 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
286 'upload_date': '20140720',
287 'formats': 'mincount:11',
291 'skip_download': True,
293 'skip': 'video gone',
297 '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',
301 'upload_date': '20130224',
302 'uploader_id': 'TheVerge',
303 'description': r're:^Chris Ziegler takes a look at the\.*',
304 'uploader': 'The Verge',
305 'title': 'First Firefox OS phones side-by-side',
308 'skip_download': False,
312 # redirect in Refresh HTTP header
313 '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',
317 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
318 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
319 'upload_date': '20150917',
320 'uploader_id': 'brtvofficial',
321 'uploader': 'Boiler Room',
324 'skip_download': False,
328 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
329 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
331 'id': '13601338388002',
333 'uploader': 'www.hodiho.fr',
334 'title': 'R\u00e9gis plante sa Jeep',
337 # bandcamp page with custom domain
339 'add_ie': ['Bandcamp'],
340 'url': 'http://bronyrock.com/track/the-pony-mash',
344 'title': 'The Pony Mash',
345 'uploader': 'M_Pallante',
347 'skip': 'There is a limit of 200 free downloads / month for the test song',
350 # embedded brightcove video
351 # it also tests brightcove videos that need to set the 'Referer'
352 # in the http requests
353 'add_ie': ['BrightcoveLegacy'],
354 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
356 'id': '2765128793001',
358 'title': 'Le cours de bourse : l’analyse technique',
359 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
360 'uploader': 'BFM BUSINESS',
363 'skip_download': True,
367 # embedded with itemprop embedURL and video id spelled as `idVideo`
368 'add_id': ['BrightcoveLegacy'],
369 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
371 'id': '5255628253001',
373 'title': 'md5:37c519b1128915607601e75a87995fc0',
374 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
375 'uploader': 'BFM BUSINESS',
376 'uploader_id': '876450612001',
377 'timestamp': 1482255315,
378 'upload_date': '20161220',
381 'skip_download': True,
385 # https://github.com/rg3/youtube-dl/issues/2253
386 'url': 'http://bcove.me/i6nfkrc3',
387 'md5': '0ba9446db037002366bab3b3eb30c88c',
389 'id': '3101154703001',
391 'title': 'Still no power',
392 'uploader': 'thestar.com',
393 '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.',
395 'add_ie': ['BrightcoveLegacy'],
396 'skip': 'video gone',
399 'url': 'http://www.championat.com/video/football/v/87/87499.html',
400 'md5': 'fb973ecf6e4a78a67453647444222983',
402 'id': '3414141473001',
404 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
405 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
406 'uploader': 'Championat',
410 # https://github.com/rg3/youtube-dl/issues/3541
411 'add_ie': ['BrightcoveLegacy'],
412 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
414 'id': '3866516442001',
416 'title': 'Leer mij vrouwen kennen: Aflevering 1',
417 'description': 'Leer mij vrouwen kennen: Aflevering 1',
418 'uploader': 'SBS Broadcasting',
420 'skip': 'Restricted to Netherlands',
422 'skip_download': True, # m3u8 download
426 # Brightcove with alternative playerID key
427 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
429 'id': 'nmeth.2062_SV1',
430 'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
434 'id': '2228375078001',
436 'title': 'nmeth.2062-sv1',
437 'description': 'nmeth.2062-sv1',
438 'timestamp': 1363357591,
439 'upload_date': '20130315',
440 'uploader': 'Nature Publishing Group',
441 'uploader_id': '1964492299001',
447 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
448 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
450 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
452 'title': '2cc213299525360.mov', # that's what we get
455 'add_ie': ['Ooyala'],
458 # ooyala video embedded with http://player.ooyala.com/iframe.js
459 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
461 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
463 'title': '"Steve Jobs: Man in the Machine" trailer',
464 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
468 'skip_download': True,
470 'skip': 'movie expired',
474 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
478 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
479 'upload_date': '20140225',
480 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
481 'uploader': 'Tested',
482 'uploader_id': 'testedcom',
484 # No need to test YoutubeIE here
486 'skip_download': True,
491 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
495 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
496 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
498 # HEAD requests lead to endless 301, while GET is OK
499 'expected_warnings': ['301'],
503 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
507 'title': 'Охотское море стало целиком российским',
508 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
512 'skip_download': True,
517 '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/',
521 'title': 'Дошкольное воспитание',
526 'url': 'http://www.vestifinance.ru/articles/25753',
529 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
534 'title': 'Госзаказ. День 3',
540 'title': 'Госзаказ. День 2',
546 'title': 'Госзаказ. День 1',
552 'skip_download': True,
557 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
559 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
561 'title': 'Ужастики, русский трейлер (2015)',
562 'thumbnail': r're:^https?://.*\.jpg$',
568 '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',
571 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
573 'playlist_mincount': 7,
574 # This forum does not allow <iframe> syntaxes anymore
575 # Now HTML tags are displayed as-is
576 'skip': 'No videos on this page',
580 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
581 'md5': '65fdff94098e4a607385a60c5177c638',
585 'title': 'Hidden miracles of the natural world',
586 'uploader': 'Louie Schwartzberg',
587 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
590 # Embedded Ustream video
592 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
593 'md5': '27b99cdb639c9b12a79bca876a073417',
597 'uploader': 'AU SPA: The NSA and Privacy',
598 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
601 # nowvideo embed hidden behind percent encoding
603 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
604 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
606 'id': '06e53103ca9aa',
608 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
609 'description': 'No description',
614 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
615 'md5': '7653032cbb25bf6c80d80f217055fa43',
617 'id': '048195-004_PLUS7-F',
620 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
621 'upload_date': '20140320',
624 'skip_download': 'Requires rtmpdump'
626 'skip': 'video gone',
630 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
634 'title': 'Alcaline, le concert avec Calogero',
635 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
636 'upload_date': '20150226',
637 'timestamp': 1424989860,
642 'skip_download': True,
644 'expected_warnings': [
650 'url': 'http://www.wired.com/2014/04/honda-asimo/',
651 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
653 'id': '53501be369702d3275860000',
655 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
