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 .vimeo import VimeoIE
62 from .dailymotion import DailymotionIE
63 from .dailymail import DailyMailIE
64 from .onionstudios import OnionStudiosIE
65 from .viewlift import ViewLiftEmbedIE
66 from .mtv import MTVServicesEmbeddedIE
67 from .pladform import PladformIE
68 from .videomore import VideomoreIE
69 from .webcaster import WebcasterFeedIE
70 from .googledrive import GoogleDriveIE
71 from .jwplatform import JWPlatformIE
72 from .digiteka import DigitekaIE
73 from .arkena import ArkenaIE
74 from .instagram import InstagramIE
75 from .liveleak import LiveLeakIE
76 from .threeqsdn import ThreeQSDNIE
77 from .theplatform import ThePlatformIE
78 from .vessel import VesselIE
79 from .kaltura import KalturaIE
80 from .eagleplatform import EaglePlatformIE
81 from .facebook import FacebookIE
82 from .soundcloud import SoundcloudIE
83 from .tunein import TuneInBaseIE
84 from .vbox7 import Vbox7IE
85 from .dbtv import DBTVIE
86 from .piksel import PikselIE
87 from .videa import VideaIE
88 from .twentymin import TwentyMinutenIE
89 from .ustream import UstreamIE
90 from .openload import OpenloadIE
91 from .videopress import VideoPressIE
92 from .rutube import RutubeIE
93 from .limelight import LimelightBaseIE
94 from .anvato import AnvatoIE
95 from .washingtonpost import WashingtonPostIE
96 from .wistia import WistiaIE
97 from .mediaset import MediasetIE
98 from .joj import JojIE
99 from .megaphone import MegaphoneIE
100 from .vzaar import VzaarIE
101 from .channel9 import Channel9IE
102 from .vshare import VShareIE
103 from .mediasite import MediasiteIE
104 from .springboardplatform import SpringboardPlatformIE
105 from .yapfiles import YapFilesIE
106 from .vice import ViceIE
107 from .xfileshare import XFileShareIE
110 class GenericIE(InfoExtractor):
111 IE_DESC = 'Generic downloader that works on some sites'
115 # Direct link to a video
117 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
118 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
123 'upload_date': '20100513',
126 # Direct link to media delivered compressed (until Accept-Encoding is *)
128 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
129 'md5': '128c42e68b13950268b648275386fc74',
131 'id': 'FictionJunction-Parallel_Hearts',
133 'title': 'FictionJunction-Parallel_Hearts',
134 'upload_date': '20140522',
136 'expected_warnings': [
137 'URL could be a direct video link, returning it as such.'
139 'skip': 'URL invalid',
141 # Direct download with broken HEAD
143 'url': 'http://ai-radio.org:8000/radio.opus',
150 'skip_download': True, # infinite live stream
152 'expected_warnings': [
153 r'501.*Not Implemented',
157 # Direct link with incorrect MIME type
159 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
160 'md5': '4ccbebe5f36706d85221f204d7eb5913',
162 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
163 'id': '5_Lennart_Poettering_-_Systemd',
165 'title': '5_Lennart_Poettering_-_Systemd',
166 'upload_date': '20141120',
168 'expected_warnings': [
169 'URL could be a direct video link, returning it as such.'
174 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
176 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
177 'title': 'Zero Punctuation',
178 'description': 're:.*groundbreaking video review series.*'
180 'playlist_mincount': 11,
182 # RSS feed with enclosure
184 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
186 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
188 'upload_date': '20150228',
189 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
192 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
194 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
198 'title': 'Automatics, robotics and biocybernetics',
199 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
200 'upload_date': '20130627',
201 'formats': 'mincount:16',
202 'subtitles': 'mincount:1',
205 'force_generic_extractor': True,
206 'skip_download': True,
209 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
211 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
216 'formats': 'mincount:1',
219 'skip_download': True,
222 # SMIL from https://www.restudy.dk/video/play/id/1637
224 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
228 'title': 'video_1637',
229 'formats': 'mincount:3',
232 'skip_download': True,
235 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
237 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
239 'id': 'smil-service',
241 'title': 'smil-service',
242 'formats': 'mincount:1',
245 'skip_download': True,
248 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
250 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
254 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
255 'formats': 'mincount:3',
258 'skip_download': True,
261 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
263 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
265 'id': 'mZlp2ctYIUEB',
267 'title': 'Tikibad ontruimd wegens brand',
268 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
269 'thumbnail': r're:^https?://.*\.jpg$',
273 'skip_download': True,
276 # MPD from http://dash-mse-test.appspot.com/media.html
278 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
279 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
281 'id': 'car-20120827-manifest',
283 'title': 'car-20120827-manifest',
284 'formats': 'mincount:9',
285 'upload_date': '20130904',
288 'format': 'bestvideo',
291 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
293 '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',
298 'formats': 'mincount:8',
302 'skip_download': True,
304 'skip': 'video gone',
306 # m3u8 served with Content-Type: text/plain
308 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
313 'upload_date': '20140720',
314 'formats': 'mincount:11',
318 'skip_download': True,
320 'skip': 'video gone',
324 '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',
328 'upload_date': '20130224',
329 'uploader_id': 'TheVerge',
330 'description': r're:^Chris Ziegler takes a look at the\.*',
331 'uploader': 'The Verge',
332 'title': 'First Firefox OS phones side-by-side',
335 'skip_download': False,
339 # redirect in Refresh HTTP header
340 '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',
344 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
345 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
346 'upload_date': '20150917',
347 'uploader_id': 'brtvofficial',
348 'uploader': 'Boiler Room',
351 'skip_download': False,
355 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
356 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
358 'id': '13601338388002',
360 'uploader': 'www.hodiho.fr',
361 'title': 'R\u00e9gis plante sa Jeep',
364 # bandcamp page with custom domain
366 'add_ie': ['Bandcamp'],
367 'url': 'http://bronyrock.com/track/the-pony-mash',
371 'title': 'The Pony Mash',
372 'uploader': 'M_Pallante',
374 'skip': 'There is a limit of 200 free downloads / month for the test song',
377 # embedded brightcove video
378 # it also tests brightcove videos that need to set the 'Referer'
379 # in the http requests
380 'add_ie': ['BrightcoveLegacy'],
381 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
383 'id': '2765128793001',
385 'title': 'Le cours de bourse : l’analyse technique',
386 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
387 'uploader': 'BFM BUSINESS',
390 'skip_download': True,
394 # embedded with itemprop embedURL and video id spelled as `idVideo`
395 'add_id': ['BrightcoveLegacy'],
396 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
398 'id': '5255628253001',
400 'title': 'md5:37c519b1128915607601e75a87995fc0',
401 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
402 'uploader': 'BFM BUSINESS',
403 'uploader_id': '876450612001',
404 'timestamp': 1482255315,
405 'upload_date': '20161220',
408 'skip_download': True,
412 # https://github.com/rg3/youtube-dl/issues/2253
413 'url': 'http://bcove.me/i6nfkrc3',
414 'md5': '0ba9446db037002366bab3b3eb30c88c',
416 'id': '3101154703001',
418 'title': 'Still no power',
419 'uploader': 'thestar.com',
420 '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.',
422 'add_ie': ['BrightcoveLegacy'],
423 'skip': 'video gone',
426 'url': 'http://www.championat.com/video/football/v/87/87499.html',
427 'md5': 'fb973ecf6e4a78a67453647444222983',
429 'id': '3414141473001',
431 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
432 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
433 'uploader': 'Championat',
437 # https://github.com/rg3/youtube-dl/issues/3541
438 'add_ie': ['BrightcoveLegacy'],
439 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
441 'id': '3866516442001',
443 'title': 'Leer mij vrouwen kennen: Aflevering 1',
444 'description': 'Leer mij vrouwen kennen: Aflevering 1',
445 'uploader': 'SBS Broadcasting',
447 'skip': 'Restricted to Netherlands',
449 'skip_download': True, # m3u8 download
453 # Brightcove video in <iframe>
454 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
455 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
457 'id': '5360463607001',
459 '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',
460 '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。',
461 'uploader': 'United Nations',
462 'uploader_id': '1362235914001',
463 'timestamp': 1489593889,
464 'upload_date': '20170315',
466 'add_ie': ['BrightcoveLegacy'],
469 # Brightcove with alternative playerID key
470 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
472 'id': 'nmeth.2062_SV1',
473 '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',
477 'id': '2228375078001',
479 'title': 'nmeth.2062-sv1',
480 'description': 'nmeth.2062-sv1',
481 'timestamp': 1363357591,
482 'upload_date': '20130315',
483 'uploader': 'Nature Publishing Group',
484 'uploader_id': '1964492299001',
489 # Brightcove with UUID in videoPlayer
490 'url': 'http://www8.hp.com/cn/zh/home.html',
492 'id': '5255815316001',
494 'title': 'Sprocket Video - China',
495 'description': 'Sprocket Video - China',
496 'uploader': 'HP-Video Gallery',
497 'timestamp': 1482263210,
498 'upload_date': '20161220',
499 'uploader_id': '1107601872001',
502 'skip_download': True, # m3u8 download
504 'skip': 'video rotates...weekly?',
507 # Brightcove:new type [2].
