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.

3228 lines
130 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
11 years ago
11 years ago
11 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. mimetype2ext,
  24. orderedSet,
  25. sanitized_Request,
  26. smuggle_url,
  27. unescapeHTML,
  28. unified_strdate,
  29. unsmuggle_url,
  30. UnsupportedError,
  31. xpath_text,
  32. )
  33. from .commonprotocols import RtmpIE
  34. from .brightcove import (
  35. BrightcoveLegacyIE,
  36. BrightcoveNewIE,
  37. )
  38. from .nexx import (
  39. NexxIE,
  40. NexxEmbedIE,
  41. )
  42. from .nbc import NBCSportsVPlayerIE
  43. from .ooyala import OoyalaIE
  44. from .rutv import RUTVIE
  45. from .tvc import TVCIE
  46. from .sportbox import SportBoxEmbedIE
  47. from .smotri import SmotriIE
  48. from .myvi import MyviIE
  49. from .condenast import CondeNastIE
  50. from .udn import UDNEmbedIE
  51. from .senateisvp import SenateISVPIE
  52. from .svt import SVTIE
  53. from .pornhub import PornHubIE
  54. from .xhamster import XHamsterEmbedIE
  55. from .tnaflix import TNAFlixNetworkEmbedIE
  56. from .drtuber import DrTuberIE
  57. from .redtube import RedTubeIE
  58. from .vimeo import VimeoIE
  59. from .dailymotion import DailymotionIE
  60. from .dailymail import DailyMailIE
  61. from .onionstudios import OnionStudiosIE
  62. from .viewlift import ViewLiftEmbedIE
  63. from .mtv import MTVServicesEmbeddedIE
  64. from .pladform import PladformIE
  65. from .videomore import VideomoreIE
  66. from .webcaster import WebcasterFeedIE
  67. from .googledrive import GoogleDriveIE
  68. from .jwplatform import JWPlatformIE
  69. from .digiteka import DigitekaIE
  70. from .arkena import ArkenaIE
  71. from .instagram import InstagramIE
  72. from .liveleak import LiveLeakIE
  73. from .threeqsdn import ThreeQSDNIE
  74. from .theplatform import ThePlatformIE
  75. from .vessel import VesselIE
  76. from .kaltura import KalturaIE
  77. from .eagleplatform import EaglePlatformIE
  78. from .facebook import FacebookIE
  79. from .soundcloud import SoundcloudIE
  80. from .tunein import TuneInBaseIE
  81. from .vbox7 import Vbox7IE
  82. from .dbtv import DBTVIE
  83. from .piksel import PikselIE
  84. from .videa import VideaIE
  85. from .twentymin import TwentyMinutenIE
  86. from .ustream import UstreamIE
  87. from .openload import OpenloadIE
  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. class GenericIE(InfoExtractor):
  105. IE_DESC = 'Generic downloader that works on some sites'
  106. _VALID_URL = r'.*'
  107. IE_NAME = 'generic'
  108. _TESTS = [
  109. # Direct link to a video
  110. {
  111. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  112. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  113. 'info_dict': {
  114. 'id': 'trailer',
  115. 'ext': 'mp4',
  116. 'title': 'trailer',
  117. 'upload_date': '20100513',
  118. }
  119. },
  120. # Direct link to media delivered compressed (until Accept-Encoding is *)
  121. {
  122. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  123. 'md5': '128c42e68b13950268b648275386fc74',
  124. 'info_dict': {
  125. 'id': 'FictionJunction-Parallel_Hearts',
  126. 'ext': 'flac',
  127. 'title': 'FictionJunction-Parallel_Hearts',
  128. 'upload_date': '20140522',
  129. },
  130. 'expected_warnings': [
  131. 'URL could be a direct video link, returning it as such.'
  132. ],
  133. 'skip': 'URL invalid',
  134. },
  135. # Direct download with broken HEAD
  136. {
  137. 'url': 'http://ai-radio.org:8000/radio.opus',
  138. 'info_dict': {
  139. 'id': 'radio',
  140. 'ext': 'opus',
  141. 'title': 'radio',
  142. },
  143. 'params': {
  144. 'skip_download': True, # infinite live stream
  145. },
  146. 'expected_warnings': [
  147. r'501.*Not Implemented',
  148. r'400.*Bad Request',
  149. ],
  150. },
  151. # Direct link with incorrect MIME type
  152. {
  153. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  154. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  155. 'info_dict': {
  156. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  157. 'id': '5_Lennart_Poettering_-_Systemd',
  158. 'ext': 'webm',
  159. 'title': '5_Lennart_Poettering_-_Systemd',
  160. 'upload_date': '20141120',
  161. },
  162. 'expected_warnings': [
  163. 'URL could be a direct video link, returning it as such.'
  164. ]
  165. },
  166. # RSS feed
  167. {
  168. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  169. 'info_dict': {
  170. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  171. 'title': 'Zero Punctuation',
  172. 'description': 're:.*groundbreaking video review series.*'
  173. },
  174. 'playlist_mincount': 11,
  175. },
  176. # RSS feed with enclosure
  177. {
  178. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  179. 'info_dict': {
  180. 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  181. 'ext': 'm4v',
  182. 'upload_date': '20150228',
  183. 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  184. }
  185. },
  186. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  187. {
  188. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  189. 'info_dict': {
  190. 'id': 'smil',
  191. 'ext': 'mp4',
  192. 'title': 'Automatics, robotics and biocybernetics',
  193. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  194. 'upload_date': '20130627',
  195. 'formats': 'mincount:16',
  196. 'subtitles': 'mincount:1',
  197. },
  198. 'params': {
  199. 'force_generic_extractor': True,
  200. 'skip_download': True,
  201. },
  202. },
  203. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  204. {
  205. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  206. 'info_dict': {
  207. 'id': 'hds',
  208. 'ext': 'flv',
  209. 'title': 'hds',
  210. 'formats': 'mincount:1',
  211. },
  212. 'params': {
  213. 'skip_download': True,
  214. },
  215. },
  216. # SMIL from https://www.restudy.dk/video/play/id/1637
  217. {
  218. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  219. 'info_dict': {
  220. 'id': 'video_1637',
  221. 'ext': 'flv',
  222. 'title': 'video_1637',
  223. 'formats': 'mincount:3',
  224. },
  225. 'params': {
  226. 'skip_download': True,
  227. },
  228. },
  229. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  230. {
  231. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  232. 'info_dict': {
  233. 'id': 'smil-service',
  234. 'ext': 'flv',
  235. 'title': 'smil-service',
  236. 'formats': 'mincount:1',
  237. },
  238. 'params': {
  239. 'skip_download': True,
  240. },
  241. },
  242. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  243. {
  244. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  245. 'info_dict': {
  246. 'id': '4719370',
  247. 'ext': 'mp4',
  248. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  249. 'formats': 'mincount:3',
  250. },
  251. 'params': {
  252. 'skip_download': True,
  253. },
  254. },
  255. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  256. {
  257. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  258. 'info_dict': {
  259. 'id': 'mZlp2ctYIUEB',
  260. 'ext': 'mp4',
  261. 'title': 'Tikibad ontruimd wegens brand',
  262. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  263. 'thumbnail': r're:^https?://.*\.jpg$',
  264. 'duration': 33,
  265. },
  266. 'params': {
  267. 'skip_download': True,
  268. },
  269. },
  270. # MPD from http://dash-mse-test.appspot.com/media.html
  271. {
  272. 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
  273. 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
  274. 'info_dict': {
  275. 'id': 'car-20120827-manifest',
  276. 'ext': 'mp4',
  277. 'title': 'car-20120827-manifest',
  278. 'formats': 'mincount:9',
  279. 'upload_date': '20130904',
  280. },
  281. 'params': {
  282. 'format': 'bestvideo',
  283. },
  284. },
  285. # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
  286. {
  287. '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',
  288. 'info_dict': {
  289. 'id': 'content',
  290. 'ext': 'mp4',
  291. 'title': 'content',
  292. 'formats': 'mincount:8',
  293. },
  294. 'params': {
  295. # m3u8 downloads
  296. 'skip_download': True,
  297. },
  298. 'skip': 'video gone',
  299. },
  300. # m3u8 served with Content-Type: text/plain
  301. {
  302. 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
  303. 'info_dict': {
  304. 'id': 'index',
  305. 'ext': 'mp4',
  306. 'title': 'index',
  307. 'upload_date': '20140720',
  308. 'formats': 'mincount:11',
  309. },
  310. 'params': {
  311. # m3u8 downloads
  312. 'skip_download': True,
  313. },
  314. 'skip': 'video gone',
  315. },
  316. # google redirect
  317. {
  318. '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',
  319. 'info_dict': {
  320. 'id': 'cmQHVoWB5FY',
  321. 'ext': 'mp4',
  322. 'upload_date': '20130224',
  323. 'uploader_id': 'TheVerge',
  324. 'description': r're:^Chris Ziegler takes a look at the\.*',
  325. 'uploader': 'The Verge',
  326. 'title': 'First Firefox OS phones side-by-side',
  327. },
  328. 'params': {
  329. 'skip_download': False,
  330. }
  331. },
  332. {
  333. # redirect in Refresh HTTP header
  334. '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',
  335. 'info_dict': {
  336. 'id': 'pO8h3EaFRdo',
  337. 'ext': 'mp4',
  338. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  339. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  340. 'upload_date': '20150917',
  341. 'uploader_id': 'brtvofficial',
  342. 'uploader': 'Boiler Room',
  343. },
  344. 'params': {
  345. 'skip_download': False,
  346. },
  347. },
  348. {
  349. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  350. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  351. 'info_dict': {
  352. 'id': '13601338388002',
  353. 'ext': 'mp4',
  354. 'uploader': 'www.hodiho.fr',
  355. 'title': 'R\u00e9gis plante sa Jeep',
  356. }
  357. },
  358. # bandcamp page with custom domain
  359. {
  360. 'add_ie': ['Bandcamp'],
  361. 'url': 'http://bronyrock.com/track/the-pony-mash',
  362. 'info_dict': {
  363. 'id': '3235767654',
  364. 'ext': 'mp3',
  365. 'title': 'The Pony Mash',
  366. 'uploader': 'M_Pallante',
  367. },
  368. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  369. },
  370. {
  371. # embedded brightcove video
  372. # it also tests brightcove videos that need to set the 'Referer'
  373. # in the http requests
  374. 'add_ie': ['BrightcoveLegacy'],
  375. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  376. 'info_dict': {
  377. 'id': '2765128793001',
  378. 'ext': 'mp4',
  379. 'title': 'Le cours de bourse : l’analyse technique',
  380. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  381. 'uploader': 'BFM BUSINESS',
  382. },
  383. 'params': {
  384. 'skip_download': True,
  385. },
  386. },
  387. {
  388. # embedded with itemprop embedURL and video id spelled as `idVideo`
  389. 'add_id': ['BrightcoveLegacy'],
  390. 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
  391. 'info_dict': {
  392. 'id': '5255628253001',
  393. 'ext': 'mp4',
  394. 'title': 'md5:37c519b1128915607601e75a87995fc0',
  395. 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
  396. 'uploader': 'BFM BUSINESS',
  397. 'uploader_id': '876450612001',
  398. 'timestamp': 1482255315,
  399. 'upload_date': '20161220',
  400. },
  401. 'params': {
  402. 'skip_download': True,
  403. },
  404. },
  405. {
  406. # https://github.com/rg3/youtube-dl/issues/2253
  407. 'url': 'http://bcove.me/i6nfkrc3',
  408. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  409. 'info_dict': {
  410. 'id': '3101154703001',
  411. 'ext': 'mp4',
  412. 'title': 'Still no power',
  413. 'uploader': 'thestar.com',
  414. '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.',
  415. },
  416. 'add_ie': ['BrightcoveLegacy'],
  417. 'skip': 'video gone',
  418. },
  419. {
  420. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  421. 'md5': 'fb973ecf6e4a78a67453647444222983',
  422. 'info_dict': {
  423. 'id': '3414141473001',
  424. 'ext': 'mp4',
  425. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  426. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  427. 'uploader': 'Championat',
  428. },
  429. },
  430. {
  431. # https://github.com/rg3/youtube-dl/issues/3541
  432. 'add_ie': ['BrightcoveLegacy'],
  433. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  434. 'info_dict': {
  435. 'id': '3866516442001',
  436. 'ext': 'mp4',
  437. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  438. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  439. 'uploader': 'SBS Broadcasting',
  440. },
  441. 'skip': 'Restricted to Netherlands',
  442. 'params': {
  443. 'skip_download': True, # m3u8 download
  444. },
  445. },
  446. {
  447. # Brightcove video in <iframe>
  448. 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
  449. 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
  450. 'info_dict': {
  451. 'id': '5360463607001',
  452. 'ext': 'mp4',
  453. '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',
  454. '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。',
  455. 'uploader': 'United Nations',
  456. 'uploader_id': '1362235914001',
  457. 'timestamp': 1489593889,
  458. 'upload_date': '20170315',
  459. },
  460. 'add_ie': ['BrightcoveLegacy'],
  461. },
  462. {
  463. # Brightcove with alternative playerID key
  464. 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
  465. 'info_dict': {
  466. 'id': 'nmeth.2062_SV1',
  467. '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',
  468. },
  469. 'playlist': [{
  470. 'info_dict': {
  471. 'id': '2228375078001',
  472. 'ext': 'mp4',
  473. 'title': 'nmeth.2062-sv1',
  474. 'description': 'nmeth.2062-sv1',
  475. 'timestamp': 1363357591,
  476. 'upload_date': '20130315',
  477. 'uploader': 'Nature Publishing Group',
  478. 'uploader_id': '1964492299001',
  479. },
  480. }],
  481. },
  482. {
  483. # Brightcove with UUID in videoPlayer
  484. 'url': 'http://www8.hp.com/cn/zh/home.html',
  485. 'info_dict': {
  486. 'id': '5255815316001',
  487. 'ext': 'mp4',
  488. 'title': 'Sprocket Video - China',
  489. 'description': 'Sprocket Video - China',
  490. 'uploader': 'HP-Video Gallery',
  491. 'timestamp': 1482263210,
  492. 'upload_date': '20161220',
  493. 'uploader_id': '1107601872001',
  494. },
  495. 'params': {
  496. 'skip_download': True, # m3u8 download
  497. },
  498. 'skip': 'video rotates...weekly?',
  499. },
  500. {
  501. # Brightcove:new type [2].
