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 .mofosex
import MofosexEmbedIE
64 from .spankwire
import SpankwireIE
65 from .youporn
import YouPornIE
66 from .vimeo
import VimeoIE
67 from .dailymotion
import DailymotionIE
68 from .dailymail
import DailyMailIE
69 from .onionstudios
import OnionStudiosIE
70 from .viewlift
import ViewLiftEmbedIE
71 from .mtv
import MTVServicesEmbeddedIE
72 from .pladform
import PladformIE
73 from .videomore
import VideomoreIE
74 from .webcaster
import WebcasterFeedIE
75 from .googledrive
import GoogleDriveIE
76 from .jwplatform
import JWPlatformIE
77 from .digiteka
import DigitekaIE
78 from .arkena
import ArkenaIE
79 from .instagram
import InstagramIE
80 from .liveleak
import LiveLeakIE
81 from .threeqsdn
import ThreeQSDNIE
82 from .theplatform
import ThePlatformIE
83 from .kaltura
import KalturaIE
84 from .eagleplatform
import EaglePlatformIE
85 from .facebook
import FacebookIE
86 from .soundcloud
import SoundcloudEmbedIE
87 from .tunein
import TuneInBaseIE
88 from .vbox7
import Vbox7IE
89 from .dbtv
import DBTVIE
90 from .piksel
import PikselIE
91 from .videa
import VideaIE
92 from .twentymin
import TwentyMinutenIE
93 from .ustream
import UstreamIE
94 from .arte
import ArteTVEmbedIE
95 from .videopress
import VideoPressIE
96 from .rutube
import RutubeIE
97 from .limelight
import LimelightBaseIE
98 from .anvato
import AnvatoIE
99 from .washingtonpost
import WashingtonPostIE
100 from .wistia
import WistiaIE
101 from .mediaset
import MediasetIE
102 from .joj
import JojIE
103 from .megaphone
import MegaphoneIE
104 from .vzaar
import VzaarIE
105 from .channel9
import Channel9IE
106 from .vshare
import VShareIE
107 from .mediasite
import MediasiteIE
108 from .springboardplatform
import SpringboardPlatformIE
109 from .yapfiles
import YapFilesIE
110 from .vice
import ViceIE
111 from .xfileshare
import XFileShareIE
112 from .cloudflarestream
import CloudflareStreamIE
113 from .peertube
import PeerTubeIE
114 from .teachable
import TeachableIE
115 from .indavideo
import IndavideoEmbedIE
116 from .apa
import APAIE
117 from .foxnews
import FoxNewsIE
118 from .viqeo
import ViqeoIE
119 from .expressen
import ExpressenIE
120 from .zype
import ZypeIE
121 from .odnoklassniki
import OdnoklassnikiIE
122 from .kinja
import KinjaEmbedIE
123 from .bitchute
import BitChuteIE
126 class GenericIE(InfoExtractor
):
127 IE_DESC
= 'Generic downloader that works on some sites'
131 # Direct link to a video
133 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
134 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
139 'upload_date': '20100513',
142 # Direct link to media delivered compressed (until Accept-Encoding is *)
144 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
145 'md5': '128c42e68b13950268b648275386fc74',
147 'id': 'FictionJunction-Parallel_Hearts',
149 'title': 'FictionJunction-Parallel_Hearts',
150 'upload_date': '20140522',
152 'expected_warnings': [
153 'URL could be a direct video link, returning it as such.'
155 'skip': 'URL invalid',
157 # Direct download with broken HEAD
159 'url': 'http://ai-radio.org:8000/radio.opus',
166 'skip_download': True, # infinite live stream
168 'expected_warnings': [
169 r
'501.*Not Implemented',
173 # Direct link with incorrect MIME type
175 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
176 'md5': '4ccbebe5f36706d85221f204d7eb5913',
178 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
179 'id': '5_Lennart_Poettering_-_Systemd',
181 'title': '5_Lennart_Poettering_-_Systemd',
182 'upload_date': '20141120',
184 'expected_warnings': [
185 'URL could be a direct video link, returning it as such.'
190 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
192 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
193 'title': 'Zero Punctuation',
194 'description': 're:.*groundbreaking video review series.*'
196 'playlist_mincount': 11,
198 # RSS feed with enclosure
200 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
202 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
204 'upload_date': '20150228',
205 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
208 # RSS feed with enclosures and unsupported link URLs
210 'url': 'http://www.hellointernet.fm/podcast?format=rss',
212 'id': 'http://www.hellointernet.fm/podcast?format=rss',
213 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
214 'title': 'Hello Internet',
216 'playlist_mincount': 100,
218 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
220 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
224 'title': 'Automatics, robotics and biocybernetics',
225 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
226 'upload_date': '20130627',
227 'formats': 'mincount:16',
228 'subtitles': 'mincount:1',
231 'force_generic_extractor': True,
232 'skip_download': True,
235 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
237 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
242 'formats': 'mincount:1',
245 'skip_download': True,
248 # SMIL from https://www.restudy.dk/video/play/id/1637
250 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
254 'title': 'video_1637',
255 'formats': 'mincount:3',
258 'skip_download': True,
261 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
263 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
265 'id': 'smil-service',
267 'title': 'smil-service',
268 'formats': 'mincount:1',
271 'skip_download': True,
274 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
276 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
280 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
281 'formats': 'mincount:3',
284 'skip_download': True,
287 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
289 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
291 'id': 'mZlp2ctYIUEB',
293 'title': 'Tikibad ontruimd wegens brand',
294 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
295 'thumbnail': r
're:^https?://.*\.jpg$',
299 'skip_download': True,
302 # MPD from http://dash-mse-test.appspot.com/media.html
304 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
305 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
307 'id': 'car-20120827-manifest',
309 'title': 'car-20120827-manifest',
310 'formats': 'mincount:9',
311 'upload_date': '20130904',
314 'format': 'bestvideo',
317 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
319 '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',
324 'formats': 'mincount:8',
328 'skip_download': True,
330 'skip': 'video gone',
332 # m3u8 served with Content-Type: text/plain
334 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
339 'upload_date': '20140720',
340 'formats': 'mincount:11',
344 'skip_download': True,
346 'skip': 'video gone',
350 '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',
354 'upload_date': '20130224',
355 'uploader_id': 'TheVerge',
356 'description': r
're:^Chris Ziegler takes a look at the\.*',
357 'uploader': 'The Verge',
358 'title': 'First Firefox OS phones side-by-side',
361 'skip_download': False,
365 # redirect in Refresh HTTP header
366 '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',
370 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
371 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
372 'upload_date': '20150917',
373 'uploader_id': 'brtvofficial',
374 'uploader': 'Boiler Room',
377 'skip_download': False,
381 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
382 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
384 'id': '13601338388002',
386 'uploader': 'www.hodiho.fr',
387 'title': 'R\u00e9gis plante sa Jeep',
390 # bandcamp page with custom domain
392 'add_ie': ['Bandcamp'],
393 'url': 'http://bronyrock.com/track/the-pony-mash',
397 'title': 'The Pony Mash',
398 'uploader': 'M_Pallante',
400 'skip': 'There is a limit of 200 free downloads / month for the test song',
403 # embedded brightcove video
404 # it also tests brightcove videos that need to set the 'Referer'
405 # in the http requests
406 'add_ie': ['BrightcoveLegacy'],
407 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
409 'id': '2765128793001',
411 'title': 'Le cours de bourse : l’analyse technique',
412 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
413 'uploader': 'BFM BUSINESS',
416 'skip_download': True,
420 # embedded with itemprop embedURL and video id spelled as `idVideo`
421 'add_id': ['BrightcoveLegacy'],
422 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
424 'id': '5255628253001',
426 'title': 'md5:37c519b1128915607601e75a87995fc0',
427 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
428 'uploader': 'BFM BUSINESS',
429 'uploader_id': '876450612001',
430 'timestamp': 1482255315,
431 'upload_date': '20161220',
434 'skip_download': True,
438 # https://github.com/ytdl-org/youtube-dl/issues/2253
439 'url': 'http://bcove.me/i6nfkrc3',
440 'md5': '0ba9446db037002366bab3b3eb30c88c',
442 'id': '3101154703001',
444 'title': 'Still no power',
445 'uploader': 'thestar.com',
446 '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.',
448 'add_ie': ['BrightcoveLegacy'],
449 'skip': 'video gone',
452 'url': 'http://www.championat.com/video/football/v/87/87499.html',
453 'md5': 'fb973ecf6e4a78a67453647444222983',
455 'id': '3414141473001',
457 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
458 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
459 'uploader': 'Championat',
463 # https://github.com/ytdl-org/youtube-dl/issues/3541
464 'add_ie': ['BrightcoveLegacy'],
465 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
467 'id': '3866516442001',
469 'title': 'Leer mij vrouwen kennen: Aflevering 1',
470 'description': 'Leer mij vrouwen kennen: Aflevering 1',
471 'uploader': 'SBS Broadcasting',
473 'skip': 'Restricted to Netherlands',
475 'skip_download': True, # m3u8 download
479 # Brightcove video in <iframe>
480 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
481 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
483 'id': '5360463607001',
485 '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',
486 '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。',
487 'uploader': 'United Nations',
488 'uploader_id': '1362235914001',
489 'timestamp': 1489593889,
490 'upload_date': '20170315',
492 'add_ie': ['BrightcoveLegacy'],
495 # Brightcove with alternative playerID key
496 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
498 'id': 'nmeth.2062_SV1',
499 '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',
503 'id': '2228375078001',
505 'title': 'nmeth.2062-sv1',
506 'description': 'nmeth.2062-sv1',
507 'timestamp': 1363357591,
508 'upload_date': '20130315',
509 'uploader': 'Nature Publishing Group',
510 'uploader_id': '1964492299001',
515 # Brightcove with UUID in videoPlayer
516 'url': 'http://www8.hp.com/cn/zh/home.html',
518 'id': '5255815316001',
520 'title': 'Sprocket Video - China',
521 'description': 'Sprocket Video - China',
522 'uploader': 'HP-Video Gallery',
523 'timestamp': 1482263210,
524 'upload_date': '20161220',
525 'uploader_id': '1107601872001',
528 'skip_download': True, # m3u8 download
530 'skip': 'video rotates...weekly?',
533 # Brightcove:new type [2].
