3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
14 compat_urllib_parse_unquote,
16 compat_xml_parse_error,
36 from .commonprotocols import RtmpIE
37 from .brightcove import (
45 from .nbc import NBCSportsVPlayerIE
46 from .ooyala import OoyalaIE
47 from .rutv import RUTVIE
48 from .tvc import TVCIE
49 from .sportbox import SportBoxEmbedIE
50 from .smotri import SmotriIE
51 from .myvi import MyviIE
52 from .condenast import CondeNastIE
53 from .udn import UDNEmbedIE
54 from .senateisvp import SenateISVPIE
55 from .svt import SVTIE
56 from .pornhub import PornHubIE
57 from .xhamster import XHamsterEmbedIE
58 from .tnaflix import TNAFlixNetworkEmbedIE
59 from .drtuber import DrTuberIE
60 from .redtube import RedTubeIE
61 from .tube8 import Tube8IE
62 from .vimeo import VimeoIE
63 from .dailymotion import DailymotionIE
64 from .dailymail import DailyMailIE
65 from .onionstudios import OnionStudiosIE
66 from .viewlift import ViewLiftEmbedIE
67 from .mtv import MTVServicesEmbeddedIE
68 from .pladform import PladformIE
69 from .videomore import VideomoreIE
70 from .webcaster import WebcasterFeedIE
71 from .googledrive import GoogleDriveIE
72 from .jwplatform import JWPlatformIE
73 from .digiteka import DigitekaIE
74 from .arkena import ArkenaIE
75 from .instagram import InstagramIE
76 from .liveleak import LiveLeakIE
77 from .threeqsdn import ThreeQSDNIE
78 from .theplatform import ThePlatformIE
79 from .vessel import VesselIE
80 from .kaltura import KalturaIE
81 from .eagleplatform import EaglePlatformIE
82 from .facebook import FacebookIE
83 from .soundcloud import SoundcloudIE
84 from .tunein import TuneInBaseIE
85 from .vbox7 import Vbox7IE
86 from .dbtv import DBTVIE
87 from .piksel import PikselIE
88 from .videa import VideaIE
89 from .twentymin import TwentyMinutenIE
90 from .ustream import UstreamIE
91 from .openload import OpenloadIE
92 from .videopress import VideoPressIE
93 from .rutube import RutubeIE
94 from .limelight import LimelightBaseIE
95 from .anvato import AnvatoIE
96 from .washingtonpost import WashingtonPostIE
97 from .wistia import WistiaIE
98 from .mediaset import MediasetIE
99 from .joj import JojIE
100 from .megaphone import MegaphoneIE
101 from .vzaar import VzaarIE
102 from .channel9 import Channel9IE
103 from .vshare import VShareIE
104 from .mediasite import MediasiteIE
105 from .springboardplatform import SpringboardPlatformIE
106 from .yapfiles import YapFilesIE
107 from .vice import ViceIE
108 from .xfileshare import XFileShareIE
111 class GenericIE(InfoExtractor):
112 IE_DESC = 'Generic downloader that works on some sites'
116 # Direct link to a video
118 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
119 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
124 'upload_date': '20100513',
127 # Direct link to media delivered compressed (until Accept-Encoding is *)
129 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
130 'md5': '128c42e68b13950268b648275386fc74',
132 'id': 'FictionJunction-Parallel_Hearts',
134 'title': 'FictionJunction-Parallel_Hearts',
135 'upload_date': '20140522',
137 'expected_warnings': [
138 'URL could be a direct video link, returning it as such.'
140 'skip': 'URL invalid',
142 # Direct download with broken HEAD
144 'url': 'http://ai-radio.org:8000/radio.opus',
151 'skip_download': True, # infinite live stream
153 'expected_warnings': [
154 r'501.*Not Implemented',
158 # Direct link with incorrect MIME type
160 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
161 'md5': '4ccbebe5f36706d85221f204d7eb5913',
163 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
164 'id': '5_Lennart_Poettering_-_Systemd',
166 'title': '5_Lennart_Poettering_-_Systemd',
167 'upload_date': '20141120',
169 'expected_warnings': [
170 'URL could be a direct video link, returning it as such.'
175 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
177 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
178 'title': 'Zero Punctuation',
179 'description': 're:.*groundbreaking video review series.*'
181 'playlist_mincount': 11,
183 # RSS feed with enclosure
185 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
187 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
189 'upload_date': '20150228',
190 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
193 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
195 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
199 'title': 'Automatics, robotics and biocybernetics',
200 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
201 'upload_date': '20130627',
202 'formats': 'mincount:16',
203 'subtitles': 'mincount:1',
206 'force_generic_extractor': True,
207 'skip_download': True,
210 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
212 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
217 'formats': 'mincount:1',
220 'skip_download': True,
223 # SMIL from https://www.restudy.dk/video/play/id/1637
225 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
229 'title': 'video_1637',
230 'formats': 'mincount:3',
233 'skip_download': True,
236 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
238 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
240 'id': 'smil-service',
242 'title': 'smil-service',
243 'formats': 'mincount:1',
246 'skip_download': True,
249 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
251 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
255 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
256 'formats': 'mincount:3',
259 'skip_download': True,
262 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
264 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
266 'id': 'mZlp2ctYIUEB',
268 'title': 'Tikibad ontruimd wegens brand',
269 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
270 'thumbnail': r're:^https?://.*\.jpg$',
274 'skip_download': True,
277 # MPD from http://dash-mse-test.appspot.com/media.html
279 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
280 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
282 'id': 'car-20120827-manifest',
284 'title': 'car-20120827-manifest',
285 'formats': 'mincount:9',
286 'upload_date': '20130904',
289 'format': 'bestvideo',
292 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
294 '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',
299 'formats': 'mincount:8',
303 'skip_download': True,
305 'skip': 'video gone',
307 # m3u8 served with Content-Type: text/plain
309 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
314 'upload_date': '20140720',
315 'formats': 'mincount:11',
319 'skip_download': True,
321 'skip': 'video gone',
325 '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',
329 'upload_date': '20130224',
330 'uploader_id': 'TheVerge',
331 'description': r're:^Chris Ziegler takes a look at the\.*',
332 'uploader': 'The Verge',
333 'title': 'First Firefox OS phones side-by-side',
336 'skip_download': False,
340 # redirect in Refresh HTTP header
341 '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',
345 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
346 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
347 'upload_date': '20150917',
348 'uploader_id': 'brtvofficial',
349 'uploader': 'Boiler Room',
352 'skip_download': False,
356 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
357 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
359 'id': '13601338388002',
361 'uploader': 'www.hodiho.fr',
362 'title': 'R\u00e9gis plante sa Jeep',
365 # bandcamp page with custom domain
367 'add_ie': ['Bandcamp'],
368 'url': 'http://bronyrock.com/track/the-pony-mash',
372 'title': 'The Pony Mash',
373 'uploader': 'M_Pallante',
375 'skip': 'There is a limit of 200 free downloads / month for the test song',
378 # embedded brightcove video
379 # it also tests brightcove videos that need to set the 'Referer'
380 # in the http requests
381 'add_ie': ['BrightcoveLegacy'],
382 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
384 'id': '2765128793001',
386 'title': 'Le cours de bourse : l’analyse technique',
387 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
388 'uploader': 'BFM BUSINESS',
391 'skip_download': True,
395 # embedded with itemprop embedURL and video id spelled as `idVideo`
396 'add_id': ['BrightcoveLegacy'],
397 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
399 'id': '5255628253001',
401 'title': 'md5:37c519b1128915607601e75a87995fc0',
402 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
403 'uploader': 'BFM BUSINESS',
404 'uploader_id': '876450612001',
405 'timestamp': 1482255315,
406 'upload_date': '20161220',
409 'skip_download': True,
413 # https://github.com/rg3/youtube-dl/issues/2253
414 'url': 'http://bcove.me/i6nfkrc3',
415 'md5': '0ba9446db037002366bab3b3eb30c88c',
417 'id': '3101154703001',
419 'title': 'Still no power',
420 'uploader': 'thestar.com',
421 '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.',
423 'add_ie': ['BrightcoveLegacy'],
424 'skip': 'video gone',
427 'url': 'http://www.championat.com/video/football/v/87/87499.html',
428 'md5': 'fb973ecf6e4a78a67453647444222983',
430 'id': '3414141473001',
432 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
433 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
434 'uploader': 'Championat',
438 # https://github.com/rg3/youtube-dl/issues/3541
439 'add_ie': ['BrightcoveLegacy'],
440 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
442 'id': '3866516442001',
444 'title': 'Leer mij vrouwen kennen: Aflevering 1',
445 'description': 'Leer mij vrouwen kennen: Aflevering 1',
446 'uploader': 'SBS Broadcasting',
