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.

1941 lines
78 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 .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 .googledrive import GoogleDriveIE
  55. from .jwplatform import JWPlatformIE
  56. class GenericIE(InfoExtractor):
  57. IE_DESC = 'Generic downloader that works on some sites'
  58. _VALID_URL = r'.*'
  59. IE_NAME = 'generic'
  60. _TESTS = [
  61. # Direct link to a video
  62. {
  63. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  64. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  65. 'info_dict': {
  66. 'id': 'trailer',
  67. 'ext': 'mp4',
  68. 'title': 'trailer',
  69. 'upload_date': '20100513',
  70. }
  71. },
  72. # Direct link to media delivered compressed (until Accept-Encoding is *)
  73. {
  74. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  75. 'md5': '128c42e68b13950268b648275386fc74',
  76. 'info_dict': {
  77. 'id': 'FictionJunction-Parallel_Hearts',
  78. 'ext': 'flac',
  79. 'title': 'FictionJunction-Parallel_Hearts',
  80. 'upload_date': '20140522',
  81. },
  82. 'expected_warnings': [
  83. 'URL could be a direct video link, returning it as such.'
  84. ]
  85. },
  86. # Direct download with broken HEAD
  87. {
  88. 'url': 'http://ai-radio.org:8000/radio.opus',
  89. 'info_dict': {
  90. 'id': 'radio',
  91. 'ext': 'opus',
  92. 'title': 'radio',
  93. },
  94. 'params': {
  95. 'skip_download': True, # infinite live stream
  96. },
  97. 'expected_warnings': [
  98. r'501.*Not Implemented'
  99. ],
  100. },
  101. # Direct link with incorrect MIME type
  102. {
  103. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  104. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  105. 'info_dict': {
  106. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  107. 'id': '5_Lennart_Poettering_-_Systemd',
  108. 'ext': 'webm',
  109. 'title': '5_Lennart_Poettering_-_Systemd',
  110. 'upload_date': '20141120',
  111. },
  112. 'expected_warnings': [
  113. 'URL could be a direct video link, returning it as such.'
  114. ]
  115. },
  116. # RSS feed
  117. {
  118. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  119. 'info_dict': {
  120. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  121. 'title': 'Zero Punctuation',
  122. 'description': 're:.*groundbreaking video review series.*'
  123. },
  124. 'playlist_mincount': 11,
  125. },
  126. # RSS feed with enclosure
  127. {
  128. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  129. 'info_dict': {
  130. 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  131. 'ext': 'm4v',
  132. 'upload_date': '20150228',
  133. 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  134. }
  135. },
  136. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  137. {
  138. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  139. 'info_dict': {
  140. 'id': 'smil',
  141. 'ext': 'mp4',
  142. 'title': 'Automatics, robotics and biocybernetics',
  143. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  144. 'upload_date': '20130627',
  145. 'formats': 'mincount:16',
  146. 'subtitles': 'mincount:1',
  147. },
  148. 'params': {
  149. 'force_generic_extractor': True,
  150. 'skip_download': True,
  151. },
  152. },
  153. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  154. {
  155. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  156. 'info_dict': {
  157. 'id': 'hds',
  158. 'ext': 'flv',
  159. 'title': 'hds',
  160. 'formats': 'mincount:1',
  161. },
  162. 'params': {
  163. 'skip_download': True,
  164. },
  165. },
  166. # SMIL from https://www.restudy.dk/video/play/id/1637
  167. {
  168. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  169. 'info_dict': {
  170. 'id': 'video_1637',
  171. 'ext': 'flv',
  172. 'title': 'video_1637',
  173. 'formats': 'mincount:3',
  174. },
  175. 'params': {
  176. 'skip_download': True,
  177. },
  178. },
  179. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  180. {
  181. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  182. 'info_dict': {
  183. 'id': 'smil-service',
  184. 'ext': 'flv',
  185. 'title': 'smil-service',
  186. 'formats': 'mincount:1',
  187. },
  188. 'params': {
  189. 'skip_download': True,
  190. },
  191. },
  192. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  193. {
  194. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  195. 'info_dict': {
  196. 'id': '4719370',
  197. 'ext': 'mp4',
  198. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  199. 'formats': 'mincount:3',
  200. },
  201. 'params': {
  202. 'skip_download': True,
  203. },
  204. },
  205. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  206. {
  207. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  208. 'info_dict': {
  209. 'id': 'mZlp2ctYIUEB',
  210. 'ext': 'mp4',
  211. 'title': 'Tikibad ontruimd wegens brand',
  212. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  213. 'thumbnail': 're:^https?://.*\.jpg$',
  214. 'duration': 33,
  215. },
  216. 'params': {
  217. 'skip_download': True,
  218. },
  219. },
  220. # google redirect
  221. {
  222. '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',
  223. 'info_dict': {
  224. 'id': 'cmQHVoWB5FY',
  225. 'ext': 'mp4',
  226. 'upload_date': '20130224',
  227. 'uploader_id': 'TheVerge',
  228. 'description': 're:^Chris Ziegler takes a look at the\.*',
  229. 'uploader': 'The Verge',
  230. 'title': 'First Firefox OS phones side-by-side',
  231. },
  232. 'params': {
  233. 'skip_download': False,
  234. }
  235. },
  236. {
  237. # redirect in Refresh HTTP header
  238. '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',
  239. 'info_dict': {
  240. 'id': 'pO8h3EaFRdo',
  241. 'ext': 'mp4',
  242. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  243. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  244. 'upload_date': '20150917',
  245. 'uploader_id': 'brtvofficial',
  246. 'uploader': 'Boiler Room',
  247. },
  248. 'params': {
  249. 'skip_download': False,
  250. },
  251. },
  252. {
  253. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  254. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  255. 'info_dict': {
  256. 'id': '13601338388002',
  257. 'ext': 'mp4',
  258. 'uploader': 'www.hodiho.fr',
  259. 'title': 'R\u00e9gis plante sa Jeep',
  260. }
  261. },
  262. # bandcamp page with custom domain
  263. {
  264. 'add_ie': ['Bandcamp'],
  265. 'url': 'http://bronyrock.com/track/the-pony-mash',
  266. 'info_dict': {
  267. 'id': '3235767654',
  268. 'ext': 'mp3',
  269. 'title': 'The Pony Mash',
  270. 'uploader': 'M_Pallante',
  271. },
  272. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  273. },
  274. # embedded brightcove video
  275. # it also tests brightcove videos that need to set the 'Referer' in the
  276. # http requests
  277. {
  278. 'add_ie': ['BrightcoveLegacy'],
  279. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  280. 'info_dict': {
  281. 'id': '2765128793001',
  282. 'ext': 'mp4',
  283. 'title': 'Le cours de bourse : l’analyse technique',
  284. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  285. 'uploader': 'BFM BUSINESS',
  286. },
  287. 'params': {
  288. 'skip_download': True,
  289. },
  290. },
  291. {
  292. # https://github.com/rg3/youtube-dl/issues/2253
  293. 'url': 'http://bcove.me/i6nfkrc3',
  294. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  295. 'info_dict': {
  296. 'id': '3101154703001',
  297. 'ext': 'mp4',
  298. 'title': 'Still no power',
  299. 'uploader': 'thestar.com',
  300. '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.',
  301. },
  302. 'add_ie': ['BrightcoveLegacy'],
  303. },