534 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
535 'md5': '2b35148fcf48da41c9fb4591650784f3',
537 'id': '5348741021001',
539 'upload_date': '20170306',
540 'uploader_id': '4191638492001',
541 'timestamp': 1488769918,
542 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
547 # Alternative brightcove <video> attributes
548 '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/',
550 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
551 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
554 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
556 'id': '5311302538001',
558 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
559 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
560 'timestamp': 1486321708,
561 'upload_date': '20170205',
562 'uploader_id': '800000640001',
564 'only_matching': True,
568 # Brightcove with UUID in videoPlayer
569 'url': 'http://www8.hp.com/cn/zh/home.html',
571 'id': '5255815316001',
573 'title': 'Sprocket Video - China',
574 'description': 'Sprocket Video - China',
575 'uploader': 'HP-Video Gallery',
576 'timestamp': 1482263210,
577 'upload_date': '20161220',
578 'uploader_id': '1107601872001',
581 'skip_download': True, # m3u8 download
586 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
587 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
589 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
591 'title': '2cc213299525360.mov', # that's what we get
594 'add_ie': ['Ooyala'],
597 # ooyala video embedded with http://player.ooyala.com/iframe.js
598 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
600 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
602 'title': '"Steve Jobs: Man in the Machine" trailer',
603 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
607 'skip_download': True,
609 'skip': 'movie expired',
611 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
613 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
615 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
617 'title': 'Steampunk Fest Comes to Honesdale',
621 'skip_download': True,
626 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
630 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
631 'upload_date': '20140225',
632 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
633 'uploader': 'Tested',
634 'uploader_id': 'testedcom',
636 # No need to test YoutubeIE here
638 'skip_download': True,
643 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
647 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
648 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
650 # HEAD requests lead to endless 301, while GET is OK
651 'expected_warnings': ['301'],
655 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
659 'title': 'Охотское море стало целиком российским',
660 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
664 'skip_download': True,
669 '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/',
673 'title': 'Дошкольное воспитание',
678 'url': 'http://www.vestifinance.ru/articles/25753',
681 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
686 'title': 'Госзаказ. День 3',
692 'title': 'Госзаказ. День 2',
698 'title': 'Госзаказ. День 1',
704 'skip_download': True,
709 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
711 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
713 'title': 'Ужастики, русский трейлер (2015)',
714 'thumbnail': r
're:^https?://.*\.jpg$',
720 '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',
723 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
725 'playlist_mincount': 7,
726 # This forum does not allow <iframe> syntaxes anymore
727 # Now HTML tags are displayed as-is
728 'skip': 'No videos on this page',
732 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
733 'md5': '65fdff94098e4a607385a60c5177c638',
737 'title': 'Hidden miracles of the natural world',
738 'uploader': 'Louie Schwartzberg',
739 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
742 # nowvideo embed hidden behind percent encoding
744 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
745 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
747 'id': '06e53103ca9aa',
749 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
750 'description': 'No description',
755 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
756 'md5': '7653032cbb25bf6c80d80f217055fa43',
758 'id': '048195-004_PLUS7-F',
761 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
762 'upload_date': '20140320',
765 'skip_download': 'Requires rtmpdump'
767 'skip': 'video gone',
771 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
775 'title': 'Alcaline, le concert avec Calogero',
776 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
777 'upload_date': '20150226',
778 'timestamp': 1424989860,
783 'skip_download': True,
785 'expected_warnings': [
791 'url': 'http://www.wired.com/2014/04/honda-asimo/',
792 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
794 'id': '53501be369702d3275860000',
796 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
801 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
802 'md5': '441aeeb82eb72c422c7f14ec533999cd',
804 'id': 'k2mm4bCdJ6CQ2i7c8o2',
806 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
807 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
809 'uploader_id': 'xgditw',
810 'upload_date': '20140425',
811 'timestamp': 1398441542,
813 'add_ie': ['Dailymotion'],
817 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
821 'title': 'Care worker punches elderly dementia patient in head 11 times',
822 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
824 'add_ie': ['DailyMail'],
826 'skip_download': True,
831 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
835 'title': 'The NBL Auction 2014',
836 'uploader': 'BADMINTON England',
837 'uploader_id': 'BADMINTONEvents',
838 'upload_date': '20140603',
839 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
841 'add_ie': ['Youtube'],
843 'skip_download': True,
848 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
849 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
851 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
853 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
854 'description': 'Two valets share their love for movie star Liam Neesons.',
855 'timestamp': 1349922600,
856 'upload_date': '20121011',
859 # YouTube embed via <data-embed-url="">
861 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
865 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
866 'uploader': 'Gameloft',
867 'uploader_id': 'gameloft',
868 'upload_date': '20140828',
869 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
872 'skip_download': True,
875 # YouTube <object> embed
877 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
878 'md5': '516718101ec834f74318df76259fb3cc',
882 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
883 'upload_date': '20080526',
884 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
885 'uploader': 'Christopher Sykes',
886 'uploader_id': 'ChristopherJSykes',
888 'add_ie': ['Youtube'],
892 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
894 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
896 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
897 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
902 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
904 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
905 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
911 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
916 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
917 'md5': '9d65602bf31c6e20014319c7d07fba27',
919 'id': '5123ea6d5e5a7',
922 'uploader': 'www.handjobhub.com',
923 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
926 # Multiple brightcove videos
927 # https://github.com/ytdl-org/youtube-dl/issues/2283
929 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
931 'id': 'always-never',
932 'title': 'Always / Never - The New Yorker',
936 'extract_flat': False,
937 'skip_download': True,
942 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
943 'md5': '96f09a37e44da40dd083e12d9a683327',
947 'title': 'Ump changes call to ball',
948 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
950 'timestamp': 1401537900,
951 'upload_date': '20140531',
952 'thumbnail': r
're:^https?://.*\.jpg$',
957 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
958 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
962 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
963 'description': 'a Paywall Videos video from Remilon',
965 'uploader': 'study.com',
966 'timestamp': 1459678540,
967 'upload_date': '20160403',
968 'filesize': 24687186,
972 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
973 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
977 'title': 'Conversation about Hexagonal Rails Part 1',
978 'description': 'a Martin Fowler video from ThoughtWorks',
980 'uploader': 'thoughtworks.wistia.com',
981 'timestamp': 1401832161,
982 'upload_date': '20140603',
985 # Wistia standard embed (async)
987 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
991 'title': 'Drip Brennan Dunn Workshop',
992 'description': 'a JV Webinars video from getdrip-1',
994 'timestamp': 1463607249,
995 'upload_date': '20160518',
998 'skip_download': True,
1003 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1007 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1008 'uploader': 'Sophos Security',
1009 'title': 'Chet Chat 171 - Oct 29, 2014',
1010 'upload_date': '20141029',
1013 # Soundcloud multiple embeds
1015 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1018 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1020 'playlist_mincount': 7,
1022 # TuneIn station embed
1024 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1029 'location': 'Paris, France',
1034 'skip_download': True,
1039 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1043 'upload_date': '20141112',
1044 'title': 'Rosetta #CometLanding webcast HL 10',
1047 # Another Livestream embed, without 'new.' in URL
1049 'url': 'https://www.freespeech.org/',
1053 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1057 'skip_download': True,
1062 'url': 'https://skiplagged.com/',
1065 'title': 'Skiplagged: The smart way to find cheap flights',
1067 'playlist_mincount': 1,
1068 'add_ie': ['Youtube'],
1072 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1076 'upload_date': '20141126',
1077 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1082 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1084 'id': '730m_DandD_1901_512k',
1086 'uploader': 'www.abc.net.au',
1087 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1090 # embedded viddler video
1092 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1096 'uploader': 'deadspin',
1097 'title': 'WALL-TO-GORTAT',
1098 'timestamp': 1422285291,
1099 'upload_date': '20150126',
1101 'add_ie': ['Viddler'],
1105 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1109 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1110 'description': 'md5:601cb790edd05908957dae8aaa866465',
1111 'upload_date': '20150220',
1113 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1117 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1119 'id': 'Mrj4DVp2zeA',
