You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

3424 lines
138 KiB

10 years ago
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
10 years ago
10 years ago
10 years ago
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
10 years ago
10 years ago
  1. # coding: utf-8
  2. from __future__ import unicode_literals
  3. import os
  4. import re
  5. import sys
  6. from .common import InfoExtractor
  7. from .youtube import YoutubeIE
  8. from ..compat import (
  9. compat_etree_fromstring,
  10. compat_str,
  11. compat_urllib_parse_unquote,
  12. compat_urlparse,
  13. compat_xml_parse_error,
  14. )
  15. from ..utils import (
  16. determine_ext,
  17. ExtractorError,
  18. float_or_none,
  19. HEADRequest,
  20. is_html,
  21. js_to_json,
  22. KNOWN_EXTENSIONS,
  23. merge_dicts,
  24. mimetype2ext,
  25. orderedSet,
  26. sanitized_Request,
  27. smuggle_url,
  28. unescapeHTML,
  29. unified_strdate,
  30. unsmuggle_url,
  31. UnsupportedError,
  32. xpath_text,
  33. )
  34. from .commonprotocols import RtmpIE
  35. from .brightcove import (
  36. BrightcoveLegacyIE,
  37. BrightcoveNewIE,
  38. )
  39. from .nexx import (
  40. NexxIE,
  41. NexxEmbedIE,
  42. )
  43. from .nbc import NBCSportsVPlayerIE
  44. from .ooyala import OoyalaIE
  45. from .rutv import RUTVIE
  46. from .tvc import TVCIE
  47. from .sportbox import SportBoxIE
  48. from .smotri import SmotriIE
  49. from .myvi import MyviIE
  50. from .condenast import CondeNastIE
  51. from .udn import UDNEmbedIE
  52. from .senateisvp import SenateISVPIE
  53. from .svt import SVTIE
  54. from .pornhub import PornHubIE
  55. from .xhamster import XHamsterEmbedIE
  56. from .tnaflix import TNAFlixNetworkEmbedIE
  57. from .drtuber import DrTuberIE
  58. from .redtube import RedTubeIE
  59. from .tube8 import Tube8IE
  60. from .vimeo import VimeoIE
  61. from .dailymotion import DailymotionIE
  62. from .dailymail import DailyMailIE
  63. from .onionstudios import OnionStudiosIE
  64. from .viewlift import ViewLiftEmbedIE
  65. from .mtv import MTVServicesEmbeddedIE
  66. from .pladform import PladformIE
  67. from .videomore import VideomoreIE
  68. from .webcaster import WebcasterFeedIE
  69. from .googledrive import GoogleDriveIE
  70. from .jwplatform import JWPlatformIE
  71. from .digiteka import DigitekaIE
  72. from .arkena import ArkenaIE
  73. from .instagram import InstagramIE
  74. from .liveleak import LiveLeakIE
  75. from .threeqsdn import ThreeQSDNIE
  76. from .theplatform import ThePlatformIE
  77. from .kaltura import KalturaIE
  78. from .eagleplatform import EaglePlatformIE
  79. from .facebook import FacebookIE
  80. from .soundcloud import SoundcloudEmbedIE
  81. from .tunein import TuneInBaseIE
  82. from .vbox7 import Vbox7IE
  83. from .dbtv import DBTVIE
  84. from .piksel import PikselIE
  85. from .videa import VideaIE
  86. from .twentymin import TwentyMinutenIE
  87. from .ustream import UstreamIE
  88. from .videopress import VideoPressIE
  89. from .rutube import RutubeIE
  90. from .limelight import LimelightBaseIE
  91. from .anvato import AnvatoIE
  92. from .washingtonpost import WashingtonPostIE
  93. from .wistia import WistiaIE
  94. from .mediaset import MediasetIE
  95. from .joj import JojIE
  96. from .megaphone import MegaphoneIE
  97. from .vzaar import VzaarIE
  98. from .channel9 import Channel9IE
  99. from .vshare import VShareIE
  100. from .mediasite import MediasiteIE
  101. from .springboardplatform import SpringboardPlatformIE
  102. from .yapfiles import YapFilesIE
  103. from .vice import ViceIE
  104. from .xfileshare import XFileShareIE
  105. from .cloudflarestream import CloudflareStreamIE
  106. from .peertube import PeerTubeIE
  107. from .teachable import TeachableIE
  108. from .indavideo import IndavideoEmbedIE
  109. from .apa import APAIE
  110. from .foxnews import FoxNewsIE
  111. from .viqeo import ViqeoIE
  112. from .expressen import ExpressenIE
  113. from .zype import ZypeIE
  114. from .odnoklassniki import OdnoklassnikiIE
  115. from .kinja import KinjaEmbedIE
  116. class GenericIE(InfoExtractor):
  117. IE_DESC = 'Generic downloader that works on some sites'
  118. _VALID_URL = r'.*'
  119. IE_NAME = 'generic'
  120. _TESTS = [
  121. # Direct link to a video
  122. {
  123. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  124. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  125. 'info_dict': {
  126. 'id': 'trailer',
  127. 'ext': 'mp4',
  128. 'title': 'trailer',
  129. 'upload_date': '20100513',
  130. }
  131. },
  132. # Direct link to media delivered compressed (until Accept-Encoding is *)
  133. {
  134. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  135. 'md5': '128c42e68b13950268b648275386fc74',
  136. 'info_dict': {
  137. 'id': 'FictionJunction-Parallel_Hearts',
  138. 'ext': 'flac',
  139. 'title': 'FictionJunction-Parallel_Hearts',
  140. 'upload_date': '20140522',
  141. },
  142. 'expected_warnings': [
  143. 'URL could be a direct video link, returning it as such.'
  144. ],
  145. 'skip': 'URL invalid',
  146. },
  147. # Direct download with broken HEAD
  148. {
  149. 'url': 'http://ai-radio.org:8000/radio.opus',
  150. 'info_dict': {
  151. 'id': 'radio',
  152. 'ext': 'opus',
  153. 'title': 'radio',
  154. },
  155. 'params': {
  156. 'skip_download': True, # infinite live stream
  157. },
  158. 'expected_warnings': [
  159. r'501.*Not Implemented',
  160. r'400.*Bad Request',
  161. ],
  162. },
  163. # Direct link with incorrect MIME type
  164. {
  165. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  166. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  167. 'info_dict': {
  168. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  169. 'id': '5_Lennart_Poettering_-_Systemd',
  170. 'ext': 'webm',
  171. 'title': '5_Lennart_Poettering_-_Systemd',
  172. 'upload_date': '20141120',
  173. },
  174. 'expected_warnings': [
  175. 'URL could be a direct video link, returning it as such.'
  176. ]
  177. },
  178. # RSS feed
  179. {
  180. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  181. 'info_dict': {
  182. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  183. 'title': 'Zero Punctuation',
  184. 'description': 're:.*groundbreaking video review series.*'
  185. },
  186. 'playlist_mincount': 11,
  187. },
  188. # RSS feed with enclosure
  189. {
  190. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  191. 'info_dict': {
  192. 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  193. 'ext': 'm4v',
  194. 'upload_date': '20150228',
  195. 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  196. }
  197. },
  198. # RSS feed with enclosures and unsupported link URLs
  199. {
  200. 'url': 'http://www.hellointernet.fm/podcast?format=rss',
  201. 'info_dict': {
  202. 'id': 'http://www.hellointernet.fm/podcast?format=rss',
  203. 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
  204. 'title': 'Hello Internet',
  205. },
  206. 'playlist_mincount': 100,
  207. },
  208. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  209. {
  210. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  211. 'info_dict': {
  212. 'id': 'smil',
  213. 'ext': 'mp4',
  214. 'title': 'Automatics, robotics and biocybernetics',
  215. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  216. 'upload_date': '20130627',
  217. 'formats': 'mincount:16',
  218. 'subtitles': 'mincount:1',
  219. },
  220. 'params': {
  221. 'force_generic_extractor': True,
  222. 'skip_download': True,
  223. },
  224. },
  225. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  226. {
  227. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  228. 'info_dict': {
  229. 'id': 'hds',
  230. 'ext': 'flv',
  231. 'title': 'hds',
  232. 'formats': 'mincount:1',
  233. },
  234. 'params': {
  235. 'skip_download': True,
  236. },
  237. },
  238. # SMIL from https://www.restudy.dk/video/play/id/1637
  239. {
  240. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  241. 'info_dict': {
  242. 'id': 'video_1637',
  243. 'ext': 'flv',
  244. 'title': 'video_1637',
  245. 'formats': 'mincount:3',
  246. },
  247. 'params': {
  248. 'skip_download': True,
  249. },
  250. },
  251. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  252. {
  253. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  254. 'info_dict': {
  255. 'id': 'smil-service',
  256. 'ext': 'flv',
  257. 'title': 'smil-service',
  258. 'formats': 'mincount:1',
  259. },
  260. 'params': {
  261. 'skip_download': True,
  262. },
  263. },
  264. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  265. {
  266. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  267. 'info_dict': {
  268. 'id': '4719370',
  269. 'ext': 'mp4',
  270. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  271. 'formats': 'mincount:3',
  272. },
  273. 'params': {
  274. 'skip_download': True,
  275. },
  276. },
  277. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  278. {
  279. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  280. 'info_dict': {
  281. 'id': 'mZlp2ctYIUEB',
  282. 'ext': 'mp4',
  283. 'title': 'Tikibad ontruimd wegens brand',
  284. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  285. 'thumbnail': r're:^https?://.*\.jpg$',
  286. 'duration': 33,
  287. },
  288. 'params': {
  289. 'skip_download': True,
  290. },
  291. },
  292. # MPD from http://dash-mse-test.appspot.com/media.html
  293. {
  294. 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
  295. 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
  296. 'info_dict': {
  297. 'id': 'car-20120827-manifest',
  298. 'ext': 'mp4',
  299. 'title': 'car-20120827-manifest',
  300. 'formats': 'mincount:9',
  301. 'upload_date': '20130904',
  302. },
  303. 'params': {
  304. 'format': 'bestvideo',
  305. },
  306. },
  307. # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
  308. {
  309. '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',
  310. 'info_dict': {
  311. 'id': 'content',
  312. 'ext': 'mp4',
  313. 'title': 'content',
  314. 'formats': 'mincount:8',
  315. },
  316. 'params': {
  317. # m3u8 downloads
  318. 'skip_download': True,
  319. },
  320. 'skip': 'video gone',
  321. },
  322. # m3u8 served with Content-Type: text/plain
  323. {
  324. 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
  325. 'info_dict': {
  326. 'id': 'index',
  327. 'ext': 'mp4',
  328. 'title': 'index',
  329. 'upload_date': '20140720',
  330. 'formats': 'mincount:11',
  331. },
  332. 'params': {
  333. # m3u8 downloads
  334. 'skip_download': True,
  335. },
  336. 'skip': 'video gone',
  337. },
  338. # google redirect
  339. {
  340. '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',
  341. 'info_dict': {
  342. 'id': 'cmQHVoWB5FY',
  343. 'ext': 'mp4',
  344. 'upload_date': '20130224',
  345. 'uploader_id': 'TheVerge',
  346. 'description': r're:^Chris Ziegler takes a look at the\.*',
  347. 'uploader': 'The Verge',
  348. 'title': 'First Firefox OS phones side-by-side',
  349. },
  350. 'params': {
  351. 'skip_download': False,
  352. }
  353. },
  354. {
  355. # redirect in Refresh HTTP header
  356. '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',
  357. 'info_dict': {
  358. 'id': 'pO8h3EaFRdo',
  359. 'ext': 'mp4',
  360. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  361. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  362. 'upload_date': '20150917',
  363. 'uploader_id': 'brtvofficial',
  364. 'uploader': 'Boiler Room',
  365. },
  366. 'params': {
  367. 'skip_download': False,
  368. },
  369. },
  370. {
  371. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  372. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  373. 'info_dict': {
  374. 'id': '13601338388002',
  375. 'ext': 'mp4',
  376. 'uploader': 'www.hodiho.fr',
  377. 'title': 'R\u00e9gis plante sa Jeep',
  378. }
  379. },
  380. # bandcamp page with custom domain
  381. {
  382. 'add_ie': ['Bandcamp'],
  383. 'url': 'http://bronyrock.com/track/the-pony-mash',
  384. 'info_dict': {
  385. 'id': '3235767654',
  386. 'ext': 'mp3',
  387. 'title': 'The Pony Mash',
  388. 'uploader': 'M_Pallante',
  389. },
  390. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  391. },
  392. {
  393. # embedded brightcove video
  394. # it also tests brightcove videos that need to set the 'Referer'
  395. # in the http requests
  396. 'add_ie': ['BrightcoveLegacy'],
  397. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  398. 'info_dict': {
  399. 'id': '2765128793001',
  400. 'ext': 'mp4',
  401. 'title': 'Le cours de bourse : l’analyse technique',
  402. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  403. 'uploader': 'BFM BUSINESS',
  404. },
  405. 'params': {
  406. 'skip_download': True,
  407. },
  408. },
  409. {
  410. # embedded with itemprop embedURL and video id spelled as `idVideo`
  411. 'add_id': ['BrightcoveLegacy'],
  412. 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
  413. 'info_dict': {
  414. 'id': '5255628253001',
  415. 'ext': 'mp4',
  416. 'title': 'md5:37c519b1128915607601e75a87995fc0',
  417. 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
  418. 'uploader': 'BFM BUSINESS',
  419. 'uploader_id': '876450612001',
  420. 'timestamp': 1482255315,
  421. 'upload_date': '20161220',
  422. },
  423. 'params': {
  424. 'skip_download': True,
  425. },
  426. },
  427. {
  428. # https://github.com/ytdl-org/youtube-dl/issues/2253
  429. 'url': 'http://bcove.me/i6nfkrc3',
  430. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  431. 'info_dict': {
  432. 'id': '3101154703001',
  433. 'ext': 'mp4',
  434. 'title': 'Still no power',
  435. 'uploader': 'thestar.com',
  436. '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.',
  437. },
  438. 'add_ie': ['BrightcoveLegacy'],
  439. 'skip': 'video gone',
  440. },
  441. {
  442. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  443. 'md5': 'fb973ecf6e4a78a67453647444222983',
  444. 'info_dict': {
  445. 'id': '3414141473001',
  446. 'ext': 'mp4',
  447. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  448. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  449. 'uploader': 'Championat',
  450. },
  451. },
  452. {
  453. # https://github.com/ytdl-org/youtube-dl/issues/3541
  454. 'add_ie': ['BrightcoveLegacy'],
  455. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  456. 'info_dict': {
  457. 'id': '3866516442001',
  458. 'ext': 'mp4',
  459. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  460. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  461. 'uploader': 'SBS Broadcasting',
  462. },
  463. 'skip': 'Restricted to Netherlands',
  464. 'params': {
  465. 'skip_download': True, # m3u8 download
  466. },
  467. },
  468. {
  469. # Brightcove video in <iframe>
  470. 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
  471. 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
  472. 'info_dict': {
  473. 'id': '5360463607001',
  474. 'ext': 'mp4',
  475. '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',
  476. '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。',
  477. 'uploader': 'United Nations',
  478. 'uploader_id': '1362235914001',
  479. 'timestamp': 1489593889,
  480. 'upload_date': '20170315',
  481. },
  482. 'add_ie': ['BrightcoveLegacy'],
  483. },
  484. {
  485. # Brightcove with alternative playerID key
  486. 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
  487. 'info_dict': {
  488. 'id': 'nmeth.2062_SV1',
  489. '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',
  490. },
  491. 'playlist': [{
  492. 'info_dict': {
  493. 'id': '2228375078001',
  494. 'ext': 'mp4',
  495. 'title': 'nmeth.2062-sv1',
  496. 'description': 'nmeth.2062-sv1',
  497. 'timestamp': 1363357591,
  498. 'upload_date': '20130315',
  499. 'uploader': 'Nature Publishing Group',
  500. 'uploader_id': '1964492299001',
  501. },
  502. }],
  503. },
  504. {
  505. # Brightcove with UUID in videoPlayer
  506. 'url': 'http://www8.hp.com/cn/zh/home.html',
  507. 'info_dict': {
  508. 'id': '5255815316001',
  509. 'ext': 'mp4',
  510. 'title': 'Sprocket Video - China',
  511. 'description': 'Sprocket Video - China',
  512. 'uploader': 'HP-Video Gallery',
  513. 'timestamp': 1482263210,
  514. 'upload_date': '20161220',
  515. 'uploader_id': '1107601872001',
  516. },
  517. 'params': {
  518. 'skip_download': True, # m3u8 download
  519. },
  520. 'skip': 'video rotates...weekly?',
  521. },
  522. {
  523. # Brightcove:new type [2].
