3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_urllib_parse_unquote,
15 compat_xml_parse_error,
33 from .commonprotocols import RtmpIE
34 from .brightcove import (
38 from .nbc import NBCSportsVPlayerIE
39 from .ooyala import OoyalaIE
40 from .rutv import RUTVIE
41 from .tvc import TVCIE
42 from .sportbox import SportBoxEmbedIE
43 from .smotri import SmotriIE
44 from .myvi import MyviIE
45 from .condenast import CondeNastIE
46 from .udn import UDNEmbedIE
47 from .senateisvp import SenateISVPIE
48 from .svt import SVTIE
49 from .pornhub import PornHubIE
50 from .xhamster import XHamsterEmbedIE
51 from .tnaflix import TNAFlixNetworkEmbedIE
52 from .drtuber import DrTuberIE
53 from .redtube import RedTubeIE
54 from .vimeo import VimeoIE
55 from .dailymotion import (
59 from .onionstudios import OnionStudiosIE
60 from .viewlift import ViewLiftEmbedIE
61 from .mtv import MTVServicesEmbeddedIE
62 from .pladform import PladformIE
63 from .videomore import VideomoreIE
64 from .webcaster import WebcasterFeedIE
65 from .googledrive import GoogleDriveIE
66 from .jwplatform import JWPlatformIE
67 from .digiteka import DigitekaIE
68 from .arkena import ArkenaIE
69 from .instagram import InstagramIE
70 from .liveleak import LiveLeakIE
71 from .threeqsdn import ThreeQSDNIE
72 from .theplatform import ThePlatformIE
73 from .vessel import VesselIE
74 from .kaltura import KalturaIE
75 from .eagleplatform import EaglePlatformIE
76 from .facebook import FacebookIE
77 from .soundcloud import SoundcloudIE
78 from .tunein import TuneInBaseIE
79 from .vbox7 import Vbox7IE
80 from .dbtv import DBTVIE
81 from .piksel import PikselIE
82 from .videa import VideaIE
83 from .twentymin import TwentyMinutenIE
84 from .ustream import UstreamIE
85 from .openload import OpenloadIE
86 from .videopress import VideoPressIE
89 class GenericIE(InfoExtractor):
90 IE_DESC = 'Generic downloader that works on some sites'
94 # Direct link to a video
96 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
97 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
102 'upload_date': '20100513',
105 # Direct link to media delivered compressed (until Accept-Encoding is *)
107 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
108 'md5': '128c42e68b13950268b648275386fc74',
110 'id': 'FictionJunction-Parallel_Hearts',
112 'title': 'FictionJunction-Parallel_Hearts',
113 'upload_date': '20140522',
115 'expected_warnings': [
116 'URL could be a direct video link, returning it as such.'
118 'skip': 'URL invalid',
120 # Direct download with broken HEAD
122 'url': 'http://ai-radio.org:8000/radio.opus',
129 'skip_download': True, # infinite live stream
131 'expected_warnings': [
132 r'501.*Not Implemented',
136 # Direct link with incorrect MIME type
138 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
139 'md5': '4ccbebe5f36706d85221f204d7eb5913',
141 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
142 'id': '5_Lennart_Poettering_-_Systemd',
144 'title': '5_Lennart_Poettering_-_Systemd',
145 'upload_date': '20141120',
147 'expected_warnings': [
148 'URL could be a direct video link, returning it as such.'
153 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
155 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
156 'title': 'Zero Punctuation',
157 'description': 're:.*groundbreaking video review series.*'
159 'playlist_mincount': 11,
161 # RSS feed with enclosure
163 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
165 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
167 'upload_date': '20150228',
168 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
171 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
173 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
177 'title': 'Automatics, robotics and biocybernetics',
178 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
179 'upload_date': '20130627',
180 'formats': 'mincount:16',
181 'subtitles': 'mincount:1',
184 'force_generic_extractor': True,
185 'skip_download': True,
188 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
190 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
195 'formats': 'mincount:1',
198 'skip_download': True,
201 # SMIL from https://www.restudy.dk/video/play/id/1637
203 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
207 'title': 'video_1637',
208 'formats': 'mincount:3',
211 'skip_download': True,
214 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
216 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
218 'id': 'smil-service',
220 'title': 'smil-service',
221 'formats': 'mincount:1',
224 'skip_download': True,
227 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
229 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
233 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
234 'formats': 'mincount:3',
237 'skip_download': True,
240 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
242 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
244 'id': 'mZlp2ctYIUEB',
246 'title': 'Tikibad ontruimd wegens brand',
247 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
248 'thumbnail': r're:^https?://.*\.jpg$',
252 'skip_download': True,
255 # MPD from http://dash-mse-test.appspot.com/media.html
257 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
258 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
260 'id': 'car-20120827-manifest',
262 'title': 'car-20120827-manifest',
263 'formats': 'mincount:9',
264 'upload_date': '20130904',
267 'format': 'bestvideo',
270 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
272 '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',
277 'formats': 'mincount:8',
281 'skip_download': True,
283 'skip': 'video gone',
285 # m3u8 served with Content-Type: text/plain
287 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
292 'upload_date': '20140720',
293 'formats': 'mincount:11',
297 'skip_download': True,
299 'skip': 'video gone',
303 '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',
307 'upload_date': '20130224',
308 'uploader_id': 'TheVerge',
309 'description': r're:^Chris Ziegler takes a look at the\.*',
310 'uploader': 'The Verge',
311 'title': 'First Firefox OS phones side-by-side',
314 'skip_download': False,
318 # redirect in Refresh HTTP header
319 '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',
323 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
324 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
325 'upload_date': '20150917',
326 'uploader_id': 'brtvofficial',
327 'uploader': 'Boiler Room',
330 'skip_download': False,
334 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
335 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
337 'id': '13601338388002',
339 'uploader': 'www.hodiho.fr',
340 'title': 'R\u00e9gis plante sa Jeep',
343 # bandcamp page with custom domain
345 'add_ie': ['Bandcamp'],
346 'url': 'http://bronyrock.com/track/the-pony-mash',
350 'title': 'The Pony Mash',
351 'uploader': 'M_Pallante',
353 'skip': 'There is a limit of 200 free downloads / month for the test song',
356 # embedded brightcove video
357 # it also tests brightcove videos that need to set the 'Referer'
358 # in the http requests
359 'add_ie': ['BrightcoveLegacy'],
360 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
362 'id': '2765128793001',
364 'title': 'Le cours de bourse : l’analyse technique',
365 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
366 'uploader': 'BFM BUSINESS',
369 'skip_download': True,
373 # embedded with itemprop embedURL and video id spelled as `idVideo`
374 'add_id': ['BrightcoveLegacy'],
375 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
377 'id': '5255628253001',
379 'title': 'md5:37c519b1128915607601e75a87995fc0',
