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.

2003 lines
80 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. # encoding: 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_urllib_parse_unquote,
  11. compat_urlparse,
  12. compat_xml_parse_error,
  13. )
  14. from ..utils import (
  15. determine_ext,
  16. ExtractorError,
  17. float_or_none,
  18. HEADRequest,
  19. is_html,
  20. orderedSet,
  21. sanitized_Request,
  22. smuggle_url,
  23. unescapeHTML,
  24. unified_strdate,
  25. unsmuggle_url,
  26. UnsupportedError,
  27. url_basename,
  28. xpath_text,
  29. )
  30. from .brightcove import (
  31. BrightcoveLegacyIE,
  32. BrightcoveNewIE,
  33. )
  34. from .nbc import NBCSportsVPlayerIE
  35. from .ooyala import OoyalaIE
  36. from .rutv import RUTVIE
  37. from .tvc import TVCIE
  38. from .sportbox import SportBoxEmbedIE
  39. from .smotri import SmotriIE
  40. from .myvi import MyviIE
  41. from .condenast import CondeNastIE
  42. from .udn import UDNEmbedIE
  43. from .senateisvp import SenateISVPIE
  44. from .svt import SVTIE
  45. from .pornhub import PornHubIE
  46. from .xhamster import XHamsterEmbedIE
  47. from .tnaflix import TNAFlixNetworkEmbedIE
  48. from .vimeo import VimeoIE
  49. from .dailymotion import DailymotionCloudIE
  50. from .onionstudios import OnionStudiosIE
  51. from .snagfilms import SnagFilmsEmbedIE
  52. from .screenwavemedia import ScreenwaveMediaIE
  53. from .mtv import MTVServicesEmbeddedIE
  54. from .pladform import PladformIE
  55. from .videomore import VideomoreIE
  56. from .googledrive import GoogleDriveIE
  57. from .jwplatform import JWPlatformIE
  58. from .digiteka import DigitekaIE
  59. class GenericIE(InfoExtractor):
  60. IE_DESC = 'Generic downloader that works on some sites'
  61. _VALID_URL = r'.*'
  62. IE_NAME = 'generic'
  63. _TESTS = [
  64. # Direct link to a video
  65. {
  66. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  67. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  68. 'info_dict': {
  69. 'id': 'trailer',
  70. 'ext': 'mp4',
  71. 'title': 'trailer',
  72. 'upload_date': '20100513',
  73. }
  74. },
  75. # Direct link to media delivered compressed (until Accept-Encoding is *)
  76. {
  77. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  78. 'md5': '128c42e68b13950268b648275386fc74',
  79. 'info_dict': {
  80. 'id': 'FictionJunction-Parallel_Hearts',
  81. 'ext': 'flac',
  82. 'title': 'FictionJunction-Parallel_Hearts',
  83. 'upload_date': '20140522',
  84. },
  85. 'expected_warnings': [
  86. 'URL could be a direct video link, returning it as such.'
  87. ]
  88. },
  89. # Direct download with broken HEAD
  90. {
  91. 'url': 'http://ai-radio.org:8000/radio.opus',
  92. 'info_dict': {
  93. 'id': 'radio',
  94. 'ext': 'opus',
  95. 'title': 'radio',
  96. },
  97. 'params': {
  98. 'skip_download': True, # infinite live stream
  99. },
  100. 'expected_warnings': [
  101. r'501.*Not Implemented'
  102. ],
  103. },
  104. # Direct link with incorrect MIME type
  105. {
  106. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  107. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  108. 'info_dict': {
  109. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  110. 'id': '5_Lennart_Poettering_-_Systemd',
  111. 'ext': 'webm',
  112. 'title': '5_Lennart_Poettering_-_Systemd',
  113. 'upload_date': '20141120',
  114. },
  115. 'expected_warnings': [
  116. 'URL could be a direct video link, returning it as such.'
  117. ]
  118. },
  119. # RSS feed
  120. {
  121. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  122. 'info_dict': {
  123. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  124. 'title': 'Zero Punctuation',
  125. 'description': 're:.*groundbreaking video review series.*'
  126. },
  127. 'playlist_mincount': 11,
  128. },
  129. # RSS feed with enclosure
  130. {
  131. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  132. 'info_dict': {
  133. 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  134. 'ext': 'm4v',
  135. 'upload_date': '20150228',
  136. 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  137. }
  138. },
  139. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  140. {
  141. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  142. 'info_dict': {
  143. 'id': 'smil',
  144. 'ext': 'mp4',
  145. 'title': 'Automatics, robotics and biocybernetics',
  146. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  147. 'upload_date': '20130627',
  148. 'formats': 'mincount:16',
  149. 'subtitles': 'mincount:1',
  150. },
  151. 'params': {
  152. 'force_generic_extractor': True,
  153. 'skip_download': True,
  154. },
  155. },
  156. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  157. {
  158. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  159. 'info_dict': {
  160. 'id': 'hds',
  161. 'ext': 'flv',
  162. 'title': 'hds',
  163. 'formats': 'mincount:1',
  164. },
  165. 'params': {
  166. 'skip_download': True,
  167. },
  168. },
  169. # SMIL from https://www.restudy.dk/video/play/id/1637
  170. {
  171. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  172. 'info_dict': {
  173. 'id': 'video_1637',
  174. 'ext': 'flv',
  175. 'title': 'video_1637',
  176. 'formats': 'mincount:3',
  177. },
  178. 'params': {
  179. 'skip_download': True,
  180. },
  181. },
  182. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  183. {
  184. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  185. 'info_dict': {
  186. 'id': 'smil-service',
  187. 'ext': 'flv',
  188. 'title': 'smil-service',
  189. 'formats': 'mincount:1',
  190. },
  191. 'params': {
  192. 'skip_download': True,
  193. },
  194. },
  195. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  196. {
  197. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  198. 'info_dict': {
  199. 'id': '4719370',
  200. 'ext': 'mp4',
  201. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  202. 'formats': 'mincount:3',
  203. },
  204. 'params': {
  205. 'skip_download': True,
  206. },
  207. },
  208. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  209. {
  210. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  211. 'info_dict': {
  212. 'id': 'mZlp2ctYIUEB',
  213. 'ext': 'mp4',
  214. 'title': 'Tikibad ontruimd wegens brand',
  215. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  216. 'thumbnail': 're:^https?://.*\.jpg$',
  217. 'duration': 33,
  218. },
  219. 'params': {
  220. 'skip_download': True,
  221. },
  222. },
  223. # MPD from http://dash-mse-test.appspot.com/media.html
  224. {
  225. 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
  226. 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
  227. 'info_dict': {
  228. 'id': 'car-20120827-manifest',
  229. 'ext': 'mp4',
  230. 'title': 'car-20120827-manifest',
  231. 'formats': 'mincount:9',
  232. },
  233. 'params': {
  234. 'format': 'bestvideo',
  235. },
  236. },
  237. # google redirect
  238. {
  239. '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',
  240. 'info_dict': {
  241. 'id': 'cmQHVoWB5FY',
  242. 'ext': 'mp4',
  243. 'upload_date': '20130224',
  244. 'uploader_id': 'TheVerge',
  245. 'description': 're:^Chris Ziegler takes a look at the\.*',
  246. 'uploader': 'The Verge',
  247. 'title': 'First Firefox OS phones side-by-side',
  248. },
  249. 'params': {
  250. 'skip_download': False,
  251. }
  252. },
  253. {
  254. # redirect in Refresh HTTP header
  255. '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',
  256. 'info_dict': {
  257. 'id': 'pO8h3EaFRdo',
  258. 'ext': 'mp4',
  259. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  260. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  261. 'upload_date': '20150917',
  262. 'uploader_id': 'brtvofficial',
  263. 'uploader': 'Boiler Room',
  264. },
  265. 'params': {
  266. 'skip_download': False,
  267. },
  268. },
  269. {
  270. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  271. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  272. 'info_dict': {
  273. 'id': '13601338388002',
  274. 'ext': 'mp4',
  275. 'uploader': 'www.hodiho.fr',