1121 'upload_date': '20150212',
1122 'uploader': 'The National Archives UK',
1123 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1124 'uploader_id': 'NationalArchives08',
1125 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1130 'url': 'http://www.suffolk.edu/sjc/live.php',
1134 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1135 'uploader': 'www.suffolk.edu',
1138 'skip_download': True,
1140 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1144 'url': 'http://www.indiedb.com/games/king-machine/videos',
1148 'title': 'king machine trailer 1',
1149 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1150 'thumbnail': r
're:^https?://.*\.jpg$',
1154 # JWPlayer config passed as variable
1155 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1159 'title': 'ARIELE | Tube Cup',
1160 'uploader': 'www.txxx.com',
1164 'skip_download': True,
1169 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1170 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1174 'upload_date': '20171122',
1175 'timestamp': 1511366290,
1176 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1178 'add_ie': [JWPlatformIE
.ie_key()],
1181 # Video.js embed, multiple formats
1182 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1184 'id': 'yygqldloqIk',
1186 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1187 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1188 'upload_date': '20130314',
1189 'uploader': 'PROстое3D',
1190 'uploader_id': 'PROstoe3D',
1193 'skip_download': True,
1197 # Video.js embed, single format
1198 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1202 'title': 'Step 1 - Good Foundation',
1203 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1206 'skip_download': True,
1211 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1212 'playlist_mincount': 5,
1214 'id': 'aanslagen-kopenhagen',
1215 'title': 'Aanslagen Kopenhagen',
1220 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1224 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1227 # Kaltura embed (different embed code)
1229 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1233 'upload_date': '20150127',
1234 'uploader_id': 'PremierMedia',
1236 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1239 # Kaltura embed with single quotes
1241 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1246 'timestamp': 1355743100,
1247 'upload_date': '20121217',
1248 'uploader_id': 'cplapp@learn360.com',
1250 'add_ie': ['Kaltura'],
1253 # Kaltura embedded via quoted entry_id
1254 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1258 'title': '06_matthew_brender_raj_dutt',
1259 'timestamp': 1466638791,
1260 'upload_date': '20160622',
1262 'add_ie': ['Kaltura'],
1263 'expected_warnings': [
1264 'Could not send HEAD request'
1267 'skip_download': True,
1271 # Kaltura embedded, some fileExt broken (#11480)
1272 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1276 'title': 'Our "Standard Models" of particle physics and cosmology',
1277 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1278 'timestamp': 1321158993,
1279 'upload_date': '20111113',
1280 'uploader_id': 'kps1',
1282 'add_ie': ['Kaltura'],
1285 # Kaltura iframe embed
1286 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1287 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1291 'title': 'I. M. Pei: A Centennial Celebration',
1292 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1293 'upload_date': '20170403',
1294 'uploader_id': 'batchUser',
1295 'timestamp': 1491232186,
1297 'add_ie': ['Kaltura'],
1300 # Kaltura iframe embed, more sophisticated
1301 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1305 'title': 'lecture-05sep2017',
1306 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1307 'upload_date': '20170913',
1308 'uploader_id': 'eps2',
1309 'timestamp': 1505340777,
1312 'skip_download': True,
1314 'add_ie': ['Kaltura'],
1317 # meta twitter:player
1318 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1322 'title': 'Main Twerk (Video)',
1323 'upload_date': '20171208',
1324 'uploader_id': 'sebastian.salinas@thechive.com',
1325 'timestamp': 1512713057,
1328 'skip_download': True,
1330 'add_ie': ['Kaltura'],
1332 # referrer protected EaglePlatform embed
1334 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1338 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1339 'thumbnail': r
're:^https?://.*\.jpg$',
1344 'skip_download': True,
1347 # ClipYou (EaglePlatform) embed (custom URL)
1349 'url': 'http://muz-tv.ru/play/7129/',
1350 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1354 'title': "'O Sole Mio",
1355 'thumbnail': r
're:^https?://.*\.jpg$',
1360 'skip_download': True,
1362 'skip': 'This video is unavailable.',
1366 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1370 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1371 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1372 'thumbnail': r
're:^https?://.*\.jpg$',
1376 'skip': 'HTTP Error 404: Not Found',
1380 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1384 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1385 'thumbnail': r
're:^https?://.*\.png$',
1391 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1392 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1396 'title': 'Facebook Creates "On This Day" | Crunch Report',
1397 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1398 'timestamp': 1427237531,
1399 'uploader': 'Crunch Report',
1400 'upload_date': '20150324',
1404 'skip_download': True,
1407 # Crooks and Liars embed
1409 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1413 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1414 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1415 'timestamp': 1428207000,
1416 'upload_date': '20150405',
1417 'uploader': 'Heather',
1420 # Crooks and Liars external embed
1422 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1424 'id': 'MTE3MjUtMzQ2MzA',
1426 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1427 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1428 'timestamp': 1265032391,
1429 'upload_date': '20100201',
1430 'uploader': 'Heather',
1433 # NBC Sports vplayer embed
1435 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1437 'id': 'ln7x1qSThw4k',
1439 'title': "PFT Live: New leader in the 'new-look' defense",
1440 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1441 'uploader': 'NBCU-SPORTS',
1442 'upload_date': '20140107',
1443 'timestamp': 1389118457,
1445 'skip': 'Invalid Page URL',
1449 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1450 'md5': '1aa589c675898ae6d37a17913cf68d66',
1452 'id': 'x_dtl_oa_LettermanliftPR_160608',
1454 'title': 'David Letterman: A Preview',
1455 '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.',
1456 'upload_date': '20160609',
1457 'timestamp': 1465431544,
1458 'uploader': 'NBCU-NEWS',
1463 'url': 'https://video.udn.com/news/300346',
1464 'md5': 'fd2060e988c326991037b9aff9df21a6',
1468 'title': '中一中男師變性 全校師生力挺',
1469 'thumbnail': r
're:^https?://.*\.jpg$',
1473 'skip_download': True,
1475 'expected_warnings': ['Failed to parse JSON Expecting value'],
1477 # Brightcove URL in single quotes
1479 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1480 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1482 'id': '4255764656001',
1484 'title': 'SN Presents: Russell Martin, World Citizen',
1485 '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.',
1486 'uploader': 'Rogers Sportsnet',
1487 'uploader_id': '1704050871',
1488 'upload_date': '20150525',
1489 'timestamp': 1432570283,
1494 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1498 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1499 'description': 'Migrated from OnionStudios',
1500 'thumbnail': r
're:^https?://.*\.jpe?g$',
1501 'uploader': 'clickhole',
1502 'upload_date': '20150527',
1503 'timestamp': 1432744860,
1508 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1510 'id': '74849a00-85a9-11e1-9660-123139220831',
1512 'title': '#whilewewatch',
1515 # AdobeTVVideo embed
1517 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1518 'md5': '43662b577c018ad707a63766462b1e87',
1522 'title': 'New experience with Acrobat DC',
1523 'description': 'New experience with Acrobat DC',
1524 'duration': 248.667,
1527 # BrightcoveInPageEmbed embed
1529 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1531 'id': '4238694884001',
1533 'title': 'Tabletop: Dread, Last Thoughts',
1534 'description': 'Tabletop: Dread, Last Thoughts',
1538 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1539 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1541 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1543 'id': '4785848093001',
1545 'title': 'The Cardinal Pell Interview',
1546 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1547 'uploader': 'GlobeCast Australia - GlobeStream',
1548 'uploader_id': '2733773828001',
1549 'upload_date': '20160304',
1550 'timestamp': 1457083087,
1554 'skip_download': True,
1558 # Brightcove embed with whitespace around attribute names
1559 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1561 'id': '3167554373001',
1563 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1564 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1565 'uploader_id': '1079349493',
1566 'upload_date': '20140207',
1567 'timestamp': 1391810548,
1570 'skip_download': True,
1573 # Another form of arte.tv embed
1575 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1576 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1578 'id': '030273-562_PLUS7-F',
1580 'title': 'ARTE Reportage - Nulle part, en France',
1581 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1582 'upload_date': '20160409',
1587 'url': 'http://www.wykop.pl/link/3088787/',
1588 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1590 'id': '874_1459135191',
1592 'title': 'Man shows poor quality of new apartment building',
1593 'description': 'The wall is like a sand pile.',
1594 'uploader': 'Lake8737',
1596 'add_ie': [LiveLeakIE
.ie_key()],
1598 # Another LiveLeak embed pattern (#13336)
1600 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1602 'id': '2eb_1496309988',
1604 'title': 'Thief robs place where everyone was armed',
1605 'description': 'md5:694d73ee79e535953cf2488562288eee',
1606 'uploader': 'brazilwtf',
1608 'add_ie': [LiveLeakIE
.ie_key()],
1610 # Duplicated embedded video URLs
1612 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1614 'id': '149298443_480_16c25b74_2',
1616 'title': 'vs. Blue Orange Spring Game',
1617 'uploader': 'www.hudl.com',
1620 # twitter:player:stream embed
1622 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1626 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1627 'uploader': 'www.rtl.be',
1631 'skip_download': True,
1634 # twitter:player embed
1636 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1637 'md5': 'a3e0df96369831de324f0778e126653c',
1639 'id': '4909620399001',
1641 'title': 'What Do Black Holes Sound Like?',
1642 'description': 'what do black holes sound like',
1643 'upload_date': '20160524',
1644 'uploader_id': '29913724001',
1645 'timestamp': 1464107587,
1646 'uploader': 'TheAtlantic',
1648 'add_ie': ['BrightcoveLegacy'],
1650 # Facebook <iframe> embed
1652 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1653 'md5': 'fbcde74f534176ecb015849146dd3aee',