  304. {
  305. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  306. 'md5': 'fb973ecf6e4a78a67453647444222983',
  307. 'info_dict': {
  308. 'id': '3414141473001',
  309. 'ext': 'mp4',
  310. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  311. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  312. 'uploader': 'Championat',
  313. },
  314. },
  315. {
  316. # https://github.com/rg3/youtube-dl/issues/3541
  317. 'add_ie': ['BrightcoveLegacy'],
  318. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  319. 'info_dict': {
  320. 'id': '3866516442001',
  321. 'ext': 'mp4',
  322. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  323. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  324. 'uploader': 'SBS Broadcasting',
  325. },
  326. 'skip': 'Restricted to Netherlands',
  327. 'params': {
  328. 'skip_download': True, # m3u8 download
  329. },
  330. },
  331. # ooyala video
  332. {
  333. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  334. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  335. 'info_dict': {
  336. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  337. 'ext': 'mp4',
  338. 'title': '2cc213299525360.mov', # that's what we get
  339. 'duration': 238.231,
  340. },
  341. 'add_ie': ['Ooyala'],
  342. },
  343. {
  344. # ooyala video embedded with http://player.ooyala.com/iframe.js
  345. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  346. 'info_dict': {
  347. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  348. 'ext': 'mp4',
  349. 'title': '"Steve Jobs: Man in the Machine" trailer',
  350. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  351. 'duration': 135.427,
  352. },
  353. 'params': {
  354. 'skip_download': True,
  355. },
  356. },
  357. # multiple ooyala embeds on SBN network websites
  358. {
  359. 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
  360. 'info_dict': {
  361. 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
  362. 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
  363. },
  364. 'playlist_mincount': 3,
  365. 'params': {
  366. 'skip_download': True,
  367. },
  368. 'add_ie': ['Ooyala'],
  369. },
  370. # embed.ly video
  371. {
  372. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  373. 'info_dict': {
  374. 'id': '9ODmcdjQcHQ',
  375. 'ext': 'mp4',
  376. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  377. 'upload_date': '20140225',
  378. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  379. 'uploader': 'Tested',
  380. 'uploader_id': 'testedcom',
  381. },
  382. # No need to test YoutubeIE here
  383. 'params': {
  384. 'skip_download': True,
  385. },
  386. },
  387. # funnyordie embed
  388. {
  389. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  390. 'info_dict': {
  391. 'id': '18e820ec3f',
  392. 'ext': 'mp4',
  393. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  394. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  395. },
  396. },
  397. # RUTV embed
  398. {
  399. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  400. 'info_dict': {
  401. 'id': '776940',
  402. 'ext': 'mp4',
  403. 'title': 'Охотское море стало целиком российским',
  404. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  405. },
  406. 'params': {
  407. # m3u8 download
  408. 'skip_download': True,
  409. },
  410. },
  411. # TVC embed
  412. {
  413. '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/',
  414. 'info_dict': {
  415. 'id': '55304',
  416. 'ext': 'mp4',
  417. 'title': 'Дошкольное воспитание',
  418. },
  419. },
  420. # SportBox embed
  421. {
  422. 'url': 'http://www.vestifinance.ru/articles/25753',
  423. 'info_dict': {
  424. 'id': '25753',
  425. 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  426. },
  427. 'playlist': [{
  428. 'info_dict': {
  429. 'id': '370908',
  430. 'title': 'Госзаказ. День 3',
  431. 'ext': 'mp4',
  432. }
  433. }, {
  434. 'info_dict': {
  435. 'id': '370905',
  436. 'title': 'Госзаказ. День 2',
  437. 'ext': 'mp4',
  438. }
  439. }, {
  440. 'info_dict': {
  441. 'id': '370902',
  442. 'title': 'Госзаказ. День 1',
  443. 'ext': 'mp4',
  444. }
  445. }],
  446. 'params': {
  447. # m3u8 download
  448. 'skip_download': True,
  449. },
  450. },
  451. # Myvi.ru embed
  452. {
  453. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  454. 'info_dict': {
  455. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  456. 'ext': 'mp4',
  457. 'title': 'Ужастики, русский трейлер (2015)',
  458. 'thumbnail': 're:^https?://.*\.jpg$',
  459. 'duration': 153,
  460. }
  461. },
  462. # XHamster embed
  463. {
  464. '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',
  465. 'info_dict': {
  466. 'id': 'showthread',
  467. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  468. },
  469. 'playlist_mincount': 7,
  470. },
  471. # Embedded TED video
  472. {
  473. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  474. 'md5': '65fdff94098e4a607385a60c5177c638',
  475. 'info_dict': {
  476. 'id': '1969',
  477. 'ext': 'mp4',
  478. 'title': 'Hidden miracles of the natural world',
  479. 'uploader': 'Louie Schwartzberg',
  480. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  481. }
  482. },
  483. # Embeded Ustream video
  484. {
  485. 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
  486. 'md5': '27b99cdb639c9b12a79bca876a073417',
  487. 'info_dict': {
  488. 'id': '45734260',
  489. 'ext': 'flv',
  490. 'uploader': 'AU SPA: The NSA and Privacy',
  491. 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
  492. }
  493. },
  494. # nowvideo embed hidden behind percent encoding
  495. {
  496. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  497. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  498. 'info_dict': {
  499. 'id': '06e53103ca9aa',
  500. 'ext': 'flv',
  501. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  502. 'description': 'No description',
  503. },
  504. },
  505. # arte embed
  506. {
  507. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  508. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  509. 'info_dict': {
  510. 'id': '048195-004_PLUS7-F',
  511. 'ext': 'flv',
  512. 'title': 'X:enius',
  513. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  514. 'upload_date': '20140320',
  515. },
  516. 'params': {
  517. 'skip_download': 'Requires rtmpdump'
  518. }
  519. },
  520. # francetv embed
  521. {
  522. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  523. 'info_dict': {
  524. 'id': 'EV_30231',
  525. 'ext': 'mp4',
  526. 'title': 'Alcaline, le concert avec Calogero',
  527. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  528. 'upload_date': '20150226',
  529. 'timestamp': 1424989860,
  530. 'duration': 5400,
  531. },
  532. 'params': {
  533. # m3u8 downloads
  534. 'skip_download': True,
  535. },
  536. 'expected_warnings': [
  537. 'Forbidden'
  538. ]
  539. },
  540. # Condé Nast embed
  541. {
  542. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  543. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  544. 'info_dict': {
  545. 'id': '53501be369702d3275860000',
  546. 'ext': 'mp4',
  547. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  548. }
  549. },
  550. # Dailymotion embed
  551. {
  552. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  553. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  554. 'info_dict': {
  555. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  556. 'ext': 'mp4',
  557. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  558. 'uploader': 'Spi0n',
  559. },
  560. 'add_ie': ['Dailymotion'],
  561. },
  562. # YouTube embed
  563. {