  276. 'title': 'R\u00e9gis plante sa Jeep',
  277. }
  278. },
  279. # bandcamp page with custom domain
  280. {
  281. 'add_ie': ['Bandcamp'],
  282. 'url': 'http://bronyrock.com/track/the-pony-mash',
  283. 'info_dict': {
  284. 'id': '3235767654',
  285. 'ext': 'mp3',
  286. 'title': 'The Pony Mash',
  287. 'uploader': 'M_Pallante',
  288. },
  289. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  290. },
  291. # embedded brightcove video
  292. # it also tests brightcove videos that need to set the 'Referer' in the
  293. # http requests
  294. {
  295. 'add_ie': ['BrightcoveLegacy'],
  296. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  297. 'info_dict': {
  298. 'id': '2765128793001',
  299. 'ext': 'mp4',
  300. 'title': 'Le cours de bourse : l’analyse technique',
  301. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  302. 'uploader': 'BFM BUSINESS',
  303. },
  304. 'params': {
  305. 'skip_download': True,
  306. },
  307. },
  308. {
  309. # https://github.com/rg3/youtube-dl/issues/2253
  310. 'url': 'http://bcove.me/i6nfkrc3',
  311. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  312. 'info_dict': {
  313. 'id': '3101154703001',
  314. 'ext': 'mp4',
  315. 'title': 'Still no power',
  316. 'uploader': 'thestar.com',
  317. '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.',
  318. },
  319. 'add_ie': ['BrightcoveLegacy'],
  320. },
  321. {
  322. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  323. 'md5': 'fb973ecf6e4a78a67453647444222983',
  324. 'info_dict': {
  325. 'id': '3414141473001',
  326. 'ext': 'mp4',
  327. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  328. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  329. 'uploader': 'Championat',
  330. },
  331. },
  332. {
  333. # https://github.com/rg3/youtube-dl/issues/3541
  334. 'add_ie': ['BrightcoveLegacy'],
  335. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  336. 'info_dict': {
  337. 'id': '3866516442001',
  338. 'ext': 'mp4',
  339. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  340. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  341. 'uploader': 'SBS Broadcasting',
  342. },
  343. 'skip': 'Restricted to Netherlands',
  344. 'params': {
  345. 'skip_download': True, # m3u8 download
  346. },
  347. },
  348. # ooyala video
  349. {
  350. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  351. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  352. 'info_dict': {
  353. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  354. 'ext': 'mp4',
  355. 'title': '2cc213299525360.mov', # that's what we get
  356. 'duration': 238.231,
  357. },
  358. 'add_ie': ['Ooyala'],
  359. },
  360. {
  361. # ooyala video embedded with http://player.ooyala.com/iframe.js
  362. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  363. 'info_dict': {
  364. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  365. 'ext': 'mp4',
  366. 'title': '"Steve Jobs: Man in the Machine" trailer',
  367. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  368. 'duration': 135.427,
  369. },
  370. 'params': {
  371. 'skip_download': True,
  372. },
  373. },
  374. # multiple ooyala embeds on SBN network websites
  375. {
  376. 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
  377. 'info_dict': {
  378. 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
  379. 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
  380. },
  381. 'playlist_mincount': 3,
  382. 'params': {
  383. 'skip_download': True,
  384. },
  385. 'add_ie': ['Ooyala'],
  386. },
  387. # embed.ly video
  388. {
  389. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  390. 'info_dict': {
  391. 'id': '9ODmcdjQcHQ',
  392. 'ext': 'mp4',
  393. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  394. 'upload_date': '20140225',
  395. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  396. 'uploader': 'Tested',
  397. 'uploader_id': 'testedcom',
  398. },
  399. # No need to test YoutubeIE here
  400. 'params': {
  401. 'skip_download': True,
  402. },
  403. },
  404. # funnyordie embed
  405. {
  406. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  407. 'info_dict': {
  408. 'id': '18e820ec3f',
  409. 'ext': 'mp4',
  410. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  411. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  412. },
  413. },
  414. # RUTV embed
  415. {
  416. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  417. 'info_dict': {
  418. 'id': '776940',
  419. 'ext': 'mp4',
  420. 'title': 'Охотское море стало целиком российским',
  421. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  422. },
  423. 'params': {
  424. # m3u8 download
  425. 'skip_download': True,
  426. },
  427. },
  428. # TVC embed
  429. {
  430. '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/',
  431. 'info_dict': {
  432. 'id': '55304',
  433. 'ext': 'mp4',
  434. 'title': 'Дошкольное воспитание',
  435. },
  436. },
  437. # SportBox embed
  438. {
  439. 'url': 'http://www.vestifinance.ru/articles/25753',
  440. 'info_dict': {
  441. 'id': '25753',
  442. 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  443. },
  444. 'playlist': [{
  445. 'info_dict': {
  446. 'id': '370908',
  447. 'title': 'Госзаказ. День 3',
  448. 'ext': 'mp4',
  449. }
  450. }, {
  451. 'info_dict': {
  452. 'id': '370905',
  453. 'title': 'Госзаказ. День 2',
  454. 'ext': 'mp4',
  455. }
  456. }, {
  457. 'info_dict': {
  458. 'id': '370902',
  459. 'title': 'Госзаказ. День 1',
  460. 'ext': 'mp4',
  461. }
  462. }],
  463. 'params': {
  464. # m3u8 download
  465. 'skip_download': True,
  466. },
  467. },
  468. # Myvi.ru embed
  469. {
  470. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  471. 'info_dict': {
  472. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  473. 'ext': 'mp4',
  474. 'title': 'Ужастики, русский трейлер (2015)',
  475. 'thumbnail': 're:^https?://.*\.jpg$',
  476. 'duration': 153,
  477. }
  478. },
  479. # XHamster embed
  480. {
  481. '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',
  482. 'info_dict': {
  483. 'id': 'showthread',
  484. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  485. },
  486. 'playlist_mincount': 7,
  487. },
  488. # Embedded TED video
  489. {
  490. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  491. 'md5': '65fdff94098e4a607385a60c5177c638',
  492. 'info_dict': {
  493. 'id': '1969',
  494. 'ext': 'mp4',
  495. 'title': 'Hidden miracles of the natural world',
  496. 'uploader': 'Louie Schwartzberg',
  497. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  498. }
  499. },
  500. # Embedded Ustream video
  501. {
  502. 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
  503. 'md5': '27b99cdb639c9b12a79bca876a073417',
  504. 'info_dict': {
  505. 'id': '45734260',
  506. 'ext': 'flv',
  507. 'uploader': 'AU SPA: The NSA and Privacy',
  508. 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
  509. }
  510. },
  511. # nowvideo embed hidden behind percent encoding
  512. {
  513. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  514. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  515. 'info_dict': {
  516. 'id': '06e53103ca9aa',
  517. 'ext': 'flv',
  518. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  519. 'description': 'No description',
  520. },
  521. },
  522. # arte embed
  523. {
  524. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  525. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  526. 'info_dict': {
  527. 'id': '048195-004_PLUS7-F',
  528. 'ext': 'flv',
  529. 'title': 'X:enius',
  530. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  531. 'upload_date': '20140320',
  532. },
  533. 'params': {
  534. 'skip_download': 'Requires rtmpdump'
  535. }
  536. },
  537. # francetv embed
  538. {
  539. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  540. 'info_dict': {
  541. 'id': 'EV_30231',
  542. 'ext': 'mp4',
  543. 'title': 'Alcaline, le concert avec Calogero',
  544. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  545. 'upload_date': '20150226',
  546. 'timestamp': 1424989860,
  547. 'duration': 5400,
  548. },