1655 'id': '599637780109885',
1657 'title': 'Facebook video #599637780109885',
1660 # Facebook <iframe> embed, plugin video
1662 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1664 'id': '1754168231264132',
1666 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1667 'uploader': 'Tariq Ramadan (official)',
1668 'timestamp': 1496758379,
1669 'upload_date': '20170606',
1672 'skip_download': True,
1675 # Facebook API embed
1677 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1678 'md5': 'a47372ee61b39a7b90287094d447d94e',
1680 'id': '10153467542406923',
1682 'title': 'Facebook video #10153467542406923',
1685 # Wordpress "YouTube Video Importer" plugin
1687 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1688 'md5': 'd16797741b560b485194eddda8121b48',
1690 'id': 'HNTXWDXV9Is',
1692 'title': 'Blue Devils Drumline Stanford lot 2016',
1693 'upload_date': '20160627',
1694 'uploader_id': 'GENOCIDE8GENERAL10',
1695 'uploader': 'cylus cyrus',
1699 # video stored on custom kaltura server
1700 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1701 'md5': '537617d06e64dfed891fa1593c4b30cc',
1705 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1706 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1707 'uploader_id': 'videos.expansion@el-mundo.net',
1708 'upload_date': '20150429',
1709 'timestamp': 1430303472,
1711 'add_ie': ['Kaltura'],
1714 # multiple kaltura embeds, nsfw
1715 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
1717 'id': 'kamila-avec-video-jaime-sadomie',
1718 'title': "Kamila avec vídeo “J'aime sadomie”",
1720 'playlist_count': 8,
1723 # Non-standard Vimeo embed
1724 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1725 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1729 'title': 'Understanding the web - Teaser',
1730 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1731 'upload_date': '20151214',
1732 'uploader': 'OpenClassrooms',
1733 'uploader_id': 'openclassrooms',
1735 'add_ie': ['Vimeo'],
1738 # generic vimeo embed that requires original URL passed as Referer
1739 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1740 'only_matching': True,
1743 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1744 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1746 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1748 'title': 'Big Buck Bunny',
1749 'description': 'Royalty free test video',
1750 'timestamp': 1432816365,
1751 'upload_date': '20150528',
1755 'skip_download': True,
1757 'add_ie': [ArkenaIE
.ie_key()],
1760 '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/',
1764 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1767 'skip_download': True,
1769 'add_ie': [Vbox7IE
.ie_key()],
1773 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1776 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1778 'playlist_mincount': 3,
1782 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1784 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1785 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1787 'playlist_mincount': 2,
1791 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1795 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1796 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1799 'skip_download': True,
1801 'add_ie': [TwentyMinutenIE
.ie_key()],
1805 'url': 'https://en.support.wordpress.com/videopress/',
1809 'title': 'IMG_5786',
1810 'timestamp': 1435711927,
1811 'upload_date': '20150701',
1814 'skip_download': True,
1816 'add_ie': [VideoPressIE
.ie_key()],
1820 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1822 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1824 'title': 'Магаззино: Казань 2',
1825 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1826 'uploader': 'Магаззино',
1827 'upload_date': '20170228',
1828 'uploader_id': '996642',
1831 'skip_download': True,
1833 'add_ie': [RutubeIE
.ie_key()],
1836 # ThePlatform embedded with whitespaces in URLs
1837 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1838 'only_matching': True,
1841 # Senate ISVP iframe https
1842 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1843 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1845 'id': 'govtaff020316',
1847 'title': 'Integrated Senate Video Player',
1849 'add_ie': [SenateISVPIE
.ie_key()],
1852 # Limelight embeds (1 channel embed + 4 media embeds)
1853 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1855 'id': 'FacilitatorTraining2017',
1856 'title': 'Facilitator Training 2017',
1858 'playlist_mincount': 5,
1861 # Limelight embed (LimelightPlayerUtil.embed)
1862 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1864 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1866 'title': '07448641',
1867 'timestamp': 1499890639,
1868 'upload_date': '20170712',
1871 'skip_download': True,
1873 'add_ie': ['LimelightMedia'],
1876 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1878 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1879 'title': 'Standoff with Walnut Creek murder suspect ends',
1880 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1882 'playlist_mincount': 4,
1885 # WashingtonPost embed
1886 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1888 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1890 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1891 '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.',
1892 'timestamp': 1455216756,
1893 'uploader': 'The Washington Post',
1894 'upload_date': '20160211',
1896 'add_ie': [WashingtonPostIE
.ie_key()],
1900 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1904 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1907 'skip_download': True,
1909 'add_ie': [MediasetIE
.ie_key()],
1913 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1915 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1916 'title': 'Slovenskom sa prehnala vlna silných búrok',
1918 'playlist_mincount': 5,
1919 'add_ie': [JojIE
.ie_key()],
1922 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1923 'url': 'https://tvrain.ru/amp/418921/',
1924 'md5': 'cc00413936695987e8de148b67d14f1d',
1928 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1933 'url': 'http://help.vzaar.com/article/165-embedding-video',
1934 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1938 'title': 'Building A Business Online: Principal Chairs Q & A',
1942 # multiple HTML5 videos on one page
1943 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1945 'id': 'keyscenarios',
1946 'title': 'Rescue Kit 14 Free Edition - Getting started',
1948 'playlist_count': 4,
1952 'url': 'https://youtube-dlc-demo.neocities.org/vshare.html',
1953 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1956 'title': 'vl14062007715967',
1961 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1962 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1964 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1966 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1967 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1968 'timestamp': 1474354800,
1969 'upload_date': '20160920',
1973 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1977 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1978 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1979 'timestamp': 1516100691,
1980 'upload_date': '20180116',
1983 'skip_download': True,
1985 'add_ie': [SpringboardPlatformIE
.ie_key()],
1988 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1990 'id': 'uPDB5I9wfp8',
1992 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1993 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1994 'upload_date': '20160219',
1995 'uploader': 'Pocoyo - Português (BR)',
1996 'uploader_id': 'PocoyoBrazil',
1998 'add_ie': [YoutubeIE
.ie_key()],
2000 'skip_download': True,
2004 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2006 'id': 'vMDE4NzI1Mjgt690b',
2010 'add_ie': [YapFilesIE
.ie_key()],
2012 'skip_download': True,
2016 # CloudflareStream embed
2017 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2019 'id': '31c9291ab41fac05471db4e73aa11717',
2021 'title': '31c9291ab41fac05471db4e73aa11717',
2023 'add_ie': [CloudflareStreamIE
.ie_key()],
2025 'skip_download': True,
2030 'url': 'https://joinpeertube.org/fr/home/',
2033 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2035 'playlist_count': 2,
2039 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2043 'title': 'Így kell otthon hamburgert sütni',
2044 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2045 'timestamp': 1426330212,
2046 'upload_date': '20150314',
2047 'uploader': 'StreetKitchen',
2048 'uploader_id': '546363',
2050 'add_ie': [IndavideoEmbedIE
.ie_key()],
2052 'skip_download': True,
2056 # APA embed via JWPlatform embed
2057 'url': 'http://www.vol.at/blue-man-group/5593454',
2061 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2062 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2063 'thumbnail': r
're:^https?://.*\.jpg$',
2065 'timestamp': 1519211149,
2066 'upload_date': '20180221',
2069 'skip_download': True,
2073 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2074 'md5': 'b68d276de422ab07ee1d49388103f457',
2077 'title': 'Lock up and get excited',
2080 'skip': 'TODO: fix nested playlists processing in tests',
2084 'url': 'https://viqeo.tv/',
2087 'title': 'All-new video platform',
2089 'playlist_count': 6,
2092 # Squarespace video embed, 2019-08-28
2093 'url': 'http://ootboxford.com',
2095 'id': 'Tc7b_JGdZfw',
2096 'title': 'Out of the Blue, at Childish Things 10',
2098 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2099 'uploader_id': 'helendouglashouse',
2100 'uploader': 'Helen & Douglas House',
2101 'upload_date': '20140328',
2104 'skip_download': True,
2109 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2111 'id': '5b400b834b32992a310622b9',
2113 'title': 'Smoky Barbecue Favorites',
2114 'thumbnail': r
're:^https?://.*\.jpe?g',
2115 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2116 'upload_date': '20170909',
2117 'timestamp': 1504915200,
2119 'add_ie': [ZypeIE
.ie_key()],
2121 'skip_download': True,
2126 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2130 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2131 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2132 'thumbnail': r
're:^https?://.*\.jpg$',
2135 'skip_download': True,
2137 'expected_warnings': ['Failed to download MPD manifest'],
2140 # DailyMotion embed with DM.player
2141 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2143 'id': 'k6aKkGHd9FJs4mtJN39',
2145 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2146 'description': 'This video is private.',
2147 'uploader_id': 'x1jf30l',
2148 'uploader': 'beIN SPORTS USA',
2149 'upload_date': '20190528',
2150 'timestamp': 1559062971,
2153 'skip_download': True,
2157 # # TODO: find another test
2158 # # http://schema.org/VideoObject
2159 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2160 # 'md5': '888dcf08b7ea671381f00fab74692755',
2162 # 'id': 'nyvTSJMKId',
2164 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2165 # 'description': '#love for cats.',
2166 # 'timestamp': 1461244995,
2167 # 'upload_date': '20160421',
2170 # 'force_generic_extractor': True,
2175 def report_following_redirect(self
, new_url
):
2176 """Report information extraction."""