  564. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  565. 'info_dict': {
  566. 'id': 'FXRb4ykk4S0',
  567. 'ext': 'mp4',
  568. 'title': 'The NBL Auction 2014',
  569. 'uploader': 'BADMINTON England',
  570. 'uploader_id': 'BADMINTONEvents',
  571. 'upload_date': '20140603',
  572. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  573. },
  574. 'add_ie': ['Youtube'],
  575. 'params': {
  576. 'skip_download': True,
  577. }
  578. },
  579. # MTVSercices embed
  580. {
  581. 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
  582. 'md5': '35727f82f58c76d996fc188f9755b0d5',
  583. 'info_dict': {
  584. 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
  585. 'ext': 'mp4',
  586. 'title': 'Review',
  587. 'description': 'Mario\'s life in the fast lane has never looked so good.',
  588. },
  589. },
  590. # YouTube embed via <data-embed-url="">
  591. {
  592. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  593. 'info_dict': {
  594. 'id': '4vAffPZIT44',
  595. 'ext': 'mp4',
  596. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  597. 'uploader': 'Gameloft',
  598. 'uploader_id': 'gameloft',
  599. 'upload_date': '20140828',
  600. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  601. },
  602. 'params': {
  603. 'skip_download': True,
  604. }
  605. },
  606. # Camtasia studio
  607. {
  608. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  609. 'playlist': [{
  610. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  611. 'info_dict': {
  612. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  613. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  614. 'ext': 'flv',
  615. 'duration': 2235.90,
  616. }
  617. }, {
  618. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  619. 'info_dict': {
  620. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  621. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  622. 'ext': 'flv',
  623. 'duration': 2235.93,
  624. }
  625. }],
  626. 'info_dict': {
  627. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  628. }
  629. },
  630. # Flowplayer
  631. {
  632. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  633. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  634. 'info_dict': {
  635. 'id': '5123ea6d5e5a7',
  636. 'ext': 'mp4',
  637. 'age_limit': 18,
  638. 'uploader': 'www.handjobhub.com',
  639. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  640. }
  641. },
  642. # Multiple brightcove videos
  643. # https://github.com/rg3/youtube-dl/issues/2283
  644. {
  645. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  646. 'info_dict': {
  647. 'id': 'always-never',
  648. 'title': 'Always / Never - The New Yorker',
  649. },
  650. 'playlist_count': 3,
  651. 'params': {
  652. 'extract_flat': False,
  653. 'skip_download': True,
  654. }
  655. },
  656. # MLB embed
  657. {
  658. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  659. 'md5': '96f09a37e44da40dd083e12d9a683327',
  660. 'info_dict': {
  661. 'id': '33322633',
  662. 'ext': 'mp4',
  663. 'title': 'Ump changes call to ball',
  664. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  665. 'duration': 48,
  666. 'timestamp': 1401537900,
  667. 'upload_date': '20140531',
  668. 'thumbnail': 're:^https?://.*\.jpg$',
  669. },
  670. },
  671. # Wistia embed
  672. {
  673. 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  674. 'md5': '8788b683c777a5cf25621eaf286d0c23',
  675. 'info_dict': {
  676. 'id': '1cfaf6b7ea',
  677. 'ext': 'mov',
  678. 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
  679. 'duration': 643.0,
  680. 'filesize': 182808282,
  681. 'uploader': 'education-portal.com',
  682. },
  683. },
  684. {
  685. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  686. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  687. 'info_dict': {
  688. 'id': 'uxjb0lwrcz',
  689. 'ext': 'mp4',
  690. 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
  691. 'duration': 1715.0,
  692. 'uploader': 'thoughtworks.wistia.com',
  693. },
  694. },
  695. # Soundcloud embed
  696. {
  697. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  698. 'info_dict': {
  699. 'id': '174391317',
  700. 'ext': 'mp3',
  701. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  702. 'uploader': 'Sophos Security',
  703. 'title': 'Chet Chat 171 - Oct 29, 2014',
  704. 'upload_date': '20141029',
  705. }
  706. },
  707. # Livestream embed
  708. {
  709. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  710. 'info_dict': {
  711. 'id': '67864563',
  712. 'ext': 'flv',
  713. 'upload_date': '20141112',
  714. 'title': 'Rosetta #CometLanding webcast HL 10',
  715. }
  716. },
  717. # LazyYT
  718. {
  719. 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
  720. 'info_dict': {
  721. 'id': '1986',
  722. 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
  723. },
  724. 'playlist_mincount': 2,
  725. },
  726. # Cinchcast embed
  727. {
  728. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  729. 'info_dict': {
  730. 'id': '7141703',
  731. 'ext': 'mp3',
  732. 'upload_date': '20141126',
  733. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  734. }
  735. },
  736. # Cinerama player
  737. {
  738. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  739. 'info_dict': {
  740. 'id': '730m_DandD_1901_512k',
  741. 'ext': 'mp4',
  742. 'uploader': 'www.abc.net.au',
  743. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  744. }
  745. },
  746. # embedded viddler video
  747. {
  748. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  749. 'info_dict': {
  750. 'id': '4d03aad9',
  751. 'ext': 'mp4',
  752. 'uploader': 'deadspin',
  753. 'title': 'WALL-TO-GORTAT',
  754. 'timestamp': 1422285291,
  755. 'upload_date': '20150126',
  756. },
  757. 'add_ie': ['Viddler'],
  758. },
  759. # Libsyn embed
  760. {
  761. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  762. 'info_dict': {
  763. 'id': '3377616',
  764. 'ext': 'mp3',
  765. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  766. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  767. 'upload_date': '20150220',
  768. },
  769. },
  770. # jwplayer YouTube
  771. {
  772. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  773. 'info_dict': {
  774. 'id': 'Mrj4DVp2zeA',
  775. 'ext': 'mp4',
  776. 'upload_date': '20150212',
  777. 'uploader': 'The National Archives UK',
  778. 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
  779. 'uploader_id': 'NationalArchives08',
  780. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  781. },
  782. },
  783. # rtl.nl embed
  784. {
  785. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  786. 'playlist_mincount': 5,
  787. 'info_dict': {
  788. 'id': 'aanslagen-kopenhagen',
  789. 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
  790. }
  791. },
  792. # Zapiks embed
  793. {
  794. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  795. 'info_dict': {
  796. 'id': '118046',
  797. 'ext': 'mp4',
  798. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  799. }
  800. },
  801. # Kaltura embed
  802. {
  803. 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
  804. 'info_dict': {
  805. 'id': '1_eergr3h1',
  806. 'ext': 'mp4',
  807. 'upload_date': '20150226',
  808. 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
  809. 'timestamp': int,
  810. 'title': 'John Carlson Postgame 2/25/15',
  811. },
  812. },
  813. # Kaltura embed (different embed code)
  814. {
  815. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  816. 'info_dict': {
  817. 'id': '1_a52wc67y',
  818. 'ext': 'flv',
  819. 'upload_date': '20150127',
  820. 'uploader_id': 'PremierMedia',
  821. 'timestamp': int,