448 'skip': 'Restricted to Netherlands',
450 'skip_download': True, # m3u8 download
454 # Brightcove video in <iframe>
455 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
456 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
458 'id': '5360463607001',
460 'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
461 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼(Zade Dirani)在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》(HEARTBEAT),为受到六年冲突影响的叙利亚儿童发出强烈呐喊,呼吁世界做出共同努力,使叙利亚儿童重新获得享有正常童年生活的权利。',
462 'uploader': 'United Nations',
463 'uploader_id': '1362235914001',
464 'timestamp': 1489593889,
465 'upload_date': '20170315',
467 'add_ie': ['BrightcoveLegacy'],
470 # Brightcove with alternative playerID key
471 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
473 'id': 'nmeth.2062_SV1',
474 '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',
478 'id': '2228375078001',
480 'title': 'nmeth.2062-sv1',
481 'description': 'nmeth.2062-sv1',
482 'timestamp': 1363357591,
483 'upload_date': '20130315',
484 'uploader': 'Nature Publishing Group',
485 'uploader_id': '1964492299001',
490 # Brightcove with UUID in videoPlayer
491 'url': 'http://www8.hp.com/cn/zh/home.html',
493 'id': '5255815316001',
495 'title': 'Sprocket Video - China',
496 'description': 'Sprocket Video - China',
497 'uploader': 'HP-Video Gallery',
498 'timestamp': 1482263210,
499 'upload_date': '20161220',
500 'uploader_id': '1107601872001',
503 'skip_download': True, # m3u8 download
505 'skip': 'video rotates...weekly?',
508 # Brightcove:new type [2].
509 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
510 'md5': '2b35148fcf48da41c9fb4591650784f3',
512 'id': '5348741021001',
514 'upload_date': '20170306',
515 'uploader_id': '4191638492001',
516 'timestamp': 1488769918,
517 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
522 # Alternative brightcove <video> attributes
523 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
525 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
526 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
529 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
531 'id': '5311302538001',
533 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
534 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
535 'timestamp': 1486321708,
536 'upload_date': '20170205',
537 'uploader_id': '800000640001',
539 'only_matching': True,
543 # Brightcove with UUID in videoPlayer
544 'url': 'http://www8.hp.com/cn/zh/home.html',
546 'id': '5255815316001',
548 'title': 'Sprocket Video - China',
549 'description': 'Sprocket Video - China',
550 'uploader': 'HP-Video Gallery',
551 'timestamp': 1482263210,
552 'upload_date': '20161220',
553 'uploader_id': '1107601872001',
556 'skip_download': True, # m3u8 download
561 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
562 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
564 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
566 'title': '2cc213299525360.mov', # that's what we get
569 'add_ie': ['Ooyala'],
572 # ooyala video embedded with http://player.ooyala.com/iframe.js
573 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
575 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
577 'title': '"Steve Jobs: Man in the Machine" trailer',
578 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
582 'skip_download': True,
584 'skip': 'movie expired',
586 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
588 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
590 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
592 'title': 'Steampunk Fest Comes to Honesdale',
596 'skip_download': True,
601 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
605 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
606 'upload_date': '20140225',
607 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
608 'uploader': 'Tested',
609 'uploader_id': 'testedcom',
611 # No need to test YoutubeIE here
613 'skip_download': True,
618 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
622 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
623 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
625 # HEAD requests lead to endless 301, while GET is OK
626 'expected_warnings': ['301'],
630 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
634 'title': 'Охотское море стало целиком российским',
635 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
639 'skip_download': True,
644 '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/',
648 'title': 'Дошкольное воспитание',
653 'url': 'http://www.vestifinance.ru/articles/25753',
656 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
661 'title': 'Госзаказ. День 3',
667 'title': 'Госзаказ. День 2',
673 'title': 'Госзаказ. День 1',
679 'skip_download': True,
684 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
686 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
688 'title': 'Ужастики, русский трейлер (2015)',
689 'thumbnail': r're:^https?://.*\.jpg$',
695 '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',
698 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
700 'playlist_mincount': 7,
701 # This forum does not allow <iframe> syntaxes anymore
702 # Now HTML tags are displayed as-is
703 'skip': 'No videos on this page',
707 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
708 'md5': '65fdff94098e4a607385a60c5177c638',
712 'title': 'Hidden miracles of the natural world',
713 'uploader': 'Louie Schwartzberg',
714 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
717 # nowvideo embed hidden behind percent encoding
719 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
720 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
722 'id': '06e53103ca9aa',
724 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
725 'description': 'No description',
730 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
731 'md5': '7653032cbb25bf6c80d80f217055fa43',
733 'id': '048195-004_PLUS7-F',
736 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
737 'upload_date': '20140320',
740 'skip_download': 'Requires rtmpdump'
742 'skip': 'video gone',
746 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
750 'title': 'Alcaline, le concert avec Calogero',
751 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
752 'upload_date': '20150226',
753 'timestamp': 1424989860,
758 'skip_download': True,
760 'expected_warnings': [
766 'url': 'http://www.wired.com/2014/04/honda-asimo/',
767 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
769 'id': '53501be369702d3275860000',
771 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
776 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
777 'md5': '441aeeb82eb72c422c7f14ec533999cd',
779 'id': 'k2mm4bCdJ6CQ2i7c8o2',
781 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
782 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
784 'uploader_id': 'xgditw',
785 'upload_date': '20140425',
786 'timestamp': 1398441542,
788 'add_ie': ['Dailymotion'],
792 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
796 'title': 'Care worker punches elderly dementia patient in head 11 times',
797 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
799 'add_ie': ['DailyMail'],
801 'skip_download': True,
806 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
810 'title': 'The NBL Auction 2014',
811 'uploader': 'BADMINTON England',
812 'uploader_id': 'BADMINTONEvents',
813 'upload_date': '20140603',
814 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
816 'add_ie': ['Youtube'],
818 'skip_download': True,
823 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
824 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
826 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
828 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
829 'description': 'Two valets share their love for movie star Liam Neesons.',
830 'timestamp': 1349922600,
831 'upload_date': '20121011',
834 # YouTube embed via <data-embed-url="">
836 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
840 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
841 'uploader': 'Gameloft',
842 'uploader_id': 'gameloft',
843 'upload_date': '20140828',
844 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
847 'skip_download': True,
850 # YouTube <object> embed
852 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
853 'md5': '516718101ec834f74318df76259fb3cc',
857 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
858 'upload_date': '20080526',
859 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
860 'uploader': 'Christopher Sykes',
861 'uploader_id': 'ChristopherJSykes',
863 'add_ie': ['Youtube'],
867 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
869 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
871 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
872 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
877 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
879 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
880 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
886 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
891 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
892 'md5': '9d65602bf31c6e20014319c7d07fba27',
894 'id': '5123ea6d5e5a7',
897 'uploader': 'www.handjobhub.com',
898 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
901 # Multiple brightcove videos
902 # https://github.com/rg3/youtube-dl/issues/2283
904 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
906 'id': 'always-never',
907 'title': 'Always / Never - The New Yorker',
911 'extract_flat': False,