  549. 'params': {
  550. # m3u8 downloads
  551. 'skip_download': True,
  552. },
  553. 'expected_warnings': [
  554. 'Forbidden'
  555. ]
  556. },
  557. # Condé Nast embed
  558. {
  559. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  560. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  561. 'info_dict': {
  562. 'id': '53501be369702d3275860000',
  563. 'ext': 'mp4',
  564. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  565. }
  566. },
  567. # Dailymotion embed
  568. {
  569. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  570. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  571. 'info_dict': {
  572. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  573. 'ext': 'mp4',
  574. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  575. 'uploader': 'Spi0n',
  576. },
  577. 'add_ie': ['Dailymotion'],
  578. },
  579. # YouTube embed
  580. {
  581. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  582. 'info_dict': {
  583. 'id': 'FXRb4ykk4S0',
  584. 'ext': 'mp4',
  585. 'title': 'The NBL Auction 2014',
  586. 'uploader': 'BADMINTON England',
  587. 'uploader_id': 'BADMINTONEvents',
  588. 'upload_date': '20140603',
  589. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  590. },
  591. 'add_ie': ['Youtube'],
  592. 'params': {
  593. 'skip_download': True,
  594. }
  595. },
  596. # MTVSercices embed
  597. {
  598. 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
  599. 'md5': '35727f82f58c76d996fc188f9755b0d5',
  600. 'info_dict': {
  601. 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
  602. 'ext': 'mp4',
  603. 'title': 'Review',
  604. 'description': 'Mario\'s life in the fast lane has never looked so good.',
  605. },
  606. },
  607. # YouTube embed via <data-embed-url="">
  608. {
  609. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  610. 'info_dict': {
  611. 'id': '4vAffPZIT44',
  612. 'ext': 'mp4',
  613. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  614. 'uploader': 'Gameloft',
  615. 'uploader_id': 'gameloft',
  616. 'upload_date': '20140828',
  617. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  618. },
  619. 'params': {
  620. 'skip_download': True,
  621. }
  622. },
  623. # Camtasia studio
  624. {
  625. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  626. 'playlist': [{
  627. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  628. 'info_dict': {
  629. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  630. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  631. 'ext': 'flv',
  632. 'duration': 2235.90,
  633. }
  634. }, {
  635. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  636. 'info_dict': {
  637. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  638. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  639. 'ext': 'flv',
  640. 'duration': 2235.93,
  641. }
  642. }],
  643. 'info_dict': {
  644. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  645. }
  646. },
  647. # Flowplayer
  648. {
  649. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  650. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  651. 'info_dict': {
  652. 'id': '5123ea6d5e5a7',
  653. 'ext': 'mp4',
  654. 'age_limit': 18,
  655. 'uploader': 'www.handjobhub.com',
  656. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  657. }
  658. },
  659. # Multiple brightcove videos
  660. # https://github.com/rg3/youtube-dl/issues/2283
  661. {
  662. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  663. 'info_dict': {
  664. 'id': 'always-never',
  665. 'title': 'Always / Never - The New Yorker',
  666. },
  667. 'playlist_count': 3,
  668. 'params': {
  669. 'extract_flat': False,
  670. 'skip_download': True,
  671. }
  672. },
  673. # MLB embed
  674. {
  675. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  676. 'md5': '96f09a37e44da40dd083e12d9a683327',
  677. 'info_dict': {
  678. 'id': '33322633',
  679. 'ext': 'mp4',
  680. 'title': 'Ump changes call to ball',
  681. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  682. 'duration': 48,
  683. 'timestamp': 1401537900,
  684. 'upload_date': '20140531',
  685. 'thumbnail': 're:^https?://.*\.jpg$',
  686. },
  687. },
  688. # Wistia embed
  689. {
  690. 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  691. 'md5': '8788b683c777a5cf25621eaf286d0c23',
  692. 'info_dict': {
  693. 'id': '1cfaf6b7ea',
  694. 'ext': 'mov',
  695. 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
  696. 'duration': 643.0,
  697. 'filesize': 182808282,
  698. 'uploader': 'education-portal.com',
  699. },
  700. },
  701. {
  702. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  703. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  704. 'info_dict': {
  705. 'id': 'uxjb0lwrcz',
  706. 'ext': 'mp4',
  707. 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
  708. 'duration': 1715.0,
  709. 'uploader': 'thoughtworks.wistia.com',
  710. },
  711. },
  712. # Soundcloud embed
  713. {
  714. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  715. 'info_dict': {
  716. 'id': '174391317',
  717. 'ext': 'mp3',
  718. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  719. 'uploader': 'Sophos Security',
  720. 'title': 'Chet Chat 171 - Oct 29, 2014',
  721. 'upload_date': '20141029',
  722. }
  723. },
  724. # Livestream embed
  725. {
  726. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  727. 'info_dict': {
  728. 'id': '67864563',
  729. 'ext': 'flv',
  730. 'upload_date': '20141112',
  731. 'title': 'Rosetta #CometLanding webcast HL 10',
  732. }
  733. },
  734. # LazyYT
  735. {
  736. 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
  737. 'info_dict': {
  738. 'id': '1986',
  739. 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
  740. },
  741. 'playlist_mincount': 2,
  742. },
  743. # Cinchcast embed
  744. {
  745. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  746. 'info_dict': {
  747. 'id': '7141703',
  748. 'ext': 'mp3',
  749. 'upload_date': '20141126',
  750. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  751. }
  752. },
  753. # Cinerama player
  754. {
  755. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  756. 'info_dict': {
  757. 'id': '730m_DandD_1901_512k',
  758. 'ext': 'mp4',
  759. 'uploader': 'www.abc.net.au',
  760. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  761. }
  762. },
  763. # embedded viddler video
  764. {
  765. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  766. 'info_dict': {
  767. 'id': '4d03aad9',
  768. 'ext': 'mp4',
  769. 'uploader': 'deadspin',
  770. 'title': 'WALL-TO-GORTAT',
  771. 'timestamp': 1422285291,
  772. 'upload_date': '20150126',
  773. },
  774. 'add_ie': ['Viddler'],
  775. },
  776. # Libsyn embed
  777. {
  778. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  779. 'info_dict': {
  780. 'id': '3377616',
  781. 'ext': 'mp3',
  782. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  783. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  784. 'upload_date': '20150220',
  785. },
  786. },
  787. # jwplayer YouTube
  788. {
  789. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  790. 'info_dict': {
  791. 'id': 'Mrj4DVp2zeA',
  792. 'ext': 'mp4',
  793. 'upload_date': '20150212',
  794. 'uploader': 'The National Archives UK',
  795. 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
  796. 'uploader_id': 'NationalArchives08',
  797. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  798. },
  799. },
  800. # rtl.nl embed
  801. {
  802. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  803. 'playlist_mincount': 5,
  804. 'info_dict': {
  805. 'id': 'aanslagen-kopenhagen',
  806. 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
  807. }
  808. },
  809. # Zapiks embed
  810. {
  811. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  812. 'info_dict': {
  813. 'id': '118046',
  814. 'ext': 'mp4',
  815. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  816. }
  817. },
  818. # Kaltura embed
  819. {
  820. 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
  821. 'info_dict': {
  822. 'id': '1_eergr3h1',
  823. 'ext': 'mp4',
  824. 'upload_date': '20150226',