  502. 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
  503. 'md5': '2b35148fcf48da41c9fb4591650784f3',
  504. 'info_dict': {
  505. 'id': '5348741021001',
  506. 'ext': 'mp4',
  507. 'upload_date': '20170306',
  508. 'uploader_id': '4191638492001',
  509. 'timestamp': 1488769918,
  510. 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
  511. },
  512. },
  513. {
  514. # Alternative brightcove <video> attributes
  515. '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/',
  516. 'info_dict': {
  517. 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
  518. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
  519. },
  520. 'playlist': [{
  521. 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
  522. 'info_dict': {
  523. 'id': '5311302538001',
  524. 'ext': 'mp4',
  525. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
  526. 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
  527. 'timestamp': 1486321708,
  528. 'upload_date': '20170205',
  529. 'uploader_id': '800000640001',
  530. },
  531. 'only_matching': True,
  532. }],
  533. },
  534. {
  535. # Brightcove with UUID in videoPlayer
  536. 'url': 'http://www8.hp.com/cn/zh/home.html',
  537. 'info_dict': {
  538. 'id': '5255815316001',
  539. 'ext': 'mp4',
  540. 'title': 'Sprocket Video - China',
  541. 'description': 'Sprocket Video - China',
  542. 'uploader': 'HP-Video Gallery',
  543. 'timestamp': 1482263210,
  544. 'upload_date': '20161220',
  545. 'uploader_id': '1107601872001',
  546. },
  547. 'params': {
  548. 'skip_download': True, # m3u8 download
  549. },
  550. },
  551. # ooyala video
  552. {
  553. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  554. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  555. 'info_dict': {
  556. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  557. 'ext': 'mp4',
  558. 'title': '2cc213299525360.mov', # that's what we get
  559. 'duration': 238.231,
  560. },
  561. 'add_ie': ['Ooyala'],
  562. },
  563. {
  564. # ooyala video embedded with http://player.ooyala.com/iframe.js
  565. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  566. 'info_dict': {
  567. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  568. 'ext': 'mp4',
  569. 'title': '"Steve Jobs: Man in the Machine" trailer',
  570. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  571. 'duration': 135.427,
  572. },
  573. 'params': {
  574. 'skip_download': True,
  575. },
  576. 'skip': 'movie expired',
  577. },
  578. # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
  579. {
  580. 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
  581. 'info_dict': {
  582. 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
  583. 'ext': 'mp4',
  584. 'title': 'Steampunk Fest Comes to Honesdale',
  585. 'duration': 43.276,
  586. },
  587. 'params': {
  588. 'skip_download': True,
  589. }
  590. },
  591. # embed.ly video
  592. {
  593. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  594. 'info_dict': {
  595. 'id': '9ODmcdjQcHQ',
  596. 'ext': 'mp4',
  597. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  598. 'upload_date': '20140225',
  599. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  600. 'uploader': 'Tested',
  601. 'uploader_id': 'testedcom',
  602. },
  603. # No need to test YoutubeIE here
  604. 'params': {
  605. 'skip_download': True,
  606. },
  607. },
  608. # funnyordie embed
  609. {
  610. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  611. 'info_dict': {
  612. 'id': '18e820ec3f',
  613. 'ext': 'mp4',
  614. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  615. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  616. },
  617. # HEAD requests lead to endless 301, while GET is OK
  618. 'expected_warnings': ['301'],
  619. },
  620. # RUTV embed
  621. {
  622. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  623. 'info_dict': {
  624. 'id': '776940',
  625. 'ext': 'mp4',
  626. 'title': 'Охотское море стало целиком российским',
  627. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  628. },
  629. 'params': {
  630. # m3u8 download
  631. 'skip_download': True,
  632. },
  633. },
  634. # TVC embed
  635. {
  636. '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/',
  637. 'info_dict': {
  638. 'id': '55304',
  639. 'ext': 'mp4',
  640. 'title': 'Дошкольное воспитание',
  641. },
  642. },
  643. # SportBox embed
  644. {
  645. 'url': 'http://www.vestifinance.ru/articles/25753',
  646. 'info_dict': {
  647. 'id': '25753',
  648. 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  649. },
  650. 'playlist': [{
  651. 'info_dict': {
  652. 'id': '370908',
  653. 'title': 'Госзаказ. День 3',
  654. 'ext': 'mp4',
  655. }
  656. }, {
  657. 'info_dict': {
  658. 'id': '370905',
  659. 'title': 'Госзаказ. День 2',
  660. 'ext': 'mp4',
  661. }
  662. }, {
  663. 'info_dict': {
  664. 'id': '370902',
  665. 'title': 'Госзаказ. День 1',
  666. 'ext': 'mp4',
  667. }
  668. }],
  669. 'params': {
  670. # m3u8 download
  671. 'skip_download': True,
  672. },
  673. },
  674. # Myvi.ru embed
  675. {
  676. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  677. 'info_dict': {
  678. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  679. 'ext': 'mp4',
  680. 'title': 'Ужастики, русский трейлер (2015)',
  681. 'thumbnail': r're:^https?://.*\.jpg$',
  682. 'duration': 153,
  683. }
  684. },
  685. # XHamster embed
  686. {
  687. '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',
  688. 'info_dict': {
  689. 'id': 'showthread',
  690. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  691. },
  692. 'playlist_mincount': 7,
  693. # This forum does not allow <iframe> syntaxes anymore
  694. # Now HTML tags are displayed as-is
  695. 'skip': 'No videos on this page',
  696. },
  697. # Embedded TED video
  698. {
  699. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  700. 'md5': '65fdff94098e4a607385a60c5177c638',
  701. 'info_dict': {
  702. 'id': '1969',
  703. 'ext': 'mp4',
  704. 'title': 'Hidden miracles of the natural world',
  705. 'uploader': 'Louie Schwartzberg',
  706. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  707. }
  708. },
  709. # nowvideo embed hidden behind percent encoding
  710. {
  711. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  712. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  713. 'info_dict': {
  714. 'id': '06e53103ca9aa',
  715. 'ext': 'flv',
  716. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  717. 'description': 'No description',
  718. },
  719. },
  720. # arte embed
  721. {
  722. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  723. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  724. 'info_dict': {
  725. 'id': '048195-004_PLUS7-F',
  726. 'ext': 'flv',
  727. 'title': 'X:enius',
  728. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  729. 'upload_date': '20140320',
  730. },
  731. 'params': {
  732. 'skip_download': 'Requires rtmpdump'
  733. },
  734. 'skip': 'video gone',
  735. },
  736. # francetv embed
  737. {
  738. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  739. 'info_dict': {
  740. 'id': 'EV_30231',
  741. 'ext': 'mp4',
  742. 'title': 'Alcaline, le concert avec Calogero',
  743. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  744. 'upload_date': '20150226',
  745. 'timestamp': 1424989860,
  746. 'duration': 5400,
  747. },
  748. 'params': {
  749. # m3u8 downloads
  750. 'skip_download': True,
  751. },
  752. 'expected_warnings': [
  753. 'Forbidden'
  754. ]
  755. },
  756. # Condé Nast embed
  757. {
  758. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  759. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  760. 'info_dict': {
  761. 'id': '53501be369702d3275860000',
  762. 'ext': 'mp4',
  763. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  764. }
  765. },
  766. # Dailymotion embed
  767. {
  768. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  769. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  770. 'info_dict': {
  771. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  772. 'ext': 'mp4',
  773. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  774. 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
  775. 'uploader': 'Spi0n',
  776. 'uploader_id': 'xgditw',
  777. 'upload_date': '20140425',
  778. 'timestamp': 1398441542,
  779. },
  780. 'add_ie': ['Dailymotion'],
  781. },
  782. # DailyMail embed
  783. {
  784. 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
  785. 'info_dict': {
  786. 'id': '1495629',
  787. 'ext': 'mp4',
  788. 'title': 'Care worker punches elderly dementia patient in head 11 times',
  789. 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
  790. },
  791. 'add_ie': ['DailyMail'],
  792. 'params': {
  793. 'skip_download': True,
  794. },
  795. },
  796. # YouTube embed
  797. {
  798. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  799. 'info_dict': {
  800. 'id': 'FXRb4ykk4S0',
  801. 'ext': 'mp4',
  802. 'title': 'The NBL Auction 2014',
  803. 'uploader': 'BADMINTON England',
  804. 'uploader_id': 'BADMINTONEvents',
  805. 'upload_date': '20140603',
  806. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  807. },
  808. 'add_ie': ['Youtube'],
  809. 'params': {
  810. 'skip_download': True,
  811. }
  812. },
  813. # MTVSercices embed
  814. {
  815. 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
  816. 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
  817. 'info_dict': {
  818. 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
  819. 'ext': 'mp4',
  820. 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
  821. 'description': 'Two valets share their love for movie star Liam Neesons.',
  822. 'timestamp': 1349922600,
  823. 'upload_date': '20121011',
  824. },
  825. },
  826. # YouTube embed via <data-embed-url="">
  827. {
  828. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  829. 'info_dict': {
  830. 'id': '4vAffPZIT44',
  831. 'ext': 'mp4',
  832. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  833. 'uploader': 'Gameloft',
  834. 'uploader_id': 'gameloft',
  835. 'upload_date': '20140828',
  836. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  837. },
  838. 'params': {
  839. 'skip_download': True,
  840. }
  841. },
  842. # YouTube <object> embed
  843. {
  844. 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
  845. 'md5': '516718101ec834f74318df76259fb3cc',
  846. 'info_dict': {
  847. 'id': 'msN87y-iEx0',
  848. 'ext': 'webm',
  849. 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
  850. 'upload_date': '20080526',
  851. 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
  852. 'uploader': 'Christopher Sykes',
  853. 'uploader_id': 'ChristopherJSykes',
  854. },
  855. 'add_ie': ['Youtube'],
  856. },
  857. # Camtasia studio
  858. {
  859. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  860. 'playlist': [{
  861. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  862. 'info_dict': {
  863. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  864. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  865. 'ext': 'flv',
  866. 'duration': 2235.90,
  867. }
  868. }, {
  869. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  870. 'info_dict': {
  871. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  872. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  873. 'ext': 'flv',
  874. 'duration': 2235.93,
  875. }
  876. }],
  877. 'info_dict': {
  878. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  879. }
  880. },
  881. # Flowplayer
  882. {
