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.

2164 lines
87 KiB

10 years ago
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
11 years ago
11 years ago
11 years ago
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
10 years ago
10 years ago
  1. # encoding: utf-8
  2. from __future__ import unicode_literals
  3. import os
  4. import re
  5. import sys
  6. from .common import InfoExtractor
  7. from .youtube import YoutubeIE
  8. from ..compat import (
  9. compat_etree_fromstring,
  10. compat_urllib_parse_unquote,
  11. compat_urlparse,
  12. compat_xml_parse_error,
  13. )
  14. from ..utils import (
  15. determine_ext,
  16. ExtractorError,
  17. float_or_none,
  18. HEADRequest,
  19. is_html,
  20. orderedSet,
  21. sanitized_Request,
  22. smuggle_url,
  23. unescapeHTML,
  24. unified_strdate,
  25. unsmuggle_url,
  26. UnsupportedError,
  27. url_basename,
  28. xpath_text,
  29. )
  30. from .brightcove import (
  31. BrightcoveLegacyIE,
  32. BrightcoveNewIE,
  33. )
  34. from .nbc import NBCSportsVPlayerIE
  35. from .ooyala import OoyalaIE
  36. from .rutv import RUTVIE
  37. from .tvc import TVCIE
  38. from .sportbox import SportBoxEmbedIE
  39. from .smotri import SmotriIE
  40. from .myvi import MyviIE
  41. from .condenast import CondeNastIE
  42. from .udn import UDNEmbedIE
  43. from .senateisvp import SenateISVPIE
  44. from .svt import SVTIE
  45. from .pornhub import PornHubIE
  46. from .xhamster import XHamsterEmbedIE
  47. from .tnaflix import TNAFlixNetworkEmbedIE
  48. from .vimeo import VimeoIE
  49. from .dailymotion import DailymotionCloudIE
  50. from .onionstudios import OnionStudiosIE
  51. from .viewlift import ViewLiftEmbedIE
  52. from .screenwavemedia import ScreenwaveMediaIE
  53. from .mtv import MTVServicesEmbeddedIE
  54. from .pladform import PladformIE
  55. from .videomore import VideomoreIE
  56. from .googledrive import GoogleDriveIE
  57. from .jwplatform import JWPlatformIE
  58. from .digiteka import DigitekaIE
  59. from .instagram import InstagramIE
  60. from .liveleak import LiveLeakIE
  61. from .threeqsdn import ThreeQSDNIE
  62. from .theplatform import ThePlatformIE
  63. class GenericIE(InfoExtractor):
  64. IE_DESC = 'Generic downloader that works on some sites'
  65. _VALID_URL = r'.*'
  66. IE_NAME = 'generic'
  67. _TESTS = [
  68. # Direct link to a video
  69. {
  70. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  71. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  72. 'info_dict': {
  73. 'id': 'trailer',
  74. 'ext': 'mp4',
  75. 'title': 'trailer',
  76. 'upload_date': '20100513',
  77. }
  78. },
  79. # Direct link to media delivered compressed (until Accept-Encoding is *)
  80. {
  81. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  82. 'md5': '128c42e68b13950268b648275386fc74',
  83. 'info_dict': {
  84. 'id': 'FictionJunction-Parallel_Hearts',
  85. 'ext': 'flac',
  86. 'title': 'FictionJunction-Parallel_Hearts',
  87. 'upload_date': '20140522',
  88. },
  89. 'expected_warnings': [
  90. 'URL could be a direct video link, returning it as such.'