660 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
661 'md5': '441aeeb82eb72c422c7f14ec533999cd',
663 'id': 'k2mm4bCdJ6CQ2i7c8o2',
665 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
666 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
668 'uploader_id': 'xgditw',
669 'upload_date': '20140425',
670 'timestamp': 1398441542,
672 'add_ie': ['Dailymotion'],
676 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
680 'title': 'The NBL Auction 2014',
681 'uploader': 'BADMINTON England',
682 'uploader_id': 'BADMINTONEvents',
683 'upload_date': '20140603',
684 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
686 'add_ie': ['Youtube'],
688 'skip_download': True,
693 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
694 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
696 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
698 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
699 'description': 'Two valets share their love for movie star Liam Neesons.',
700 'timestamp': 1349922600,
701 'upload_date': '20121011',
704 # YouTube embed via <data-embed-url="">
706 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
710 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
711 'uploader': 'Gameloft',
712 'uploader_id': 'gameloft',
713 'upload_date': '20140828',
714 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
717 'skip_download': True,
722 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
724 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
726 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
727 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
732 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
734 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
735 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
741 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
746 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
747 'md5': '9d65602bf31c6e20014319c7d07fba27',
749 'id': '5123ea6d5e5a7',
752 'uploader': 'www.handjobhub.com',
753 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
756 # Multiple brightcove videos
757 # https://github.com/rg3/youtube-dl/issues/2283
759 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
761 'id': 'always-never',
762 'title': 'Always / Never - The New Yorker',
766 'extract_flat': False,
767 'skip_download': True,
772 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
773 'md5': '96f09a37e44da40dd083e12d9a683327',
777 'title': 'Ump changes call to ball',
778 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
780 'timestamp': 1401537900,
781 'upload_date': '20140531',
782 'thumbnail': r're:^https?://.*\.jpg$',
787 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
788 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
792 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
793 'description': 'a Paywall Videos video from Remilon',
795 'uploader': 'study.com',
796 'timestamp': 1459678540,
797 'upload_date': '20160403',
798 'filesize': 24687186,
802 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
803 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
807 'title': 'Conversation about Hexagonal Rails Part 1',
808 'description': 'a Martin Fowler video from ThoughtWorks',
810 'uploader': 'thoughtworks.wistia.com',
811 'timestamp': 1401832161,
812 'upload_date': '20140603',
815 # Wistia standard embed (async)
817 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
821 'title': 'Drip Brennan Dunn Workshop',
822 'description': 'a JV Webinars video from getdrip-1',
824 'timestamp': 1463607249,
825 'upload_date': '20160518',
828 'skip_download': True,
833 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
837 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
838 'uploader': 'Sophos Security',
839 'title': 'Chet Chat 171 - Oct 29, 2014',
840 'upload_date': '20141029',
843 # Soundcloud multiple embeds
845 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
848 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
850 'playlist_mincount': 7,
852 # TuneIn station embed
854 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
859 'location': 'Paris, France',
864 'skip_download': True,
869 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
873 'upload_date': '20141112',
874 'title': 'Rosetta #CometLanding webcast HL 10',
877 # Another Livestream embed, without 'new.' in URL
879 'url': 'https://www.freespeech.org/',
883 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
887 'skip_download': True,
892 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
895 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
897 'playlist_mincount': 2,
901 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
905 'upload_date': '20141126',
906 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
911 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
913 'id': '730m_DandD_1901_512k',
915 'uploader': 'www.abc.net.au',
916 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
919 # embedded viddler video
921 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
925 'uploader': 'deadspin',
926 'title': 'WALL-TO-GORTAT',
927 'timestamp': 1422285291,
928 'upload_date': '20150126',
930 'add_ie': ['Viddler'],
934 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
938 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
939 'description': 'md5:601cb790edd05908957dae8aaa866465',
940 'upload_date': '20150220',
942 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
946 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
950 'upload_date': '20150212',
951 'uploader': 'The National Archives UK',
952 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
953 'uploader_id': 'NationalArchives08',
954 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
959 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
960 'playlist_mincount': 5,
962 'id': 'aanslagen-kopenhagen',
963 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
968 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
972 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
975 # Kaltura embed (different embed code)
977 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
981 'upload_date': '20150127',
982 'uploader_id': 'PremierMedia',
984 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
987 # Kaltura embed protected with referrer
989 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
993 'title': 'Violetta - Achter De Schermen - Ruggero',
994 'description': 'Achter de schermen met Ruggero',
995 'timestamp': 1435133761,
996 'upload_date': '20150624',
997 'uploader_id': 'echojecka',
1000 # Kaltura embed with single quotes
1002 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1007 'timestamp': 1355743100,
1008 'upload_date': '20121217',
1009 'uploader_id': 'batchUser',
1011 'add_ie': ['Kaltura'],
1014 # Kaltura embedded via quoted entry_id
1015 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1019 'title': '06_matthew_brender_raj_dutt',
1020 'timestamp': 1466638791,
1021 'upload_date': '20160622',
1023 'add_ie': ['Kaltura'],
1024 'expected_warnings': [
1025 'Could not send HEAD request'
1028 'skip_download': True,
1032 # Kaltura embedded, some fileExt broken (#11480)
1033 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1037 'title': 'Our "Standard Models" of particle physics and cosmology',
1038 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1039 'timestamp': 1321158993,
1040 'upload_date': '20111113',