  822. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  823. },
  824. },
  825. # Kaltura embed protected with referrer
  826. {
  827. 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
  828. 'info_dict': {
  829. 'id': '1_g4fbemnq',
  830. 'ext': 'mp4',
  831. 'title': 'Violetta - Achter De Schermen - Ruggero',
  832. 'description': 'Achter de schermen met Ruggero',
  833. 'timestamp': 1435133761,
  834. 'upload_date': '20150624',
  835. 'uploader_id': 'echojecka',
  836. },
  837. },
  838. # Eagle.Platform embed (generic URL)
  839. {
  840. 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
  841. 'info_dict': {
  842. 'id': '227304',
  843. 'ext': 'mp4',
  844. 'title': 'Навальный вышел на свободу',
  845. 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
  846. 'thumbnail': 're:^https?://.*\.jpg$',
  847. 'duration': 87,
  848. 'view_count': int,
  849. 'age_limit': 0,
  850. },
  851. },
  852. # ClipYou (Eagle.Platform) embed (custom URL)
  853. {
  854. 'url': 'http://muz-tv.ru/play/7129/',
  855. 'info_dict': {
  856. 'id': '12820',
  857. 'ext': 'mp4',
  858. 'title': "'O Sole Mio",
  859. 'thumbnail': 're:^https?://.*\.jpg$',
  860. 'duration': 216,
  861. 'view_count': int,
  862. },
  863. },
  864. # Pladform embed
  865. {
  866. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  867. 'info_dict': {
  868. 'id': '100183293',
  869. 'ext': 'mp4',
  870. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  871. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  872. 'thumbnail': 're:^https?://.*\.jpg$',
  873. 'duration': 694,
  874. 'age_limit': 0,
  875. },
  876. },
  877. # Playwire embed
  878. {
  879. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  880. 'info_dict': {
  881. 'id': '3519514',
  882. 'ext': 'mp4',
  883. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  884. 'thumbnail': 're:^https?://.*\.png$',
  885. 'duration': 45.115,
  886. },
  887. },
  888. # 5min embed
  889. {
  890. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  891. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  892. 'info_dict': {
  893. 'id': '518726732',
  894. 'ext': 'mp4',
  895. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  896. },
  897. },
  898. # SVT embed
  899. {
  900. 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
  901. 'info_dict': {
  902. 'id': '2900353',
  903. 'ext': 'flv',
  904. 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
  905. 'duration': 27,
  906. 'age_limit': 0,
  907. },
  908. },
  909. # Crooks and Liars embed
  910. {
  911. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  912. 'info_dict': {
  913. 'id': '8RUoRhRi',
  914. 'ext': 'mp4',
  915. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  916. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  917. 'timestamp': 1428207000,
  918. 'upload_date': '20150405',
  919. 'uploader': 'Heather',
  920. },
  921. },
  922. # Crooks and Liars external embed
  923. {
  924. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  925. 'info_dict': {
  926. 'id': 'MTE3MjUtMzQ2MzA',
  927. 'ext': 'mp4',
  928. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  929. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  930. 'timestamp': 1265032391,
  931. 'upload_date': '20100201',
  932. 'uploader': 'Heather',
  933. },
  934. },
  935. # NBC Sports vplayer embed
  936. {
  937. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  938. 'info_dict': {
  939. 'id': 'ln7x1qSThw4k',
  940. 'ext': 'flv',
  941. 'title': "PFT Live: New leader in the 'new-look' defense",
  942. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  943. },
  944. },
  945. # UDN embed
  946. {
  947. 'url': 'http://www.udn.com/news/story/7314/822787',
  948. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  949. 'info_dict': {
  950. 'id': '300346',
  951. 'ext': 'mp4',
  952. 'title': '中一中男師變性 全校師生力挺',
  953. 'thumbnail': 're:^https?://.*\.jpg$',
  954. }
  955. },
  956. # Ooyala embed
  957. {
  958. 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
  959. 'info_dict': {
  960. 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
  961. 'ext': 'mp4',
  962. 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
  963. 'title': 'This is what separates the Excel masters from the wannabes',
  964. 'duration': 191.933,
  965. },
  966. 'params': {
  967. # m3u8 downloads
  968. 'skip_download': True,
  969. }
  970. },
  971. # Contains a SMIL manifest
  972. {
  973. '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',
  974. 'info_dict': {
  975. 'id': 'file',
  976. 'ext': 'flv',
  977. 'title': '+ Football: Lottery Champions League Europe',
  978. 'uploader': 'www.telewebion.com',
  979. },
  980. 'params': {
  981. # rtmpe downloads
  982. 'skip_download': True,
  983. }
  984. },
  985. # Brightcove URL in single quotes
  986. {
  987. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  988. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  989. 'info_dict': {
  990. 'id': '4255764656001',
  991. 'ext': 'mp4',
  992. 'title': 'SN Presents: Russell Martin, World Citizen',
  993. '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.',
  994. 'uploader': 'Rogers Sportsnet',
  995. },
  996. },
  997. # Dailymotion Cloud video
  998. {
  999. 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
  1000. 'md5': '49444254273501a64675a7e68c502681',
  1001. 'info_dict': {
  1002. 'id': '5585de919473990de4bee11b',
  1003. 'ext': 'mp4',
  1004. 'title': 'Le débat',
  1005. 'thumbnail': 're:^https?://.*\.jpe?g$',
  1006. }
  1007. },
  1008. # OnionStudios embed
  1009. {
  1010. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1011. 'info_dict': {
  1012. 'id': '2855',
  1013. 'ext': 'mp4',
  1014. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1015. 'thumbnail': 're:^https?://.*\.jpe?g$',
  1016. 'uploader': 'ClickHole',
  1017. 'uploader_id': 'clickhole',
  1018. }
  1019. },
  1020. # SnagFilms embed
  1021. {
  1022. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1023. 'info_dict': {
  1024. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1025. 'ext': 'mp4',
  1026. 'title': '#whilewewatch',
  1027. }
  1028. },
  1029. # AdobeTVVideo embed
  1030. {
  1031. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1032. 'md5': '43662b577c018ad707a63766462b1e87',
  1033. 'info_dict': {
  1034. 'id': '2456',
  1035. 'ext': 'mp4',
  1036. 'title': 'New experience with Acrobat DC',
  1037. 'description': 'New experience with Acrobat DC',
  1038. 'duration': 248.667,
  1039. },
  1040. },
  1041. # ScreenwaveMedia embed
  1042. {
  1043. 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
  1044. 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
  1045. 'info_dict': {
  1046. 'id': 'cinemasnob-55d26273809dd',
  1047. 'ext': 'mp4',
  1048. 'title': 'cinemasnob',
  1049. },
  1050. },
  1051. # BrightcoveInPageEmbed embed
  1052. {
  1053. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1054. 'info_dict': {
  1055. 'id': '4238694884001',
  1056. 'ext': 'flv',
  1057. 'title': 'Tabletop: Dread, Last Thoughts',
  1058. 'description': 'Tabletop: Dread, Last Thoughts',
  1059. 'duration': 51690,
  1060. },
  1061. },
  1062. # JWPlayer with M3U8
  1063. {
  1064. 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
  1065. 'info_dict': {
  1066. 'id': 'playlist',
  1067. 'ext': 'mp4',
  1068. 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
  1069. 'uploader': 'ren.tv',
  1070. },
  1071. 'params': {
  1072. # m3u8 downloads
  1073. 'skip_download': True,
  1074. }
  1075. }
  1076. ]
  1077. def report_following_redirect(self, new_url):
  1078. """Report information extraction."""