  91. ]
  92. },
  93. # Direct download with broken HEAD
  94. {
  95. 'url': 'http://ai-radio.org:8000/radio.opus',
  96. 'info_dict': {
  97. 'id': 'radio',
  98. 'ext': 'opus',
  99. 'title': 'radio',
  100. },
  101. 'params': {
  102. 'skip_download': True, # infinite live stream
  103. },
  104. 'expected_warnings': [
  105. r'501.*Not Implemented',
  106. r'400.*Bad Request',
  107. ],
  108. },
  109. # Direct link with incorrect MIME type
  110. {
  111. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  112. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  113. 'info_dict': {
  114. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  115. 'id': '5_Lennart_Poettering_-_Systemd',
  116. 'ext': 'webm',
  117. 'title': '5_Lennart_Poettering_-_Systemd',
  118. 'upload_date': '20141120',
  119. },
  120. 'expected_warnings': [
  121. 'URL could be a direct video link, returning it as such.'
  122. ]
  123. },
  124. # RSS feed
  125. {
  126. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  127. 'info_dict': {
  128. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  129. 'title': 'Zero Punctuation',
  130. 'description': 're:.*groundbreaking video review series.*'
  131. },
  132. 'playlist_mincount': 11,
  133. },
  134. # RSS feed with enclosure
  135. {
  136. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  137. 'info_dict': {
  138. 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  139. 'ext': 'm4v',
  140. 'upload_date': '20150228',
  141. 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  142. }
  143. },
  144. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  145. {
  146. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  147. 'info_dict': {
  148. 'id': 'smil',
  149. 'ext': 'mp4',
  150. 'title': 'Automatics, robotics and biocybernetics',
  151. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  152. 'upload_date': '20130627',
  153. 'formats': 'mincount:16',
  154. 'subtitles': 'mincount:1',
  155. },
  156. 'params': {
  157. 'force_generic_extractor': True,
  158. 'skip_download': True,
  159. },
  160. },
  161. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  162. {
  163. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  164. 'info_dict': {
  165. 'id': 'hds',
  166. 'ext': 'flv',
  167. 'title': 'hds',
  168. 'formats': 'mincount:1',
  169. },
  170. 'params': {
  171. 'skip_download': True,
  172. },
  173. },
  174. # SMIL from https://www.restudy.dk/video/play/id/1637
  175. {
  176. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  177. 'info_dict': {
  178. 'id': 'video_1637',
  179. 'ext': 'flv',
  180. 'title': 'video_1637',
  181. 'formats': 'mincount:3',
  182. },
  183. 'params': {
  184. 'skip_download': True,
  185. },
  186. },
  187. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  188. {
  189. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  190. 'info_dict': {
  191. 'id': 'smil-service',
  192. 'ext': 'flv',
  193. 'title': 'smil-service',
  194. 'formats': 'mincount:1',
  195. },
  196. 'params': {
  197. 'skip_download': True,
  198. },
  199. },
  200. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  201. {
  202. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  203. 'info_dict': {
  204. 'id': '4719370',
  205. 'ext': 'mp4',
  206. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  207. 'formats': 'mincount:3',
  208. },
  209. 'params': {
  210. 'skip_download': True,
  211. },
  212. },
  213. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  214. {
  215. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  216. 'info_dict': {
  217. 'id': 'mZlp2ctYIUEB',
  218. 'ext': 'mp4',
  219. 'title': 'Tikibad ontruimd wegens brand',
  220. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  221. 'thumbnail': 're:^https?://.*\.jpg$',
  222. 'duration': 33,
  223. },
  224. 'params': {
  225. 'skip_download': True,
  226. },
  227. },
  228. # MPD from http://dash-mse-test.appspot.com/media.html
  229. {
  230. 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
  231. 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
  232. 'info_dict': {
  233. 'id': 'car-20120827-manifest',
  234. 'ext': 'mp4',
