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,
37 from .commonprotocols import RtmpIE
38 from .brightcove import (
46 from .nbc import NBCSportsVPlayerIE
47 from .ooyala import OoyalaIE
48 from .rutv import RUTVIE
49 from .tvc import TVCIE
50 from .sportbox import SportBoxIE
51 from .smotri import SmotriIE
52 from .myvi import MyviIE
53 from .condenast import CondeNastIE
54 from .udn import UDNEmbedIE
55 from .senateisvp import SenateISVPIE
56 from .svt import SVTIE
57 from .pornhub import PornHubIE
58 from .xhamster import XHamsterEmbedIE
59 from .tnaflix import TNAFlixNetworkEmbedIE
60 from .drtuber import DrTuberIE
61 from .redtube import RedTubeIE
62 from .tube8 import Tube8IE
63 from .vimeo import VimeoIE
64 from .dailymotion import DailymotionIE
65 from .dailymail import DailyMailIE
66 from .onionstudios import OnionStudiosIE
67 from .viewlift import ViewLiftEmbedIE
68 from .mtv import MTVServicesEmbeddedIE
69 from .pladform import PladformIE
70 from .videomore import VideomoreIE
71 from .webcaster import WebcasterFeedIE
72 from .googledrive import GoogleDriveIE
73 from .jwplatform import JWPlatformIE
74 from .digiteka import DigitekaIE
75 from .arkena import ArkenaIE
76 from .instagram import InstagramIE
77 from .liveleak import LiveLeakIE
78 from .threeqsdn import ThreeQSDNIE
79 from .theplatform import ThePlatformIE
80 from .vessel import VesselIE
81 from .kaltura import KalturaIE
82 from .eagleplatform import EaglePlatformIE
83 from .facebook import FacebookIE
84 from .soundcloud import SoundcloudIE
85 from .tunein import TuneInBaseIE
86 from .vbox7 import Vbox7IE
87 from .dbtv import DBTVIE
88 from .piksel import PikselIE
89 from .videa import VideaIE
90 from .twentymin import TwentyMinutenIE
91 from .ustream import UstreamIE
92 from .openload import OpenloadIE
93 from .videopress import VideoPressIE
94 from .rutube import RutubeIE
95 from .limelight import LimelightBaseIE
96 from .anvato import AnvatoIE
97 from .washingtonpost import WashingtonPostIE
98 from .wistia import WistiaIE
99 from .mediaset import MediasetIE
100 from .joj import JojIE
101 from .megaphone import MegaphoneIE
102 from .vzaar import VzaarIE
103 from .channel9 import Channel9IE
104 from .vshare import VShareIE
105 from .mediasite import MediasiteIE
106 from .springboardplatform import SpringboardPlatformIE
107 from .yapfiles import YapFilesIE
108 from .vice import ViceIE
109 from .xfileshare import XFileShareIE
110 from .cloudflarestream import CloudflareStreamIE
111 from .peertube import PeerTubeIE
112 from .indavideo import IndavideoEmbedIE
113 from .apa import APAIE
114 from .foxnews import FoxNewsIE
115 from .viqeo import ViqeoIE
116 from .expressen import ExpressenIE
117 from .zype import ZypeIE
120 class GenericIE(InfoExtractor):
121 IE_DESC = 'Generic downloader that works on some sites'
125 # Direct link to a video
127 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
128 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
133 'upload_date': '20100513',
136 # Direct link to media delivered compressed (until Accept-Encoding is *)
138 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
139 'md5': '128c42e68b13950268b648275386fc74',
141 'id': 'FictionJunction-Parallel_Hearts',
143 'title': 'FictionJunction-Parallel_Hearts',
144 'upload_date': '20140522',
146 'expected_warnings': [
147 'URL could be a direct video link, returning it as such.'
149 'skip': 'URL invalid',
151 # Direct download with broken HEAD
153 'url': 'http://ai-radio.org:8000/radio.opus',
160 'skip_download': True, # infinite live stream
162 'expected_warnings': [
163 r'501.*Not Implemented',
167 # Direct link with incorrect MIME type
169 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
170 'md5': '4ccbebe5f36706d85221f204d7eb5913',
172 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
173 'id': '5_Lennart_Poettering_-_Systemd',
175 'title': '5_Lennart_Poettering_-_Systemd',
176 'upload_date': '20141120',
178 'expected_warnings': [
179 'URL could be a direct video link, returning it as such.'
184 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
186 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
187 'title': 'Zero Punctuation',
188 'description': 're:.*groundbreaking video review series.*'
190 'playlist_mincount': 11,
192 # RSS feed with enclosure
194 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
196 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
198 'upload_date': '20150228',
199 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
202 # RSS feed with enclosures and unsupported link URLs
204 'url': 'http://www.hellointernet.fm/podcast?format=rss',
206 'id': 'http://www.hellointernet.fm/podcast?format=rss',
207 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
208 'title': 'Hello Internet',
210 'playlist_mincount': 100,
212 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
214 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
218 'title': 'Automatics, robotics and biocybernetics',
219 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
220 'upload_date': '20130627',
221 'formats': 'mincount:16',
222 'subtitles': 'mincount:1',
225 'force_generic_extractor': True,
226 'skip_download': True,
229 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
231 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
236 'formats': 'mincount:1',
239 'skip_download': True,
242 # SMIL from https://www.restudy.dk/video/play/id/1637
244 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
248 'title': 'video_1637',
249 'formats': 'mincount:3',
252 'skip_download': True,
255 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
257 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
259 'id': 'smil-service',
261 'title': 'smil-service',
262 'formats': 'mincount:1',
265 'skip_download': True,
268 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
270 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
274 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
275 'formats': 'mincount:3',
278 'skip_download': True,
281 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
283 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
285 'id': 'mZlp2ctYIUEB',
287 'title': 'Tikibad ontruimd wegens brand',
288 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
289 'thumbnail': r're:^https?://.*\.jpg$',
293 'skip_download': True,
296 # MPD from http://dash-mse-test.appspot.com/media.html
298 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
299 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
301 'id': 'car-20120827-manifest',
303 'title': 'car-20120827-manifest',
304 'formats': 'mincount:9',
305 'upload_date': '20130904',
308 'format': 'bestvideo',
311 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
313 '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',
318 'formats': 'mincount:8',
322 'skip_download': True,
324 'skip': 'video gone',
326 # m3u8 served with Content-Type: text/plain
328 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
333 'upload_date': '20140720',
334 'formats': 'mincount:11',
338 'skip_download': True,
340 'skip': 'video gone',
344 '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',
348 'upload_date': '20130224',
349 'uploader_id': 'TheVerge',
350 'description': r're:^Chris Ziegler takes a look at the\.*',
351 'uploader': 'The Verge',
352 'title': 'First Firefox OS phones side-by-side',
355 'skip_download': False,
359 # redirect in Refresh HTTP header
360 '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',
364 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
365 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
366 'upload_date': '20150917',
367 'uploader_id': 'brtvofficial',
368 'uploader': 'Boiler Room',
371 'skip_download': False,
375 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
376 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
378 'id': '13601338388002',
380 'uploader': 'www.hodiho.fr',
381 'title': 'R\u00e9gis plante sa Jeep',
384 # bandcamp page with custom domain
386 'add_ie': ['Bandcamp'],
387 'url': 'http://bronyrock.com/track/the-pony-mash',
391 'title': 'The Pony Mash',
392 'uploader': 'M_Pallante',
394 'skip': 'There is a limit of 200 free downloads / month for the test song',
397 # embedded brightcove video
398 # it also tests brightcove videos that need to set the 'Referer'
399 # in the http requests
400 'add_ie': ['BrightcoveLegacy'],
401 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
403 'id': '2765128793001',
405 'title': 'Le cours de bourse : l’analyse technique',
406 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
407 'uploader': 'BFM BUSINESS',
410 'skip_download': True,
414 # embedded with itemprop embedURL and video id spelled as `idVideo`
415 'add_id': ['BrightcoveLegacy'],
416 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
418 'id': '5255628253001',
420 'title': 'md5:37c519b1128915607601e75a87995fc0',
421 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
422 'uploader': 'BFM BUSINESS',
423 'uploader_id': '876450612001',
424 'timestamp': 1482255315,
425 'upload_date': '20161220',
428 'skip_download': True,
432 # https://github.com/rg3/youtube-dl/issues/2253
433 'url': 'http://bcove.me/i6nfkrc3',
434 'md5': '0ba9446db037002366bab3b3eb30c88c',
436 'id': '3101154703001',
438 'title': 'Still no power',
439 'uploader': 'thestar.com',
440 '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.',
442 'add_ie': ['BrightcoveLegacy'],
443 'skip': 'video gone',
446 'url': 'http://www.championat.com/video/football/v/87/87499.html',
447 'md5': 'fb973ecf6e4a78a67453647444222983',
449 'id': '3414141473001',
451 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
452 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
453 'uploader': 'Championat',
457 # https://github.com/rg3/youtube-dl/issues/3541
458 'add_ie': ['BrightcoveLegacy'],
459 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
461 'id': '3866516442001',
463 'title': 'Leer mij vrouwen kennen: Aflevering 1',
464 'description': 'Leer mij vrouwen kennen: Aflevering 1',
465 'uploader': 'SBS Broadcasting',
467 'skip': 'Restricted to Netherlands',
469 'skip_download': True, # m3u8 download
473 # Brightcove video in <iframe>
474 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
475 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
477 'id': '5360463607001',
479 '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',
480 '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。',
481 'uploader': 'United Nations',
482 'uploader_id': '1362235914001',
483 'timestamp': 1489593889,
484 'upload_date': '20170315',
486 'add_ie': ['BrightcoveLegacy'],
489 # Brightcove with alternative playerID key
490 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
492 'id': 'nmeth.2062_SV1',
493 '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',
497 'id': '2228375078001',
499 'title': 'nmeth.2062-sv1',
500 'description': 'nmeth.2062-sv1',
501 'timestamp': 1363357591,
502 'upload_date': '20130315',
503 'uploader': 'Nature Publishing Group',
504 'uploader_id': '1964492299001',
509 # Brightcove with UUID in videoPlayer
510 'url': 'http://www8.hp.com/cn/zh/home.html',
512 'id': '5255815316001',
514 'title': 'Sprocket Video - China',
515 'description': 'Sprocket Video - China',
516 'uploader': 'HP-Video Gallery',
517 'timestamp': 1482263210,
518 'upload_date': '20161220',
519 'uploader_id': '1107601872001',
522 'skip_download': True, # m3u8 download
524 'skip': 'video rotates...weekly?',
527 # Brightcove:new type [2].