1041 'uploader_id': 'kps1',
1043 'add_ie': ['Kaltura'],
1045 # Eagle.Platform embed (generic URL)
1047 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1048 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1052 'title': 'Навальный вышел на свободу',
1053 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1054 'thumbnail': r're:^https?://.*\.jpg$',
1060 # ClipYou (Eagle.Platform) embed (custom URL)
1062 'url': 'http://muz-tv.ru/play/7129/',
1063 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1067 'title': "'O Sole Mio",
1068 'thumbnail': r're:^https?://.*\.jpg$',
1075 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1079 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1080 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1081 'thumbnail': r're:^https?://.*\.jpg$',
1088 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1092 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1093 'thumbnail': r're:^https?://.*\.png$',
1099 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1100 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1104 'title': 'Facebook Creates "On This Day" | Crunch Report',
1109 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1113 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1118 # Crooks and Liars embed
1120 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1124 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1125 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1126 'timestamp': 1428207000,
1127 'upload_date': '20150405',
1128 'uploader': 'Heather',
1131 # Crooks and Liars external embed
1133 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1135 'id': 'MTE3MjUtMzQ2MzA',
1137 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1138 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1139 'timestamp': 1265032391,
1140 'upload_date': '20100201',
1141 'uploader': 'Heather',
1144 # NBC Sports vplayer embed
1146 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1148 'id': 'ln7x1qSThw4k',
1150 'title': "PFT Live: New leader in the 'new-look' defense",
1151 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1152 'uploader': 'NBCU-SPORTS',
1153 'upload_date': '20140107',
1154 'timestamp': 1389118457,
1159 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1160 'md5': '1aa589c675898ae6d37a17913cf68d66',
1162 'id': '701714499682',
1164 'title': 'PREVIEW: On Assignment: David Letterman',
1165 '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.',
1170 'url': 'https://video.udn.com/news/300346',
1171 'md5': 'fd2060e988c326991037b9aff9df21a6',
1175 'title': '中一中男師變性 全校師生力挺',
1176 'thumbnail': r're:^https?://.*\.jpg$',
1180 'skip_download': True,
1185 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1187 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1189 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1190 'title': 'This is what separates the Excel masters from the wannabes',
1191 'duration': 191.933,
1195 'skip_download': True,
1198 # Brightcove URL in single quotes
1200 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1201 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1203 'id': '4255764656001',
1205 'title': 'SN Presents: Russell Martin, World Citizen',
1206 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1207 'uploader': 'Rogers Sportsnet',
1208 'uploader_id': '1704050871',
1209 'upload_date': '20150525',
1210 'timestamp': 1432570283,
1213 # Dailymotion Cloud video
1215 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1216 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1220 'title': 'Sauvons les abeilles ! - Le débat',
1221 'description': 'md5:d9082128b1c5277987825d684939ca26',
1222 'thumbnail': r're:^https?://.*\.jpe?g$',
1223 'timestamp': 1434970506,
1224 'upload_date': '20150622',
1225 'uploader': 'Public Sénat',
1226 'uploader_id': 'xa9gza',
1229 # OnionStudios embed
1231 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1235 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1236 'thumbnail': r're:^https?://.*\.jpe?g$',
1237 'uploader': 'ClickHole',
1238 'uploader_id': 'clickhole',
1243 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1245 'id': '74849a00-85a9-11e1-9660-123139220831',
1247 'title': '#whilewewatch',
1250 # AdobeTVVideo embed
1252 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1253 'md5': '43662b577c018ad707a63766462b1e87',
1257 'title': 'New experience with Acrobat DC',
1258 'description': 'New experience with Acrobat DC',
1259 'duration': 248.667,
1262 # BrightcoveInPageEmbed embed
1264 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1266 'id': '4238694884001',
1268 'title': 'Tabletop: Dread, Last Thoughts',
1269 'description': 'Tabletop: Dread, Last Thoughts',
1273 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1274 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1276 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1278 'id': '4785848093001',
1280 'title': 'The Cardinal Pell Interview',
1281 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1282 'uploader': 'GlobeCast Australia - GlobeStream',
1283 'uploader_id': '2733773828001',
1284 'upload_date': '20160304',
1285 'timestamp': 1457083087,
1289 'skip_download': True,
1292 # Another form of arte.tv embed
1294 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1295 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1297 'id': '030273-562_PLUS7-F',
1299 'title': 'ARTE Reportage - Nulle part, en France',
1300 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1301 'upload_date': '20160409',
1306 'url': 'http://www.wykop.pl/link/3088787/',
1307 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1309 'id': '874_1459135191',
1311 'title': 'Man shows poor quality of new apartment building',
1312 'description': 'The wall is like a sand pile.',
1313 'uploader': 'Lake8737',
1316 # Duplicated embedded video URLs
1318 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1320 'id': '149298443_480_16c25b74_2',
1322 'title': 'vs. Blue Orange Spring Game',
1323 'uploader': 'www.hudl.com',
1326 # twitter:player:stream embed
1328 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1332 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1333 'uploader': 'www.rtl.be',
1337 'skip_download': True,
1340 # twitter:player embed
1342 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1343 'md5': 'a3e0df96369831de324f0778e126653c',
1345 'id': '4909620399001',
1347 'title': 'What Do Black Holes Sound Like?',
1348 'description': 'what do black holes sound like',
1349 'upload_date': '20160524',
1350 'uploader_id': '29913724001',
1351 'timestamp': 1464107587,
1352 'uploader': 'TheAtlantic',
1354 'add_ie': ['BrightcoveLegacy'],
1356 # Facebook <iframe> embed
1358 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1359 'md5': 'fbcde74f534176ecb015849146dd3aee',
1361 'id': '599637780109885',
1363 'title': 'Facebook video #599637780109885',
1366 # Facebook API embed
1368 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1369 'md5': 'a47372ee61b39a7b90287094d447d94e',
1371 'id': '10153467542406923',
1373 'title': 'Facebook video #10153467542406923',
1376 # Wordpress "YouTube Video Importer" plugin
1378 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1379 'md5': 'd16797741b560b485194eddda8121b48',
1381 'id': 'HNTXWDXV9Is',
1383 'title': 'Blue Devils Drumline Stanford lot 2016',
1384 'upload_date': '20160627',
1385 'uploader_id': 'GENOCIDE8GENERAL10',