380 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
381 'uploader': 'BFM BUSINESS',
382 'uploader_id': '876450612001',
383 'timestamp': 1482255315,
384 'upload_date': '20161220',
387 'skip_download': True,
391 # https://github.com/rg3/youtube-dl/issues/2253
392 'url': 'http://bcove.me/i6nfkrc3',
393 'md5': '0ba9446db037002366bab3b3eb30c88c',
395 'id': '3101154703001',
397 'title': 'Still no power',
398 'uploader': 'thestar.com',
399 '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.',
401 'add_ie': ['BrightcoveLegacy'],
402 'skip': 'video gone',
405 'url': 'http://www.championat.com/video/football/v/87/87499.html',
406 'md5': 'fb973ecf6e4a78a67453647444222983',
408 'id': '3414141473001',
410 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
411 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
412 'uploader': 'Championat',
416 # https://github.com/rg3/youtube-dl/issues/3541
417 'add_ie': ['BrightcoveLegacy'],
418 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
420 'id': '3866516442001',
422 'title': 'Leer mij vrouwen kennen: Aflevering 1',
423 'description': 'Leer mij vrouwen kennen: Aflevering 1',
424 'uploader': 'SBS Broadcasting',
426 'skip': 'Restricted to Netherlands',
428 'skip_download': True, # m3u8 download
432 # Brightcove with alternative playerID key
433 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
435 'id': 'nmeth.2062_SV1',
436 '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',
440 'id': '2228375078001',
442 'title': 'nmeth.2062-sv1',
443 'description': 'nmeth.2062-sv1',
444 'timestamp': 1363357591,
445 'upload_date': '20130315',
446 'uploader': 'Nature Publishing Group',
447 'uploader_id': '1964492299001',
453 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
454 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
456 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
458 'title': '2cc213299525360.mov', # that's what we get
461 'add_ie': ['Ooyala'],
464 # ooyala video embedded with http://player.ooyala.com/iframe.js
465 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
467 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
469 'title': '"Steve Jobs: Man in the Machine" trailer',
470 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
474 'skip_download': True,
476 'skip': 'movie expired',
480 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
484 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
485 'upload_date': '20140225',
486 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
487 'uploader': 'Tested',
488 'uploader_id': 'testedcom',
490 # No need to test YoutubeIE here
492 'skip_download': True,
497 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
501 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
502 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
504 # HEAD requests lead to endless 301, while GET is OK
505 'expected_warnings': ['301'],
509 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
513 'title': 'Охотское море стало целиком российским',
514 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
518 'skip_download': True,
523 '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/',
527 'title': 'Дошкольное воспитание',
532 'url': 'http://www.vestifinance.ru/articles/25753',
535 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
540 'title': 'Госзаказ. День 3',
546 'title': 'Госзаказ. День 2',
552 'title': 'Госзаказ. День 1',
558 'skip_download': True,
563 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
565 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
567 'title': 'Ужастики, русский трейлер (2015)',
568 'thumbnail': r're:^https?://.*\.jpg$',
574 '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',
577 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
579 'playlist_mincount': 7,
580 # This forum does not allow <iframe> syntaxes anymore
581 # Now HTML tags are displayed as-is
582 'skip': 'No videos on this page',
586 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
587 'md5': '65fdff94098e4a607385a60c5177c638',
591 'title': 'Hidden miracles of the natural world',
592 'uploader': 'Louie Schwartzberg',
593 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
596 # nowvideo embed hidden behind percent encoding
598 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
599 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
601 'id': '06e53103ca9aa',
603 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
604 'description': 'No description',
609 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
610 'md5': '7653032cbb25bf6c80d80f217055fa43',
612 'id': '048195-004_PLUS7-F',
615 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
616 'upload_date': '20140320',
619 'skip_download': 'Requires rtmpdump'
621 'skip': 'video gone',
625 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
629 'title': 'Alcaline, le concert avec Calogero',
630 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
631 'upload_date': '20150226',
632 'timestamp': 1424989860,
637 'skip_download': True,
639 'expected_warnings': [
645 'url': 'http://www.wired.com/2014/04/honda-asimo/',
646 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
648 'id': '53501be369702d3275860000',
650 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
655 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
656 'md5': '441aeeb82eb72c422c7f14ec533999cd',
658 'id': 'k2mm4bCdJ6CQ2i7c8o2',
660 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
661 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
663 'uploader_id': 'xgditw',
664 'upload_date': '20140425',
665 'timestamp': 1398441542,
667 'add_ie': ['Dailymotion'],
671 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
675 'title': 'The NBL Auction 2014',
676 'uploader': 'BADMINTON England',
677 'uploader_id': 'BADMINTONEvents',
678 'upload_date': '20140603',
679 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
681 'add_ie': ['Youtube'],
683 'skip_download': True,
688 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
689 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
691 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
693 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
694 'description': 'Two valets share their love for movie star Liam Neesons.',
695 'timestamp': 1349922600,
696 'upload_date': '20121011',
699 # YouTube embed via <data-embed-url="">
701 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
705 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
706 'uploader': 'Gameloft',
707 'uploader_id': 'gameloft',
708 'upload_date': '20140828',
709 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
712 'skip_download': True,
717 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
719 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
721 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
722 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
727 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
729 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
730 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
736 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
741 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
742 'md5': '9d65602bf31c6e20014319c7d07fba27',
744 'id': '5123ea6d5e5a7',
747 'uploader': 'www.handjobhub.com',
748 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
751 # Multiple brightcove videos
752 # https://github.com/rg3/youtube-dl/issues/2283
754 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
756 'id': 'always-never',
757 'title': 'Always / Never - The New Yorker',
761 'extract_flat': False,
762 'skip_download': True,
767 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