528 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
529 'md5': '2b35148fcf48da41c9fb4591650784f3',
531 'id': '5348741021001',
533 'upload_date': '20170306',
534 'uploader_id': '4191638492001',
535 'timestamp': 1488769918,
536 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
541 # Alternative brightcove <video> attributes
542 '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/',
544 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
545 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
548 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
550 'id': '5311302538001',
552 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
553 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
554 'timestamp': 1486321708,
555 'upload_date': '20170205',
556 'uploader_id': '800000640001',
558 'only_matching': True,
562 # Brightcove with UUID in videoPlayer
563 'url': 'http://www8.hp.com/cn/zh/home.html',
565 'id': '5255815316001',
567 'title': 'Sprocket Video - China',
568 'description': 'Sprocket Video - China',
569 'uploader': 'HP-Video Gallery',
570 'timestamp': 1482263210,
571 'upload_date': '20161220',
572 'uploader_id': '1107601872001',
575 'skip_download': True, # m3u8 download
580 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
581 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
583 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
585 'title': '2cc213299525360.mov', # that's what we get
588 'add_ie': ['Ooyala'],
591 # ooyala video embedded with http://player.ooyala.com/iframe.js
592 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
594 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
596 'title': '"Steve Jobs: Man in the Machine" trailer',
597 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
601 'skip_download': True,
603 'skip': 'movie expired',
605 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
607 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
609 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
611 'title': 'Steampunk Fest Comes to Honesdale',
615 'skip_download': True,
620 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
624 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
625 'upload_date': '20140225',
626 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
627 'uploader': 'Tested',
628 'uploader_id': 'testedcom',
630 # No need to test YoutubeIE here
632 'skip_download': True,
637 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
641 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
642 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
644 # HEAD requests lead to endless 301, while GET is OK
645 'expected_warnings': ['301'],
649 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
653 'title': 'Охотское море стало целиком российским',
654 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
658 'skip_download': True,
663 '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/',
667 'title': 'Дошкольное воспитание',
672 'url': 'http://www.vestifinance.ru/articles/25753',
675 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
680 'title': 'Госзаказ. День 3',
686 'title': 'Госзаказ. День 2',
692 'title': 'Госзаказ. День 1',
698 'skip_download': True,
703 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
705 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
707 'title': 'Ужастики, русский трейлер (2015)',
708 'thumbnail': r're:^https?://.*\.jpg$',
714 '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',
717 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
719 'playlist_mincount': 7,
720 # This forum does not allow <iframe> syntaxes anymore
721 # Now HTML tags are displayed as-is
722 'skip': 'No videos on this page',
726 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
727 'md5': '65fdff94098e4a607385a60c5177c638',
731 'title': 'Hidden miracles of the natural world',
732 'uploader': 'Louie Schwartzberg',
733 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
736 # nowvideo embed hidden behind percent encoding
738 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
739 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
741 'id': '06e53103ca9aa',
743 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
744 'description': 'No description',
749 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
750 'md5': '7653032cbb25bf6c80d80f217055fa43',
752 'id': '048195-004_PLUS7-F',
755 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
756 'upload_date': '20140320',
759 'skip_download': 'Requires rtmpdump'
761 'skip': 'video gone',
765 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
769 'title': 'Alcaline, le concert avec Calogero',
770 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
771 'upload_date': '20150226',
772 'timestamp': 1424989860,
777 'skip_download': True,
779 'expected_warnings': [
785 'url': 'http://www.wired.com/2014/04/honda-asimo/',
786 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
788 'id': '53501be369702d3275860000',
790 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
795 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
796 'md5': '441aeeb82eb72c422c7f14ec533999cd',
798 'id': 'k2mm4bCdJ6CQ2i7c8o2',
800 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
801 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
803 'uploader_id': 'xgditw',
804 'upload_date': '20140425',
805 'timestamp': 1398441542,
807 'add_ie': ['Dailymotion'],
811 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
815 'title': 'Care worker punches elderly dementia patient in head 11 times',
816 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
818 'add_ie': ['DailyMail'],
820 'skip_download': True,
825 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
829 'title': 'The NBL Auction 2014',
830 'uploader': 'BADMINTON England',
831 'uploader_id': 'BADMINTONEvents',
832 'upload_date': '20140603',
833 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
835 'add_ie': ['Youtube'],
837 'skip_download': True,
842 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
843 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
845 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
847 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
848 'description': 'Two valets share their love for movie star Liam Neesons.',
849 'timestamp': 1349922600,
850 'upload_date': '20121011',
853 # YouTube embed via <data-embed-url="">
855 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
859 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
860 'uploader': 'Gameloft',
861 'uploader_id': 'gameloft',
862 'upload_date': '20140828',
863 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
866 'skip_download': True,
869 # YouTube <object> embed
871 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
872 'md5': '516718101ec834f74318df76259fb3cc',
876 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
877 'upload_date': '20080526',
878 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
879 'uploader': 'Christopher Sykes',
880 'uploader_id': 'ChristopherJSykes',
882 'add_ie': ['Youtube'],
886 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
888 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
890 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
891 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
896 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
898 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
899 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
905 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
910 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
911 'md5': '9d65602bf31c6e20014319c7d07fba27',
913 'id': '5123ea6d5e5a7',
916 'uploader': 'www.handjobhub.com',
917 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
920 # Multiple brightcove videos
921 # https://github.com/rg3/youtube-dl/issues/2283
923 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
925 'id': 'always-never',
926 'title': 'Always / Never - The New Yorker',
930 'extract_flat': False,
931 'skip_download': True,
936 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
937 'md5': '96f09a37e44da40dd083e12d9a683327',
941 'title': 'Ump changes call to ball',
942 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
944 'timestamp': 1401537900,
945 'upload_date': '20140531',
946 'thumbnail': r're:^https?://.*\.jpg$',
951 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
952 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
956 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
957 'description': 'a Paywall Videos video from Remilon',
959 'uploader': 'study.com',
960 'timestamp': 1459678540,
961 'upload_date': '20160403',
962 'filesize': 24687186,
966 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
967 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
971 'title': 'Conversation about Hexagonal Rails Part 1',
972 'description': 'a Martin Fowler video from ThoughtWorks',
974 'uploader': 'thoughtworks.wistia.com',
975 'timestamp': 1401832161,
976 'upload_date': '20140603',
979 # Wistia standard embed (async)
981 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
985 'title': 'Drip Brennan Dunn Workshop',
986 'description': 'a JV Webinars video from getdrip-1',
988 'timestamp': 1463607249,
989 'upload_date': '20160518',
992 'skip_download': True,
997 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1001 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1002 'uploader': 'Sophos Security',
1003 'title': 'Chet Chat 171 - Oct 29, 2014',
1004 'upload_date': '20141029',