  883. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  884. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  885. 'info_dict': {
  886. 'id': '5123ea6d5e5a7',
  887. 'ext': 'mp4',
  888. 'age_limit': 18,
  889. 'uploader': 'www.handjobhub.com',
  890. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  891. }
  892. },
  893. # Multiple brightcove videos
  894. # https://github.com/rg3/youtube-dl/issues/2283
  895. {
  896. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  897. 'info_dict': {
  898. 'id': 'always-never',
  899. 'title': 'Always / Never - The New Yorker',
  900. },
  901. 'playlist_count': 3,
  902. 'params': {
  903. 'extract_flat': False,
  904. 'skip_download': True,
  905. }
  906. },
  907. # MLB embed
  908. {
  909. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  910. 'md5': '96f09a37e44da40dd083e12d9a683327',
  911. 'info_dict': {
  912. 'id': '33322633',
  913. 'ext': 'mp4',
  914. 'title': 'Ump changes call to ball',
  915. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  916. 'duration': 48,
  917. 'timestamp': 1401537900,
  918. 'upload_date': '20140531',
  919. 'thumbnail': r're:^https?://.*\.jpg$',
  920. },
  921. },
  922. # Wistia embed
  923. {
  924. 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  925. 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
  926. 'info_dict': {
  927. 'id': '6e2wtrbdaf',
  928. 'ext': 'mov',
  929. 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
  930. 'description': 'a Paywall Videos video from Remilon',
  931. 'duration': 644.072,
  932. 'uploader': 'study.com',
  933. 'timestamp': 1459678540,
  934. 'upload_date': '20160403',
  935. 'filesize': 24687186,
  936. },
  937. },
  938. {
  939. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  940. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  941. 'info_dict': {
  942. 'id': 'uxjb0lwrcz',
  943. 'ext': 'mp4',
  944. 'title': 'Conversation about Hexagonal Rails Part 1',
  945. 'description': 'a Martin Fowler video from ThoughtWorks',
  946. 'duration': 1715.0,
  947. 'uploader': 'thoughtworks.wistia.com',
  948. 'timestamp': 1401832161,
  949. 'upload_date': '20140603',
  950. },
  951. },
  952. # Wistia standard embed (async)
  953. {
  954. 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
  955. 'info_dict': {
  956. 'id': '807fafadvk',
  957. 'ext': 'mp4',
  958. 'title': 'Drip Brennan Dunn Workshop',
  959. 'description': 'a JV Webinars video from getdrip-1',
  960. 'duration': 4986.95,
  961. 'timestamp': 1463607249,
  962. 'upload_date': '20160518',
  963. },
  964. 'params': {
  965. 'skip_download': True,
  966. }
  967. },
  968. # Soundcloud embed
  969. {
  970. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  971. 'info_dict': {
  972. 'id': '174391317',
  973. 'ext': 'mp3',
  974. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  975. 'uploader': 'Sophos Security',
  976. 'title': 'Chet Chat 171 - Oct 29, 2014',
  977. 'upload_date': '20141029',
  978. }
  979. },
  980. # Soundcloud multiple embeds
  981. {
  982. 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
  983. 'info_dict': {
  984. 'id': '52809',
  985. 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
  986. },
  987. 'playlist_mincount': 7,
  988. },
  989. # TuneIn station embed
  990. {
  991. 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
  992. 'info_dict': {
  993. 'id': '204146',
  994. 'ext': 'mp3',
  995. 'title': 'CNRV',
  996. 'location': 'Paris, France',
  997. 'is_live': True,
  998. },
  999. 'params': {
  1000. # Live stream
  1001. 'skip_download': True,
  1002. },
  1003. },
  1004. # Livestream embed
  1005. {
  1006. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  1007. 'info_dict': {
  1008. 'id': '67864563',
  1009. 'ext': 'flv',
  1010. 'upload_date': '20141112',
  1011. 'title': 'Rosetta #CometLanding webcast HL 10',
  1012. }
  1013. },
  1014. # Another Livestream embed, without 'new.' in URL
  1015. {
  1016. 'url': 'https://www.freespeech.org/',
  1017. 'info_dict': {
  1018. 'id': '123537347',
  1019. 'ext': 'mp4',
  1020. 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  1021. },
  1022. 'params': {
  1023. # Live stream
  1024. 'skip_download': True,
  1025. },
  1026. },
  1027. # LazyYT
  1028. {
  1029. 'url': 'https://skiplagged.com/',
  1030. 'info_dict': {
  1031. 'id': 'skiplagged',
  1032. 'title': 'Skiplagged: The smart way to find cheap flights',
  1033. },
  1034. 'playlist_mincount': 1,
  1035. 'add_ie': ['Youtube'],
  1036. },
  1037. # Cinchcast embed
  1038. {
  1039. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  1040. 'info_dict': {
  1041. 'id': '7141703',
  1042. 'ext': 'mp3',
  1043. 'upload_date': '20141126',
  1044. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  1045. }
  1046. },
  1047. # Cinerama player
  1048. {
  1049. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  1050. 'info_dict': {
  1051. 'id': '730m_DandD_1901_512k',
  1052. 'ext': 'mp4',
  1053. 'uploader': 'www.abc.net.au',
  1054. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  1055. }
  1056. },
  1057. # embedded viddler video
  1058. {
  1059. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  1060. 'info_dict': {
  1061. 'id': '4d03aad9',
  1062. 'ext': 'mp4',
  1063. 'uploader': 'deadspin',
  1064. 'title': 'WALL-TO-GORTAT',
  1065. 'timestamp': 1422285291,
  1066. 'upload_date': '20150126',
  1067. },
  1068. 'add_ie': ['Viddler'],
  1069. },
  1070. # Libsyn embed
  1071. {
  1072. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  1073. 'info_dict': {
  1074. 'id': '3377616',
  1075. 'ext': 'mp3',
  1076. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  1077. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  1078. 'upload_date': '20150220',
  1079. },
  1080. 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
  1081. },
  1082. # jwplayer YouTube
  1083. {
  1084. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  1085. 'info_dict': {
  1086. 'id': 'Mrj4DVp2zeA',
  1087. 'ext': 'mp4',
  1088. 'upload_date': '20150212',
  1089. 'uploader': 'The National Archives UK',
  1090. 'description': 'md5:8078af856dca76edc42910b61273dbbf',
  1091. 'uploader_id': 'NationalArchives08',
  1092. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  1093. },
  1094. },
  1095. # jwplayer rtmp
  1096. {
  1097. 'url': 'http://www.suffolk.edu/sjc/live.php',
  1098. 'info_dict': {
  1099. 'id': 'live',
  1100. 'ext': 'flv',
  1101. 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
  1102. 'uploader': 'www.suffolk.edu',
  1103. },
  1104. 'params': {
  1105. 'skip_download': True,
  1106. },
  1107. 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
  1108. },
  1109. # Complex jwplayer
  1110. {
  1111. 'url': 'http://www.indiedb.com/games/king-machine/videos',
  1112. 'info_dict': {
  1113. 'id': 'videos',
  1114. 'ext': 'mp4',
  1115. 'title': 'king machine trailer 1',
  1116. 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
  1117. 'thumbnail': r're:^https?://.*\.jpg$',
  1118. },
  1119. },
  1120. {
  1121. # JWPlayer config passed as variable
  1122. 'url': 'http://www.txxx.com/videos/3326530/ariele/',
  1123. 'info_dict': {
  1124. 'id': '3326530_hq',
  1125. 'ext': 'mp4',
  1126. 'title': 'ARIELE | Tube Cup',
  1127. 'uploader': 'www.txxx.com',
  1128. 'age_limit': 18,
  1129. },
  1130. 'params': {
  1131. 'skip_download': True,
  1132. }
  1133. },
  1134. {
  1135. # JWPlatform iframe
  1136. 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
  1137. 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
  1138. 'info_dict': {
  1139. 'id': 'O0c5JcKT',
  1140. 'ext': 'mp4',
  1141. 'upload_date': '20171122',
  1142. 'timestamp': 1511366290,
  1143. 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
  1144. },
  1145. 'add_ie': [JWPlatformIE.ie_key()],
  1146. },
  1147. {
  1148. # Video.js embed, multiple formats
  1149. 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
  1150. 'info_dict': {
  1151. 'id': 'yygqldloqIk',
  1152. 'ext': 'mp4',
  1153. 'title': 'SolidWorks. Урок 6 Настройка чертежа',
  1154. 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
  1155. 'upload_date': '20130314',
  1156. 'uploader': 'PROстое3D',
  1157. 'uploader_id': 'PROstoe3D',
  1158. },
  1159. 'params': {
  1160. 'skip_download': True,
  1161. },
  1162. },
  1163. {
  1164. # Video.js embed, single format
  1165. 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
  1166. 'info_dict': {
  1167. 'id': 'watch',
  1168. 'ext': 'mp4',
  1169. 'title': 'Step 1 - Good Foundation',
  1170. 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
  1171. },
  1172. 'params': {
  1173. 'skip_download': True,
  1174. },
  1175. },
  1176. # rtl.nl embed
  1177. {
  1178. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  1179. 'playlist_mincount': 5,
  1180. 'info_dict': {
  1181. 'id': 'aanslagen-kopenhagen',
  1182. 'title': 'Aanslagen Kopenhagen',
  1183. }
  1184. },
  1185. # Zapiks embed
  1186. {
  1187. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  1188. 'info_dict': {
  1189. 'id': '118046',
  1190. 'ext': 'mp4',
  1191. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  1192. }
  1193. },
  1194. # Kaltura embed (different embed code)
  1195. {
  1196. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  1197. 'info_dict': {
  1198. 'id': '1_a52wc67y',
  1199. 'ext': 'flv',
  1200. 'upload_date': '20150127',
  1201. 'uploader_id': 'PremierMedia',
  1202. 'timestamp': int,
  1203. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  1204. },
  1205. },
  1206. # Kaltura embed with single quotes
  1207. {
  1208. 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
  1209. 'info_dict': {
  1210. 'id': '0_izeg5utt',
  1211. 'ext': 'mp4',
  1212. 'title': '35871',
  1213. 'timestamp': 1355743100,
  1214. 'upload_date': '20121217',
  1215. 'uploader_id': 'batchUser',
  1216. },
  1217. 'add_ie': ['Kaltura'],
  1218. },
  1219. {
  1220. # Kaltura embedded via quoted entry_id
  1221. 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
  1222. 'info_dict': {
  1223. 'id': '0_utuok90b',
  1224. 'ext': 'mp4',
  1225. 'title': '06_matthew_brender_raj_dutt',
  1226. 'timestamp': 1466638791,
  1227. 'upload_date': '20160622',
  1228. },
  1229. 'add_ie': ['Kaltura'],
  1230. 'expected_warnings': [
  1231. 'Could not send HEAD request'
  1232. ],
  1233. 'params': {
  1234. 'skip_download': True,
  1235. }
  1236. },
  1237. {
  1238. # Kaltura embedded, some fileExt broken (#11480)
  1239. 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
  1240. 'info_dict': {
  1241. 'id': '1_sgtvehim',
  1242. 'ext': 'mp4',
  1243. 'title': 'Our "Standard Models" of particle physics and cosmology',
  1244. 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
  1245. 'timestamp': 1321158993,
  1246. 'upload_date': '20111113',
  1247. 'uploader_id': 'kps1',
  1248. },
  1249. 'add_ie': ['Kaltura'],
  1250. },
  1251. {
  1252. # Kaltura iframe embed
  1253. 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
  1254. 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
  1255. 'info_dict': {
  1256. 'id': '0_f2cfbpwy',
  1257. 'ext': 'mp4',
  1258. 'title': 'I. M. Pei: A Centennial Celebration',
  1259. 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
  1260. 'upload_date': '20170403',
  1261. 'uploader_id': 'batchUser',
  1262. 'timestamp': 1491232186,
  1263. },
  1264. 'add_ie': ['Kaltura'],
  1265. },
  1266. # EaglePlatform embed (generic URL)
  1267. {
  1268. 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
  1269. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  1270. 'info_dict': {