508 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
509 'md5': '2b35148fcf48da41c9fb4591650784f3',
511 'id': '5348741021001',
513 'upload_date': '20170306',
514 'uploader_id': '4191638492001',
515 'timestamp': 1488769918,
516 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
521 # Alternative brightcove <video> attributes
522 '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/',
524 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
525 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
528 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
530 'id': '5311302538001',
532 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
533 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
534 'timestamp': 1486321708,
535 'upload_date': '20170205',
536 'uploader_id': '800000640001',
538 'only_matching': True,
542 # Brightcove with UUID in videoPlayer
543 'url': 'http://www8.hp.com/cn/zh/home.html',
545 'id': '5255815316001',
547 'title': 'Sprocket Video - China',
548 'description': 'Sprocket Video - China',
549 'uploader': 'HP-Video Gallery',
550 'timestamp': 1482263210,
551 'upload_date': '20161220',
552 'uploader_id': '1107601872001',
555 'skip_download': True, # m3u8 download
560 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
561 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
563 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
565 'title': '2cc213299525360.mov', # that's what we get
568 'add_ie': ['Ooyala'],
571 # ooyala video embedded with http://player.ooyala.com/iframe.js
572 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
574 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
576 'title': '"Steve Jobs: Man in the Machine" trailer',
577 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
581 'skip_download': True,
583 'skip': 'movie expired',
585 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
587 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
589 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
591 'title': 'Steampunk Fest Comes to Honesdale',
595 'skip_download': True,
600 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
604 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
605 'upload_date': '20140225',
606 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
607 'uploader': 'Tested',
608 'uploader_id': 'testedcom',
610 # No need to test YoutubeIE here
612 'skip_download': True,
617 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
621 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
622 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
624 # HEAD requests lead to endless 301, while GET is OK
625 'expected_warnings': ['301'],
629 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
633 'title': 'Охотское море стало целиком российским',
634 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
638 'skip_download': True,
643 '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/',
647 'title': 'Дошкольное воспитание',
652 'url': 'http://www.vestifinance.ru/articles/25753',
655 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
660 'title': 'Госзаказ. День 3',
666 'title': 'Госзаказ. День 2',
672 'title': 'Госзаказ. День 1',
678 'skip_download': True,
683 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
685 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
687 'title': 'Ужастики, русский трейлер (2015)',
688 'thumbnail': r're:^https?://.*\.jpg$',
694 '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',
697 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
699 'playlist_mincount': 7,
700 # This forum does not allow <iframe> syntaxes anymore
701 # Now HTML tags are displayed as-is
702 'skip': 'No videos on this page',
706 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
707 'md5': '65fdff94098e4a607385a60c5177c638',
711 'title': 'Hidden miracles of the natural world',
712 'uploader': 'Louie Schwartzberg',
713 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
716 # nowvideo embed hidden behind percent encoding
718 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
719 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
721 'id': '06e53103ca9aa',
723 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
724 'description': 'No description',
729 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
730 'md5': '7653032cbb25bf6c80d80f217055fa43',
732 'id': '048195-004_PLUS7-F',
735 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
736 'upload_date': '20140320',
739 'skip_download': 'Requires rtmpdump'
741 'skip': 'video gone',
745 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
749 'title': 'Alcaline, le concert avec Calogero',
750 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
751 'upload_date': '20150226',
752 'timestamp': 1424989860,
757 'skip_download': True,
759 'expected_warnings': [
765 'url': 'http://www.wired.com/2014/04/honda-asimo/',
766 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
768 'id': '53501be369702d3275860000',
770 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
775 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
776 'md5': '441aeeb82eb72c422c7f14ec533999cd',
778 'id': 'k2mm4bCdJ6CQ2i7c8o2',
780 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
781 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
783 'uploader_id': 'xgditw',
784 'upload_date': '20140425',
785 'timestamp': 1398441542,
787 'add_ie': ['Dailymotion'],
791 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
795 'title': 'Care worker punches elderly dementia patient in head 11 times',
796 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
798 'add_ie': ['DailyMail'],
800 'skip_download': True,
805 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
809 'title': 'The NBL Auction 2014',
810 'uploader': 'BADMINTON England',
811 'uploader_id': 'BADMINTONEvents',
812 'upload_date': '20140603',
813 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
815 'add_ie': ['Youtube'],
817 'skip_download': True,
822 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
823 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
825 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
827 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
828 'description': 'Two valets share their love for movie star Liam Neesons.',
829 'timestamp': 1349922600,
830 'upload_date': '20121011',
833 # YouTube embed via <data-embed-url="">
835 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
839 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
840 'uploader': 'Gameloft',
841 'uploader_id': 'gameloft',
842 'upload_date': '20140828',
843 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
846 'skip_download': True,
849 # YouTube <object> embed
851 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
852 'md5': '516718101ec834f74318df76259fb3cc',
856 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
857 'upload_date': '20080526',
858 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
859 'uploader': 'Christopher Sykes',
860 'uploader_id': 'ChristopherJSykes',
862 'add_ie': ['Youtube'],
866 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
868 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
870 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
871 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
876 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
878 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
879 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
885 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
890 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
891 'md5': '9d65602bf31c6e20014319c7d07fba27',
893 'id': '5123ea6d5e5a7',
896 'uploader': 'www.handjobhub.com',
897 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
900 # Multiple brightcove videos
901 # https://github.com/rg3/youtube-dl/issues/2283
903 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
905 'id': 'always-never',
906 'title': 'Always / Never - The New Yorker',
910 'extract_flat': False,
911 'skip_download': True,
916 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
917 'md5': '96f09a37e44da40dd083e12d9a683327',
921 'title': 'Ump changes call to ball',
922 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
924 'timestamp': 1401537900,
925 'upload_date': '20140531',
926 'thumbnail': r're:^https?://.*\.jpg$',
931 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
932 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
936 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
937 'description': 'a Paywall Videos video from Remilon',
939 'uploader': 'study.com',
940 'timestamp': 1459678540,
941 'upload_date': '20160403',
942 'filesize': 24687186,
946 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
947 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
951 'title': 'Conversation about Hexagonal Rails Part 1',
952 'description': 'a Martin Fowler video from ThoughtWorks',
954 'uploader': 'thoughtworks.wistia.com',
955 'timestamp': 1401832161,
956 'upload_date': '20140603',
959 # Wistia standard embed (async)
961 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
965 'title': 'Drip Brennan Dunn Workshop',
966 'description': 'a JV Webinars video from getdrip-1',
968 'timestamp': 1463607249,
969 'upload_date': '20160518',
972 'skip_download': True,
977 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
981 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
982 'uploader': 'Sophos Security',
983 'title': 'Chet Chat 171 - Oct 29, 2014',
984 'upload_date': '20141029',
987 # Soundcloud multiple embeds
989 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
992 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
994 'playlist_mincount': 7,
996 # TuneIn station embed
998 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1003 'location': 'Paris, France',
1008 'skip_download': True,
1013 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1017 'upload_date': '20141112',
1018 'title': 'Rosetta #CometLanding webcast HL 10',
1021 # Another Livestream embed, without 'new.' in URL
1023 'url': 'https://www.freespeech.org/',
1027 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1031 'skip_download': True,
1036 'url': 'https://skiplagged.com/',
1039 'title': 'Skiplagged: The smart way to find cheap flights',