1386 'uploader': 'cylus cyrus',
1390 # video stored on custom kaltura server
1391 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1392 'md5': '537617d06e64dfed891fa1593c4b30cc',
1396 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1397 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1398 'uploader_id': 'videos.expansion@el-mundo.net',
1399 'upload_date': '20150429',
1400 'timestamp': 1430303472,
1402 'add_ie': ['Kaltura'],
1405 # Non-standard Vimeo embed
1406 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1407 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1411 'title': 'Understanding the web - Teaser',
1412 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1413 'upload_date': '20151214',
1414 'uploader': 'OpenClassrooms',
1415 'uploader_id': 'openclassrooms',
1417 'add_ie': ['Vimeo'],
1420 # generic vimeo embed that requires original URL passed as Referer
1421 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1422 'only_matching': True,
1425 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1426 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1428 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1430 'title': 'Big Buck Bunny',
1431 'description': 'Royalty free test video',
1432 'timestamp': 1432816365,
1433 'upload_date': '20150528',
1437 'skip_download': True,
1439 'add_ie': [ArkenaIE.ie_key()],
1442 '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/',
1446 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1449 'skip_download': True,
1451 'add_ie': [Vbox7IE.ie_key()],
1455 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1458 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1460 'playlist_mincount': 3,
1464 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1466 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1467 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1469 'playlist_mincount': 2,
1472 # # TODO: find another test
1473 # # http://schema.org/VideoObject
1474 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1475 # 'md5': '888dcf08b7ea671381f00fab74692755',
1477 # 'id': 'nyvTSJMKId',
1479 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1480 # 'description': '#love for cats.',
1481 # 'timestamp': 1461244995,
1482 # 'upload_date': '20160421',
1485 # 'force_generic_extractor': True,
1490 def report_following_redirect(self, new_url):
1491 """Report information extraction."""
1492 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1494 def _extract_rss(self, url, video_id, doc):
1495 playlist_title = doc.find('./channel/title').text
1496 playlist_desc_el = doc.find('./channel/description')
1497 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1500 for it in doc.findall('./channel/item'):
1501 next_url = xpath_text(it, 'link', fatal=False)
1503 enclosure_nodes = it.findall('./enclosure')
1504 for e in enclosure_nodes:
1505 next_url = e.attrib.get('url')
1515 'title': it.find('title').text,
1519 '_type': 'playlist',
1521 'title': playlist_title,
1522 'description': playlist_desc,
1526 def _extract_camtasia(self, url, video_id, webpage):
1527 """ Returns None if no camtasia video can be found. """
1529 camtasia_cfg = self._search_regex(
1530 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1531 webpage, 'camtasia configuration file', default=None)
1532 if camtasia_cfg is None:
1535 title = self._html_search_meta('DC.title', webpage, fatal=True)
1537 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1538 camtasia_cfg = self._download_xml(
1539 camtasia_url, video_id,
1540 note='Downloading camtasia configuration',
1541 errnote='Failed to download camtasia configuration')
1542 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1545 for n in fileset_node.getchildren():
1546 url_n = n.find('./uri')
1551 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1552 'title': '%s - %s' % (title, n.tag),
1553 'url': compat_urlparse.urljoin(url, url_n.text),
1554 'duration': float_or_none(n.find('./duration').text),
1558 '_type': 'playlist',
1563 def _real_extract(self, url):
1564 if url.startswith('//'):
1567 'url': self.http_scheme() + url,
1570 parsed_url = compat_urlparse.urlparse(url)
1571 if not parsed_url.scheme:
1572 default_search = self._downloader.params.get('default_search')
1573 if default_search is None:
1574 default_search = 'fixup_error'
1576 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1578 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1579 return self.url_result('http://' + url)
1580 elif default_search != 'fixup_error':
1581 if default_search == 'auto_warning':
1582 if re.match(r'^(?:url|URL)$', url):
1583 raise ExtractorError(
1584 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1587 self._downloader.report_warning(
1588 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1589 return self.url_result('ytsearch:' + url)
1591 if default_search in ('error', 'fixup_error'):
1592 raise ExtractorError(
1593 '%r is not a valid URL. '
1594 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1595 % (url, url), expected=True)
1597 if ':' not in default_search:
1598 default_search += ':'
1599 return self.url_result(default_search + url)
1601 url, smuggled_data = unsmuggle_url(url)
1602 force_videoid = None
1603 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1604 if smuggled_data and 'force_videoid' in smuggled_data:
1605 force_videoid = smuggled_data['force_videoid']
1606 video_id = force_videoid
1608 video_id = self._generic_id(url)
1610 self.to_screen('%s: Requesting header' % video_id)
1612 head_req = HEADRequest(url)
1613 head_response = self._request_webpage(
1615 note=False, errnote='Could not send HEAD request to %s' % url,
1618 if head_response is not False:
1619 # Check for redirect
1620 new_url = head_response.geturl()
1622 self.report_following_redirect(new_url)
1624 new_url = smuggle_url(
1625 new_url, {'force_videoid': force_videoid})
1626 return self.url_result(new_url)
1628 full_response = None
1629 if head_response is False:
1630 request = sanitized_Request(url)
1631 request.add_header('Accept-Encoding', '*')
1632 full_response = self._request_webpage(request, video_id)
1633 head_response = full_response
1637 'title': self._generic_title(url),
1638 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1641 # Check for direct link to a video
1642 content_type = head_response.headers.get('Content-Type', '').lower()
1643 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1645 format_id = m.group('format_id')
1646 if format_id.endswith('mpegurl'):
1647 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1648 elif format_id == 'f4m':
1649 formats = self._extract_f4m_formats(url, video_id)
1652 'format_id': m.group('format_id'),
1654 'vcodec': 'none' if m.group('type') == 'audio' else None
1656 info_dict['direct'] = True
1657 self._sort_formats(formats)
1658 info_dict['formats'] = formats
1661 if not self._downloader.params.get('test', False) and not is_intentional:
1662 force = self._downloader.params.get('force_generic_extractor', False)
1663 self._downloader.report_warning(
1664 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1666 if not full_response:
1667 request = sanitized_Request(url)
1668 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1669 # making it impossible to download only chunk of the file (yet we need only 512kB to
1670 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1671 # that will always result in downloading the whole file that is not desirable.