  825. 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
  826. 'timestamp': int,
  827. 'title': 'John Carlson Postgame 2/25/15',
  828. },
  829. },
  830. # Kaltura embed (different embed code)
  831. {
  832. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  833. 'info_dict': {
  834. 'id': '1_a52wc67y',
  835. 'ext': 'flv',
  836. 'upload_date': '20150127',
  837. 'uploader_id': 'PremierMedia',
  838. 'timestamp': int,
  839. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  840. },
  841. },
  842. # Kaltura embed protected with referrer
  843. {
  844. 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
  845. 'info_dict': {
  846. 'id': '1_g4fbemnq',
  847. 'ext': 'mp4',
  848. 'title': 'Violetta - Achter De Schermen - Ruggero',
  849. 'description': 'Achter de schermen met Ruggero',
  850. 'timestamp': 1435133761,
  851. 'upload_date': '20150624',
  852. 'uploader_id': 'echojecka',
  853. },
  854. },
  855. # Eagle.Platform embed (generic URL)
  856. {
  857. 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
  858. 'info_dict': {
  859. 'id': '227304',
  860. 'ext': 'mp4',
  861. 'title': 'Навальный вышел на свободу',
  862. 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
  863. 'thumbnail': 're:^https?://.*\.jpg$',
  864. 'duration': 87,
  865. 'view_count': int,
  866. 'age_limit': 0,
  867. },
  868. },
  869. # ClipYou (Eagle.Platform) embed (custom URL)
  870. {
  871. 'url': 'http://muz-tv.ru/play/7129/',
  872. 'info_dict': {
  873. 'id': '12820',
  874. 'ext': 'mp4',
  875. 'title': "'O Sole Mio",
  876. 'thumbnail': 're:^https?://.*\.jpg$',
  877. 'duration': 216,
  878. 'view_count': int,
  879. },
  880. },
  881. # Pladform embed
  882. {
  883. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  884. 'info_dict': {
  885. 'id': '100183293',
  886. 'ext': 'mp4',
  887. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  888. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  889. 'thumbnail': 're:^https?://.*\.jpg$',
  890. 'duration': 694,
  891. 'age_limit': 0,
  892. },
  893. },
  894. # Playwire embed
  895. {
  896. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  897. 'info_dict': {
  898. 'id': '3519514',
  899. 'ext': 'mp4',
  900. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  901. 'thumbnail': 're:^https?://.*\.png$',
  902. 'duration': 45.115,
  903. },
  904. },
  905. # 5min embed
  906. {
  907. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  908. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  909. 'info_dict': {
  910. 'id': '518726732',
  911. 'ext': 'mp4',
  912. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  913. },
  914. },
  915. # SVT embed
  916. {
  917. 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
  918. 'info_dict': {
  919. 'id': '2900353',
  920. 'ext': 'flv',
  921. 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
  922. 'duration': 27,
  923. 'age_limit': 0,
  924. },
  925. },
  926. # Crooks and Liars embed
  927. {
  928. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  929. 'info_dict': {
  930. 'id': '8RUoRhRi',
  931. 'ext': 'mp4',
  932. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  933. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  934. 'timestamp': 1428207000,
  935. 'upload_date': '20150405',
  936. 'uploader': 'Heather',
  937. },
  938. },
  939. # Crooks and Liars external embed
  940. {
  941. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  942. 'info_dict': {
  943. 'id': 'MTE3MjUtMzQ2MzA',
  944. 'ext': 'mp4',
  945. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  946. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  947. 'timestamp': 1265032391,
  948. 'upload_date': '20100201',
  949. 'uploader': 'Heather',
  950. },
  951. },
  952. # NBC Sports vplayer embed
  953. {
  954. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  955. 'info_dict': {
  956. 'id': 'ln7x1qSThw4k',
  957. 'ext': 'flv',
  958. 'title': "PFT Live: New leader in the 'new-look' defense",
  959. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  960. },
  961. },
  962. # UDN embed
  963. {
  964. 'url': 'http://www.udn.com/news/story/7314/822787',
  965. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  966. 'info_dict': {
  967. 'id': '300346',
  968. 'ext': 'mp4',
  969. 'title': '中一中男師變性 全校師生力挺',
  970. 'thumbnail': 're:^https?://.*\.jpg$',
  971. }
  972. },
  973. # Ooyala embed
  974. {
  975. 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
  976. 'info_dict': {
  977. 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
  978. 'ext': 'mp4',
  979. 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
  980. 'title': 'This is what separates the Excel masters from the wannabes',
  981. 'duration': 191.933,
  982. },
  983. 'params': {
  984. # m3u8 downloads
  985. 'skip_download': True,
  986. }
  987. },
  988. # Contains a SMIL manifest
  989. {
  990. 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
  991. 'info_dict': {
  992. 'id': 'file',
  993. 'ext': 'flv',
  994. 'title': '+ Football: Lottery Champions League Europe',
  995. 'uploader': 'www.telewebion.com',
  996. },
  997. 'params': {
  998. # rtmpe downloads
  999. 'skip_download': True,
  1000. }
  1001. },
  1002. # Brightcove URL in single quotes
  1003. {
  1004. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  1005. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  1006. 'info_dict': {
  1007. 'id': '4255764656001',
  1008. 'ext': 'mp4',
  1009. 'title': 'SN Presents: Russell Martin, World Citizen',
  1010. '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.',
  1011. 'uploader': 'Rogers Sportsnet',
  1012. },
  1013. },
  1014. # Dailymotion Cloud video
  1015. {
  1016. 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
  1017. 'md5': '49444254273501a64675a7e68c502681',
  1018. 'info_dict': {
  1019. 'id': '5585de919473990de4bee11b',
  1020. 'ext': 'mp4',
  1021. 'title': 'Le débat',
  1022. 'thumbnail': 're:^https?://.*\.jpe?g$',
  1023. }
  1024. },
  1025. # OnionStudios embed
  1026. {
  1027. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1028. 'info_dict': {
  1029. 'id': '2855',
  1030. 'ext': 'mp4',
  1031. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1032. 'thumbnail': 're:^https?://.*\.jpe?g$',
  1033. 'uploader': 'ClickHole',
  1034. 'uploader_id': 'clickhole',
  1035. }
  1036. },
  1037. # SnagFilms embed
  1038. {
  1039. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1040. 'info_dict': {
  1041. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1042. 'ext': 'mp4',
  1043. 'title': '#whilewewatch',
  1044. }
  1045. },
  1046. # AdobeTVVideo embed
  1047. {
  1048. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1049. 'md5': '43662b577c018ad707a63766462b1e87',
  1050. 'info_dict': {
  1051. 'id': '2456',
  1052. 'ext': 'mp4',
  1053. 'title': 'New experience with Acrobat DC',
  1054. 'description': 'New experience with Acrobat DC',
  1055. 'duration': 248.667,
  1056. },
  1057. },
  1058. # ScreenwaveMedia embed
  1059. {
  1060. 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
  1061. 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
  1062. 'info_dict': {
  1063. 'id': 'cinemasnob-55d26273809dd',
  1064. 'ext': 'mp4',
  1065. 'title': 'cinemasnob',
  1066. },
  1067. },
  1068. # BrightcoveInPageEmbed embed
  1069. {
  1070. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1071. 'info_dict': {
  1072. 'id': '4238694884001',
  1073. 'ext': 'flv',
  1074. 'title': 'Tabletop: Dread, Last Thoughts',
  1075. 'description': 'Tabletop: Dread, Last Thoughts',
  1076. 'duration': 51690,
  1077. },
  1078. },
  1079. # JWPlayer with M3U8
  1080. {
  1081. 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
  1082. 'info_dict': {
  1083. 'id': 'playlist',
  1084. 'ext': 'mp4',
  1085. 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
  1086. 'uploader': 'ren.tv',
  1087. },
  1088. 'params': {
  1089. # m3u8 downloads
  1090. 'skip_download': True,
  1091. }
  1092. }
  1093. ]
  1094. def report_following_redirect(self, new_url):
  1095. """Report information extraction."""