  235. 'title': 'car-20120827-manifest',
  236. 'formats': 'mincount:9',
  237. 'upload_date': '20130904',
  238. },
  239. 'params': {
  240. 'format': 'bestvideo',
  241. },
  242. },
  243. # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
  244. {
  245. 'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
  246. 'info_dict': {
  247. 'id': 'content',
  248. 'ext': 'mp4',
  249. 'title': 'content',
  250. 'formats': 'mincount:8',
  251. },
  252. 'params': {
  253. # m3u8 downloads
  254. 'skip_download': True,
  255. }
  256. },
  257. # m3u8 served with Content-Type: text/plain
  258. {
  259. 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
  260. 'info_dict': {
  261. 'id': 'index',
  262. 'ext': 'mp4',
  263. 'title': 'index',
  264. 'upload_date': '20140720',
  265. 'formats': 'mincount:11',
  266. },
  267. 'params': {
  268. # m3u8 downloads
  269. 'skip_download': True,
  270. }
  271. },
  272. # google redirect
  273. {
  274. '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',
  275. 'info_dict': {
  276. 'id': 'cmQHVoWB5FY',
  277. 'ext': 'mp4',
  278. 'upload_date': '20130224',
  279. 'uploader_id': 'TheVerge',
  280. 'description': 're:^Chris Ziegler takes a look at the\.*',
  281. 'uploader': 'The Verge',
  282. 'title': 'First Firefox OS phones side-by-side',
  283. },
  284. 'params': {
  285. 'skip_download': False,
  286. }
  287. },
  288. {
  289. # redirect in Refresh HTTP header
  290. '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',
  291. 'info_dict': {
  292. 'id': 'pO8h3EaFRdo',
  293. 'ext': 'mp4',
  294. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  295. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  296. 'upload_date': '20150917',
  297. 'uploader_id': 'brtvofficial',
  298. 'uploader': 'Boiler Room',
  299. },
  300. 'params': {
  301. 'skip_download': False,
  302. },
  303. },
  304. {
  305. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  306. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  307. 'info_dict': {
  308. 'id': '13601338388002',
  309. 'ext': 'mp4',
  310. 'uploader': 'www.hodiho.fr',
  311. 'title': 'R\u00e9gis plante sa Jeep',
  312. }
  313. },
  314. # bandcamp page with custom domain
  315. {
  316. 'add_ie': ['Bandcamp'],
  317. 'url': 'http://bronyrock.com/track/the-pony-mash',
  318. 'info_dict': {
  319. 'id': '3235767654',
  320. 'ext': 'mp3',
  321. 'title': 'The Pony Mash',
  322. 'uploader': 'M_Pallante',
  323. },
  324. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  325. },
  326. # embedded brightcove video
  327. # it also tests brightcove videos that need to set the 'Referer' in the
  328. # http requests
  329. {
  330. 'add_ie': ['BrightcoveLegacy'],
  331. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  332. 'info_dict': {
  333. 'id': '2765128793001',
  334. 'ext': 'mp4',
  335. 'title': 'Le cours de bourse : l’analyse technique',
  336. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  337. 'uploader': 'BFM BUSINESS',
  338. },
  339. 'params': {
  340. 'skip_download': True,
  341. },
  342. },
  343. {
  344. # https://github.com/rg3/youtube-dl/issues/2253
  345. 'url': 'http://bcove.me/i6nfkrc3',
  346. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  347. 'info_dict': {
  348. 'id': '3101154703001',
  349. 'ext': 'mp4',
  350. 'title': 'Still no power',
  351. 'uploader': 'thestar.com',
  352. '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.',
  353. },
  354. 'add_ie': ['BrightcoveLegacy'],
  355. },
  356. {
  357. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  358. 'md5': 'fb973ecf6e4a78a67453647444222983',
  359. 'info_dict': {
  360. 'id': '3414141473001',
  361. 'ext': 'mp4',
  362. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  363. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  364. 'uploader': 'Championat',
  365. },
  366. },
  367. {
  368. # https://github.com/rg3/youtube-dl/issues/3541
  369. 'add_ie': ['BrightcoveLegacy'],
  370. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  371. 'info_dict': {
  372. 'id': '3866516442001',
  373. 'ext': 'mp4',
  374. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  375. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  376. 'uploader': 'SBS Broadcasting',