  1271. 'id': '227304',
  1272. 'ext': 'mp4',
  1273. 'title': 'Навальный вышел на свободу',
  1274. 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
  1275. 'thumbnail': r're:^https?://.*\.jpg$',
  1276. 'duration': 87,
  1277. 'view_count': int,
  1278. 'age_limit': 0,
  1279. },
  1280. 'params': {
  1281. 'skip_download': True,
  1282. },
  1283. },
  1284. # referrer protected EaglePlatform embed
  1285. {
  1286. 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
  1287. 'info_dict': {
  1288. 'id': '582306',
  1289. 'ext': 'mp4',
  1290. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1291. 'thumbnail': r're:^https?://.*\.jpg$',
  1292. 'duration': 3382,
  1293. 'view_count': int,
  1294. },
  1295. 'params': {
  1296. 'skip_download': True,
  1297. },
  1298. },
  1299. # ClipYou (EaglePlatform) embed (custom URL)
  1300. {
  1301. 'url': 'http://muz-tv.ru/play/7129/',
  1302. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  1303. 'info_dict': {
  1304. 'id': '12820',
  1305. 'ext': 'mp4',
  1306. 'title': "'O Sole Mio",
  1307. 'thumbnail': r're:^https?://.*\.jpg$',
  1308. 'duration': 216,
  1309. 'view_count': int,
  1310. },
  1311. 'params': {
  1312. 'skip_download': True,
  1313. },
  1314. 'skip': 'This video is unavailable.',
  1315. },
  1316. # Pladform embed
  1317. {
  1318. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  1319. 'info_dict': {
  1320. 'id': '100183293',
  1321. 'ext': 'mp4',
  1322. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  1323. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  1324. 'thumbnail': r're:^https?://.*\.jpg$',
  1325. 'duration': 694,
  1326. 'age_limit': 0,
  1327. },
  1328. 'skip': 'HTTP Error 404: Not Found',
  1329. },
  1330. # Playwire embed
  1331. {
  1332. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  1333. 'info_dict': {
  1334. 'id': '3519514',
  1335. 'ext': 'mp4',
  1336. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  1337. 'thumbnail': r're:^https?://.*\.png$',
  1338. 'duration': 45.115,
  1339. },
  1340. },
  1341. # 5min embed
  1342. {
  1343. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  1344. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  1345. 'info_dict': {
  1346. 'id': '518726732',
  1347. 'ext': 'mp4',
  1348. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  1349. 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
  1350. 'timestamp': 1427237531,
  1351. 'uploader': 'Crunch Report',
  1352. 'upload_date': '20150324',
  1353. },
  1354. 'params': {
  1355. # m3u8 download
  1356. 'skip_download': True,
  1357. },
  1358. },
  1359. # SVT embed
  1360. {
  1361. 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
  1362. 'info_dict': {
  1363. 'id': '2900353',
  1364. 'ext': 'flv',
  1365. 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
  1366. 'duration': 27,
  1367. 'age_limit': 0,
  1368. },
  1369. },
  1370. # Crooks and Liars embed
  1371. {
  1372. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  1373. 'info_dict': {
  1374. 'id': '8RUoRhRi',
  1375. 'ext': 'mp4',
  1376. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  1377. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  1378. 'timestamp': 1428207000,
  1379. 'upload_date': '20150405',
  1380. 'uploader': 'Heather',
  1381. },
  1382. },
  1383. # Crooks and Liars external embed
  1384. {
  1385. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  1386. 'info_dict': {
  1387. 'id': 'MTE3MjUtMzQ2MzA',
  1388. 'ext': 'mp4',
  1389. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  1390. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  1391. 'timestamp': 1265032391,
  1392. 'upload_date': '20100201',
  1393. 'uploader': 'Heather',
  1394. },
  1395. },
  1396. # NBC Sports vplayer embed
  1397. {
  1398. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  1399. 'info_dict': {
  1400. 'id': 'ln7x1qSThw4k',
  1401. 'ext': 'flv',
  1402. 'title': "PFT Live: New leader in the 'new-look' defense",
  1403. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  1404. 'uploader': 'NBCU-SPORTS',
  1405. 'upload_date': '20140107',
  1406. 'timestamp': 1389118457,
  1407. },
  1408. 'skip': 'Invalid Page URL',
  1409. },
  1410. # NBC News embed
  1411. {
  1412. 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
  1413. 'md5': '1aa589c675898ae6d37a17913cf68d66',
  1414. 'info_dict': {
  1415. 'id': 'x_dtl_oa_LettermanliftPR_160608',
  1416. 'ext': 'mp4',
  1417. 'title': 'David Letterman: A Preview',
  1418. '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.',
  1419. 'upload_date': '20160609',
  1420. 'timestamp': 1465431544,
  1421. 'uploader': 'NBCU-NEWS',
  1422. },
  1423. },
  1424. # UDN embed
  1425. {
  1426. 'url': 'https://video.udn.com/news/300346',
  1427. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  1428. 'info_dict': {
  1429. 'id': '300346',
  1430. 'ext': 'mp4',
  1431. 'title': '中一中男師變性 全校師生力挺',
  1432. 'thumbnail': r're:^https?://.*\.jpg$',
  1433. },
  1434. 'params': {
  1435. # m3u8 download
  1436. 'skip_download': True,
  1437. },
  1438. 'expected_warnings': ['Failed to parse JSON Expecting value'],
  1439. },
  1440. # Ooyala embed
  1441. {
  1442. 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
  1443. 'info_dict': {
  1444. 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
  1445. 'ext': 'mp4',
  1446. 'description': 'Index/Match versus VLOOKUP.',
  1447. 'title': 'This is what separates the Excel masters from the wannabes',
  1448. 'duration': 191.933,
  1449. },
  1450. 'params': {
  1451. # m3u8 downloads
  1452. 'skip_download': True,
  1453. }
  1454. },
  1455. # Brightcove URL in single quotes
  1456. {
  1457. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  1458. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  1459. 'info_dict': {
  1460. 'id': '4255764656001',
  1461. 'ext': 'mp4',
  1462. 'title': 'SN Presents: Russell Martin, World Citizen',
  1463. 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
  1464. 'uploader': 'Rogers Sportsnet',
  1465. 'uploader_id': '1704050871',
  1466. 'upload_date': '20150525',
  1467. 'timestamp': 1432570283,
  1468. },
  1469. },
  1470. # OnionStudios embed
  1471. {
  1472. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1473. 'info_dict': {
  1474. 'id': '2855',
  1475. 'ext': 'mp4',
  1476. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1477. 'thumbnail': r're:^https?://.*\.jpe?g$',
  1478. 'uploader': 'ClickHole',
  1479. 'uploader_id': 'clickhole',
  1480. }
  1481. },
  1482. # SnagFilms embed
  1483. {
  1484. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1485. 'info_dict': {
  1486. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1487. 'ext': 'mp4',
  1488. 'title': '#whilewewatch',
  1489. }
  1490. },
  1491. # AdobeTVVideo embed
  1492. {
  1493. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1494. 'md5': '43662b577c018ad707a63766462b1e87',
  1495. 'info_dict': {
  1496. 'id': '2456',
  1497. 'ext': 'mp4',
  1498. 'title': 'New experience with Acrobat DC',
  1499. 'description': 'New experience with Acrobat DC',
  1500. 'duration': 248.667,
  1501. },
  1502. },
  1503. # BrightcoveInPageEmbed embed
  1504. {
  1505. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1506. 'info_dict': {
  1507. 'id': '4238694884001',
  1508. 'ext': 'flv',
  1509. 'title': 'Tabletop: Dread, Last Thoughts',
  1510. 'description': 'Tabletop: Dread, Last Thoughts',
  1511. 'duration': 51690,
  1512. },
  1513. },
  1514. # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
  1515. # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
  1516. {
  1517. 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
  1518. 'info_dict': {
  1519. 'id': '4785848093001',
  1520. 'ext': 'mp4',
  1521. 'title': 'The Cardinal Pell Interview',
  1522. 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
  1523. 'uploader': 'GlobeCast Australia - GlobeStream',
  1524. 'uploader_id': '2733773828001',
  1525. 'upload_date': '20160304',
  1526. 'timestamp': 1457083087,
  1527. },
  1528. 'params': {
  1529. # m3u8 downloads
  1530. 'skip_download': True,
  1531. },
  1532. },
  1533. {
  1534. # Brightcove embed with whitespace around attribute names
  1535. 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
  1536. 'info_dict': {
  1537. 'id': '3167554373001',
  1538. 'ext': 'mp4',
  1539. 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
  1540. 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
  1541. 'uploader_id': '1079349493',
  1542. 'upload_date': '20140207',
  1543. 'timestamp': 1391810548,
  1544. },
  1545. 'params': {
  1546. 'skip_download': True,
  1547. },
  1548. },
  1549. # Another form of arte.tv embed
  1550. {
  1551. 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
  1552. 'md5': '850bfe45417ddf221288c88a0cffe2e2',
  1553. 'info_dict': {
  1554. 'id': '030273-562_PLUS7-F',
  1555. 'ext': 'mp4',
  1556. 'title': 'ARTE Reportage - Nulle part, en France',
  1557. 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
  1558. 'upload_date': '20160409',
  1559. },
  1560. },
  1561. # LiveLeak embed
  1562. {
  1563. 'url': 'http://www.wykop.pl/link/3088787/',
  1564. 'md5': '7619da8c820e835bef21a1efa2a0fc71',
  1565. 'info_dict': {
  1566. 'id': '874_1459135191',
  1567. 'ext': 'mp4',
  1568. 'title': 'Man shows poor quality of new apartment building',
  1569. 'description': 'The wall is like a sand pile.',
  1570. 'uploader': 'Lake8737',
  1571. },
  1572. 'add_ie': [LiveLeakIE.ie_key()],
  1573. },
  1574. # Another LiveLeak embed pattern (#13336)
  1575. {
  1576. 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
  1577. 'info_dict': {
  1578. 'id': '2eb_1496309988',
  1579. 'ext': 'mp4',
  1580. 'title': 'Thief robs place where everyone was armed',
  1581. 'description': 'md5:694d73ee79e535953cf2488562288eee',
  1582. 'uploader': 'brazilwtf',
  1583. },
  1584. 'add_ie': [LiveLeakIE.ie_key()],
  1585. },
  1586. # Duplicated embedded video URLs
  1587. {
  1588. 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
  1589. 'info_dict': {
  1590. 'id': '149298443_480_16c25b74_2',
  1591. 'ext': 'mp4',
  1592. 'title': 'vs. Blue Orange Spring Game',
  1593. 'uploader': 'www.hudl.com',
  1594. },
  1595. },
  1596. # twitter:player:stream embed
  1597. {
  1598. 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
  1599. 'info_dict': {
  1600. 'id': 'master',
  1601. 'ext': 'mp4',
  1602. 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
  1603. 'uploader': 'www.rtl.be',
  1604. },
  1605. 'params': {
  1606. # m3u8 downloads
  1607. 'skip_download': True,
  1608. },
  1609. },
  1610. # twitter:player embed
  1611. {
  1612. 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
  1613. 'md5': 'a3e0df96369831de324f0778e126653c',
  1614. 'info_dict': {
  1615. 'id': '4909620399001',
  1616. 'ext': 'mp4',
  1617. 'title': 'What Do Black Holes Sound Like?',
  1618. 'description': 'what do black holes sound like',
  1619. 'upload_date': '20160524',
  1620. 'uploader_id': '29913724001',
  1621. 'timestamp': 1464107587,
  1622. 'uploader': 'TheAtlantic',
  1623. },
  1624. 'add_ie': ['BrightcoveLegacy'],
  1625. },
  1626. # Facebook <iframe> embed
  1627. {
  1628. 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
  1629. 'md5': 'fbcde74f534176ecb015849146dd3aee',
  1630. 'info_dict': {
  1631. 'id': '599637780109885',
  1632. 'ext': 'mp4',
  1633. 'title': 'Facebook video #599637780109885',
  1634. },
  1635. },
  1636. # Facebook <iframe> embed, plugin video
  1637. {