  1096. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  1097. def _extract_rss(self, url, video_id, doc):
  1098. playlist_title = doc.find('./channel/title').text
  1099. playlist_desc_el = doc.find('./channel/description')
  1100. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  1101. entries = []
  1102. for it in doc.findall('./channel/item'):
  1103. next_url = xpath_text(it, 'link', fatal=False)
  1104. if not next_url:
  1105. enclosure_nodes = it.findall('./enclosure')
  1106. for e in enclosure_nodes:
  1107. next_url = e.attrib.get('url')
  1108. if next_url:
  1109. break
  1110. if not next_url:
  1111. continue
  1112. entries.append({
  1113. '_type': 'url',
  1114. 'url': next_url,
  1115. 'title': it.find('title').text,
  1116. })
  1117. return {
  1118. '_type': 'playlist',
  1119. 'id': url,
  1120. 'title': playlist_title,
  1121. 'description': playlist_desc,
  1122. 'entries': entries,
  1123. }
  1124. def _extract_camtasia(self, url, video_id, webpage):
  1125. """ Returns None if no camtasia video can be found. """
  1126. camtasia_cfg = self._search_regex(
  1127. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  1128. webpage, 'camtasia configuration file', default=None)
  1129. if camtasia_cfg is None:
  1130. return None
  1131. title = self._html_search_meta('DC.title', webpage, fatal=True)
  1132. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  1133. camtasia_cfg = self._download_xml(
  1134. camtasia_url, video_id,
  1135. note='Downloading camtasia configuration',
  1136. errnote='Failed to download camtasia configuration')
  1137. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  1138. entries = []
  1139. for n in fileset_node.getchildren():
  1140. url_n = n.find('./uri')
  1141. if url_n is None:
  1142. continue
  1143. entries.append({
  1144. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  1145. 'title': '%s - %s' % (title, n.tag),
  1146. 'url': compat_urlparse.urljoin(url, url_n.text),
  1147. 'duration': float_or_none(n.find('./duration').text),
  1148. })
  1149. return {
  1150. '_type': 'playlist',
  1151. 'entries': entries,
  1152. 'title': title,
  1153. }
  1154. def _real_extract(self, url):
  1155. if url.startswith('//'):
  1156. return {
  1157. '_type': 'url',
  1158. 'url': self.http_scheme() + url,
  1159. }
  1160. parsed_url = compat_urlparse.urlparse(url)
  1161. if not parsed_url.scheme:
  1162. default_search = self._downloader.params.get('default_search')
  1163. if default_search is None:
  1164. default_search = 'fixup_error'
  1165. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  1166. if '/' in url:
  1167. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  1168. return self.url_result('http://' + url)
  1169. elif default_search != 'fixup_error':
  1170. if default_search == 'auto_warning':
  1171. if re.match(r'^(?:url|URL)$', url):
  1172. raise ExtractorError(
  1173. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  1174. expected=True)
  1175. else:
  1176. self._downloader.report_warning(
  1177. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  1178. return self.url_result('ytsearch:' + url)
  1179. if default_search in ('error', 'fixup_error'):
  1180. raise ExtractorError(
  1181. '%r is not a valid URL. '
  1182. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  1183. % (url, url), expected=True)
  1184. else:
  1185. if ':' not in default_search:
  1186. default_search += ':'
  1187. return self.url_result(default_search + url)
  1188. url, smuggled_data = unsmuggle_url(url)
  1189. force_videoid = None
  1190. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  1191. if smuggled_data and 'force_videoid' in smuggled_data:
  1192. force_videoid = smuggled_data['force_videoid']
  1193. video_id = force_videoid
  1194. else:
  1195. video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
  1196. self.to_screen('%s: Requesting header' % video_id)
  1197. head_req = HEADRequest(url)
  1198. head_response = self._request_webpage(
  1199. head_req, video_id,
  1200. note=False, errnote='Could not send HEAD request to %s' % url,
  1201. fatal=False)
  1202. if head_response is not False:
  1203. # Check for redirect
  1204. new_url = head_response.geturl()
  1205. if url != new_url:
  1206. self.report_following_redirect(new_url)
  1207. if force_videoid:
  1208. new_url = smuggle_url(
  1209. new_url, {'force_videoid': force_videoid})
  1210. return self.url_result(new_url)
  1211. full_response = None
  1212. if head_response is False:
  1213. request = sanitized_Request(url)
  1214. request.add_header('Accept-Encoding', '*')
  1215. full_response = self._request_webpage(request, video_id)
  1216. head_response = full_response
  1217. # Check for direct link to a video
  1218. content_type = head_response.headers.get('Content-Type', '')
  1219. m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>.+)$', content_type)
  1220. if m:
  1221. upload_date = unified_strdate(
  1222. head_response.headers.get('Last-Modified'))
  1223. formats = []
  1224. if m.group('format_id').endswith('mpegurl'):
  1225. formats = self._extract_m3u8_formats(url, video_id, 'mp4')
  1226. else:
  1227. formats = [{
  1228. 'format_id': m.group('format_id'),
  1229. 'url': url,
  1230. 'vcodec': 'none' if m.group('type') == 'audio' else None
  1231. }]
  1232. return {
  1233. 'id': video_id,
  1234. 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
  1235. 'direct': True,
  1236. 'formats': formats,
  1237. 'upload_date': upload_date,
  1238. }
  1239. if not self._downloader.params.get('test', False) and not is_intentional:
  1240. force = self._downloader.params.get('force_generic_extractor', False)
  1241. self._downloader.report_warning(
  1242. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  1243. if not full_response:
  1244. request = sanitized_Request(url)
  1245. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  1246. # making it impossible to download only chunk of the file (yet we need only 512kB to
  1247. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  1248. # that will always result in downloading the whole file that is not desirable.
  1249. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  1250. # to accept raw bytes and being able to download only a chunk.
  1251. # It may probably better to solve this by checking Content-Type for application/octet-stream
  1252. # after HEAD request finishes, but not sure if we can rely on this.