1672 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1673 # to accept raw bytes and being able to download only a chunk.
1674 # It may probably better to solve this by checking Content-Type for application/octet-stream
1675 # after HEAD request finishes, but not sure if we can rely on this.
1676 request.add_header('Accept-Encoding', '*')
1677 full_response = self._request_webpage(request, video_id)
1679 first_bytes = full_response.read(512)
1681 # Is it an M3U playlist?
1682 if first_bytes.startswith(b'#EXTM3U'):
1683 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1684 self._sort_formats(info_dict['formats'])
1687 # Maybe it's a direct link to a video?
1688 # Be careful not to download the whole thing!
1689 if not is_html(first_bytes):
1690 self._downloader.report_warning(
1691 'URL could be a direct video link, returning it as such.')
1698 webpage = self._webpage_read_content(
1699 full_response, url, video_id, prefix=first_bytes)
1701 self.report_extraction(video_id)
1703 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1705 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1706 if doc.tag == 'rss':
1707 return self._extract_rss(url, video_id, doc)
1708 elif doc.tag == 'SmoothStreamingMedia':
1709 info_dict['formats'] = self._parse_ism_formats(doc, url)
1710 self._sort_formats(info_dict['formats'])
1712 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1713 smil = self._parse_smil(doc, url, video_id)
1714 self._sort_formats(smil['formats'])
1716 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1717 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1718 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1719 info_dict['formats'] = self._parse_mpd_formats(
1721 mpd_base_url=full_response.geturl().rpartition('/')[0],
1723 self._sort_formats(info_dict['formats'])
1725 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1726 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1727 self._sort_formats(info_dict['formats'])
1729 except compat_xml_parse_error:
1732 # Is it a Camtasia project?
1733 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1734 if camtasia_res is not None:
1737 # Sometimes embedded video player is hidden behind percent encoding
1738 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1739 # Unescaping the whole page allows to handle those cases in a generic way
1740 webpage = compat_urllib_parse_unquote(webpage)
1742 # it's tempting to parse this further, but you would
1743 # have to take into account all the variations like
1744 # Video Title - Site Name
1745 # Site Name | Video Title
1746 # Video Title - Tagline | Site Name
1747 # and so on and so forth; it's just not practical
1748 video_title = self._og_search_title(
1749 webpage, default=None) or self._html_search_regex(
1750 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1753 # Try to detect age limit automatically
1754 age_limit = self._rta_search(webpage)
1755 # And then there are the jokers who advertise that they use RTA,
1756 # but actually don't.
1757 AGE_LIMIT_MARKERS = [
1758 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1760 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1763 # video uploader is domain name
1764 video_uploader = self._search_regex(
1765 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1767 video_description = self._og_search_description(webpage, default=None)
1768 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1771 def _playlist_from_matches(matches, getter=None, ie=None):
1773 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1775 return self.playlist_result(
1776 urlrs, playlist_id=video_id, playlist_title=video_title)
1778 # Look for Brightcove Legacy Studio embeds
1779 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1781 self.to_screen('Brightcove video detected.')
