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.

1977 lines
79 KiB

10 years ago
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
10 years ago
10 years ago
10 years ago
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
10 years ago
10 years ago
  1. # 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 .vimeo import VimeoIE
  48. from .dailymotion import DailymotionCloudIE
  49. from .onionstudios import OnionStudiosIE
  50. from .snagfilms import SnagFilmsEmbedIE
  51. from .screenwavemedia import ScreenwaveMediaIE
  52. from .mtv import MTVServicesEmbeddedIE
  53. from .pladform import PladformIE
  54. from .videomore import VideomoreIE
  55. from .googledrive import GoogleDriveIE
  56. from .jwplatform import JWPlatformIE
  57. from .digiteka import DigitekaIE
  58. class GenericIE(InfoExtractor):
  59. IE_DESC = 'Generic downloader that works on some sites'
  60. _VALID_URL = r'.*'
  61. IE_NAME = 'generic'
  62. _TESTS = [
  63. # Direct link to a video
  64. {
  65. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  66. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  67. 'info_dict': {
  68. 'id': 'trailer',
  69. 'ext': 'mp4',
  70. 'title': 'trailer',
  71. 'upload_date': '20100513',
  72. }
  73. },
  74. # Direct link to media delivered compressed (until Accept-Encoding is *)
  75. {
  76. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  77. 'md5': '128c42e68b13950268b648275386fc74',
  78. 'info_dict': {
  79. 'id': 'FictionJunction-Parallel_Hearts',
  80. 'ext': 'flac',
  81. 'title': 'FictionJunction-Parallel_Hearts',
  82. 'upload_date': '20140522',
  83. },
  84. 'expected_warnings': [
  85. 'URL could be a direct video link, returning it as such.'
  86. ]
  87. },
  88. # Direct download with broken HEAD
  89. {
  90. 'url': 'http://ai-radio.org:8000/radio.opus',
  91. 'info_dict': {
  92. 'id': 'radio',
  93. 'ext': 'opus',
  94. 'title': 'radio',
  95. },
  96. 'params': {
  97. 'skip_download': True, # infinite live stream
  98. },
  99. 'expected_warnings': [
  100. r'501.*Not Implemented'
  101. ],
  102. },
  103. # Direct link with incorrect MIME type
  104. {
  105. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  106. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  107. 'info_dict': {
  108. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  109. 'id': '5_Lennart_Poettering_-_Systemd',
  110. 'ext': 'webm',
  111. 'title': '5_Lennart_Poettering_-_Systemd',
  112. 'upload_date': '20141120',
  113. },
  114. 'expected_warnings': [
  115. 'URL could be a direct video link, returning it as such.'
  116. ]
  117. },
  118. # RSS feed
  119. {
  120. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  121. 'info_dict': {
  122. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  123. 'title': 'Zero Punctuation',
  124. 'description': 're:.*groundbreaking video review series.*'
  125. },
  126. 'playlist_mincount': 11,
  127. },
  128. # RSS feed with enclosure
  129. {
  130. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  131. 'info_dict': {
  132. 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  133. 'ext': 'm4v',
  134. 'upload_date': '20150228',
  135. 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  136. }
  137. },
  138. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  139. {
  140. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  141. 'info_dict': {
  142. 'id': 'smil',
  143. 'ext': 'mp4',
  144. 'title': 'Automatics, robotics and biocybernetics',
  145. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  146. 'upload_date': '20130627',
  147. 'formats': 'mincount:16',
  148. 'subtitles': 'mincount:1',
  149. },
  150. 'params': {
  151. 'force_generic_extractor': True,
  152. 'skip_download': True,
  153. },
  154. },
  155. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  156. {
  157. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  158. 'info_dict': {
  159. 'id': 'hds',
  160. 'ext': 'flv',
  161. 'title': 'hds',
  162. 'formats': 'mincount:1',
  163. },
  164. 'params': {
  165. 'skip_download': True,
  166. },
  167. },
  168. # SMIL from https://www.restudy.dk/video/play/id/1637
  169. {
  170. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  171. 'info_dict': {
  172. 'id': 'video_1637',
  173. 'ext': 'flv',
  174. 'title': 'video_1637',
  175. 'formats': 'mincount:3',
  176. },
  177. 'params': {
  178. 'skip_download': True,
  179. },
  180. },
  181. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  182. {
  183. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  184. 'info_dict': {
  185. 'id': 'smil-service',
  186. 'ext': 'flv',
  187. 'title': 'smil-service',
  188. 'formats': 'mincount:1',
  189. },
  190. 'params': {
  191. 'skip_download': True,
  192. },
  193. },
  194. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  195. {
  196. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  197. 'info_dict': {
  198. 'id': '4719370',
  199. 'ext': 'mp4',
  200. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  201. 'formats': 'mincount:3',
  202. },
  203. 'params': {
  204. 'skip_download': True,
  205. },
  206. },
  207. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  208. {
  209. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  210. 'info_dict': {
  211. 'id': 'mZlp2ctYIUEB',
  212. 'ext': 'mp4',
  213. 'title': 'Tikibad ontruimd wegens brand',
  214. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  215. 'thumbnail': 're:^https?://.*\.jpg$',
  216. 'duration': 33,
  217. },
  218. 'params': {
  219. 'skip_download': True,
  220. },
  221. },
  222. # google redirect
  223. {
  224. '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',
  225. 'info_dict': {
  226. 'id': 'cmQHVoWB5FY',
  227. 'ext': 'mp4',
  228. 'upload_date': '20130224',
  229. 'uploader_id': 'TheVerge',
  230. 'description': 're:^Chris Ziegler takes a look at the\.*',
  231. 'uploader': 'The Verge',
  232. 'title': 'First Firefox OS phones side-by-side',
  233. },
  234. 'params': {
  235. 'skip_download': False,
  236. }
  237. },
  238. {
  239. # redirect in Refresh HTTP header
  240. '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',
  241. 'info_dict': {
  242. 'id': 'pO8h3EaFRdo',
  243. 'ext': 'mp4',
  244. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  245. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  246. 'upload_date': '20150917',
  247. 'uploader_id': 'brtvofficial',
  248. 'uploader': 'Boiler Room',
  249. },
  250. 'params': {
  251. 'skip_download': False,
  252. },
  253. },
  254. {
  255. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  256. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  257. 'info_dict': {
  258. 'id': '13601338388002',
  259. 'ext': 'mp4',
  260. 'uploader': 'www.hodiho.fr',
  261. 'title': 'R\u00e9gis plante sa Jeep',
  262. }
  263. },
  264. # bandcamp page with custom domain
  265. {
  266. 'add_ie': ['Bandcamp'],
  267. 'url': 'http://bronyrock.com/track/the-pony-mash',
  268. 'info_dict': {
  269. 'id': '3235767654',
  270. 'ext': 'mp3',
  271. 'title': 'The Pony Mash',
  272. 'uploader': 'M_Pallante',
  273. },
  274. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  275. },
  276. # embedded brightcove video
  277. # it also tests brightcove videos that need to set the 'Referer' in the
  278. # http requests
  279. {
  280. 'add_ie': ['BrightcoveLegacy'],
  281. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  282. 'info_dict': {
  283. 'id': '2765128793001',
  284. 'ext': 'mp4',
  285. 'title': 'Le cours de bourse : l’analyse technique',
  286. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  287. 'uploader': 'BFM BUSINESS',
  288. },
  289. 'params': {
  290. 'skip_download': True,
  291. },
  292. },
  293. {