  524. 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
  525. 'md5': '2b35148fcf48da41c9fb4591650784f3',
  526. 'info_dict': {
  527. 'id': '5348741021001',
  528. 'ext': 'mp4',
  529. 'upload_date': '20170306',
  530. 'uploader_id': '4191638492001',
  531. 'timestamp': 1488769918,
  532. 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
  533. },
  534. },
  535. {
  536. # Alternative brightcove <video> attributes
  537. '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/',
  538. 'info_dict': {
  539. 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
  540. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
  541. },
  542. 'playlist': [{
  543. 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
  544. 'info_dict': {
  545. 'id': '5311302538001',
  546. 'ext': 'mp4',
  547. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
  548. 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
  549. 'timestamp': 1486321708,
  550. 'upload_date': '20170205',
  551. 'uploader_id': '800000640001',
  552. },
  553. 'only_matching': True,
  554. }],
  555. },
  556. {
  557. # Brightcove with UUID in videoPlayer
  558. 'url': 'http://www8.hp.com/cn/zh/home.html',
  559. 'info_dict': {
  560. 'id': '5255815316001',
  561. 'ext': 'mp4',
  562. 'title': 'Sprocket Video - China',
  563. 'description': 'Sprocket Video - China',
  564. 'uploader': 'HP-Video Gallery',
  565. 'timestamp': 1482263210,
  566. 'upload_date': '20161220',
  567. 'uploader_id': '1107601872001',
  568. },
  569. 'params': {
  570. 'skip_download': True, # m3u8 download
  571. },
  572. },
  573. # ooyala video
  574. {
  575. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  576. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  577. 'info_dict': {
  578. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  579. 'ext': 'mp4',
  580. 'title': '2cc213299525360.mov', # that's what we get
  581. 'duration': 238.231,
  582. },
  583. 'add_ie': ['Ooyala'],
  584. },
  585. {
  586. # ooyala video embedded with http://player.ooyala.com/iframe.js
  587. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  588. 'info_dict': {
  589. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  590. 'ext': 'mp4',
  591. 'title': '"Steve Jobs: Man in the Machine" trailer',
  592. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  593. 'duration': 135.427,
  594. },
  595. 'params': {
  596. 'skip_download': True,
  597. },
  598. 'skip': 'movie expired',
  599. },
  600. # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
  601. {
  602. 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
  603. 'info_dict': {
  604. 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
  605. 'ext': 'mp4',
  606. 'title': 'Steampunk Fest Comes to Honesdale',
  607. 'duration': 43.276,
  608. },
  609. 'params': {
  610. 'skip_download': True,
  611. }
  612. },
  613. # embed.ly video
  614. {
  615. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  616. 'info_dict': {
  617. 'id': '9ODmcdjQcHQ',
  618. 'ext': 'mp4',
  619. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  620. 'upload_date': '20140225',
  621. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  622. 'uploader': 'Tested',
  623. 'uploader_id': 'testedcom',
  624. },
  625. # No need to test YoutubeIE here
  626. 'params': {
  627. 'skip_download': True,
  628. },
  629. },
  630. # funnyordie embed
  631. {
  632. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  633. 'info_dict': {
  634. 'id': '18e820ec3f',
  635. 'ext': 'mp4',
  636. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  637. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  638. },
  639. # HEAD requests lead to endless 301, while GET is OK
  640. 'expected_warnings': ['301'],
  641. },
  642. # RUTV embed
  643. {
  644. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  645. 'info_dict': {
  646. 'id': '776940',
  647. 'ext': 'mp4',
  648. 'title': 'Охотское море стало целиком российским',
  649. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  650. },
  651. 'params': {
  652. # m3u8 download
  653. 'skip_download': True,
  654. },
  655. },
  656. # TVC embed
  657. {
  658. '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/',
  659. 'info_dict': {
  660. 'id': '55304',
  661. 'ext': 'mp4',
  662. 'title': 'Дошкольное воспитание',
  663. },
  664. },
  665. # SportBox embed
  666. {
  667. 'url': 'http://www.vestifinance.ru/articles/25753',
  668. 'info_dict': {
  669. 'id': '25753',
  670. 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  671. },
  672. 'playlist': [{
  673. 'info_dict': {
  674. 'id': '370908',
  675. 'title': 'Госзаказ. День 3',
  676. 'ext': 'mp4',
  677. }
  678. }, {
  679. 'info_dict': {
  680. 'id': '370905',
  681. 'title': 'Госзаказ. День 2',
  682. 'ext': 'mp4',
  683. }
  684. }, {
  685. 'info_dict': {
  686. 'id': '370902',
  687. 'title': 'Госзаказ. День 1',
  688. 'ext': 'mp4',
  689. }
  690. }],
  691. 'params': {
  692. # m3u8 download
  693. 'skip_download': True,
  694. },
  695. },
  696. # Myvi.ru embed
  697. {
  698. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  699. 'info_dict': {
  700. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  701. 'ext': 'mp4',
  702. 'title': 'Ужастики, русский трейлер (2015)',
  703. 'thumbnail': r're:^https?://.*\.jpg$',
  704. 'duration': 153,
  705. }
  706. },
  707. # XHamster embed
  708. {
  709. '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',
  710. 'info_dict': {
  711. 'id': 'showthread',
  712. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  713. },
  714. 'playlist_mincount': 7,
  715. # This forum does not allow <iframe> syntaxes anymore
  716. # Now HTML tags are displayed as-is
  717. 'skip': 'No videos on this page',
  718. },
  719. # Embedded TED video
  720. {
  721. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  722. 'md5': '65fdff94098e4a607385a60c5177c638',
  723. 'info_dict': {
  724. 'id': '1969',
  725. 'ext': 'mp4',
  726. 'title': 'Hidden miracles of the natural world',
  727. 'uploader': 'Louie Schwartzberg',
  728. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  729. }
  730. },
  731. # nowvideo embed hidden behind percent encoding
  732. {
  733. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  734. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  735. 'info_dict': {
  736. 'id': '06e53103ca9aa',
  737. 'ext': 'flv',
  738. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  739. 'description': 'No description',
  740. },
  741. },
  742. # arte embed
  743. {
  744. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  745. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  746. 'info_dict': {
  747. 'id': '048195-004_PLUS7-F',
  748. 'ext': 'flv',
  749. 'title': 'X:enius',
  750. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  751. 'upload_date': '20140320',
  752. },
  753. 'params': {
  754. 'skip_download': 'Requires rtmpdump'
  755. },
  756. 'skip': 'video gone',
  757. },
  758. # francetv embed
  759. {
  760. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  761. 'info_dict': {
  762. 'id': 'EV_30231',
  763. 'ext': 'mp4',
  764. 'title': 'Alcaline, le concert avec Calogero',
  765. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  766. 'upload_date': '20150226',
  767. 'timestamp': 1424989860,
  768. 'duration': 5400,
  769. },
  770. 'params': {
  771. # m3u8 downloads
  772. 'skip_download': True,
  773. },
  774. 'expected_warnings': [
  775. 'Forbidden'
  776. ]
  777. },
  778. # Condé Nast embed
  779. {
  780. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  781. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  782. 'info_dict': {
  783. 'id': '53501be369702d3275860000',
  784. 'ext': 'mp4',
  785. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  786. }
  787. },
  788. # Dailymotion embed
  789. {
  790. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  791. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  792. 'info_dict': {
  793. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  794. 'ext': 'mp4',
  795. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  796. 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
  797. 'uploader': 'Spi0n',
  798. 'uploader_id': 'xgditw',
  799. 'upload_date': '20140425',
  800. 'timestamp': 1398441542,
  801. },
  802. 'add_ie': ['Dailymotion'],
  803. },
  804. # DailyMail embed
  805. {
  806. 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
  807. 'info_dict': {
  808. 'id': '1495629',
  809. 'ext': 'mp4',
  810. 'title': 'Care worker punches elderly dementia patient in head 11 times',
  811. 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
  812. },
  813. 'add_ie': ['DailyMail'],
  814. 'params': {
  815. 'skip_download': True,
  816. },
  817. },
  818. # YouTube embed
  819. {
  820. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  821. 'info_dict': {
  822. 'id': 'FXRb4ykk4S0',
  823. 'ext': 'mp4',
  824. 'title': 'The NBL Auction 2014',
  825. 'uploader': 'BADMINTON England',
  826. 'uploader_id': 'BADMINTONEvents',
  827. 'upload_date': '20140603',
  828. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  829. },
  830. 'add_ie': ['Youtube'],
  831. 'params': {
  832. 'skip_download': True,
  833. }
  834. },
  835. # MTVSercices embed
  836. {
  837. 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
  838. 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
  839. 'info_dict': {
  840. 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
  841. 'ext': 'mp4',
  842. 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
  843. 'description': 'Two valets share their love for movie star Liam Neesons.',
  844. 'timestamp': 1349922600,
  845. 'upload_date': '20121011',
  846. },
  847. },
  848. # YouTube embed via <data-embed-url="">
  849. {
  850. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  851. 'info_dict': {
  852. 'id': '4vAffPZIT44',
  853. 'ext': 'mp4',
  854. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  855. 'uploader': 'Gameloft',
  856. 'uploader_id': 'gameloft',
  857. 'upload_date': '20140828',
  858. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  859. },
  860. 'params': {
  861. 'skip_download': True,
  862. }
  863. },
  864. # YouTube <object> embed
  865. {
  866. 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
  867. 'md5': '516718101ec834f74318df76259fb3cc',
  868. 'info_dict': {
  869. 'id': 'msN87y-iEx0',
  870. 'ext': 'webm',
  871. 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
  872. 'upload_date': '20080526',
  873. 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
  874. 'uploader': 'Christopher Sykes',
  875. 'uploader_id': 'ChristopherJSykes',
  876. },
  877. 'add_ie': ['Youtube'],
  878. },
  879. # Camtasia studio
  880. {
  881. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  882. 'playlist': [{
  883. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  884. 'info_dict': {
  885. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  886. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  887. 'ext': 'flv',
  888. 'duration': 2235.90,
  889. }
  890. }, {
  891. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  892. 'info_dict': {
  893. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  894. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  895. 'ext': 'flv',
  896. 'duration': 2235.93,
  897. }
  898. }],
  899. 'info_dict': {
  900. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  901. }
  902. },
  903. # Flowplayer
  904. {
  905. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  906. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  907. 'info_dict': {
  908. 'id': '5123ea6d5e5a7',
  909. 'ext': 'mp4',
  910. 'age_limit': 18,
  911. 'uploader': 'www.handjobhub.com',
  912. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  913. }
  914. },
  915. # Multiple brightcove videos
  916. # https://github.com/ytdl-org/youtube-dl/issues/2283
  917. {
  918. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  919. 'info_dict': {
  920. 'id': 'always-never',
  921. 'title': 'Always / Never - The New Yorker',
  922. },
  923. 'playlist_count': 3,
  924. 'params': {
  925. 'extract_flat': False,
  926. 'skip_download': True,
  927. }
  928. },
  929. # MLB embed
  930. {
  931. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  932. 'md5': '96f09a37e44da40dd083e12d9a683327',
  933. 'info_dict': {
  934. 'id': '33322633',
  935. 'ext': 'mp4',
  936. 'title': 'Ump changes call to ball',