1784 'url': smuggle_url(bc_url, {'Referer': url}),
1785 'ie_key': 'BrightcoveLegacy'
1786 } for bc_url in bc_urls]
1789 '_type': 'playlist',
1790 'title': video_title,
1795 # Look for Brightcove New Studio embeds
1796 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1798 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1800 # Look for ThePlatform embeds
1801 tp_urls = ThePlatformIE._extract_urls(webpage)
1803 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1805 # Look for Vessel embeds
1806 vessel_urls = VesselIE._extract_urls(webpage)
1808 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1810 # Look for embedded rtl.nl player
1811 matches = re.findall(
1812 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1815 return _playlist_from_matches(matches, ie='RtlNl')
1817 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1819 return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
1821 vid_me_embed_url = self._search_regex(
1822 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1823 webpage, 'vid.me embed', default=None)
1824 if vid_me_embed_url is not None:
1825 return self.url_result(vid_me_embed_url, 'Vidme')
1827 # Look for embedded YouTube player
1828 matches = re.findall(r'''(?x)
1837 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1841 return _playlist_from_matches(
1842 matches, lambda m: unescapeHTML(m[1]))
1844 # Look for lazyYT YouTube embed
1845 matches = re.findall(
1846 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1848 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1850 # Look for Wordpress "YouTube Video Importer" plugin
1851 matches = re.findall(r'''(?x)<div[^>]+
1852 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1853 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1855 return _playlist_from_matches(matches, lambda m: m[-1])
1857 matches = DailymotionIE._extract_urls(webpage)
1859 return _playlist_from_matches(matches)
1861 # Look for embedded Dailymotion playlist player (#3822)
1863 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1865 playlists = re.findall(
1866 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1868 return _playlist_from_matches(
1869 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1871 # Look for embedded Wistia player
1873 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1875 embed_url = self._proto_relative_url(
1876 unescapeHTML(match.group('url')))
1878 '_type': 'url_transparent',
1881 'uploader': video_uploader,
1884 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1887 '_type': 'url_transparent',
1888 'url': 'wistia:%s' % match.group('id'),
1890 'uploader': video_uploader,
1895 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1896 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1899 return self.url_result(self._proto_relative_url(
1900 'wistia:%s' % match.group('id')), 'Wistia')
1902 # Look for SVT player
1903 svt_url = SVTIE._extract_url(webpage)
1905 return self.url_result(svt_url, 'SVT')
1907 # Look for embedded condenast player
1908 matches = re.findall(
1909 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1913 '_type': 'playlist',
1916 'ie_key': 'CondeNast',
1918 } for ma in matches],
1919 'title': video_title,
1923 # Look for Bandcamp pages with custom domain
1924 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1925 if mobj is not None:
1926 burl = unescapeHTML(mobj.group(1))
1927 # Don't set the extractor because it can be a track url or an album
1928 return self.url_result(burl)
1930 # Look for embedded Vevo player
1932 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1933 if mobj is not None:
1934 return self.url_result(mobj.group('url'))
1936 # Look for embedded Viddler player
1938 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1940 if mobj is not None:
1941 return self.url_result(mobj.group('url'))
1943 # Look for NYTimes player
1945 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1947 if mobj is not None:
1948 return self.url_result(mobj.group('url'))
1950 # Look for Libsyn player
1952 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1953 if mobj is not None:
1954 return self.url_result(mobj.group('url'))
1956 # Look for Ooyala videos
1957 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1958 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1959 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1960 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1961 if mobj is not None:
1962 embed_token = self._search_regex(
1963 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
1964 webpage, 'ooyala embed token', default=None)
1965 return OoyalaIE._build_url_result(smuggle_url(
1968 'embed_token': embed_token,
1971 # Look for multiple Ooyala embeds on SBN network websites
1972 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1973 if mobj is not None:
1974 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1976 return _playlist_from_matches(
1977 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1979 # Look for Aparat videos
1980 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1981 if mobj is not None:
1982 return self.url_result(mobj.group(1), 'Aparat')
1984 # Look for MPORA videos
1985 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1986 if mobj is not None:
1987 return self.url_result(mobj.group(1), 'Mpora')
1989 # Look for embedded NovaMov-based player
1991 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1992 (?P<url>http://(?:(?:embed|www)\.)?
1994 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1995 videoweed\.(?:es|com)|
1996 movshare\.(?:net|sx|ag)|
1997 divxstage\.(?:eu|net|ch|co|at|ag))
1998 /embed\.php.+?)\1''', webpage)
1999 if mobj is not None:
2000 return self.url_result(mobj.group('url'))
2002 # Look for embedded Facebook player
2003 facebook_url = FacebookIE._extract_url(webpage)
2004 if facebook_url is not None:
2005 return self.url_result(facebook_url, 'Facebook')
2007 # Look for embedded VK player
2008 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2009 if mobj is not None:
2010 return self.url_result(mobj.group('url'), 'VK')
2012 # Look for embedded Odnoklassniki player
2013 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2014 if mobj is not None:
2015 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2017 # Look for embedded ivi player
2018 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2019 if mobj is not None:
2020 return self.url_result(mobj.group('url'), 'Ivi')
2022 # Look for embedded Huffington Post player
2024 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2025 if mobj is not None:
2026 return self.url_result(mobj.group('url'), 'HuffPost')
2029 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2030 if mobj is not None:
2031 return self.url_result(mobj.group('url'))
2032 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2033 if mobj is not None:
2034 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2036 # Look for funnyordie embed
2037 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2039 return _playlist_from_matches(
2040 matches, getter=unescapeHTML, ie='FunnyOrDie')
2042 # Look for BBC iPlayer embed
2043 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2045 return _playlist_from_matches(matches, ie='BBCCoUk')
2047 # Look for embedded RUTV player
2048 rutv_url = RUTVIE._extract_url(webpage)
2050 return self.url_result(rutv_url, 'RUTV')
2052 # Look for embedded TVC player
2053 tvc_url = TVCIE._extract_url(webpage)
2055 return self.url_result(tvc_url, 'TVC')
2057 # Look for embedded SportBox player
2058 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2060 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