  294. # https://github.com/rg3/youtube-dl/issues/2253
  295. 'url': 'http://bcove.me/i6nfkrc3',
  296. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  297. 'info_dict': {
  298. 'id': '3101154703001',
  299. 'ext': 'mp4',
  300. 'title': 'Still no power',
  301. 'uploader': 'thestar.com',
  302. '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.',
  303. },
  304. 'add_ie': ['BrightcoveLegacy'],
  305. },
  306. {
  307. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  308. 'md5': 'fb973ecf6e4a78a67453647444222983',
  309. 'info_dict': {
  310. 'id': '3414141473001',
  311. 'ext': 'mp4',
  312. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  313. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  314. 'uploader': 'Championat',
  315. },
  316. },
  317. {
  318. # https://github.com/rg3/youtube-dl/issues/3541
  319. 'add_ie': ['BrightcoveLegacy'],
  320. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  321. 'info_dict': {
  322. 'id': '3866516442001',
  323. 'ext': 'mp4',
  324. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  325. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  326. 'uploader': 'SBS Broadcasting',
  327. },
  328. 'skip': 'Restricted to Netherlands',
  329. 'params': {
  330. 'skip_download': True, # m3u8 download
  331. },
  332. },
  333. # ooyala video
  334. {
  335. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  336. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  337. 'info_dict': {
  338. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  339. 'ext': 'mp4',
  340. 'title': '2cc213299525360.mov', # that's what we get
  341. 'duration': 238.231,
  342. },
  343. 'add_ie': ['Ooyala'],
  344. },
  345. {
  346. # ooyala video embedded with http://player.ooyala.com/iframe.js
  347. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  348. 'info_dict': {
  349. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  350. 'ext': 'mp4',
  351. 'title': '"Steve Jobs: Man in the Machine" trailer',
  352. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  353. 'duration': 135.427,
  354. },
  355. 'params': {
  356. 'skip_download': True,
  357. },
  358. },
  359. # multiple ooyala embeds on SBN network websites
  360. {
  361. 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
  362. 'info_dict': {
  363. 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
  364. 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
  365. },
  366. 'playlist_mincount': 3,
  367. 'params': {
  368. 'skip_download': True,
  369. },
  370. 'add_ie': ['Ooyala'],
  371. },
  372. # embed.ly video
  373. {
  374. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  375. 'info_dict': {
  376. 'id': '9ODmcdjQcHQ',
  377. 'ext': 'mp4',
  378. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  379. 'upload_date': '20140225',
  380. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  381. 'uploader': 'Tested',
  382. 'uploader_id': 'testedcom',
  383. },
  384. # No need to test YoutubeIE here
  385. 'params': {
  386. 'skip_download': True,
  387. },
  388. },
  389. # funnyordie embed
  390. {
  391. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  392. 'info_dict': {
  393. 'id': '18e820ec3f',
  394. 'ext': 'mp4',
  395. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  396. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  397. },
  398. },
  399. # RUTV embed
  400. {
  401. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  402. 'info_dict': {
  403. 'id': '776940',
  404. 'ext': 'mp4',
  405. 'title': 'Охотское море стало целиком российским',
  406. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  407. },
  408. 'params': {
  409. # m3u8 download
  410. 'skip_download': True,
  411. },
  412. },
  413. # TVC embed
  414. {
  415. '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/',
  416. 'info_dict': {
  417. 'id': '55304',
  418. 'ext': 'mp4',
  419. 'title': 'Дошкольное воспитание',
  420. },
  421. },
  422. # SportBox embed
  423. {
  424. 'url': 'http://www.vestifinance.ru/articles/25753',
  425. 'info_dict': {
  426. 'id': '25753',
  427. 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  428. },
  429. 'playlist': [{
  430. 'info_dict': {
  431. 'id': '370908',
  432. 'title': 'Госзаказ. День 3',
  433. 'ext': 'mp4',
  434. }
  435. }, {
  436. 'info_dict': {
  437. 'id': '370905',
  438. 'title': 'Госзаказ. День 2',
  439. 'ext': 'mp4',
  440. }
  441. }, {
  442. 'info_dict': {
  443. 'id': '370902',
  444. 'title': 'Госзаказ. День 1',
  445. 'ext': 'mp4',
  446. }
  447. }],
  448. 'params': {
  449. # m3u8 download
  450. 'skip_download': True,
  451. },
  452. },
  453. # Myvi.ru embed
  454. {
  455. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  456. 'info_dict': {
  457. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  458. 'ext': 'mp4',
  459. 'title': 'Ужастики, русский трейлер (2015)',
  460. 'thumbnail': 're:^https?://.*\.jpg$',
  461. 'duration': 153,
  462. }
  463. },
  464. # XHamster embed
  465. {
  466. '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',
  467. 'info_dict': {
  468. 'id': 'showthread',
  469. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  470. },
  471. 'playlist_mincount': 7,
  472. },
  473. # Embedded TED video
  474. {
  475. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  476. 'md5': '65fdff94098e4a607385a60c5177c638',
  477. 'info_dict': {
  478. 'id': '1969',
  479. 'ext': 'mp4',
  480. 'title': 'Hidden miracles of the natural world',
  481. 'uploader': 'Louie Schwartzberg',
  482. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  483. }
  484. },
  485. # Embedded Ustream video
  486. {
  487. 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
  488. 'md5': '27b99cdb639c9b12a79bca876a073417',
  489. 'info_dict': {
  490. 'id': '45734260',
  491. 'ext': 'flv',
  492. 'uploader': 'AU SPA: The NSA and Privacy',
  493. 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
  494. }
  495. },
  496. # nowvideo embed hidden behind percent encoding
  497. {
  498. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  499. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  500. 'info_dict': {
  501. 'id': '06e53103ca9aa',
  502. 'ext': 'flv',
  503. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  504. 'description': 'No description',
  505. },
  506. },
  507. # arte embed
  508. {
  509. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  510. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  511. 'info_dict': {
  512. 'id': '048195-004_PLUS7-F',
  513. 'ext': 'flv',
  514. 'title': 'X:enius',
  515. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  516. 'upload_date': '20140320',
  517. },
  518. 'params': {
  519. 'skip_download': 'Requires rtmpdump'
  520. }
  521. },
  522. # francetv embed
  523. {
  524. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  525. 'info_dict': {
  526. 'id': 'EV_30231',
  527. 'ext': 'mp4',
  528. 'title': 'Alcaline, le concert avec Calogero',
  529. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  530. 'upload_date': '20150226',
  531. 'timestamp': 1424989860,
  532. 'duration': 5400,
  533. },
  534. 'params': {
  535. # m3u8 downloads
  536. 'skip_download': True,
  537. },
  538. 'expected_warnings': [
  539. 'Forbidden'
  540. ]
  541. },
  542. # Condé Nast embed
  543. {
  544. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  545. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  546. 'info_dict': {
  547. 'id': '53501be369702d3275860000',
  548. 'ext': 'mp4',
  549. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  550. }
  551. },
  552. # Dailymotion embed
  553. {
  554. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  555. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  556. 'info_dict': {