2177 self
._downloader
.to_screen('[redirect] Following redirect to %s' % new_url
)
2179 def _extract_rss(self
, url
, video_id
, doc
):
2180 playlist_title
= doc
.find('./channel/title').text
2181 playlist_desc_el
= doc
.find('./channel/description')
2182 playlist_desc
= None if playlist_desc_el
is None else playlist_desc_el
.text
2185 for it
in doc
.findall('./channel/item'):
2187 enclosure_nodes
= it
.findall('./enclosure')
2188 for e
in enclosure_nodes
:
2189 next_url
= e
.attrib
.get('url')
2194 next_url
= xpath_text(it
, 'link', fatal
=False)
2200 '_type': 'url_transparent',
2202 'title': it
.find('title').text
,
2206 '_type': 'playlist',
2208 'title': playlist_title
,
2209 'description': playlist_desc
,
2213 def _extract_camtasia(self
, url
, video_id
, webpage
):
2214 """ Returns None if no camtasia video can be found. """
2216 camtasia_cfg
= self
._search
_regex
(
2217 r
'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2218 webpage
, 'camtasia configuration file', default
=None)
2219 if camtasia_cfg
is None:
2222 title
= self
._html
_search
_meta
('DC.title', webpage
, fatal
=True)
2224 camtasia_url
= compat_urlparse
.urljoin(url
, camtasia_cfg
)
2225 camtasia_cfg
= self
._download
_xml
(
2226 camtasia_url
, video_id
,
2227 note
='Downloading camtasia configuration',
2228 errnote
='Failed to download camtasia configuration')
2229 fileset_node
= camtasia_cfg
.find('./playlist/array/fileset')
2232 for n
in fileset_node
.getchildren():
2233 url_n
= n
.find('./uri')
2238 'id': os
.path
.splitext(url_n
.text
.rpartition('/')[2])[0],
2239 'title': '%s - %s' % (title
, n
.tag
),
2240 'url': compat_urlparse
.urljoin(url
, url_n
.text
),
2241 'duration': float_or_none(n
.find('./duration').text
),
2245 '_type': 'playlist',
2250 def _real_extract(self
, url
):
2251 if url
.startswith('//'):
2252 return self
.url_result(self
.http_scheme() + url
)
2254 parsed_url
= compat_urlparse
.urlparse(url
)
2255 if not parsed_url
.scheme
:
2256 default_search
= self
._downloader
.params
.get('default_search')
2257 if default_search
is None:
2258 default_search
= 'fixup_error'
2260 if default_search
in ('auto', 'auto_warning', 'fixup_error'):
2261 if re
.match(r
'^[^\s/]+\.[^\s/]+/', url
):
2262 self
._downloader
.report_warning('The url doesn\'t specify the protocol, trying with http')
2263 return self
.url_result('http://' + url
)
2264 elif default_search
!= 'fixup_error':
2265 if default_search
== 'auto_warning':
2266 if re
.match(r
'^(?:url|URL)$', url
):
2267 raise ExtractorError(
2268 'Invalid URL: %r . Call youtube-dlc like this: youtube-dlc -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url
,
2271 self
._downloader
.report_warning(
2272 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url
)
2273 return self
.url_result('ytsearch:' + url
)
2275 if default_search
in ('error', 'fixup_error'):
2276 raise ExtractorError(
2277 '%r is not a valid URL. '
2278 'Set --default-search "ytsearch" (or run youtube-dlc "ytsearch:%s" ) to search YouTube'
2279 % (url
, url
), expected
=True)
2281 if ':' not in default_search
:
2282 default_search
+= ':'
2283 return self
.url_result(default_search
+ url
)
2285 url
, smuggled_data
= unsmuggle_url(url
)
2286 force_videoid
= None
2287 is_intentional
= smuggled_data
and smuggled_data
.get('to_generic')
2288 if smuggled_data
and 'force_videoid' in smuggled_data
:
2289 force_videoid
= smuggled_data
['force_videoid']
2290 video_id
= force_videoid
2292 video_id
= self
._generic
_id
(url
)
2294 self
.to_screen('%s: Requesting header' % video_id
)
2296 head_req
= HEADRequest(url
)
2297 head_response
= self
._request
_webpage
(
2299 note
=False, errnote
='Could not send HEAD request to %s' % url
,
2302 if head_response
is not False:
2303 # Check for redirect
2304 new_url
= head_response
.geturl()
2306 self
.report_following_redirect(new_url
)
2308 new_url
= smuggle_url(
2309 new_url
, {'force_videoid': force_videoid}
)
2310 return self
.url_result(new_url
)
2312 full_response
= None
2313 if head_response
is False:
2314 request
= sanitized_Request(url
)
2315 request
.add_header('Accept-Encoding', '*')
2316 full_response
= self
._request
_webpage
(request
, video_id
)
2317 head_response
= full_response
2321 'title': self
._generic
_title
(url
),
2322 'upload_date': unified_strdate(head_response
.headers
.get('Last-Modified'))
2325 # Check for direct link to a video
2326 content_type
= head_response
.headers
.get('Content-Type', '').lower()
2327 m
= re
.match(r
'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type
)
2329 format_id
= compat_str(m
.group('format_id'))
2330 if format_id
.endswith('mpegurl'):
2331 formats
= self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
2332 elif format_id
== 'f4m':
2333 formats
= self
._extract
_f
4m
_formats
(url
, video_id
)
2336 'format_id': format_id
,
2338 'vcodec': 'none' if m
.group('type') == 'audio' else None
2340 info_dict
['direct'] = True
2341 self
._sort
_formats
(formats
)
2342 info_dict
['formats'] = formats
2345 if not self
._downloader
.params
.get('test', False) and not is_intentional
:
2346 force
= self
._downloader
.params
.get('force_generic_extractor', False)
2347 self
._downloader
.report_warning(
2348 '%s on generic information extractor.' % ('Forcing' if force
else 'Falling back'))
2350 if not full_response
:
2351 request
= sanitized_Request(url
)
2352 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2353 # making it impossible to download only chunk of the file (yet we need only 512kB to
2354 # test whether it's HTML or not). According to youtube-dlc default Accept-Encoding
2355 # that will always result in downloading the whole file that is not desirable.
2356 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2357 # to accept raw bytes and being able to download only a chunk.
2358 # It may probably better to solve this by checking Content-Type for application/octet-stream
2359 # after HEAD request finishes, but not sure if we can rely on this.
2360 request
.add_header('Accept-Encoding', '*')
2361 full_response
= self
._request
_webpage
(request
, video_id
)
2363 first_bytes
= full_response
.read(512)
2365 # Is it an M3U playlist?
2366 if first_bytes
.startswith(b
'#EXTM3U'):
2367 info_dict
['formats'] = self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
2368 self
._sort
_formats
(info_dict
['formats'])
2371 # Maybe it's a direct link to a video?
2372 # Be careful not to download the whole thing!
2373 if not is_html(first_bytes
):
2374 self
._downloader
.report_warning(
2375 'URL could be a direct video link, returning it as such.')
2382 webpage
= self
._webpage
_read
_content
(
2383 full_response
, url
, video_id
, prefix
=first_bytes
)
2385 self
.report_extraction(video_id
)
2387 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2389 doc
= compat_etree_fromstring(webpage
.encode('utf-8'))
2390 if doc
.tag
== 'rss':
2391 return self
._extract
_rss
(url
, video_id
, doc
)
2392 elif doc
.tag
== 'SmoothStreamingMedia':
2393 info_dict
['formats'] = self
._parse
_ism
_formats
(doc
, url
)
2394 self
._sort
_formats
(info_dict
['formats'])
2396 elif re
.match(r
'^(?:{[^}]+})?smil$', doc
.tag
):
2397 smil
= self
._parse
_smil
(doc
, url
, video_id
)
2398 self
._sort
_formats
(smil
['formats'])
2400 elif doc
.tag
== '{http://xspf.org/ns/0/}playlist':
2401 return self
.playlist_result(
2403 doc
, video_id
, xspf_url
=url
,
2404 xspf_base_url
=full_response
.geturl()),
2406 elif re
.match(r
'(?i)^(?:{[^}]+})?MPD$', doc
.tag
):
2407 info_dict
['formats'] = self
._parse
_mpd
_formats
(
2409 mpd_base_url
=full_response
.geturl().rpartition('/')[0],
2411 self
._sort
_formats
(info_dict
['formats'])
2413 elif re
.match(r
'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc
.tag
):
2414 info_dict
['formats'] = self
._parse
_f
4m
_formats
(doc
, url
, video_id
)
2415 self
._sort
_formats
(info_dict
['formats'])
2417 except compat_xml_parse_error
:
2420 # Is it a Camtasia project?
2421 camtasia_res
= self
._extract
_camtasia
(url
, video_id
, webpage
)
2422 if camtasia_res
is not None:
2425 # Sometimes embedded video player is hidden behind percent encoding
2426 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2427 # Unescaping the whole page allows to handle those cases in a generic way
2428 webpage
= compat_urllib_parse_unquote(webpage
)
2430 # Unescape squarespace embeds to be detected by generic extractor,
2431 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2433 r
'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2434 lambda x
: unescapeHTML(x
.group(0)), webpage
)
2436 # it's tempting to parse this further, but you would
2437 # have to take into account all the variations like
2438 # Video Title - Site Name
2439 # Site Name | Video Title
2440 # Video Title - Tagline | Site Name
2441 # and so on and so forth; it's just not practical
2442 video_title
= self
._og
_search
_title
(
2443 webpage
, default
=None) or self
._html
_search
_regex
(
2444 r
'(?s)<title>(.*?)</title>', webpage
, 'video title',
2447 # Try to detect age limit automatically
2448 age_limit
= self
._rta
_search
(webpage
)
2449 # And then there are the jokers who advertise that they use RTA,
2450 # but actually don't.