2062 # Look for embedded XHamster player
2063 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2065 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
2067 # Look for embedded TNAFlixNetwork player
2068 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2070 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
2072 # Look for embedded PornHub player
2073 pornhub_urls = PornHubIE._extract_urls(webpage)
2075 return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
2077 # Look for embedded DrTuber player
2078 drtuber_urls = DrTuberIE._extract_urls(webpage)
2080 return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
2082 # Look for embedded RedTube player
2083 redtube_urls = RedTubeIE._extract_urls(webpage)
2085 return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
2087 # Look for embedded Tvigle player
2089 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2090 if mobj is not None:
2091 return self.url_result(mobj.group('url'), 'Tvigle')
2093 # Look for embedded TED player
2095 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2096 if mobj is not None:
2097 return self.url_result(mobj.group('url'), 'TED')
2099 # Look for embedded Ustream videos
2101 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
2102 if mobj is not None:
2103 return self.url_result(mobj.group('url'), 'Ustream')
2105 # Look for embedded arte.tv player
2107 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2109 if mobj is not None:
2110 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2112 # Look for embedded francetv player
2114 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2116 if mobj is not None:
2117 return self.url_result(mobj.group('url'))
2119 # Look for embedded smotri.com player
2120 smotri_url = SmotriIE._extract_url(webpage)
2122 return self.url_result(smotri_url, 'Smotri')
2124 # Look for embedded Myvi.ru player
2125 myvi_url = MyviIE._extract_url(webpage)
2127 return self.url_result(myvi_url)
2129 # Look for embedded soundcloud player
2130 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2132 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2134 # Look for tunein player
2135 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2137 return _playlist_from_matches(tunein_urls)
2139 # Look for embedded mtvservices player
2140 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2142 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2144 # Look for embedded yahoo player
2146 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2148 if mobj is not None:
2149 return self.url_result(mobj.group('url'), 'Yahoo')
2151 # Look for embedded sbs.com.au player
2155 <meta\s+property="og:video"\s+content=|
2158 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2160 if mobj is not None:
2161 return self.url_result(mobj.group('url'), 'SBS')
2163 # Look for embedded Cinchcast player
2165 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2167 if mobj is not None:
2168 return self.url_result(mobj.group('url'), 'Cinchcast')
2171 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2175 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2177 if mobj is not None:
2178 return self.url_result(mobj.group('url'), 'MLB')
2181 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2183 if mobj is not None:
2184 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2187 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2189 if mobj is not None:
2190 return self.url_result(mobj.group('url'), 'Livestream')
2192 # Look for Zapiks embed
2194 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2195 if mobj is not None:
2196 return self.url_result(mobj.group('url'), 'Zapiks')
2198 # Look for Kaltura embeds
2199 kaltura_url = KalturaIE._extract_url(webpage)
2201 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2203 # Look for Eagle.Platform embeds
2204 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2205 if eagleplatform_url:
2206 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2208 # Look for ClipYou (uses Eagle.Platform) embeds
2210 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2211 if mobj is not None:
2212 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2214 # Look for Pladform embeds
2215 pladform_url = PladformIE._extract_url(webpage)
2217 return self.url_result(pladform_url)
2219 # Look for Videomore embeds
2220 videomore_url = VideomoreIE._extract_url(webpage)
2222 return self.url_result(videomore_url)
2224 # Look for Webcaster embeds
2225 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2227 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2229 # Look for Playwire embeds
2231 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2232 if mobj is not None:
2233 return self.url_result(mobj.group('url'))
2235 # Look for 5min embeds
2237 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2238 if mobj is not None:
2239 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2241 # Look for Crooks and Liars embeds
2243 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2244 if mobj is not None:
2245 return self.url_result(mobj.group('url'))
2247 # Look for NBC Sports VPlayer embeds
2248 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2250 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2252 # Look for NBC News embeds
2253 nbc_news_embed_url = re.search(
2254 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2255 if nbc_news_embed_url:
2256 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2258 # Look for Google Drive embeds
2259 google_drive_url = GoogleDriveIE._extract_url(webpage)
2260 if google_drive_url:
2261 return self.url_result(google_drive_url, 'GoogleDrive')
2263 # Look for UDN embeds
2265 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2266 if mobj is not None:
2267 return self.url_result(
2268 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2270 # Look for Senate ISVP iframe
2271 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2273 return self.url_result(senate_isvp_url, 'SenateISVP')
2275 # Look for Dailymotion Cloud videos
2276 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2278 return self.url_result(dmcloud_url, 'DailymotionCloud')
2280 # Look for OnionStudios embeds
2281 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2282 if onionstudios_url:
2283 return self.url_result(onionstudios_url)
2285 # Look for ViewLift embeds
2286 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2288 return self.url_result(viewlift_url)
2290 # Look for JWPlatform embeds
2291 jwplatform_url = JWPlatformIE._extract_url(webpage)
2293 return self.url_result(jwplatform_url, 'JWPlatform')
2295 # Look for Digiteka embeds
2296 digiteka_url = DigitekaIE._extract_url(webpage)
2298 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2300 # Look for Arkena embeds
2301 arkena_url = ArkenaIE._extract_url(webpage)
2303 return self.url_result(arkena_url, ArkenaIE.ie_key())
2305 # Look for Piksel embeds
2306 piksel_url = PikselIE._extract_url(webpage)
2308 return self.url_result(piksel_url, PikselIE.ie_key())
2310 # Look for Limelight embeds
2311 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2315 'Channel': 'channel',
2316 'ChannelList': 'channel_list',
2318 return self.url_result('limelight:%s:%s' % (
2319 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2323 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2325 name=(["\'])flashVars\2[^>]+
2326 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2329 return self.url_result('limelight:media:%s' % mobj.group('id'))
2331 # Look for AdobeTVVideo embeds