  557. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  558. 'ext': 'mp4',
  559. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  560. 'uploader': 'Spi0n',
  561. },
  562. 'add_ie': ['Dailymotion'],
  563. },
  564. # YouTube embed
  565. {
  566. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  567. 'info_dict': {
  568. 'id': 'FXRb4ykk4S0',
  569. 'ext': 'mp4',
  570. 'title': 'The NBL Auction 2014',
  571. 'uploader': 'BADMINTON England',
  572. 'uploader_id': 'BADMINTONEvents',
  573. 'upload_date': '20140603',
  574. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  575. },
  576. 'add_ie': ['Youtube'],
  577. 'params': {
  578. 'skip_download': True,
  579. }
  580. },
  581. # MTVSercices embed
  582. {
  583. 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
  584. 'md5': '35727f82f58c76d996fc188f9755b0d5',
  585. 'info_dict': {
  586. 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
  587. 'ext': 'mp4',
  588. 'title': 'Review',
  589. 'description': 'Mario\'s life in the fast lane has never looked so good.',
  590. },
  591. },
  592. # YouTube embed via <data-embed-url="">
  593. {
  594. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  595. 'info_dict': {
  596. 'id': '4vAffPZIT44',
  597. 'ext': 'mp4',
  598. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  599. 'uploader': 'Gameloft',
  600. 'uploader_id': 'gameloft',
  601. 'upload_date': '20140828',
  602. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  603. },
  604. 'params': {
  605. 'skip_download': True,
  606. }
  607. },
  608. # Camtasia studio
  609. {
  610. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  611. 'playlist': [{
  612. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  613. 'info_dict': {
  614. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  615. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  616. 'ext': 'flv',
  617. 'duration': 2235.90,
  618. }
  619. }, {
  620. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  621. 'info_dict': {
  622. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  623. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  624. 'ext': 'flv',
  625. 'duration': 2235.93,
  626. }
  627. }],
  628. 'info_dict': {
  629. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  630. }
  631. },
  632. # Flowplayer
  633. {
  634. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  635. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  636. 'info_dict': {
  637. 'id': '5123ea6d5e5a7',
  638. 'ext': 'mp4',
  639. 'age_limit': 18,
  640. 'uploader': 'www.handjobhub.com',
  641. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  642. }
  643. },
  644. # Multiple brightcove videos
  645. # https://github.com/rg3/youtube-dl/issues/2283
  646. {
  647. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  648. 'info_dict': {
  649. 'id': 'always-never',
  650. 'title': 'Always / Never - The New Yorker',
  651. },
  652. 'playlist_count': 3,
  653. 'params': {
  654. 'extract_flat': False,
  655. 'skip_download': True,
  656. }
  657. },
  658. # MLB embed
  659. {
  660. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  661. 'md5': '96f09a37e44da40dd083e12d9a683327',
  662. 'info_dict': {
  663. 'id': '33322633',
  664. 'ext': 'mp4',
  665. 'title': 'Ump changes call to ball',
  666. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  667. 'duration': 48,
  668. 'timestamp': 1401537900,
  669. 'upload_date': '20140531',
  670. 'thumbnail': 're:^https?://.*\.jpg$',
  671. },
  672. },
  673. # Wistia embed
  674. {
  675. 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  676. 'md5': '8788b683c777a5cf25621eaf286d0c23',
  677. 'info_dict': {
  678. 'id': '1cfaf6b7ea',
  679. 'ext': 'mov',
  680. 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
  681. 'duration': 643.0,
  682. 'filesize': 182808282,
  683. 'uploader': 'education-portal.com',
  684. },
  685. },
  686. {
  687. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  688. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  689. 'info_dict': {
  690. 'id': 'uxjb0lwrcz',
  691. 'ext': 'mp4',
  692. 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
  693. 'duration': 1715.0,
  694. 'uploader': 'thoughtworks.wistia.com',
  695. },
  696. },
  697. # Soundcloud embed
  698. {
  699. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  700. 'info_dict': {
  701. 'id': '174391317',
  702. 'ext': 'mp3',
  703. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  704. 'uploader': 'Sophos Security',
  705. 'title': 'Chet Chat 171 - Oct 29, 2014',
  706. 'upload_date': '20141029',
  707. }
  708. },
  709. # Livestream embed
  710. {
  711. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  712. 'info_dict': {
  713. 'id': '67864563',
  714. 'ext': 'flv',
  715. 'upload_date': '20141112',
  716. 'title': 'Rosetta #CometLanding webcast HL 10',
  717. }
  718. },
  719. # LazyYT
  720. {
  721. 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
  722. 'info_dict': {
  723. 'id': '1986',
  724. 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
  725. },
  726. 'playlist_mincount': 2,
  727. },
  728. # Cinchcast embed
  729. {
  730. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  731. 'info_dict': {
  732. 'id': '7141703',
  733. 'ext': 'mp3',
  734. 'upload_date': '20141126',
  735. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  736. }
  737. },
  738. # Cinerama player
  739. {
  740. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  741. 'info_dict': {
  742. 'id': '730m_DandD_1901_512k',
  743. 'ext': 'mp4',
  744. 'uploader': 'www.abc.net.au',
  745. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  746. }
  747. },
  748. # embedded viddler video
  749. {
  750. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  751. 'info_dict': {
  752. 'id': '4d03aad9',
  753. 'ext': 'mp4',
  754. 'uploader': 'deadspin',
  755. 'title': 'WALL-TO-GORTAT',
  756. 'timestamp': 1422285291,
  757. 'upload_date': '20150126',
  758. },
  759. 'add_ie': ['Viddler'],
  760. },
  761. # Libsyn embed
  762. {
  763. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  764. 'info_dict': {
  765. 'id': '3377616',
  766. 'ext': 'mp3',
  767. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  768. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  769. 'upload_date': '20150220',
  770. },
  771. },
  772. # jwplayer YouTube
  773. {
  774. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  775. 'info_dict': {
  776. 'id': 'Mrj4DVp2zeA',
  777. 'ext': 'mp4',
  778. 'upload_date': '20150212',
  779. 'uploader': 'The National Archives UK',
  780. 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
  781. 'uploader_id': 'NationalArchives08',
  782. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  783. },
  784. },
  785. # rtl.nl embed
  786. {
  787. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  788. 'playlist_mincount': 5,
  789. 'info_dict': {
  790. 'id': 'aanslagen-kopenhagen',
  791. 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
  792. }
  793. },
  794. # Zapiks embed
  795. {
  796. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  797. 'info_dict': {
  798. 'id': '118046',
  799. 'ext': 'mp4',
  800. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  801. }
  802. },
  803. # Kaltura embed
  804. {
  805. 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
  806. 'info_dict': {
  807. 'id': '1_eergr3h1',
  808. 'ext': 'mp4',
  809. 'upload_date': '20150226',
  810. 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
  811. 'timestamp': int,
  812. 'title': 'John Carlson Postgame 2/25/15',
  813. },
  814. },
  815. # Kaltura embed (different embed code)
  816. {
  817. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  818. 'info_dict': {
  819. 'id': '1_a52wc67y',