912 'skip_download': True,
917 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
918 'md5': '96f09a37e44da40dd083e12d9a683327',
922 'title': 'Ump changes call to ball',
923 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
925 'timestamp': 1401537900,
926 'upload_date': '20140531',
927 'thumbnail': r're:^https?://.*\.jpg$',
932 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
933 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
937 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
938 'description': 'a Paywall Videos video from Remilon',
940 'uploader': 'study.com',
941 'timestamp': 1459678540,
942 'upload_date': '20160403',
943 'filesize': 24687186,
947 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
948 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
952 'title': 'Conversation about Hexagonal Rails Part 1',
953 'description': 'a Martin Fowler video from ThoughtWorks',
955 'uploader': 'thoughtworks.wistia.com',
956 'timestamp': 1401832161,
957 'upload_date': '20140603',
960 # Wistia standard embed (async)
962 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
966 'title': 'Drip Brennan Dunn Workshop',
967 'description': 'a JV Webinars video from getdrip-1',
969 'timestamp': 1463607249,
970 'upload_date': '20160518',
973 'skip_download': True,
978 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
982 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
983 'uploader': 'Sophos Security',
984 'title': 'Chet Chat 171 - Oct 29, 2014',
985 'upload_date': '20141029',
988 # Soundcloud multiple embeds
990 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
993 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
995 'playlist_mincount': 7,
997 # TuneIn station embed
999 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1004 'location': 'Paris, France',
1009 'skip_download': True,
1014 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1018 'upload_date': '20141112',
1019 'title': 'Rosetta #CometLanding webcast HL 10',
1022 # Another Livestream embed, without 'new.' in URL
1024 'url': 'https://www.freespeech.org/',
1028 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1032 'skip_download': True,
1037 'url': 'https://skiplagged.com/',
1040 'title': 'Skiplagged: The smart way to find cheap flights',
1042 'playlist_mincount': 1,
1043 'add_ie': ['Youtube'],
1047 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1051 'upload_date': '20141126',
1052 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1057 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1059 'id': '730m_DandD_1901_512k',
1061 'uploader': 'www.abc.net.au',
1062 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1065 # embedded viddler video
1067 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1071 'uploader': 'deadspin',
1072 'title': 'WALL-TO-GORTAT',
1073 'timestamp': 1422285291,
1074 'upload_date': '20150126',
1076 'add_ie': ['Viddler'],
1080 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1084 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1085 'description': 'md5:601cb790edd05908957dae8aaa866465',
1086 'upload_date': '20150220',
1088 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1092 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1094 'id': 'Mrj4DVp2zeA',
1096 'upload_date': '20150212',
1097 'uploader': 'The National Archives UK',
1098 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1099 'uploader_id': 'NationalArchives08',
1100 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1105 'url': 'http://www.suffolk.edu/sjc/live.php',
1109 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1110 'uploader': 'www.suffolk.edu',
1113 'skip_download': True,
1115 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1119 'url': 'http://www.indiedb.com/games/king-machine/videos',
1123 'title': 'king machine trailer 1',
1124 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1125 'thumbnail': r're:^https?://.*\.jpg$',
1129 # JWPlayer config passed as variable
1130 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1134 'title': 'ARIELE | Tube Cup',
1135 'uploader': 'www.txxx.com',
1139 'skip_download': True,
1144 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1145 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1149 'upload_date': '20171122',
1150 'timestamp': 1511366290,
1151 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1153 'add_ie': [JWPlatformIE.ie_key()],
1156 # Video.js embed, multiple formats
1157 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1159 'id': 'yygqldloqIk',
1161 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1162 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1163 'upload_date': '20130314',
1164 'uploader': 'PROстое3D',
1165 'uploader_id': 'PROstoe3D',
1168 'skip_download': True,
1172 # Video.js embed, single format
1173 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1177 'title': 'Step 1 - Good Foundation',
1178 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1181 'skip_download': True,
1186 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1187 'playlist_mincount': 5,
1189 'id': 'aanslagen-kopenhagen',
1190 'title': 'Aanslagen Kopenhagen',
1195 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1199 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1202 # Kaltura embed (different embed code)
1204 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1208 'upload_date': '20150127',
1209 'uploader_id': 'PremierMedia',
1211 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1214 # Kaltura embed with single quotes
1216 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1221 'timestamp': 1355743100,
1222 'upload_date': '20121217',
1223 'uploader_id': 'batchUser',
1225 'add_ie': ['Kaltura'],
1228 # Kaltura embedded via quoted entry_id
1229 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1233 'title': '06_matthew_brender_raj_dutt',
1234 'timestamp': 1466638791,
1235 'upload_date': '20160622',
1237 'add_ie': ['Kaltura'],
1238 'expected_warnings': [
1239 'Could not send HEAD request'
1242 'skip_download': True,
1246 # Kaltura embedded, some fileExt broken (#11480)
1247 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1251 'title': 'Our "Standard Models" of particle physics and cosmology',
1252 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1253 'timestamp': 1321158993,
1254 'upload_date': '20111113',
1255 'uploader_id': 'kps1',
1257 'add_ie': ['Kaltura'],
1260 # Kaltura iframe embed
1261 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1262 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1266 'title': 'I. M. Pei: A Centennial Celebration',
1267 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1268 'upload_date': '20170403',
1269 'uploader_id': 'batchUser',
1270 'timestamp': 1491232186,
1272 'add_ie': ['Kaltura'],
1274 # referrer protected EaglePlatform embed
1276 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1280 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1281 'thumbnail': r're:^https?://.*\.jpg$',
1286 'skip_download': True,
1289 # ClipYou (EaglePlatform) embed (custom URL)
1291 'url': 'http://muz-tv.ru/play/7129/',
1292 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1296 'title': "'O Sole Mio",
1297 'thumbnail': r're:^https?://.*\.jpg$',
1302 'skip_download': True,
1304 'skip': 'This video is unavailable.',
1308 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1312 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1313 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1314 'thumbnail': r're:^https?://.*\.jpg$',
1318 'skip': 'HTTP Error 404: Not Found',
1322 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1326 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1327 'thumbnail': r're:^https?://.*\.png$',
1333 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1334 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1338 'title': 'Facebook Creates "On This Day" | Crunch Report',
1339 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1340 'timestamp': 1427237531,
1341 'uploader': 'Crunch Report',
1342 'upload_date': '20150324',
1346 'skip_download': True,
1351 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1355 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1360 # Crooks and Liars embed
1362 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1366 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1367 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1368 'timestamp': 1428207000,
1369 'upload_date': '20150405',
1370 'uploader': 'Heather',
1373 # Crooks and Liars external embed
1375 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1377 'id': 'MTE3MjUtMzQ2MzA',
1379 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1380 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1381 'timestamp': 1265032391,
1382 'upload_date': '20100201',
1383 'uploader': 'Heather',
1386 # NBC Sports vplayer embed
1388 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1390 'id': 'ln7x1qSThw4k',
1392 'title': "PFT Live: New leader in the 'new-look' defense",
1393 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1394 'uploader': 'NBCU-SPORTS',
1395 'upload_date': '20140107',
1396 'timestamp': 1389118457,
1398 'skip': 'Invalid Page URL',
1402 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1403 'md5': '1aa589c675898ae6d37a17913cf68d66',
1405 'id': 'x_dtl_oa_LettermanliftPR_160608',
1407 'title': 'David Letterman: A Preview',
1408 '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.',
1409 'upload_date': '20160609',
1410 'timestamp': 1465431544,