2451 AGE_LIMIT_MARKERS
= [
2452 r
'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2454 if any(re
.search(marker
, webpage
) for marker
in AGE_LIMIT_MARKERS
):
2457 # video uploader is domain name
2458 video_uploader
= self
._search
_regex
(
2459 r
'^(?:https?://)?([^/]*)/.*', url
, 'video uploader')
2461 video_description
= self
._og
_search
_description
(webpage
, default
=None)
2462 video_thumbnail
= self
._og
_search
_thumbnail
(webpage
, default
=None)
2465 'title': video_title
,
2466 'description': video_description
,
2467 'thumbnail': video_thumbnail
,
2468 'age_limit': age_limit
,
2471 # Look for Brightcove Legacy Studio embeds
2472 bc_urls
= BrightcoveLegacyIE
._extract
_brightcove
_urls
(webpage
)
2476 'url': smuggle_url(bc_url
, {'Referer': url}
),
2477 'ie_key': 'BrightcoveLegacy'
2478 } for bc_url
in bc_urls
]
2481 '_type': 'playlist',
2482 'title': video_title
,
2487 # Look for Brightcove New Studio embeds
2488 bc_urls
= BrightcoveNewIE
._extract
_urls
(self
, webpage
)
2490 return self
.playlist_from_matches(
2491 bc_urls
, video_id
, video_title
,
2492 getter
=lambda x
: smuggle_url(x
, {'referrer': url}
),
2495 # Look for Nexx embeds
2496 nexx_urls
= NexxIE
._extract
_urls
(webpage
)
2498 return self
.playlist_from_matches(nexx_urls
, video_id
, video_title
, ie
=NexxIE
.ie_key())
2500 # Look for Nexx iFrame embeds
2501 nexx_embed_urls
= NexxEmbedIE
._extract
_urls
(webpage
)
2503 return self
.playlist_from_matches(nexx_embed_urls
, video_id
, video_title
, ie
=NexxEmbedIE
.ie_key())
2505 # Look for ThePlatform embeds
2506 tp_urls
= ThePlatformIE
._extract
_urls
(webpage
)
2508 return self
.playlist_from_matches(tp_urls
, video_id
, video_title
, ie
='ThePlatform')
2510 # Look for embedded rtl.nl player
2511 matches
= re
.findall(
2512 r
'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2515 return self
.playlist_from_matches(matches
, video_id
, video_title
, ie
='RtlNl')
2517 vimeo_urls
= VimeoIE
._extract
_urls
(url
, webpage
)
2519 return self
.playlist_from_matches(vimeo_urls
, video_id
, video_title
, ie
=VimeoIE
.ie_key())
2521 vid_me_embed_url
= self
._search
_regex
(
2522 r
'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2523 webpage, 'vid.me embed', default=None)
2524 if vid_me_embed_url is not None:
2525 return self.url_result(vid_me_embed_url, 'Vidme')
2527 # Look for YouTube embeds
2528 youtube_urls = YoutubeIE._extract_urls(webpage)
2530 return self.playlist_from_matches(
2531 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2533 matches = DailymotionIE._extract_urls(webpage)
2535 return self.playlist_from_matches(matches, video_id, video_title)
2537 # Look for embedded Dailymotion playlist player (#3822)
2539 r'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:www\
.)?dailymotion\
.[a
-z
]{2,3}
/widget
/jukebox
\?.+?
)\
1', webpage)
2541 playlists = re.findall(
2542 r'list\
[\
]=/playlist
/([^
/]+)/', unescapeHTML(m.group('url
')))
2544 return self.playlist_from_matches(
2545 playlists, video_id, video_title, lambda p: '//dailymotion
.com
/playlist
/%s' % p)
2547 # Look for DailyMail embeds
2548 dailymail_urls = DailyMailIE._extract_urls(webpage)
2550 return self.playlist_from_matches(
2551 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2553 # Look for Teachable embeds, must be before Wistia
2554 teachable_url = TeachableIE._extract_url(webpage, url)
2556 return self.url_result(teachable_url)
2558 # Look for embedded Wistia player
2559 wistia_urls = WistiaIE._extract_urls(webpage)
2561 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2562 for entry in playlist['entries
']:
2564 '_type
': 'url_transparent
',
2565 'uploader
': video_uploader,
2569 # Look for SVT player
2570 svt_url = SVTIE._extract_url(webpage)
2572 return self.url_result(svt_url, 'SVT
')
2574 # Look for Bandcamp pages with custom domain
2575 mobj = re.search(r'<meta
property="og:url"[^
>]*?content
="(.*?bandcamp\.com.*?)"', webpage)
2576 if mobj is not None:
2577 burl = unescapeHTML(mobj.group(1))
2578 # Don't
set the extractor because it can be a track url
or an album
2579 return self
.url_result(burl
)
2581 # Look for embedded Vevo player
2583 r
'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:cache\
.)?vevo\
.com
/.+?
)\
1', webpage)
2584 if mobj is not None:
2585 return self.url_result(mobj.group('url
'))
2587 # Look for embedded Viddler player
2589 r'<(?
:iframe
[^
>]+?src|param
[^
>]+?value
)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2591 if mobj is not None:
2592 return self.url_result(mobj.group('url'))
2594 # Look for NYTimes player
2596 r'<iframe[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//graphics8\
.nytimes\
.com
/bcvideo
/[^
/]+/iframe
/embed\
.html
.+?
)\
1>',
2598 if mobj is not None:
2599 return self.url_result(mobj.group('url
'))
2601 # Look for Libsyn player
2603 r'<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2604 if mobj is not None:
2605 return self.url_result(mobj.group('url'))
2607 # Look for Ooyala videos
2608 mobj = (re.search(r'player\.ooyala\.com/[^"?
]+[?
#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2609 or re
.search(r
'OO\.Player\.create\([\'"].*?[\'"],\s
*[\'"](?P<ec>.{32})[\'"]', webpage)
2610 or re.search(r'OO\
.Player\
.create\
.apply\
(\s
*OO\
.Player\s
*,\s
*op\
(\s
*\
[\s
*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P
<ec
>.{32}
)[\'"]', webpage)
2611 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P
<ec
>.{32}
)[\'"]\)', webpage)
2612 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P
<ec
>.{32}
)[\'"]', webpage))
2613 if mobj is not None:
2614 embed_token = self._search_regex(
2615 r'embedToken[\'"]?\s
*:\s
*[\'"]([^\'"]+)',
2616 webpage, 'ooyala embed token
', default=None)
2617 return OoyalaIE._build_url_result(smuggle_url(
2620 'embed_token
': embed_token,
2623 # Look for multiple Ooyala embeds on SBN network websites
2624 mobj = re.search(r'SBN\
.VideoLinkset\
.entryGroup\
((\
[.*?\
])', webpage)
2625 if mobj is not None:
2626 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2628 return self.playlist_from_matches(
2629 embeds, video_id, video_title,
2630 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id
'], {'domain': url})), ie='Ooyala
')
2632 # Look for Aparat videos
2633 mobj = re.search(r'<iframe
.*?src
="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2634 if mobj is not None:
2635 return self.url_result(mobj.group(1), 'Aparat')
2637 # Look for MPORA videos
2638 mobj = re.search(r'<iframe .*?src="(http
://mpora\
.(?
:com|de
)/videos
/[^
"]+)"', webpage)
2639 if mobj is not None:
2640 return self.url_result(mobj.group(1), 'Mpora
')
2642 # Look for embedded Facebook player
2643 facebook_urls = FacebookIE._extract_urls(webpage)
2645 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2647 # Look for embedded VK player
2648 mobj = re.search(r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2649 if mobj is not None:
2650 return self.url_result(mobj.group('url'), 'VK')
2652 # Look for embedded Odnoklassniki player
2653 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2654 if odnoklassniki_url:
2655 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2657 # Look for embedded ivi player
2658 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P
<url
>https?
://(?
:www\
.)?ivi\
.ru
/video
/player
.+?
)\
1', webpage)
2659 if mobj is not None:
2660 return self.url_result(mobj.group('url
'), 'Ivi
')
2662 # Look for embedded Huffington Post player
2664 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2665 if mobj is not None:
2666 return self.url_result(mobj.group('url'), 'HuffPost')
2669 mobj = re.search(r'class=["\']embedly
-card
["\'][^>]href=["\'](?P
<url
>[^
"\']+)', webpage)
2670 if mobj is not None:
2671 return self.url_result(mobj.group('url'))
2672 mobj = re.search(r'class=["\']embedly
-embed
["\'][^>]src=["\'][^
"\']*url=(?P<url>[^&]+)', webpage)
2673 if mobj is not None:
2674 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2676 # Look for funnyordie embed
2677 matches = re.findall(r'<iframe[^>]+?src="(https?
://(?
:www\
.)?funnyordie\
.com
/embed
/[^
"]+)"', webpage)
2679 return self.playlist_from_matches(
2680 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie
')
2682 # Look for BBC iPlayer embed
2683 matches = re.findall(r'setPlaylist\
("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\
)', webpage)
2685 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk
')
2687 # Look for embedded RUTV player
2688 rutv_url = RUTVIE._extract_url(webpage)
2690 return self.url_result(rutv_url, 'RUTV
')
2692 # Look for embedded TVC player
2693 tvc_url = TVCIE._extract_url(webpage)
2695 return self.url_result(tvc_url, 'TVC
')
2697 # Look for embedded SportBox player
2698 sportbox_urls = SportBoxIE._extract_urls(webpage)
2700 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2702 # Look for embedded XHamster player
2703 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2705 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed
')
2707 # Look for embedded TNAFlixNetwork player
2708 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2710 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2712 # Look for embedded PornHub player
2713 pornhub_urls = PornHubIE._extract_urls(webpage)
2715 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2717 # Look for embedded DrTuber player
2718 drtuber_urls = DrTuberIE._extract_urls(webpage)
2720 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2722 # Look for embedded RedTube player
2723 redtube_urls = RedTubeIE._extract_urls(webpage)
2725 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2727 # Look for embedded Tube8 player
2728 tube8_urls = Tube8IE._extract_urls(webpage)
2730 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2732 # Look for embedded Mofosex player
2733 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
2735 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
2737 # Look for embedded Spankwire player
2738 spankwire_urls = SpankwireIE._extract_urls(webpage)
2740 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
2742 # Look for embedded YouPorn player
2743 youporn_urls = YouPornIE._extract_urls(webpage)
2745 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
2747 # Look for embedded Tvigle player
2749 r'<iframe
[^
>]+?src
=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2750 if mobj is not None:
2751 return self.url_result(mobj.group('url'), 'Tvigle')
2753 # Look for embedded TED player
2755 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://embed(?
:-ssl
)?\
.ted\
.com
/.+?