  820. 'ext': 'flv',
  821. 'upload_date': '20150127',
  822. 'uploader_id': 'PremierMedia',
  823. 'timestamp': int,
  824. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  825. },
  826. },
  827. # Kaltura embed protected with referrer
  828. {
  829. 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
  830. 'info_dict': {
  831. 'id': '1_g4fbemnq',
  832. 'ext': 'mp4',
  833. 'title': 'Violetta - Achter De Schermen - Ruggero',
  834. 'description': 'Achter de schermen met Ruggero',
  835. 'timestamp': 1435133761,
  836. 'upload_date': '20150624',
  837. 'uploader_id': 'echojecka',
  838. },
  839. },
  840. # Eagle.Platform embed (generic URL)
  841. {
  842. 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
  843. 'info_dict': {
  844. 'id': '227304',
  845. 'ext': 'mp4',
  846. 'title': 'Навальный вышел на свободу',
  847. 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
  848. 'thumbnail': 're:^https?://.*\.jpg$',
  849. 'duration': 87,
  850. 'view_count': int,
  851. 'age_limit': 0,
  852. },
  853. },
  854. # ClipYou (Eagle.Platform) embed (custom URL)
  855. {
  856. 'url': 'http://muz-tv.ru/play/7129/',
  857. 'info_dict': {
  858. 'id': '12820',
  859. 'ext': 'mp4',
  860. 'title': "'O Sole Mio",
  861. 'thumbnail': 're:^https?://.*\.jpg$',
  862. 'duration': 216,
  863. 'view_count': int,
  864. },
  865. },
  866. # Pladform embed
  867. {
  868. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  869. 'info_dict': {
  870. 'id': '100183293',
  871. 'ext': 'mp4',
  872. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  873. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  874. 'thumbnail': 're:^https?://.*\.jpg$',
  875. 'duration': 694,
  876. 'age_limit': 0,
  877. },
  878. },
  879. # Playwire embed
  880. {
  881. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  882. 'info_dict': {
  883. 'id': '3519514',
  884. 'ext': 'mp4',
  885. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  886. 'thumbnail': 're:^https?://.*\.png$',
  887. 'duration': 45.115,
  888. },
  889. },
  890. # 5min embed
  891. {
  892. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  893. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  894. 'info_dict': {
  895. 'id': '518726732',
  896. 'ext': 'mp4',
  897. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  898. },
  899. },
  900. # SVT embed
  901. {
  902. 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
  903. 'info_dict': {
  904. 'id': '2900353',
  905. 'ext': 'flv',
  906. 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
  907. 'duration': 27,
  908. 'age_limit': 0,
  909. },
  910. },
  911. # Crooks and Liars embed
  912. {
  913. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  914. 'info_dict': {
  915. 'id': '8RUoRhRi',
  916. 'ext': 'mp4',
  917. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  918. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  919. 'timestamp': 1428207000,
  920. 'upload_date': '20150405',
  921. 'uploader': 'Heather',
  922. },
  923. },
  924. # Crooks and Liars external embed
  925. {
  926. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  927. 'info_dict': {
  928. 'id': 'MTE3MjUtMzQ2MzA',
  929. 'ext': 'mp4',
  930. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  931. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  932. 'timestamp': 1265032391,
  933. 'upload_date': '20100201',
  934. 'uploader': 'Heather',
  935. },
  936. },
  937. # NBC Sports vplayer embed
  938. {
  939. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  940. 'info_dict': {
  941. 'id': 'ln7x1qSThw4k',
  942. 'ext': 'flv',
  943. 'title': "PFT Live: New leader in the 'new-look' defense",
  944. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  945. },
  946. },
  947. # UDN embed
  948. {
  949. 'url': 'http://www.udn.com/news/story/7314/822787',
  950. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  951. 'info_dict': {
  952. 'id': '300346',
  953. 'ext': 'mp4',
  954. 'title': '中一中男師變性 全校師生力挺',
  955. 'thumbnail': 're:^https?://.*\.jpg$',
  956. }
  957. },
  958. # Ooyala embed
  959. {
  960. 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
  961. 'info_dict': {
  962. 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
  963. 'ext': 'mp4',
  964. 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
  965. 'title': 'This is what separates the Excel masters from the wannabes',
  966. 'duration': 191.933,
  967. },
  968. 'params': {
  969. # m3u8 downloads
  970. 'skip_download': True,
  971. }
  972. },
  973. # Contains a SMIL manifest
  974. {
  975. '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',
  976. 'info_dict': {
  977. 'id': 'file',
  978. 'ext': 'flv',
  979. 'title': '+ Football: Lottery Champions League Europe',
  980. 'uploader': 'www.telewebion.com',
  981. },
  982. 'params': {
  983. # rtmpe downloads
  984. 'skip_download': True,
  985. }
  986. },
  987. # Brightcove URL in single quotes
  988. {
  989. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  990. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  991. 'info_dict': {
  992. 'id': '4255764656001',
  993. 'ext': 'mp4',
  994. 'title': 'SN Presents: Russell Martin, World Citizen',
  995. '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.',
  996. 'uploader': 'Rogers Sportsnet',
  997. },
  998. },
  999. # Dailymotion Cloud video
  1000. {
  1001. 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
  1002. 'md5': '49444254273501a64675a7e68c502681',
  1003. 'info_dict': {
  1004. 'id': '5585de919473990de4bee11b',
  1005. 'ext': 'mp4',
  1006. 'title': 'Le débat',
  1007. 'thumbnail': 're:^https?://.*\.jpe?g$',
  1008. }
  1009. },
  1010. # OnionStudios embed
  1011. {
  1012. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1013. 'info_dict': {
  1014. 'id': '2855',
  1015. 'ext': 'mp4',
  1016. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1017. 'thumbnail': 're:^https?://.*\.jpe?g$',
  1018. 'uploader': 'ClickHole',
  1019. 'uploader_id': 'clickhole',
  1020. }
  1021. },
  1022. # SnagFilms embed
  1023. {
  1024. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1025. 'info_dict': {
  1026. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1027. 'ext': 'mp4',
  1028. 'title': '#whilewewatch',
  1029. }
  1030. },
  1031. # AdobeTVVideo embed
  1032. {
  1033. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1034. 'md5': '43662b577c018ad707a63766462b1e87',
  1035. 'info_dict': {
  1036. 'id': '2456',
  1037. 'ext': 'mp4',
  1038. 'title': 'New experience with Acrobat DC',
  1039. 'description': 'New experience with Acrobat DC',
  1040. 'duration': 248.667,
  1041. },
  1042. },
  1043. # ScreenwaveMedia embed
  1044. {
  1045. 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
  1046. 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
  1047. 'info_dict': {
  1048. 'id': 'cinemasnob-55d26273809dd',
  1049. 'ext': 'mp4',
  1050. 'title': 'cinemasnob',
  1051. },
  1052. },
  1053. # BrightcoveInPageEmbed embed
  1054. {
  1055. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1056. 'info_dict': {
  1057. 'id': '4238694884001',
  1058. 'ext': 'flv',
  1059. 'title': 'Tabletop: Dread, Last Thoughts',
  1060. 'description': 'Tabletop: Dread, Last Thoughts',
  1061. 'duration': 51690,
  1062. },
  1063. },
  1064. # JWPlayer with M3U8
  1065. {
  1066. 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
  1067. 'info_dict': {
  1068. 'id': 'playlist',
  1069. 'ext': 'mp4',
  1070. 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
  1071. 'uploader': 'ren.tv',
  1072. },
  1073. 'params': {
  1074. # m3u8 downloads
  1075. 'skip_download': True,
  1076. }
  1077. }
  1078. ]
  1079. def report_following_redirect(self, new_url):
  1080. """Report information extraction."""