1411 'uploader': 'NBCU-NEWS',
1416 'url': 'https://video.udn.com/news/300346',
1417 'md5': 'fd2060e988c326991037b9aff9df21a6',
1421 'title': '中一中男師變性 全校師生力挺',
1422 'thumbnail': r're:^https?://.*\.jpg$',
1426 'skip_download': True,
1428 'expected_warnings': ['Failed to parse JSON Expecting value'],
1432 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1434 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1436 'description': 'Index/Match versus VLOOKUP.',
1437 'title': 'This is what separates the Excel masters from the wannabes',
1438 'duration': 191.933,
1442 'skip_download': True,
1445 # Brightcove URL in single quotes
1447 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1448 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1450 'id': '4255764656001',
1452 'title': 'SN Presents: Russell Martin, World Citizen',
1453 '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.',
1454 'uploader': 'Rogers Sportsnet',
1455 'uploader_id': '1704050871',
1456 'upload_date': '20150525',
1457 'timestamp': 1432570283,
1460 # OnionStudios embed
1462 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1466 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1467 'thumbnail': r're:^https?://.*\.jpe?g$',
1468 'uploader': 'ClickHole',
1469 'uploader_id': 'clickhole',
1474 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1476 'id': '74849a00-85a9-11e1-9660-123139220831',
1478 'title': '#whilewewatch',
1481 # AdobeTVVideo embed
1483 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1484 'md5': '43662b577c018ad707a63766462b1e87',
1488 'title': 'New experience with Acrobat DC',
1489 'description': 'New experience with Acrobat DC',
1490 'duration': 248.667,
1493 # BrightcoveInPageEmbed embed
1495 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1497 'id': '4238694884001',
1499 'title': 'Tabletop: Dread, Last Thoughts',
1500 'description': 'Tabletop: Dread, Last Thoughts',
1504 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1505 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1507 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1509 'id': '4785848093001',
1511 'title': 'The Cardinal Pell Interview',
1512 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1513 'uploader': 'GlobeCast Australia - GlobeStream',
1514 'uploader_id': '2733773828001',
1515 'upload_date': '20160304',
1516 'timestamp': 1457083087,
1520 'skip_download': True,
1524 # Brightcove embed with whitespace around attribute names
1525 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1527 'id': '3167554373001',
1529 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1530 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1531 'uploader_id': '1079349493',
1532 'upload_date': '20140207',
1533 'timestamp': 1391810548,
1536 'skip_download': True,
1539 # Another form of arte.tv embed
1541 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1542 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1544 'id': '030273-562_PLUS7-F',
1546 'title': 'ARTE Reportage - Nulle part, en France',
1547 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1548 'upload_date': '20160409',
1553 'url': 'http://www.wykop.pl/link/3088787/',
1554 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1556 'id': '874_1459135191',
1558 'title': 'Man shows poor quality of new apartment building',
1559 'description': 'The wall is like a sand pile.',
1560 'uploader': 'Lake8737',
1562 'add_ie': [LiveLeakIE.ie_key()],
1564 # Another LiveLeak embed pattern (#13336)
1566 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1568 'id': '2eb_1496309988',
1570 'title': 'Thief robs place where everyone was armed',
1571 'description': 'md5:694d73ee79e535953cf2488562288eee',
1572 'uploader': 'brazilwtf',
1574 'add_ie': [LiveLeakIE.ie_key()],
1576 # Duplicated embedded video URLs
1578 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1580 'id': '149298443_480_16c25b74_2',
1582 'title': 'vs. Blue Orange Spring Game',
1583 'uploader': 'www.hudl.com',
1586 # twitter:player:stream embed
1588 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1592 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1593 'uploader': 'www.rtl.be',
1597 'skip_download': True,
1600 # twitter:player embed
1602 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1603 'md5': 'a3e0df96369831de324f0778e126653c',
1605 'id': '4909620399001',
1607 'title': 'What Do Black Holes Sound Like?',
1608 'description': 'what do black holes sound like',
1609 'upload_date': '20160524',
1610 'uploader_id': '29913724001',
1611 'timestamp': 1464107587,
1612 'uploader': 'TheAtlantic',
1614 'add_ie': ['BrightcoveLegacy'],
1616 # Facebook <iframe> embed
1618 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1619 'md5': 'fbcde74f534176ecb015849146dd3aee',
1621 'id': '599637780109885',
1623 'title': 'Facebook video #599637780109885',
1626 # Facebook <iframe> embed, plugin video
1628 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1630 'id': '1754168231264132',
1632 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1633 'uploader': 'Tariq Ramadan (official)',
1634 'timestamp': 1496758379,
1635 'upload_date': '20170606',
1638 'skip_download': True,
1641 # Facebook API embed
1643 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1644 'md5': 'a47372ee61b39a7b90287094d447d94e',
1646 'id': '10153467542406923',
1648 'title': 'Facebook video #10153467542406923',
1651 # Wordpress "YouTube Video Importer" plugin
1653 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1654 'md5': 'd16797741b560b485194eddda8121b48',
1656 'id': 'HNTXWDXV9Is',
1658 'title': 'Blue Devils Drumline Stanford lot 2016',
1659 'upload_date': '20160627',
1660 'uploader_id': 'GENOCIDE8GENERAL10',
1661 'uploader': 'cylus cyrus',
1665 # video stored on custom kaltura server
1666 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1667 'md5': '537617d06e64dfed891fa1593c4b30cc',
1671 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1672 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1673 'uploader_id': 'videos.expansion@el-mundo.net',
1674 'upload_date': '20150429',
1675 'timestamp': 1430303472,
1677 'add_ie': ['Kaltura'],
1680 # Non-standard Vimeo embed
1681 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1682 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1686 'title': 'Understanding the web - Teaser',
1687 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1688 'upload_date': '20151214',
1689 'uploader': 'OpenClassrooms',
1690 'uploader_id': 'openclassrooms',
1692 'add_ie': ['Vimeo'],
1695 # generic vimeo embed that requires original URL passed as Referer
1696 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1697 'only_matching': True,
1700 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1701 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1703 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1705 'title': 'Big Buck Bunny',
1706 'description': 'Royalty free test video',
1707 'timestamp': 1432816365,
1708 'upload_date': '20150528',
1712 'skip_download': True,
1714 'add_ie': [ArkenaIE.ie_key()],
1717 '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/',
1721 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1724 'skip_download': True,
1726 'add_ie': [Vbox7IE.ie_key()],
1730 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1733 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1735 'playlist_mincount': 3,
1739 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1741 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1742 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1744 'playlist_mincount': 2,
1748 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1752 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1753 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1756 'skip_download': True,
1758 'add_ie': [TwentyMinutenIE.ie_key()],
1762 'url': 'https://en.support.wordpress.com/videopress/',
1766 'title': 'IMG_5786',
1767 'timestamp': 1435711927,
1768 'upload_date': '20150701',
1771 'skip_download': True,
1773 'add_ie': [VideoPressIE.ie_key()],
1777 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1779 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1781 'title': 'Магаззино: Казань 2',
1782 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1783 'uploader': 'Магаззино',
1784 'upload_date': '20170228',
1785 'uploader_id': '996642',
1788 'skip_download': True,
1790 'add_ie': [RutubeIE.ie_key()],
1793 # ThePlatform embedded with whitespaces in URLs
1794 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1795 'only_matching': True,
1798 # Senate ISVP iframe https
1799 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1800 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1802 'id': 'govtaff020316',
1804 'title': 'Integrated Senate Video Player',
1806 'add_ie': [SenateISVPIE.ie_key()],
1809 # Limelight embeds (1 channel embed + 4 media embeds)
1810 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1812 'id': 'FacilitatorTraining2017',
1813 'title': 'Facilitator Training 2017',
1815 'playlist_mincount': 5,
1818 # Limelight embed (LimelightPlayerUtil.embed)
1819 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1821 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1823 'title': '07448641',
1824 'timestamp': 1499890639,
1825 'upload_date': '20170712',
1828 'skip_download': True,
1830 'add_ie': ['LimelightMedia'],
1833 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1835 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1836 'title': 'Standoff with Walnut Creek murder suspect ends',