  1079. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  1080. def _extract_rss(self, url, video_id, doc):
  1081. playlist_title = doc.find('./channel/title').text
  1082. playlist_desc_el = doc.find('./channel/description')
  1083. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  1084. entries = []
  1085. for it in doc.findall('./channel/item'):
  1086. next_url = xpath_text(it, 'link', fatal=False)
  1087. if not next_url:
  1088. enclosure_nodes = it.findall('./enclosure')
  1089. for e in enclosure_nodes:
  1090. next_url = e.attrib.get('url')
  1091. if next_url:
  1092. break
  1093. if not next_url:
  1094. continue
  1095. entries.append({
  1096. '_type': 'url',
  1097. 'url': next_url,
  1098. 'title': it.find('title').text,
  1099. })
  1100. return {
  1101. '_type': 'playlist',
  1102. 'id': url,
  1103. 'title': playlist_title,
  1104. 'description': playlist_desc,
  1105. 'entries': entries,
  1106. }
  1107. def _extract_camtasia(self, url, video_id, webpage):
  1108. """ Returns None if no camtasia video can be found. """
  1109. camtasia_cfg = self._search_regex(
  1110. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  1111. webpage, 'camtasia configuration file', default=None)
  1112. if camtasia_cfg is None:
  1113. return None
  1114. title = self._html_search_meta('DC.title', webpage, fatal=True)
  1115. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  1116. camtasia_cfg = self._download_xml(
  1117. camtasia_url, video_id,
  1118. note='Downloading camtasia configuration',
  1119. errnote='Failed to download camtasia configuration')
  1120. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  1121. entries = []
  1122. for n in fileset_node.getchildren():
  1123. url_n = n.find('./uri')
  1124. if url_n is None:
  1125. continue
  1126. entries.append({
  1127. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  1128. 'title': '%s - %s' % (title, n.tag),
  1129. 'url': compat_urlparse.urljoin(url, url_n.text),
  1130. 'duration': float_or_none(n.find('./duration').text),
  1131. })
  1132. return {
  1133. '_type': 'playlist',
  1134. 'entries': entries,
  1135. 'title': title,
  1136. }
  1137. def _real_extract(self, url):
  1138. if url.startswith('//'):
  1139. return {
  1140. '_type': 'url',
  1141. 'url': self.http_scheme() + url,
  1142. }
  1143. parsed_url = compat_urlparse.urlparse(url)
  1144. if not parsed_url.scheme:
  1145. default_search = self._downloader.params.get('default_search')
  1146. if default_search is None:
  1147. default_search = 'fixup_error'
  1148. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  1149. if '/' in url:
  1150. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  1151. return self.url_result('http://' + url)
  1152. elif default_search != 'fixup_error':
  1153. if default_search == 'auto_warning':
  1154. if re.match(r'^(?:url|URL)$', url):
  1155. raise ExtractorError(
  1156. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  1157. expected=True)
  1158. else:
  1159. self._downloader.report_warning(
  1160. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  1161. return self.url_result('ytsearch:' + url)
  1162. if default_search in ('error', 'fixup_error'):
  1163. raise ExtractorError(
  1164. '%r is not a valid URL. '
  1165. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  1166. % (url, url), expected=True)
  1167. else:
  1168. if ':' not in default_search:
  1169. default_search += ':'
  1170. return self.url_result(default_search + url)
  1171. url, smuggled_data = unsmuggle_url(url)
  1172. force_videoid = None
  1173. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  1174. if smuggled_data and 'force_videoid' in smuggled_data:
  1175. force_videoid = smuggled_data['force_videoid']
  1176. video_id = force_videoid
  1177. else:
  1178. video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
  1179. self.to_screen('%s: Requesting header' % video_id)
  1180. head_req = HEADRequest(url)
  1181. head_response = self._request_webpage(
  1182. head_req, video_id,
  1183. note=False, errnote='Could not send HEAD request to %s' % url,
  1184. fatal=False)
  1185. if head_response is not False:
  1186. # Check for redirect
  1187. new_url = head_response.geturl()
  1188. if url != new_url:
  1189. self.report_following_redirect(new_url)
  1190. if force_videoid:
  1191. new_url = smuggle_url(
  1192. new_url, {'force_videoid': force_videoid})
  1193. return self.url_result(new_url)
  1194. full_response = None
  1195. if head_response is False:
  1196. request = sanitized_Request(url)
  1197. request.add_header('Accept-Encoding', '*')
  1198. full_response = self._request_webpage(request, video_id)
  1199. head_response = full_response
  1200. # Check for direct link to a video
  1201. content_type = head_response.headers.get('Content-Type', '')
  1202. m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
  1203. if m:
  1204. upload_date = unified_strdate(
  1205. head_response.headers.get('Last-Modified'))
  1206. return {
  1207. 'id': video_id,
  1208. 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
  1209. 'direct': True,
  1210. 'formats': [{
  1211. 'format_id': m.group('format_id'),
  1212. 'url': url,
  1213. 'vcodec': 'none' if m.group('type') == 'audio' else None
  1214. }],
  1215. 'upload_date': upload_date,
  1216. }
  1217. if not self._downloader.params.get('test', False) and not is_intentional:
  1218. force = self._downloader.params.get('force_generic_extractor', False)
  1219. self._downloader.report_warning(
  1220. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  1221. if not full_response:
  1222. request = sanitized_Request(url)
  1223. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  1224. # making it impossible to download only chunk of the file (yet we need only 512kB to
  1225. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  1226. # that will always result in downloading the whole file that is not desirable.
  1227. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  1228. # to accept raw bytes and being able to download only a chunk.
  1229. # It may probably better to solve this by checking Content-Type for application/octet-stream
  1230. # after HEAD request finishes, but not sure if we can rely on this.
  1231. request.add_header('Accept-Encoding', '*')
  1232. full_response = self._request_webpage(request, video_id)
  1233. # Maybe it's a direct link to a video?
  1234. # Be careful not to download the whole thing!