  377. },
  378. 'skip': 'Restricted to Netherlands',
  379. 'params': {
  380. 'skip_download': True, # m3u8 download
  381. },
  382. },
  383. # ooyala video
  384. {
  385. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  386. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  387. 'info_dict': {
  388. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  389. 'ext': 'mp4',
  390. 'title': '2cc213299525360.mov', # that's what we get
  391. 'duration': 238.231,
  392. },
  393. 'add_ie': ['Ooyala'],
  394. },
  395. {
  396. # ooyala video embedded with http://player.ooyala.com/iframe.js
  397. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  398. 'info_dict': {
  399. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  400. 'ext': 'mp4',
  401. 'title': '"Steve Jobs: Man in the Machine" trailer',
  402. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  403. 'duration': 135.427,
  404. },
  405. 'params': {
  406. 'skip_download': True,
  407. },
  408. },
  409. # embed.ly video
  410. {
  411. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  412. 'info_dict': {
  413. 'id': '9ODmcdjQcHQ',
  414. 'ext': 'mp4',
  415. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  416. 'upload_date': '20140225',
  417. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  418. 'uploader': 'Tested',
  419. 'uploader_id': 'testedcom',
  420. },
  421. # No need to test YoutubeIE here
  422. 'params': {
  423. 'skip_download': True,
  424. },
  425. },
  426. # funnyordie embed
  427. {
  428. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  429. 'info_dict': {
  430. 'id': '18e820ec3f',
  431. 'ext': 'mp4',
  432. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  433. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  434. },
  435. },
  436. # RUTV embed
  437. {
  438. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  439. 'info_dict': {
  440. 'id': '776940',
  441. 'ext': 'mp4',
  442. 'title': 'Охотское море стало целиком российским',
  443. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  444. },
  445. 'params': {
  446. # m3u8 download
  447. 'skip_download': True,
  448. },
  449. },
  450. # TVC embed
  451. {
  452. '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/',
  453. 'info_dict': {
  454. 'id': '55304',
  455. 'ext': 'mp4',
  456. 'title': 'Дошкольное воспитание',
  457. },
  458. },
  459. # SportBox embed
  460. {
  461. 'url': 'http://www.vestifinance.ru/articles/25753',
  462. 'info_dict': {
  463. 'id': '25753',
  464. 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  465. },
  466. 'playlist': [{
  467. 'info_dict': {
  468. 'id': '370908',
  469. 'title': 'Госзаказ. День 3',
  470. 'ext': 'mp4',
  471. }
  472. }, {
  473. 'info_dict': {
  474. 'id': '370905',
  475. 'title': 'Госзаказ. День 2',
  476. 'ext': 'mp4',
  477. }
  478. }, {
  479. 'info_dict': {
  480. 'id': '370902',
  481. 'title': 'Госзаказ. День 1',
  482. 'ext': 'mp4',
  483. }
  484. }],
  485. 'params': {
  486. # m3u8 download
  487. 'skip_download': True,
  488. },
  489. },
  490. # Myvi.ru embed
  491. {
  492. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  493. 'info_dict': {
  494. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  495. 'ext': 'mp4',
  496. 'title': 'Ужастики, русский трейлер (2015)',
  497. 'thumbnail': 're:^https?://.*\.jpg$',
  498. 'duration': 153,
  499. }
  500. },
  501. # XHamster embed
  502. {
  503. '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',
  504. 'info_dict': {
  505. 'id': 'showthread',
  506. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  507. },
  508. 'playlist_mincount': 7,
  509. },
  510. # Embedded TED video
  511. {
  512. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  513. 'md5': '65fdff94098e4a607385a60c5177c638',
  514. 'info_dict': {
  515. 'id': '1969',
  516. 'ext': 'mp4',
  517. 'title': 'Hidden miracles of the natural world',
  518. 'uploader': 'Louie Schwartzberg',
  519. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  520. }
  521. },
  522. # Embedded Ustream video
  523. {
  524. 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
  525. 'md5': '27b99cdb639c9b12a79bca876a073417',