  937. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  938. 'duration': 48,
  939. 'timestamp': 1401537900,
  940. 'upload_date': '20140531',
  941. 'thumbnail': r're:^https?://.*\.jpg$',
  942. },
  943. },
  944. # Wistia embed
  945. {
  946. 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  947. 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
  948. 'info_dict': {
  949. 'id': '6e2wtrbdaf',
  950. 'ext': 'mov',
  951. 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
  952. 'description': 'a Paywall Videos video from Remilon',
  953. 'duration': 644.072,
  954. 'uploader': 'study.com',
  955. 'timestamp': 1459678540,
  956. 'upload_date': '20160403',
  957. 'filesize': 24687186,
  958. },
  959. },
  960. {
  961. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  962. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  963. 'info_dict': {
  964. 'id': 'uxjb0lwrcz',
  965. 'ext': 'mp4',
  966. 'title': 'Conversation about Hexagonal Rails Part 1',
  967. 'description': 'a Martin Fowler video from ThoughtWorks',
  968. 'duration': 1715.0,
  969. 'uploader': 'thoughtworks.wistia.com',
  970. 'timestamp': 1401832161,
  971. 'upload_date': '20140603',
  972. },
  973. },
  974. # Wistia standard embed (async)
  975. {
  976. 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
  977. 'info_dict': {
  978. 'id': '807fafadvk',
  979. 'ext': 'mp4',
  980. 'title': 'Drip Brennan Dunn Workshop',
  981. 'description': 'a JV Webinars video from getdrip-1',
  982. 'duration': 4986.95,
  983. 'timestamp': 1463607249,
  984. 'upload_date': '20160518',
  985. },
  986. 'params': {
  987. 'skip_download': True,
  988. }
  989. },
  990. # Soundcloud embed
  991. {
  992. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  993. 'info_dict': {
  994. 'id': '174391317',
  995. 'ext': 'mp3',
  996. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  997. 'uploader': 'Sophos Security',
  998. 'title': 'Chet Chat 171 - Oct 29, 2014',
  999. 'upload_date': '20141029',
  1000. }
  1001. },
  1002. # Soundcloud multiple embeds
  1003. {
  1004. 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
  1005. 'info_dict': {
  1006. 'id': '52809',
  1007. 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
  1008. },
  1009. 'playlist_mincount': 7,
  1010. },
  1011. # TuneIn station embed
  1012. {
  1013. 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
  1014. 'info_dict': {
  1015. 'id': '204146',
  1016. 'ext': 'mp3',
  1017. 'title': 'CNRV',
  1018. 'location': 'Paris, France',
  1019. 'is_live': True,
  1020. },
  1021. 'params': {
  1022. # Live stream
  1023. 'skip_download': True,
  1024. },
  1025. },
  1026. # Livestream embed
  1027. {
  1028. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  1029. 'info_dict': {
  1030. 'id': '67864563',
  1031. 'ext': 'flv',
  1032. 'upload_date': '20141112',
  1033. 'title': 'Rosetta #CometLanding webcast HL 10',
  1034. }
  1035. },
  1036. # Another Livestream embed, without 'new.' in URL
  1037. {
  1038. 'url': 'https://www.freespeech.org/',
  1039. 'info_dict': {
  1040. 'id': '123537347',
  1041. 'ext': 'mp4',
  1042. 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  1043. },
  1044. 'params': {
  1045. # Live stream
  1046. 'skip_download': True,
  1047. },
  1048. },
  1049. # LazyYT
  1050. {
  1051. 'url': 'https://skiplagged.com/',
  1052. 'info_dict': {
  1053. 'id': 'skiplagged',
  1054. 'title': 'Skiplagged: The smart way to find cheap flights',
  1055. },
  1056. 'playlist_mincount': 1,
  1057. 'add_ie': ['Youtube'],
  1058. },
  1059. # Cinchcast embed
  1060. {
  1061. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  1062. 'info_dict': {
  1063. 'id': '7141703',
  1064. 'ext': 'mp3',
  1065. 'upload_date': '20141126',
  1066. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  1067. }
  1068. },
  1069. # Cinerama player
  1070. {
  1071. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  1072. 'info_dict': {
  1073. 'id': '730m_DandD_1901_512k',
  1074. 'ext': 'mp4',
  1075. 'uploader': 'www.abc.net.au',
  1076. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  1077. }
  1078. },
  1079. # embedded viddler video
  1080. {
  1081. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  1082. 'info_dict': {
  1083. 'id': '4d03aad9',
  1084. 'ext': 'mp4',
  1085. 'uploader': 'deadspin',
  1086. 'title': 'WALL-TO-GORTAT',
  1087. 'timestamp': 1422285291,
  1088. 'upload_date': '20150126',
  1089. },
  1090. 'add_ie': ['Viddler'],
  1091. },
  1092. # Libsyn embed
  1093. {
  1094. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  1095. 'info_dict': {
  1096. 'id': '3377616',
  1097. 'ext': 'mp3',
  1098. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  1099. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  1100. 'upload_date': '20150220',
  1101. },
  1102. 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
  1103. },
  1104. # jwplayer YouTube
  1105. {
  1106. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  1107. 'info_dict': {
  1108. 'id': 'Mrj4DVp2zeA',
  1109. 'ext': 'mp4',
  1110. 'upload_date': '20150212',
  1111. 'uploader': 'The National Archives UK',
  1112. 'description': 'md5:8078af856dca76edc42910b61273dbbf',
  1113. 'uploader_id': 'NationalArchives08',
  1114. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  1115. },
  1116. },
  1117. # jwplayer rtmp
  1118. {
  1119. 'url': 'http://www.suffolk.edu/sjc/live.php',
  1120. 'info_dict': {
  1121. 'id': 'live',
  1122. 'ext': 'flv',
  1123. 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
  1124. 'uploader': 'www.suffolk.edu',
  1125. },
  1126. 'params': {
  1127. 'skip_download': True,
  1128. },
  1129. 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
  1130. },
  1131. # Complex jwplayer
  1132. {
  1133. 'url': 'http://www.indiedb.com/games/king-machine/videos',
  1134. 'info_dict': {
  1135. 'id': 'videos',
  1136. 'ext': 'mp4',
  1137. 'title': 'king machine trailer 1',
  1138. 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
  1139. 'thumbnail': r're:^https?://.*\.jpg$',
  1140. },
  1141. },
  1142. {
  1143. # JWPlayer config passed as variable
  1144. 'url': 'http://www.txxx.com/videos/3326530/ariele/',
  1145. 'info_dict': {
  1146. 'id': '3326530_hq',
  1147. 'ext': 'mp4',
  1148. 'title': 'ARIELE | Tube Cup',
  1149. 'uploader': 'www.txxx.com',
  1150. 'age_limit': 18,
  1151. },
  1152. 'params': {
  1153. 'skip_download': True,
  1154. }
  1155. },
  1156. {
  1157. # JWPlatform iframe
  1158. 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
  1159. 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
  1160. 'info_dict': {
  1161. 'id': 'O0c5JcKT',
  1162. 'ext': 'mp4',
  1163. 'upload_date': '20171122',
  1164. 'timestamp': 1511366290,
  1165. 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
  1166. },
  1167. 'add_ie': [JWPlatformIE.ie_key()],
  1168. },
  1169. {
  1170. # Video.js embed, multiple formats
  1171. 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
  1172. 'info_dict': {
  1173. 'id': 'yygqldloqIk',
  1174. 'ext': 'mp4',
  1175. 'title': 'SolidWorks. Урок 6 Настройка чертежа',
  1176. 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
  1177. 'upload_date': '20130314',
  1178. 'uploader': 'PROстое3D',
  1179. 'uploader_id': 'PROstoe3D',
  1180. },
  1181. 'params': {
  1182. 'skip_download': True,
  1183. },
  1184. },
  1185. {
  1186. # Video.js embed, single format
  1187. 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
  1188. 'info_dict': {
  1189. 'id': 'watch',
  1190. 'ext': 'mp4',
  1191. 'title': 'Step 1 - Good Foundation',
  1192. 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
  1193. },
  1194. 'params': {
  1195. 'skip_download': True,
  1196. },
  1197. },
  1198. # rtl.nl embed
  1199. {
  1200. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  1201. 'playlist_mincount': 5,
  1202. 'info_dict': {
  1203. 'id': 'aanslagen-kopenhagen',
  1204. 'title': 'Aanslagen Kopenhagen',
  1205. }
  1206. },
  1207. # Zapiks embed
  1208. {
  1209. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  1210. 'info_dict': {
  1211. 'id': '118046',
  1212. 'ext': 'mp4',
  1213. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  1214. }
  1215. },
  1216. # Kaltura embed (different embed code)
  1217. {
  1218. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  1219. 'info_dict': {
  1220. 'id': '1_a52wc67y',
  1221. 'ext': 'flv',
  1222. 'upload_date': '20150127',
  1223. 'uploader_id': 'PremierMedia',
  1224. 'timestamp': int,
  1225. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  1226. },
  1227. },
  1228. # Kaltura embed with single quotes
  1229. {
  1230. 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
  1231. 'info_dict': {
  1232. 'id': '0_izeg5utt',
  1233. 'ext': 'mp4',
  1234. 'title': '35871',
  1235. 'timestamp': 1355743100,
  1236. 'upload_date': '20121217',
  1237. 'uploader_id': 'cplapp@learn360.com',
  1238. },
  1239. 'add_ie': ['Kaltura'],
  1240. },
  1241. {
  1242. # Kaltura embedded via quoted entry_id
  1243. 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
  1244. 'info_dict': {
  1245. 'id': '0_utuok90b',
  1246. 'ext': 'mp4',
  1247. 'title': '06_matthew_brender_raj_dutt',
  1248. 'timestamp': 1466638791,
  1249. 'upload_date': '20160622',
  1250. },
  1251. 'add_ie': ['Kaltura'],
  1252. 'expected_warnings': [
  1253. 'Could not send HEAD request'
  1254. ],
  1255. 'params': {
  1256. 'skip_download': True,
  1257. }
  1258. },
  1259. {
  1260. # Kaltura embedded, some fileExt broken (#11480)
  1261. 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
  1262. 'info_dict': {
  1263. 'id': '1_sgtvehim',
  1264. 'ext': 'mp4',
  1265. 'title': 'Our "Standard Models" of particle physics and cosmology',
  1266. 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
  1267. 'timestamp': 1321158993,
  1268. 'upload_date': '20111113',
  1269. 'uploader_id': 'kps1',
  1270. },
  1271. 'add_ie': ['Kaltura'],
  1272. },
  1273. {
  1274. # Kaltura iframe embed
  1275. 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
  1276. 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
  1277. 'info_dict': {
  1278. 'id': '0_f2cfbpwy',
  1279. 'ext': 'mp4',
  1280. 'title': 'I. M. Pei: A Centennial Celebration',
  1281. 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
  1282. 'upload_date': '20170403',
  1283. 'uploader_id': 'batchUser',
  1284. 'timestamp': 1491232186,
  1285. },
  1286. 'add_ie': ['Kaltura'],
  1287. },
  1288. {
  1289. # Kaltura iframe embed, more sophisticated
  1290. 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
  1291. 'info_dict': {
  1292. 'id': '1_9gzouybz',
  1293. 'ext': 'mp4',
  1294. 'title': 'lecture-05sep2017',
  1295. 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
  1296. 'upload_date': '20170913',
  1297. 'uploader_id': 'eps2',
  1298. 'timestamp': 1505340777,
  1299. },
  1300. 'params': {
  1301. 'skip_download': True,
  1302. },
  1303. 'add_ie': ['Kaltura'],
  1304. },
  1305. {
  1306. # meta twitter:player
  1307. 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
  1308. 'info_dict': {
  1309. 'id': '0_01b42zps',
  1310. 'ext': 'mp4',
  1311. 'title': 'Main Twerk (Video)',
  1312. 'upload_date': '20171208',
  1313. 'uploader_id': 'sebastian.salinas@thechive.com',
  1314. 'timestamp': 1512713057,
  1315. },
  1316. 'params': {
  1317. 'skip_download': True,
  1318. },
  1319. 'add_ie': ['Kaltura'],
  1320. },
  1321. # referrer protected EaglePlatform embed
  1322. {
  1323. 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
  1324. 'info_dict': {
  1325. 'id': '582306',
  1326. 'ext': 'mp4',
  1327. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1328. 'thumbnail': r're:^https?://.*\.jpg$',
  1329. 'duration': 3382,
  1330. 'view_count': int,
  1331. },
  1332. 'params': {
  1333. 'skip_download': True,
  1334. },
  1335. },
  1336. # ClipYou (EaglePlatform) embed (custom URL)
  1337. {
  1338. 'url': 'http://muz-tv.ru/play/7129/',
  1339. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  1340. 'info_dict': {
  1341. 'id': '12820',
  1342. 'ext': 'mp4',
  1343. 'title': "'O Sole Mio",
  1344. 'thumbnail': r're:^https?://.*\.jpg$',
  1345. 'duration': 216,
  1346. 'view_count': int,
  1347. },
  1348. 'params': {
  1349. 'skip_download': True,
  1350. },
  1351. 'skip': 'This video is unavailable.',
  1352. },
  1353. # Pladform embed
  1354. {
  1355. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  1356. 'info_dict': {
  1357. 'id': '100183293',
  1358. 'ext': 'mp4',