768 'md5': '96f09a37e44da40dd083e12d9a683327',
772 'title': 'Ump changes call to ball',
773 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
775 'timestamp': 1401537900,
776 'upload_date': '20140531',
777 'thumbnail': r're:^https?://.*\.jpg$',
782 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
783 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
787 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
788 'description': 'a Paywall Videos video from Remilon',
790 'uploader': 'study.com',
791 'timestamp': 1459678540,
792 'upload_date': '20160403',
793 'filesize': 24687186,
797 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
798 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
802 'title': 'Conversation about Hexagonal Rails Part 1',
803 'description': 'a Martin Fowler video from ThoughtWorks',
805 'uploader': 'thoughtworks.wistia.com',
806 'timestamp': 1401832161,
807 'upload_date': '20140603',
810 # Wistia standard embed (async)
812 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
816 'title': 'Drip Brennan Dunn Workshop',
817 'description': 'a JV Webinars video from getdrip-1',
819 'timestamp': 1463607249,
820 'upload_date': '20160518',
823 'skip_download': True,
828 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
832 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
833 'uploader': 'Sophos Security',
834 'title': 'Chet Chat 171 - Oct 29, 2014',
835 'upload_date': '20141029',
838 # Soundcloud multiple embeds
840 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
843 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
845 'playlist_mincount': 7,
847 # TuneIn station embed
849 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
854 'location': 'Paris, France',
859 'skip_download': True,
864 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
868 'upload_date': '20141112',
869 'title': 'Rosetta #CometLanding webcast HL 10',
872 # Another Livestream embed, without 'new.' in URL
874 'url': 'https://www.freespeech.org/',
878 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
882 'skip_download': True,
887 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
890 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
892 'playlist_mincount': 2,
896 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
900 'upload_date': '20141126',
901 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
906 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
908 'id': '730m_DandD_1901_512k',
910 'uploader': 'www.abc.net.au',
911 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
914 # embedded viddler video
916 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
920 'uploader': 'deadspin',
921 'title': 'WALL-TO-GORTAT',
922 'timestamp': 1422285291,
923 'upload_date': '20150126',
925 'add_ie': ['Viddler'],
929 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
933 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
934 'description': 'md5:601cb790edd05908957dae8aaa866465',
935 'upload_date': '20150220',
937 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
941 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
945 'upload_date': '20150212',
946 'uploader': 'The National Archives UK',
947 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
948 'uploader_id': 'NationalArchives08',
949 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
954 'url': 'http://www.suffolk.edu/sjc/',
958 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
959 'uploader': 'www.suffolk.edu',
962 'skip_download': True,
967 'url': 'http://www.indiedb.com/games/king-machine/videos',
971 'title': 'king machine trailer 1',
972 'thumbnail': r're:^https?://.*\.jpg$',
977 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
978 'playlist_mincount': 5,
980 'id': 'aanslagen-kopenhagen',
981 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
986 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
990 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
993 # Kaltura embed (different embed code)
995 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
999 'upload_date': '20150127',
1000 'uploader_id': 'PremierMedia',
1002 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1005 # Kaltura embed with single quotes
1007 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1012 'timestamp': 1355743100,
1013 'upload_date': '20121217',
1014 'uploader_id': 'batchUser',
1016 'add_ie': ['Kaltura'],
1019 # Kaltura embedded via quoted entry_id
1020 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1024 'title': '06_matthew_brender_raj_dutt',
1025 'timestamp': 1466638791,
1026 'upload_date': '20160622',
1028 'add_ie': ['Kaltura'],
1029 'expected_warnings': [
1030 'Could not send HEAD request'
1033 'skip_download': True,
1037 # Kaltura embedded, some fileExt broken (#11480)
1038 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1042 'title': 'Our "Standard Models" of particle physics and cosmology',
1043 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1044 'timestamp': 1321158993,
1045 'upload_date': '20111113',
1046 'uploader_id': 'kps1',
1048 'add_ie': ['Kaltura'],
1050 # Eagle.Platform embed (generic URL)
1052 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1053 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1057 'title': 'Навальный вышел на свободу',
1058 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1059 'thumbnail': r're:^https?://.*\.jpg$',
1065 # ClipYou (Eagle.Platform) embed (custom URL)
1067 'url': 'http://muz-tv.ru/play/7129/',
1068 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1072 'title': "'O Sole Mio",
1073 'thumbnail': r're:^https?://.*\.jpg$',
1080 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1084 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1085 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1086 'thumbnail': r're:^https?://.*\.jpg$',
1093 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1097 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1098 'thumbnail': r're:^https?://.*\.png$',
1104 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1105 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1109 'title': 'Facebook Creates "On This Day" | Crunch Report',
1114 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1118 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1123 # Crooks and Liars embed
1125 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1129 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1130 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1131 'timestamp': 1428207000,
1132 'upload_date': '20150405',
1133 'uploader': 'Heather',
1136 # Crooks and Liars external embed
1138 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1140 'id': 'MTE3MjUtMzQ2MzA',
1142 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1143 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1144 'timestamp': 1265032391,
1145 'upload_date': '20100201',
1146 'uploader': 'Heather',
1149 # NBC Sports vplayer embed
1151 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1153 'id': 'ln7x1qSThw4k',
1155 'title': "PFT Live: New leader in the 'new-look' defense",
1156 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1157 'uploader': 'NBCU-SPORTS',
1158 'upload_date': '20140107',
1159 'timestamp': 1389118457,
1164 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1165 'md5': '1aa589c675898ae6d37a17913cf68d66',
1167 'id': '701714499682',
1169 'title': 'PREVIEW: On Assignment: David Letterman',
1170 '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.',
1175 'url': 'https://video.udn.com/news/300346',
1176 'md5': 'fd2060e988c326991037b9aff9df21a6',
1180 'title': '中一中男師變性 全校師生力挺',