  526. 'info_dict': {
  527. 'id': '45734260',
  528. 'ext': 'flv',
  529. 'uploader': 'AU SPA: The NSA and Privacy',
  530. 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
  531. }
  532. },
  533. # nowvideo embed hidden behind percent encoding
  534. {
  535. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  536. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  537. 'info_dict': {
  538. 'id': '06e53103ca9aa',
  539. 'ext': 'flv',
  540. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  541. 'description': 'No description',
  542. },
  543. },
  544. # arte embed
  545. {
  546. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  547. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  548. 'info_dict': {
  549. 'id': '048195-004_PLUS7-F',
  550. 'ext': 'flv',
  551. 'title': 'X:enius',
  552. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  553. 'upload_date': '20140320',
  554. },
  555. 'params': {
  556. 'skip_download': 'Requires rtmpdump'
  557. }
  558. },
  559. # francetv embed
  560. {
  561. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  562. 'info_dict': {
  563. 'id': 'EV_30231',
  564. 'ext': 'mp4',
  565. 'title': 'Alcaline, le concert avec Calogero',
  566. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  567. 'upload_date': '20150226',
  568. 'timestamp': 1424989860,
  569. 'duration': 5400,
  570. },
  571. 'params': {
  572. # m3u8 downloads
  573. 'skip_download': True,
  574. },
  575. 'expected_warnings': [
  576. 'Forbidden'
  577. ]
  578. },
  579. # Condé Nast embed
  580. {
  581. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  582. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  583. 'info_dict': {
  584. 'id': '53501be369702d3275860000',
  585. 'ext': 'mp4',
  586. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  587. }
  588. },
  589. # Dailymotion embed
  590. {
  591. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  592. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  593. 'info_dict': {
  594. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  595. 'ext': 'mp4',
  596. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  597. 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
  598. 'uploader': 'Spi0n',
  599. 'uploader_id': 'xgditw',
  600. 'upload_date': '20140425',
  601. 'timestamp': 1398441542,
  602. },
  603. 'add_ie': ['Dailymotion'],
  604. },
  605. # YouTube embed
  606. {
  607. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  608. 'info_dict': {
  609. 'id': 'FXRb4ykk4S0',
  610. 'ext': 'mp4',
  611. 'title': 'The NBL Auction 2014',
  612. 'uploader': 'BADMINTON England',
  613. 'uploader_id': 'BADMINTONEvents',
  614. 'upload_date': '20140603',
  615. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  616. },
  617. 'add_ie': ['Youtube'],
  618. 'params': {
  619. 'skip_download': True,
  620. }
  621. },
  622. # MTVSercices embed
  623. {
  624. 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
  625. 'md5': '35727f82f58c76d996fc188f9755b0d5',
  626. 'info_dict': {
  627. 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
  628. 'ext': 'mp4',
  629. 'title': 'Review',
  630. 'description': 'Mario\'s life in the fast lane has never looked so good.',
  631. },
  632. },
  633. # YouTube embed via <data-embed-url="">
  634. {
  635. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  636. 'info_dict': {
  637. 'id': '4vAffPZIT44',
  638. 'ext': 'mp4',
  639. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  640. 'uploader': 'Gameloft',
  641. 'uploader_id': 'gameloft',
  642. 'upload_date': '20140828',
  643. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  644. },
  645. 'params': {
  646. 'skip_download': True,
  647. }
  648. },
  649. # Camtasia studio
  650. {
  651. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  652. 'playlist': [{
  653. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  654. 'info_dict': {
  655. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  656. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  657. 'ext': 'flv',
  658. 'duration': 2235.90,
  659. }
  660. }, {
  661. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  662. 'info_dict': {