1041 'playlist_mincount': 1,
1042 'add_ie': ['Youtube'],
1046 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1050 'upload_date': '20141126',
1051 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1056 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1058 'id': '730m_DandD_1901_512k',
1060 'uploader': 'www.abc.net.au',
1061 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1064 # embedded viddler video
1066 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1070 'uploader': 'deadspin',
1071 'title': 'WALL-TO-GORTAT',
1072 'timestamp': 1422285291,
1073 'upload_date': '20150126',
1075 'add_ie': ['Viddler'],
1079 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1083 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1084 'description': 'md5:601cb790edd05908957dae8aaa866465',
1085 'upload_date': '20150220',
1087 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1091 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1093 'id': 'Mrj4DVp2zeA',
1095 'upload_date': '20150212',
1096 'uploader': 'The National Archives UK',
1097 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1098 'uploader_id': 'NationalArchives08',
1099 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1104 'url': 'http://www.suffolk.edu/sjc/live.php',
1108 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1109 'uploader': 'www.suffolk.edu',
1112 'skip_download': True,
1114 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1118 'url': 'http://www.indiedb.com/games/king-machine/videos',
1122 'title': 'king machine trailer 1',
1123 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1124 'thumbnail': r're:^https?://.*\.jpg$',
1128 # JWPlayer config passed as variable
1129 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1133 'title': 'ARIELE | Tube Cup',
1134 'uploader': 'www.txxx.com',
1138 'skip_download': True,
1143 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1144 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1148 'upload_date': '20171122',
1149 'timestamp': 1511366290,
1150 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1152 'add_ie': [JWPlatformIE.ie_key()],
1155 # Video.js embed, multiple formats
1156 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1158 'id': 'yygqldloqIk',
1160 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1161 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1162 'upload_date': '20130314',
1163 'uploader': 'PROстое3D',
1164 'uploader_id': 'PROstoe3D',
1167 'skip_download': True,
1171 # Video.js embed, single format
1172 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1176 'title': 'Step 1 - Good Foundation',
1177 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1180 'skip_download': True,
1185 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1186 'playlist_mincount': 5,
1188 'id': 'aanslagen-kopenhagen',
1189 'title': 'Aanslagen Kopenhagen',
1194 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1198 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1201 # Kaltura embed (different embed code)
1203 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1207 'upload_date': '20150127',
1208 'uploader_id': 'PremierMedia',
1210 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1213 # Kaltura embed with single quotes
1215 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1220 'timestamp': 1355743100,
1221 'upload_date': '20121217',
1222 'uploader_id': 'batchUser',
1224 'add_ie': ['Kaltura'],
1227 # Kaltura embedded via quoted entry_id
1228 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1232 'title': '06_matthew_brender_raj_dutt',
1233 'timestamp': 1466638791,
1234 'upload_date': '20160622',
1236 'add_ie': ['Kaltura'],
1237 'expected_warnings': [
1238 'Could not send HEAD request'
1241 'skip_download': True,
1245 # Kaltura embedded, some fileExt broken (#11480)
1246 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1250 'title': 'Our "Standard Models" of particle physics and cosmology',
1251 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1252 'timestamp': 1321158993,
1253 'upload_date': '20111113',
1254 'uploader_id': 'kps1',
1256 'add_ie': ['Kaltura'],
1259 # Kaltura iframe embed
1260 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1261 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1265 'title': 'I. M. Pei: A Centennial Celebration',
1266 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1267 'upload_date': '20170403',
1268 'uploader_id': 'batchUser',
1269 'timestamp': 1491232186,
1271 'add_ie': ['Kaltura'],
1273 # EaglePlatform embed (generic URL)
1275 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1276 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1280 'title': 'Навальный вышел на свободу',
1281 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1282 'thumbnail': r're:^https?://.*\.jpg$',
1288 'skip_download': True,
1291 # referrer protected EaglePlatform embed
1293 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1297 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1298 'thumbnail': r're:^https?://.*\.jpg$',
1303 'skip_download': True,
1306 # ClipYou (EaglePlatform) embed (custom URL)
1308 'url': 'http://muz-tv.ru/play/7129/',
1309 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1313 'title': "'O Sole Mio",
1314 'thumbnail': r're:^https?://.*\.jpg$',
1319 'skip_download': True,
1321 'skip': 'This video is unavailable.',
1325 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1329 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1330 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1331 'thumbnail': r're:^https?://.*\.jpg$',
1335 'skip': 'HTTP Error 404: Not Found',
1339 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1343 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1344 'thumbnail': r're:^https?://.*\.png$',
1350 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1351 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1355 'title': 'Facebook Creates "On This Day" | Crunch Report',
1356 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1357 'timestamp': 1427237531,
1358 'uploader': 'Crunch Report',
1359 'upload_date': '20150324',
1363 'skip_download': True,
1368 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1372 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1377 # Crooks and Liars embed
1379 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1383 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1384 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1385 'timestamp': 1428207000,
1386 'upload_date': '20150405',
1387 'uploader': 'Heather',
1390 # Crooks and Liars external embed
1392 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1394 'id': 'MTE3MjUtMzQ2MzA',
1396 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1397 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1398 'timestamp': 1265032391,
1399 'upload_date': '20100201',
1400 'uploader': 'Heather',
1403 # NBC Sports vplayer embed
1405 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1407 'id': 'ln7x1qSThw4k',
1409 'title': "PFT Live: New leader in the 'new-look' defense",
1410 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1411 'uploader': 'NBCU-SPORTS',
1412 'upload_date': '20140107',
1413 'timestamp': 1389118457,
1415 'skip': 'Invalid Page URL',
1419 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1420 'md5': '1aa589c675898ae6d37a17913cf68d66',
1422 'id': 'x_dtl_oa_LettermanliftPR_160608',
1424 'title': 'David Letterman: A Preview',
1425 '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.',
1426 'upload_date': '20160609',
1427 'timestamp': 1465431544,
1428 'uploader': 'NBCU-NEWS',
1433 'url': 'https://video.udn.com/news/300346',
1434 'md5': 'fd2060e988c326991037b9aff9df21a6',
1438 'title': '中一中男師變性 全校師生力挺',
1439 'thumbnail': r're:^https?://.*\.jpg$',
1443 'skip_download': True,
1445 'expected_warnings': ['Failed to parse JSON Expecting value'],
1449 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1451 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1453 'description': 'Index/Match versus VLOOKUP.',
1454 'title': 'This is what separates the Excel masters from the wannabes',
1455 'duration': 191.933,
1459 'skip_download': True,
1462 # Brightcove URL in single quotes
1464 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1465 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1467 'id': '4255764656001',
1469 'title': 'SN Presents: Russell Martin, World Citizen',
1470 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1471 'uploader': 'Rogers Sportsnet',
1472 'uploader_id': '1704050871',
1473 'upload_date': '20150525',
1474 'timestamp': 1432570283,
1477 # OnionStudios embed
1479 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1483 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1484 'thumbnail': r're:^https?://.*\.jpe?g$',
1485 'uploader': 'ClickHole',
1486 'uploader_id': 'clickhole',
1491 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1493 'id': '74849a00-85a9-11e1-9660-123139220831',
1495 'title': '#whilewewatch',
1498 # AdobeTVVideo embed
1500 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1501 'md5': '43662b577c018ad707a63766462b1e87',
1505 'title': 'New experience with Acrobat DC',
1506 'description': 'New experience with Acrobat DC',
1507 'duration': 248.667,
1510 # BrightcoveInPageEmbed embed
1512 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1514 'id': '4238694884001',
1516 'title': 'Tabletop: Dread, Last Thoughts',
1517 'description': 'Tabletop: Dread, Last Thoughts',
1521 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1522 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1524 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1526 'id': '4785848093001',
1528 'title': 'The Cardinal Pell Interview',
1529 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1530 'uploader': 'GlobeCast Australia - GlobeStream',
1531 'uploader_id': '2733773828001',
1532 'upload_date': '20160304',
1533 'timestamp': 1457083087,
1537 'skip_download': True,
1541 # Brightcove embed with whitespace around attribute names
1542 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1544 'id': '3167554373001',
1546 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1547 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1548 'uploader_id': '1079349493',