  1253. request.add_header('Accept-Encoding', '*')
  1254. full_response = self._request_webpage(request, video_id)
  1255. # Maybe it's a direct link to a video?
  1256. # Be careful not to download the whole thing!
  1257. first_bytes = full_response.read(512)
  1258. if not is_html(first_bytes):
  1259. self._downloader.report_warning(
  1260. 'URL could be a direct video link, returning it as such.')
  1261. upload_date = unified_strdate(
  1262. head_response.headers.get('Last-Modified'))
  1263. return {
  1264. 'id': video_id,
  1265. 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
  1266. 'direct': True,
  1267. 'url': url,
  1268. 'upload_date': upload_date,
  1269. }
  1270. webpage = self._webpage_read_content(
  1271. full_response, url, video_id, prefix=first_bytes)
  1272. self.report_extraction(video_id)
  1273. # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
  1274. try:
  1275. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  1276. if doc.tag == 'rss':
  1277. return self._extract_rss(url, video_id, doc)
  1278. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  1279. return self._parse_smil(doc, url, video_id)
  1280. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  1281. return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
  1282. elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
  1283. return {
  1284. 'id': video_id,
  1285. 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
  1286. 'formats': self._parse_mpd_formats(
  1287. doc, video_id, mpd_base_url=url.rpartition('/')[0]),
  1288. }
  1289. except compat_xml_parse_error:
  1290. pass
  1291. # Is it a Camtasia project?
  1292. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  1293. if camtasia_res is not None:
  1294. return camtasia_res
  1295. # Sometimes embedded video player is hidden behind percent encoding
  1296. # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
  1297. # Unescaping the whole page allows to handle those cases in a generic way
  1298. webpage = compat_urllib_parse_unquote(webpage)
  1299. # it's tempting to parse this further, but you would
  1300. # have to take into account all the variations like
  1301. # Video Title - Site Name
  1302. # Site Name | Video Title
  1303. # Video Title - Tagline | Site Name
  1304. # and so on and so forth; it's just not practical
  1305. video_title = self._html_search_regex(
  1306. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  1307. default='video')
  1308. # Try to detect age limit automatically
  1309. age_limit = self._rta_search(webpage)
  1310. # And then there are the jokers who advertise that they use RTA,
  1311. # but actually don't.
  1312. AGE_LIMIT_MARKERS = [
  1313. r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
  1314. ]
  1315. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  1316. age_limit = 18
  1317. # video uploader is domain name
  1318. video_uploader = self._search_regex(
  1319. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  1320. # Helper method
  1321. def _playlist_from_matches(matches, getter=None, ie=None):
  1322. urlrs = orderedSet(
  1323. self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
  1324. for m in matches)
  1325. return self.playlist_result(
  1326. urlrs, playlist_id=video_id, playlist_title=video_title)
  1327. # Look for Brightcove Legacy Studio embeds
  1328. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  1329. if bc_urls:
  1330. self.to_screen('Brightcove video detected.')
  1331. entries = [{
  1332. '_type': 'url',
  1333. 'url': smuggle_url(bc_url, {'Referer': url}),
  1334. 'ie_key': 'BrightcoveLegacy'
  1335. } for bc_url in bc_urls]
  1336. return {
  1337. '_type': 'playlist',
  1338. 'title': video_title,
  1339. 'id': video_id,
  1340. 'entries': entries,
  1341. }
  1342. # Look for Brightcove New Studio embeds
  1343. bc_urls = BrightcoveNewIE._extract_urls(webpage)
  1344. if bc_urls:
  1345. return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
  1346. # Look for embedded rtl.nl player
  1347. matches = re.findall(
  1348. r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
  1349. webpage)
  1350. if matches:
  1351. return _playlist_from_matches(matches, ie='RtlNl')
  1352. vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
  1353. if vimeo_url is not None:
  1354. return self.url_result(vimeo_url)
  1355. vid_me_embed_url = self._search_regex(
  1356. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  1357. webpage, 'vid.me embed', default=None)
  1358. if vid_me_embed_url is not None:
  1359. return self.url_result(vid_me_embed_url, 'Vidme')
  1360. # Look for embedded YouTube player
  1361. matches = re.findall(r'''(?x)
  1362. (?:
  1363. <iframe[^>]+?src=|
  1364. data-video-url=|
  1365. <embed[^>]+?src=|
  1366. embedSWF\(?:\s*|
  1367. new\s+SWFObject\(
  1368. )
  1369. (["\'])
  1370. (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
  1371. (?:embed|v|p)/.+?)
  1372. \1''', webpage)
  1373. if matches:
  1374. return _playlist_from_matches(
  1375. matches, lambda m: unescapeHTML(m[1]))
  1376. # Look for lazyYT YouTube embed
  1377. matches = re.findall(
  1378. r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
  1379. if matches:
  1380. return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
  1381. # Look for embedded Dailymotion player
  1382. matches = re.findall(
  1383. r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
  1384. if matches:
  1385. return _playlist_from_matches(
  1386. matches, lambda m: unescapeHTML(m[1]))
  1387. # Look for embedded Dailymotion playlist player (#3822)
  1388. m = re.search(
  1389. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  1390. if m:
  1391. playlists = re.findall(
  1392. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  1393. if playlists:
  1394. return _playlist_from_matches(
  1395. playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
  1396. # Look for embedded Wistia player
  1397. match = re.search(
  1398. r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
  1399. if match:
  1400. embed_url = self._proto_relative_url(
  1401. unescapeHTML(match.group('url')))
  1402. return {
  1403. '_type': 'url_transparent',
  1404. 'url': embed_url,
  1405. 'ie_key': 'Wistia',
  1406. 'uploader': video_uploader,
  1407. 'title': video_title,
  1408. 'id': video_id,
  1409. }
  1410. match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
  1411. if match:
  1412. return {
  1413. '_type': 'url_transparent',
  1414. 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
  1415. 'ie_key': 'Wistia',
  1416. 'uploader': video_uploader,
  1417. 'title': video_title,
  1418. 'id': match.group('id')
  1419. }
  1420. # Look for SVT player
  1421. svt_url = SVTIE._extract_url(webpage)
  1422. if svt_url:
  1423. return self.url_result(svt_url, 'SVT')
  1424. # Look for embedded condenast player
  1425. matches = re.findall(
  1426. r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
  1427. webpage)
  1428. if matches:
  1429. return {
  1430. '_type': 'playlist',
  1431. 'entries': [{
  1432. '_type': 'url',
  1433. 'ie_key': 'CondeNast',
  1434. 'url': ma,
  1435. } for ma in matches],
  1436. 'title': video_title,
  1437. 'id': video_id,
  1438. }
  1439. # Look for Bandcamp pages with custom domain
  1440. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  1441. if mobj is not None:
  1442. burl = unescapeHTML(mobj.group(1))
  1443. # Don't set the extractor because it can be a track url or an album
  1444. return self.url_result(burl)
  1445. # Look for embedded Vevo player
  1446. mobj = re.search(
  1447. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  1448. if mobj is not None:
  1449. return self.url_result(mobj.group('url'))
  1450. # Look for embedded Viddler player
  1451. mobj = re.search(
  1452. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  1453. webpage)
  1454. if mobj is not None:
  1455. return self.url_result(mobj.group('url'))
  1456. # Look for NYTimes player
  1457. mobj = re.search(
  1458. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  1459. webpage)
  1460. if mobj is not None:
  1461. return self.url_result(mobj.group('url'))
  1462. # Look for Libsyn player
  1463. mobj = re.search(
  1464. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  1465. if mobj is not None:
  1466. return self.url_result(mobj.group('url'))
  1467. # Look for Ooyala videos
  1468. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
  1469. re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
  1470. re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
  1471. re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  1472. if mobj is not None:
  1473. return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
  1474. # Look for multiple Ooyala embeds on SBN network websites
  1475. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  1476. if mobj is not None:
  1477. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  1478. if embeds:
  1479. return _playlist_from_matches(
  1480. embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  1481. # Look for Aparat videos
  1482. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  1483. if mobj is not None:
  1484. return self.url_result(mobj.group(1), 'Aparat')
  1485. # Look for MPORA videos
  1486. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  1487. if mobj is not None:
  1488. return self.url_result(mobj.group(1), 'Mpora')
  1489. # Look for embedded NovaMov-based player
  1490. mobj = re.search(
  1491. r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
  1492. (?P<url>http://(?:(?:embed|www)\.)?