  663. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  664. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  665. 'ext': 'flv',
  666. 'duration': 2235.93,
  667. }
  668. }],
  669. 'info_dict': {
  670. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  671. }
  672. },
  673. # Flowplayer
  674. {
  675. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  676. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  677. 'info_dict': {
  678. 'id': '5123ea6d5e5a7',
  679. 'ext': 'mp4',
  680. 'age_limit': 18,
  681. 'uploader': 'www.handjobhub.com',
  682. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  683. }
  684. },
  685. # Multiple brightcove videos
  686. # https://github.com/rg3/youtube-dl/issues/2283
  687. {
  688. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  689. 'info_dict': {
  690. 'id': 'always-never',
  691. 'title': 'Always / Never - The New Yorker',
  692. },
  693. 'playlist_count': 3,
  694. 'params': {
  695. 'extract_flat': False,
  696. 'skip_download': True,
  697. }
  698. },
  699. # MLB embed
  700. {
  701. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  702. 'md5': '96f09a37e44da40dd083e12d9a683327',
  703. 'info_dict': {
  704. 'id': '33322633',
  705. 'ext': 'mp4',
  706. 'title': 'Ump changes call to ball',
  707. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  708. 'duration': 48,
  709. 'timestamp': 1401537900,
  710. 'upload_date': '20140531',
  711. 'thumbnail': 're:^https?://.*\.jpg$',
  712. },
  713. },
  714. # Wistia embed
  715. {
  716. 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  717. 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
  718. 'info_dict': {
  719. 'id': '6e2wtrbdaf',
  720. 'ext': 'mov',
  721. 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
  722. 'description': 'a Paywall Videos video from Remilon',
  723. 'duration': 644.072,
  724. 'uploader': 'study.com',
  725. 'timestamp': 1459678540,
  726. 'upload_date': '20160403',
  727. 'filesize': 24687186,
  728. },
  729. },
  730. {
  731. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  732. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  733. 'info_dict': {
  734. 'id': 'uxjb0lwrcz',
  735. 'ext': 'mp4',
  736. 'title': 'Conversation about Hexagonal Rails Part 1',
  737. 'description': 'a Martin Fowler video from ThoughtWorks',
  738. 'duration': 1715.0,
  739. 'uploader': 'thoughtworks.wistia.com',
  740. 'timestamp': 1401832161,
  741. 'upload_date': '20140603',
  742. },
  743. },
  744. # Wistia standard embed (async)
  745. {
  746. 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
  747. 'info_dict': {
  748. 'id': '807fafadvk',
  749. 'ext': 'mp4',
  750. 'title': 'Drip Brennan Dunn Workshop',
  751. 'description': 'a JV Webinars video from getdrip-1',
  752. 'duration': 4986.95,
  753. 'timestamp': 1463607249,
  754. 'upload_date': '20160518',
  755. },
  756. 'params': {
  757. 'skip_download': True,
  758. }
  759. },
  760. # Soundcloud embed
  761. {
  762. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  763. 'info_dict': {
  764. 'id': '174391317',
  765. 'ext': 'mp3',
  766. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  767. 'uploader': 'Sophos Security',
  768. 'title': 'Chet Chat 171 - Oct 29, 2014',
  769. 'upload_date': '20141029',
  770. }
  771. },
  772. # Livestream embed
  773. {
  774. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  775. 'info_dict': {
  776. 'id': '67864563',
  777. 'ext': 'flv',
  778. 'upload_date': '20141112',
  779. 'title': 'Rosetta #CometLanding webcast HL 10',
  780. }
  781. },
  782. # LazyYT
  783. {
  784. 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
  785. 'info_dict': {
  786. 'id': '1986',
  787. 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
  788. },
  789. 'playlist_mincount': 2,
  790. },
  791. # Cinchcast embed
  792. {
  793. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  794. 'info_dict': {
  795. 'id': '7141703',
  796. 'ext': 'mp3',
  797. 'upload_date': '20141126',
  798. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  799. }
  800. },
  801. # Cinerama player
  802. {
  803. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  804. 'info_dict': {