1549 'upload_date': '20140207',
1550 'timestamp': 1391810548,
1553 'skip_download': True,
1556 # Another form of arte.tv embed
1558 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1559 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1561 'id': '030273-562_PLUS7-F',
1563 'title': 'ARTE Reportage - Nulle part, en France',
1564 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1565 'upload_date': '20160409',
1570 'url': 'http://www.wykop.pl/link/3088787/',
1571 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1573 'id': '874_1459135191',
1575 'title': 'Man shows poor quality of new apartment building',
1576 'description': 'The wall is like a sand pile.',
1577 'uploader': 'Lake8737',
1579 'add_ie': [LiveLeakIE.ie_key()],
1581 # Another LiveLeak embed pattern (#13336)
1583 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1585 'id': '2eb_1496309988',
1587 'title': 'Thief robs place where everyone was armed',
1588 'description': 'md5:694d73ee79e535953cf2488562288eee',
1589 'uploader': 'brazilwtf',
1591 'add_ie': [LiveLeakIE.ie_key()],
1593 # Duplicated embedded video URLs
1595 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1597 'id': '149298443_480_16c25b74_2',
1599 'title': 'vs. Blue Orange Spring Game',
1600 'uploader': 'www.hudl.com',
1603 # twitter:player:stream embed
1605 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1609 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1610 'uploader': 'www.rtl.be',
1614 'skip_download': True,
1617 # twitter:player embed
1619 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1620 'md5': 'a3e0df96369831de324f0778e126653c',
1622 'id': '4909620399001',
1624 'title': 'What Do Black Holes Sound Like?',
1625 'description': 'what do black holes sound like',
1626 'upload_date': '20160524',
1627 'uploader_id': '29913724001',
1628 'timestamp': 1464107587,
1629 'uploader': 'TheAtlantic',
1631 'add_ie': ['BrightcoveLegacy'],
1633 # Facebook <iframe> embed
1635 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1636 'md5': 'fbcde74f534176ecb015849146dd3aee',
1638 'id': '599637780109885',
1640 'title': 'Facebook video #599637780109885',
1643 # Facebook <iframe> embed, plugin video
1645 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1647 'id': '1754168231264132',
1649 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1650 'uploader': 'Tariq Ramadan (official)',
1651 'timestamp': 1496758379,
1652 'upload_date': '20170606',
1655 'skip_download': True,
1658 # Facebook API embed
1660 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1661 'md5': 'a47372ee61b39a7b90287094d447d94e',
1663 'id': '10153467542406923',
1665 'title': 'Facebook video #10153467542406923',
1668 # Wordpress "YouTube Video Importer" plugin
1670 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1671 'md5': 'd16797741b560b485194eddda8121b48',
1673 'id': 'HNTXWDXV9Is',
1675 'title': 'Blue Devils Drumline Stanford lot 2016',
1676 'upload_date': '20160627',
1677 'uploader_id': 'GENOCIDE8GENERAL10',
1678 'uploader': 'cylus cyrus',
1682 # video stored on custom kaltura server
1683 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1684 'md5': '537617d06e64dfed891fa1593c4b30cc',
1688 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1689 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1690 'uploader_id': 'videos.expansion@el-mundo.net',
1691 'upload_date': '20150429',
1692 'timestamp': 1430303472,
1694 'add_ie': ['Kaltura'],
1697 # Non-standard Vimeo embed
1698 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1699 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1703 'title': 'Understanding the web - Teaser',
1704 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1705 'upload_date': '20151214',
1706 'uploader': 'OpenClassrooms',
1707 'uploader_id': 'openclassrooms',
1709 'add_ie': ['Vimeo'],
1712 # generic vimeo embed that requires original URL passed as Referer
1713 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1714 'only_matching': True,
1717 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1718 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1720 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1722 'title': 'Big Buck Bunny',
1723 'description': 'Royalty free test video',
1724 'timestamp': 1432816365,
1725 'upload_date': '20150528',
1729 'skip_download': True,
1731 'add_ie': [ArkenaIE.ie_key()],
1734 '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/',
1738 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1741 'skip_download': True,
1743 'add_ie': [Vbox7IE.ie_key()],
1747 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1750 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1752 'playlist_mincount': 3,
1756 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1758 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1759 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1761 'playlist_mincount': 2,
1765 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1769 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1770 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1773 'skip_download': True,
1775 'add_ie': [TwentyMinutenIE.ie_key()],
1779 'url': 'https://en.support.wordpress.com/videopress/',
1783 'title': 'IMG_5786',
1784 'timestamp': 1435711927,
1785 'upload_date': '20150701',
1788 'skip_download': True,
1790 'add_ie': [VideoPressIE.ie_key()],
1794 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1796 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1798 'title': 'Магаззино: Казань 2',
1799 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1800 'uploader': 'Магаззино',
1801 'upload_date': '20170228',
1802 'uploader_id': '996642',
1805 'skip_download': True,
1807 'add_ie': [RutubeIE.ie_key()],
1810 # ThePlatform embedded with whitespaces in URLs
1811 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1812 'only_matching': True,
1815 # Senate ISVP iframe https
1816 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1817 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1819 'id': 'govtaff020316',
1821 'title': 'Integrated Senate Video Player',
1823 'add_ie': [SenateISVPIE.ie_key()],
1826 # Limelight embeds (1 channel embed + 4 media embeds)
1827 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1829 'id': 'FacilitatorTraining2017',
1830 'title': 'Facilitator Training 2017',
1832 'playlist_mincount': 5,
1835 # Limelight embed (LimelightPlayerUtil.embed)
1836 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1838 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1840 'title': '07448641',
1841 'timestamp': 1499890639,
1842 'upload_date': '20170712',
1845 'skip_download': True,
1847 'add_ie': ['LimelightMedia'],
1850 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1852 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1853 'title': 'Standoff with Walnut Creek murder suspect ends',
1854 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1856 'playlist_mincount': 4,
1859 # WashingtonPost embed
1860 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1862 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1864 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1865 '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.',
1866 'timestamp': 1455216756,
1867 'uploader': 'The Washington Post',
1868 'upload_date': '20160211',
1870 'add_ie': [WashingtonPostIE.ie_key()],
1874 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1878 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1881 'skip_download': True,
1883 'add_ie': [MediasetIE.ie_key()],
1887 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1889 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1890 'title': 'Slovenskom sa prehnala vlna silných búrok',
1892 'playlist_mincount': 5,
1893 'add_ie': [JojIE.ie_key()],
1896 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1897 'url': 'https://tvrain.ru/amp/418921/',
1898 'md5': 'cc00413936695987e8de148b67d14f1d',
1902 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1907 'url': 'http://help.vzaar.com/article/165-embedding-video',
1908 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1912 'title': 'Building A Business Online: Principal Chairs Q & A',
1916 # multiple HTML5 videos on one page
1917 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1919 'id': 'keyscenarios',
1920 'title': 'Rescue Kit 14 Free Edition - Getting started',
1922 'playlist_count': 4,
1926 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1927 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1930 'title': 'vl14062007715967',
1935 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1936 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1938 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1940 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1941 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1942 'timestamp': 1474354800,
1943 'upload_date': '20160920',
1947 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1951 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1952 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1953 'timestamp': 1516100691,
1954 'upload_date': '20180116',
1957 'skip_download': True,
1959 'add_ie': [SpringboardPlatformIE.ie_key()],
1962 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1964 'id': 'uPDB5I9wfp8',
1966 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1967 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1968 'upload_date': '20160219',
1969 'uploader': 'Pocoyo - Português (BR)',
1970 'uploader_id': 'PocoyoBrazil',
1972 'add_ie': [YoutubeIE.ie_key()],
1974 'skip_download': True,
1978 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1980 'id': 'vMDE4NzI1Mjgt690b',
1984 'add_ie': [YapFilesIE.ie_key()],
1986 'skip_download': True,
1990 # # TODO: find another test
1991 # # http://schema.org/VideoObject
1992 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1993 # 'md5': '888dcf08b7ea671381f00fab74692755',
1995 # 'id': 'nyvTSJMKId',
1997 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1998 # 'description': '#love for cats.',
1999 # 'timestamp': 1461244995,
2000 # 'upload_date': '20160421',
2003 # 'force_generic_extractor': True,
2008 def report_following_redirect(self, new_url):
2009 """Report information extraction."""