  1359. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  1360. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  1361. 'thumbnail': r're:^https?://.*\.jpg$',
  1362. 'duration': 694,
  1363. 'age_limit': 0,
  1364. },
  1365. 'skip': 'HTTP Error 404: Not Found',
  1366. },
  1367. # Playwire embed
  1368. {
  1369. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  1370. 'info_dict': {
  1371. 'id': '3519514',
  1372. 'ext': 'mp4',
  1373. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  1374. 'thumbnail': r're:^https?://.*\.png$',
  1375. 'duration': 45.115,
  1376. },
  1377. },
  1378. # 5min embed
  1379. {
  1380. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  1381. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  1382. 'info_dict': {
  1383. 'id': '518726732',
  1384. 'ext': 'mp4',
  1385. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  1386. 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
  1387. 'timestamp': 1427237531,
  1388. 'uploader': 'Crunch Report',
  1389. 'upload_date': '20150324',
  1390. },
  1391. 'params': {
  1392. # m3u8 download
  1393. 'skip_download': True,
  1394. },
  1395. },
  1396. # Crooks and Liars embed
  1397. {
  1398. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  1399. 'info_dict': {
  1400. 'id': '8RUoRhRi',
  1401. 'ext': 'mp4',
  1402. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  1403. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  1404. 'timestamp': 1428207000,
  1405. 'upload_date': '20150405',
  1406. 'uploader': 'Heather',
  1407. },
  1408. },
  1409. # Crooks and Liars external embed
  1410. {
  1411. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  1412. 'info_dict': {
  1413. 'id': 'MTE3MjUtMzQ2MzA',
  1414. 'ext': 'mp4',
  1415. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  1416. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  1417. 'timestamp': 1265032391,
  1418. 'upload_date': '20100201',
  1419. 'uploader': 'Heather',
  1420. },
  1421. },
  1422. # NBC Sports vplayer embed
  1423. {
  1424. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  1425. 'info_dict': {
  1426. 'id': 'ln7x1qSThw4k',
  1427. 'ext': 'flv',
  1428. 'title': "PFT Live: New leader in the 'new-look' defense",
  1429. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  1430. 'uploader': 'NBCU-SPORTS',
  1431. 'upload_date': '20140107',
  1432. 'timestamp': 1389118457,
  1433. },
  1434. 'skip': 'Invalid Page URL',
  1435. },
  1436. # NBC News embed
  1437. {
  1438. 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
  1439. 'md5': '1aa589c675898ae6d37a17913cf68d66',
  1440. 'info_dict': {
  1441. 'id': 'x_dtl_oa_LettermanliftPR_160608',
  1442. 'ext': 'mp4',
  1443. 'title': 'David Letterman: A Preview',
  1444. '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.',
  1445. 'upload_date': '20160609',
  1446. 'timestamp': 1465431544,
  1447. 'uploader': 'NBCU-NEWS',
  1448. },
  1449. },
  1450. # UDN embed
  1451. {
  1452. 'url': 'https://video.udn.com/news/300346',
  1453. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  1454. 'info_dict': {
  1455. 'id': '300346',
  1456. 'ext': 'mp4',
  1457. 'title': '中一中男師變性 全校師生力挺',
  1458. 'thumbnail': r're:^https?://.*\.jpg$',
  1459. },
  1460. 'params': {
  1461. # m3u8 download
  1462. 'skip_download': True,
  1463. },
  1464. 'expected_warnings': ['Failed to parse JSON Expecting value'],
  1465. },
  1466. # Brightcove URL in single quotes
  1467. {
  1468. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  1469. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  1470. 'info_dict': {
  1471. 'id': '4255764656001',
  1472. 'ext': 'mp4',
  1473. 'title': 'SN Presents: Russell Martin, World Citizen',
  1474. '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.',
  1475. 'uploader': 'Rogers Sportsnet',
  1476. 'uploader_id': '1704050871',
  1477. 'upload_date': '20150525',
  1478. 'timestamp': 1432570283,
  1479. },
  1480. },
  1481. # Kinja embed
  1482. {
  1483. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1484. 'info_dict': {
  1485. 'id': '106351',
  1486. 'ext': 'mp4',
  1487. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1488. 'description': 'Migrated from OnionStudios',
  1489. 'thumbnail': r're:^https?://.*\.jpe?g$',
  1490. 'uploader': 'clickhole',
  1491. 'upload_date': '20150527',
  1492. 'timestamp': 1432744860,
  1493. }
  1494. },
  1495. # SnagFilms embed
  1496. {
  1497. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1498. 'info_dict': {
  1499. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1500. 'ext': 'mp4',
  1501. 'title': '#whilewewatch',
  1502. }
  1503. },
  1504. # AdobeTVVideo embed
  1505. {
  1506. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1507. 'md5': '43662b577c018ad707a63766462b1e87',
  1508. 'info_dict': {
  1509. 'id': '2456',
  1510. 'ext': 'mp4',
  1511. 'title': 'New experience with Acrobat DC',
  1512. 'description': 'New experience with Acrobat DC',
  1513. 'duration': 248.667,
  1514. },
  1515. },
  1516. # BrightcoveInPageEmbed embed
  1517. {
  1518. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1519. 'info_dict': {
  1520. 'id': '4238694884001',
  1521. 'ext': 'flv',
  1522. 'title': 'Tabletop: Dread, Last Thoughts',
  1523. 'description': 'Tabletop: Dread, Last Thoughts',
  1524. 'duration': 51690,
  1525. },
  1526. },
  1527. # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
  1528. # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
  1529. {
  1530. 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
  1531. 'info_dict': {
  1532. 'id': '4785848093001',
  1533. 'ext': 'mp4',
  1534. 'title': 'The Cardinal Pell Interview',
  1535. 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
  1536. 'uploader': 'GlobeCast Australia - GlobeStream',
  1537. 'uploader_id': '2733773828001',
  1538. 'upload_date': '20160304',
  1539. 'timestamp': 1457083087,
  1540. },
  1541. 'params': {
  1542. # m3u8 downloads
  1543. 'skip_download': True,
  1544. },
  1545. },
  1546. {
  1547. # Brightcove embed with whitespace around attribute names
  1548. 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
  1549. 'info_dict': {
  1550. 'id': '3167554373001',
  1551. 'ext': 'mp4',
  1552. 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
  1553. 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
  1554. 'uploader_id': '1079349493',
  1555. 'upload_date': '20140207',
  1556. 'timestamp': 1391810548,
  1557. },
  1558. 'params': {
  1559. 'skip_download': True,
  1560. },
  1561. },
  1562. # Another form of arte.tv embed
  1563. {
  1564. 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
  1565. 'md5': '850bfe45417ddf221288c88a0cffe2e2',
  1566. 'info_dict': {
  1567. 'id': '030273-562_PLUS7-F',
  1568. 'ext': 'mp4',
  1569. 'title': 'ARTE Reportage - Nulle part, en France',
  1570. 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
  1571. 'upload_date': '20160409',
  1572. },
  1573. },
  1574. # LiveLeak embed
  1575. {
  1576. 'url': 'http://www.wykop.pl/link/3088787/',
  1577. 'md5': '7619da8c820e835bef21a1efa2a0fc71',
  1578. 'info_dict': {
  1579. 'id': '874_1459135191',
  1580. 'ext': 'mp4',
  1581. 'title': 'Man shows poor quality of new apartment building',
  1582. 'description': 'The wall is like a sand pile.',
  1583. 'uploader': 'Lake8737',
  1584. },
  1585. 'add_ie': [LiveLeakIE.ie_key()],
  1586. },
  1587. # Another LiveLeak embed pattern (#13336)
  1588. {
  1589. 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
  1590. 'info_dict': {
  1591. 'id': '2eb_1496309988',
  1592. 'ext': 'mp4',
  1593. 'title': 'Thief robs place where everyone was armed',
  1594. 'description': 'md5:694d73ee79e535953cf2488562288eee',
  1595. 'uploader': 'brazilwtf',
  1596. },
  1597. 'add_ie': [LiveLeakIE.ie_key()],
  1598. },
  1599. # Duplicated embedded video URLs
  1600. {
  1601. 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
  1602. 'info_dict': {
  1603. 'id': '149298443_480_16c25b74_2',
  1604. 'ext': 'mp4',
  1605. 'title': 'vs. Blue Orange Spring Game',
  1606. 'uploader': 'www.hudl.com',
  1607. },
  1608. },
  1609. # twitter:player:stream embed
  1610. {
  1611. 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
  1612. 'info_dict': {
  1613. 'id': 'master',
  1614. 'ext': 'mp4',
  1615. 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
  1616. 'uploader': 'www.rtl.be',
  1617. },
  1618. 'params': {
  1619. # m3u8 downloads
  1620. 'skip_download': True,
  1621. },
  1622. },
  1623. # twitter:player embed
  1624. {
  1625. 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
  1626. 'md5': 'a3e0df96369831de324f0778e126653c',
  1627. 'info_dict': {
  1628. 'id': '4909620399001',
  1629. 'ext': 'mp4',
  1630. 'title': 'What Do Black Holes Sound Like?',
  1631. 'description': 'what do black holes sound like',
  1632. 'upload_date': '20160524',
  1633. 'uploader_id': '29913724001',
  1634. 'timestamp': 1464107587,
  1635. 'uploader': 'TheAtlantic',
  1636. },
  1637. 'add_ie': ['BrightcoveLegacy'],
  1638. },
  1639. # Facebook <iframe> embed
  1640. {
  1641. 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
  1642. 'md5': 'fbcde74f534176ecb015849146dd3aee',
  1643. 'info_dict': {
  1644. 'id': '599637780109885',
  1645. 'ext': 'mp4',
  1646. 'title': 'Facebook video #599637780109885',
  1647. },
  1648. },
  1649. # Facebook <iframe> embed, plugin video
  1650. {
  1651. 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
  1652. 'info_dict': {
  1653. 'id': '1754168231264132',
  1654. 'ext': 'mp4',
  1655. 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
  1656. 'uploader': 'Tariq Ramadan (official)',
  1657. 'timestamp': 1496758379,
  1658. 'upload_date': '20170606',
  1659. },
  1660. 'params': {
  1661. 'skip_download': True,
  1662. },
  1663. },
  1664. # Facebook API embed
  1665. {
  1666. 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
  1667. 'md5': 'a47372ee61b39a7b90287094d447d94e',
  1668. 'info_dict': {
  1669. 'id': '10153467542406923',
  1670. 'ext': 'mp4',
  1671. 'title': 'Facebook video #10153467542406923',
  1672. },
  1673. },
  1674. # Wordpress "YouTube Video Importer" plugin
  1675. {
  1676. 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
  1677. 'md5': 'd16797741b560b485194eddda8121b48',
  1678. 'info_dict': {
  1679. 'id': 'HNTXWDXV9Is',
  1680. 'ext': 'mp4',
  1681. 'title': 'Blue Devils Drumline Stanford lot 2016',
  1682. 'upload_date': '20160627',
  1683. 'uploader_id': 'GENOCIDE8GENERAL10',
  1684. 'uploader': 'cylus cyrus',
  1685. },
  1686. },
  1687. {
  1688. # video stored on custom kaltura server
  1689. 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
  1690. 'md5': '537617d06e64dfed891fa1593c4b30cc',
  1691. 'info_dict': {
  1692. 'id': '0_1iotm5bh',
  1693. 'ext': 'mp4',
  1694. 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
  1695. 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
  1696. 'uploader_id': 'videos.expansion@el-mundo.net',
  1697. 'upload_date': '20150429',
  1698. 'timestamp': 1430303472,
  1699. },
  1700. 'add_ie': ['Kaltura'],
  1701. },
  1702. {
  1703. # Non-standard Vimeo embed
  1704. 'url': 'https://openclassrooms.com/courses/understanding-the-web',
  1705. 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
  1706. 'info_dict': {
  1707. 'id': '148867247',
  1708. 'ext': 'mp4',
  1709. 'title': 'Understanding the web - Teaser',
  1710. 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
  1711. 'upload_date': '20151214',
  1712. 'uploader': 'OpenClassrooms',
  1713. 'uploader_id': 'openclassrooms',
  1714. },
  1715. 'add_ie': ['Vimeo'],
  1716. },
  1717. {
  1718. # generic vimeo embed that requires original URL passed as Referer
  1719. 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
  1720. 'only_matching': True,
  1721. },
  1722. {
  1723. 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
  1724. 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
  1725. 'info_dict': {
  1726. 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
  1727. 'ext': 'mp4',
  1728. 'title': 'Big Buck Bunny',
  1729. 'description': 'Royalty free test video',
  1730. 'timestamp': 1432816365,
  1731. 'upload_date': '20150528',
  1732. 'is_live': False,
  1733. },
  1734. 'params': {
  1735. 'skip_download': True,
  1736. },
  1737. 'add_ie': [ArkenaIE.ie_key()],
  1738. },
  1739. {
  1740. '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/',
  1741. 'info_dict': {
  1742. 'id': '1c7141f46c',
  1743. 'ext': 'mp4',
  1744. 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
  1745. },
  1746. 'params': {