  1638. 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
  1639. 'info_dict': {
  1640. 'id': '1754168231264132',
  1641. 'ext': 'mp4',
  1642. 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
  1643. 'uploader': 'Tariq Ramadan (official)',
  1644. 'timestamp': 1496758379,
  1645. 'upload_date': '20170606',
  1646. },
  1647. 'params': {
  1648. 'skip_download': True,
  1649. },
  1650. },
  1651. # Facebook API embed
  1652. {
  1653. 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
  1654. 'md5': 'a47372ee61b39a7b90287094d447d94e',
  1655. 'info_dict': {
  1656. 'id': '10153467542406923',
  1657. 'ext': 'mp4',
  1658. 'title': 'Facebook video #10153467542406923',
  1659. },
  1660. },
  1661. # Wordpress "YouTube Video Importer" plugin
  1662. {
  1663. 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
  1664. 'md5': 'd16797741b560b485194eddda8121b48',
  1665. 'info_dict': {
  1666. 'id': 'HNTXWDXV9Is',
  1667. 'ext': 'mp4',
  1668. 'title': 'Blue Devils Drumline Stanford lot 2016',
  1669. 'upload_date': '20160627',
  1670. 'uploader_id': 'GENOCIDE8GENERAL10',
  1671. 'uploader': 'cylus cyrus',
  1672. },
  1673. },
  1674. {
  1675. # video stored on custom kaltura server
  1676. 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
  1677. 'md5': '537617d06e64dfed891fa1593c4b30cc',
  1678. 'info_dict': {
  1679. 'id': '0_1iotm5bh',
  1680. 'ext': 'mp4',
  1681. 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
  1682. 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
  1683. 'uploader_id': 'videos.expansion@el-mundo.net',
  1684. 'upload_date': '20150429',
  1685. 'timestamp': 1430303472,
  1686. },
  1687. 'add_ie': ['Kaltura'],
  1688. },
  1689. {
  1690. # Non-standard Vimeo embed
  1691. 'url': 'https://openclassrooms.com/courses/understanding-the-web',
  1692. 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
  1693. 'info_dict': {
  1694. 'id': '148867247',
  1695. 'ext': 'mp4',
  1696. 'title': 'Understanding the web - Teaser',
  1697. 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
  1698. 'upload_date': '20151214',
  1699. 'uploader': 'OpenClassrooms',
  1700. 'uploader_id': 'openclassrooms',
  1701. },
  1702. 'add_ie': ['Vimeo'],
  1703. },
  1704. {
  1705. # generic vimeo embed that requires original URL passed as Referer
  1706. 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
  1707. 'only_matching': True,
  1708. },
  1709. {
  1710. 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
  1711. 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
  1712. 'info_dict': {
  1713. 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
  1714. 'ext': 'mp4',
  1715. 'title': 'Big Buck Bunny',
  1716. 'description': 'Royalty free test video',
  1717. 'timestamp': 1432816365,
  1718. 'upload_date': '20150528',
  1719. 'is_live': False,
  1720. },
  1721. 'params': {
  1722. 'skip_download': True,
  1723. },
  1724. 'add_ie': [ArkenaIE.ie_key()],
  1725. },
  1726. {
  1727. '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/',
  1728. 'info_dict': {
  1729. 'id': '1c7141f46c',
  1730. 'ext': 'mp4',
  1731. 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
  1732. },
  1733. 'params': {
  1734. 'skip_download': True,
  1735. },
  1736. 'add_ie': [Vbox7IE.ie_key()],
  1737. },
  1738. {
  1739. # DBTV embeds
  1740. 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
  1741. 'info_dict': {
  1742. 'id': '43254897',
  1743. 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
  1744. },
  1745. 'playlist_mincount': 3,
  1746. },
  1747. {
  1748. # Videa embeds
  1749. 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
  1750. 'info_dict': {
  1751. 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
  1752. 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
  1753. },
  1754. 'playlist_mincount': 2,
  1755. },
  1756. {
  1757. # 20 minuten embed
  1758. 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
  1759. 'info_dict': {
  1760. 'id': '523629',
  1761. 'ext': 'mp4',
  1762. 'title': 'So kommen Sie bei Eis und Schnee sicher an',
  1763. 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
  1764. },
  1765. 'params': {
  1766. 'skip_download': True,
  1767. },
  1768. 'add_ie': [TwentyMinutenIE.ie_key()],
  1769. },
  1770. {
  1771. # VideoPress embed
  1772. 'url': 'https://en.support.wordpress.com/videopress/',
  1773. 'info_dict': {
  1774. 'id': 'OcobLTqC',
  1775. 'ext': 'm4v',
  1776. 'title': 'IMG_5786',
  1777. 'timestamp': 1435711927,
  1778. 'upload_date': '20150701',
  1779. },
  1780. 'params': {
  1781. 'skip_download': True,
  1782. },
  1783. 'add_ie': [VideoPressIE.ie_key()],
  1784. },
  1785. {
  1786. # Rutube embed
  1787. 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
  1788. 'info_dict': {
  1789. 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
  1790. 'ext': 'flv',
  1791. 'title': 'Магаззино: Казань 2',
  1792. 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
  1793. 'uploader': 'Магаззино',
  1794. 'upload_date': '20170228',
  1795. 'uploader_id': '996642',
  1796. },
  1797. 'params': {
  1798. 'skip_download': True,
  1799. },
  1800. 'add_ie': [RutubeIE.ie_key()],
  1801. },
  1802. {
  1803. # ThePlatform embedded with whitespaces in URLs
  1804. 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
  1805. 'only_matching': True,
  1806. },
  1807. {
  1808. # Senate ISVP iframe https
  1809. 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
  1810. 'md5': 'fb8c70b0b515e5037981a2492099aab8',
  1811. 'info_dict': {
  1812. 'id': 'govtaff020316',
  1813. 'ext': 'mp4',
  1814. 'title': 'Integrated Senate Video Player',
  1815. },
  1816. 'add_ie': [SenateISVPIE.ie_key()],
  1817. },
  1818. {
  1819. # Limelight embeds (1 channel embed + 4 media embeds)
  1820. 'url': 'http://www.sedona.com/FacilitatorTraining2017',
  1821. 'info_dict': {
  1822. 'id': 'FacilitatorTraining2017',
  1823. 'title': 'Facilitator Training 2017',
  1824. },
  1825. 'playlist_mincount': 5,
  1826. },
  1827. {
  1828. # Limelight embed (LimelightPlayerUtil.embed)
  1829. 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
  1830. 'info_dict': {
  1831. 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
  1832. 'ext': 'mp4',
  1833. 'title': '07448641',
  1834. 'timestamp': 1499890639,
  1835. 'upload_date': '20170712',
  1836. },
  1837. 'params': {
  1838. 'skip_download': True,
  1839. },
  1840. 'add_ie': ['LimelightMedia'],
  1841. },
  1842. {
  1843. 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
  1844. 'info_dict': {
  1845. 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
  1846. 'title': 'Standoff with Walnut Creek murder suspect ends',
  1847. 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
  1848. },
  1849. 'playlist_mincount': 4,
  1850. },
  1851. {
  1852. # WashingtonPost embed
  1853. 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
  1854. 'info_dict': {
  1855. 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
  1856. 'ext': 'mp4',
  1857. 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
  1858. '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.',
  1859. 'timestamp': 1455216756,
  1860. 'uploader': 'The Washington Post',
  1861. 'upload_date': '20160211',
  1862. },
  1863. 'add_ie': [WashingtonPostIE.ie_key()],
  1864. },
  1865. {
  1866. # Mediaset embed
  1867. 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
  1868. 'info_dict': {
  1869. 'id': '720642',
  1870. 'ext': 'mp4',
  1871. 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
  1872. },
  1873. 'params': {
  1874. 'skip_download': True,
  1875. },
  1876. 'add_ie': [MediasetIE.ie_key()],
  1877. },
  1878. {
  1879. # JOJ.sk embeds
  1880. 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1881. 'info_dict': {
  1882. 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1883. 'title': 'Slovenskom sa prehnala vlna silných búrok',
  1884. },
  1885. 'playlist_mincount': 5,
  1886. 'add_ie': [JojIE.ie_key()],
  1887. },
  1888. {
  1889. # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
  1890. 'url': 'https://tvrain.ru/amp/418921/',
  1891. 'md5': 'cc00413936695987e8de148b67d14f1d',
  1892. 'info_dict': {
  1893. 'id': '418921',
  1894. 'ext': 'mp4',
  1895. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1896. },
  1897. },
  1898. {
  1899. # vzaar embed
  1900. 'url': 'http://help.vzaar.com/article/165-embedding-video',
  1901. 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
  1902. 'info_dict': {
  1903. 'id': '8707641',
  1904. 'ext': 'mp4',
  1905. 'title': 'Building A Business Online: Principal Chairs Q & A',
  1906. },
  1907. },
  1908. {
  1909. # multiple HTML5 videos on one page
  1910. 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
  1911. 'info_dict': {
  1912. 'id': 'keyscenarios',
  1913. 'title': 'Rescue Kit 14 Free Edition - Getting started',
  1914. },
  1915. 'playlist_count': 4,
  1916. },
  1917. {
  1918. # vshare embed
  1919. 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
  1920. 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
  1921. 'info_dict': {
  1922. 'id': '0f64ce6',
  1923. 'title': 'vl14062007715967',
  1924. 'ext': 'mp4',
  1925. }
  1926. },
  1927. {
  1928. 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
  1929. 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
  1930. 'info_dict': {
  1931. 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
  1932. 'ext': 'mp4',
  1933. 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
  1934. 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
  1935. 'timestamp': 1474354800,
  1936. 'upload_date': '20160920',
  1937. }
  1938. },
  1939. {
  1940. 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
  1941. 'info_dict': {
  1942. 'id': '1731611',
  1943. 'ext': 'mp4',
  1944. 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
  1945. 'description': 'md5:eb5f23826a027ba95277d105f248b825',
  1946. 'timestamp': 1516100691,
  1947. 'upload_date': '20180116',
  1948. },
  1949. 'params': {
  1950. 'skip_download': True,
  1951. },
  1952. 'add_ie': [SpringboardPlatformIE.ie_key()],
  1953. },
  1954. {
  1955. 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
  1956. 'info_dict': {
  1957. 'id': 'uPDB5I9wfp8',
  1958. 'ext': 'webm',
  1959. 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
  1960. 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
  1961. 'upload_date': '20160219',
  1962. 'uploader': 'Pocoyo - Português (BR)',
  1963. 'uploader_id': 'PocoyoBrazil',
  1964. },
  1965. 'add_ie': [YoutubeIE.ie_key()],
  1966. 'params': {
  1967. 'skip_download': True,
  1968. },
  1969. },
  1970. {
  1971. 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
  1972. 'info_dict': {
  1973. 'id': 'vMDE4NzI1Mjgt690b',
  1974. 'ext': 'mp4',
  1975. 'title': 'Котята',
  1976. },
  1977. 'add_ie': [YapFilesIE.ie_key()],
  1978. 'params': {
  1979. 'skip_download': True,
  1980. },
  1981. }
  1982. # {
  1983. # # TODO: find another test
  1984. # # http://schema.org/VideoObject
  1985. # 'url': 'https://flipagram.com/f/nyvTSJMKId',
  1986. # 'md5': '888dcf08b7ea671381f00fab74692755',
  1987. # 'info_dict': {
  1988. # 'id': 'nyvTSJMKId',
  1989. # 'ext': 'mp4',
  1990. # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
  1991. # 'description': '#love for cats.',
  1992. # 'timestamp': 1461244995,
  1993. # 'upload_date': '20160421',
  1994. # },
  1995. # 'params': {
  1996. # 'force_generic_extractor': True,
  1997. # },
  1998. # }
  1999. ]
  2000. def report_following_redirect(self, new_url):
  2001. """Report information extraction."""