  1235. first_bytes = full_response.read(512)
  1236. if not is_html(first_bytes):
  1237. self._downloader.report_warning(
  1238. 'URL could be a direct video link, returning it as such.')
  1239. upload_date = unified_strdate(
  1240. head_response.headers.get('Last-Modified'))
  1241. return {
  1242. 'id': video_id,
  1243. 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
  1244. 'direct': True,
  1245. 'url': url,
  1246. 'upload_date': upload_date,
  1247. }
  1248. webpage = self._webpage_read_content(
  1249. full_response, url, video_id, prefix=first_bytes)
  1250. self.report_extraction(video_id)
  1251. # Is it an RSS feed, a SMIL file or a XSPF playlist?
  1252. try:
  1253. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  1254. if doc.tag == 'rss':
  1255. return self._extract_rss(url, video_id, doc)
  1256. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  1257. return self._parse_smil(doc, url, video_id)
  1258. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  1259. return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
  1260. except compat_xml_parse_error:
  1261. pass
  1262. # Is it a Camtasia project?
  1263. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  1264. if camtasia_res is not None:
  1265. return camtasia_res
  1266. # Sometimes embedded video player is hidden behind percent encoding
  1267. # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
  1268. # Unescaping the whole page allows to handle those cases in a generic way
  1269. webpage = compat_urllib_parse_unquote(webpage)
  1270. # it's tempting to parse this further, but you would
  1271. # have to take into account all the variations like
  1272. # Video Title - Site Name
  1273. # Site Name | Video Title
  1274. # Video Title - Tagline | Site Name
  1275. # and so on and so forth; it's just not practical
  1276. video_title = self._html_search_regex(
  1277. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  1278. default='video')
  1279. # Try to detect age limit automatically
  1280. age_limit = self._rta_search(webpage)
  1281. # And then there are the jokers who advertise that they use RTA,
  1282. # but actually don't.
  1283. AGE_LIMIT_MARKERS = [
  1284. r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
  1285. ]
  1286. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  1287. age_limit = 18
  1288. # video uploader is domain name
  1289. video_uploader = self._search_regex(
  1290. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  1291. # Helper method
  1292. def _playlist_from_matches(matches, getter=None, ie=None):
  1293. urlrs = orderedSet(
  1294. self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
  1295. for m in matches)
  1296. return self.playlist_result(
  1297. urlrs, playlist_id=video_id, playlist_title=video_title)
  1298. # Look for Brightcove Legacy Studio embeds
  1299. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  1300. if bc_urls:
  1301. self.to_screen('Brightcove video detected.')
  1302. entries = [{
  1303. '_type': 'url',
  1304. 'url': smuggle_url(bc_url, {'Referer': url}),
  1305. 'ie_key': 'BrightcoveLegacy'
  1306. } for bc_url in bc_urls]
  1307. return {
  1308. '_type': 'playlist',
  1309. 'title': video_title,
  1310. 'id': video_id,
  1311. 'entries': entries,
  1312. }
  1313. # Look for Brightcove New Studio embeds
  1314. bc_urls = BrightcoveNewIE._extract_urls(webpage)
  1315. if bc_urls:
  1316. return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
  1317. # Look for embedded rtl.nl player
  1318. matches = re.findall(
  1319. r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
  1320. webpage)
  1321. if matches:
  1322. return _playlist_from_matches(matches, ie='RtlNl')
  1323. vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
  1324. if vimeo_url is not None:
  1325. return self.url_result(vimeo_url)
  1326. vid_me_embed_url = self._search_regex(
  1327. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  1328. webpage, 'vid.me embed', default=None)
  1329. if vid_me_embed_url is not None:
  1330. return self.url_result(vid_me_embed_url, 'Vidme')
  1331. # Look for embedded YouTube player
  1332. matches = re.findall(r'''(?x)
  1333. (?:
  1334. <iframe[^>]+?src=|
  1335. data-video-url=|
  1336. <embed[^>]+?src=|
  1337. embedSWF\(?:\s*|
  1338. new\s+SWFObject\(
  1339. )
  1340. (["\'])
  1341. (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
  1342. (?:embed|v|p)/.+?)
  1343. \1''', webpage)
  1344. if matches:
  1345. return _playlist_from_matches(
  1346. matches, lambda m: unescapeHTML(m[1]))
  1347. # Look for lazyYT YouTube embed
  1348. matches = re.findall(
  1349. r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
  1350. if matches:
  1351. return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
  1352. # Look for embedded Dailymotion player
  1353. matches = re.findall(
  1354. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
  1355. if matches:
  1356. return _playlist_from_matches(
  1357. matches, lambda m: unescapeHTML(m[1]))
  1358. # Look for embedded Dailymotion playlist player (#3822)
  1359. m = re.search(
  1360. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  1361. if m:
  1362. playlists = re.findall(
  1363. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  1364. if playlists:
  1365. return _playlist_from_matches(
  1366. playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
  1367. # Look for embedded Wistia player
  1368. match = re.search(
  1369. r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
  1370. if match:
  1371. embed_url = self._proto_relative_url(
  1372. unescapeHTML(match.group('url')))
  1373. return {
  1374. '_type': 'url_transparent',
  1375. 'url': embed_url,
  1376. 'ie_key': 'Wistia',
  1377. 'uploader': video_uploader,
  1378. 'title': video_title,
  1379. 'id': video_id,
  1380. }
  1381. match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
  1382. if match:
  1383. return {
  1384. '_type': 'url_transparent',
  1385. 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
  1386. 'ie_key': 'Wistia',
  1387. 'uploader': video_uploader,
  1388. 'title': video_title,
  1389. 'id': match.group('id')
  1390. }
  1391. # Look for SVT player
  1392. svt_url = SVTIE._extract_url(webpage)
  1393. if svt_url:
  1394. return self.url_result(svt_url, 'SVT')
  1395. # Look for embedded condenast player
  1396. matches = re.findall(
  1397. r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
  1398. webpage)
  1399. if matches:
  1400. return {
  1401. '_type': 'playlist',
  1402. 'entries': [{
  1403. '_type': 'url',
  1404. 'ie_key': 'CondeNast',
  1405. 'url': ma,
  1406. } for ma in matches],
  1407. 'title': video_title,
  1408. 'id': video_id,
  1409. }
  1410. # Look for Bandcamp pages with custom domain
  1411. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  1412. if mobj is not None:
  1413. burl = unescapeHTML(mobj.group(1))
  1414. # Don't set the extractor because it can be a track url or an album
  1415. return self.url_result(burl)
  1416. # Look for embedded Vevo player
  1417. mobj = re.search(
  1418. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  1419. if mobj is not None:
  1420. return self.url_result(mobj.group('url'))
  1421. # Look for embedded Viddler player
  1422. mobj = re.search(
  1423. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  1424. webpage)
  1425. if mobj is not None:
  1426. return self.url_result(mobj.group('url'))
  1427. # Look for NYTimes player
  1428. mobj = re.search(
  1429. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  1430. webpage)
  1431. if mobj is not None:
  1432. return self.url_result(mobj.group('url'))
  1433. # Look for Libsyn player
  1434. mobj = re.search(
  1435. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  1436. if mobj is not None:
  1437. return self.url_result(mobj.group('url'))
  1438. # Look for Ooyala videos
  1439. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
  1440. re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
  1441. re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
  1442. re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  1443. if mobj is not None:
  1444. return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
  1445. # Look for multiple Ooyala embeds on SBN network websites
  1446. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  1447. if mobj is not None:
  1448. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  1449. if embeds:
  1450. return _playlist_from_matches(
  1451. embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  1452. # Look for Aparat videos
  1453. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  1454. if mobj is not None:
  1455. return self.url_result(mobj.group(1), 'Aparat')
  1456. # Look for MPORA videos
  1457. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  1458. if mobj is not None:
  1459. return self.url_result(mobj.group(1), 'Mpora')
  1460. # Look for embedded NovaMov-based player
  1461. mobj = re.search(
  1462. r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
  1463. (?P<url>http://(?:(?:embed|www)\.)?