1181 'thumbnail': r're:^https?://.*\.jpg$',
1185 'skip_download': True,
1190 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1192 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1194 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1195 'title': 'This is what separates the Excel masters from the wannabes',
1196 'duration': 191.933,
1200 'skip_download': True,
1203 # Brightcove URL in single quotes
1205 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1206 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1208 'id': '4255764656001',
1210 'title': 'SN Presents: Russell Martin, World Citizen',
1211 '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.',
1212 'uploader': 'Rogers Sportsnet',
1213 'uploader_id': '1704050871',
1214 'upload_date': '20150525',
1215 'timestamp': 1432570283,
1218 # Dailymotion Cloud video
1220 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1221 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1225 'title': 'Sauvons les abeilles ! - Le débat',
1226 'description': 'md5:d9082128b1c5277987825d684939ca26',
1227 'thumbnail': r're:^https?://.*\.jpe?g$',
1228 'timestamp': 1434970506,
1229 'upload_date': '20150622',
1230 'uploader': 'Public Sénat',
1231 'uploader_id': 'xa9gza',
1234 # OnionStudios embed
1236 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1240 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1241 'thumbnail': r're:^https?://.*\.jpe?g$',
1242 'uploader': 'ClickHole',
1243 'uploader_id': 'clickhole',
1248 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1250 'id': '74849a00-85a9-11e1-9660-123139220831',
1252 'title': '#whilewewatch',
1255 # AdobeTVVideo embed
1257 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1258 'md5': '43662b577c018ad707a63766462b1e87',
1262 'title': 'New experience with Acrobat DC',
1263 'description': 'New experience with Acrobat DC',
1264 'duration': 248.667,
1267 # BrightcoveInPageEmbed embed
1269 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1271 'id': '4238694884001',
1273 'title': 'Tabletop: Dread, Last Thoughts',
1274 'description': 'Tabletop: Dread, Last Thoughts',
1278 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1279 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1281 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1283 'id': '4785848093001',
1285 'title': 'The Cardinal Pell Interview',
1286 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1287 'uploader': 'GlobeCast Australia - GlobeStream',
1288 'uploader_id': '2733773828001',
1289 'upload_date': '20160304',
1290 'timestamp': 1457083087,
1294 'skip_download': True,
1297 # Another form of arte.tv embed
1299 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1300 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1302 'id': '030273-562_PLUS7-F',
1304 'title': 'ARTE Reportage - Nulle part, en France',
1305 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1306 'upload_date': '20160409',
1311 'url': 'http://www.wykop.pl/link/3088787/',
1312 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1314 'id': '874_1459135191',
1316 'title': 'Man shows poor quality of new apartment building',
1317 'description': 'The wall is like a sand pile.',
1318 'uploader': 'Lake8737',
1321 # Duplicated embedded video URLs
1323 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1325 'id': '149298443_480_16c25b74_2',
1327 'title': 'vs. Blue Orange Spring Game',
1328 'uploader': 'www.hudl.com',
1331 # twitter:player:stream embed
1333 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1337 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1338 'uploader': 'www.rtl.be',
1342 'skip_download': True,
1345 # twitter:player embed
1347 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1348 'md5': 'a3e0df96369831de324f0778e126653c',
1350 'id': '4909620399001',
1352 'title': 'What Do Black Holes Sound Like?',
1353 'description': 'what do black holes sound like',
1354 'upload_date': '20160524',
1355 'uploader_id': '29913724001',
1356 'timestamp': 1464107587,
1357 'uploader': 'TheAtlantic',
1359 'add_ie': ['BrightcoveLegacy'],
1361 # Facebook <iframe> embed
1363 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1364 'md5': 'fbcde74f534176ecb015849146dd3aee',
1366 'id': '599637780109885',
1368 'title': 'Facebook video #599637780109885',
1371 # Facebook API embed
1373 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1374 'md5': 'a47372ee61b39a7b90287094d447d94e',
1376 'id': '10153467542406923',
1378 'title': 'Facebook video #10153467542406923',
1381 # Wordpress "YouTube Video Importer" plugin
1383 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1384 'md5': 'd16797741b560b485194eddda8121b48',
1386 'id': 'HNTXWDXV9Is',
1388 'title': 'Blue Devils Drumline Stanford lot 2016',
1389 'upload_date': '20160627',
1390 'uploader_id': 'GENOCIDE8GENERAL10',
1391 'uploader': 'cylus cyrus',
1395 # video stored on custom kaltura server
1396 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1397 'md5': '537617d06e64dfed891fa1593c4b30cc',
1401 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1402 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1403 'uploader_id': 'videos.expansion@el-mundo.net',
1404 'upload_date': '20150429',
1405 'timestamp': 1430303472,
1407 'add_ie': ['Kaltura'],
1410 # Non-standard Vimeo embed
1411 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1412 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1416 'title': 'Understanding the web - Teaser',
1417 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1418 'upload_date': '20151214',
1419 'uploader': 'OpenClassrooms',
1420 'uploader_id': 'openclassrooms',
1422 'add_ie': ['Vimeo'],
1425 # generic vimeo embed that requires original URL passed as Referer
1426 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1427 'only_matching': True,
1430 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1431 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1433 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1435 'title': 'Big Buck Bunny',
1436 'description': 'Royalty free test video',
1437 'timestamp': 1432816365,
1438 'upload_date': '20150528',
1442 'skip_download': True,
1444 'add_ie': [ArkenaIE.ie_key()],
1447 '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/',
1451 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1454 'skip_download': True,
1456 'add_ie': [Vbox7IE.ie_key()],
1460 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1463 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1465 'playlist_mincount': 3,
1469 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1471 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1472 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1474 'playlist_mincount': 2,
1478 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1482 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1483 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1486 'skip_download': True,
1488 'add_ie': [TwentyMinutenIE.ie_key()],
1492 'url': 'https://en.support.wordpress.com/videopress/',
1496 'title': 'IMG_5786',
1497 'timestamp': 1435711927,
1498 'upload_date': '20150701',
1501 'skip_download': True,
1503 'add_ie': [VideoPressIE.ie_key()],
1506 # # TODO: find another test
1507 # # http://schema.org/VideoObject
1508 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1509 # 'md5': '888dcf08b7ea671381f00fab74692755',
1511 # 'id': 'nyvTSJMKId',
1513 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1514 # 'description': '#love for cats.',
1515 # 'timestamp': 1461244995,
1516 # 'upload_date': '20160421',
1519 # 'force_generic_extractor': True,
1524 def report_following_redirect(self, new_url):
1525 """Report information extraction."""