2010 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2012 def _extract_rss(self, url, video_id, doc):
2013 playlist_title = doc.find('./channel/title').text
2014 playlist_desc_el = doc.find('./channel/description')
2015 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2018 for it in doc.findall('./channel/item'):
2019 next_url = xpath_text(it, 'link', fatal=False)
2021 enclosure_nodes = it.findall('./enclosure')
2022 for e in enclosure_nodes:
2023 next_url = e.attrib.get('url')
2031 '_type': 'url_transparent',
2033 'title': it.find('title').text,
2037 '_type': 'playlist',
2039 'title': playlist_title,
2040 'description': playlist_desc,
2044 def _extract_camtasia(self, url, video_id, webpage):
2045 """ Returns None if no camtasia video can be found. """
2047 camtasia_cfg = self._search_regex(
2048 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2049 webpage, 'camtasia configuration file', default=None)
2050 if camtasia_cfg is None:
2053 title = self._html_search_meta('DC.title', webpage, fatal=True)
2055 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2056 camtasia_cfg = self._download_xml(
2057 camtasia_url, video_id,
2058 note='Downloading camtasia configuration',
2059 errnote='Failed to download camtasia configuration')
2060 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2063 for n in fileset_node.getchildren():
2064 url_n = n.find('./uri')
2069 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2070 'title': '%s - %s' % (title, n.tag),
2071 'url': compat_urlparse.urljoin(url, url_n.text),
2072 'duration': float_or_none(n.find('./duration').text),
2076 '_type': 'playlist',
2081 def _real_extract(self, url):
2082 if url.startswith('//'):
2085 'url': self.http_scheme() + url,
2088 parsed_url = compat_urlparse.urlparse(url)
2089 if not parsed_url.scheme:
2090 default_search = self._downloader.params.get('default_search')
2091 if default_search is None:
2092 default_search = 'fixup_error'
2094 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2096 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2097 return self.url_result('http://' + url)
2098 elif default_search != 'fixup_error':
2099 if default_search == 'auto_warning':
2100 if re.match(r'^(?:url|URL)$', url):
2101 raise ExtractorError(
2102 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2105 self._downloader.report_warning(
2106 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2107 return self.url_result('ytsearch:' + url)
2109 if default_search in ('error', 'fixup_error'):
2110 raise ExtractorError(
2111 '%r is not a valid URL. '
2112 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2113 % (url, url), expected=True)
2115 if ':' not in default_search:
2116 default_search += ':'
2117 return self.url_result(default_search + url)
2119 url, smuggled_data = unsmuggle_url(url)
2120 force_videoid = None
2121 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2122 if smuggled_data and 'force_videoid' in smuggled_data:
2123 force_videoid = smuggled_data['force_videoid']
2124 video_id = force_videoid
2126 video_id = self._generic_id(url)
2128 self.to_screen('%s: Requesting header' % video_id)
2130 head_req = HEADRequest(url)
2131 head_response = self._request_webpage(
2133 note=False, errnote='Could not send HEAD request to %s' % url,
2136 if head_response is not False:
2137 # Check for redirect
2138 new_url = compat_str(head_response.geturl())
2140 self.report_following_redirect(new_url)
2142 new_url = smuggle_url(
2143 new_url, {'force_videoid': force_videoid})
2144 return self.url_result(new_url)
2146 full_response = None
2147 if head_response is False:
2148 request = sanitized_Request(url)
2149 request.add_header('Accept-Encoding', '*')
2150 full_response = self._request_webpage(request, video_id)
2151 head_response = full_response
2155 'title': self._generic_title(url),
2156 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2159 # Check for direct link to a video
2160 content_type = head_response.headers.get('Content-Type', '').lower()
2161 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2163 format_id = compat_str(m.group('format_id'))
2164 if format_id.endswith('mpegurl'):
2165 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2166 elif format_id == 'f4m':
2167 formats = self._extract_f4m_formats(url, video_id)
2170 'format_id': format_id,
2172 'vcodec': 'none' if m.group('type') == 'audio' else None
2174 info_dict['direct'] = True
2175 self._sort_formats(formats)
2176 info_dict['formats'] = formats
2179 if not self._downloader.params.get('test', False) and not is_intentional:
2180 force = self._downloader.params.get('force_generic_extractor', False)
2181 self._downloader.report_warning(
2182 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2184 if not full_response:
2185 request = sanitized_Request(url)
2186 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2187 # making it impossible to download only chunk of the file (yet we need only 512kB to
2188 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2189 # that will always result in downloading the whole file that is not desirable.
2190 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2191 # to accept raw bytes and being able to download only a chunk.
2192 # It may probably better to solve this by checking Content-Type for application/octet-stream
2193 # after HEAD request finishes, but not sure if we can rely on this.
2194 request.add_header('Accept-Encoding', '*')
2195 full_response = self._request_webpage(request, video_id)
2197 first_bytes = full_response.read(512)
2199 # Is it an M3U playlist?
2200 if first_bytes.startswith(b'#EXTM3U'):
2201 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2202 self._sort_formats(info_dict['formats'])
2205 # Maybe it's a direct link to a video?
2206 # Be careful not to download the whole thing!
2207 if not is_html(first_bytes):
2208 self._downloader.report_warning(
2209 'URL could be a direct video link, returning it as such.')