1007 # Soundcloud multiple embeds
1009 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1012 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1014 'playlist_mincount': 7,
1016 # TuneIn station embed
1018 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1023 'location': 'Paris, France',
1028 'skip_download': True,
1033 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1037 'upload_date': '20141112',
1038 'title': 'Rosetta #CometLanding webcast HL 10',
1041 # Another Livestream embed, without 'new.' in URL
1043 'url': 'https://www.freespeech.org/',
1047 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1051 'skip_download': True,
1056 'url': 'https://skiplagged.com/',
1059 'title': 'Skiplagged: The smart way to find cheap flights',
1061 'playlist_mincount': 1,
1062 'add_ie': ['Youtube'],
1066 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1070 'upload_date': '20141126',
1071 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1076 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1078 'id': '730m_DandD_1901_512k',
1080 'uploader': 'www.abc.net.au',
1081 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1084 # embedded viddler video
1086 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1090 'uploader': 'deadspin',
1091 'title': 'WALL-TO-GORTAT',
1092 'timestamp': 1422285291,
1093 'upload_date': '20150126',
1095 'add_ie': ['Viddler'],
1099 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1103 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1104 'description': 'md5:601cb790edd05908957dae8aaa866465',
1105 'upload_date': '20150220',
1107 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1111 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1113 'id': 'Mrj4DVp2zeA',
1115 'upload_date': '20150212',
1116 'uploader': 'The National Archives UK',
1117 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1118 'uploader_id': 'NationalArchives08',
1119 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1124 'url': 'http://www.suffolk.edu/sjc/live.php',
1128 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1129 'uploader': 'www.suffolk.edu',
1132 'skip_download': True,
1134 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1138 'url': 'http://www.indiedb.com/games/king-machine/videos',
1142 'title': 'king machine trailer 1',
1143 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1144 'thumbnail': r're:^https?://.*\.jpg$',
1148 # JWPlayer config passed as variable
1149 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1153 'title': 'ARIELE | Tube Cup',
1154 'uploader': 'www.txxx.com',
1158 'skip_download': True,
1163 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1164 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1168 'upload_date': '20171122',
1169 'timestamp': 1511366290,
1170 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1172 'add_ie': [JWPlatformIE.ie_key()],
1175 # Video.js embed, multiple formats
1176 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1178 'id': 'yygqldloqIk',
1180 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1181 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1182 'upload_date': '20130314',
1183 'uploader': 'PROстое3D',
1184 'uploader_id': 'PROstoe3D',
1187 'skip_download': True,
1191 # Video.js embed, single format
1192 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1196 'title': 'Step 1 - Good Foundation',
1197 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1200 'skip_download': True,
1205 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1206 'playlist_mincount': 5,
1208 'id': 'aanslagen-kopenhagen',
1209 'title': 'Aanslagen Kopenhagen',
1214 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1218 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1221 # Kaltura embed (different embed code)
1223 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1227 'upload_date': '20150127',
1228 'uploader_id': 'PremierMedia',
1230 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1233 # Kaltura embed with single quotes
1235 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1240 'timestamp': 1355743100,
1241 'upload_date': '20121217',
1242 'uploader_id': 'cplapp@learn360.com',
1244 'add_ie': ['Kaltura'],
1247 # Kaltura embedded via quoted entry_id
1248 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1252 'title': '06_matthew_brender_raj_dutt',
1253 'timestamp': 1466638791,
1254 'upload_date': '20160622',
1256 'add_ie': ['Kaltura'],
1257 'expected_warnings': [
1258 'Could not send HEAD request'
1261 'skip_download': True,
1265 # Kaltura embedded, some fileExt broken (#11480)
1266 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1270 'title': 'Our "Standard Models" of particle physics and cosmology',
1271 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1272 'timestamp': 1321158993,
1273 'upload_date': '20111113',
1274 'uploader_id': 'kps1',
1276 'add_ie': ['Kaltura'],
1279 # Kaltura iframe embed
1280 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1281 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1285 'title': 'I. M. Pei: A Centennial Celebration',
1286 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1287 'upload_date': '20170403',
1288 'uploader_id': 'batchUser',
1289 'timestamp': 1491232186,
1291 'add_ie': ['Kaltura'],
1294 # Kaltura iframe embed, more sophisticated
1295 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1299 'title': 'lecture-05sep2017',
1300 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1301 'upload_date': '20170913',
1302 'uploader_id': 'eps2',
1303 'timestamp': 1505340777,
1306 'skip_download': True,
1308 'add_ie': ['Kaltura'],
1311 # meta twitter:player
1312 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1316 'title': 'Main Twerk (Video)',
1317 'upload_date': '20171208',
1318 'uploader_id': 'sebastian.salinas@thechive.com',
1319 'timestamp': 1512713057,
1322 'skip_download': True,
1324 'add_ie': ['Kaltura'],
1326 # referrer protected EaglePlatform embed
1328 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1332 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1333 'thumbnail': r're:^https?://.*\.jpg$',
1338 'skip_download': True,
1341 # ClipYou (EaglePlatform) embed (custom URL)
1343 'url': 'http://muz-tv.ru/play/7129/',
1344 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1348 'title': "'O Sole Mio",
1349 'thumbnail': r're:^https?://.*\.jpg$',
1354 'skip_download': True,
1356 'skip': 'This video is unavailable.',
1360 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1364 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1365 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1366 'thumbnail': r're:^https?://.*\.jpg$',
1370 'skip': 'HTTP Error 404: Not Found',
1374 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1378 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1379 'thumbnail': r're:^https?://.*\.png$',
1385 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1386 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1390 'title': 'Facebook Creates "On This Day" | Crunch Report',
1391 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1392 'timestamp': 1427237531,
1393 'uploader': 'Crunch Report',
1394 'upload_date': '20150324',
1398 'skip_download': True,
1401 # Crooks and Liars embed
1403 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1407 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1408 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1409 'timestamp': 1428207000,
1410 'upload_date': '20150405',
1411 'uploader': 'Heather',
1414 # Crooks and Liars external embed
1416 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1418 'id': 'MTE3MjUtMzQ2MzA',
1420 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1421 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1422 'timestamp': 1265032391,
1423 'upload_date': '20100201',
1424 'uploader': 'Heather',
1427 # NBC Sports vplayer embed
1429 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1431 'id': 'ln7x1qSThw4k',
1433 'title': "PFT Live: New leader in the 'new-look' defense",
1434 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1435 'uploader': 'NBCU-SPORTS',
1436 'upload_date': '20140107',
1437 'timestamp': 1389118457,
1439 'skip': 'Invalid Page URL',
1443 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1444 'md5': '1aa589c675898ae6d37a17913cf68d66',
1446 'id': 'x_dtl_oa_LettermanliftPR_160608',
1448 'title': 'David Letterman: A Preview',
1449 '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.',
1450 'upload_date': '20160609',
1451 'timestamp': 1465431544,
1452 'uploader': 'NBCU-NEWS',
1457 'url': 'https://video.udn.com/news/300346',
1458 'md5': 'fd2060e988c326991037b9aff9df21a6',
1462 'title': '中一中男師變性 全校師生力挺',
1463 'thumbnail': r're:^https?://.*\.jpg$',
1467 'skip_download': True,
1469 'expected_warnings': ['Failed to parse JSON Expecting value'],
1471 # Brightcove URL in single quotes
1473 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1474 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1476 'id': '4255764656001',
1478 'title': 'SN Presents: Russell Martin, World Citizen',
1479 '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.',
1480 'uploader': 'Rogers Sportsnet',
1481 'uploader_id': '1704050871',
1482 'upload_date': '20150525',
1483 'timestamp': 1432570283,
1486 # OnionStudios embed
1488 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1492 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1493 'thumbnail': r're:^https?://.*\.jpe?g$',
1494 'uploader': 'ClickHole',