1837 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1839 'playlist_mincount': 4,
1842 # WashingtonPost embed
1843 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1845 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1847 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1848 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
1849 'timestamp': 1455216756,
1850 'uploader': 'The Washington Post',
1851 'upload_date': '20160211',
1853 'add_ie': [WashingtonPostIE.ie_key()],
1857 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1861 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1864 'skip_download': True,
1866 'add_ie': [MediasetIE.ie_key()],
1870 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1872 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1873 'title': 'Slovenskom sa prehnala vlna silných búrok',
1875 'playlist_mincount': 5,
1876 'add_ie': [JojIE.ie_key()],
1879 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1880 'url': 'https://tvrain.ru/amp/418921/',
1881 'md5': 'cc00413936695987e8de148b67d14f1d',
1885 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1890 'url': 'http://help.vzaar.com/article/165-embedding-video',
1891 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1895 'title': 'Building A Business Online: Principal Chairs Q & A',
1899 # multiple HTML5 videos on one page
1900 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1902 'id': 'keyscenarios',
1903 'title': 'Rescue Kit 14 Free Edition - Getting started',
1905 'playlist_count': 4,
1909 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1910 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1913 'title': 'vl14062007715967',
1918 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1919 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1921 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1923 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1924 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1925 'timestamp': 1474354800,
1926 'upload_date': '20160920',
1930 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1934 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1935 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1936 'timestamp': 1516100691,
1937 'upload_date': '20180116',
1940 'skip_download': True,
1942 'add_ie': [SpringboardPlatformIE.ie_key()],
1945 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1947 'id': 'uPDB5I9wfp8',
1949 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1950 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1951 'upload_date': '20160219',
1952 'uploader': 'Pocoyo - Português (BR)',
1953 'uploader_id': 'PocoyoBrazil',
1955 'add_ie': [YoutubeIE.ie_key()],
1957 'skip_download': True,
1961 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1963 'id': 'vMDE4NzI1Mjgt690b',
1967 'add_ie': [YapFilesIE.ie_key()],
1969 'skip_download': True,
1973 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
1974 'md5': 'b68d276de422ab07ee1d49388103f457',
1977 'title': 'Lock up and get excited',
1980 'skip': 'TODO: fix nested playlists processing in tests',
1983 # # TODO: find another test
1984 # # http://schema.org/VideoObject
1985 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1986 # 'md5': '888dcf08b7ea671381f00fab74692755',
1988 # 'id': 'nyvTSJMKId',
1990 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1991 # 'description': '#love for cats.',
1992 # 'timestamp': 1461244995,
1993 # 'upload_date': '20160421',
1996 # 'force_generic_extractor': True,
2001 def report_following_redirect(self, new_url):
2002 """Report information extraction."""
2003 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2005 def _extract_rss(self, url, video_id, doc):
2006 playlist_title = doc.find('./channel/title').text
2007 playlist_desc_el = doc.find('./channel/description')
2008 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2011 for it in doc.findall('./channel/item'):
2012 next_url = xpath_text(it, 'link', fatal=False)
2014 enclosure_nodes = it.findall('./enclosure')
2015 for e in enclosure_nodes:
2016 next_url = e.attrib.get('url')
2024 '_type': 'url_transparent',
2026 'title': it.find('title').text,
2030 '_type': 'playlist',
2032 'title': playlist_title,
2033 'description': playlist_desc,
2037 def _extract_camtasia(self, url, video_id, webpage):
2038 """ Returns None if no camtasia video can be found. """
2040 camtasia_cfg = self._search_regex(
2041 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2042 webpage, 'camtasia configuration file', default=None)
2043 if camtasia_cfg is None:
2046 title = self._html_search_meta('DC.title', webpage, fatal=True)
2048 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2049 camtasia_cfg = self._download_xml(
2050 camtasia_url, video_id,
2051 note='Downloading camtasia configuration',
2052 errnote='Failed to download camtasia configuration')
2053 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2056 for n in fileset_node.getchildren():
2057 url_n = n.find('./uri')
2062 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2063 'title': '%s - %s' % (title, n.tag),
2064 'url': compat_urlparse.urljoin(url, url_n.text),
2065 'duration': float_or_none(n.find('./duration').text),
2069 '_type': 'playlist',
2074 def _real_extract(self, url):
2075 if url.startswith('//'):
2078 'url': self.http_scheme() + url,
2081 parsed_url = compat_urlparse.urlparse(url)
2082 if not parsed_url.scheme:
2083 default_search = self._downloader.params.get('default_search')
2084 if default_search is None:
2085 default_search = 'fixup_error'
2087 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2089 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2090 return self.url_result('http://' + url)
2091 elif default_search != 'fixup_error':
2092 if default_search == 'auto_warning':
2093 if re.match(r'^(?:url|URL)$', url):
2094 raise ExtractorError(
2095 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2098 self._downloader.report_warning(
2099 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2100 return self.url_result('ytsearch:' + url)
2102 if default_search in ('error', 'fixup_error'):
2103 raise ExtractorError(
2104 '%r is not a valid URL. '
2105 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2106 % (url, url), expected=True)
2108 if ':' not in default_search:
2109 default_search += ':'
2110 return self.url_result(default_search + url)
2112 url, smuggled_data = unsmuggle_url(url)
2113 force_videoid = None
2114 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2115 if smuggled_data and 'force_videoid' in smuggled_data:
2116 force_videoid = smuggled_data['force_videoid']
2117 video_id = force_videoid
2119 video_id = self._generic_id(url)
2121 self.to_screen('%s: Requesting header' % video_id)
2123 head_req = HEADRequest(url)
2124 head_response = self._request_webpage(
2126 note=False, errnote='Could not send HEAD request to %s' % url,
2129 if head_response is not False:
2130 # Check for redirect
2131 new_url = compat_str(head_response.geturl())
2133 self.report_following_redirect(new_url)
2135 new_url = smuggle_url(
2136 new_url, {'force_videoid': force_videoid})
2137 return self.url_result(new_url)
2139 full_response = None
2140 if head_response is False:
2141 request = sanitized_Request(url)
2142 request.add_header('Accept-Encoding', '*')
2143 full_response = self._request_webpage(request, video_id)
2144 head_response = full_response
2148 'title': self._generic_title(url),
2149 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2152 # Check for direct link to a video
2153 content_type = head_response.headers.get('Content-Type', '').lower()
2154 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2156 format_id = compat_str(m.group('format_id'))
2157 if format_id.endswith('mpegurl'):
2158 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2159 elif format_id == 'f4m':
2160 formats = self._extract_f4m_formats(url, video_id)
2163 'format_id': format_id,
2165 'vcodec': 'none' if m.group('type') == 'audio' else None
2167 info_dict['direct'] = True
2168 self._sort_formats(formats)
2169 info_dict['formats'] = formats
2172 if not self._downloader.params.get('test', False) and not is_intentional:
2173 force = self._downloader.params.get('force_generic_extractor', False)
2174 self._downloader.report_warning(
2175 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2177 if not full_response:
2178 request = sanitized_Request(url)
2179 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2180 # making it impossible to download only chunk of the file (yet we need only 512kB to
2181 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2182 # that will always result in downloading the whole file that is not desirable.
2183 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2184 # to accept raw bytes and being able to download only a chunk.
2185 # It may probably better to solve this by checking Content-Type for application/octet-stream
2186 # after HEAD request finishes, but not sure if we can rely on this.
2187 request.add_header('Accept-Encoding', '*')
2188 full_response = self._request_webpage(request, video_id)
2190 first_bytes = full_response.read(512)
2192 # Is it an M3U playlist?
2193 if first_bytes.startswith(b'#EXTM3U'):
2194 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2195 self._sort_formats(info_dict['formats'])
2198 # Maybe it's a direct link to a video?
2199 # Be careful not to download the whole thing!
2200 if not is_html(first_bytes):
2201 self._downloader.report_warning(
2202 'URL could be a direct video link, returning it as such.')