2216 webpage = self._webpage_read_content(
2217 full_response, url, video_id, prefix=first_bytes)
2219 self.report_extraction(video_id)
2221 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2223 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2224 if doc.tag == 'rss':
2225 return self._extract_rss(url, video_id, doc)
2226 elif doc.tag == 'SmoothStreamingMedia':
2227 info_dict['formats'] = self._parse_ism_formats(doc, url)
2228 self._sort_formats(info_dict['formats'])
2230 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2231 smil = self._parse_smil(doc, url, video_id)
2232 self._sort_formats(smil['formats'])
2234 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2235 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2236 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2237 info_dict['formats'] = self._parse_mpd_formats(
2239 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2241 self._sort_formats(info_dict['formats'])
2243 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2244 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2245 self._sort_formats(info_dict['formats'])
2247 except compat_xml_parse_error:
2250 # Is it a Camtasia project?
2251 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2252 if camtasia_res is not None:
2255 # Sometimes embedded video player is hidden behind percent encoding
2256 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2257 # Unescaping the whole page allows to handle those cases in a generic way
2258 webpage = compat_urllib_parse_unquote(webpage)
2260 # it's tempting to parse this further, but you would
2261 # have to take into account all the variations like
2262 # Video Title - Site Name
2263 # Site Name | Video Title
2264 # Video Title - Tagline | Site Name
2265 # and so on and so forth; it's just not practical
2266 video_title = self._og_search_title(
2267 webpage, default=None) or self._html_search_regex(
2268 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2271 # Try to detect age limit automatically
2272 age_limit = self._rta_search(webpage)
2273 # And then there are the jokers who advertise that they use RTA,
2274 # but actually don't.
2275 AGE_LIMIT_MARKERS = [
2276 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2278 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2281 # video uploader is domain name
2282 video_uploader = self._search_regex(
2283 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2285 video_description = self._og_search_description(webpage, default=None)
2286 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2289 'title': video_title,
2290 'description': video_description,
2291 'thumbnail': video_thumbnail,
2292 'age_limit': age_limit,
2295 # Look for Brightcove Legacy Studio embeds
2296 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2300 'url': smuggle_url(bc_url, {'Referer': url}),
2301 'ie_key': 'BrightcoveLegacy'
2302 } for bc_url in bc_urls]
2305 '_type': 'playlist',
2306 'title': video_title,
2311 # Look for Brightcove New Studio embeds
2312 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2314 return self.playlist_from_matches(
2315 bc_urls, video_id, video_title,
2316 getter=lambda x: smuggle_url(x, {'referrer': url}),
2319 # Look for Nexx embeds
2320 nexx_urls = NexxIE._extract_urls(webpage)
2322 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2324 # Look for Nexx iFrame embeds
2325 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2327 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2329 # Look for ThePlatform embeds
2330 tp_urls = ThePlatformIE._extract_urls(webpage)
2332 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2334 # Look for Vessel embeds
2335 vessel_urls = VesselIE._extract_urls(webpage)
2337 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2339 # Look for embedded rtl.nl player
2340 matches = re.findall(
2341 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2344 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2346 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2348 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2350 vid_me_embed_url = self._search_regex(
2351 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2352 webpage, 'vid.me embed', default=None)
2353 if vid_me_embed_url is not None:
2354 return self.url_result(vid_me_embed_url, 'Vidme')
2356 # Look for YouTube embeds
2357 youtube_urls = YoutubeIE._extract_urls(webpage)
2359 return self.playlist_from_matches(
2360 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2362 matches = DailymotionIE._extract_urls(webpage)
2364 return self.playlist_from_matches(matches, video_id, video_title)
2366 # Look for embedded Dailymotion playlist player (#3822)
2368 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2370 playlists = re.findall(
2371 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2373 return self.playlist_from_matches(
2374 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2376 # Look for DailyMail embeds
2377 dailymail_urls = DailyMailIE._extract_urls(webpage)
2379 return self.playlist_from_matches(
2380 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2382 # Look for embedded Wistia player
2383 wistia_url = WistiaIE._extract_url(webpage)
2386 '_type': 'url_transparent',
2387 'url': self._proto_relative_url(wistia_url),
2388 'ie_key': WistiaIE.ie_key(),
2389 'uploader': video_uploader,
2392 # Look for SVT player
2393 svt_url = SVTIE._extract_url(webpage)
2395 return self.url_result(svt_url, 'SVT')
2397 # Look for Bandcamp pages with custom domain
2398 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2399 if mobj is not None:
2400 burl = unescapeHTML(mobj.group(1))
2401 # Don't set the extractor because it can be a track url or an album
2402 return self.url_result(burl)
2404 # Look for embedded Vevo player
2406 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2407 if mobj is not None:
2408 return self.url_result(mobj.group('url'))
2410 # Look for embedded Viddler player
2412 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2414 if mobj is not None:
2415 return self.url_result(mobj.group('url'))
2417 # Look for NYTimes player
2419 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2421 if mobj is not None:
2422 return self.url_result(mobj.group('url'))
2424 # Look for Libsyn player
2426 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2427 if mobj is not None:
2428 return self.url_result(mobj.group('url'))
2430 # Look for Ooyala videos
2431 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2432 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2433 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2434 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2435 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2436 if mobj is not None:
2437 embed_token = self._search_regex(
2438 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2439 webpage, 'ooyala embed token', default=None)
2440 return OoyalaIE._build_url_result(smuggle_url(
2443 'embed_token': embed_token,
2446 # Look for multiple Ooyala embeds on SBN network websites
2447 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2448 if mobj is not None:
2449 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2451 return self.playlist_from_matches(
2452 embeds, video_id, video_title,
2453 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2455 # Look for Aparat videos
2456 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2457 if mobj is not None:
2458 return self.url_result(mobj.group(1), 'Aparat')
2460 # Look for MPORA videos
2461 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2462 if mobj is not None:
2463 return self.url_result(mobj.group(1), 'Mpora')
2465 # Look for embedded NovaMov-based player
2467 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2468 (?P<url>http://(?:(?:embed|www)\.)?