1495 'uploader_id': 'clickhole',
1500 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1502 'id': '74849a00-85a9-11e1-9660-123139220831',
1504 'title': '#whilewewatch',
1507 # AdobeTVVideo embed
1509 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1510 'md5': '43662b577c018ad707a63766462b1e87',
1514 'title': 'New experience with Acrobat DC',
1515 'description': 'New experience with Acrobat DC',
1516 'duration': 248.667,
1519 # BrightcoveInPageEmbed embed
1521 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1523 'id': '4238694884001',
1525 'title': 'Tabletop: Dread, Last Thoughts',
1526 'description': 'Tabletop: Dread, Last Thoughts',
1530 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1531 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1533 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1535 'id': '4785848093001',
1537 'title': 'The Cardinal Pell Interview',
1538 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1539 'uploader': 'GlobeCast Australia - GlobeStream',
1540 'uploader_id': '2733773828001',
1541 'upload_date': '20160304',
1542 'timestamp': 1457083087,
1546 'skip_download': True,
1550 # Brightcove embed with whitespace around attribute names
1551 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1553 'id': '3167554373001',
1555 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1556 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1557 'uploader_id': '1079349493',
1558 'upload_date': '20140207',
1559 'timestamp': 1391810548,
1562 'skip_download': True,
1565 # Another form of arte.tv embed
1567 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1568 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1570 'id': '030273-562_PLUS7-F',
1572 'title': 'ARTE Reportage - Nulle part, en France',
1573 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1574 'upload_date': '20160409',
1579 'url': 'http://www.wykop.pl/link/3088787/',
1580 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1582 'id': '874_1459135191',
1584 'title': 'Man shows poor quality of new apartment building',
1585 'description': 'The wall is like a sand pile.',
1586 'uploader': 'Lake8737',
1588 'add_ie': [LiveLeakIE.ie_key()],
1590 # Another LiveLeak embed pattern (#13336)
1592 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1594 'id': '2eb_1496309988',
1596 'title': 'Thief robs place where everyone was armed',
1597 'description': 'md5:694d73ee79e535953cf2488562288eee',
1598 'uploader': 'brazilwtf',
1600 'add_ie': [LiveLeakIE.ie_key()],
1602 # Duplicated embedded video URLs
1604 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1606 'id': '149298443_480_16c25b74_2',
1608 'title': 'vs. Blue Orange Spring Game',
1609 'uploader': 'www.hudl.com',
1612 # twitter:player:stream embed
1614 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1618 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1619 'uploader': 'www.rtl.be',
1623 'skip_download': True,
1626 # twitter:player embed
1628 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1629 'md5': 'a3e0df96369831de324f0778e126653c',
1631 'id': '4909620399001',
1633 'title': 'What Do Black Holes Sound Like?',
1634 'description': 'what do black holes sound like',
1635 'upload_date': '20160524',
1636 'uploader_id': '29913724001',
1637 'timestamp': 1464107587,
1638 'uploader': 'TheAtlantic',
1640 'add_ie': ['BrightcoveLegacy'],
1642 # Facebook <iframe> embed
1644 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1645 'md5': 'fbcde74f534176ecb015849146dd3aee',
1647 'id': '599637780109885',
1649 'title': 'Facebook video #599637780109885',
1652 # Facebook <iframe> embed, plugin video
1654 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1656 'id': '1754168231264132',
1658 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1659 'uploader': 'Tariq Ramadan (official)',
1660 'timestamp': 1496758379,
1661 'upload_date': '20170606',
1664 'skip_download': True,
1667 # Facebook API embed
1669 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1670 'md5': 'a47372ee61b39a7b90287094d447d94e',
1672 'id': '10153467542406923',
1674 'title': 'Facebook video #10153467542406923',
1677 # Wordpress "YouTube Video Importer" plugin
1679 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1680 'md5': 'd16797741b560b485194eddda8121b48',
1682 'id': 'HNTXWDXV9Is',
1684 'title': 'Blue Devils Drumline Stanford lot 2016',
1685 'upload_date': '20160627',
1686 'uploader_id': 'GENOCIDE8GENERAL10',
1687 'uploader': 'cylus cyrus',
1691 # video stored on custom kaltura server
1692 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1693 'md5': '537617d06e64dfed891fa1593c4b30cc',
1697 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1698 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1699 'uploader_id': 'videos.expansion@el-mundo.net',
1700 'upload_date': '20150429',
1701 'timestamp': 1430303472,
1703 'add_ie': ['Kaltura'],
1706 # Non-standard Vimeo embed
1707 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1708 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1712 'title': 'Understanding the web - Teaser',
1713 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1714 'upload_date': '20151214',
1715 'uploader': 'OpenClassrooms',
1716 'uploader_id': 'openclassrooms',
1718 'add_ie': ['Vimeo'],
1721 # generic vimeo embed that requires original URL passed as Referer
1722 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1723 'only_matching': True,
1726 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1727 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1729 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1731 'title': 'Big Buck Bunny',
1732 'description': 'Royalty free test video',
1733 'timestamp': 1432816365,
1734 'upload_date': '20150528',
1738 'skip_download': True,
1740 'add_ie': [ArkenaIE.ie_key()],
1743 '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/',
1747 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1750 'skip_download': True,
1752 'add_ie': [Vbox7IE.ie_key()],
1756 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1759 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1761 'playlist_mincount': 3,
1765 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1767 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1768 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1770 'playlist_mincount': 2,
1774 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1778 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1779 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1782 'skip_download': True,
1784 'add_ie': [TwentyMinutenIE.ie_key()],
1788 'url': 'https://en.support.wordpress.com/videopress/',
1792 'title': 'IMG_5786',
1793 'timestamp': 1435711927,
1794 'upload_date': '20150701',
1797 'skip_download': True,
1799 'add_ie': [VideoPressIE.ie_key()],
1803 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1805 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1807 'title': 'Магаззино: Казань 2',
1808 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1809 'uploader': 'Магаззино',
1810 'upload_date': '20170228',
1811 'uploader_id': '996642',
1814 'skip_download': True,
1816 'add_ie': [RutubeIE.ie_key()],
1819 # ThePlatform embedded with whitespaces in URLs
1820 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1821 'only_matching': True,
1824 # Senate ISVP iframe https
1825 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1826 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1828 'id': 'govtaff020316',
1830 'title': 'Integrated Senate Video Player',
1832 'add_ie': [SenateISVPIE.ie_key()],
1835 # Limelight embeds (1 channel embed + 4 media embeds)
1836 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1838 'id': 'FacilitatorTraining2017',
1839 'title': 'Facilitator Training 2017',
1841 'playlist_mincount': 5,
1844 # Limelight embed (LimelightPlayerUtil.embed)
1845 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1847 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1849 'title': '07448641',
1850 'timestamp': 1499890639,
1851 'upload_date': '20170712',
1854 'skip_download': True,
1856 'add_ie': ['LimelightMedia'],
1859 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1861 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1862 'title': 'Standoff with Walnut Creek murder suspect ends',
1863 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1865 'playlist_mincount': 4,
1868 # WashingtonPost embed
1869 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1871 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1873 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1874 '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.',
1875 'timestamp': 1455216756,
1876 'uploader': 'The Washington Post',
1877 'upload_date': '20160211',
1879 'add_ie': [WashingtonPostIE.ie_key()],
1883 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1887 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1890 'skip_download': True,
1892 'add_ie': [MediasetIE.ie_key()],
1896 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1898 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1899 'title': 'Slovenskom sa prehnala vlna silných búrok',
1901 'playlist_mincount': 5,
1902 'add_ie': [JojIE.ie_key()],
1905 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1906 'url': 'https://tvrain.ru/amp/418921/',
1907 'md5': 'cc00413936695987e8de148b67d14f1d',
1911 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1916 'url': 'http://help.vzaar.com/article/165-embedding-video',