1526 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1528 def _extract_rss(self, url, video_id, doc):
1529 playlist_title = doc.find('./channel/title').text
1530 playlist_desc_el = doc.find('./channel/description')
1531 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1534 for it in doc.findall('./channel/item'):
1535 next_url = xpath_text(it, 'link', fatal=False)
1537 enclosure_nodes = it.findall('./enclosure')
1538 for e in enclosure_nodes:
1539 next_url = e.attrib.get('url')
1549 'title': it.find('title').text,
1553 '_type': 'playlist',
1555 'title': playlist_title,
1556 'description': playlist_desc,
1560 def _extract_camtasia(self, url, video_id, webpage):
1561 """ Returns None if no camtasia video can be found. """
1563 camtasia_cfg = self._search_regex(
1564 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1565 webpage, 'camtasia configuration file', default=None)
1566 if camtasia_cfg is None:
1569 title = self._html_search_meta('DC.title', webpage, fatal=True)
1571 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1572 camtasia_cfg = self._download_xml(
1573 camtasia_url, video_id,
1574 note='Downloading camtasia configuration',
1575 errnote='Failed to download camtasia configuration')
1576 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1579 for n in fileset_node.getchildren():
1580 url_n = n.find('./uri')
1585 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1586 'title': '%s - %s' % (title, n.tag),
1587 'url': compat_urlparse.urljoin(url, url_n.text),
1588 'duration': float_or_none(n.find('./duration').text),
1592 '_type': 'playlist',
1597 def _real_extract(self, url):
1598 if url.startswith('//'):
1601 'url': self.http_scheme() + url,
1604 parsed_url = compat_urlparse.urlparse(url)
1605 if not parsed_url.scheme:
1606 default_search = self._downloader.params.get('default_search')
1607 if default_search is None:
1608 default_search = 'fixup_error'
1610 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1612 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1613 return self.url_result('http://' + url)
1614 elif default_search != 'fixup_error':
1615 if default_search == 'auto_warning':
1616 if re.match(r'^(?:url|URL)$', url):
1617 raise ExtractorError(
1618 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1621 self._downloader.report_warning(
1622 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1623 return self.url_result('ytsearch:' + url)
1625 if default_search in ('error', 'fixup_error'):
1626 raise ExtractorError(
1627 '%r is not a valid URL. '
1628 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1629 % (url, url), expected=True)
1631 if ':' not in default_search:
1632 default_search += ':'
1633 return self.url_result(default_search + url)
1635 url, smuggled_data = unsmuggle_url(url)
1636 force_videoid = None
1637 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1638 if smuggled_data and 'force_videoid' in smuggled_data:
1639 force_videoid = smuggled_data['force_videoid']
1640 video_id = force_videoid
1642 video_id = self._generic_id(url)
1644 self.to_screen('%s: Requesting header' % video_id)
1646 head_req = HEADRequest(url)
1647 head_response = self._request_webpage(
1649 note=False, errnote='Could not send HEAD request to %s' % url,
1652 if head_response is not False:
1653 # Check for redirect
1654 new_url = head_response.geturl()
1656 self.report_following_redirect(new_url)
1658 new_url = smuggle_url(
1659 new_url, {'force_videoid': force_videoid})
1660 return self.url_result(new_url)
1662 full_response = None
1663 if head_response is False:
1664 request = sanitized_Request(url)
1665 request.add_header('Accept-Encoding', '*')
1666 full_response = self._request_webpage(request, video_id)
1667 head_response = full_response
1671 'title': self._generic_title(url),
1672 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1675 # Check for direct link to a video
1676 content_type = head_response.headers.get('Content-Type', '').lower()
1677 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1679 format_id = m.group('format_id')
1680 if format_id.endswith('mpegurl'):
1681 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1682 elif format_id == 'f4m':
1683 formats = self._extract_f4m_formats(url, video_id)
1686 'format_id': m.group('format_id'),
1688 'vcodec': 'none' if m.group('type') == 'audio' else None
1690 info_dict['direct'] = True
1691 self._sort_formats(formats)
1692 info_dict['formats'] = formats
1695 if not self._downloader.params.get('test', False) and not is_intentional:
1696 force = self._downloader.params.get('force_generic_extractor', False)
1697 self._downloader.report_warning(
1698 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1700 if not full_response:
1701 request = sanitized_Request(url)
1702 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1703 # making it impossible to download only chunk of the file (yet we need only 512kB to
1704 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1705 # that will always result in downloading the whole file that is not desirable.
1706 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1707 # to accept raw bytes and being able to download only a chunk.
1708 # It may probably better to solve this by checking Content-Type for application/octet-stream
1709 # after HEAD request finishes, but not sure if we can rely on this.
1710 request.add_header('Accept-Encoding', '*')
1711 full_response = self._request_webpage(request, video_id)
1713 first_bytes = full_response.read(512)
1715 # Is it an M3U playlist?
1716 if first_bytes.startswith(b'#EXTM3U'):
1717 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1718 self._sort_formats(info_dict['formats'])
1721 # Maybe it's a direct link to a video?
1722 # Be careful not to download the whole thing!
1723 if not is_html(first_bytes):
1724 self._downloader.report_warning(
1725 'URL could be a direct video link, returning it as such.')
1732 webpage = self._webpage_read_content(
1733 full_response, url, video_id, prefix=first_bytes)
1735 self.report_extraction(video_id)
1737 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1739 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1740 if doc.tag == 'rss':
1741 return self._extract_rss(url, video_id, doc)
1742 elif doc.tag == 'SmoothStreamingMedia':
1743 info_dict['formats'] = self._parse_ism_formats(doc, url)
1744 self._sort_formats(info_dict['formats'])
1746 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1747 smil = self._parse_smil(doc, url, video_id)
1748 self._sort_formats(smil['formats'])
1750 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1751 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1752 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1753 info_dict['formats'] = self._parse_mpd_formats(
1755 mpd_base_url=full_response.geturl().rpartition('/')[0],
1757 self._sort_formats(info_dict['formats'])
1759 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1760 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1761 self._sort_formats(info_dict['formats'])
1763 except compat_xml_parse_error:
1766 # Is it a Camtasia project?
1767 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1768 if camtasia_res is not None:
1771 # Sometimes embedded video player is hidden behind percent encoding
1772 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1773 # Unescaping the whole page allows to handle those cases in a generic way
1774 webpage = compat_urllib_parse_unquote(webpage)
1776 # it's tempting to parse this further, but you would
1777 # have to take into account all the variations like
1778 # Video Title - Site Name
1779 # Site Name | Video Title
1780 # Video Title - Tagline | Site Name
1781 # and so on and so forth; it's just not practical
1782 video_title = self._og_search_title(
1783 webpage, default=None) or self._html_search_regex(
1784 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1787 # Try to detect age limit automatically
1788 age_limit = self._rta_search(webpage)
1789 # And then there are the jokers who advertise that they use RTA,
1790 # but actually don't.
1791 AGE_LIMIT_MARKERS = [
1792 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1794 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1797 # video uploader is domain name
1798 video_uploader = self._search_regex(
1799 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1801 video_description = self._og_search_description(webpage, default=None)
1802 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1805 def _playlist_from_matches(matches, getter=None, ie=None):
1807 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1809 return self.playlist_result(
1810 urlrs, playlist_id=video_id, playlist_title=video_title)
1812 # Look for Brightcove Legacy Studio embeds
1813 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1815 self.to_screen('Brightcove video detected.')