  1464. (?:novamov\.com|
  1465. nowvideo\.(?:ch|sx|eu|at|ag|co)|
  1466. videoweed\.(?:es|com)|
  1467. movshare\.(?:net|sx|ag)|
  1468. divxstage\.(?:eu|net|ch|co|at|ag))
  1469. /embed\.php.+?)\1''', webpage)
  1470. if mobj is not None:
  1471. return self.url_result(mobj.group('url'))
  1472. # Look for embedded Facebook player
  1473. mobj = re.search(
  1474. r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
  1475. if mobj is not None:
  1476. return self.url_result(mobj.group('url'), 'Facebook')
  1477. # Look for embedded VK player
  1478. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  1479. if mobj is not None:
  1480. return self.url_result(mobj.group('url'), 'VK')
  1481. # Look for embedded ivi player
  1482. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  1483. if mobj is not None:
  1484. return self.url_result(mobj.group('url'), 'Ivi')
  1485. # Look for embedded Huffington Post player
  1486. mobj = re.search(
  1487. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  1488. if mobj is not None:
  1489. return self.url_result(mobj.group('url'), 'HuffPost')
  1490. # Look for embed.ly
  1491. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  1492. if mobj is not None:
  1493. return self.url_result(mobj.group('url'))
  1494. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  1495. if mobj is not None:
  1496. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  1497. # Look for funnyordie embed
  1498. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  1499. if matches:
  1500. return _playlist_from_matches(
  1501. matches, getter=unescapeHTML, ie='FunnyOrDie')
  1502. # Look for BBC iPlayer embed
  1503. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  1504. if matches:
  1505. return _playlist_from_matches(matches, ie='BBCCoUk')
  1506. # Look for embedded RUTV player
  1507. rutv_url = RUTVIE._extract_url(webpage)
  1508. if rutv_url:
  1509. return self.url_result(rutv_url, 'RUTV')
  1510. # Look for embedded TVC player
  1511. tvc_url = TVCIE._extract_url(webpage)
  1512. if tvc_url:
  1513. return self.url_result(tvc_url, 'TVC')
  1514. # Look for embedded SportBox player
  1515. sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
  1516. if sportbox_urls:
  1517. return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
  1518. # Look for embedded PornHub player
  1519. pornhub_url = PornHubIE._extract_url(webpage)
  1520. if pornhub_url:
  1521. return self.url_result(pornhub_url, 'PornHub')
  1522. # Look for embedded XHamster player
  1523. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  1524. if xhamster_urls:
  1525. return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
  1526. # Look for embedded Tvigle player
  1527. mobj = re.search(
  1528. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  1529. if mobj is not None:
  1530. return self.url_result(mobj.group('url'), 'Tvigle')
  1531. # Look for embedded TED player
  1532. mobj = re.search(
  1533. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  1534. if mobj is not None:
  1535. return self.url_result(mobj.group('url'), 'TED')
  1536. # Look for embedded Ustream videos
  1537. mobj = re.search(
  1538. r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
  1539. if mobj is not None:
  1540. return self.url_result(mobj.group('url'), 'Ustream')
  1541. # Look for embedded arte.tv player
  1542. mobj = re.search(
  1543. r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
  1544. webpage)
  1545. if mobj is not None:
  1546. return self.url_result(mobj.group('url'), 'ArteTVEmbed')
  1547. # Look for embedded francetv player
  1548. mobj = re.search(
  1549. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  1550. webpage)
  1551. if mobj is not None:
  1552. return self.url_result(mobj.group('url'))
  1553. # Look for embedded smotri.com player
  1554. smotri_url = SmotriIE._extract_url(webpage)
  1555. if smotri_url:
  1556. return self.url_result(smotri_url, 'Smotri')
  1557. # Look for embedded Myvi.ru player
  1558. myvi_url = MyviIE._extract_url(webpage)
  1559. if myvi_url:
  1560. return self.url_result(myvi_url)
  1561. # Look for embeded soundcloud player
  1562. mobj = re.search(
  1563. r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
  1564. webpage)
  1565. if mobj is not None:
  1566. url = unescapeHTML(mobj.group('url'))
  1567. return self.url_result(url)
  1568. # Look for embedded vulture.com player
  1569. mobj = re.search(
  1570. r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
  1571. webpage)
  1572. if mobj is not None:
  1573. url = unescapeHTML(mobj.group('url'))
  1574. return self.url_result(url, ie='Vulture')
  1575. # Look for embedded mtvservices player
  1576. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  1577. if mtvservices_url:
  1578. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  1579. # Look for embedded yahoo player
  1580. mobj = re.search(
  1581. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  1582. webpage)
  1583. if mobj is not None:
  1584. return self.url_result(mobj.group('url'), 'Yahoo')
  1585. # Look for embedded sbs.com.au player
  1586. mobj = re.search(
  1587. r'''(?x)
  1588. (?:
  1589. <meta\s+property="og:video"\s+content=|
  1590. <iframe[^>]+?src=
  1591. )
  1592. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  1593. webpage)
  1594. if mobj is not None:
  1595. return self.url_result(mobj.group('url'), 'SBS')
  1596. # Look for embedded Cinchcast player
  1597. mobj = re.search(
  1598. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  1599. webpage)
  1600. if mobj is not None:
  1601. return self.url_result(mobj.group('url'), 'Cinchcast')
  1602. mobj = re.search(
  1603. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  1604. webpage)
  1605. if not mobj:
  1606. mobj = re.search(
  1607. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  1608. webpage)
  1609. if mobj is not None:
  1610. return self.url_result(mobj.group('url'), 'MLB')
  1611. mobj = re.search(
  1612. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  1613. webpage)
  1614. if mobj is not None:
  1615. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  1616. mobj = re.search(
  1617. r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
  1618. webpage)
  1619. if mobj is not None:
  1620. return self.url_result(mobj.group('url'), 'Livestream')
  1621. # Look for Zapiks embed
  1622. mobj = re.search(
  1623. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  1624. if mobj is not None:
  1625. return self.url_result(mobj.group('url'), 'Zapiks')
  1626. # Look for Kaltura embeds
  1627. mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
  1628. 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))
  1629. if mobj is not None:
  1630. return self.url_result(smuggle_url(
  1631. 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
  1632. {'source_url': url}), 'Kaltura')
  1633. # Look for Eagle.Platform embeds
  1634. mobj = re.search(
  1635. r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
  1636. if mobj is not None:
  1637. return self.url_result(mobj.group('url'), 'EaglePlatform')
  1638. # Look for ClipYou (uses Eagle.Platform) embeds
  1639. mobj = re.search(
  1640. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  1641. if mobj is not None:
  1642. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  1643. # Look for Pladform embeds
  1644. pladform_url = PladformIE._extract_url(webpage)
  1645. if pladform_url:
  1646. return self.url_result(pladform_url)
  1647. # Look for Playwire embeds
  1648. mobj = re.search(
  1649. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  1650. if mobj is not None:
  1651. return self.url_result(mobj.group('url'))
  1652. # Look for 5min embeds
  1653. mobj = re.search(
  1654. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  1655. if mobj is not None:
  1656. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  1657. # Look for Crooks and Liars embeds
  1658. mobj = re.search(
  1659. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  1660. if mobj is not None:
  1661. return self.url_result(mobj.group('url'))
  1662. # Look for NBC Sports VPlayer embeds
  1663. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  1664. if nbc_sports_url:
  1665. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  1666. # Look for Google Drive embeds
  1667. google_drive_url = GoogleDriveIE._extract_url(webpage)
  1668. if google_drive_url:
  1669. return self.url_result(google_drive_url, 'GoogleDrive')
  1670. # Look for UDN embeds
  1671. mobj = re.search(
  1672. r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  1673. if mobj is not None:
  1674. return self.url_result(
  1675. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  1676. # Look for Senate ISVP iframe
  1677. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  1678. if senate_isvp_url:
  1679. return self.url_result(senate_isvp_url, 'SenateISVP')
  1680. # Look for Dailymotion Cloud videos
  1681. dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
  1682. if dmcloud_url:
  1683. return self.url_result(dmcloud_url, 'DailymotionCloud')
  1684. # Look for OnionStudios embeds
  1685. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  1686. if onionstudios_url:
  1687. return self.url_result(onionstudios_url)
  1688. # Look for SnagFilms embeds
  1689. snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
  1690. if snagfilms_url:
  1691. return self.url_result(snagfilms_url)
  1692. # Look for JWPlatform embeds
  1693. jwplatform_url = JWPlatformIE._extract_url(webpage)
  1694. if jwplatform_url:
  1695. return self.url_result(jwplatform_url, 'JWPlatform')
  1696. # Look for ScreenwaveMedia embeds
  1697. mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
  1698. if mobj is not None:
  1699. return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
  1700. # Look for AdobeTVVideo embeds
  1701. mobj = re.search(
  1702. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  1703. webpage)
  1704. if mobj is not None:
  1705. return self.url_result(
  1706. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  1707. 'AdobeTVVideo')
  1708. def check_video(vurl):
  1709. if YoutubeIE.suitable(vurl):
  1710. return True
  1711. vpath = compat_urlparse.urlparse(vurl).path
  1712. vext = determine_ext(vpath)
  1713. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
  1714. def filter_video(urls):
  1715. return list(filter(check_video, urls))
  1716. # Start with something easy: JW Player in SWFObject
  1717. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  1718. if not found:
  1719. # Look for gorilla-vid style embedding
  1720. found = filter_video(re.findall(r'''(?sx)
  1721. (?:
  1722. jw_plugins|
  1723. JWPlayerOptions|
  1724. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  1725. )
  1726. .*?
  1727. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  1728. if not found:
  1729. # Broaden the search a little bit
  1730. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  1731. if not found:
  1732. # Broaden the findall a little bit: JWPlayer JS loader
  1733. found = filter_video(re.findall(
  1734. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  1735. if not found:
  1736. # Flow player
  1737. found = filter_video(re.findall(r'''(?xs)
  1738. flowplayer\("[^"]+",\s*
  1739. \{[^}]+?\}\s*,
  1740. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  1741. ["']?url["']?\s*:\s*["']([^"']+)["']
  1742. ''', webpage))
  1743. if not found:
  1744. # Cinerama player
  1745. found = re.findall(
  1746. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  1747. if not found:
  1748. # Try to find twitter cards info
  1749. found = filter_video(re.findall(
  1750. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  1751. if not found:
  1752. # We look for Open Graph info:
  1753. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  1754. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  1755. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  1756. if m_video_type is not None:
  1757. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  1758. if not found:
  1759. # HTML5 video
  1760. found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
  1761. if not found:
  1762. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  1763. found = re.search(
  1764. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  1765. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  1766. webpage)
  1767. if not found:
  1768. # Look also in Refresh HTTP header
  1769. refresh_header = head_response.headers.get('Refresh')
  1770. if refresh_header:
  1771. # In python 2 response HTTP headers are bytestrings
  1772. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  1773. refresh_header = refresh_header.decode('iso-8859-1')
  1774. found = re.search(REDIRECT_REGEX, refresh_header)
  1775. if found:
  1776. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  1777. self.report_following_redirect(new_url)
  1778. return {
  1779. '_type': 'url',
  1780. 'url': new_url,
  1781. }
  1782. if not found:
  1783. raise UnsupportedError(url)
  1784. entries = []
  1785. for video_url in found:
  1786. video_url = video_url.replace('\\/', '/')
  1787. video_url = compat_urlparse.urljoin(url, video_url)
  1788. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  1789. # Sometimes, jwplayer extraction will result in a YouTube URL
  1790. if YoutubeIE.suitable(video_url):
  1791. entries.append(self.url_result(video_url, 'Youtube'))
  1792. continue
  1793. # here's a fun little line of code for you:
  1794. video_id = os.path.splitext(video_id)[0]
  1795. entry_info_dict = {
  1796. 'id': video_id,
  1797. 'uploader': video_uploader,
  1798. 'title': video_title,
  1799. 'age_limit': age_limit,
  1800. }
  1801. ext = determine_ext(video_url)
  1802. if ext == 'smil':
  1803. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  1804. elif ext == 'xspf':
  1805. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  1806. elif ext == 'm3u8':
  1807. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  1808. else:
  1809. entry_info_dict['url'] = video_url
  1810. entries.append(entry_info_dict)
  1811. if len(entries) == 1:
  1812. return entries[0]
  1813. else:
  1814. for num, e in enumerate(entries, start=1):
  1815. # 'url' results don't have a title
  1816. if e.get('title') is not None:
  1817. e['title'] = '%s (%d)' % (e['title'], num)
  1818. return {
  1819. '_type': 'playlist',
  1820. 'entries': entries,
  1821. }