1917 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1921 'title': 'Building A Business Online: Principal Chairs Q & A',
1925 # multiple HTML5 videos on one page
1926 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1928 'id': 'keyscenarios',
1929 'title': 'Rescue Kit 14 Free Edition - Getting started',
1931 'playlist_count': 4,
1935 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1936 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1939 'title': 'vl14062007715967',
1944 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1945 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1947 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1949 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1950 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1951 'timestamp': 1474354800,
1952 'upload_date': '20160920',
1956 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1960 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1961 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1962 'timestamp': 1516100691,
1963 'upload_date': '20180116',
1966 'skip_download': True,
1968 'add_ie': [SpringboardPlatformIE.ie_key()],
1971 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1973 'id': 'uPDB5I9wfp8',
1975 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1976 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1977 'upload_date': '20160219',
1978 'uploader': 'Pocoyo - Português (BR)',
1979 'uploader_id': 'PocoyoBrazil',
1981 'add_ie': [YoutubeIE.ie_key()],
1983 'skip_download': True,
1987 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1989 'id': 'vMDE4NzI1Mjgt690b',
1993 'add_ie': [YapFilesIE.ie_key()],
1995 'skip_download': True,
1999 # CloudflareStream embed
2000 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2002 'id': '31c9291ab41fac05471db4e73aa11717',
2004 'title': '31c9291ab41fac05471db4e73aa11717',
2006 'add_ie': [CloudflareStreamIE.ie_key()],
2008 'skip_download': True,
2013 'url': 'https://joinpeertube.org/fr/home/',
2016 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2018 'playlist_count': 2,
2022 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2026 'title': 'Így kell otthon hamburgert sütni',
2027 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2028 'timestamp': 1426330212,
2029 'upload_date': '20150314',
2030 'uploader': 'StreetKitchen',
2031 'uploader_id': '546363',
2033 'add_ie': [IndavideoEmbedIE.ie_key()],
2035 'skip_download': True,
2039 # APA embed via JWPlatform embed
2040 'url': 'http://www.vol.at/blue-man-group/5593454',
2044 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2045 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2046 'thumbnail': r're:^https?://.*\.jpg$',
2048 'timestamp': 1519211149,
2049 'upload_date': '20180221',
2052 'skip_download': True,
2056 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2057 'md5': 'b68d276de422ab07ee1d49388103f457',
2060 'title': 'Lock up and get excited',
2063 'skip': 'TODO: fix nested playlists processing in tests',
2067 'url': 'https://viqeo.tv/',
2070 'title': 'All-new video platform',
2072 'playlist_count': 6,
2076 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2078 'id': '5b400b834b32992a310622b9',
2080 'title': 'Smoky Barbecue Favorites',
2081 'thumbnail': r're:^https?://.*\.jpe?g',
2083 'add_ie': [ZypeIE.ie_key()],
2085 'skip_download': True,
2090 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2094 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2095 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2096 'thumbnail': r're:^https?://.*\.jpg$',
2099 'skip_download': True,
2101 'expected_warnings': ['Failed to download MPD manifest'],
2104 # # TODO: find another test
2105 # # http://schema.org/VideoObject
2106 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2107 # 'md5': '888dcf08b7ea671381f00fab74692755',
2109 # 'id': 'nyvTSJMKId',
2111 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2112 # 'description': '#love for cats.',
2113 # 'timestamp': 1461244995,
2114 # 'upload_date': '20160421',
2117 # 'force_generic_extractor': True,
2122 def report_following_redirect(self, new_url):
2123 """Report information extraction."""
2124 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2126 def _extract_rss(self, url, video_id, doc):
2127 playlist_title = doc.find('./channel/title').text
2128 playlist_desc_el = doc.find('./channel/description')
2129 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2132 for it in doc.findall('./channel/item'):
2134 enclosure_nodes = it.findall('./enclosure')
2135 for e in enclosure_nodes:
2136 next_url = e.attrib.get('url')
2141 next_url = xpath_text(it, 'link', fatal=False)
2147 '_type': 'url_transparent',
2149 'title': it.find('title').text,
2153 '_type': 'playlist',
2155 'title': playlist_title,
2156 'description': playlist_desc,
2160 def _extract_camtasia(self, url, video_id, webpage):
2161 """ Returns None if no camtasia video can be found. """
2163 camtasia_cfg = self._search_regex(
2164 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2165 webpage, 'camtasia configuration file', default=None)
2166 if camtasia_cfg is None:
2169 title = self._html_search_meta('DC.title', webpage, fatal=True)
2171 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2172 camtasia_cfg = self._download_xml(
2173 camtasia_url, video_id,
2174 note='Downloading camtasia configuration',
2175 errnote='Failed to download camtasia configuration')
2176 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2179 for n in fileset_node.getchildren():
2180 url_n = n.find('./uri')
2185 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2186 'title': '%s - %s' % (title, n.tag),
2187 'url': compat_urlparse.urljoin(url, url_n.text),
2188 'duration': float_or_none(n.find('./duration').text),
2192 '_type': 'playlist',
2197 def _real_extract(self, url):
2198 if url.startswith('//'):
2201 'url': self.http_scheme() + url,
2204 parsed_url = compat_urlparse.urlparse(url)
2205 if not parsed_url.scheme:
2206 default_search = self._downloader.params.get('default_search')
2207 if default_search is None:
2208 default_search = 'fixup_error'
2210 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2212 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2213 return self.url_result('http://' + url)
2214 elif default_search != 'fixup_error':
2215 if default_search == 'auto_warning':
2216 if re.match(r'^(?:url|URL)$', url):
2217 raise ExtractorError(
2218 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2221 self._downloader.report_warning(
2222 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2223 return self.url_result('ytsearch:' + url)
2225 if default_search in ('error', 'fixup_error'):
2226 raise ExtractorError(
2227 '%r is not a valid URL. '
2228 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2229 % (url, url), expected=True)
2231 if ':' not in default_search:
2232 default_search += ':'
2233 return self.url_result(default_search + url)
2235 url, smuggled_data = unsmuggle_url(url)
2236 force_videoid = None
2237 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2238 if smuggled_data and 'force_videoid' in smuggled_data:
2239 force_videoid = smuggled_data['force_videoid']
2240 video_id = force_videoid
2242 video_id = self._generic_id(url)
2244 self.to_screen('%s: Requesting header' % video_id)
2246 head_req = HEADRequest(url)
2247 head_response = self._request_webpage(
2249 note=False, errnote='Could not send HEAD request to %s' % url,
2252 if head_response is not False:
2253 # Check for redirect
2254 new_url = compat_str(head_response.geturl())
2256 self.report_following_redirect(new_url)
2258 new_url = smuggle_url(
2259 new_url, {'force_videoid': force_videoid})
2260 return self.url_result(new_url)
2262 full_response = None
2263 if head_response is False:
2264 request = sanitized_Request(url)
2265 request.add_header('Accept-Encoding', '*')
2266 full_response = self._request_webpage(request, video_id)
2267 head_response = full_response
2271 'title': self._generic_title(url),
2272 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2275 # Check for direct link to a video
2276 content_type = head_response.headers.get('Content-Type', '').lower()
2277 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2279 format_id = compat_str(m.group('format_id'))
2280 if format_id.endswith('mpegurl'):
2281 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2282 elif format_id == 'f4m':
2283 formats = self._extract_f4m_formats(url, video_id)
2286 'format_id': format_id,
2288 'vcodec': 'none' if m.group('type') == 'audio' else None
2290 info_dict['direct'] = True
2291 self._sort_formats(formats)
2292 info_dict['formats'] = formats
2295 if not self._downloader.params.get('test', False) and not is_intentional:
2296 force = self._downloader.params.get('force_generic_extractor', False)
2297 self._downloader.report_warning(
2298 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2300 if not full_response:
2301 request = sanitized_Request(url)
2302 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2303 # making it impossible to download only chunk of the file (yet we need only 512kB to
2304 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2305 # that will always result in downloading the whole file that is not desirable.
2306 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2307 # to accept raw bytes and being able to download only a chunk.
2308 # It may probably better to solve this by checking Content-Type for application/octet-stream
2309 # after HEAD request finishes, but not sure if we can rely on this.