2333 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2335 if mobj is not None:
2336 return self.url_result(
2337 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2340 # Look for Vine embeds
2342 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2344 if mobj is not None:
2345 return self.url_result(
2346 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2348 # Look for VODPlatform embeds
2350 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2352 if mobj is not None:
2353 return self.url_result(
2354 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2356 # Look for Mangomolo embeds
2358 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2360 video\?.*?\bid=(?P<video_id>\d+)|
2361 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2362 ).+?)\1''', webpage)
2363 if mobj is not None:
2365 '_type': 'url_transparent',
2366 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2367 'title': video_title,
2368 'description': video_description,
2369 'thumbnail': video_thumbnail,
2370 'uploader': video_uploader,
2372 video_id = mobj.group('video_id')
2375 'ie_key': 'MangomoloVideo',
2380 'ie_key': 'MangomoloLive',
2381 'id': mobj.group('channel_id'),
2385 # Look for Instagram embeds
2386 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2387 if instagram_embed_url is not None:
2388 return self.url_result(
2389 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2391 # Look for LiveLeak embeds
2392 liveleak_url = LiveLeakIE._extract_url(webpage)
2394 return self.url_result(liveleak_url, 'LiveLeak')
2396 # Look for 3Q SDN embeds
2397 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2400 '_type': 'url_transparent',
2401 'ie_key': ThreeQSDNIE.ie_key(),
2402 'url': self._proto_relative_url(threeqsdn_url),
2403 'title': video_title,
2404 'description': video_description,
2405 'thumbnail': video_thumbnail,
2406 'uploader': video_uploader,
2409 # Look for VBOX7 embeds
2410 vbox7_url = Vbox7IE._extract_url(webpage)
2412 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2414 # Look for DBTV embeds
2415 dbtv_urls = DBTVIE._extract_urls(webpage)
2417 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2419 # Look for Videa embeds
2420 videa_urls = VideaIE._extract_urls(webpage)
2422 return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
2424 # Looking for http://schema.org/VideoObject
2425 json_ld = self._search_json_ld(
2426 webpage, video_id, default={}, expected_type='VideoObject')
2427 if json_ld.get('url'):
2429 'title': video_title or info_dict['title'],
2430 'description': video_description,
2431 'thumbnail': video_thumbnail,
2432 'age_limit': age_limit
2434 info_dict.update(json_ld)
2437 # Look for HTML5 media
2438 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2440 for entry in entries:
2443 'title': video_title,
2445 self._sort_formats(entry['formats'])
2446 return self.playlist_result(entries)
2448 def check_video(vurl):
2449 if YoutubeIE.suitable(vurl):
2451 vpath = compat_urlparse.urlparse(vurl).path
2452 vext = determine_ext(vpath)
2453 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2455 def filter_video(urls):
2456 return list(filter(check_video, urls))
2458 # Start with something easy: JW Player in SWFObject
2459 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2461 # Look for gorilla-vid style embedding
2462 found = filter_video(re.findall(r'''(?sx)
2466 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2469 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2471 # Broaden the search a little bit
2472 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2474 # Broaden the findall a little bit: JWPlayer JS loader
2475 found = filter_video(re.findall(
2476 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2479 found = filter_video(re.findall(r'''(?xs)
2480 flowplayer\("[^"]+",\s*
2482 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2483 ["']?url["']?\s*:\s*["']([^"']+)["']
2488 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2490 # Try to find twitter cards info
2491 # twitter:player:stream should be checked before twitter:player since
2492 # it is expected to contain a raw stream (see
2493 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2494 found = filter_video(re.findall(
2495 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2497 # We look for Open Graph info:
2498 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2499 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2500 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2501 if m_video_type is not None:
2502 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2504 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2506 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2507 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2510 # Look also in Refresh HTTP header
2511 refresh_header = head_response.headers.get('Refresh')
2513 # In python 2 response HTTP headers are bytestrings
2514 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2515 refresh_header = refresh_header.decode('iso-8859-1')
2516 found = re.search(REDIRECT_REGEX, refresh_header)
2518 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2519 self.report_following_redirect(new_url)
2526 # twitter:player is a https URL to iframe player that may or may not
2527 # be supported by youtube-dl thus this is checked the very last (see
2528 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2529 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2531 return self.url_result(embed_url)
2534 raise UnsupportedError(url)
2537 for video_url in orderedSet(found):
2538 video_url = unescapeHTML(video_url)
2539 video_url = video_url.replace('\\/', '/')
2540 video_url = compat_urlparse.urljoin(url, video_url)
2541 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2543 # Sometimes, jwplayer extraction will result in a YouTube URL
2544 if YoutubeIE.suitable(video_url):
2545 entries.append(self.url_result(video_url, 'Youtube'))
2548 # here's a fun little line of code for you:
2549 video_id = os.path.splitext(video_id)[0]
2553 'uploader': video_uploader,
2554 'title': video_title,
2555 'age_limit': age_limit,
2558 ext = determine_ext(video_url)
2560 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2562 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2564 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2566 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2568 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2569 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2570 # Just matching .ism/manifest is not enough to be reliably sure
2571 # whether it's actually an ISM manifest or some other streaming
2572 # manifest since there are various streaming URL formats
2573 # possible (see [1]) as well as some other shenanigans like
2574 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2576 # Thus the most reasonable way to solve this is to delegate
2577 # to generic extractor in order to look into the contents of
2578 # the manifest itself.
2579 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2580 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2581 entry_info_dict = self.url_result(
2582 smuggle_url(video_url, {'to_generic': True}),
2585 entry_info_dict['url'] = video_url
2587 if entry_info_dict.get('formats'):
2588 self._sort_formats(entry_info_dict['formats'])
2590 entries.append(entry_info_dict)
2592 if len(entries) == 1:
2595 for num, e in enumerate(entries, start=1):
2596 # 'url' results don't have a title
2597 if e.get('title') is not None:
2598 e['title'] = '%s (%d)' % (e['title'], num)
2600 '_type': 'playlist',