  1081. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  1082. def _extract_rss(self, url, video_id, doc):
  1083. playlist_title = doc.find('./channel/title').text
  1084. playlist_desc_el = doc.find('./channel/description')
  1085. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  1086. entries = []
  1087. for it in doc.findall('./channel/item'):
  1088. next_url = xpath_text(it, 'link', fatal=False)
  1089. if not next_url:
  1090. enclosure_nodes = it.findall('./enclosure')
  1091. for e in enclosure_nodes:
  1092. next_url = e.attrib.get('url')
  1093. if next_url:
  1094. break
  1095. if not next_url:
  1096. continue
  1097. entries.append({
  1098. '_type': 'url',
  1099. 'url': next_url,
  1100. 'title': it.find('title').text,
  1101. })
  1102. return {
  1103. '_type': 'playlist',
  1104. 'id': url,
  1105. 'title': playlist_title,
  1106. 'description': playlist_desc,
  1107. 'entries': entries,
  1108. }
  1109. def _extract_camtasia(self, url, video_id, webpage):
  1110. """ Returns None if no camtasia video can be found. """
  1111. camtasia_cfg = self._search_regex(
  1112. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  1113. webpage, 'camtasia configuration file', default=None)
  1114. if camtasia_cfg is None:
  1115. return None
  1116. title = self._html_search_meta('DC.title', webpage, fatal=True)
  1117. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  1118. camtasia_cfg = self._download_xml(
  1119. camtasia_url, video_id,
  1120. note='Downloading camtasia configuration',
  1121. errnote='Failed to download camtasia configuration')
  1122. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  1123. entries = []
  1124. for n in fileset_node.getchildren():
  1125. url_n = n.find('./uri')
  1126. if url_n is None:
  1127. continue
  1128. entries.append({
  1129. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  1130. 'title': '%s - %s' % (title, n.tag),
  1131. 'url': compat_urlparse.urljoin(url, url_n.text),
  1132. 'duration': float_or_none(n.find('./duration').text),
  1133. })
  1134. return {
  1135. '_type': 'playlist',
  1136. 'entries': entries,
  1137. 'title': title,
  1138. }
  1139. def _real_extract(self, url):
  1140. if url.startswith('//'):
  1141. return {
  1142. '_type': 'url',
  1143. 'url': self.http_scheme() + url,
  1144. }
  1145. parsed_url = compat_urlparse.urlparse(url)
  1146. if not parsed_url.scheme:
  1147. default_search = self._downloader.params.get('default_search')
  1148. if default_search is None:
  1149. default_search = 'fixup_error'
  1150. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  1151. if '/' in url:
  1152. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  1153. return self.url_result('http://' + url)
  1154. elif default_search != 'fixup_error':
  1155. if default_search == 'auto_warning':
  1156. if re.match(r'^(?:url|URL)$', url):
  1157. raise ExtractorError(
  1158. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  1159. expected=True)
  1160. else:
  1161. self._downloader.report_warning(
  1162. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  1163. return self.url_result('ytsearch:' + url)
  1164. if default_search in ('error', 'fixup_error'):
  1165. raise ExtractorError(
  1166. '%r is not a valid URL. '
  1167. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  1168. % (url, url), expected=True)
  1169. else:
  1170. if ':' not in default_search:
  1171. default_search += ':'
  1172. return self.url_result(default_search + url)
  1173. url, smuggled_data = unsmuggle_url(url)
  1174. force_videoid = None
  1175. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  1176. if smuggled_data and 'force_videoid' in smuggled_data:
  1177. force_videoid = smuggled_data['force_videoid']
  1178. video_id = force_videoid
  1179. else:
  1180. video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
  1181. self.to_screen('%s: Requesting header' % video_id)
  1182. head_req = HEADRequest(url)
  1183. head_response = self._request_webpage(
  1184. head_req, video_id,
  1185. note=False, errnote='Could not send HEAD request to %s' % url,
  1186. fatal=False)
  1187. if head_response is not False:
  1188. # Check for redirect
  1189. new_url = head_response.geturl()
  1190. if url != new_url:
  1191. self.report_following_redirect(new_url)
  1192. if force_videoid:
  1193. new_url = smuggle_url(
  1194. new_url, {'force_videoid': force_videoid})
  1195. return self.url_result(new_url)
  1196. full_response = None
  1197. if head_response is False:
  1198. request = sanitized_Request(url)
  1199. request.add_header('Accept-Encoding', '*')
  1200. full_response = self._request_webpage(request, video_id)
  1201. head_response = full_response
  1202. # Check for direct link to a video
  1203. content_type = head_response.headers.get('Content-Type', '')
  1204. m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>.+)$', content_type)
  1205. if m:
  1206. upload_date = unified_strdate(
  1207. head_response.headers.get('Last-Modified'))
  1208. formats = []
  1209. if m.group('format_id').endswith('mpegurl'):
  1210. formats = self._extract_m3u8_formats(url, video_id, 'mp4')
  1211. else:
  1212. formats = [{
  1213. 'format_id': m.group('format_id'),
  1214. 'url': url,
  1215. 'vcodec': 'none' if m.group('type') == 'audio' else None
  1216. }]
  1217. return {
  1218. 'id': video_id,
  1219. 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
  1220. 'direct': True,
  1221. 'formats': formats,
  1222. 'upload_date': upload_date,
  1223. }
  1224. if not self._downloader.params.get('test', False) and not is_intentional:
  1225. force = self._downloader.params.get('force_generic_extractor', False)
  1226. self._downloader.report_warning(
  1227. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  1228. if not full_response:
  1229. request = sanitized_Request(url)
  1230. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  1231. # making it impossible to download only chunk of the file (yet we need only 512kB to
  1232. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  1233. # that will always result in downloading the whole file that is not desirable.
  1234. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  1235. # to accept raw bytes and being able to download only a chunk.
  1236. # It may probably better to solve this by checking Content-Type for application/octet-stream
  1237. # after HEAD request finishes, but not sure if we can rely on this.
  1238. request.add_header('Accept-Encoding', '*')
  1239. full_response = self._request_webpage(request, video_id)
  1240. # Maybe it's a direct link to a video?
  1241. # Be careful not to download the whole thing!
  1242. first_bytes = full_response.read(512)
  1243. if not is_html(first_bytes):
  1244. self._downloader.report_warning(
  1245. 'URL could be a direct video link, returning it as such.')