  1493. (?:novamov\.com|
  1494. nowvideo\.(?:ch|sx|eu|at|ag|co)|
  1495. videoweed\.(?:es|com)|
  1496. movshare\.(?:net|sx|ag)|
  1497. divxstage\.(?:eu|net|ch|co|at|ag))
  1498. /embed\.php.+?)\1''', webpage)
  1499. if mobj is not None:
  1500. return self.url_result(mobj.group('url'))
  1501. # Look for embedded Facebook player
  1502. mobj = re.search(
  1503. r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
  1504. if mobj is not None:
  1505. return self.url_result(mobj.group('url'), 'Facebook')
  1506. # Look for embedded VK player
  1507. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  1508. if mobj is not None:
  1509. return self.url_result(mobj.group('url'), 'VK')
  1510. # Look for embedded Odnoklassniki player
  1511. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
  1512. if mobj is not None:
  1513. return self.url_result(mobj.group('url'), 'Odnoklassniki')
  1514. # Look for embedded ivi player
  1515. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  1516. if mobj is not None:
  1517. return self.url_result(mobj.group('url'), 'Ivi')
  1518. # Look for embedded Huffington Post player
  1519. mobj = re.search(
  1520. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  1521. if mobj is not None:
  1522. return self.url_result(mobj.group('url'), 'HuffPost')
  1523. # Look for embed.ly
  1524. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  1525. if mobj is not None:
  1526. return self.url_result(mobj.group('url'))
  1527. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  1528. if mobj is not None:
  1529. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  1530. # Look for funnyordie embed
  1531. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  1532. if matches:
  1533. return _playlist_from_matches(
  1534. matches, getter=unescapeHTML, ie='FunnyOrDie')
  1535. # Look for BBC iPlayer embed
  1536. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  1537. if matches:
  1538. return _playlist_from_matches(matches, ie='BBCCoUk')
  1539. # Look for embedded RUTV player
  1540. rutv_url = RUTVIE._extract_url(webpage)
  1541. if rutv_url:
  1542. return self.url_result(rutv_url, 'RUTV')
  1543. # Look for embedded TVC player
  1544. tvc_url = TVCIE._extract_url(webpage)
  1545. if tvc_url:
  1546. return self.url_result(tvc_url, 'TVC')
  1547. # Look for embedded SportBox player
  1548. sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
  1549. if sportbox_urls:
  1550. return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
  1551. # Look for embedded PornHub player
  1552. pornhub_url = PornHubIE._extract_url(webpage)
  1553. if pornhub_url:
  1554. return self.url_result(pornhub_url, 'PornHub')
  1555. # Look for embedded XHamster player
  1556. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  1557. if xhamster_urls:
  1558. return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
  1559. # Look for embedded TNAFlixNetwork player
  1560. tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
  1561. if tnaflix_urls:
  1562. return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
  1563. # Look for embedded Tvigle player
  1564. mobj = re.search(
  1565. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  1566. if mobj is not None:
  1567. return self.url_result(mobj.group('url'), 'Tvigle')
  1568. # Look for embedded TED player
  1569. mobj = re.search(
  1570. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  1571. if mobj is not None:
  1572. return self.url_result(mobj.group('url'), 'TED')
  1573. # Look for embedded Ustream videos
  1574. mobj = re.search(
  1575. r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
  1576. if mobj is not None:
  1577. return self.url_result(mobj.group('url'), 'Ustream')
  1578. # Look for embedded arte.tv player
  1579. mobj = re.search(
  1580. r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
  1581. webpage)
  1582. if mobj is not None:
  1583. return self.url_result(mobj.group('url'), 'ArteTVEmbed')
  1584. # Look for embedded francetv player
  1585. mobj = re.search(
  1586. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  1587. webpage)
  1588. if mobj is not None:
  1589. return self.url_result(mobj.group('url'))
  1590. # Look for embedded smotri.com player
  1591. smotri_url = SmotriIE._extract_url(webpage)
  1592. if smotri_url:
  1593. return self.url_result(smotri_url, 'Smotri')
  1594. # Look for embedded Myvi.ru player
  1595. myvi_url = MyviIE._extract_url(webpage)
  1596. if myvi_url:
  1597. return self.url_result(myvi_url)
  1598. # Look for embedded soundcloud player
  1599. mobj = re.search(
  1600. r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
  1601. webpage)
  1602. if mobj is not None:
  1603. url = unescapeHTML(mobj.group('url'))
  1604. return self.url_result(url)
  1605. # Look for embedded vulture.com player
  1606. mobj = re.search(
  1607. r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
  1608. webpage)
  1609. if mobj is not None:
  1610. url = unescapeHTML(mobj.group('url'))
  1611. return self.url_result(url, ie='Vulture')
  1612. # Look for embedded mtvservices player
  1613. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  1614. if mtvservices_url:
  1615. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  1616. # Look for embedded yahoo player
  1617. mobj = re.search(
  1618. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  1619. webpage)
  1620. if mobj is not None:
  1621. return self.url_result(mobj.group('url'), 'Yahoo')
  1622. # Look for embedded sbs.com.au player
  1623. mobj = re.search(
  1624. r'''(?x)
  1625. (?:
  1626. <meta\s+property="og:video"\s+content=|
  1627. <iframe[^>]+?src=
  1628. )
  1629. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  1630. webpage)
  1631. if mobj is not None:
  1632. return self.url_result(mobj.group('url'), 'SBS')
  1633. # Look for embedded Cinchcast player
  1634. mobj = re.search(
  1635. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  1636. webpage)
  1637. if mobj is not None:
  1638. return self.url_result(mobj.group('url'), 'Cinchcast')
  1639. mobj = re.search(
  1640. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  1641. webpage)
  1642. if not mobj:
  1643. mobj = re.search(
  1644. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  1645. webpage)
  1646. if mobj is not None:
  1647. return self.url_result(mobj.group('url'), 'MLB')
  1648. mobj = re.search(
  1649. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  1650. webpage)
  1651. if mobj is not None:
  1652. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  1653. mobj = re.search(
  1654. r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
  1655. webpage)
  1656. if mobj is not None:
  1657. return self.url_result(mobj.group('url'), 'Livestream')
  1658. # Look for Zapiks embed
  1659. mobj = re.search(
  1660. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  1661. if mobj is not None:
  1662. return self.url_result(mobj.group('url'), 'Zapiks')
  1663. # Look for Kaltura embeds
  1664. mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
  1665. re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
  1666. if mobj is not None:
  1667. return self.url_result(smuggle_url(
  1668. 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
  1669. {'source_url': url}), 'Kaltura')
  1670. # Look for Eagle.Platform embeds
  1671. mobj = re.search(
  1672. r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
  1673. if mobj is not None:
  1674. return self.url_result(mobj.group('url'), 'EaglePlatform')
  1675. # Look for ClipYou (uses Eagle.Platform) embeds
  1676. mobj = re.search(
  1677. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  1678. if mobj is not None:
  1679. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  1680. # Look for Pladform embeds
  1681. pladform_url = PladformIE._extract_url(webpage)