2470 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2471 videoweed\.(?:es|com)|
2472 movshare\.(?:net|sx|ag)|
2473 divxstage\.(?:eu|net|ch|co|at|ag))
2474 /embed\.php.+?)\1''', webpage)
2475 if mobj is not None:
2476 return self.url_result(mobj.group('url'))
2478 # Look for embedded Facebook player
2479 facebook_urls = FacebookIE._extract_urls(webpage)
2481 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2483 # Look for embedded VK player
2484 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2485 if mobj is not None:
2486 return self.url_result(mobj.group('url'), 'VK')
2488 # Look for embedded Odnoklassniki player
2489 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2490 if mobj is not None:
2491 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2493 # Look for embedded ivi player
2494 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2495 if mobj is not None:
2496 return self.url_result(mobj.group('url'), 'Ivi')
2498 # Look for embedded Huffington Post player
2500 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2501 if mobj is not None:
2502 return self.url_result(mobj.group('url'), 'HuffPost')
2505 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2506 if mobj is not None:
2507 return self.url_result(mobj.group('url'))
2508 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2509 if mobj is not None:
2510 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2512 # Look for funnyordie embed
2513 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2515 return self.playlist_from_matches(
2516 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2518 # Look for BBC iPlayer embed
2519 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2521 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2523 # Look for embedded RUTV player
2524 rutv_url = RUTVIE._extract_url(webpage)
2526 return self.url_result(rutv_url, 'RUTV')
2528 # Look for embedded TVC player
2529 tvc_url = TVCIE._extract_url(webpage)
2531 return self.url_result(tvc_url, 'TVC')
2533 # Look for embedded SportBox player
2534 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2536 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2538 # Look for embedded XHamster player
2539 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2541 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2543 # Look for embedded TNAFlixNetwork player
2544 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2546 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2548 # Look for embedded PornHub player
2549 pornhub_urls = PornHubIE._extract_urls(webpage)
2551 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2553 # Look for embedded DrTuber player
2554 drtuber_urls = DrTuberIE._extract_urls(webpage)
2556 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2558 # Look for embedded RedTube player
2559 redtube_urls = RedTubeIE._extract_urls(webpage)
2561 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2563 # Look for embedded Tvigle player
2565 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2566 if mobj is not None:
2567 return self.url_result(mobj.group('url'), 'Tvigle')
2569 # Look for embedded TED player
2571 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2572 if mobj is not None:
2573 return self.url_result(mobj.group('url'), 'TED')
2575 # Look for embedded Ustream videos
2576 ustream_url = UstreamIE._extract_url(webpage)
2578 return self.url_result(ustream_url, UstreamIE.ie_key())
2580 # Look for embedded arte.tv player
2582 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2584 if mobj is not None:
2585 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2587 # Look for embedded francetv player
2589 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2591 if mobj is not None:
2592 return self.url_result(mobj.group('url'))
2594 # Look for embedded smotri.com player
2595 smotri_url = SmotriIE._extract_url(webpage)
2597 return self.url_result(smotri_url, 'Smotri')
2599 # Look for embedded Myvi.ru player
2600 myvi_url = MyviIE._extract_url(webpage)
2602 return self.url_result(myvi_url)
2604 # Look for embedded soundcloud player
2605 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2607 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2609 # Look for tunein player
2610 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2612 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2614 # Look for embedded mtvservices player
2615 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2617 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2619 # Look for embedded yahoo player
2621 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2623 if mobj is not None:
2624 return self.url_result(mobj.group('url'), 'Yahoo')
2626 # Look for embedded sbs.com.au player
2630 <meta\s+property="og:video"\s+content=|
2633 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2635 if mobj is not None:
2636 return self.url_result(mobj.group('url'), 'SBS')
2638 # Look for embedded Cinchcast player
2640 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2642 if mobj is not None:
2643 return self.url_result(mobj.group('url'), 'Cinchcast')
2646 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2650 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2652 if mobj is not None:
2653 return self.url_result(mobj.group('url'), 'MLB')
2656 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2658 if mobj is not None:
2659 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2662 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2664 if mobj is not None:
2665 return self.url_result(mobj.group('url'), 'Livestream')
2667 # Look for Zapiks embed
2669 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2670 if mobj is not None:
2671 return self.url_result(mobj.group('url'), 'Zapiks')
2673 # Look for Kaltura embeds
2674 kaltura_url = KalturaIE._extract_url(webpage)
2676 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2678 # Look for EaglePlatform embeds
2679 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2680 if eagleplatform_url:
2681 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2683 # Look for ClipYou (uses EaglePlatform) embeds
2685 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2686 if mobj is not None:
2687 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2689 # Look for Pladform embeds
2690 pladform_url = PladformIE._extract_url(webpage)
2692 return self.url_result(pladform_url)
2694 # Look for Videomore embeds
2695 videomore_url = VideomoreIE._extract_url(webpage)
2697 return self.url_result(videomore_url)
2699 # Look for Webcaster embeds
2700 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2702 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2704 # Look for Playwire embeds
2706 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2707 if mobj is not None:
2708 return self.url_result(mobj.group('url'))
2710 # Look for 5min embeds
2712 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2713 if mobj is not None:
2714 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2716 # Look for Crooks and Liars embeds
2718 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2719 if mobj is not None:
2720 return self.url_result(mobj.group('url'))
2722 # Look for NBC Sports VPlayer embeds
2723 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2725 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2727 # Look for NBC News embeds
2728 nbc_news_embed_url = re.search(
2729 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2730 if nbc_news_embed_url:
2731 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2733 # Look for Google Drive embeds
2734 google_drive_url = GoogleDriveIE._extract_url(webpage)
2735 if google_drive_url:
2736 return self.url_result(google_drive_url, 'GoogleDrive')
2738 # Look for UDN embeds
2740 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2741 if mobj is not None:
2742 return self.url_result(
2743 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2745 # Look for Senate ISVP iframe
2746 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2748 return self.url_result(senate_isvp_url, 'SenateISVP')
2750 # Look for OnionStudios embeds
2751 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2752 if onionstudios_url:
2753 return self.url_result(onionstudios_url)
2755 # Look for ViewLift embeds
2756 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2758 return self.url_result(viewlift_url)
2760 # Look for JWPlatform embeds
2761 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2763 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2765 # Look for Digiteka embeds
2766 digiteka_url = DigitekaIE._extract_url(webpage)
2768 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2770 # Look for Arkena embeds
2771 arkena_url = ArkenaIE._extract_url(webpage)
2773 return self.url_result(arkena_url, ArkenaIE.ie_key())
2775 # Look for Piksel embeds
2776 piksel_url = PikselIE._extract_url(webpage)
2778 return self.url_result(piksel_url, PikselIE.ie_key())
2780 # Look for Limelight embeds
2781 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2783 return self.playlist_result(
2784 limelight_urls, video_id, video_title, video_description)
2786 # Look for Anvato embeds
2787 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2789 return self.playlist_result(
2790 anvato_urls, video_id, video_title, video_description)
2792 # Look for AdobeTVVideo embeds
2794 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2796 if mobj is not None:
2797 return self.url_result(
2798 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2801 # Look for Vine embeds
2803 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2805 if mobj is not None:
2806 return self.url_result(
2807 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2809 # Look for VODPlatform embeds
2811 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2813 if mobj is not None:
2814 return self.url_result(
2815 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2817 # Look for Mangomolo embeds
2819 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2821 video\?.*?\bid=(?P<video_id>\d+)|
2822 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2823 ).+?)\1''', webpage)
2824 if mobj is not None:
2826 '_type': 'url_transparent',
2827 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2828 'title': video_title,
2829 'description': video_description,
2830 'thumbnail': video_thumbnail,
2831 'uploader': video_uploader,
2833 video_id = mobj.group('video_id')
2836 'ie_key': 'MangomoloVideo',
2841 'ie_key': 'MangomoloLive',
2842 'id': mobj.group('channel_id'),
2846 # Look for Instagram embeds
2847 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2848 if instagram_embed_url is not None:
2849 return self.url_result(
2850 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2852 # Look for LiveLeak embeds
2853 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2855 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2857 # Look for 3Q SDN embeds