  1747. 'skip_download': True,
  1748. },
  1749. 'add_ie': [Vbox7IE.ie_key()],
  1750. },
  1751. {
  1752. # DBTV embeds
  1753. 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
  1754. 'info_dict': {
  1755. 'id': '43254897',
  1756. 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
  1757. },
  1758. 'playlist_mincount': 3,
  1759. },
  1760. {
  1761. # Videa embeds
  1762. 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
  1763. 'info_dict': {
  1764. 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
  1765. 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
  1766. },
  1767. 'playlist_mincount': 2,
  1768. },
  1769. {
  1770. # 20 minuten embed
  1771. 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
  1772. 'info_dict': {
  1773. 'id': '523629',
  1774. 'ext': 'mp4',
  1775. 'title': 'So kommen Sie bei Eis und Schnee sicher an',
  1776. 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
  1777. },
  1778. 'params': {
  1779. 'skip_download': True,
  1780. },
  1781. 'add_ie': [TwentyMinutenIE.ie_key()],
  1782. },
  1783. {
  1784. # VideoPress embed
  1785. 'url': 'https://en.support.wordpress.com/videopress/',
  1786. 'info_dict': {
  1787. 'id': 'OcobLTqC',
  1788. 'ext': 'm4v',
  1789. 'title': 'IMG_5786',
  1790. 'timestamp': 1435711927,
  1791. 'upload_date': '20150701',
  1792. },
  1793. 'params': {
  1794. 'skip_download': True,
  1795. },
  1796. 'add_ie': [VideoPressIE.ie_key()],
  1797. },
  1798. {
  1799. # Rutube embed
  1800. 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
  1801. 'info_dict': {
  1802. 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
  1803. 'ext': 'flv',
  1804. 'title': 'Магаззино: Казань 2',
  1805. 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
  1806. 'uploader': 'Магаззино',
  1807. 'upload_date': '20170228',
  1808. 'uploader_id': '996642',
  1809. },
  1810. 'params': {
  1811. 'skip_download': True,
  1812. },
  1813. 'add_ie': [RutubeIE.ie_key()],
  1814. },
  1815. {
  1816. # ThePlatform embedded with whitespaces in URLs
  1817. 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
  1818. 'only_matching': True,
  1819. },
  1820. {
  1821. # Senate ISVP iframe https
  1822. 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
  1823. 'md5': 'fb8c70b0b515e5037981a2492099aab8',
  1824. 'info_dict': {
  1825. 'id': 'govtaff020316',
  1826. 'ext': 'mp4',
  1827. 'title': 'Integrated Senate Video Player',
  1828. },
  1829. 'add_ie': [SenateISVPIE.ie_key()],
  1830. },
  1831. {
  1832. # Limelight embeds (1 channel embed + 4 media embeds)
  1833. 'url': 'http://www.sedona.com/FacilitatorTraining2017',
  1834. 'info_dict': {
  1835. 'id': 'FacilitatorTraining2017',
  1836. 'title': 'Facilitator Training 2017',
  1837. },
  1838. 'playlist_mincount': 5,
  1839. },
  1840. {
  1841. # Limelight embed (LimelightPlayerUtil.embed)
  1842. 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
  1843. 'info_dict': {
  1844. 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
  1845. 'ext': 'mp4',
  1846. 'title': '07448641',
  1847. 'timestamp': 1499890639,
  1848. 'upload_date': '20170712',
  1849. },
  1850. 'params': {
  1851. 'skip_download': True,
  1852. },
  1853. 'add_ie': ['LimelightMedia'],
  1854. },
  1855. {
  1856. 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
  1857. 'info_dict': {
  1858. 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
  1859. 'title': 'Standoff with Walnut Creek murder suspect ends',
  1860. 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
  1861. },
  1862. 'playlist_mincount': 4,
  1863. },
  1864. {
  1865. # WashingtonPost embed
  1866. 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
  1867. 'info_dict': {
  1868. 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
  1869. 'ext': 'mp4',
  1870. 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
  1871. '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.',
  1872. 'timestamp': 1455216756,
  1873. 'uploader': 'The Washington Post',
  1874. 'upload_date': '20160211',
  1875. },
  1876. 'add_ie': [WashingtonPostIE.ie_key()],
  1877. },
  1878. {
  1879. # Mediaset embed
  1880. 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
  1881. 'info_dict': {
  1882. 'id': '720642',
  1883. 'ext': 'mp4',
  1884. 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
  1885. },
  1886. 'params': {
  1887. 'skip_download': True,
  1888. },
  1889. 'add_ie': [MediasetIE.ie_key()],
  1890. },
  1891. {
  1892. # JOJ.sk embeds
  1893. 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1894. 'info_dict': {
  1895. 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1896. 'title': 'Slovenskom sa prehnala vlna silných búrok',
  1897. },
  1898. 'playlist_mincount': 5,
  1899. 'add_ie': [JojIE.ie_key()],
  1900. },
  1901. {
  1902. # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
  1903. 'url': 'https://tvrain.ru/amp/418921/',
  1904. 'md5': 'cc00413936695987e8de148b67d14f1d',
  1905. 'info_dict': {
  1906. 'id': '418921',
  1907. 'ext': 'mp4',
  1908. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1909. },
  1910. },
  1911. {
  1912. # vzaar embed
  1913. 'url': 'http://help.vzaar.com/article/165-embedding-video',
  1914. 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
  1915. 'info_dict': {
  1916. 'id': '8707641',
  1917. 'ext': 'mp4',
  1918. 'title': 'Building A Business Online: Principal Chairs Q & A',
  1919. },
  1920. },
  1921. {
  1922. # multiple HTML5 videos on one page
  1923. 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
  1924. 'info_dict': {
  1925. 'id': 'keyscenarios',
  1926. 'title': 'Rescue Kit 14 Free Edition - Getting started',
  1927. },
  1928. 'playlist_count': 4,
  1929. },
  1930. {
  1931. # vshare embed
  1932. 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
  1933. 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
  1934. 'info_dict': {
  1935. 'id': '0f64ce6',
  1936. 'title': 'vl14062007715967',
  1937. 'ext': 'mp4',
  1938. }
  1939. },
  1940. {
  1941. 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
  1942. 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
  1943. 'info_dict': {
  1944. 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
  1945. 'ext': 'mp4',
  1946. 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
  1947. 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
  1948. 'timestamp': 1474354800,
  1949. 'upload_date': '20160920',
  1950. }
  1951. },
  1952. {
  1953. 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
  1954. 'info_dict': {
  1955. 'id': '1731611',
  1956. 'ext': 'mp4',
  1957. 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
  1958. 'description': 'md5:eb5f23826a027ba95277d105f248b825',
  1959. 'timestamp': 1516100691,
  1960. 'upload_date': '20180116',
  1961. },
  1962. 'params': {
  1963. 'skip_download': True,
  1964. },
  1965. 'add_ie': [SpringboardPlatformIE.ie_key()],
  1966. },
  1967. {
  1968. 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
  1969. 'info_dict': {
  1970. 'id': 'uPDB5I9wfp8',
  1971. 'ext': 'webm',
  1972. 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
  1973. 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
  1974. 'upload_date': '20160219',
  1975. 'uploader': 'Pocoyo - Português (BR)',
  1976. 'uploader_id': 'PocoyoBrazil',
  1977. },
  1978. 'add_ie': [YoutubeIE.ie_key()],
  1979. 'params': {
  1980. 'skip_download': True,
  1981. },
  1982. },
  1983. {
  1984. 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
  1985. 'info_dict': {
  1986. 'id': 'vMDE4NzI1Mjgt690b',
  1987. 'ext': 'mp4',
  1988. 'title': 'Котята',
  1989. },
  1990. 'add_ie': [YapFilesIE.ie_key()],
  1991. 'params': {
  1992. 'skip_download': True,
  1993. },
  1994. },
  1995. {
  1996. # CloudflareStream embed
  1997. 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
  1998. 'info_dict': {
  1999. 'id': '31c9291ab41fac05471db4e73aa11717',
  2000. 'ext': 'mp4',
  2001. 'title': '31c9291ab41fac05471db4e73aa11717',
  2002. },
  2003. 'add_ie': [CloudflareStreamIE.ie_key()],
  2004. 'params': {
  2005. 'skip_download': True,
  2006. },
  2007. },
  2008. {
  2009. # PeerTube embed
  2010. 'url': 'https://joinpeertube.org/fr/home/',
  2011. 'info_dict': {
  2012. 'id': 'home',
  2013. 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
  2014. },
  2015. 'playlist_count': 2,
  2016. },
  2017. {
  2018. # Indavideo embed
  2019. 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
  2020. 'info_dict': {
  2021. 'id': '1693903',
  2022. 'ext': 'mp4',
  2023. 'title': 'Így kell otthon hamburgert sütni',
  2024. 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
  2025. 'timestamp': 1426330212,
  2026. 'upload_date': '20150314',
  2027. 'uploader': 'StreetKitchen',
  2028. 'uploader_id': '546363',
  2029. },
  2030. 'add_ie': [IndavideoEmbedIE.ie_key()],
  2031. 'params': {
  2032. 'skip_download': True,
  2033. },
  2034. },
  2035. {
  2036. # APA embed via JWPlatform embed
  2037. 'url': 'http://www.vol.at/blue-man-group/5593454',
  2038. 'info_dict': {
  2039. 'id': 'jjv85FdZ',
  2040. 'ext': 'mp4',
  2041. 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
  2042. 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  2043. 'thumbnail': r're:^https?://.*\.jpg$',
  2044. 'duration': 254,
  2045. 'timestamp': 1519211149,
  2046. 'upload_date': '20180221',
  2047. },
  2048. 'params': {
  2049. 'skip_download': True,
  2050. },
  2051. },
  2052. {
  2053. 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
  2054. 'md5': 'b68d276de422ab07ee1d49388103f457',
  2055. 'info_dict': {
  2056. 'id': '83645793',
  2057. 'title': 'Lock up and get excited',
  2058. 'ext': 'mp4'
  2059. },
  2060. 'skip': 'TODO: fix nested playlists processing in tests',
  2061. },
  2062. {
  2063. # Viqeo embeds
  2064. 'url': 'https://viqeo.tv/',
  2065. 'info_dict': {
  2066. 'id': 'viqeo',
  2067. 'title': 'All-new video platform',
  2068. },
  2069. 'playlist_count': 6,
  2070. },
  2071. {
  2072. # Squarespace video embed, 2019-08-28
  2073. 'url': 'http://ootboxford.com',
  2074. 'info_dict': {
  2075. 'id': 'Tc7b_JGdZfw',
  2076. 'title': 'Out of the Blue, at Childish Things 10',
  2077. 'ext': 'mp4',
  2078. 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
  2079. 'uploader_id': 'helendouglashouse',
  2080. 'uploader': 'Helen & Douglas House',
  2081. 'upload_date': '20140328',
  2082. },
  2083. 'params': {
  2084. 'skip_download': True,
  2085. },
  2086. },
  2087. {
  2088. # Zype embed
  2089. 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
  2090. 'info_dict': {
  2091. 'id': '5b400b834b32992a310622b9',
  2092. 'ext': 'mp4',
  2093. 'title': 'Smoky Barbecue Favorites',
  2094. 'thumbnail': r're:^https?://.*\.jpe?g',
  2095. },
  2096. 'add_ie': [ZypeIE.ie_key()],
  2097. 'params': {
  2098. 'skip_download': True,
  2099. },
  2100. },
  2101. {
  2102. # videojs embed
  2103. 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
  2104. 'info_dict': {
  2105. 'id': 'shell',
  2106. 'ext': 'mp4',
  2107. 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
  2108. 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
  2109. 'thumbnail': r're:^https?://.*\.jpg$',
  2110. },
  2111. 'params': {
  2112. 'skip_download': True,
  2113. },
  2114. 'expected_warnings': ['Failed to download MPD manifest'],
  2115. },
  2116. {
  2117. # DailyMotion embed with DM.player
  2118. 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
  2119. 'info_dict': {
  2120. 'id': 'k6aKkGHd9FJs4mtJN39',
  2121. 'ext': 'mp4',
  2122. 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
  2123. 'description': 'This video is private.',
  2124. 'uploader_id': 'x1jf30l',
  2125. 'uploader': 'beIN SPORTS USA',
  2126. 'upload_date': '20190528',
  2127. 'timestamp': 1559062971,
  2128. },
  2129. 'params': {
  2130. 'skip_download': True,
  2131. },
  2132. },
  2133. # {
  2134. # # TODO: find another test
  2135. # # http://schema.org/VideoObject
  2136. # 'url': 'https://flipagram.com/f/nyvTSJMKId',
  2137. # 'md5': '888dcf08b7ea671381f00fab74692755',
  2138. # 'info_dict': {
  2139. # 'id': 'nyvTSJMKId',
  2140. # 'ext': 'mp4',
  2141. # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
  2142. # 'description': '#love for cats.',
  2143. # 'timestamp': 1461244995,
  2144. # 'upload_date': '20160421',
  2145. # },
  2146. # 'params': {
  2147. # 'force_generic_extractor': True,
  2148. # },
  2149. # }
  2150. ]
  2151. def report_following_redirect(self, new_url):
  2152. """Report information extraction."""