  1682. if pladform_url:
  1683. return self.url_result(pladform_url)
  1684. # Look for Videomore embeds
  1685. videomore_url = VideomoreIE._extract_url(webpage)
  1686. if videomore_url:
  1687. return self.url_result(videomore_url)
  1688. # Look for Playwire embeds
  1689. mobj = re.search(
  1690. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  1691. if mobj is not None:
  1692. return self.url_result(mobj.group('url'))
  1693. # Look for 5min embeds
  1694. mobj = re.search(
  1695. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  1696. if mobj is not None:
  1697. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  1698. # Look for Crooks and Liars embeds
  1699. mobj = re.search(
  1700. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  1701. if mobj is not None:
  1702. return self.url_result(mobj.group('url'))
  1703. # Look for NBC Sports VPlayer embeds
  1704. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  1705. if nbc_sports_url:
  1706. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  1707. # Look for Google Drive embeds
  1708. google_drive_url = GoogleDriveIE._extract_url(webpage)
  1709. if google_drive_url:
  1710. return self.url_result(google_drive_url, 'GoogleDrive')
  1711. # Look for UDN embeds
  1712. mobj = re.search(
  1713. r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  1714. if mobj is not None:
  1715. return self.url_result(
  1716. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  1717. # Look for Senate ISVP iframe
  1718. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  1719. if senate_isvp_url:
  1720. return self.url_result(senate_isvp_url, 'SenateISVP')
  1721. # Look for Dailymotion Cloud videos
  1722. dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
  1723. if dmcloud_url:
  1724. return self.url_result(dmcloud_url, 'DailymotionCloud')
  1725. # Look for OnionStudios embeds
  1726. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  1727. if onionstudios_url:
  1728. return self.url_result(onionstudios_url)
  1729. # Look for SnagFilms embeds
  1730. snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
  1731. if snagfilms_url:
  1732. return self.url_result(snagfilms_url)
  1733. # Look for JWPlatform embeds
  1734. jwplatform_url = JWPlatformIE._extract_url(webpage)
  1735. if jwplatform_url:
  1736. return self.url_result(jwplatform_url, 'JWPlatform')
  1737. # Look for ScreenwaveMedia embeds
  1738. mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
  1739. if mobj is not None:
  1740. return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
  1741. # Look for Digiteka embeds
  1742. digiteka_url = DigitekaIE._extract_url(webpage)
  1743. if digiteka_url:
  1744. return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
  1745. # Look for Limelight embeds
  1746. mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
  1747. if mobj:
  1748. lm = {
  1749. 'Media': 'media',
  1750. 'Channel': 'channel',
  1751. 'ChannelList': 'channel_list',
  1752. }
  1753. return self.url_result('limelight:%s:%s' % (
  1754. lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
  1755. # Look for AdobeTVVideo embeds
  1756. mobj = re.search(
  1757. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  1758. webpage)
  1759. if mobj is not None:
  1760. return self.url_result(
  1761. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  1762. 'AdobeTVVideo')
  1763. def check_video(vurl):
  1764. if YoutubeIE.suitable(vurl):
  1765. return True
  1766. vpath = compat_urlparse.urlparse(vurl).path
  1767. vext = determine_ext(vpath)
  1768. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
  1769. def filter_video(urls):
  1770. return list(filter(check_video, urls))
  1771. # Start with something easy: JW Player in SWFObject
  1772. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  1773. if not found:
  1774. # Look for gorilla-vid style embedding
  1775. found = filter_video(re.findall(r'''(?sx)
  1776. (?:
  1777. jw_plugins|
  1778. JWPlayerOptions|
  1779. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  1780. )
  1781. .*?
  1782. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  1783. if not found:
  1784. # Broaden the search a little bit
  1785. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  1786. if not found:
  1787. # Broaden the findall a little bit: JWPlayer JS loader
  1788. found = filter_video(re.findall(
  1789. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  1790. if not found:
  1791. # Flow player
  1792. found = filter_video(re.findall(r'''(?xs)
  1793. flowplayer\("[^"]+",\s*
  1794. \{[^}]+?\}\s*,
  1795. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  1796. ["']?url["']?\s*:\s*["']([^"']+)["']
  1797. ''', webpage))
  1798. if not found:
  1799. # Cinerama player
  1800. found = re.findall(
  1801. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  1802. if not found:
  1803. # Try to find twitter cards info
  1804. found = filter_video(re.findall(
  1805. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  1806. if not found:
  1807. # We look for Open Graph info:
  1808. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  1809. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  1810. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  1811. if m_video_type is not None:
  1812. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  1813. if not found:
  1814. # HTML5 video
  1815. found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
  1816. if not found:
  1817. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  1818. found = re.search(
  1819. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  1820. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  1821. webpage)
  1822. if not found:
  1823. # Look also in Refresh HTTP header
  1824. refresh_header = head_response.headers.get('Refresh')
  1825. if refresh_header:
  1826. # In python 2 response HTTP headers are bytestrings
  1827. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  1828. refresh_header = refresh_header.decode('iso-8859-1')
  1829. found = re.search(REDIRECT_REGEX, refresh_header)
  1830. if found:
  1831. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  1832. self.report_following_redirect(new_url)
  1833. return {
  1834. '_type': 'url',
  1835. 'url': new_url,
  1836. }
  1837. if not found:
  1838. raise UnsupportedError(url)
  1839. entries = []
  1840. for video_url in found:
  1841. video_url = video_url.replace('\\/', '/')
  1842. video_url = compat_urlparse.urljoin(url, video_url)
  1843. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  1844. # Sometimes, jwplayer extraction will result in a YouTube URL
  1845. if YoutubeIE.suitable(video_url):
  1846. entries.append(self.url_result(video_url, 'Youtube'))
  1847. continue
  1848. # here's a fun little line of code for you:
  1849. video_id = os.path.splitext(video_id)[0]
  1850. entry_info_dict = {
  1851. 'id': video_id,
  1852. 'uploader': video_uploader,
  1853. 'title': video_title,
  1854. 'age_limit': age_limit,
  1855. }
  1856. ext = determine_ext(video_url)
  1857. if ext == 'smil':
  1858. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  1859. elif ext == 'xspf':
  1860. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  1861. elif ext == 'm3u8':
  1862. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  1863. elif ext == 'mpd':
  1864. entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
  1865. else:
  1866. entry_info_dict['url'] = video_url
  1867. entries.append(entry_info_dict)
  1868. if len(entries) == 1:
  1869. return entries[0]
  1870. else:
  1871. for num, e in enumerate(entries, start=1):
  1872. # 'url' results don't have a title
  1873. if e.get('title') is not None:
  1874. e['title'] = '%s (%d)' % (e['title'], num)
  1875. return {
  1876. '_type': 'playlist',
  1877. 'entries': entries,
  1878. }