1818 'url': smuggle_url(bc_url, {'Referer': url}),
1819 'ie_key': 'BrightcoveLegacy'
1820 } for bc_url in bc_urls]
1823 '_type': 'playlist',
1824 'title': video_title,
1829 # Look for Brightcove New Studio embeds
1830 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1832 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1834 # Look for ThePlatform embeds
1835 tp_urls = ThePlatformIE._extract_urls(webpage)
1837 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1839 # Look for Vessel embeds
1840 vessel_urls = VesselIE._extract_urls(webpage)
1842 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1844 # Look for embedded rtl.nl player
1845 matches = re.findall(
1846 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1849 return _playlist_from_matches(matches, ie='RtlNl')
1851 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1853 return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
1855 vid_me_embed_url = self._search_regex(
1856 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1857 webpage, 'vid.me embed', default=None)
1858 if vid_me_embed_url is not None:
1859 return self.url_result(vid_me_embed_url, 'Vidme')
1861 # Look for embedded YouTube player
1862 matches = re.findall(r'''(?x)
1871 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1875 return _playlist_from_matches(
1876 matches, lambda m: unescapeHTML(m[1]))
1878 # Look for lazyYT YouTube embed
1879 matches = re.findall(
1880 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1882 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1884 # Look for Wordpress "YouTube Video Importer" plugin
1885 matches = re.findall(r'''(?x)<div[^>]+
1886 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1887 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1889 return _playlist_from_matches(matches, lambda m: m[-1])
1891 matches = DailymotionIE._extract_urls(webpage)
1893 return _playlist_from_matches(matches)
1895 # Look for embedded Dailymotion playlist player (#3822)
1897 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1899 playlists = re.findall(
1900 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1902 return _playlist_from_matches(
1903 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1905 # Look for embedded Wistia player
1907 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1909 embed_url = self._proto_relative_url(
1910 unescapeHTML(match.group('url')))
1912 '_type': 'url_transparent',
1915 'uploader': video_uploader,
1918 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1921 '_type': 'url_transparent',
1922 'url': 'wistia:%s' % match.group('id'),
1924 'uploader': video_uploader,
1929 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1930 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1933 return self.url_result(self._proto_relative_url(
1934 'wistia:%s' % match.group('id')), 'Wistia')
1936 # Look for SVT player
1937 svt_url = SVTIE._extract_url(webpage)
1939 return self.url_result(svt_url, 'SVT')
1941 # Look for embedded condenast player
1942 matches = re.findall(
1943 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1947 '_type': 'playlist',
1950 'ie_key': 'CondeNast',
1952 } for ma in matches],
1953 'title': video_title,
1957 # Look for Bandcamp pages with custom domain
1958 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1959 if mobj is not None:
1960 burl = unescapeHTML(mobj.group(1))
1961 # Don't set the extractor because it can be a track url or an album
1962 return self.url_result(burl)
1964 # Look for embedded Vevo player
1966 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1967 if mobj is not None:
1968 return self.url_result(mobj.group('url'))
1970 # Look for embedded Viddler player
1972 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1974 if mobj is not None:
1975 return self.url_result(mobj.group('url'))
1977 # Look for NYTimes player
1979 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1981 if mobj is not None:
1982 return self.url_result(mobj.group('url'))
1984 # Look for Libsyn player
1986 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1987 if mobj is not None:
1988 return self.url_result(mobj.group('url'))
1990 # Look for Ooyala videos
1991 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1992 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1993 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1994 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1995 if mobj is not None:
1996 embed_token = self._search_regex(
1997 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
1998 webpage, 'ooyala embed token', default=None)
1999 return OoyalaIE._build_url_result(smuggle_url(
2002 'embed_token': embed_token,
2005 # Look for multiple Ooyala embeds on SBN network websites
2006 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2007 if mobj is not None:
2008 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2010 return _playlist_from_matches(
2011 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2013 # Look for Aparat videos
2014 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2015 if mobj is not None:
2016 return self.url_result(mobj.group(1), 'Aparat')
2018 # Look for MPORA videos
2019 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2020 if mobj is not None:
2021 return self.url_result(mobj.group(1), 'Mpora')
2023 # Look for embedded NovaMov-based player
2025 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2026 (?P<url>http://(?:(?:embed|www)\.)?
2028 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2029 videoweed\.(?:es|com)|
2030 movshare\.(?:net|sx|ag)|
2031 divxstage\.(?:eu|net|ch|co|at|ag))
2032 /embed\.php.+?)\1''', webpage)
2033 if mobj is not None:
2034 return self.url_result(mobj.group('url'))
2036 # Look for embedded Facebook player
2037 facebook_url = FacebookIE._extract_url(webpage)
2038 if facebook_url is not None:
2039 return self.url_result(facebook_url, 'Facebook')
2041 # Look for embedded VK player
2042 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2043 if mobj is not None:
2044 return self.url_result(mobj.group('url'), 'VK')
2046 # Look for embedded Odnoklassniki player
2047 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2048 if mobj is not None:
2049 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2051 # Look for embedded ivi player
2052 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2053 if mobj is not None:
2054 return self.url_result(mobj.group('url'), 'Ivi')
2056 # Look for embedded Huffington Post player
2058 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2059 if mobj is not None:
2060 return self.url_result(mobj.group('url'), 'HuffPost')
2063 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2064 if mobj is not None:
2065 return self.url_result(mobj.group('url'))
2066 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2067 if mobj is not None:
2068 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2070 # Look for funnyordie embed
2071 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2073 return _playlist_from_matches(
2074 matches, getter=unescapeHTML, ie='FunnyOrDie')
2076 # Look for BBC iPlayer embed
2077 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2079 return _playlist_from_matches(matches, ie='BBCCoUk')
2081 # Look for embedded RUTV player
2082 rutv_url = RUTVIE._extract_url(webpage)
2084 return self.url_result(rutv_url, 'RUTV')
2086 # Look for embedded TVC player
2087 tvc_url = TVCIE._extract_url(webpage)
2089 return self.url_result(tvc_url, 'TVC')
2091 # Look for embedded SportBox player
2092 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2094 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
2096 # Look for embedded XHamster player
2097 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2099 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
2101 # Look for embedded TNAFlixNetwork player
2102 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2104 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