)\
1', webpage)
2756 if mobj is not None:
2757 return self.url_result(mobj.group('url
'), 'TED
')
2759 # Look for embedded Ustream videos
2760 ustream_url = UstreamIE._extract_url(webpage)
2762 return self.url_result(ustream_url, UstreamIE.ie_key())
2764 # Look for embedded arte.tv player
2765 arte_urls = ArteTVEmbedIE._extract_urls(webpage)
2767 return self.playlist_from_matches(arte_urls, video_id, video_title)
2769 # Look for embedded francetv player
2771 r'<iframe
[^
>]+?src
=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2773 if mobj is not None:
2774 return self.url_result(mobj.group('url'))
2776 # Look for embedded smotri.com player
2777 smotri_url = SmotriIE._extract_url(webpage)
2779 return self.url_result(smotri_url, 'Smotri')
2781 # Look for embedded Myvi.ru player
2782 myvi_url = MyviIE._extract_url(webpage)
2784 return self.url_result(myvi_url)
2786 # Look for embedded soundcloud player
2787 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
2789 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
2791 # Look for tunein player
2792 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2794 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2796 # Look for embedded mtvservices player
2797 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2799 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2801 # Look for embedded yahoo player
2803 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://(?
:screen|movies
)\
.yahoo\
.com
/.+?\
.html
\?format
=embed
)\
1',
2805 if mobj is not None:
2806 return self.url_result(mobj.group('url
'), 'Yahoo
')
2808 # Look for embedded sbs.com.au player
2812 <meta\s+property="og:video"\s+content=|
2815 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2817 if mobj is not None:
2818 return self.url_result(mobj.group('url
'), 'SBS
')
2820 # Look for embedded Cinchcast player
2822 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2824 if mobj is not None:
2825 return self.url_result(mobj.group('url'), 'Cinchcast')
2828 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://m(?
:lb
)?\
.mlb\
.com
/shared
/video
/embed
/embed\
.html
\?.+?
)\
1',
2832 r'data
-video
-link
=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2834 if mobj is not None:
2835 return self.url_result(mobj.group('url
'), 'MLB
')
2838 r'<(?
:iframe|script
)[^
>]+?src
=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2840 if mobj is not None:
2841 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2844 r'<iframe[^>]+src="(?P
<url
>https?
://(?
:new\
.)?livestream\
.com
/[^
"]+/player[^"]+)"',
2846 if mobj is not None:
2847 return self.url_result(mobj.group('url'), 'Livestream')
2849 # Look for Zapiks embed
2851 r'<iframe[^>]+src="(?P
<url
>https?
://(?
:www\
.)?zapiks\
.fr
/index\
.php
\?.+?
)"', webpage)
2852 if mobj is not None:
2853 return self.url_result(mobj.group('url'), 'Zapiks')
2855 # Look for Kaltura embeds
2856 kaltura_urls = KalturaIE._extract_urls(webpage)
2858 return self.playlist_from_matches(
2859 kaltura_urls, video_id, video_title,
2860 getter=lambda x: smuggle_url(x, {'source_url': url}),
2861 ie=KalturaIE.ie_key())
2863 # Look for EaglePlatform embeds
2864 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2865 if eagleplatform_url:
2866 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2868 # Look for ClipYou (uses EaglePlatform) embeds
2870 r'<iframe[^>]+src="https?
://(?P
<host
>media\
.clipyou\
.ru
)/index
/player
\?.*\brecord
_id
=(?P
<id>\d
+).*"', webpage)
2871 if mobj is not None:
2872 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2874 # Look for Pladform embeds
2875 pladform_url = PladformIE._extract_url(webpage)
2877 return self.url_result(pladform_url)
2879 # Look for Videomore embeds
2880 videomore_url = VideomoreIE._extract_url(webpage)
2882 return self.url_result(videomore_url)
2884 # Look for Webcaster embeds
2885 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2887 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2889 # Look for Playwire embeds
2891 r'<script[^>]+data-config=(["\'])(?P
<url
>(?
:https?
:)?
//config\
.playwire\
.com
/.+?
)\
1', webpage)
2892 if mobj is not None:
2893 return self.url_result(mobj.group('url
'))
2895 # Look for 5min embeds
2897 r'<meta
[^
>]+property="og:video"[^
>]+content
="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2898 if mobj is not None:
2899 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2901 # Look for Crooks and Liars embeds
2903 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P
<url
>(?
:https?
:)?
//embed\
.crooksandliars\
.com
/(?
:embed|v
)/.+?
)\
1', webpage)
2904 if mobj is not None:
2905 return self.url_result(mobj.group('url
'))
2907 # Look for NBC Sports VPlayer embeds
2908 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2910 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer
')
2912 # Look for NBC News embeds
2913 nbc_news_embed_url = re.search(
2914 r'<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\
1', webpage)
2915 if nbc_news_embed_url:
2916 return self.url_result(nbc_news_embed_url.group('url
'), 'NBCNews
')
2918 # Look for Google Drive embeds
2919 google_drive_url = GoogleDriveIE._extract_url(webpage)
2920 if google_drive_url:
2921 return self.url_result(google_drive_url, 'GoogleDrive
')
2923 # Look for UDN embeds
2925 r'<iframe
[^
>]+src
="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2926 if mobj is not None:
2927 return self.url_result(
2928 compat_urlparse.urljoin(url, mobj.group('url
')), 'UDNEmbed
')
2930 # Look for Senate ISVP iframe
2931 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2933 return self.url_result(senate_isvp_url, 'SenateISVP
')
2935 # Look for Kinja embeds
2936 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
2937 if kinja_embed_urls:
2938 return self.playlist_from_matches(
2939 kinja_embed_urls, video_id, video_title)
2941 # Look for OnionStudios embeds
2942 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2943 if onionstudios_url:
2944 return self.url_result(onionstudios_url)
2946 # Look for ViewLift embeds
2947 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2949 return self.url_result(viewlift_url)
2951 # Look for JWPlatform embeds
2952 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2954 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2956 # Look for Digiteka embeds
2957 digiteka_url = DigitekaIE._extract_url(webpage)
2959 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2961 # Look for Arkena embeds
2962 arkena_url = ArkenaIE._extract_url(webpage)
2964 return self.url_result(arkena_url, ArkenaIE.ie_key())
2966 # Look for Piksel embeds
2967 piksel_url = PikselIE._extract_url(webpage)
2969 return self.url_result(piksel_url, PikselIE.ie_key())
2971 # Look for Limelight embeds
2972 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2974 return self.playlist_result(
2975 limelight_urls, video_id, video_title, video_description)
2977 # Look for Anvato embeds
2978 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2980 return self.playlist_result(
2981 anvato_urls, video_id, video_title, video_description)
2983 # Look for AdobeTVVideo embeds
2985 r'<iframe
[^
>]+src
=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2987 if mobj is not None:
2988 return self.url_result(
2989 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2992 # Look for Vine embeds
2994 r'<iframe[^>]+src=[\'"]((?
:https?
:)?
//(?
:www\
.)?vine\
.co
/v
/[^
/]+/embed
/(?
:simple|postcard
))',
2996 if mobj is not None:
2997 return self.url_result(
2998 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine
')
3000 # Look for VODPlatform embeds
3002 r'<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
3004 if mobj is not None:
3005 return self.url_result(
3006 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
3008 # Look for Mangomolo embeds
3010 r'''(?x)<iframe[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//
3012 admin\
.mangomolo\
.com
/analytics
/index\
.php
/customers
/embed|
3013 player\
.mangomolo\
.com
/v1
3016 video
\?.*?
\bid
=(?P
<video_id
>\d
+)|
3017 (?
:index|live
)\?.*?
\bchannelid
=(?P
<channel_id
>(?
:[A
-Za
-z0
-9+/=]|
%2B|
%2F|
%3D
)+)
3018 ).+?