2209 webpage = self._webpage_read_content(
2210 full_response, url, video_id, prefix=first_bytes)
2212 self.report_extraction(video_id)
2214 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2216 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2217 if doc.tag == 'rss':
2218 return self._extract_rss(url, video_id, doc)
2219 elif doc.tag == 'SmoothStreamingMedia':
2220 info_dict['formats'] = self._parse_ism_formats(doc, url)
2221 self._sort_formats(info_dict['formats'])
2223 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2224 smil = self._parse_smil(doc, url, video_id)
2225 self._sort_formats(smil['formats'])
2227 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2228 return self.playlist_result(
2230 doc, video_id, xspf_url=url,
2231 xspf_base_url=compat_str(full_response.geturl())),
2233 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2234 info_dict['formats'] = self._parse_mpd_formats(
2236 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2238 self._sort_formats(info_dict['formats'])
2240 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2241 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2242 self._sort_formats(info_dict['formats'])
2244 except compat_xml_parse_error:
2247 # Is it a Camtasia project?
2248 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2249 if camtasia_res is not None:
2252 # Sometimes embedded video player is hidden behind percent encoding
2253 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2254 # Unescaping the whole page allows to handle those cases in a generic way
2255 webpage = compat_urllib_parse_unquote(webpage)
2257 # it's tempting to parse this further, but you would
2258 # have to take into account all the variations like
2259 # Video Title - Site Name
2260 # Site Name | Video Title
2261 # Video Title - Tagline | Site Name
2262 # and so on and so forth; it's just not practical
2263 video_title = self._og_search_title(
2264 webpage, default=None) or self._html_search_regex(
2265 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2268 # Try to detect age limit automatically
2269 age_limit = self._rta_search(webpage)
2270 # And then there are the jokers who advertise that they use RTA,
2271 # but actually don't.
2272 AGE_LIMIT_MARKERS = [
2273 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2275 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2278 # video uploader is domain name
2279 video_uploader = self._search_regex(
2280 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2282 video_description = self._og_search_description(webpage, default=None)
2283 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2286 'title': video_title,
2287 'description': video_description,
2288 'thumbnail': video_thumbnail,
2289 'age_limit': age_limit,
2292 # Look for Brightcove Legacy Studio embeds
2293 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2297 'url': smuggle_url(bc_url, {'Referer': url}),
2298 'ie_key': 'BrightcoveLegacy'
2299 } for bc_url in bc_urls]
2302 '_type': 'playlist',
2303 'title': video_title,
2308 # Look for Brightcove New Studio embeds
2309 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2311 return self.playlist_from_matches(
2312 bc_urls, video_id, video_title,
2313 getter=lambda x: smuggle_url(x, {'referrer': url}),
2316 # Look for Nexx embeds
2317 nexx_urls = NexxIE._extract_urls(webpage)
2319 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2321 # Look for Nexx iFrame embeds
2322 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2324 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2326 # Look for ThePlatform embeds
2327 tp_urls = ThePlatformIE._extract_urls(webpage)
2329 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2331 # Look for Vessel embeds
2332 vessel_urls = VesselIE._extract_urls(webpage)
2334 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2336 # Look for embedded rtl.nl player
2337 matches = re.findall(
2338 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2341 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2343 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2345 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2347 vid_me_embed_url = self._search_regex(
2348 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2349 webpage, 'vid.me embed', default=None)
2350 if vid_me_embed_url is not None:
2351 return self.url_result(vid_me_embed_url, 'Vidme')
2353 # Look for YouTube embeds
2354 youtube_urls = YoutubeIE._extract_urls(webpage)
2356 return self.playlist_from_matches(
2357 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2359 matches = DailymotionIE._extract_urls(webpage)
2361 return self.playlist_from_matches(matches, video_id, video_title)
2363 # Look for embedded Dailymotion playlist player (#3822)
2365 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2367 playlists = re.findall(
2368 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2370 return self.playlist_from_matches(
2371 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2373 # Look for DailyMail embeds
2374 dailymail_urls = DailyMailIE._extract_urls(webpage)
2376 return self.playlist_from_matches(
2377 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2379 # Look for embedded Wistia player
2380 wistia_url = WistiaIE._extract_url(webpage)
2383 '_type': 'url_transparent',
2384 'url': self._proto_relative_url(wistia_url),
2385 'ie_key': WistiaIE.ie_key(),
2386 'uploader': video_uploader,
2389 # Look for SVT player
2390 svt_url = SVTIE._extract_url(webpage)
2392 return self.url_result(svt_url, 'SVT')
2394 # Look for Bandcamp pages with custom domain
2395 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2396 if mobj is not None:
2397 burl = unescapeHTML(mobj.group(1))
2398 # Don't set the extractor because it can be a track url or an album
2399 return self.url_result(burl)
2401 # Look for embedded Vevo player
2403 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2404 if mobj is not None:
2405 return self.url_result(mobj.group('url'))
2407 # Look for embedded Viddler player
2409 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2411 if mobj is not None:
2412 return self.url_result(mobj.group('url'))
2414 # Look for NYTimes player
2416 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2418 if mobj is not None:
2419 return self.url_result(mobj.group('url'))
2421 # Look for Libsyn player
2423 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2424 if mobj is not None:
2425 return self.url_result(mobj.group('url'))
2427 # Look for Ooyala videos
2428 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2429 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2430 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2431 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2432 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2433 if mobj is not None:
2434 embed_token = self._search_regex(
2435 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2436 webpage, 'ooyala embed token', default=None)
2437 return OoyalaIE._build_url_result(smuggle_url(
2440 'embed_token': embed_token,
2443 # Look for multiple Ooyala embeds on SBN network websites
2444 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2445 if mobj is not None:
2446 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2448 return self.playlist_from_matches(
2449 embeds, video_id, video_title,
2450 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2452 # Look for Aparat videos
2453 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2454 if mobj is not None:
2455 return self.url_result(mobj.group(1), 'Aparat')
2457 # Look for MPORA videos
2458 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2459 if mobj is not None:
2460 return self.url_result(mobj.group(1), 'Mpora')
2462 # Look for embedded NovaMov-based player
2464 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2465 (?P<url>http://(?:(?:embed|www)\.)?