  1246. upload_date = unified_strdate(
  1247. head_response.headers.get('Last-Modified'))
  1248. return {
  1249. 'id': video_id,
  1250. 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
  1251. 'direct': True,
  1252. 'url': url,
  1253. 'upload_date': upload_date,
  1254. }
  1255. webpage = self._webpage_read_content(
  1256. full_response, url, video_id, prefix=first_bytes)
  1257. self.report_extraction(video_id)
  1258. # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
  1259. try:
  1260. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  1261. if doc.tag == 'rss':
  1262. return self._extract_rss(url, video_id, doc)
  1263. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  1264. return self._parse_smil(doc, url, video_id)
  1265. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  1266. return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
  1267. elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
  1268. return {
  1269. 'id': video_id,
  1270. 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
  1271. 'formats': self._parse_mpd_formats(doc, video_id),
  1272. }
  1273. except compat_xml_parse_error:
  1274. pass
  1275. # Is it a Camtasia project?
  1276. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  1277. if camtasia_res is not None:
  1278. return camtasia_res
  1279. # Sometimes embedded video player is hidden behind percent encoding
  1280. # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
  1281. # Unescaping the whole page allows to handle those cases in a generic way
  1282. webpage = compat_urllib_parse_unquote(webpage)
  1283. # it's tempting to parse this further, but you would
  1284. # have to take into account all the variations like
  1285. # Video Title - Site Name
  1286. # Site Name | Video Title
  1287. # Video Title - Tagline | Site Name
  1288. # and so on and so forth; it's just not practical
  1289. video_title = self._html_search_regex(
  1290. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  1291. default='video')
  1292. # Try to detect age limit automatically
  1293. age_limit = self._rta_search(webpage)
  1294. # And then there are the jokers who advertise that they use RTA,
  1295. # but actually don't.
  1296. AGE_LIMIT_MARKERS = [
  1297. r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
  1298. ]
  1299. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  1300. age_limit = 18
  1301. # video uploader is domain name
  1302. video_uploader = self._search_regex(
  1303. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  1304. # Helper method
  1305. def _playlist_from_matches(matches, getter=None, ie=None):
  1306. urlrs = orderedSet(
  1307. self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
  1308. for m in matches)
  1309. return self.playlist_result(
  1310. urlrs, playlist_id=video_id, playlist_title=video_title)
  1311. # Look for Brightcove Legacy Studio embeds
  1312. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  1313. if bc_urls:
  1314. self.to_screen('Brightcove video detected.')
  1315. entries = [{
  1316. '_type': 'url',
  1317. 'url': smuggle_url(bc_url, {'Referer': url}),
  1318. 'ie_key': 'BrightcoveLegacy'
  1319. } for bc_url in bc_urls]
  1320. return {
  1321. '_type': 'playlist',
  1322. 'title': video_title,
  1323. 'id': video_id,
  1324. 'entries': entries,
  1325. }
  1326. # Look for Brightcove New Studio embeds
  1327. bc_urls = BrightcoveNewIE._extract_urls(webpage)
  1328. if bc_urls:
  1329. return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
  1330. # Look for embedded rtl.nl player
  1331. matches = re.findall(
  1332. r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
  1333. webpage)
  1334. if matches:
  1335. return _playlist_from_matches(matches, ie='RtlNl')
  1336. vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
  1337. if vimeo_url is not None:
  1338. return self.url_result(vimeo_url)
  1339. vid_me_embed_url = self._search_regex(
  1340. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  1341. webpage, 'vid.me embed', default=None)
  1342. if vid_me_embed_url is not None:
  1343. return self.url_result(vid_me_embed_url, 'Vidme')
  1344. # Look for embedded YouTube player
  1345. matches = re.findall(r'''(?x)
  1346. (?:
  1347. <iframe[^>]+?src=|
  1348. data-video-url=|
  1349. <embed[^>]+?src=|
  1350. embedSWF\(?:\s*|
  1351. new\s+SWFObject\(
  1352. )
  1353. (["\'])
  1354. (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
  1355. (?:embed|v|p)/.+?)
  1356. \1''', webpage)
  1357. if matches:
  1358. return _playlist_from_matches(
  1359. matches, lambda m: unescapeHTML(m[1]))
  1360. # Look for lazyYT YouTube embed
  1361. matches = re.findall(
  1362. r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
  1363. if matches:
  1364. return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
  1365. # Look for embedded Dailymotion player
  1366. matches = re.findall(
  1367. r'<(?:embed|iframe)[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
  1368. if matches:
  1369. return _playlist_from_matches(
  1370. matches, lambda m: unescapeHTML(m[1]))
  1371. # Look for embedded Dailymotion playlist player (#3822)
  1372. m = re.search(
  1373. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  1374. if m:
  1375. playlists = re.findall(
  1376. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  1377. if playlists:
  1378. return _playlist_from_matches(
  1379. playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
  1380. # Look for embedded Wistia player
  1381. match = re.search(
  1382. r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
  1383. if match:
  1384. embed_url = self._proto_relative_url(
  1385. unescapeHTML(match.group('url')))
  1386. return {
  1387. '_type': 'url_transparent',
  1388. 'url': embed_url,
  1389. 'ie_key': 'Wistia',
  1390. 'uploader': video_uploader,
  1391. 'title': video_title,
  1392. 'id': video_id,
  1393. }
  1394. match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
  1395. if match:
  1396. return {
  1397. '_type': 'url_transparent',
  1398. 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
  1399. 'ie_key': 'Wistia',
  1400. 'uploader': video_uploader,
  1401. 'title': video_title,
  1402. 'id': match.group('id')
  1403. }
  1404. # Look for SVT player
  1405. svt_url = SVTIE._extract_url(webpage)
  1406. if svt_url:
  1407. return self.url_result(svt_url, 'SVT')
  1408. # Look for embedded condenast player
  1409. matches = re.findall(
  1410. r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
  1411. webpage)
  1412. if matches:
  1413. return {
  1414. '_type': 'playlist',
  1415. 'entries': [{
  1416. '_type': 'url',
  1417. 'ie_key': 'CondeNast',
  1418. 'url': ma,
  1419. } for ma in matches],
  1420. 'title': video_title,
  1421. 'id': video_id,
  1422. }
  1423. # Look for Bandcamp pages with custom domain
  1424. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  1425. if mobj is not None:
  1426. burl = unescapeHTML(mobj.group(1))
  1427. # Don't set the extractor because it can be a track url or an album
  1428. return self.url_result(burl)
  1429. # Look for embedded Vevo player
  1430. mobj = re.search(
  1431. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  1432. if mobj is not None:
  1433. return self.url_result(mobj.group('url'))
  1434. # Look for embedded Viddler player
  1435. mobj = re.search(
  1436. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  1437. webpage)
  1438. if mobj is not None:
  1439. return self.url_result(mobj.group('url'))
  1440. # Look for NYTimes player
  1441. mobj = re.search(
  1442. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  1443. webpage)
  1444. if mobj is not None:
  1445. return self.url_result(mobj.group('url'))
  1446. # Look for Libsyn player
  1447. mobj = re.search(
  1448. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  1449. if mobj is not None:
  1450. return self.url_result(mobj.group('url'))
  1451. # Look for Ooyala videos
  1452. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
  1453. re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
  1454. re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
  1455. re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  1456. if mobj is not None:
  1457. return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
  1458. # Look for multiple Ooyala embeds on SBN network websites
  1459. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  1460. if mobj is not None:
  1461. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  1462. if embeds:
  1463. return _playlist_from_matches(
  1464. embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  1465. # Look for Aparat videos
  1466. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  1467. if mobj is not None:
  1468. return self.url_result(mobj.group(1), 'Aparat')
  1469. # Look for MPORA videos
  1470. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  1471. if mobj is not None:
  1472. return self.url_result(mobj.group(1), 'Mpora')
  1473. # Look for embedded NovaMov-based player
  1474. mobj = re.search(
  1475. r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
  1476. (?P<url>http://(?:(?:embed|www)\.)?