)\
1''', webpage)
3019 if mobj is not None:
3021 '_type': 'url_transparent',
3022 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3023 'title': video_title,
3024 'description': video_description,
3025 'thumbnail': video_thumbnail,
3026 'uploader': video_uploader,
3028 video_id = mobj.group('video_id')
3031 'ie_key': 'MangomoloVideo',
3036 'ie_key': 'MangomoloLive',
3037 'id': mobj.group('channel_id'),
3041 # Look for Instagram embeds
3042 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3043 if instagram_embed_url is not None:
3044 return self.url_result(
3045 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3047 # Look for LiveLeak embeds
3048 liveleak_urls = LiveLeakIE._extract_urls(webpage)
3050 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
3052 # Look for 3Q SDN embeds
3053 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3056 '_type': 'url_transparent',
3057 'ie_key': ThreeQSDNIE.ie_key(),
3058 'url': self._proto_relative_url(threeqsdn_url),
3059 'title': video_title,
3060 'description': video_description,
3061 'thumbnail': video_thumbnail,
3062 'uploader': video_uploader,
3065 # Look for VBOX7 embeds
3066 vbox7_url = Vbox7IE._extract_url(webpage)
3068 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3070 # Look for DBTV embeds
3071 dbtv_urls = DBTVIE._extract_urls(webpage)
3073 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3075 # Look for Videa embeds
3076 videa_urls = VideaIE._extract_urls(webpage)
3078 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3080 # Look for 20 minuten embeds
3081 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3083 return self.playlist_from_matches(
3084 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3086 # Look for VideoPress embeds
3087 videopress_urls = VideoPressIE._extract_urls(webpage)
3089 return self.playlist_from_matches(
3090 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3092 # Look for Rutube embeds
3093 rutube_urls = RutubeIE._extract_urls(webpage)
3095 return self.playlist_from_matches(
3096 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3098 # Look for WashingtonPost embeds
3099 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3101 return self.playlist_from_matches(
3102 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3104 # Look for Mediaset embeds
3105 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3107 return self.playlist_from_matches(
3108 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3110 # Look for JOJ.sk embeds
3111 joj_urls = JojIE._extract_urls(webpage)
3113 return self.playlist_from_matches(
3114 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3116 # Look for megaphone.fm embeds
3117 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3119 return self.playlist_from_matches(
3120 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3122 # Look for vzaar embeds
3123 vzaar_urls = VzaarIE._extract_urls(webpage)
3125 return self.playlist_from_matches(
3126 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3128 channel9_urls = Channel9IE._extract_urls(webpage)
3130 return self.playlist_from_matches(
3131 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3133 vshare_urls = VShareIE._extract_urls(webpage)
3135 return self.playlist_from_matches(
3136 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3138 # Look for Mediasite embeds
3139 mediasite_urls = MediasiteIE._extract_urls(webpage)
3142 self.url_result(smuggle_url(
3143 compat_urlparse.urljoin(url, mediasite_url),
3144 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3145 for mediasite_url in mediasite_urls]
3146 return self.playlist_result(entries, video_id, video_title)
3148 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3149 if springboardplatform_urls:
3150 return self.playlist_from_matches(
3151 springboardplatform_urls, video_id, video_title,
3152 ie=SpringboardPlatformIE.ie_key())
3154 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3156 return self.playlist_from_matches(
3157 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3159 vice_urls = ViceIE._extract_urls(webpage)
3161 return self.playlist_from_matches(
3162 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3164 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3166 return self.playlist_from_matches(
3167 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3169 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3170 if cloudflarestream_urls:
3171 return self.playlist_from_matches(
3172 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3174 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3176 return self.playlist_from_matches(
3177 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3179 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3181 return self.playlist_from_matches(
3182 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3184 apa_urls = APAIE._extract_urls(webpage)
3186 return self.playlist_from_matches(
3187 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3189 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3191 return self.playlist_from_matches(
3192 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3194 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3195 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3197 if sharevideos_urls:
3198 return self.playlist_from_matches(
3199 sharevideos_urls, video_id, video_title)
3201 viqeo_urls = ViqeoIE._extract_urls(webpage)
3203 return self.playlist_from_matches(
3204 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3206 expressen_urls = ExpressenIE._extract_urls(webpage)
3208 return self.playlist_from_matches(
3209 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3211 zype_urls = ZypeIE._extract_urls(webpage)
3213 return self.playlist_from_matches(
3214 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3216 bitchute_urls = BitChuteIE._extract_urls(webpage)
3218 return self.playlist_from_matches(
3219 bitchute_urls, video_id, video_title, ie=BitChuteIE.ie_key())
3221 # Look for HTML5 media
3222 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3224 if len(entries) == 1:
3227 'title': video_title,
3230 for num, entry in enumerate(entries, start=1):
3232 'id': '%s-%s' % (video_id, num),
3233 'title': '%s (%d)' % (video_title, num),
3235 for entry in entries:
3236 self._sort_formats(entry['formats'])
3237 return self.playlist_result(entries, video_id, video_title)
3239 jwplayer_data = self._find_jwplayer_data(
3240 webpage, video_id, transform_source=js_to_json)
3243 info = self._parse_jwplayer_data(
3244 jwplayer_data, video_id, require_title=False, base_url=url)
3245 return merge_dicts(info, info_dict)
3246 except ExtractorError:
3247 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3252 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3254 if mobj is not None:
3255 sources = self._parse_json(
3256 mobj.group(1), video_id, transform_source=js_to_json,
3258 if not isinstance(sources, list):
3261 for source in sources:
3262 src = source.get('src')
3263 if not src or not isinstance(src, compat_str):
3265 src = compat_urlparse.urljoin(url, src)
3266 src_type = source.get('type')
3267 if isinstance(src_type, compat_str):
3268 src_type = src_type.lower()
3269 ext = determine_ext(src).lower()
3270 if src_type == 'video/youtube':
3271 return self.url_result(src, YoutubeIE.ie_key())
3272 if src_type == 'application/dash+xml' or ext == 'mpd':
3273 formats.extend(self._extract_mpd_formats(
3274 src, video_id, mpd_id='dash', fatal=False))
3275 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3276 formats.extend(self._extract_m3u8_formats(
3277 src, video_id, 'mp4', entry_protocol='m3u8_native',
3278 m3u8_id='hls', fatal=False))
3282 'ext': (mimetype2ext(src_type)
3283 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3286 self._sort_formats(formats)
3287 info_dict['formats'] = formats
3290 # Looking for http://schema.org/VideoObject
3291 json_ld = self._search_json_ld(
3292 webpage, video_id, default={}, expected_type='VideoObject')
3293 if json_ld.get('url'):
3294 return merge_dicts(json_ld, info_dict)
3296 def check_video(vurl):
3297 if YoutubeIE.suitable(vurl):
3299 if RtmpIE.suitable(vurl):
3301 vpath = compat_urlparse.urlparse(vurl).path
3302 vext = determine_ext(vpath)
3303 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3305 def filter_video(urls):
3306 return list(filter(check_video, urls))
3308 # Start with something easy: JW Player in SWFObject
3309 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3311 # Look for gorilla-vid style embedding
3312 found = filter_video(re.findall(r'''(?sx
)
3316 jwplayer\s
*\
(\s
*["'][^'"]+["']\s*\)\s*\.setup
3319 ['"]?
file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3321 # Broaden the search a little bit
3322 found = filter_video(re.findall(r'[^A
-Za
-z0
-9]?
(?
:file|source
)=(http
[^
\'"&]*)', webpage))
3324 # Broaden the findall a little bit: JWPlayer JS loader
3325 found = filter_video(re.findall(
3326 r'[^A-Za-z0-9]?(?:file|video_url)["\']?
:\s
*["\'](http(?![^\'"]+\
.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3329 found = filter_video(re.findall(r'''(?xs)
3330 flowplayer\("[^
"]+",\s
*
3332 \s
*\{[^}
]+?
["']?clip["']?\s*:\s*\{\s*
3333 ["']?url
["']?\s*:\s*["']([^"']+)["']
3338 r"cinerama\
.embedPlayer\
(\s
*\'[^
']+\',\s*'([^
']+)'", webpage)
3340 # Try to find twitter cards info
3341 # twitter:player:stream should be checked before twitter:player since
3342 # it is expected to contain a raw stream (see
3343 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3344 found = filter_video(re.findall(
3345 r'<meta (?:property|name)="twitter
:player
:stream
" (?:content|value)="(.+?
)"', webpage))
3347 # We look for Open Graph info:
3348 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3349 m_video_type = re.findall(r'<meta.*?property="og
:video
:type".*?content="video
/(.*?
)"', webpage)
3350 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3351 if m_video_type is not None:
3352 found = filter_video(re.findall(r'<meta.*?property="og
:video
".*?content="(.*?
)"', webpage))
3354 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3356 r'(?i
)<meta\s
+(?
=(?
:[a
-z
-]+="[^"]+"\s+)*http-equiv="refresh
")'
3357 r'(?:[a-z-]+="[^
"]+"\s
+)*?content
="%s' % REDIRECT_REGEX,
3360 # Look also in Refresh HTTP header
3361 refresh_header = head_response.headers.get('Refresh')
3363 # In python 2 response HTTP headers are bytestrings
3364 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3365 refresh_header = refresh_header.decode('iso-8859-1')
3366 found = re.search(REDIRECT_REGEX, refresh_header)
3368 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3370 self.report_following_redirect(new_url)
3379 # twitter:player is a https URL to iframe player that may or may not
3380 # be supported by youtube-dlc thus this is checked the very last (see
3381 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3382 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3383 if embed_url and embed_url != url:
3384 return self.url_result(embed_url)
3387 raise UnsupportedError(url)
3390 for video_url in orderedSet(found):
3391 video_url = unescapeHTML(video_url)
3392 video_url = video_url.replace('\\/', '/')
3393 video_url = compat_urlparse.urljoin(url, video_url)
3394 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3396 # Sometimes, jwplayer extraction will result in a YouTube URL
3397 if YoutubeIE.suitable(video_url):
3398 entries.append(self.url_result(video_url, 'Youtube'))
3401 # here's a fun little line of code for you:
3402 video_id = os.path.splitext(video_id)[0]
3406 'uploader': video_uploader,
3407 'title': video_title,
3408 'age_limit': age_limit,
3411 if RtmpIE.suitable(video_url):
3412 entry_info_dict.update({
3413 '_type': 'url_transparent',
3414 'ie_key': RtmpIE.ie_key(),
3417 entries.append(entry_info_dict)
3420 ext = determine_ext(video_url)
3422 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3424 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3426 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3428 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3430 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3431 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3432 # Just matching .ism/manifest is not enough to be reliably sure
3433 # whether it's actually an ISM manifest or some other streaming
3434 # manifest since there are various streaming URL formats
3435 # possible (see [1]) as well as some other shenanigans like
3436 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3438 # Thus the most reasonable way to solve this is to delegate
3439 # to generic extractor in order to look into the contents of
3440 # the manifest itself.
3441 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3442 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3443 entry_info_dict = self.url_result(
3444 smuggle_url(video_url, {'to_generic': True}),
3447 entry_info_dict['url'] = video_url
3449 if entry_info_dict.get('formats'):
3450 self._sort_formats(entry_info_dict['formats'])
3452 entries.append(entry_info_dict)
3454 if len(entries) == 1:
3457 for num, e in enumerate(entries, start=1):
3458 # 'url' results don't have a title
3459 if e.get('title') is not None:
3460 e['title'] = '%s (%d)' % (e['title'], num)
3462 '_type': 'playlist',