2310 request.add_header('Accept-Encoding', '*')
2311 full_response = self._request_webpage(request, video_id)
2313 first_bytes = full_response.read(512)
2315 # Is it an M3U playlist?
2316 if first_bytes.startswith(b'#EXTM3U'):
2317 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2318 self._sort_formats(info_dict['formats'])
2321 # Maybe it's a direct link to a video?
2322 # Be careful not to download the whole thing!
2323 if not is_html(first_bytes):
2324 self._downloader.report_warning(
2325 'URL could be a direct video link, returning it as such.')
2332 webpage = self._webpage_read_content(
2333 full_response, url, video_id, prefix=first_bytes)
2335 self.report_extraction(video_id)
2337 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2339 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2340 if doc.tag == 'rss':
2341 return self._extract_rss(url, video_id, doc)
2342 elif doc.tag == 'SmoothStreamingMedia':
2343 info_dict['formats'] = self._parse_ism_formats(doc, url)
2344 self._sort_formats(info_dict['formats'])
2346 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2347 smil = self._parse_smil(doc, url, video_id)
2348 self._sort_formats(smil['formats'])
2350 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2351 return self.playlist_result(
2353 doc, video_id, xspf_url=url,
2354 xspf_base_url=compat_str(full_response.geturl())),
2356 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2357 info_dict['formats'] = self._parse_mpd_formats(
2359 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2361 self._sort_formats(info_dict['formats'])
2363 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2364 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2365 self._sort_formats(info_dict['formats'])
2367 except compat_xml_parse_error:
2370 # Is it a Camtasia project?
2371 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2372 if camtasia_res is not None:
2375 # Sometimes embedded video player is hidden behind percent encoding
2376 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2377 # Unescaping the whole page allows to handle those cases in a generic way
2378 webpage = compat_urllib_parse_unquote(webpage)
2380 # it's tempting to parse this further, but you would
2381 # have to take into account all the variations like
2382 # Video Title - Site Name
2383 # Site Name | Video Title
2384 # Video Title - Tagline | Site Name
2385 # and so on and so forth; it's just not practical
2386 video_title = self._og_search_title(
2387 webpage, default=None) or self._html_search_regex(
2388 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2391 # Try to detect age limit automatically
2392 age_limit = self._rta_search(webpage)
2393 # And then there are the jokers who advertise that they use RTA,
2394 # but actually don't.
2395 AGE_LIMIT_MARKERS = [
2396 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2398 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2401 # video uploader is domain name
2402 video_uploader = self._search_regex(
2403 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2405 video_description = self._og_search_description(webpage, default=None)
2406 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2409 'title': video_title,
2410 'description': video_description,
2411 'thumbnail': video_thumbnail,
2412 'age_limit': age_limit,
2415 # Look for Brightcove Legacy Studio embeds
2416 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2420 'url': smuggle_url(bc_url, {'Referer': url}),
2421 'ie_key': 'BrightcoveLegacy'
2422 } for bc_url in bc_urls]
2425 '_type': 'playlist',
2426 'title': video_title,
2431 # Look for Brightcove New Studio embeds
2432 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2434 return self.playlist_from_matches(
2435 bc_urls, video_id, video_title,
2436 getter=lambda x: smuggle_url(x, {'referrer': url}),
2439 # Look for Nexx embeds
2440 nexx_urls = NexxIE._extract_urls(webpage)
2442 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2444 # Look for Nexx iFrame embeds
2445 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2447 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2449 # Look for ThePlatform embeds
2450 tp_urls = ThePlatformIE._extract_urls(webpage)
2452 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2454 # Look for Vessel embeds
2455 vessel_urls = VesselIE._extract_urls(webpage)
2457 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2459 # Look for embedded rtl.nl player
2460 matches = re.findall(
2461 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2464 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2466 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2468 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2470 vid_me_embed_url = self._search_regex(
2471 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2472 webpage, 'vid.me embed', default=None)
2473 if vid_me_embed_url is not None:
2474 return self.url_result(vid_me_embed_url, 'Vidme')
2476 # Look for YouTube embeds
2477 youtube_urls = YoutubeIE._extract_urls(webpage)
2479 return self.playlist_from_matches(
2480 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2482 matches = DailymotionIE._extract_urls(webpage)
2484 return self.playlist_from_matches(matches, video_id, video_title)
2486 # Look for embedded Dailymotion playlist player (#3822)
2488 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2490 playlists = re.findall(
2491 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2493 return self.playlist_from_matches(
2494 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2496 # Look for DailyMail embeds
2497 dailymail_urls = DailyMailIE._extract_urls(webpage)
2499 return self.playlist_from_matches(
2500 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2502 # Look for embedded Wistia player
2503 wistia_url = WistiaIE._extract_url(webpage)
2506 '_type': 'url_transparent',
2507 'url': self._proto_relative_url(wistia_url),
2508 'ie_key': WistiaIE.ie_key(),
2509 'uploader': video_uploader,
2512 # Look for SVT player
2513 svt_url = SVTIE._extract_url(webpage)
2515 return self.url_result(svt_url, 'SVT')
2517 # Look for Bandcamp pages with custom domain
2518 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2519 if mobj is not None:
2520 burl = unescapeHTML(mobj.group(1))
2521 # Don't set the extractor because it can be a track url or an album
2522 return self.url_result(burl)
2524 # Look for embedded Vevo player
2526 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2527 if mobj is not None:
2528 return self.url_result(mobj.group('url'))
2530 # Look for embedded Viddler player
2532 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2534 if mobj is not None:
2535 return self.url_result(mobj.group('url'))
2537 # Look for NYTimes player
2539 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2541 if mobj is not None:
2542 return self.url_result(mobj.group('url'))
2544 # Look for Libsyn player
2546 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2547 if mobj is not None:
2548 return self.url_result(mobj.group('url'))
2550 # Look for Ooyala videos
2551 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2552 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2553 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2554 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2555 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2556 if mobj is not None:
2557 embed_token = self._search_regex(
2558 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2559 webpage, 'ooyala embed token', default=None)
2560 return OoyalaIE._build_url_result(smuggle_url(
2563 'embed_token': embed_token,
2566 # Look for multiple Ooyala embeds on SBN network websites
2567 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2568 if mobj is not None:
2569 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2571 return self.playlist_from_matches(
2572 embeds, video_id, video_title,
2573 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2575 # Look for Aparat videos
2576 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2577 if mobj is not None:
2578 return self.url_result(mobj.group(1), 'Aparat')
2580 # Look for MPORA videos
2581 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2582 if mobj is not None:
2583 return self.url_result(mobj.group(1), 'Mpora')
2585 # Look for embedded NovaMov-based player
2587 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2588 (?P<url>http://(?:(?:embed|www)\.)?