2106 # Look for embedded PornHub player
2107 pornhub_urls = PornHubIE._extract_urls(webpage)
2109 return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
2111 # Look for embedded DrTuber player
2112 drtuber_urls = DrTuberIE._extract_urls(webpage)
2114 return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
2116 # Look for embedded RedTube player
2117 redtube_urls = RedTubeIE._extract_urls(webpage)
2119 return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
2121 # Look for embedded Tvigle player
2123 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2124 if mobj is not None:
2125 return self.url_result(mobj.group('url'), 'Tvigle')
2127 # Look for embedded TED player
2129 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2130 if mobj is not None:
2131 return self.url_result(mobj.group('url'), 'TED')
2133 # Look for embedded Ustream videos
2134 ustream_url = UstreamIE._extract_url(webpage)
2136 return self.url_result(ustream_url, UstreamIE.ie_key())
2138 # Look for embedded arte.tv player
2140 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2142 if mobj is not None:
2143 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2145 # Look for embedded francetv player
2147 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2149 if mobj is not None:
2150 return self.url_result(mobj.group('url'))
2152 # Look for embedded smotri.com player
2153 smotri_url = SmotriIE._extract_url(webpage)
2155 return self.url_result(smotri_url, 'Smotri')
2157 # Look for embedded Myvi.ru player
2158 myvi_url = MyviIE._extract_url(webpage)
2160 return self.url_result(myvi_url)
2162 # Look for embedded soundcloud player
2163 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2165 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2167 # Look for tunein player
2168 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2170 return _playlist_from_matches(tunein_urls)
2172 # Look for embedded mtvservices player
2173 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2175 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2177 # Look for embedded yahoo player
2179 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2181 if mobj is not None:
2182 return self.url_result(mobj.group('url'), 'Yahoo')
2184 # Look for embedded sbs.com.au player
2188 <meta\s+property="og:video"\s+content=|
2191 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2193 if mobj is not None:
2194 return self.url_result(mobj.group('url'), 'SBS')
2196 # Look for embedded Cinchcast player
2198 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2200 if mobj is not None:
2201 return self.url_result(mobj.group('url'), 'Cinchcast')
2204 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2208 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2210 if mobj is not None:
2211 return self.url_result(mobj.group('url'), 'MLB')
2214 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2216 if mobj is not None:
2217 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2220 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2222 if mobj is not None:
2223 return self.url_result(mobj.group('url'), 'Livestream')
2225 # Look for Zapiks embed
2227 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2228 if mobj is not None:
2229 return self.url_result(mobj.group('url'), 'Zapiks')
2231 # Look for Kaltura embeds
2232 kaltura_url = KalturaIE._extract_url(webpage)
2234 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2236 # Look for Eagle.Platform embeds
2237 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2238 if eagleplatform_url:
2239 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2241 # Look for ClipYou (uses Eagle.Platform) embeds
2243 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2244 if mobj is not None:
2245 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2247 # Look for Pladform embeds
2248 pladform_url = PladformIE._extract_url(webpage)
2250 return self.url_result(pladform_url)
2252 # Look for Videomore embeds
2253 videomore_url = VideomoreIE._extract_url(webpage)
2255 return self.url_result(videomore_url)
2257 # Look for Webcaster embeds
2258 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2260 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2262 # Look for Playwire embeds
2264 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2265 if mobj is not None:
2266 return self.url_result(mobj.group('url'))
2268 # Look for 5min embeds
2270 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2271 if mobj is not None:
2272 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2274 # Look for Crooks and Liars embeds
2276 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2277 if mobj is not None:
2278 return self.url_result(mobj.group('url'))
2280 # Look for NBC Sports VPlayer embeds
2281 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2283 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2285 # Look for NBC News embeds
2286 nbc_news_embed_url = re.search(
2287 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2288 if nbc_news_embed_url:
2289 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2291 # Look for Google Drive embeds
2292 google_drive_url = GoogleDriveIE._extract_url(webpage)
2293 if google_drive_url:
2294 return self.url_result(google_drive_url, 'GoogleDrive')
2296 # Look for UDN embeds
2298 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2299 if mobj is not None:
2300 return self.url_result(
2301 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2303 # Look for Senate ISVP iframe
2304 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2306 return self.url_result(senate_isvp_url, 'SenateISVP')
2308 # Look for Dailymotion Cloud videos
2309 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2311 return self.url_result(dmcloud_url, 'DailymotionCloud')
2313 # Look for OnionStudios embeds
2314 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2315 if onionstudios_url:
2316 return self.url_result(onionstudios_url)
2318 # Look for ViewLift embeds
2319 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2321 return self.url_result(viewlift_url)
2323 # Look for JWPlatform embeds
2324 jwplatform_url = JWPlatformIE._extract_url(webpage)
2326 return self.url_result(jwplatform_url, 'JWPlatform')
2328 # Look for Digiteka embeds
2329 digiteka_url = DigitekaIE._extract_url(webpage)
2331 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2333 # Look for Arkena embeds
2334 arkena_url = ArkenaIE._extract_url(webpage)
2336 return self.url_result(arkena_url, ArkenaIE.ie_key())
2338 # Look for Piksel embeds
2339 piksel_url = PikselIE._extract_url(webpage)
2341 return self.url_result(piksel_url, PikselIE.ie_key())
2343 # Look for Limelight embeds
2344 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2348 'Channel': 'channel',
2349 'ChannelList': 'channel_list',
2351 return self.url_result(smuggle_url('limelight:%s:%s' % (
2352 lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
2353 'Limelight%s' % mobj.group(1), mobj.group(2))
2357 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2359 name=(["\'])flashVars\2[^>]+
2360 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2363 return self.url_result(smuggle_url(
2364 'limelight:media:%s' % mobj.group('id'),
2365 {'source_url': url}), 'LimelightMedia', mobj.group('id'))
2367 # Look for AdobeTVVideo embeds
2369 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2371 if mobj is not None:
2372 return self.url_result(
2373 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2376 # Look for Vine embeds
2378 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2380 if mobj is not None:
2381 return self.url_result(
2382 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2384 # Look for VODPlatform embeds
2386 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2388 if mobj is not None:
2389 return self.url_result(
2390 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2392 # Look for Mangomolo embeds