  2153. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  2154. def _extract_rss(self, url, video_id, doc):
  2155. playlist_title = doc.find('./channel/title').text
  2156. playlist_desc_el = doc.find('./channel/description')
  2157. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  2158. entries = []
  2159. for it in doc.findall('./channel/item'):
  2160. next_url = None
  2161. enclosure_nodes = it.findall('./enclosure')
  2162. for e in enclosure_nodes:
  2163. next_url = e.attrib.get('url')
  2164. if next_url:
  2165. break
  2166. if not next_url:
  2167. next_url = xpath_text(it, 'link', fatal=False)
  2168. if not next_url:
  2169. continue
  2170. entries.append({
  2171. '_type': 'url_transparent',
  2172. 'url': next_url,
  2173. 'title': it.find('title').text,
  2174. })
  2175. return {
  2176. '_type': 'playlist',
  2177. 'id': url,
  2178. 'title': playlist_title,
  2179. 'description': playlist_desc,
  2180. 'entries': entries,
  2181. }
  2182. def _extract_camtasia(self, url, video_id, webpage):
  2183. """ Returns None if no camtasia video can be found. """
  2184. camtasia_cfg = self._search_regex(
  2185. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  2186. webpage, 'camtasia configuration file', default=None)
  2187. if camtasia_cfg is None:
  2188. return None
  2189. title = self._html_search_meta('DC.title', webpage, fatal=True)
  2190. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  2191. camtasia_cfg = self._download_xml(
  2192. camtasia_url, video_id,
  2193. note='Downloading camtasia configuration',
  2194. errnote='Failed to download camtasia configuration')
  2195. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  2196. entries = []
  2197. for n in fileset_node.getchildren():
  2198. url_n = n.find('./uri')
  2199. if url_n is None:
  2200. continue
  2201. entries.append({
  2202. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  2203. 'title': '%s - %s' % (title, n.tag),
  2204. 'url': compat_urlparse.urljoin(url, url_n.text),
  2205. 'duration': float_or_none(n.find('./duration').text),
  2206. })
  2207. return {
  2208. '_type': 'playlist',
  2209. 'entries': entries,
  2210. 'title': title,
  2211. }
  2212. def _real_extract(self, url):
  2213. if url.startswith('//'):
  2214. return self.url_result(self.http_scheme() + url)
  2215. parsed_url = compat_urlparse.urlparse(url)
  2216. if not parsed_url.scheme:
  2217. default_search = self._downloader.params.get('default_search')
  2218. if default_search is None:
  2219. default_search = 'fixup_error'
  2220. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  2221. if re.match(r'^[^\s/]+\.[^\s/]+/', url):
  2222. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  2223. return self.url_result('http://' + url)
  2224. elif default_search != 'fixup_error':
  2225. if default_search == 'auto_warning':
  2226. if re.match(r'^(?:url|URL)$', url):
  2227. raise ExtractorError(
  2228. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  2229. expected=True)
  2230. else:
  2231. self._downloader.report_warning(
  2232. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  2233. return self.url_result('ytsearch:' + url)
  2234. if default_search in ('error', 'fixup_error'):
  2235. raise ExtractorError(
  2236. '%r is not a valid URL. '
  2237. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  2238. % (url, url), expected=True)
  2239. else:
  2240. if ':' not in default_search:
  2241. default_search += ':'
  2242. return self.url_result(default_search + url)
  2243. url, smuggled_data = unsmuggle_url(url)
  2244. force_videoid = None
  2245. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  2246. if smuggled_data and 'force_videoid' in smuggled_data:
  2247. force_videoid = smuggled_data['force_videoid']
  2248. video_id = force_videoid
  2249. else:
  2250. video_id = self._generic_id(url)
  2251. self.to_screen('%s: Requesting header' % video_id)
  2252. head_req = HEADRequest(url)
  2253. head_response = self._request_webpage(
  2254. head_req, video_id,
  2255. note=False, errnote='Could not send HEAD request to %s' % url,
  2256. fatal=False)
  2257. if head_response is not False:
  2258. # Check for redirect
  2259. new_url = compat_str(head_response.geturl())
  2260. if url != new_url:
  2261. self.report_following_redirect(new_url)
  2262. if force_videoid:
  2263. new_url = smuggle_url(
  2264. new_url, {'force_videoid': force_videoid})
  2265. return self.url_result(new_url)
  2266. full_response = None
  2267. if head_response is False:
  2268. request = sanitized_Request(url)
  2269. request.add_header('Accept-Encoding', '*')
  2270. full_response = self._request_webpage(request, video_id)
  2271. head_response = full_response
  2272. info_dict = {
  2273. 'id': video_id,
  2274. 'title': self._generic_title(url),
  2275. 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
  2276. }
  2277. # Check for direct link to a video
  2278. content_type = head_response.headers.get('Content-Type', '').lower()
  2279. m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
  2280. if m:
  2281. format_id = compat_str(m.group('format_id'))
  2282. if format_id.endswith('mpegurl'):
  2283. formats = self._extract_m3u8_formats(url, video_id, 'mp4')
  2284. elif format_id == 'f4m':
  2285. formats = self._extract_f4m_formats(url, video_id)
  2286. else:
  2287. formats = [{
  2288. 'format_id': format_id,
  2289. 'url': url,
  2290. 'vcodec': 'none' if m.group('type') == 'audio' else None
  2291. }]
  2292. info_dict['direct'] = True
  2293. self._sort_formats(formats)
  2294. info_dict['formats'] = formats
  2295. return info_dict
  2296. if not self._downloader.params.get('test', False) and not is_intentional:
  2297. force = self._downloader.params.get('force_generic_extractor', False)
  2298. self._downloader.report_warning(
  2299. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  2300. if not full_response:
  2301. request = sanitized_Request(url)
  2302. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  2303. # making it impossible to download only chunk of the file (yet we need only 512kB to
  2304. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  2305. # that will always result in downloading the whole file that is not desirable.
  2306. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  2307. # to accept raw bytes and being able to download only a chunk.
  2308. # It may probably better to solve this by checking Content-Type for application/octet-stream
  2309. # after HEAD request finishes, but not sure if we can rely on this.
  2310. request.add_header('Accept-Encoding', '*')
  2311. full_response = self._request_webpage(request, video_id)
  2312. first_bytes = full_response.read(512)
  2313. # Is it an M3U playlist?
  2314. if first_bytes.startswith(b'#EXTM3U'):
  2315. info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
  2316. self._sort_formats(info_dict['formats'])
  2317. return info_dict
  2318. # Maybe it's a direct link to a video?
  2319. # Be careful not to download the whole thing!
  2320. if not is_html(first_bytes):
  2321. self._downloader.report_warning(
  2322. 'URL could be a direct video link, returning it as such.')
  2323. info_dict.update({
  2324. 'direct': True,
  2325. 'url': url,
  2326. })
  2327. return info_dict
  2328. webpage = self._webpage_read_content(
  2329. full_response, url, video_id, prefix=first_bytes)
  2330. self.report_extraction(video_id)
  2331. # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
  2332. try:
  2333. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  2334. if doc.tag == 'rss':
  2335. return self._extract_rss(url, video_id, doc)
  2336. elif doc.tag == 'SmoothStreamingMedia':
  2337. info_dict['formats'] = self._parse_ism_formats(doc, url)
  2338. self._sort_formats(info_dict['formats'])
  2339. return info_dict
  2340. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  2341. smil = self._parse_smil(doc, url, video_id)
  2342. self._sort_formats(smil['formats'])
  2343. return smil
  2344. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  2345. return self.playlist_result(
  2346. self._parse_xspf(
  2347. doc, video_id, xspf_url=url,
  2348. xspf_base_url=compat_str(full_response.geturl())),
  2349. video_id)
  2350. elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
  2351. info_dict['formats'] = self._parse_mpd_formats(
  2352. doc,
  2353. mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
  2354. mpd_url=url)
  2355. self._sort_formats(info_dict['formats'])
  2356. return info_dict
  2357. elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
  2358. info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
  2359. self._sort_formats(info_dict['formats'])
  2360. return info_dict
  2361. except compat_xml_parse_error:
  2362. pass
  2363. # Is it a Camtasia project?
  2364. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  2365. if camtasia_res is not None:
  2366. return camtasia_res
  2367. # Sometimes embedded video player is hidden behind percent encoding
  2368. # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
  2369. # Unescaping the whole page allows to handle those cases in a generic way
  2370. webpage = compat_urllib_parse_unquote(webpage)
  2371. # Unescape squarespace embeds to be detected by generic extractor,
  2372. # see https://github.com/ytdl-org/youtube-dl/issues/21294
  2373. webpage = re.sub(
  2374. r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
  2375. lambda x: unescapeHTML(x.group(0)), webpage)
  2376. # it's tempting to parse this further, but you would
  2377. # have to take into account all the variations like
  2378. # Video Title - Site Name
  2379. # Site Name | Video Title
  2380. # Video Title - Tagline | Site Name
  2381. # and so on and so forth; it's just not practical
  2382. video_title = self._og_search_title(
  2383. webpage, default=None) or self._html_search_regex(
  2384. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  2385. default='video')
  2386. # Try to detect age limit automatically
  2387. age_limit = self._rta_search(webpage)
  2388. # And then there are the jokers who advertise that they use RTA,
  2389. # but actually don't.
  2390. AGE_LIMIT_MARKERS = [
  2391. r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
  2392. ]
  2393. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  2394. age_limit = 18
  2395. # video uploader is domain name
  2396. video_uploader = self._search_regex(
  2397. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  2398. video_description = self._og_search_description(webpage, default=None)
  2399. video_thumbnail = self._og_search_thumbnail(webpage, default=None)
  2400. info_dict.update({
  2401. 'title': video_title,
  2402. 'description': video_description,
  2403. 'thumbnail': video_thumbnail,
  2404. 'age_limit': age_limit,
  2405. })
  2406. # Look for Brightcove Legacy Studio embeds
  2407. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  2408. if bc_urls:
  2409. entries = [{
  2410. '_type': 'url',
  2411. 'url': smuggle_url(bc_url, {'Referer': url}),
  2412. 'ie_key': 'BrightcoveLegacy'
  2413. } for bc_url in bc_urls]
  2414. return {
  2415. '_type': 'playlist',
  2416. 'title': video_title,
  2417. 'id': video_id,
  2418. 'entries': entries,
  2419. }
  2420. # Look for Brightcove New Studio embeds
  2421. bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
  2422. if bc_urls:
  2423. return self.playlist_from_matches(
  2424. bc_urls, video_id, video_title,
  2425. getter=lambda x: smuggle_url(x, {'referrer': url}),
  2426. ie='BrightcoveNew')
  2427. # Look for Nexx embeds
  2428. nexx_urls = NexxIE._extract_urls(webpage)
  2429. if nexx_urls:
  2430. return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
  2431. # Look for Nexx iFrame embeds
  2432. nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
  2433. if nexx_embed_urls:
  2434. return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
  2435. # Look for ThePlatform embeds
  2436. tp_urls = ThePlatformIE._extract_urls(webpage)
  2437. if tp_urls:
  2438. return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
  2439. # Look for embedded rtl.nl player
  2440. matches = re.findall(
  2441. r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
  2442. webpage)
  2443. if matches:
  2444. return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
  2445. vimeo_urls = VimeoIE._extract_urls(url, webpage)
  2446. if vimeo_urls:
  2447. return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
  2448. vid_me_embed_url = self._search_regex(
  2449. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  2450. webpage, 'vid.me embed', default=None)
  2451. if vid_me_embed_url is not None:
  2452. return self.url_result(vid_me_embed_url, 'Vidme')
  2453. # Look for YouTube embeds
  2454. youtube_urls = YoutubeIE._extract_urls(webpage)
  2455. if youtube_urls:
  2456. return self.playlist_from_matches(
  2457. youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
  2458. matches = DailymotionIE._extract_urls(webpage)
  2459. if matches:
  2460. return self.playlist_from_matches(matches, video_id, video_title)
  2461. # Look for embedded Dailymotion playlist player (#3822)
  2462. m = re.search(
  2463. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  2464. if m:
  2465. playlists = re.findall(
  2466. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  2467. if playlists:
  2468. return self.playlist_from_matches(
  2469. playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
  2470. # Look for DailyMail embeds
  2471. dailymail_urls = DailyMailIE._extract_urls(webpage)
  2472. if dailymail_urls:
  2473. return self.playlist_from_matches(
  2474. dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
  2475. # Look for embedded Wistia player
  2476. wistia_url = WistiaIE._extract_url(webpage)
  2477. if wistia_url:
  2478. return {
  2479. '_type': 'url_transparent',
  2480. 'url': self._proto_relative_url(wistia_url),
  2481. 'ie_key': WistiaIE.ie_key(),
  2482. 'uploader': video_uploader,
  2483. }
  2484. # Look for SVT player
  2485. svt_url = SVTIE._extract_url(webpage)
  2486. if svt_url:
  2487. return self.url_result(svt_url, 'SVT')
  2488. # Look for Bandcamp pages with custom domain
  2489. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  2490. if mobj is not None:
  2491. burl = unescapeHTML(mobj.group(1))
  2492. # Don't set the extractor because it can be a track url or an album
  2493. return self.url_result(burl)
  2494. # Look for embedded Vevo player
  2495. mobj = re.search(
  2496. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  2497. if mobj is not None:
  2498. return self.url_result(mobj.group('url'))
  2499. # Look for embedded Viddler player
  2500. mobj = re.search(
  2501. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  2502. webpage)
  2503. if mobj is not None:
  2504. return self.url_result(mobj.group('url'))
  2505. # Look for NYTimes player
  2506. mobj = re.search(
  2507. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  2508. webpage)
  2509. if mobj is not None:
  2510. return self.url_result(mobj.group('url'))
  2511. # Look for Libsyn player
  2512. mobj = re.search(
  2513. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  2514. if mobj is not None:
  2515. return self.url_result(mobj.group('url'))
  2516. # Look for Ooyala videos
  2517. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
  2518. or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
  2519. or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
  2520. or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
  2521. or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  2522. if mobj is not None:
  2523. embed_token = self._search_regex(
  2524. r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
  2525. webpage, 'ooyala embed token', default=None)
  2526. return OoyalaIE._build_url_result(smuggle_url(
  2527. mobj.group('ec'), {
  2528. 'domain': url,
  2529. 'embed_token': embed_token,
  2530. }))
  2531. # Look for multiple Ooyala embeds on SBN network websites
  2532. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  2533. if mobj is not None:
  2534. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  2535. if embeds:
  2536. return self.playlist_from_matches(
  2537. embeds, video_id, video_title,
  2538. getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  2539. # Look for Aparat videos
  2540. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  2541. if mobj is not None:
  2542. return self.url_result(mobj.group(1), 'Aparat')
  2543. # Look for MPORA videos
  2544. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  2545. if mobj is not None:
  2546. return self.url_result(mobj.group(1), 'Mpora')
  2547. # Look for embedded Facebook player
  2548. facebook_urls = FacebookIE._extract_urls(webpage)
  2549. if facebook_urls:
  2550. return self.playlist_from_matches(facebook_urls, video_id, video_title)
  2551. # Look for embedded VK player
  2552. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  2553. if mobj is not None:
  2554. return self.url_result(mobj.group('url'), 'VK')
  2555. # Look for embedded Odnoklassniki player
  2556. odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
  2557. if odnoklassniki_url:
  2558. return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
  2559. # Look for embedded ivi player
  2560. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  2561. if mobj is not None:
  2562. return self.url_result(mobj.group('url'), 'Ivi')
  2563. # Look for embedded Huffington Post player
  2564. mobj = re.search(
  2565. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  2566. if mobj is not None:
  2567. return self.url_result(mobj.group('url'), 'HuffPost')
  2568. # Look for embed.ly
  2569. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  2570. if mobj is not None:
  2571. return self.url_result(mobj.group('url'))
  2572. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  2573. if mobj is not None:
  2574. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  2575. # Look for funnyordie embed
  2576. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  2577. if matches:
  2578. return self.playlist_from_matches(
  2579. matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
  2580. # Look for BBC iPlayer embed
  2581. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  2582. if matches:
  2583. return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
  2584. # Look for embedded RUTV player
  2585. rutv_url = RUTVIE._extract_url(webpage)
  2586. if rutv_url:
  2587. return self.url_result(rutv_url, 'RUTV')
  2588. # Look for embedded TVC player
  2589. tvc_url = TVCIE._extract_url(webpage)
  2590. if tvc_url:
  2591. return self.url_result(tvc_url, 'TVC')
  2592. # Look for embedded SportBox player
  2593. sportbox_urls = SportBoxIE._extract_urls(webpage)
  2594. if sportbox_urls:
  2595. return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
  2596. # Look for embedded XHamster player
  2597. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  2598. if xhamster_urls:
  2599. return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
  2600. # Look for embedded TNAFlixNetwork player
  2601. tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
  2602. if tnaflix_urls:
  2603. return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
  2604. # Look for embedded PornHub player
  2605. pornhub_urls = PornHubIE._extract_urls(webpage)
  2606. if pornhub_urls:
  2607. return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
  2608. # Look for embedded DrTuber player
  2609. drtuber_urls = DrTuberIE._extract_urls(webpage)
  2610. if drtuber_urls:
  2611. return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
  2612. # Look for embedded RedTube player
  2613. redtube_urls = RedTubeIE._extract_urls(webpage)
  2614. if redtube_urls:
  2615. return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
  2616. # Look for embedded Tube8 player
  2617. tube8_urls = Tube8IE._extract_urls(webpage)
  2618. if tube8_urls:
  2619. return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
  2620. # Look for embedded Tvigle player
  2621. mobj = re.search(
  2622. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  2623. if mobj is not None:
  2624. return self.url_result(mobj.group('url'), 'Tvigle')
  2625. # Look for embedded TED player
  2626. mobj = re.search(
  2627. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  2628. if mobj is not None:
  2629. return self.url_result(mobj.group('url'), 'TED')
  2630. # Look for embedded Ustream videos
  2631. ustream_url = UstreamIE._extract_url(webpage)
  2632. if ustream_url:
  2633. return self.url_result(ustream_url, UstreamIE.ie_key())
  2634. # Look for embedded arte.tv player
  2635. mobj = re.search(
  2636. r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
  2637. webpage)
  2638. if mobj is not None:
  2639. return self.url_result(mobj.group('url'), 'ArteTVEmbed')
  2640. # Look for embedded francetv player
  2641. mobj = re.search(
  2642. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  2643. webpage)
  2644. if mobj is not None:
  2645. return self.url_result(mobj.group('url'))
  2646. # Look for embedded smotri.com player
  2647. smotri_url = SmotriIE._extract_url(webpage)
  2648. if smotri_url:
  2649. return self.url_result(smotri_url, 'Smotri')
  2650. # Look for embedded Myvi.ru player
  2651. myvi_url = MyviIE._extract_url(webpage)
  2652. if myvi_url:
  2653. return self.url_result(myvi_url)
  2654. # Look for embedded soundcloud player
  2655. soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
  2656. if soundcloud_urls:
  2657. return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
  2658. # Look for tunein player
  2659. tunein_urls = TuneInBaseIE._extract_urls(webpage)
  2660. if tunein_urls:
  2661. return self.playlist_from_matches(tunein_urls, video_id, video_title)
  2662. # Look for embedded mtvservices player
  2663. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  2664. if mtvservices_url:
  2665. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  2666. # Look for embedded yahoo player
  2667. mobj = re.search(
  2668. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  2669. webpage)
  2670. if mobj is not None:
  2671. return self.url_result(mobj.group('url'), 'Yahoo')
  2672. # Look for embedded sbs.com.au player
  2673. mobj = re.search(
  2674. r'''(?x)
  2675. (?:
  2676. <meta\s+property="og:video"\s+content=|
  2677. <iframe[^>]+?src=
  2678. )
  2679. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  2680. webpage)
  2681. if mobj is not None:
  2682. return self.url_result(mobj.group('url'), 'SBS')
  2683. # Look for embedded Cinchcast player
  2684. mobj = re.search(
  2685. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  2686. webpage)
  2687. if mobj is not None:
  2688. return self.url_result(mobj.group('url'), 'Cinchcast')
  2689. mobj = re.search(
  2690. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  2691. webpage)
  2692. if not mobj:
  2693. mobj = re.search(
  2694. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  2695. webpage)
  2696. if mobj is not None:
  2697. return self.url_result(mobj.group('url'), 'MLB')
  2698. mobj = re.search(
  2699. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  2700. webpage)
  2701. if mobj is not None:
  2702. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  2703. mobj = re.search(
  2704. r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
  2705. webpage)
  2706. if mobj is not None:
  2707. return self.url_result(mobj.group('url'), 'Livestream')
  2708. # Look for Zapiks embed
  2709. mobj = re.search(
  2710. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  2711. if mobj is not None:
  2712. return self.url_result(mobj.group('url'), 'Zapiks')
  2713. # Look for Kaltura embeds
  2714. kaltura_url = KalturaIE._extract_url(webpage)
  2715. if kaltura_url:
  2716. return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
  2717. # Look for EaglePlatform embeds
  2718. eagleplatform_url = EaglePlatformIE._extract_url(webpage)
  2719. if eagleplatform_url:
  2720. return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
  2721. # Look for ClipYou (uses EaglePlatform) embeds
  2722. mobj = re.search(
  2723. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  2724. if mobj is not None:
  2725. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  2726. # Look for Pladform embeds
  2727. pladform_url = PladformIE._extract_url(webpage)
  2728. if pladform_url:
  2729. return self.url_result(pladform_url)
  2730. # Look for Videomore embeds
  2731. videomore_url = VideomoreIE._extract_url(webpage)
  2732. if videomore_url:
  2733. return self.url_result(videomore_url)
  2734. # Look for Webcaster embeds
  2735. webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
  2736. if webcaster_url:
  2737. return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
  2738. # Look for Playwire embeds
  2739. mobj = re.search(
  2740. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  2741. if mobj is not None:
  2742. return self.url_result(mobj.group('url'))
  2743. # Look for 5min embeds
  2744. mobj = re.search(
  2745. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  2746. if mobj is not None:
  2747. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  2748. # Look for Crooks and Liars embeds
  2749. mobj = re.search(
  2750. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  2751. if mobj is not None:
  2752. return self.url_result(mobj.group('url'))
  2753. # Look for NBC Sports VPlayer embeds
  2754. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  2755. if nbc_sports_url:
  2756. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  2757. # Look for NBC News embeds
  2758. nbc_news_embed_url = re.search(
  2759. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
  2760. if nbc_news_embed_url:
  2761. return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
  2762. # Look for Google Drive embeds
  2763. google_drive_url = GoogleDriveIE._extract_url(webpage)
  2764. if google_drive_url:
  2765. return self.url_result(google_drive_url, 'GoogleDrive')
  2766. # Look for UDN embeds
  2767. mobj = re.search(
  2768. r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  2769. if mobj is not None:
  2770. return self.url_result(
  2771. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  2772. # Look for Senate ISVP iframe
  2773. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  2774. if senate_isvp_url:
  2775. return self.url_result(senate_isvp_url, 'SenateISVP')
  2776. # Look for Kinja embeds
  2777. kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
  2778. if kinja_embed_urls:
  2779. return self.playlist_from_matches(
  2780. kinja_embed_urls, video_id, video_title)
  2781. # Look for OnionStudios embeds
  2782. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  2783. if onionstudios_url:
  2784. return self.url_result(onionstudios_url)
  2785. # Look for ViewLift embeds
  2786. viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
  2787. if viewlift_url:
  2788. return self.url_result(viewlift_url)
  2789. # Look for JWPlatform embeds
  2790. jwplatform_urls = JWPlatformIE._extract_urls(webpage)
  2791. if jwplatform_urls:
  2792. return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
  2793. # Look for Digiteka embeds
  2794. digiteka_url = DigitekaIE._extract_url(webpage)
  2795. if digiteka_url:
  2796. return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
  2797. # Look for Arkena embeds
  2798. arkena_url = ArkenaIE._extract_url(webpage)
  2799. if arkena_url:
  2800. return self.url_result(arkena_url, ArkenaIE.ie_key())
  2801. # Look for Piksel embeds
  2802. piksel_url = PikselIE._extract_url(webpage)
  2803. if piksel_url:
  2804. return self.url_result(piksel_url, PikselIE.ie_key())
  2805. # Look for Limelight embeds
  2806. limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
  2807. if limelight_urls:
  2808. return self.playlist_result(
  2809. limelight_urls, video_id, video_title, video_description)
  2810. # Look for Anvato embeds
  2811. anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
  2812. if anvato_urls:
  2813. return self.playlist_result(
  2814. anvato_urls, video_id, video_title, video_description)
  2815. # Look for AdobeTVVideo embeds
  2816. mobj = re.search(
  2817. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  2818. webpage)
  2819. if mobj is not None:
  2820. return self.url_result(
  2821. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  2822. 'AdobeTVVideo')
  2823. # Look for Vine embeds
  2824. mobj = re.search(
  2825. r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
  2826. webpage)
  2827. if mobj is not None:
  2828. return self.url_result(
  2829. self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
  2830. # Look for VODPlatform embeds
  2831. mobj = re.search(
  2832. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
  2833. webpage)
  2834. if mobj is not None:
  2835. return self.url_result(
  2836. self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
  2837. # Look for Mangomolo embeds
  2838. mobj = re.search(
  2839. r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
  2840. (?:
  2841. admin\.mangomolo\.com/analytics/index\.php/customers/embed|
  2842. player\.mangomolo\.com/v1
  2843. )/
  2844. (?:
  2845. video\?.*?\bid=(?P<video_id>\d+)|
  2846. (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
  2847. ).+?)\1''', webpage)
  2848. if mobj is not None:
  2849. info = {
  2850. '_type': 'url_transparent',
  2851. 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
  2852. 'title': video_title,
  2853. 'description': video_description,
  2854. 'thumbnail': video_thumbnail,
  2855. 'uploader': video_uploader,
  2856. }
  2857. video_id = mobj.group('video_id')
  2858. if video_id:
  2859. info.update({
  2860. 'ie_key': 'MangomoloVideo',
  2861. 'id': video_id,
  2862. })
  2863. else:
  2864. info.update({
  2865. 'ie_key': 'MangomoloLive',
  2866. 'id': mobj.group('channel_id'),
  2867. })
  2868. return info
  2869. # Look for Instagram embeds
  2870. instagram_embed_url = InstagramIE._extract_embed_url(webpage)
  2871. if instagram_embed_url is not None:
  2872. return self.url_result(
  2873. self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
  2874. # Look for LiveLeak embeds
  2875. liveleak_urls = LiveLeakIE._extract_urls(webpage)
  2876. if liveleak_urls:
  2877. return self.playlist_from_matches(liveleak_urls, video_id, video_title)