  1477. (?:novamov\.com|
  1478. nowvideo\.(?:ch|sx|eu|at|ag|co)|
  1479. videoweed\.(?:es|com)|
  1480. movshare\.(?:net|sx|ag)|
  1481. divxstage\.(?:eu|net|ch|co|at|ag))
  1482. /embed\.php.+?)\1''', webpage)
  1483. if mobj is not None:
  1484. return self.url_result(mobj.group('url'))
  1485. # Look for embedded Facebook player
  1486. mobj = re.search(
  1487. r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
  1488. if mobj is not None:
  1489. return self.url_result(mobj.group('url'), 'Facebook')
  1490. # Look for embedded VK player
  1491. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  1492. if mobj is not None:
  1493. return self.url_result(mobj.group('url'), 'VK')
  1494. # Look for embedded ivi player
  1495. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  1496. if mobj is not None:
  1497. return self.url_result(mobj.group('url'), 'Ivi')
  1498. # Look for embedded Huffington Post player
  1499. mobj = re.search(
  1500. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  1501. if mobj is not None:
  1502. return self.url_result(mobj.group('url'), 'HuffPost')
  1503. # Look for embed.ly
  1504. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  1505. if mobj is not None:
  1506. return self.url_result(mobj.group('url'))
  1507. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  1508. if mobj is not None:
  1509. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  1510. # Look for funnyordie embed
  1511. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  1512. if matches:
  1513. return _playlist_from_matches(
  1514. matches, getter=unescapeHTML, ie='FunnyOrDie')
  1515. # Look for BBC iPlayer embed
  1516. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  1517. if matches:
  1518. return _playlist_from_matches(matches, ie='BBCCoUk')
  1519. # Look for embedded RUTV player
  1520. rutv_url = RUTVIE._extract_url(webpage)
  1521. if rutv_url:
  1522. return self.url_result(rutv_url, 'RUTV')
  1523. # Look for embedded TVC player
  1524. tvc_url = TVCIE._extract_url(webpage)
  1525. if tvc_url:
  1526. return self.url_result(tvc_url, 'TVC')
  1527. # Look for embedded SportBox player
  1528. sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
  1529. if sportbox_urls:
  1530. return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
  1531. # Look for embedded PornHub player
  1532. pornhub_url = PornHubIE._extract_url(webpage)
  1533. if pornhub_url:
  1534. return self.url_result(pornhub_url, 'PornHub')
  1535. # Look for embedded XHamster player
  1536. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  1537. if xhamster_urls:
  1538. return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
  1539. # Look for embedded Tvigle player
  1540. mobj = re.search(
  1541. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  1542. if mobj is not None:
  1543. return self.url_result(mobj.group('url'), 'Tvigle')
  1544. # Look for embedded TED player
  1545. mobj = re.search(
  1546. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  1547. if mobj is not None:
  1548. return self.url_result(mobj.group('url'), 'TED')
  1549. # Look for embedded Ustream videos
  1550. mobj = re.search(
  1551. r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
  1552. if mobj is not None:
  1553. return self.url_result(mobj.group('url'), 'Ustream')
  1554. # Look for embedded arte.tv player
  1555. mobj = re.search(
  1556. r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
  1557. webpage)
  1558. if mobj is not None:
  1559. return self.url_result(mobj.group('url'), 'ArteTVEmbed')
  1560. # Look for embedded francetv player
  1561. mobj = re.search(
  1562. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  1563. webpage)
  1564. if mobj is not None:
  1565. return self.url_result(mobj.group('url'))
  1566. # Look for embedded smotri.com player
  1567. smotri_url = SmotriIE._extract_url(webpage)
  1568. if smotri_url:
  1569. return self.url_result(smotri_url, 'Smotri')
  1570. # Look for embedded Myvi.ru player
  1571. myvi_url = MyviIE._extract_url(webpage)
  1572. if myvi_url:
  1573. return self.url_result(myvi_url)
  1574. # Look for embedded soundcloud player
  1575. mobj = re.search(
  1576. r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
  1577. webpage)
  1578. if mobj is not None:
  1579. url = unescapeHTML(mobj.group('url'))
  1580. return self.url_result(url)
  1581. # Look for embedded vulture.com player
  1582. mobj = re.search(
  1583. r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
  1584. webpage)
  1585. if mobj is not None:
  1586. url = unescapeHTML(mobj.group('url'))
  1587. return self.url_result(url, ie='Vulture')
  1588. # Look for embedded mtvservices player
  1589. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  1590. if mtvservices_url:
  1591. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  1592. # Look for embedded yahoo player
  1593. mobj = re.search(
  1594. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  1595. webpage)
  1596. if mobj is not None:
  1597. return self.url_result(mobj.group('url'), 'Yahoo')
  1598. # Look for embedded sbs.com.au player
  1599. mobj = re.search(
  1600. r'''(?x)
  1601. (?:
  1602. <meta\s+property="og:video"\s+content=|
  1603. <iframe[^>]+?src=
  1604. )
  1605. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  1606. webpage)
  1607. if mobj is not None:
  1608. return self.url_result(mobj.group('url'), 'SBS')
  1609. # Look for embedded Cinchcast player
  1610. mobj = re.search(
  1611. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  1612. webpage)
  1613. if mobj is not None:
  1614. return self.url_result(mobj.group('url'), 'Cinchcast')
  1615. mobj = re.search(
  1616. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  1617. webpage)
  1618. if not mobj:
  1619. mobj = re.search(
  1620. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  1621. webpage)
  1622. if mobj is not None:
  1623. return self.url_result(mobj.group('url'), 'MLB')
  1624. mobj = re.search(
  1625. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  1626. webpage)
  1627. if mobj is not None:
  1628. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  1629. mobj = re.search(
  1630. r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
  1631. webpage)
  1632. if mobj is not None:
  1633. return self.url_result(mobj.group('url'), 'Livestream')
  1634. # Look for Zapiks embed
  1635. mobj = re.search(
  1636. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  1637. if mobj is not None:
  1638. return self.url_result(mobj.group('url'), 'Zapiks')
  1639. # Look for Kaltura embeds
  1640. mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
  1641. 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))
  1642. if mobj is not None:
  1643. return self.url_result(smuggle_url(
  1644. 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
  1645. {'source_url': url}), 'Kaltura')
  1646. # Look for Eagle.Platform embeds
  1647. mobj = re.search(
  1648. r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
  1649. if mobj is not None:
  1650. return self.url_result(mobj.group('url'), 'EaglePlatform')
  1651. # Look for ClipYou (uses Eagle.Platform) embeds
  1652. mobj = re.search(
  1653. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  1654. if mobj is not None:
  1655. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  1656. # Look for Pladform embeds
  1657. pladform_url = PladformIE._extract_url(webpage)
  1658. if pladform_url:
  1659. return self.url_result(pladform_url)
  1660. # Look for Videomore embeds
  1661. videomore_url = VideomoreIE._extract_url(webpage)
  1662. if videomore_url:
  1663. return self.url_result(videomore_url)
  1664. # Look for Playwire embeds
  1665. mobj = re.search(
  1666. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  1667. if mobj is not None:
  1668. return self.url_result(mobj.group('url'))
  1669. # Look for 5min embeds
  1670. mobj = re.search(
  1671. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  1672. if mobj is not None:
  1673. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  1674. # Look for Crooks and Liars embeds
  1675. mobj = re.search(
  1676. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  1677. if mobj is not None:
  1678. return self.url_result(mobj.group('url'))
  1679. # Look for NBC Sports VPlayer embeds
  1680. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  1681. if nbc_sports_url:
  1682. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  1683. # Look for Google Drive embeds
  1684. google_drive_url = GoogleDriveIE._extract_url(webpage)
  1685. if google_drive_url:
  1686. return self.url_result(google_drive_url, 'GoogleDrive')
  1687. # Look for UDN embeds
  1688. mobj = re.search(
  1689. r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  1690. if mobj is not None:
  1691. return self.url_result(
  1692. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  1693. # Look for Senate ISVP iframe
  1694. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  1695. if senate_isvp_url:
  1696. return self.url_result(senate_isvp_url, 'SenateISVP')
  1697. # Look for Dailymotion Cloud videos
  1698. dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
  1699. if dmcloud_url:
  1700. return self.url_result(dmcloud_url, 'DailymotionCloud')
  1701. # Look for OnionStudios embeds
  1702. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  1703. if onionstudios_url:
  1704. return self.url_result(onionstudios_url)
  1705. # Look for SnagFilms embeds
  1706. snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
  1707. if snagfilms_url:
  1708. return self.url_result(snagfilms_url)
  1709. # Look for JWPlatform embeds
  1710. jwplatform_url = JWPlatformIE._extract_url(webpage)
  1711. if jwplatform_url:
  1712. return self.url_result(jwplatform_url, 'JWPlatform')
  1713. # Look for ScreenwaveMedia embeds
  1714. mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
  1715. if mobj is not None:
  1716. return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
  1717. # Look for Digiteka embeds
  1718. digiteka_url = DigitekaIE._extract_url(webpage)
  1719. if digiteka_url:
  1720. return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
  1721. # Look for Limelight embeds
  1722. mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
  1723. if mobj:
  1724. lm = {
  1725. 'Media': 'media',
  1726. 'Channel': 'channel',
  1727. 'ChannelList': 'channel_list',
  1728. }
  1729. return self.url_result('limelight:%s:%s' % (
  1730. lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
  1731. # Look for AdobeTVVideo embeds
  1732. mobj = re.search(
  1733. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  1734. webpage)
  1735. if mobj is not None:
  1736. return self.url_result(
  1737. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  1738. 'AdobeTVVideo')
  1739. def check_video(vurl):
  1740. if YoutubeIE.suitable(vurl):
  1741. return True
  1742. vpath = compat_urlparse.urlparse(vurl).path
  1743. vext = determine_ext(vpath)
  1744. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
  1745. def filter_video(urls):
  1746. return list(filter(check_video, urls))
  1747. # Start with something easy: JW Player in SWFObject
  1748. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  1749. if not found:
  1750. # Look for gorilla-vid style embedding
  1751. found = filter_video(re.findall(r'''(?sx)
  1752. (?:
  1753. jw_plugins|
  1754. JWPlayerOptions|
  1755. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  1756. )
  1757. .*?
  1758. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  1759. if not found:
  1760. # Broaden the search a little bit
  1761. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  1762. if not found:
  1763. # Broaden the findall a little bit: JWPlayer JS loader
  1764. found = filter_video(re.findall(
  1765. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  1766. if not found:
  1767. # Flow player
  1768. found = filter_video(re.findall(r'''(?xs)
  1769. flowplayer\("[^"]+",\s*
  1770. \{[^}]+?\}\s*,
  1771. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  1772. ["']?url["']?\s*:\s*["']([^"']+)["']
  1773. ''', webpage))
  1774. if not found:
  1775. # Cinerama player
  1776. found = re.findall(
  1777. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  1778. if not found:
  1779. # Try to find twitter cards info
  1780. found = filter_video(re.findall(
  1781. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  1782. if not found:
  1783. # We look for Open Graph info:
  1784. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  1785. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  1786. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  1787. if m_video_type is not None:
  1788. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  1789. if not found:
  1790. # HTML5 video
  1791. found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
  1792. if not found:
  1793. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  1794. found = re.search(
  1795. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  1796. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  1797. webpage)
  1798. if not found:
  1799. # Look also in Refresh HTTP header
  1800. refresh_header = head_response.headers.get('Refresh')
  1801. if refresh_header:
  1802. # In python 2 response HTTP headers are bytestrings
  1803. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  1804. refresh_header = refresh_header.decode('iso-8859-1')
  1805. found = re.search(REDIRECT_REGEX, refresh_header)
  1806. if found:
  1807. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  1808. self.report_following_redirect(new_url)
  1809. return {
  1810. '_type': 'url',
  1811. 'url': new_url,
  1812. }
  1813. if not found:
  1814. raise UnsupportedError(url)
  1815. entries = []
  1816. for video_url in found:
  1817. video_url = video_url.replace('\\/', '/')
  1818. video_url = compat_urlparse.urljoin(url, video_url)
  1819. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  1820. # Sometimes, jwplayer extraction will result in a YouTube URL
  1821. if YoutubeIE.suitable(video_url):
  1822. entries.append(self.url_result(video_url, 'Youtube'))
  1823. continue
  1824. # here's a fun little line of code for you:
  1825. video_id = os.path.splitext(video_id)[0]
  1826. entry_info_dict = {
  1827. 'id': video_id,
  1828. 'uploader': video_uploader,
  1829. 'title': video_title,
  1830. 'age_limit': age_limit,
  1831. }
  1832. ext = determine_ext(video_url)
  1833. if ext == 'smil':
  1834. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  1835. elif ext == 'xspf':
  1836. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  1837. elif ext == 'm3u8':
  1838. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  1839. elif ext == 'mpd':
  1840. entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
  1841. else:
  1842. entry_info_dict['url'] = video_url
  1843. entries.append(entry_info_dict)
  1844. if len(entries) == 1:
  1845. return entries[0]
  1846. else:
  1847. for num, e in enumerate(entries, start=1):
  1848. # 'url' results don't have a title
  1849. if e.get('title') is not None:
  1850. e['title'] = '%s (%d)' % (e['title'], num)
  1851. return {
  1852. '_type': 'playlist',
  1853. 'entries': entries,
  1854. }