  2002. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  2003. def _extract_rss(self, url, video_id, doc):
  2004. playlist_title = doc.find('./channel/title').text
  2005. playlist_desc_el = doc.find('./channel/description')
  2006. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  2007. entries = []
  2008. for it in doc.findall('./channel/item'):
  2009. next_url = xpath_text(it, 'link', fatal=False)
  2010. if not next_url:
  2011. enclosure_nodes = it.findall('./enclosure')
  2012. for e in enclosure_nodes:
  2013. next_url = e.attrib.get('url')
  2014. if next_url:
  2015. break
  2016. if not next_url:
  2017. continue
  2018. entries.append({
  2019. '_type': 'url_transparent',
  2020. 'url': next_url,
  2021. 'title': it.find('title').text,
  2022. })
  2023. return {
  2024. '_type': 'playlist',
  2025. 'id': url,
  2026. 'title': playlist_title,
  2027. 'description': playlist_desc,
  2028. 'entries': entries,
  2029. }
  2030. def _extract_camtasia(self, url, video_id, webpage):
  2031. """ Returns None if no camtasia video can be found. """
  2032. camtasia_cfg = self._search_regex(
  2033. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  2034. webpage, 'camtasia configuration file', default=None)
  2035. if camtasia_cfg is None:
  2036. return None
  2037. title = self._html_search_meta('DC.title', webpage, fatal=True)
  2038. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  2039. camtasia_cfg = self._download_xml(
  2040. camtasia_url, video_id,
  2041. note='Downloading camtasia configuration',
  2042. errnote='Failed to download camtasia configuration')
  2043. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  2044. entries = []
  2045. for n in fileset_node.getchildren():
  2046. url_n = n.find('./uri')
  2047. if url_n is None:
  2048. continue
  2049. entries.append({
  2050. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  2051. 'title': '%s - %s' % (title, n.tag),
  2052. 'url': compat_urlparse.urljoin(url, url_n.text),
  2053. 'duration': float_or_none(n.find('./duration').text),
  2054. })
  2055. return {
  2056. '_type': 'playlist',
  2057. 'entries': entries,
  2058. 'title': title,
  2059. }
  2060. def _real_extract(self, url):
  2061. if url.startswith('//'):
  2062. return {
  2063. '_type': 'url',
  2064. 'url': self.http_scheme() + url,
  2065. }
  2066. parsed_url = compat_urlparse.urlparse(url)
  2067. if not parsed_url.scheme:
  2068. default_search = self._downloader.params.get('default_search')
  2069. if default_search is None:
  2070. default_search = 'fixup_error'
  2071. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  2072. if '/' in url:
  2073. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  2074. return self.url_result('http://' + url)
  2075. elif default_search != 'fixup_error':
  2076. if default_search == 'auto_warning':
  2077. if re.match(r'^(?:url|URL)$', url):
  2078. raise ExtractorError(
  2079. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  2080. expected=True)
  2081. else:
  2082. self._downloader.report_warning(
  2083. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  2084. return self.url_result('ytsearch:' + url)
  2085. if default_search in ('error', 'fixup_error'):
  2086. raise ExtractorError(
  2087. '%r is not a valid URL. '
  2088. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  2089. % (url, url), expected=True)
  2090. else:
  2091. if ':' not in default_search:
  2092. default_search += ':'
  2093. return self.url_result(default_search + url)
  2094. url, smuggled_data = unsmuggle_url(url)
  2095. force_videoid = None
  2096. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  2097. if smuggled_data and 'force_videoid' in smuggled_data:
  2098. force_videoid = smuggled_data['force_videoid']
  2099. video_id = force_videoid
  2100. else:
  2101. video_id = self._generic_id(url)
  2102. self.to_screen('%s: Requesting header' % video_id)
  2103. head_req = HEADRequest(url)
  2104. head_response = self._request_webpage(
  2105. head_req, video_id,
  2106. note=False, errnote='Could not send HEAD request to %s' % url,
  2107. fatal=False)
  2108. if head_response is not False:
  2109. # Check for redirect
  2110. new_url = compat_str(head_response.geturl())
  2111. if url != new_url:
  2112. self.report_following_redirect(new_url)
  2113. if force_videoid:
  2114. new_url = smuggle_url(
  2115. new_url, {'force_videoid': force_videoid})
  2116. return self.url_result(new_url)
  2117. full_response = None
  2118. if head_response is False:
  2119. request = sanitized_Request(url)
  2120. request.add_header('Accept-Encoding', '*')
  2121. full_response = self._request_webpage(request, video_id)
  2122. head_response = full_response
  2123. info_dict = {
  2124. 'id': video_id,
  2125. 'title': self._generic_title(url),
  2126. 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
  2127. }
  2128. # Check for direct link to a video
  2129. content_type = head_response.headers.get('Content-Type', '').lower()
  2130. m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
  2131. if m:
  2132. format_id = compat_str(m.group('format_id'))
  2133. if format_id.endswith('mpegurl'):
  2134. formats = self._extract_m3u8_formats(url, video_id, 'mp4')
  2135. elif format_id == 'f4m':
  2136. formats = self._extract_f4m_formats(url, video_id)
  2137. else:
  2138. formats = [{
  2139. 'format_id': format_id,
  2140. 'url': url,
  2141. 'vcodec': 'none' if m.group('type') == 'audio' else None
  2142. }]
  2143. info_dict['direct'] = True
  2144. self._sort_formats(formats)
  2145. info_dict['formats'] = formats
  2146. return info_dict
  2147. if not self._downloader.params.get('test', False) and not is_intentional:
  2148. force = self._downloader.params.get('force_generic_extractor', False)
  2149. self._downloader.report_warning(
  2150. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  2151. if not full_response:
  2152. request = sanitized_Request(url)
  2153. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  2154. # making it impossible to download only chunk of the file (yet we need only 512kB to
  2155. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  2156. # that will always result in downloading the whole file that is not desirable.
  2157. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  2158. # to accept raw bytes and being able to download only a chunk.
  2159. # It may probably better to solve this by checking Content-Type for application/octet-stream
  2160. # after HEAD request finishes, but not sure if we can rely on this.
  2161. request.add_header('Accept-Encoding', '*')
  2162. full_response = self._request_webpage(request, video_id)
  2163. first_bytes = full_response.read(512)
  2164. # Is it an M3U playlist?
  2165. if first_bytes.startswith(b'#EXTM3U'):
  2166. info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
  2167. self._sort_formats(info_dict['formats'])
  2168. return info_dict
  2169. # Maybe it's a direct link to a video?
  2170. # Be careful not to download the whole thing!
  2171. if not is_html(first_bytes):
  2172. self._downloader.report_warning(
  2173. 'URL could be a direct video link, returning it as such.')
  2174. info_dict.update({
  2175. 'direct': True,
  2176. 'url': url,
  2177. })
  2178. return info_dict
  2179. webpage = self._webpage_read_content(
  2180. full_response, url, video_id, prefix=first_bytes)
  2181. self.report_extraction(video_id)
  2182. # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
  2183. try:
  2184. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  2185. if doc.tag == 'rss':
  2186. return self._extract_rss(url, video_id, doc)
  2187. elif doc.tag == 'SmoothStreamingMedia':
  2188. info_dict['formats'] = self._parse_ism_formats(doc, url)
  2189. self._sort_formats(info_dict['formats'])
  2190. return info_dict
  2191. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  2192. smil = self._parse_smil(doc, url, video_id)
  2193. self._sort_formats(smil['formats'])
  2194. return smil
  2195. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  2196. return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
  2197. elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
  2198. info_dict['formats'] = self._parse_mpd_formats(
  2199. doc,
  2200. mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
  2201. mpd_url=url)
  2202. self._sort_formats(info_dict['formats'])
  2203. return info_dict
  2204. elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
  2205. info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
  2206. self._sort_formats(info_dict['formats'])
  2207. return info_dict
  2208. except compat_xml_parse_error:
  2209. pass
  2210. # Is it a Camtasia project?
  2211. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  2212. if camtasia_res is not None:
  2213. return camtasia_res
  2214. # Sometimes embedded video player is hidden behind percent encoding
  2215. # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
  2216. # Unescaping the whole page allows to handle those cases in a generic way
  2217. webpage = compat_urllib_parse_unquote(webpage)
  2218. # it's tempting to parse this further, but you would
  2219. # have to take into account all the variations like
  2220. # Video Title - Site Name
  2221. # Site Name | Video Title
  2222. # Video Title - Tagline | Site Name
  2223. # and so on and so forth; it's just not practical
  2224. video_title = self._og_search_title(
  2225. webpage, default=None) or self._html_search_regex(
  2226. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  2227. default='video')
  2228. # Try to detect age limit automatically
  2229. age_limit = self._rta_search(webpage)
  2230. # And then there are the jokers who advertise that they use RTA,
  2231. # but actually don't.
  2232. AGE_LIMIT_MARKERS = [
  2233. r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
  2234. ]
  2235. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  2236. age_limit = 18
  2237. # video uploader is domain name
  2238. video_uploader = self._search_regex(
  2239. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  2240. video_description = self._og_search_description(webpage, default=None)
  2241. video_thumbnail = self._og_search_thumbnail(webpage, default=None)
  2242. info_dict.update({
  2243. 'title': video_title,
  2244. 'description': video_description,
  2245. 'thumbnail': video_thumbnail,
  2246. 'age_limit': age_limit,
  2247. })
  2248. # Look for Brightcove Legacy Studio embeds
  2249. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  2250. if bc_urls:
  2251. entries = [{
  2252. '_type': 'url',
  2253. 'url': smuggle_url(bc_url, {'Referer': url}),
  2254. 'ie_key': 'BrightcoveLegacy'
  2255. } for bc_url in bc_urls]
  2256. return {
  2257. '_type': 'playlist',
  2258. 'title': video_title,
  2259. 'id': video_id,
  2260. 'entries': entries,
  2261. }
  2262. # Look for Brightcove New Studio embeds
  2263. bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
  2264. if bc_urls:
  2265. return self.playlist_from_matches(
  2266. bc_urls, video_id, video_title,
  2267. getter=lambda x: smuggle_url(x, {'referrer': url}),
  2268. ie='BrightcoveNew')
  2269. # Look for Nexx embeds
  2270. nexx_urls = NexxIE._extract_urls(webpage)
  2271. if nexx_urls:
  2272. return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
  2273. # Look for Nexx iFrame embeds
  2274. nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
  2275. if nexx_embed_urls:
  2276. return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
  2277. # Look for ThePlatform embeds
  2278. tp_urls = ThePlatformIE._extract_urls(webpage)
  2279. if tp_urls:
  2280. return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
  2281. # Look for Vessel embeds
  2282. vessel_urls = VesselIE._extract_urls(webpage)
  2283. if vessel_urls:
  2284. return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
  2285. # Look for embedded rtl.nl player
  2286. matches = re.findall(
  2287. r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
  2288. webpage)
  2289. if matches:
  2290. return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
  2291. vimeo_urls = VimeoIE._extract_urls(url, webpage)
  2292. if vimeo_urls:
  2293. return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
  2294. vid_me_embed_url = self._search_regex(
  2295. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  2296. webpage, 'vid.me embed', default=None)
  2297. if vid_me_embed_url is not None:
  2298. return self.url_result(vid_me_embed_url, 'Vidme')
  2299. # Look for YouTube embeds
  2300. youtube_urls = YoutubeIE._extract_urls(webpage)
  2301. if youtube_urls:
  2302. return self.playlist_from_matches(
  2303. youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
  2304. matches = DailymotionIE._extract_urls(webpage)
  2305. if matches:
  2306. return self.playlist_from_matches(matches, video_id, video_title)
  2307. # Look for embedded Dailymotion playlist player (#3822)
  2308. m = re.search(
  2309. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  2310. if m:
  2311. playlists = re.findall(
  2312. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  2313. if playlists:
  2314. return self.playlist_from_matches(
  2315. playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
  2316. # Look for DailyMail embeds
  2317. dailymail_urls = DailyMailIE._extract_urls(webpage)
  2318. if dailymail_urls:
  2319. return self.playlist_from_matches(
  2320. dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
  2321. # Look for embedded Wistia player
  2322. wistia_url = WistiaIE._extract_url(webpage)
  2323. if wistia_url:
  2324. return {
  2325. '_type': 'url_transparent',
  2326. 'url': self._proto_relative_url(wistia_url),
  2327. 'ie_key': WistiaIE.ie_key(),
  2328. 'uploader': video_uploader,
  2329. }
  2330. # Look for SVT player
  2331. svt_url = SVTIE._extract_url(webpage)
  2332. if svt_url:
  2333. return self.url_result(svt_url, 'SVT')
  2334. # Look for Bandcamp pages with custom domain
  2335. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  2336. if mobj is not None:
  2337. burl = unescapeHTML(mobj.group(1))
  2338. # Don't set the extractor because it can be a track url or an album
  2339. return self.url_result(burl)
  2340. # Look for embedded Vevo player
  2341. mobj = re.search(
  2342. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  2343. if mobj is not None:
  2344. return self.url_result(mobj.group('url'))
  2345. # Look for embedded Viddler player
  2346. mobj = re.search(
  2347. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  2348. webpage)
  2349. if mobj is not None:
  2350. return self.url_result(mobj.group('url'))
  2351. # Look for NYTimes player
  2352. mobj = re.search(
  2353. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  2354. webpage)
  2355. if mobj is not None:
  2356. return self.url_result(mobj.group('url'))
  2357. # Look for Libsyn player
  2358. mobj = re.search(
  2359. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  2360. if mobj is not None:
  2361. return self.url_result(mobj.group('url'))
  2362. # Look for Ooyala videos
  2363. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
  2364. re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
  2365. re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
  2366. re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
  2367. re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  2368. if mobj is not None:
  2369. embed_token = self._search_regex(
  2370. r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
  2371. webpage, 'ooyala embed token', default=None)
  2372. return OoyalaIE._build_url_result(smuggle_url(
  2373. mobj.group('ec'), {
  2374. 'domain': url,
  2375. 'embed_token': embed_token,
  2376. }))
  2377. # Look for multiple Ooyala embeds on SBN network websites
  2378. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  2379. if mobj is not None:
  2380. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  2381. if embeds:
  2382. return self.playlist_from_matches(
  2383. embeds, video_id, video_title,
  2384. getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  2385. # Look for Aparat videos
  2386. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  2387. if mobj is not None:
  2388. return self.url_result(mobj.group(1), 'Aparat')
  2389. # Look for MPORA videos
  2390. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  2391. if mobj is not None:
  2392. return self.url_result(mobj.group(1), 'Mpora')
  2393. # Look for embedded NovaMov-based player
  2394. mobj = re.search(
  2395. r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
  2396. (?P<url>http://(?:(?:embed|www)\.)?