  2878. # Look for 3Q SDN embeds
  2879. threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
  2880. if threeqsdn_url:
  2881. return {
  2882. '_type': 'url_transparent',
  2883. 'ie_key': ThreeQSDNIE.ie_key(),
  2884. 'url': self._proto_relative_url(threeqsdn_url),
  2885. 'title': video_title,
  2886. 'description': video_description,
  2887. 'thumbnail': video_thumbnail,
  2888. 'uploader': video_uploader,
  2889. }
  2890. # Look for VBOX7 embeds
  2891. vbox7_url = Vbox7IE._extract_url(webpage)
  2892. if vbox7_url:
  2893. return self.url_result(vbox7_url, Vbox7IE.ie_key())
  2894. # Look for DBTV embeds
  2895. dbtv_urls = DBTVIE._extract_urls(webpage)
  2896. if dbtv_urls:
  2897. return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
  2898. # Look for Videa embeds
  2899. videa_urls = VideaIE._extract_urls(webpage)
  2900. if videa_urls:
  2901. return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
  2902. # Look for 20 minuten embeds
  2903. twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
  2904. if twentymin_urls:
  2905. return self.playlist_from_matches(
  2906. twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
  2907. # Look for VideoPress embeds
  2908. videopress_urls = VideoPressIE._extract_urls(webpage)
  2909. if videopress_urls:
  2910. return self.playlist_from_matches(
  2911. videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
  2912. # Look for Rutube embeds
  2913. rutube_urls = RutubeIE._extract_urls(webpage)
  2914. if rutube_urls:
  2915. return self.playlist_from_matches(
  2916. rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
  2917. # Look for WashingtonPost embeds
  2918. wapo_urls = WashingtonPostIE._extract_urls(webpage)
  2919. if wapo_urls:
  2920. return self.playlist_from_matches(
  2921. wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
  2922. # Look for Mediaset embeds
  2923. mediaset_urls = MediasetIE._extract_urls(self, webpage)
  2924. if mediaset_urls:
  2925. return self.playlist_from_matches(
  2926. mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
  2927. # Look for JOJ.sk embeds
  2928. joj_urls = JojIE._extract_urls(webpage)
  2929. if joj_urls:
  2930. return self.playlist_from_matches(
  2931. joj_urls, video_id, video_title, ie=JojIE.ie_key())
  2932. # Look for megaphone.fm embeds
  2933. mpfn_urls = MegaphoneIE._extract_urls(webpage)
  2934. if mpfn_urls:
  2935. return self.playlist_from_matches(
  2936. mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
  2937. # Look for vzaar embeds
  2938. vzaar_urls = VzaarIE._extract_urls(webpage)
  2939. if vzaar_urls:
  2940. return self.playlist_from_matches(
  2941. vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
  2942. channel9_urls = Channel9IE._extract_urls(webpage)
  2943. if channel9_urls:
  2944. return self.playlist_from_matches(
  2945. channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
  2946. vshare_urls = VShareIE._extract_urls(webpage)
  2947. if vshare_urls:
  2948. return self.playlist_from_matches(
  2949. vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
  2950. # Look for Mediasite embeds
  2951. mediasite_urls = MediasiteIE._extract_urls(webpage)
  2952. if mediasite_urls:
  2953. entries = [
  2954. self.url_result(smuggle_url(
  2955. compat_urlparse.urljoin(url, mediasite_url),
  2956. {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
  2957. for mediasite_url in mediasite_urls]
  2958. return self.playlist_result(entries, video_id, video_title)
  2959. springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
  2960. if springboardplatform_urls:
  2961. return self.playlist_from_matches(
  2962. springboardplatform_urls, video_id, video_title,
  2963. ie=SpringboardPlatformIE.ie_key())
  2964. yapfiles_urls = YapFilesIE._extract_urls(webpage)
  2965. if yapfiles_urls:
  2966. return self.playlist_from_matches(
  2967. yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
  2968. vice_urls = ViceIE._extract_urls(webpage)
  2969. if vice_urls:
  2970. return self.playlist_from_matches(
  2971. vice_urls, video_id, video_title, ie=ViceIE.ie_key())
  2972. xfileshare_urls = XFileShareIE._extract_urls(webpage)
  2973. if xfileshare_urls:
  2974. return self.playlist_from_matches(
  2975. xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
  2976. cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
  2977. if cloudflarestream_urls:
  2978. return self.playlist_from_matches(
  2979. cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
  2980. peertube_urls = PeerTubeIE._extract_urls(webpage, url)
  2981. if peertube_urls:
  2982. return self.playlist_from_matches(
  2983. peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
  2984. teachable_url = TeachableIE._extract_url(webpage, url)
  2985. if teachable_url:
  2986. return self.url_result(teachable_url)
  2987. indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
  2988. if indavideo_urls:
  2989. return self.playlist_from_matches(
  2990. indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
  2991. apa_urls = APAIE._extract_urls(webpage)
  2992. if apa_urls:
  2993. return self.playlist_from_matches(
  2994. apa_urls, video_id, video_title, ie=APAIE.ie_key())
  2995. foxnews_urls = FoxNewsIE._extract_urls(webpage)
  2996. if foxnews_urls:
  2997. return self.playlist_from_matches(
  2998. foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
  2999. sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
  3000. r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
  3001. webpage)]
  3002. if sharevideos_urls:
  3003. return self.playlist_from_matches(
  3004. sharevideos_urls, video_id, video_title)
  3005. viqeo_urls = ViqeoIE._extract_urls(webpage)
  3006. if viqeo_urls:
  3007. return self.playlist_from_matches(
  3008. viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
  3009. expressen_urls = ExpressenIE._extract_urls(webpage)
  3010. if expressen_urls:
  3011. return self.playlist_from_matches(
  3012. expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
  3013. zype_urls = ZypeIE._extract_urls(webpage)
  3014. if zype_urls:
  3015. return self.playlist_from_matches(
  3016. zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
  3017. # Look for HTML5 media
  3018. entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
  3019. if entries:
  3020. if len(entries) == 1:
  3021. entries[0].update({
  3022. 'id': video_id,
  3023. 'title': video_title,
  3024. })
  3025. else:
  3026. for num, entry in enumerate(entries, start=1):
  3027. entry.update({
  3028. 'id': '%s-%s' % (video_id, num),
  3029. 'title': '%s (%d)' % (video_title, num),
  3030. })
  3031. for entry in entries:
  3032. self._sort_formats(entry['formats'])
  3033. return self.playlist_result(entries, video_id, video_title)
  3034. jwplayer_data = self._find_jwplayer_data(
  3035. webpage, video_id, transform_source=js_to_json)
  3036. if jwplayer_data:
  3037. try:
  3038. info = self._parse_jwplayer_data(
  3039. jwplayer_data, video_id, require_title=False, base_url=url)
  3040. return merge_dicts(info, info_dict)
  3041. except ExtractorError:
  3042. # See https://github.com/ytdl-org/youtube-dl/pull/16735
  3043. pass
  3044. # Video.js embed
  3045. mobj = re.search(
  3046. r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
  3047. webpage)
  3048. if mobj is not None:
  3049. sources = self._parse_json(
  3050. mobj.group(1), video_id, transform_source=js_to_json,
  3051. fatal=False) or []
  3052. if not isinstance(sources, list):
  3053. sources = [sources]
  3054. formats = []
  3055. for source in sources:
  3056. src = source.get('src')
  3057. if not src or not isinstance(src, compat_str):
  3058. continue
  3059. src = compat_urlparse.urljoin(url, src)
  3060. src_type = source.get('type')
  3061. if isinstance(src_type, compat_str):
  3062. src_type = src_type.lower()
  3063. ext = determine_ext(src).lower()
  3064. if src_type == 'video/youtube':
  3065. return self.url_result(src, YoutubeIE.ie_key())
  3066. if src_type == 'application/dash+xml' or ext == 'mpd':
  3067. formats.extend(self._extract_mpd_formats(
  3068. src, video_id, mpd_id='dash', fatal=False))
  3069. elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
  3070. formats.extend(self._extract_m3u8_formats(
  3071. src, video_id, 'mp4', entry_protocol='m3u8_native',
  3072. m3u8_id='hls', fatal=False))
  3073. else:
  3074. formats.append({
  3075. 'url': src,
  3076. 'ext': (mimetype2ext(src_type)
  3077. or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
  3078. })
  3079. if formats:
  3080. self._sort_formats(formats)
  3081. info_dict['formats'] = formats
  3082. return info_dict
  3083. # Looking for http://schema.org/VideoObject
  3084. json_ld = self._search_json_ld(
  3085. webpage, video_id, default={}, expected_type='VideoObject')
  3086. if json_ld.get('url'):
  3087. return merge_dicts(json_ld, info_dict)
  3088. def check_video(vurl):
  3089. if YoutubeIE.suitable(vurl):
  3090. return True
  3091. if RtmpIE.suitable(vurl):
  3092. return True
  3093. vpath = compat_urlparse.urlparse(vurl).path
  3094. vext = determine_ext(vpath)
  3095. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
  3096. def filter_video(urls):
  3097. return list(filter(check_video, urls))
  3098. # Start with something easy: JW Player in SWFObject
  3099. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  3100. if not found:
  3101. # Look for gorilla-vid style embedding
  3102. found = filter_video(re.findall(r'''(?sx)
  3103. (?:
  3104. jw_plugins|
  3105. JWPlayerOptions|
  3106. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  3107. )
  3108. .*?
  3109. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  3110. if not found:
  3111. # Broaden the search a little bit
  3112. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  3113. if not found:
  3114. # Broaden the findall a little bit: JWPlayer JS loader
  3115. found = filter_video(re.findall(
  3116. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  3117. if not found:
  3118. # Flow player
  3119. found = filter_video(re.findall(r'''(?xs)
  3120. flowplayer\("[^"]+",\s*
  3121. \{[^}]+?\}\s*,
  3122. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  3123. ["']?url["']?\s*:\s*["']([^"']+)["']
  3124. ''', webpage))
  3125. if not found:
  3126. # Cinerama player
  3127. found = re.findall(
  3128. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  3129. if not found:
  3130. # Try to find twitter cards info
  3131. # twitter:player:stream should be checked before twitter:player since
  3132. # it is expected to contain a raw stream (see
  3133. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  3134. found = filter_video(re.findall(
  3135. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  3136. if not found:
  3137. # We look for Open Graph info:
  3138. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  3139. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  3140. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  3141. if m_video_type is not None:
  3142. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  3143. if not found:
  3144. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  3145. found = re.search(
  3146. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  3147. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  3148. webpage)
  3149. if not found:
  3150. # Look also in Refresh HTTP header
  3151. refresh_header = head_response.headers.get('Refresh')
  3152. if refresh_header:
  3153. # In python 2 response HTTP headers are bytestrings
  3154. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  3155. refresh_header = refresh_header.decode('iso-8859-1')
  3156. found = re.search(REDIRECT_REGEX, refresh_header)
  3157. if found:
  3158. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  3159. if new_url != url:
  3160. self.report_following_redirect(new_url)
  3161. return {
  3162. '_type': 'url',
  3163. 'url': new_url,
  3164. }
  3165. else:
  3166. found = None
  3167. if not found:
  3168. # twitter:player is a https URL to iframe player that may or may not
  3169. # be supported by youtube-dl thus this is checked the very last (see
  3170. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  3171. embed_url = self._html_search_meta('twitter:player', webpage, default=None)
  3172. if embed_url and embed_url != url:
  3173. return self.url_result(embed_url)
  3174. if not found:
  3175. raise UnsupportedError(url)
  3176. entries = []
  3177. for video_url in orderedSet(found):
  3178. video_url = unescapeHTML(video_url)
  3179. video_url = video_url.replace('\\/', '/')
  3180. video_url = compat_urlparse.urljoin(url, video_url)
  3181. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  3182. # Sometimes, jwplayer extraction will result in a YouTube URL
  3183. if YoutubeIE.suitable(video_url):
  3184. entries.append(self.url_result(video_url, 'Youtube'))
  3185. continue
  3186. # here's a fun little line of code for you:
  3187. video_id = os.path.splitext(video_id)[0]
  3188. entry_info_dict = {
  3189. 'id': video_id,
  3190. 'uploader': video_uploader,
  3191. 'title': video_title,
  3192. 'age_limit': age_limit,
  3193. }
  3194. if RtmpIE.suitable(video_url):
  3195. entry_info_dict.update({
  3196. '_type': 'url_transparent',
  3197. 'ie_key': RtmpIE.ie_key(),
  3198. 'url': video_url,
  3199. })
  3200. entries.append(entry_info_dict)
  3201. continue
  3202. ext = determine_ext(video_url)
  3203. if ext == 'smil':
  3204. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  3205. elif ext == 'xspf':
  3206. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  3207. elif ext == 'm3u8':
  3208. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  3209. elif ext == 'mpd':
  3210. entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
  3211. elif ext == 'f4m':
  3212. entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
  3213. elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
  3214. # Just matching .ism/manifest is not enough to be reliably sure
  3215. # whether it's actually an ISM manifest or some other streaming
  3216. # manifest since there are various streaming URL formats
  3217. # possible (see [1]) as well as some other shenanigans like
  3218. # .smil/manifest URLs that actually serve an ISM (see [2]) and
  3219. # so on.
  3220. # Thus the most reasonable way to solve this is to delegate
  3221. # to generic extractor in order to look into the contents of
  3222. # the manifest itself.
  3223. # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
  3224. # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
  3225. entry_info_dict = self.url_result(
  3226. smuggle_url(video_url, {'to_generic': True}),
  3227. GenericIE.ie_key())
  3228. else:
  3229. entry_info_dict['url'] = video_url
  3230. if entry_info_dict.get('formats'):
  3231. self._sort_formats(entry_info_dict['formats'])
  3232. entries.append(entry_info_dict)
  3233. if len(entries) == 1:
  3234. return entries[0]
  3235. else:
  3236. for num, e in enumerate(entries, start=1):
  3237. # 'url' results don't have a title
  3238. if e.get('title') is not None:
  3239. e['title'] = '%s (%d)' % (e['title'], num)
  3240. return {
  3241. '_type': 'playlist',
  3242. 'entries': entries,
  3243. }