2590 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2591 videoweed\.(?:es|com)|
2592 movshare\.(?:net|sx|ag)|
2593 divxstage\.(?:eu|net|ch|co|at|ag))
2594 /embed\.php.+?)\1''', webpage)
2595 if mobj is not None:
2596 return self.url_result(mobj.group('url'))
2598 # Look for embedded Facebook player
2599 facebook_urls = FacebookIE._extract_urls(webpage)
2601 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2603 # Look for embedded VK player
2604 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2605 if mobj is not None:
2606 return self.url_result(mobj.group('url'), 'VK')
2608 # Look for embedded Odnoklassniki player
2609 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2610 if mobj is not None:
2611 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2613 # Look for embedded ivi player
2614 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2615 if mobj is not None:
2616 return self.url_result(mobj.group('url'), 'Ivi')
2618 # Look for embedded Huffington Post player
2620 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2621 if mobj is not None:
2622 return self.url_result(mobj.group('url'), 'HuffPost')
2625 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2626 if mobj is not None:
2627 return self.url_result(mobj.group('url'))
2628 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2629 if mobj is not None:
2630 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2632 # Look for funnyordie embed
2633 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2635 return self.playlist_from_matches(
2636 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2638 # Look for BBC iPlayer embed
2639 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2641 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2643 # Look for embedded RUTV player
2644 rutv_url = RUTVIE._extract_url(webpage)
2646 return self.url_result(rutv_url, 'RUTV')
2648 # Look for embedded TVC player
2649 tvc_url = TVCIE._extract_url(webpage)
2651 return self.url_result(tvc_url, 'TVC')
2653 # Look for embedded SportBox player
2654 sportbox_urls = SportBoxIE._extract_urls(webpage)
2656 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2658 # Look for embedded XHamster player
2659 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2661 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2663 # Look for embedded TNAFlixNetwork player
2664 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2666 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2668 # Look for embedded PornHub player
2669 pornhub_urls = PornHubIE._extract_urls(webpage)
2671 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2673 # Look for embedded DrTuber player
2674 drtuber_urls = DrTuberIE._extract_urls(webpage)
2676 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2678 # Look for embedded RedTube player
2679 redtube_urls = RedTubeIE._extract_urls(webpage)
2681 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2683 # Look for embedded Tube8 player
2684 tube8_urls = Tube8IE._extract_urls(webpage)
2686 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2688 # Look for embedded Tvigle player
2690 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2691 if mobj is not None:
2692 return self.url_result(mobj.group('url'), 'Tvigle')
2694 # Look for embedded TED player
2696 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2697 if mobj is not None:
2698 return self.url_result(mobj.group('url'), 'TED')
2700 # Look for embedded Ustream videos
2701 ustream_url = UstreamIE._extract_url(webpage)
2703 return self.url_result(ustream_url, UstreamIE.ie_key())
2705 # Look for embedded arte.tv player
2707 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2709 if mobj is not None:
2710 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2712 # Look for embedded francetv player
2714 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2716 if mobj is not None:
2717 return self.url_result(mobj.group('url'))
2719 # Look for embedded smotri.com player
2720 smotri_url = SmotriIE._extract_url(webpage)
2722 return self.url_result(smotri_url, 'Smotri')
2724 # Look for embedded Myvi.ru player
2725 myvi_url = MyviIE._extract_url(webpage)
2727 return self.url_result(myvi_url)
2729 # Look for embedded soundcloud player
2730 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2732 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2734 # Look for tunein player
2735 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2737 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2739 # Look for embedded mtvservices player
2740 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2742 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2744 # Look for embedded yahoo player
2746 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2748 if mobj is not None:
2749 return self.url_result(mobj.group('url'), 'Yahoo')
2751 # Look for embedded sbs.com.au player
2755 <meta\s+property="og:video"\s+content=|
2758 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2760 if mobj is not None:
2761 return self.url_result(mobj.group('url'), 'SBS')
2763 # Look for embedded Cinchcast player
2765 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2767 if mobj is not None:
2768 return self.url_result(mobj.group('url'), 'Cinchcast')
2771 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2775 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2777 if mobj is not None:
2778 return self.url_result(mobj.group('url'), 'MLB')
2781 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2783 if mobj is not None:
2784 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2787 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2789 if mobj is not None:
2790 return self.url_result(mobj.group('url'), 'Livestream')
2792 # Look for Zapiks embed
2794 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2795 if mobj is not None:
2796 return self.url_result(mobj.group('url'), 'Zapiks')
2798 # Look for Kaltura embeds
2799 kaltura_url = KalturaIE._extract_url(webpage)
2801 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2803 # Look for EaglePlatform embeds
2804 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2805 if eagleplatform_url:
2806 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2808 # Look for ClipYou (uses EaglePlatform) embeds
2810 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2811 if mobj is not None:
2812 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2814 # Look for Pladform embeds
2815 pladform_url = PladformIE._extract_url(webpage)
2817 return self.url_result(pladform_url)
2819 # Look for Videomore embeds
2820 videomore_url = VideomoreIE._extract_url(webpage)
2822 return self.url_result(videomore_url)
2824 # Look for Webcaster embeds
2825 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2827 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2829 # Look for Playwire embeds
2831 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2832 if mobj is not None:
2833 return self.url_result(mobj.group('url'))
2835 # Look for 5min embeds
2837 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2838 if mobj is not None:
2839 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2841 # Look for Crooks and Liars embeds
2843 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2844 if mobj is not None:
2845 return self.url_result(mobj.group('url'))
2847 # Look for NBC Sports VPlayer embeds
2848 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2850 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2852 # Look for NBC News embeds
2853 nbc_news_embed_url = re.search(
2854 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2855 if nbc_news_embed_url:
2856 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2858 # Look for Google Drive embeds
2859 google_drive_url = GoogleDriveIE._extract_url(webpage)
2860 if google_drive_url:
2861 return self.url_result(google_drive_url, 'GoogleDrive')
2863 # Look for UDN embeds
2865 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2866 if mobj is not None:
2867 return self.url_result(
2868 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2870 # Look for Senate ISVP iframe
2871 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2873 return self.url_result(senate_isvp_url, 'SenateISVP')
2875 # Look for OnionStudios embeds
2876 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2877 if onionstudios_url:
2878 return self.url_result(onionstudios_url)
2880 # Look for ViewLift embeds
2881 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2883 return self.url_result(viewlift_url)
2885 # Look for JWPlatform embeds
2886 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2888 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2890 # Look for Digiteka embeds
2891 digiteka_url = DigitekaIE._extract_url(webpage)
2893 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2895 # Look for Arkena embeds
2896 arkena_url = ArkenaIE._extract_url(webpage)
2898 return self.url_result(arkena_url, ArkenaIE.ie_key())
2900 # Look for Piksel embeds
2901 piksel_url = PikselIE._extract_url(webpage)
2903 return self.url_result(piksel_url, PikselIE.ie_key())
2905 # Look for Limelight embeds
2906 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2908 return self.playlist_result(
2909 limelight_urls, video_id, video_title, video_description)
2911 # Look for Anvato embeds
2912 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2914 return self.playlist_result(
2915 anvato_urls, video_id, video_title, video_description)
2917 # Look for AdobeTVVideo embeds
2919 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2921 if mobj is not None:
2922 return self.url_result(
2923 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2926 # Look for Vine embeds
2928 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2930 if mobj is not None:
2931 return self.url_result(
2932 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2934 # Look for VODPlatform embeds
2936 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2938 if mobj is not None:
2939 return self.url_result(
2940 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2942 # Look for Mangomolo embeds
2944 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2946 video\?.*?\bid=(?P<video_id>\d+)|
2947 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2948 ).+?)\1''', webpage)
2949 if mobj is not None:
2951 '_type': 'url_transparent',
2952 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2953 'title': video_title,
2954 'description': video_description,
2955 'thumbnail': video_thumbnail,
2956 'uploader': video_uploader,
2958 video_id = mobj.group('video_id')
2961 'ie_key': 'MangomoloVideo',
2966 'ie_key': 'MangomoloLive',
2967 'id': mobj.group('channel_id'),
2971 # Look for Instagram embeds
2972 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2973 if instagram_embed_url is not None:
2974 return self.url_result(
2975 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2977 # Look for LiveLeak embeds
2978 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2980 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2982 # Look for 3Q SDN embeds
2983 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2986 '_type': 'url_transparent',
2987 'ie_key': ThreeQSDNIE.ie_key(),
2988 'url': self._proto_relative_url(threeqsdn_url),
2989 'title': video_title,
2990 'description': video_description,
2991 'thumbnail': video_thumbnail,
2992 'uploader': video_uploader,
2995 # Look for VBOX7 embeds
2996 vbox7_url = Vbox7IE._extract_url(webpage)
2998 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3000 # Look for DBTV embeds
3001 dbtv_urls = DBTVIE._extract_urls(webpage)