2467 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2468 videoweed\.(?:es|com)|
2469 movshare\.(?:net|sx|ag)|
2470 divxstage\.(?:eu|net|ch|co|at|ag))
2471 /embed\.php.+?)\1''', webpage)
2472 if mobj is not None:
2473 return self.url_result(mobj.group('url'))
2475 # Look for embedded Facebook player
2476 facebook_urls = FacebookIE._extract_urls(webpage)
2478 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2480 # Look for embedded VK player
2481 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2482 if mobj is not None:
2483 return self.url_result(mobj.group('url'), 'VK')
2485 # Look for embedded Odnoklassniki player
2486 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2487 if mobj is not None:
2488 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2490 # Look for embedded ivi player
2491 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2492 if mobj is not None:
2493 return self.url_result(mobj.group('url'), 'Ivi')
2495 # Look for embedded Huffington Post player
2497 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2498 if mobj is not None:
2499 return self.url_result(mobj.group('url'), 'HuffPost')
2502 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2503 if mobj is not None:
2504 return self.url_result(mobj.group('url'))
2505 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2506 if mobj is not None:
2507 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2509 # Look for funnyordie embed
2510 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2512 return self.playlist_from_matches(
2513 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2515 # Look for BBC iPlayer embed
2516 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2518 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2520 # Look for embedded RUTV player
2521 rutv_url = RUTVIE._extract_url(webpage)
2523 return self.url_result(rutv_url, 'RUTV')
2525 # Look for embedded TVC player
2526 tvc_url = TVCIE._extract_url(webpage)
2528 return self.url_result(tvc_url, 'TVC')
2530 # Look for embedded SportBox player
2531 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2533 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2535 # Look for embedded XHamster player
2536 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2538 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2540 # Look for embedded TNAFlixNetwork player
2541 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2543 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2545 # Look for embedded PornHub player
2546 pornhub_urls = PornHubIE._extract_urls(webpage)
2548 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2550 # Look for embedded DrTuber player
2551 drtuber_urls = DrTuberIE._extract_urls(webpage)
2553 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2555 # Look for embedded RedTube player
2556 redtube_urls = RedTubeIE._extract_urls(webpage)
2558 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2560 # Look for embedded Tube8 player
2561 tube8_urls = Tube8IE._extract_urls(webpage)
2563 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2565 # Look for embedded Tvigle player
2567 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2568 if mobj is not None:
2569 return self.url_result(mobj.group('url'), 'Tvigle')
2571 # Look for embedded TED player
2573 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2574 if mobj is not None:
2575 return self.url_result(mobj.group('url'), 'TED')
2577 # Look for embedded Ustream videos
2578 ustream_url = UstreamIE._extract_url(webpage)
2580 return self.url_result(ustream_url, UstreamIE.ie_key())
2582 # Look for embedded arte.tv player
2584 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2586 if mobj is not None:
2587 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2589 # Look for embedded francetv player
2591 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2593 if mobj is not None:
2594 return self.url_result(mobj.group('url'))
2596 # Look for embedded smotri.com player
2597 smotri_url = SmotriIE._extract_url(webpage)
2599 return self.url_result(smotri_url, 'Smotri')
2601 # Look for embedded Myvi.ru player
2602 myvi_url = MyviIE._extract_url(webpage)
2604 return self.url_result(myvi_url)
2606 # Look for embedded soundcloud player
2607 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2609 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2611 # Look for tunein player
2612 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2614 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2616 # Look for embedded mtvservices player
2617 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2619 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2621 # Look for embedded yahoo player
2623 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2625 if mobj is not None:
2626 return self.url_result(mobj.group('url'), 'Yahoo')
2628 # Look for embedded sbs.com.au player
2632 <meta\s+property="og:video"\s+content=|
2635 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2637 if mobj is not None:
2638 return self.url_result(mobj.group('url'), 'SBS')
2640 # Look for embedded Cinchcast player
2642 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2644 if mobj is not None:
2645 return self.url_result(mobj.group('url'), 'Cinchcast')
2648 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2652 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2654 if mobj is not None:
2655 return self.url_result(mobj.group('url'), 'MLB')
2658 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2660 if mobj is not None:
2661 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2664 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2666 if mobj is not None:
2667 return self.url_result(mobj.group('url'), 'Livestream')
2669 # Look for Zapiks embed
2671 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2672 if mobj is not None:
2673 return self.url_result(mobj.group('url'), 'Zapiks')
2675 # Look for Kaltura embeds
2676 kaltura_url = KalturaIE._extract_url(webpage)
2678 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2680 # Look for EaglePlatform embeds
2681 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2682 if eagleplatform_url:
2683 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2685 # Look for ClipYou (uses EaglePlatform) embeds
2687 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2688 if mobj is not None:
2689 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2691 # Look for Pladform embeds
2692 pladform_url = PladformIE._extract_url(webpage)
2694 return self.url_result(pladform_url)
2696 # Look for Videomore embeds
2697 videomore_url = VideomoreIE._extract_url(webpage)
2699 return self.url_result(videomore_url)
2701 # Look for Webcaster embeds
2702 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2704 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2706 # Look for Playwire embeds
2708 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2709 if mobj is not None:
2710 return self.url_result(mobj.group('url'))
2712 # Look for 5min embeds
2714 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2715 if mobj is not None:
2716 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2718 # Look for Crooks and Liars embeds
2720 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2721 if mobj is not None:
2722 return self.url_result(mobj.group('url'))
2724 # Look for NBC Sports VPlayer embeds
2725 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2727 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2729 # Look for NBC News embeds
2730 nbc_news_embed_url = re.search(
2731 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2732 if nbc_news_embed_url:
2733 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2735 # Look for Google Drive embeds
2736 google_drive_url = GoogleDriveIE._extract_url(webpage)
2737 if google_drive_url:
2738 return self.url_result(google_drive_url, 'GoogleDrive')
2740 # Look for UDN embeds
2742 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2743 if mobj is not None:
2744 return self.url_result(
2745 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2747 # Look for Senate ISVP iframe
2748 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2750 return self.url_result(senate_isvp_url, 'SenateISVP')
2752 # Look for OnionStudios embeds
2753 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2754 if onionstudios_url:
2755 return self.url_result(onionstudios_url)
2757 # Look for ViewLift embeds
2758 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2760 return self.url_result(viewlift_url)
2762 # Look for JWPlatform embeds
2763 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2765 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2767 # Look for Digiteka embeds
2768 digiteka_url = DigitekaIE._extract_url(webpage)
2770 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2772 # Look for Arkena embeds
2773 arkena_url = ArkenaIE._extract_url(webpage)
2775 return self.url_result(arkena_url, ArkenaIE.ie_key())
2777 # Look for Piksel embeds
2778 piksel_url = PikselIE._extract_url(webpage)
2780 return self.url_result(piksel_url, PikselIE.ie_key())
2782 # Look for Limelight embeds
2783 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2785 return self.playlist_result(
2786 limelight_urls, video_id, video_title, video_description)
2788 # Look for Anvato embeds
2789 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2791 return self.playlist_result(
2792 anvato_urls, video_id, video_title, video_description)
2794 # Look for AdobeTVVideo embeds
2796 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2798 if mobj is not None:
2799 return self.url_result(
2800 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2803 # Look for Vine embeds
2805 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2807 if mobj is not None:
2808 return self.url_result(
2809 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2811 # Look for VODPlatform embeds
2813 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2815 if mobj is not None:
2816 return self.url_result(
2817 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2819 # Look for Mangomolo embeds
2821 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2823 video\?.*?\bid=(?P<video_id>\d+)|
2824 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2825 ).+?)\1''', webpage)
2826 if mobj is not None:
2828 '_type': 'url_transparent',
2829 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2830 'title': video_title,
2831 'description': video_description,
2832 'thumbnail': video_thumbnail,
2833 'uploader': video_uploader,
2835 video_id = mobj.group('video_id')
2838 'ie_key': 'MangomoloVideo',
2843 'ie_key': 'MangomoloLive',
2844 'id': mobj.group('channel_id'),
2848 # Look for Instagram embeds
2849 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2850 if instagram_embed_url is not None:
2851 return self.url_result(
2852 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2854 # Look for LiveLeak embeds
2855 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2857 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2859 # Look for 3Q SDN embeds