  2397. (?:novamov\.com|
  2398. nowvideo\.(?:ch|sx|eu|at|ag|co)|
  2399. videoweed\.(?:es|com)|
  2400. movshare\.(?:net|sx|ag)|
  2401. divxstage\.(?:eu|net|ch|co|at|ag))
  2402. /embed\.php.+?)\1''', webpage)
  2403. if mobj is not None:
  2404. return self.url_result(mobj.group('url'))
  2405. # Look for embedded Facebook player
  2406. facebook_urls = FacebookIE._extract_urls(webpage)
  2407. if facebook_urls:
  2408. return self.playlist_from_matches(facebook_urls, video_id, video_title)
  2409. # Look for embedded VK player
  2410. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  2411. if mobj is not None:
  2412. return self.url_result(mobj.group('url'), 'VK')
  2413. # Look for embedded Odnoklassniki player
  2414. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
  2415. if mobj is not None:
  2416. return self.url_result(mobj.group('url'), 'Odnoklassniki')
  2417. # Look for embedded ivi player
  2418. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  2419. if mobj is not None:
  2420. return self.url_result(mobj.group('url'), 'Ivi')
  2421. # Look for embedded Huffington Post player
  2422. mobj = re.search(
  2423. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  2424. if mobj is not None:
  2425. return self.url_result(mobj.group('url'), 'HuffPost')
  2426. # Look for embed.ly
  2427. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  2428. if mobj is not None:
  2429. return self.url_result(mobj.group('url'))
  2430. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  2431. if mobj is not None:
  2432. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  2433. # Look for funnyordie embed
  2434. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  2435. if matches:
  2436. return self.playlist_from_matches(
  2437. matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
  2438. # Look for BBC iPlayer embed
  2439. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  2440. if matches:
  2441. return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
  2442. # Look for embedded RUTV player
  2443. rutv_url = RUTVIE._extract_url(webpage)
  2444. if rutv_url:
  2445. return self.url_result(rutv_url, 'RUTV')
  2446. # Look for embedded TVC player
  2447. tvc_url = TVCIE._extract_url(webpage)
  2448. if tvc_url:
  2449. return self.url_result(tvc_url, 'TVC')
  2450. # Look for embedded SportBox player
  2451. sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
  2452. if sportbox_urls:
  2453. return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
  2454. # Look for embedded XHamster player
  2455. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  2456. if xhamster_urls:
  2457. return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
  2458. # Look for embedded TNAFlixNetwork player
  2459. tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
  2460. if tnaflix_urls:
  2461. return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
  2462. # Look for embedded PornHub player
  2463. pornhub_urls = PornHubIE._extract_urls(webpage)
  2464. if pornhub_urls:
  2465. return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
  2466. # Look for embedded DrTuber player
  2467. drtuber_urls = DrTuberIE._extract_urls(webpage)
  2468. if drtuber_urls:
  2469. return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
  2470. # Look for embedded RedTube player
  2471. redtube_urls = RedTubeIE._extract_urls(webpage)
  2472. if redtube_urls:
  2473. return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
  2474. # Look for embedded Tvigle player
  2475. mobj = re.search(
  2476. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  2477. if mobj is not None:
  2478. return self.url_result(mobj.group('url'), 'Tvigle')
  2479. # Look for embedded TED player
  2480. mobj = re.search(
  2481. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  2482. if mobj is not None:
  2483. return self.url_result(mobj.group('url'), 'TED')
  2484. # Look for embedded Ustream videos
  2485. ustream_url = UstreamIE._extract_url(webpage)
  2486. if ustream_url:
  2487. return self.url_result(ustream_url, UstreamIE.ie_key())
  2488. # Look for embedded arte.tv player
  2489. mobj = re.search(
  2490. r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
  2491. webpage)
  2492. if mobj is not None:
  2493. return self.url_result(mobj.group('url'), 'ArteTVEmbed')
  2494. # Look for embedded francetv player
  2495. mobj = re.search(
  2496. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  2497. webpage)
  2498. if mobj is not None:
  2499. return self.url_result(mobj.group('url'))
  2500. # Look for embedded smotri.com player
  2501. smotri_url = SmotriIE._extract_url(webpage)
  2502. if smotri_url:
  2503. return self.url_result(smotri_url, 'Smotri')
  2504. # Look for embedded Myvi.ru player
  2505. myvi_url = MyviIE._extract_url(webpage)
  2506. if myvi_url:
  2507. return self.url_result(myvi_url)
  2508. # Look for embedded soundcloud player
  2509. soundcloud_urls = SoundcloudIE._extract_urls(webpage)
  2510. if soundcloud_urls:
  2511. return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
  2512. # Look for tunein player
  2513. tunein_urls = TuneInBaseIE._extract_urls(webpage)
  2514. if tunein_urls:
  2515. return self.playlist_from_matches(tunein_urls, video_id, video_title)
  2516. # Look for embedded mtvservices player
  2517. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  2518. if mtvservices_url:
  2519. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  2520. # Look for embedded yahoo player
  2521. mobj = re.search(
  2522. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  2523. webpage)
  2524. if mobj is not None:
  2525. return self.url_result(mobj.group('url'), 'Yahoo')
  2526. # Look for embedded sbs.com.au player
  2527. mobj = re.search(
  2528. r'''(?x)
  2529. (?:
  2530. <meta\s+property="og:video"\s+content=|
  2531. <iframe[^>]+?src=
  2532. )
  2533. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  2534. webpage)
  2535. if mobj is not None:
  2536. return self.url_result(mobj.group('url'), 'SBS')
  2537. # Look for embedded Cinchcast player
  2538. mobj = re.search(
  2539. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  2540. webpage)
  2541. if mobj is not None:
  2542. return self.url_result(mobj.group('url'), 'Cinchcast')
  2543. mobj = re.search(
  2544. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  2545. webpage)
  2546. if not mobj:
  2547. mobj = re.search(
  2548. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  2549. webpage)
  2550. if mobj is not None:
  2551. return self.url_result(mobj.group('url'), 'MLB')
  2552. mobj = re.search(
  2553. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  2554. webpage)
  2555. if mobj is not None:
  2556. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  2557. mobj = re.search(
  2558. r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
  2559. webpage)
  2560. if mobj is not None:
  2561. return self.url_result(mobj.group('url'), 'Livestream')
  2562. # Look for Zapiks embed
  2563. mobj = re.search(
  2564. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  2565. if mobj is not None:
  2566. return self.url_result(mobj.group('url'), 'Zapiks')
  2567. # Look for Kaltura embeds
  2568. kaltura_url = KalturaIE._extract_url(webpage)
  2569. if kaltura_url:
  2570. return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
  2571. # Look for EaglePlatform embeds
  2572. eagleplatform_url = EaglePlatformIE._extract_url(webpage)
  2573. if eagleplatform_url:
  2574. return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
  2575. # Look for ClipYou (uses EaglePlatform) embeds
  2576. mobj = re.search(
  2577. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  2578. if mobj is not None:
  2579. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  2580. # Look for Pladform embeds
  2581. pladform_url = PladformIE._extract_url(webpage)
  2582. if pladform_url:
  2583. return self.url_result(pladform_url)
  2584. # Look for Videomore embeds
  2585. videomore_url = VideomoreIE._extract_url(webpage)
  2586. if videomore_url:
  2587. return self.url_result(videomore_url)
  2588. # Look for Webcaster embeds
  2589. webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
  2590. if webcaster_url:
  2591. return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
  2592. # Look for Playwire embeds
  2593. mobj = re.search(
  2594. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  2595. if mobj is not None:
  2596. return self.url_result(mobj.group('url'))
  2597. # Look for 5min embeds
  2598. mobj = re.search(
  2599. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  2600. if mobj is not None:
  2601. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  2602. # Look for Crooks and Liars embeds
  2603. mobj = re.search(
  2604. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  2605. if mobj is not None:
  2606. return self.url_result(mobj.group('url'))
  2607. # Look for NBC Sports VPlayer embeds
  2608. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  2609. if nbc_sports_url:
  2610. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  2611. # Look for NBC News embeds
  2612. nbc_news_embed_url = re.search(
  2613. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
  2614. if nbc_news_embed_url:
  2615. return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
  2616. # Look for Google Drive embeds
  2617. google_drive_url = GoogleDriveIE._extract_url(webpage)
  2618. if google_drive_url:
  2619. return self.url_result(google_drive_url, 'GoogleDrive')
  2620. # Look for UDN embeds
  2621. mobj = re.search(
  2622. r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  2623. if mobj is not None:
  2624. return self.url_result(
  2625. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  2626. # Look for Senate ISVP iframe
  2627. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  2628. if senate_isvp_url:
  2629. return self.url_result(senate_isvp_url, 'SenateISVP')
  2630. # Look for OnionStudios embeds
  2631. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  2632. if onionstudios_url:
  2633. return self.url_result(onionstudios_url)
  2634. # Look for ViewLift embeds
  2635. viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
  2636. if viewlift_url:
  2637. return self.url_result(viewlift_url)
  2638. # Look for JWPlatform embeds
  2639. jwplatform_urls = JWPlatformIE._extract_urls(webpage)
  2640. if jwplatform_urls:
  2641. return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
  2642. # Look for Digiteka embeds
  2643. digiteka_url = DigitekaIE._extract_url(webpage)
  2644. if digiteka_url:
  2645. return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
  2646. # Look for Arkena embeds
  2647. arkena_url = ArkenaIE._extract_url(webpage)
  2648. if arkena_url:
  2649. return self.url_result(arkena_url, ArkenaIE.ie_key())
  2650. # Look for Piksel embeds
  2651. piksel_url = PikselIE._extract_url(webpage)
  2652. if piksel_url:
  2653. return self.url_result(piksel_url, PikselIE.ie_key())
  2654. # Look for Limelight embeds
  2655. limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
  2656. if limelight_urls:
  2657. return self.playlist_result(
  2658. limelight_urls, video_id, video_title, video_description)
  2659. # Look for Anvato embeds
  2660. anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
  2661. if anvato_urls:
  2662. return self.playlist_result(
  2663. anvato_urls, video_id, video_title, video_description)
  2664. # Look for AdobeTVVideo embeds
  2665. mobj = re.search(
  2666. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  2667. webpage)
  2668. if mobj is not None:
  2669. return self.url_result(
  2670. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  2671. 'AdobeTVVideo')
  2672. # Look for Vine embeds
  2673. mobj = re.search(
  2674. r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
  2675. webpage)
  2676. if mobj is not None:
  2677. return self.url_result(
  2678. self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
  2679. # Look for VODPlatform embeds
  2680. mobj = re.search(
  2681. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
  2682. webpage)
  2683. if mobj is not None:
  2684. return self.url_result(
  2685. self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
  2686. # Look for Mangomolo embeds
  2687. mobj = re.search(
  2688. r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
  2689. (?:
  2690. video\?.*?\bid=(?P<video_id>\d+)|
  2691. index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
  2692. ).+?)\1''', webpage)
  2693. if mobj is not None:
  2694. info = {
  2695. '_type': 'url_transparent',
  2696. 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
  2697. 'title': video_title,
  2698. 'description': video_description,
  2699. 'thumbnail': video_thumbnail,
  2700. 'uploader': video_uploader,
  2701. }
  2702. video_id = mobj.group('video_id')
  2703. if video_id:
  2704. info.update({
  2705. 'ie_key': 'MangomoloVideo',
  2706. 'id': video_id,
  2707. })
  2708. else:
  2709. info.update({
  2710. 'ie_key': 'MangomoloLive',
  2711. 'id': mobj.group('channel_id'),
  2712. })
  2713. return info
  2714. # Look for Instagram embeds
  2715. instagram_embed_url = InstagramIE._extract_embed_url(webpage)
  2716. if instagram_embed_url is not None:
  2717. return self.url_result(
  2718. self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
  2719. # Look for LiveLeak embeds
  2720. liveleak_urls = LiveLeakIE._extract_urls(webpage)
  2721. if liveleak_urls:
  2722. return self.playlist_from_matches(liveleak_urls, video_id, video_title)
  2723. # Look for 3Q SDN embeds