2858 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2861 '_type': 'url_transparent',
2862 'ie_key': ThreeQSDNIE.ie_key(),
2863 'url': self._proto_relative_url(threeqsdn_url),
2864 'title': video_title,
2865 'description': video_description,
2866 'thumbnail': video_thumbnail,
2867 'uploader': video_uploader,
2870 # Look for VBOX7 embeds
2871 vbox7_url = Vbox7IE._extract_url(webpage)
2873 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2875 # Look for DBTV embeds
2876 dbtv_urls = DBTVIE._extract_urls(webpage)
2878 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2880 # Look for Videa embeds
2881 videa_urls = VideaIE._extract_urls(webpage)
2883 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2885 # Look for 20 minuten embeds
2886 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2888 return self.playlist_from_matches(
2889 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2891 # Look for Openload embeds
2892 openload_urls = OpenloadIE._extract_urls(webpage)
2894 return self.playlist_from_matches(
2895 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2897 # Look for VideoPress embeds
2898 videopress_urls = VideoPressIE._extract_urls(webpage)
2900 return self.playlist_from_matches(
2901 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2903 # Look for Rutube embeds
2904 rutube_urls = RutubeIE._extract_urls(webpage)
2906 return self.playlist_from_matches(
2907 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2909 # Look for WashingtonPost embeds
2910 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2912 return self.playlist_from_matches(
2913 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2915 # Look for Mediaset embeds
2916 mediaset_urls = MediasetIE._extract_urls(webpage)
2918 return self.playlist_from_matches(
2919 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2921 # Look for JOJ.sk embeds
2922 joj_urls = JojIE._extract_urls(webpage)
2924 return self.playlist_from_matches(
2925 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2927 # Look for megaphone.fm embeds
2928 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2930 return self.playlist_from_matches(
2931 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2933 # Look for vzaar embeds
2934 vzaar_urls = VzaarIE._extract_urls(webpage)
2936 return self.playlist_from_matches(
2937 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2939 channel9_urls = Channel9IE._extract_urls(webpage)
2941 return self.playlist_from_matches(
2942 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
2944 vshare_urls = VShareIE._extract_urls(webpage)
2946 return self.playlist_from_matches(
2947 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
2949 # Look for Mediasite embeds
2950 mediasite_urls = MediasiteIE._extract_urls(webpage)
2953 self.url_result(smuggle_url(
2954 compat_urlparse.urljoin(url, mediasite_url),
2955 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
2956 for mediasite_url in mediasite_urls]
2957 return self.playlist_result(entries, video_id, video_title)
2959 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
2960 if springboardplatform_urls:
2961 return self.playlist_from_matches(
2962 springboardplatform_urls, video_id, video_title,
2963 ie=SpringboardPlatformIE.ie_key())
2965 yapfiles_urls = YapFilesIE._extract_urls(webpage)
2967 return self.playlist_from_matches(
2968 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
2970 vice_urls = ViceIE._extract_urls(webpage)
2972 return self.playlist_from_matches(
2973 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
2975 xfileshare_urls = XFileShareIE._extract_urls(webpage)
2977 return self.playlist_from_matches(
2978 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
2980 def merge_dicts(dict1, dict2):
2982 for k, v in dict1.items():
2985 for k, v in dict2.items():
2988 if (k not in merged or
2989 (isinstance(v, compat_str) and v and
2990 isinstance(merged[k], compat_str) and
2995 # Look for HTML5 media
2996 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2998 if len(entries) == 1:
3001 'title': video_title,
3004 for num, entry in enumerate(entries, start=1):
3006 'id': '%s-%s' % (video_id, num),
3007 'title': '%s (%d)' % (video_title, num),
3009 for entry in entries:
3010 self._sort_formats(entry['formats'])
3011 return self.playlist_result(entries, video_id, video_title)
3013 jwplayer_data = self._find_jwplayer_data(
3014 webpage, video_id, transform_source=js_to_json)
3016 info = self._parse_jwplayer_data(
3017 jwplayer_data, video_id, require_title=False, base_url=url)
3018 return merge_dicts(info, info_dict)
3022 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3024 if mobj is not None:
3025 sources = self._parse_json(
3026 mobj.group(1), video_id, transform_source=js_to_json,
3028 if not isinstance(sources, list):
3031 for source in sources:
3032 src = source.get('src')
3033 if not src or not isinstance(src, compat_str):
3035 src = compat_urlparse.urljoin(url, src)
3036 src_type = source.get('type')
3037 if isinstance(src_type, compat_str):
3038 src_type = src_type.lower()
3039 ext = determine_ext(src).lower()
3040 if src_type == 'video/youtube':
3041 return self.url_result(src, YoutubeIE.ie_key())
3042 if src_type == 'application/dash+xml' or ext == 'mpd':
3043 formats.extend(self._extract_mpd_formats(
3044 src, video_id, mpd_id='dash', fatal=False))
3045 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3046 formats.extend(self._extract_m3u8_formats(
3047 src, video_id, 'mp4', entry_protocol='m3u8_native',
3048 m3u8_id='hls', fatal=False))
3052 'ext': (mimetype2ext(src_type) or
3053 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3056 self._sort_formats(formats)
3057 info_dict['formats'] = formats
3060 # Looking for http://schema.org/VideoObject
3061 json_ld = self._search_json_ld(
3062 webpage, video_id, default={}, expected_type='VideoObject')
3063 if json_ld.get('url'):
3064 return merge_dicts(json_ld, info_dict)
3066 def check_video(vurl):
3067 if YoutubeIE.suitable(vurl):
3069 if RtmpIE.suitable(vurl):
3071 vpath = compat_urlparse.urlparse(vurl).path
3072 vext = determine_ext(vpath)
3073 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3075 def filter_video(urls):
3076 return list(filter(check_video, urls))
3078 # Start with something easy: JW Player in SWFObject
3079 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3081 # Look for gorilla-vid style embedding
3082 found = filter_video(re.findall(r'''(?sx)
3086 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3089 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3091 # Broaden the search a little bit
3092 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3094 # Broaden the findall a little bit: JWPlayer JS loader
3095 found = filter_video(re.findall(
3096 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3099 found = filter_video(re.findall(r'''(?xs)
3100 flowplayer\("[^"]+",\s*
3102 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3103 ["']?url["']?\s*:\s*["']([^"']+)["']
3108 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3110 # Try to find twitter cards info
3111 # twitter:player:stream should be checked before twitter:player since
3112 # it is expected to contain a raw stream (see
3113 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3114 found = filter_video(re.findall(
3115 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3117 # We look for Open Graph info:
3118 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3119 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3120 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3121 if m_video_type is not None:
3122 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3124 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3126 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3127 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3130 # Look also in Refresh HTTP header
3131 refresh_header = head_response.headers.get('Refresh')
3133 # In python 2 response HTTP headers are bytestrings
3134 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3135 refresh_header = refresh_header.decode('iso-8859-1')
3136 found = re.search(REDIRECT_REGEX, refresh_header)
3138 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3140 self.report_following_redirect(new_url)
3149 # twitter:player is a https URL to iframe player that may or may not
3150 # be supported by youtube-dl thus this is checked the very last (see
3151 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3152 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3153 if embed_url and embed_url != url:
3154 return self.url_result(embed_url)
3157 raise UnsupportedError(url)
3160 for video_url in orderedSet(found):
3161 video_url = unescapeHTML(video_url)
3162 video_url = video_url.replace('\\/', '/')
3163 video_url = compat_urlparse.urljoin(url, video_url)
3164 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3166 # Sometimes, jwplayer extraction will result in a YouTube URL
3167 if YoutubeIE.suitable(video_url):
3168 entries.append(self.url_result(video_url, 'Youtube'))
3171 # here's a fun little line of code for you:
3172 video_id = os.path.splitext(video_id)[0]
3176 'uploader': video_uploader,
3177 'title': video_title,
3178 'age_limit': age_limit,
3181 if RtmpIE.suitable(video_url):
3182 entry_info_dict.update({
3183 '_type': 'url_transparent',
3184 'ie_key': RtmpIE.ie_key(),
3187 entries.append(entry_info_dict)
3190 ext = determine_ext(video_url)
3192 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3194 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3196 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3198 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3200 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3201 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3202 # Just matching .ism/manifest is not enough to be reliably sure
3203 # whether it's actually an ISM manifest or some other streaming
3204 # manifest since there are various streaming URL formats
3205 # possible (see [1]) as well as some other shenanigans like
3206 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3208 # Thus the most reasonable way to solve this is to delegate
3209 # to generic extractor in order to look into the contents of
3210 # the manifest itself.
3211 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3212 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3213 entry_info_dict = self.url_result(
3214 smuggle_url(video_url, {'to_generic': True}),
3217 entry_info_dict['url'] = video_url
3219 if entry_info_dict.get('formats'):
3220 self._sort_formats(entry_info_dict['formats'])
3222 entries.append(entry_info_dict)
3224 if len(entries) == 1:
3227 for num, e in enumerate(entries, start=1):
3228 # 'url' results don't have a title
3229 if e.get('title') is not None:
3230 e['title'] = '%s (%d)' % (e['title'], num)
3232 '_type': 'playlist',