2394 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2396 video\?.*?\bid=(?P<video_id>\d+)|
2397 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2398 ).+?)\1''', webpage)
2399 if mobj is not None:
2401 '_type': 'url_transparent',
2402 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2403 'title': video_title,
2404 'description': video_description,
2405 'thumbnail': video_thumbnail,
2406 'uploader': video_uploader,
2408 video_id = mobj.group('video_id')
2411 'ie_key': 'MangomoloVideo',
2416 'ie_key': 'MangomoloLive',
2417 'id': mobj.group('channel_id'),
2421 # Look for Instagram embeds
2422 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2423 if instagram_embed_url is not None:
2424 return self.url_result(
2425 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2427 # Look for LiveLeak embeds
2428 liveleak_url = LiveLeakIE._extract_url(webpage)
2430 return self.url_result(liveleak_url, 'LiveLeak')
2432 # Look for 3Q SDN embeds
2433 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2436 '_type': 'url_transparent',
2437 'ie_key': ThreeQSDNIE.ie_key(),
2438 'url': self._proto_relative_url(threeqsdn_url),
2439 'title': video_title,
2440 'description': video_description,
2441 'thumbnail': video_thumbnail,
2442 'uploader': video_uploader,
2445 # Look for VBOX7 embeds
2446 vbox7_url = Vbox7IE._extract_url(webpage)
2448 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2450 # Look for DBTV embeds
2451 dbtv_urls = DBTVIE._extract_urls(webpage)
2453 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2455 # Look for Videa embeds
2456 videa_urls = VideaIE._extract_urls(webpage)
2458 return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
2460 # Look for 20 minuten embeds
2461 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2463 return _playlist_from_matches(
2464 twentymin_urls, ie=TwentyMinutenIE.ie_key())
2466 # Look for Openload embeds
2467 openload_urls = OpenloadIE._extract_urls(webpage)
2469 return _playlist_from_matches(
2470 openload_urls, ie=OpenloadIE.ie_key())
2472 # Look for VideoPress embeds
2473 videopress_urls = VideoPressIE._extract_urls(webpage)
2475 return _playlist_from_matches(
2476 videopress_urls, ie=VideoPressIE.ie_key())
2478 # Looking for http://schema.org/VideoObject
2479 json_ld = self._search_json_ld(
2480 webpage, video_id, default={}, expected_type='VideoObject')
2481 if json_ld.get('url'):
2483 'title': video_title or info_dict['title'],
2484 'description': video_description,
2485 'thumbnail': video_thumbnail,
2486 'age_limit': age_limit
2488 info_dict.update(json_ld)
2491 # Look for HTML5 media
2492 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2494 for entry in entries:
2497 'title': video_title,
2499 self._sort_formats(entry['formats'])
2500 return self.playlist_result(entries)
2502 jwplayer_data_str = self._find_jwplayer_data(webpage)
2503 if jwplayer_data_str:
2505 jwplayer_data = self._parse_json(
2506 jwplayer_data_str, video_id, transform_source=js_to_json)
2507 return self._parse_jwplayer_data(jwplayer_data, video_id)
2508 except ExtractorError:
2511 def check_video(vurl):
2512 if YoutubeIE.suitable(vurl):
2514 if RtmpIE.suitable(vurl):
2516 vpath = compat_urlparse.urlparse(vurl).path
2517 vext = determine_ext(vpath)
2518 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2520 def filter_video(urls):
2521 return list(filter(check_video, urls))
2523 # Start with something easy: JW Player in SWFObject
2524 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2526 # Look for gorilla-vid style embedding
2527 found = filter_video(re.findall(r'''(?sx)
2531 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2534 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2536 # Broaden the search a little bit
2537 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2539 # Broaden the findall a little bit: JWPlayer JS loader
2540 found = filter_video(re.findall(
2541 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2544 found = filter_video(re.findall(r'''(?xs)
2545 flowplayer\("[^"]+",\s*
2547 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2548 ["']?url["']?\s*:\s*["']([^"']+)["']
2553 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2555 # Try to find twitter cards info
2556 # twitter:player:stream should be checked before twitter:player since
2557 # it is expected to contain a raw stream (see
2558 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2559 found = filter_video(re.findall(
2560 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2562 # We look for Open Graph info:
2563 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2564 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2565 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2566 if m_video_type is not None:
2567 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2569 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2571 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2572 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2575 # Look also in Refresh HTTP header
2576 refresh_header = head_response.headers.get('Refresh')
2578 # In python 2 response HTTP headers are bytestrings
2579 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2580 refresh_header = refresh_header.decode('iso-8859-1')
2581 found = re.search(REDIRECT_REGEX, refresh_header)
2583 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2584 self.report_following_redirect(new_url)
2591 # twitter:player is a https URL to iframe player that may or may not
2592 # be supported by youtube-dl thus this is checked the very last (see
2593 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2594 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2596 return self.url_result(embed_url)
2599 raise UnsupportedError(url)
2602 for video_url in orderedSet(found):
2603 video_url = unescapeHTML(video_url)
2604 video_url = video_url.replace('\\/', '/')
2605 video_url = compat_urlparse.urljoin(url, video_url)
2606 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2608 # Sometimes, jwplayer extraction will result in a YouTube URL
2609 if YoutubeIE.suitable(video_url):
2610 entries.append(self.url_result(video_url, 'Youtube'))
2613 # here's a fun little line of code for you:
2614 video_id = os.path.splitext(video_id)[0]
2618 'uploader': video_uploader,
2619 'title': video_title,
2620 'age_limit': age_limit,
2623 if RtmpIE.suitable(video_url):
2624 entry_info_dict.update({
2625 '_type': 'url_transparent',
2626 'ie_key': RtmpIE.ie_key(),
2629 entries.append(entry_info_dict)
2632 ext = determine_ext(video_url)
2634 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2636 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2638 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2640 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2642 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2643 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2644 # Just matching .ism/manifest is not enough to be reliably sure
2645 # whether it's actually an ISM manifest or some other streaming
2646 # manifest since there are various streaming URL formats
2647 # possible (see [1]) as well as some other shenanigans like
2648 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2650 # Thus the most reasonable way to solve this is to delegate
2651 # to generic extractor in order to look into the contents of
2652 # the manifest itself.
2653 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2654 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2655 entry_info_dict = self.url_result(
2656 smuggle_url(video_url, {'to_generic': True}),
2659 entry_info_dict['url'] = video_url
2661 if entry_info_dict.get('formats'):
2662 self._sort_formats(entry_info_dict['formats'])
2664 entries.append(entry_info_dict)
2666 if len(entries) == 1:
2669 for num, e in enumerate(entries, start=1):
2670 # 'url' results don't have a title
2671 if e.get('title') is not None:
2672 e['title'] = '%s (%d)' % (e['title'], num)
2674 '_type': 'playlist',