  2724. threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
  2725. if threeqsdn_url:
  2726. return {
  2727. '_type': 'url_transparent',
  2728. 'ie_key': ThreeQSDNIE.ie_key(),
  2729. 'url': self._proto_relative_url(threeqsdn_url),
  2730. 'title': video_title,
  2731. 'description': video_description,
  2732. 'thumbnail': video_thumbnail,
  2733. 'uploader': video_uploader,
  2734. }
  2735. # Look for VBOX7 embeds
  2736. vbox7_url = Vbox7IE._extract_url(webpage)
  2737. if vbox7_url:
  2738. return self.url_result(vbox7_url, Vbox7IE.ie_key())
  2739. # Look for DBTV embeds
  2740. dbtv_urls = DBTVIE._extract_urls(webpage)
  2741. if dbtv_urls:
  2742. return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
  2743. # Look for Videa embeds
  2744. videa_urls = VideaIE._extract_urls(webpage)
  2745. if videa_urls:
  2746. return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
  2747. # Look for 20 minuten embeds
  2748. twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
  2749. if twentymin_urls:
  2750. return self.playlist_from_matches(
  2751. twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
  2752. # Look for Openload embeds
  2753. openload_urls = OpenloadIE._extract_urls(webpage)
  2754. if openload_urls:
  2755. return self.playlist_from_matches(
  2756. openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
  2757. # Look for VideoPress embeds
  2758. videopress_urls = VideoPressIE._extract_urls(webpage)
  2759. if videopress_urls:
  2760. return self.playlist_from_matches(
  2761. videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
  2762. # Look for Rutube embeds
  2763. rutube_urls = RutubeIE._extract_urls(webpage)
  2764. if rutube_urls:
  2765. return self.playlist_from_matches(
  2766. rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
  2767. # Look for WashingtonPost embeds
  2768. wapo_urls = WashingtonPostIE._extract_urls(webpage)
  2769. if wapo_urls:
  2770. return self.playlist_from_matches(
  2771. wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
  2772. # Look for Mediaset embeds
  2773. mediaset_urls = MediasetIE._extract_urls(webpage)
  2774. if mediaset_urls:
  2775. return self.playlist_from_matches(
  2776. mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
  2777. # Look for JOJ.sk embeds
  2778. joj_urls = JojIE._extract_urls(webpage)
  2779. if joj_urls:
  2780. return self.playlist_from_matches(
  2781. joj_urls, video_id, video_title, ie=JojIE.ie_key())
  2782. # Look for megaphone.fm embeds
  2783. mpfn_urls = MegaphoneIE._extract_urls(webpage)
  2784. if mpfn_urls:
  2785. return self.playlist_from_matches(
  2786. mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
  2787. # Look for vzaar embeds
  2788. vzaar_urls = VzaarIE._extract_urls(webpage)
  2789. if vzaar_urls:
  2790. return self.playlist_from_matches(
  2791. vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
  2792. channel9_urls = Channel9IE._extract_urls(webpage)
  2793. if channel9_urls:
  2794. return self.playlist_from_matches(
  2795. channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
  2796. vshare_urls = VShareIE._extract_urls(webpage)
  2797. if vshare_urls:
  2798. return self.playlist_from_matches(
  2799. vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
  2800. # Look for Mediasite embeds
  2801. mediasite_urls = MediasiteIE._extract_urls(webpage)
  2802. if mediasite_urls:
  2803. entries = [
  2804. self.url_result(smuggle_url(
  2805. compat_urlparse.urljoin(url, mediasite_url),
  2806. {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
  2807. for mediasite_url in mediasite_urls]
  2808. return self.playlist_result(entries, video_id, video_title)
  2809. springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
  2810. if springboardplatform_urls:
  2811. return self.playlist_from_matches(
  2812. springboardplatform_urls, video_id, video_title,
  2813. ie=SpringboardPlatformIE.ie_key())
  2814. yapfiles_urls = YapFilesIE._extract_urls(webpage)
  2815. if yapfiles_urls:
  2816. return self.playlist_from_matches(
  2817. yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
  2818. vice_urls = ViceIE._extract_urls(webpage)
  2819. if vice_urls:
  2820. return self.playlist_from_matches(
  2821. vice_urls, video_id, video_title, ie=ViceIE.ie_key())
  2822. def merge_dicts(dict1, dict2):
  2823. merged = {}
  2824. for k, v in dict1.items():
  2825. if v is not None:
  2826. merged[k] = v
  2827. for k, v in dict2.items():
  2828. if v is None:
  2829. continue
  2830. if (k not in merged or
  2831. (isinstance(v, compat_str) and v and
  2832. isinstance(merged[k], compat_str) and
  2833. not merged[k])):
  2834. merged[k] = v
  2835. return merged
  2836. # Look for HTML5 media
  2837. entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
  2838. if entries:
  2839. if len(entries) == 1:
  2840. entries[0].update({
  2841. 'id': video_id,
  2842. 'title': video_title,
  2843. })
  2844. else:
  2845. for num, entry in enumerate(entries, start=1):
  2846. entry.update({
  2847. 'id': '%s-%s' % (video_id, num),
  2848. 'title': '%s (%d)' % (video_title, num),
  2849. })
  2850. for entry in entries:
  2851. self._sort_formats(entry['formats'])
  2852. return self.playlist_result(entries, video_id, video_title)
  2853. jwplayer_data = self._find_jwplayer_data(
  2854. webpage, video_id, transform_source=js_to_json)
  2855. if jwplayer_data:
  2856. info = self._parse_jwplayer_data(
  2857. jwplayer_data, video_id, require_title=False, base_url=url)
  2858. return merge_dicts(info, info_dict)
  2859. # Video.js embed
  2860. mobj = re.search(
  2861. r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
  2862. webpage)
  2863. if mobj is not None:
  2864. sources = self._parse_json(
  2865. mobj.group(1), video_id, transform_source=js_to_json,
  2866. fatal=False) or []
  2867. if not isinstance(sources, list):
  2868. sources = [sources]
  2869. formats = []
  2870. for source in sources:
  2871. src = source.get('src')
  2872. if not src or not isinstance(src, compat_str):
  2873. continue
  2874. src = compat_urlparse.urljoin(url, src)
  2875. src_type = source.get('type')
  2876. if isinstance(src_type, compat_str):
  2877. src_type = src_type.lower()
  2878. ext = determine_ext(src).lower()
  2879. if src_type == 'video/youtube':
  2880. return self.url_result(src, YoutubeIE.ie_key())
  2881. if src_type == 'application/dash+xml' or ext == 'mpd':
  2882. formats.extend(self._extract_mpd_formats(
  2883. src, video_id, mpd_id='dash', fatal=False))
  2884. elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
  2885. formats.extend(self._extract_m3u8_formats(
  2886. src, video_id, 'mp4', entry_protocol='m3u8_native',
  2887. m3u8_id='hls', fatal=False))
  2888. else:
  2889. formats.append({
  2890. 'url': src,
  2891. 'ext': (mimetype2ext(src_type) or
  2892. ext if ext in KNOWN_EXTENSIONS else 'mp4'),
  2893. })
  2894. if formats:
  2895. self._sort_formats(formats)
  2896. info_dict['formats'] = formats
  2897. return info_dict
  2898. # Looking for http://schema.org/VideoObject
  2899. json_ld = self._search_json_ld(
  2900. webpage, video_id, default={}, expected_type='VideoObject')
  2901. if json_ld.get('url'):
  2902. return merge_dicts(json_ld, info_dict)
  2903. def check_video(vurl):
  2904. if YoutubeIE.suitable(vurl):
  2905. return True
  2906. if RtmpIE.suitable(vurl):
  2907. return True
  2908. vpath = compat_urlparse.urlparse(vurl).path
  2909. vext = determine_ext(vpath)
  2910. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
  2911. def filter_video(urls):
  2912. return list(filter(check_video, urls))
  2913. # Start with something easy: JW Player in SWFObject
  2914. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  2915. if not found:
  2916. # Look for gorilla-vid style embedding
  2917. found = filter_video(re.findall(r'''(?sx)
  2918. (?:
  2919. jw_plugins|
  2920. JWPlayerOptions|
  2921. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  2922. )
  2923. .*?
  2924. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  2925. if not found:
  2926. # Broaden the search a little bit
  2927. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  2928. if not found:
  2929. # Broaden the findall a little bit: JWPlayer JS loader
  2930. found = filter_video(re.findall(
  2931. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  2932. if not found:
  2933. # Flow player
  2934. found = filter_video(re.findall(r'''(?xs)
  2935. flowplayer\("[^"]+",\s*
  2936. \{[^}]+?\}\s*,
  2937. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  2938. ["']?url["']?\s*:\s*["']([^"']+)["']
  2939. ''', webpage))
  2940. if not found:
  2941. # Cinerama player
  2942. found = re.findall(
  2943. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  2944. if not found:
  2945. # Try to find twitter cards info
  2946. # twitter:player:stream should be checked before twitter:player since
  2947. # it is expected to contain a raw stream (see
  2948. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  2949. found = filter_video(re.findall(
  2950. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  2951. if not found:
  2952. # We look for Open Graph info:
  2953. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  2954. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  2955. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  2956. if m_video_type is not None:
  2957. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  2958. if not found:
  2959. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  2960. found = re.search(
  2961. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  2962. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  2963. webpage)
  2964. if not found:
  2965. # Look also in Refresh HTTP header
  2966. refresh_header = head_response.headers.get('Refresh')
  2967. if refresh_header:
  2968. # In python 2 response HTTP headers are bytestrings
  2969. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  2970. refresh_header = refresh_header.decode('iso-8859-1')
  2971. found = re.search(REDIRECT_REGEX, refresh_header)
  2972. if found:
  2973. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  2974. if new_url != url:
  2975. self.report_following_redirect(new_url)
  2976. return {
  2977. '_type': 'url',
  2978. 'url': new_url,
  2979. }
  2980. else:
  2981. found = None
  2982. if not found:
  2983. # twitter:player is a https URL to iframe player that may or may not
  2984. # be supported by youtube-dl thus this is checked the very last (see
  2985. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  2986. embed_url = self._html_search_meta('twitter:player', webpage, default=None)
  2987. if embed_url and embed_url != url:
  2988. return self.url_result(embed_url)
  2989. if not found:
  2990. raise UnsupportedError(url)
  2991. entries = []
  2992. for video_url in orderedSet(found):
  2993. video_url = unescapeHTML(video_url)
  2994. video_url = video_url.replace('\\/', '/')
  2995. video_url = compat_urlparse.urljoin(url, video_url)
  2996. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  2997. # Sometimes, jwplayer extraction will result in a YouTube URL
  2998. if YoutubeIE.suitable(video_url):
  2999. entries.append(self.url_result(video_url, 'Youtube'))
  3000. continue
  3001. # here's a fun little line of code for you:
  3002. video_id = os.path.splitext(video_id)[0]
  3003. entry_info_dict = {
  3004. 'id': video_id,
  3005. 'uploader': video_uploader,
  3006. 'title': video_title,
  3007. 'age_limit': age_limit,
  3008. }
  3009. if RtmpIE.suitable(video_url):
  3010. entry_info_dict.update({
  3011. '_type': 'url_transparent',
  3012. 'ie_key': RtmpIE.ie_key(),
  3013. 'url': video_url,
  3014. })
  3015. entries.append(entry_info_dict)
  3016. continue
  3017. ext = determine_ext(video_url)
  3018. if ext == 'smil':
  3019. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  3020. elif ext == 'xspf':
  3021. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  3022. elif ext == 'm3u8':
  3023. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  3024. elif ext == 'mpd':
  3025. entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
  3026. elif ext == 'f4m':
  3027. entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
  3028. elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
  3029. # Just matching .ism/manifest is not enough to be reliably sure
  3030. # whether it's actually an ISM manifest or some other streaming
  3031. # manifest since there are various streaming URL formats
  3032. # possible (see [1]) as well as some other shenanigans like
  3033. # .smil/manifest URLs that actually serve an ISM (see [2]) and
  3034. # so on.
  3035. # Thus the most reasonable way to solve this is to delegate
  3036. # to generic extractor in order to look into the contents of
  3037. # the manifest itself.
  3038. # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
  3039. # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
  3040. entry_info_dict = self.url_result(
  3041. smuggle_url(video_url, {'to_generic': True}),
  3042. GenericIE.ie_key())
  3043. else:
  3044. entry_info_dict['url'] = video_url
  3045. if entry_info_dict.get('formats'):
  3046. self._sort_formats(entry_info_dict['formats'])
  3047. entries.append(entry_info_dict)
  3048. if len(entries) == 1:
  3049. return entries[0]
  3050. else:
  3051. for num, e in enumerate(entries, start=1):
  3052. # 'url' results don't have a title
  3053. if e.get('title') is not None:
  3054. e['title'] = '%s (%d)' % (e['title'], num)
  3055. return {
  3056. '_type': 'playlist',
  3057. 'entries': entries,
  3058. }