2860 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2863 '_type': 'url_transparent',
2864 'ie_key': ThreeQSDNIE.ie_key(),
2865 'url': self._proto_relative_url(threeqsdn_url),
2866 'title': video_title,
2867 'description': video_description,
2868 'thumbnail': video_thumbnail,
2869 'uploader': video_uploader,
2872 # Look for VBOX7 embeds
2873 vbox7_url = Vbox7IE._extract_url(webpage)
2875 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2877 # Look for DBTV embeds
2878 dbtv_urls = DBTVIE._extract_urls(webpage)
2880 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2882 # Look for Videa embeds
2883 videa_urls = VideaIE._extract_urls(webpage)
2885 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2887 # Look for 20 minuten embeds
2888 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2890 return self.playlist_from_matches(
2891 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2893 # Look for Openload embeds
2894 openload_urls = OpenloadIE._extract_urls(webpage)
2896 return self.playlist_from_matches(
2897 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2899 # Look for VideoPress embeds
2900 videopress_urls = VideoPressIE._extract_urls(webpage)
2902 return self.playlist_from_matches(
2903 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2905 # Look for Rutube embeds
2906 rutube_urls = RutubeIE._extract_urls(webpage)
2908 return self.playlist_from_matches(
2909 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2911 # Look for WashingtonPost embeds
2912 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2914 return self.playlist_from_matches(
2915 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2917 # Look for Mediaset embeds
2918 mediaset_urls = MediasetIE._extract_urls(webpage)
2920 return self.playlist_from_matches(
2921 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2923 # Look for JOJ.sk embeds
2924 joj_urls = JojIE._extract_urls(webpage)
2926 return self.playlist_from_matches(
2927 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2929 # Look for megaphone.fm embeds
2930 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2932 return self.playlist_from_matches(
2933 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2935 # Look for vzaar embeds
2936 vzaar_urls = VzaarIE._extract_urls(webpage)
2938 return self.playlist_from_matches(
2939 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2941 channel9_urls = Channel9IE._extract_urls(webpage)
2943 return self.playlist_from_matches(
2944 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
2946 vshare_urls = VShareIE._extract_urls(webpage)
2948 return self.playlist_from_matches(
2949 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
2951 # Look for Mediasite embeds
2952 mediasite_urls = MediasiteIE._extract_urls(webpage)
2955 self.url_result(smuggle_url(
2956 compat_urlparse.urljoin(url, mediasite_url),
2957 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
2958 for mediasite_url in mediasite_urls]
2959 return self.playlist_result(entries, video_id, video_title)
2961 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
2962 if springboardplatform_urls:
2963 return self.playlist_from_matches(
2964 springboardplatform_urls, video_id, video_title,
2965 ie=SpringboardPlatformIE.ie_key())
2967 yapfiles_urls = YapFilesIE._extract_urls(webpage)
2969 return self.playlist_from_matches(
2970 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
2972 vice_urls = ViceIE._extract_urls(webpage)
2974 return self.playlist_from_matches(
2975 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
2977 xfileshare_urls = XFileShareIE._extract_urls(webpage)
2979 return self.playlist_from_matches(
2980 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
2982 sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
2983 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
2985 if sharevideos_urls:
2986 return self.playlist_from_matches(
2987 sharevideos_urls, video_id, video_title)
2989 def merge_dicts(dict1, dict2):
2991 for k, v in dict1.items():
2994 for k, v in dict2.items():
2997 if (k not in merged or
2998 (isinstance(v, compat_str) and v and
2999 isinstance(merged[k], compat_str) and
3004 # Look for HTML5 media
3005 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3007 if len(entries) == 1:
3010 'title': video_title,
3013 for num, entry in enumerate(entries, start=1):
3015 'id': '%s-%s' % (video_id, num),
3016 'title': '%s (%d)' % (video_title, num),
3018 for entry in entries:
3019 self._sort_formats(entry['formats'])
3020 return self.playlist_result(entries, video_id, video_title)
3022 jwplayer_data = self._find_jwplayer_data(
3023 webpage, video_id, transform_source=js_to_json)
3025 info = self._parse_jwplayer_data(
3026 jwplayer_data, video_id, require_title=False, base_url=url)
3027 return merge_dicts(info, info_dict)
3031 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3033 if mobj is not None:
3034 sources = self._parse_json(
3035 mobj.group(1), video_id, transform_source=js_to_json,
3037 if not isinstance(sources, list):
3040 for source in sources:
3041 src = source.get('src')
3042 if not src or not isinstance(src, compat_str):
3044 src = compat_urlparse.urljoin(url, src)
3045 src_type = source.get('type')
3046 if isinstance(src_type, compat_str):
3047 src_type = src_type.lower()
3048 ext = determine_ext(src).lower()
3049 if src_type == 'video/youtube':
3050 return self.url_result(src, YoutubeIE.ie_key())
3051 if src_type == 'application/dash+xml' or ext == 'mpd':
3052 formats.extend(self._extract_mpd_formats(
3053 src, video_id, mpd_id='dash', fatal=False))
3054 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3055 formats.extend(self._extract_m3u8_formats(
3056 src, video_id, 'mp4', entry_protocol='m3u8_native',
3057 m3u8_id='hls', fatal=False))
3061 'ext': (mimetype2ext(src_type) or
3062 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3065 self._sort_formats(formats)
3066 info_dict['formats'] = formats
3069 # Looking for http://schema.org/VideoObject
3070 json_ld = self._search_json_ld(
3071 webpage, video_id, default={}, expected_type='VideoObject')
3072 if json_ld.get('url'):
3073 return merge_dicts(json_ld, info_dict)
3075 def check_video(vurl):
3076 if YoutubeIE.suitable(vurl):
3078 if RtmpIE.suitable(vurl):
3080 vpath = compat_urlparse.urlparse(vurl).path
3081 vext = determine_ext(vpath)
3082 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3084 def filter_video(urls):
3085 return list(filter(check_video, urls))
3087 # Start with something easy: JW Player in SWFObject
3088 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3090 # Look for gorilla-vid style embedding
3091 found = filter_video(re.findall(r'''(?sx)
3095 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3098 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3100 # Broaden the search a little bit
3101 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3103 # Broaden the findall a little bit: JWPlayer JS loader
3104 found = filter_video(re.findall(
3105 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3108 found = filter_video(re.findall(r'''(?xs)
3109 flowplayer\("[^"]+",\s*
3111 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3112 ["']?url["']?\s*:\s*["']([^"']+)["']
3117 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3119 # Try to find twitter cards info
3120 # twitter:player:stream should be checked before twitter:player since
3121 # it is expected to contain a raw stream (see
3122 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3123 found = filter_video(re.findall(
3124 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3126 # We look for Open Graph info:
3127 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3128 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3129 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3130 if m_video_type is not None:
3131 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3133 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3135 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3136 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3139 # Look also in Refresh HTTP header
3140 refresh_header = head_response.headers.get('Refresh')
3142 # In python 2 response HTTP headers are bytestrings
3143 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3144 refresh_header = refresh_header.decode('iso-8859-1')
3145 found = re.search(REDIRECT_REGEX, refresh_header)
3147 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3149 self.report_following_redirect(new_url)
3158 # twitter:player is a https URL to iframe player that may or may not
3159 # be supported by youtube-dl thus this is checked the very last (see
3160 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3161 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3162 if embed_url and embed_url != url:
3163 return self.url_result(embed_url)
3166 raise UnsupportedError(url)
3169 for video_url in orderedSet(found):
3170 video_url = unescapeHTML(video_url)
3171 video_url = video_url.replace('\\/', '/')
3172 video_url = compat_urlparse.urljoin(url, video_url)
3173 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3175 # Sometimes, jwplayer extraction will result in a YouTube URL
3176 if YoutubeIE.suitable(video_url):
3177 entries.append(self.url_result(video_url, 'Youtube'))
3180 # here's a fun little line of code for you:
3181 video_id = os.path.splitext(video_id)[0]
3185 'uploader': video_uploader,
3186 'title': video_title,
3187 'age_limit': age_limit,
3190 if RtmpIE.suitable(video_url):
3191 entry_info_dict.update({
3192 '_type': 'url_transparent',
3193 'ie_key': RtmpIE.ie_key(),
3196 entries.append(entry_info_dict)
3199 ext = determine_ext(video_url)
3201 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3203 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3205 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3207 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3209 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3210 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3211 # Just matching .ism/manifest is not enough to be reliably sure
3212 # whether it's actually an ISM manifest or some other streaming
3213 # manifest since there are various streaming URL formats
3214 # possible (see [1]) as well as some other shenanigans like
3215 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3217 # Thus the most reasonable way to solve this is to delegate
3218 # to generic extractor in order to look into the contents of
3219 # the manifest itself.
3220 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3221 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3222 entry_info_dict = self.url_result(
3223 smuggle_url(video_url, {'to_generic': True}),
3226 entry_info_dict['url'] = video_url
3228 if entry_info_dict.get('formats'):
3229 self._sort_formats(entry_info_dict['formats'])
3231 entries.append(entry_info_dict)
3233 if len(entries) == 1:
3236 for num, e in enumerate(entries, start=1):
3237 # 'url' results don't have a title
3238 if e.get('title') is not None:
3239 e['title'] = '%s (%d)' % (e['title'], num)
3241 '_type': 'playlist',