3003 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3005 # Look for Videa embeds
3006 videa_urls = VideaIE._extract_urls(webpage)
3008 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3010 # Look for 20 minuten embeds
3011 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3013 return self.playlist_from_matches(
3014 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3016 # Look for Openload embeds
3017 openload_urls = OpenloadIE._extract_urls(webpage)
3019 return self.playlist_from_matches(
3020 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
3022 # Look for VideoPress embeds
3023 videopress_urls = VideoPressIE._extract_urls(webpage)
3025 return self.playlist_from_matches(
3026 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3028 # Look for Rutube embeds
3029 rutube_urls = RutubeIE._extract_urls(webpage)
3031 return self.playlist_from_matches(
3032 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3034 # Look for WashingtonPost embeds
3035 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3037 return self.playlist_from_matches(
3038 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3040 # Look for Mediaset embeds
3041 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3043 return self.playlist_from_matches(
3044 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3046 # Look for JOJ.sk embeds
3047 joj_urls = JojIE._extract_urls(webpage)
3049 return self.playlist_from_matches(
3050 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3052 # Look for megaphone.fm embeds
3053 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3055 return self.playlist_from_matches(
3056 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3058 # Look for vzaar embeds
3059 vzaar_urls = VzaarIE._extract_urls(webpage)
3061 return self.playlist_from_matches(
3062 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3064 channel9_urls = Channel9IE._extract_urls(webpage)
3066 return self.playlist_from_matches(
3067 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3069 vshare_urls = VShareIE._extract_urls(webpage)
3071 return self.playlist_from_matches(
3072 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3074 # Look for Mediasite embeds
3075 mediasite_urls = MediasiteIE._extract_urls(webpage)
3078 self.url_result(smuggle_url(
3079 compat_urlparse.urljoin(url, mediasite_url),
3080 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3081 for mediasite_url in mediasite_urls]
3082 return self.playlist_result(entries, video_id, video_title)
3084 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3085 if springboardplatform_urls:
3086 return self.playlist_from_matches(
3087 springboardplatform_urls, video_id, video_title,
3088 ie=SpringboardPlatformIE.ie_key())
3090 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3092 return self.playlist_from_matches(
3093 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3095 vice_urls = ViceIE._extract_urls(webpage)
3097 return self.playlist_from_matches(
3098 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3100 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3102 return self.playlist_from_matches(
3103 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3105 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3106 if cloudflarestream_urls:
3107 return self.playlist_from_matches(
3108 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3110 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3112 return self.playlist_from_matches(
3113 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3115 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3117 return self.playlist_from_matches(
3118 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3120 apa_urls = APAIE._extract_urls(webpage)
3122 return self.playlist_from_matches(
3123 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3125 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3127 return self.playlist_from_matches(
3128 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3130 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3131 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3133 if sharevideos_urls:
3134 return self.playlist_from_matches(
3135 sharevideos_urls, video_id, video_title)
3137 viqeo_urls = ViqeoIE._extract_urls(webpage)
3139 return self.playlist_from_matches(
3140 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3142 expressen_urls = ExpressenIE._extract_urls(webpage)
3144 return self.playlist_from_matches(
3145 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3147 zype_urls = ZypeIE._extract_urls(webpage)
3149 return self.playlist_from_matches(
3150 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3152 # Look for HTML5 media
3153 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3155 if len(entries) == 1:
3158 'title': video_title,
3161 for num, entry in enumerate(entries, start=1):
3163 'id': '%s-%s' % (video_id, num),
3164 'title': '%s (%d)' % (video_title, num),
3166 for entry in entries:
3167 self._sort_formats(entry['formats'])
3168 return self.playlist_result(entries, video_id, video_title)
3170 jwplayer_data = self._find_jwplayer_data(
3171 webpage, video_id, transform_source=js_to_json)
3174 info = self._parse_jwplayer_data(
3175 jwplayer_data, video_id, require_title=False, base_url=url)
3176 return merge_dicts(info, info_dict)
3177 except ExtractorError:
3178 # See https://github.com/rg3/youtube-dl/pull/16735
3183 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3185 if mobj is not None:
3186 sources = self._parse_json(
3187 mobj.group(1), video_id, transform_source=js_to_json,
3189 if not isinstance(sources, list):
3192 for source in sources:
3193 src = source.get('src')
3194 if not src or not isinstance(src, compat_str):
3196 src = compat_urlparse.urljoin(url, src)
3197 src_type = source.get('type')
3198 if isinstance(src_type, compat_str):
3199 src_type = src_type.lower()
3200 ext = determine_ext(src).lower()
3201 if src_type == 'video/youtube':
3202 return self.url_result(src, YoutubeIE.ie_key())
3203 if src_type == 'application/dash+xml' or ext == 'mpd':
3204 formats.extend(self._extract_mpd_formats(
3205 src, video_id, mpd_id='dash', fatal=False))
3206 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3207 formats.extend(self._extract_m3u8_formats(
3208 src, video_id, 'mp4', entry_protocol='m3u8_native',
3209 m3u8_id='hls', fatal=False))
3213 'ext': (mimetype2ext(src_type) or
3214 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3217 self._sort_formats(formats)
3218 info_dict['formats'] = formats
3221 # Looking for http://schema.org/VideoObject
3222 json_ld = self._search_json_ld(
3223 webpage, video_id, default={}, expected_type='VideoObject')
3224 if json_ld.get('url'):
3225 return merge_dicts(json_ld, info_dict)
3227 def check_video(vurl):
3228 if YoutubeIE.suitable(vurl):
3230 if RtmpIE.suitable(vurl):
3232 vpath = compat_urlparse.urlparse(vurl).path
3233 vext = determine_ext(vpath)
3234 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3236 def filter_video(urls):
3237 return list(filter(check_video, urls))
3239 # Start with something easy: JW Player in SWFObject
3240 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3242 # Look for gorilla-vid style embedding
3243 found = filter_video(re.findall(r'''(?sx)
3247 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3250 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3252 # Broaden the search a little bit
3253 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3255 # Broaden the findall a little bit: JWPlayer JS loader
3256 found = filter_video(re.findall(
3257 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3260 found = filter_video(re.findall(r'''(?xs)
3261 flowplayer\("[^"]+",\s*
3263 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3264 ["']?url["']?\s*:\s*["']([^"']+)["']
3269 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3271 # Try to find twitter cards info
3272 # twitter:player:stream should be checked before twitter:player since
3273 # it is expected to contain a raw stream (see
3274 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3275 found = filter_video(re.findall(
3276 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3278 # We look for Open Graph info:
3279 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3280 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3281 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3282 if m_video_type is not None:
3283 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3285 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3287 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3288 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3291 # Look also in Refresh HTTP header
3292 refresh_header = head_response.headers.get('Refresh')
3294 # In python 2 response HTTP headers are bytestrings
3295 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3296 refresh_header = refresh_header.decode('iso-8859-1')
3297 found = re.search(REDIRECT_REGEX, refresh_header)
3299 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3301 self.report_following_redirect(new_url)
3310 # twitter:player is a https URL to iframe player that may or may not
3311 # be supported by youtube-dl thus this is checked the very last (see
3312 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3313 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3314 if embed_url and embed_url != url:
3315 return self.url_result(embed_url)
3318 raise UnsupportedError(url)
3321 for video_url in orderedSet(found):
3322 video_url = unescapeHTML(video_url)
3323 video_url = video_url.replace('\\/', '/')
3324 video_url = compat_urlparse.urljoin(url, video_url)
3325 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3327 # Sometimes, jwplayer extraction will result in a YouTube URL
3328 if YoutubeIE.suitable(video_url):
3329 entries.append(self.url_result(video_url, 'Youtube'))
3332 # here's a fun little line of code for you:
3333 video_id = os.path.splitext(video_id)[0]
3337 'uploader': video_uploader,
3338 'title': video_title,
3339 'age_limit': age_limit,
3342 if RtmpIE.suitable(video_url):
3343 entry_info_dict.update({
3344 '_type': 'url_transparent',
3345 'ie_key': RtmpIE.ie_key(),
3348 entries.append(entry_info_dict)
3351 ext = determine_ext(video_url)
3353 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3355 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3357 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3359 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3361 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3362 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3363 # Just matching .ism/manifest is not enough to be reliably sure
3364 # whether it's actually an ISM manifest or some other streaming
3365 # manifest since there are various streaming URL formats
3366 # possible (see [1]) as well as some other shenanigans like
3367 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3369 # Thus the most reasonable way to solve this is to delegate
3370 # to generic extractor in order to look into the contents of
3371 # the manifest itself.
3372 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3373 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3374 entry_info_dict = self.url_result(
3375 smuggle_url(video_url, {'to_generic': True}),
3378 entry_info_dict['url'] = video_url
3380 if entry_info_dict.get('formats'):
3381 self._sort_formats(entry_info_dict['formats'])
3383 entries.append(entry_info_dict)
3385 if len(entries) == 1:
3388 for num, e in enumerate(entries, start=1):
3389 # 'url' results don't have a title
3390 if e.get('title') is not None:
3391 e['title'] = '%s (%d)' % (e['title'], num)
3393 '_type': 'playlist',