  805. 'id': '730m_DandD_1901_512k',
  806. 'ext': 'mp4',
  807. 'uploader': 'www.abc.net.au',
  808. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  809. }
  810. },
  811. # embedded viddler video
  812. {
  813. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  814. 'info_dict': {
  815. 'id': '4d03aad9',
  816. 'ext': 'mp4',
  817. 'uploader': 'deadspin',
  818. 'title': 'WALL-TO-GORTAT',
  819. 'timestamp': 1422285291,
  820. 'upload_date': '20150126',
  821. },
  822. 'add_ie': ['Viddler'],
  823. },
  824. # Libsyn embed
  825. {
  826. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  827. 'info_dict': {
  828. 'id': '3377616',
  829. 'ext': 'mp3',
  830. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  831. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  832. 'upload_date': '20150220',
  833. },
  834. },
  835. # jwplayer YouTube
  836. {
  837. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  838. 'info_dict': {
  839. 'id': 'Mrj4DVp2zeA',
  840. 'ext': 'mp4',
  841. 'upload_date': '20150212',
  842. 'uploader': 'The National Archives UK',
  843. 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
  844. 'uploader_id': 'NationalArchives08',
  845. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  846. },
  847. },
  848. # rtl.nl embed
  849. {
  850. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  851. 'playlist_mincount': 5,
  852. 'info_dict': {
  853. 'id': 'aanslagen-kopenhagen',
  854. 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
  855. }
  856. },
  857. # Zapiks embed
  858. {
  859. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  860. 'info_dict': {
  861. 'id': '118046',
  862. 'ext': 'mp4',
  863. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  864. }
  865. },
  866. # Kaltura embed
  867. {
  868. 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
  869. 'info_dict': {
  870. 'id': '1_eergr3h1',
  871. 'ext': 'mp4',
  872. 'upload_date': '20150226',
  873. 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
  874. 'timestamp': int,
  875. 'title': 'John Carlson Postgame 2/25/15',
  876. },
  877. },
  878. # Kaltura embed (different embed code)
  879. {
  880. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  881. 'info_dict': {
  882. 'id': '1_a52wc67y',
  883. 'ext': 'flv',
  884. 'upload_date': '20150127',
  885. 'uploader_id': 'PremierMedia',
  886. 'timestamp': int,
  887. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  888. },
  889. },
  890. # Kaltura embed protected with referrer
  891. {
  892. 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
  893. 'info_dict': {
  894. 'id': '1_g4fbemnq',
  895. 'ext': 'mp4',
  896. 'title': 'Violetta - Achter De Schermen - Ruggero',
  897. 'description': 'Achter de schermen met Ruggero',
  898. 'timestamp': 1435133761,
  899. 'upload_date': '20150624',
  900. 'uploader_id': 'echojecka',
  901. },
  902. },
  903. # Eagle.Platform embed (generic URL)
  904. {
  905. 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
  906. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  907. 'info_dict': {
  908. 'id': '227304',
  909. 'ext': 'mp4',
  910. 'title': 'Навальный вышел на свободу',
  911. 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
  912. 'thumbnail': 're:^https?://.*\.jpg$',
  913. 'duration': 87,
  914. 'view_count': int,
  915. 'age_limit': 0,
  916. },
  917. },
  918. # ClipYou (Eagle.Platform) embed (custom URL)
  919. {
  920. 'url': 'http://muz-tv.ru/play/7129/',
  921. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  922. 'info_dict': {
  923. 'id': '12820',
  924. 'ext': 'mp4',
  925. 'title': "'O Sole Mio",
  926. 'thumbnail': 're:^https?://.*\.jpg$',
  927. 'duration': 216,
  928. 'view_count': int,
  929. },
  930. },
  931. # Pladform embed
  932. {
  933. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  934. 'info_dict': {
  935. 'id': '100183293',
  936. 'ext': 'mp4',
  937. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  938. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  939. 'thumbnail': 're:^https?://.*\.jpg$',
  940. 'duration': 694,
  941. 'age_limit': 0,
  942. },
  943. },
  944. # Playwire embed
  945. {
  946. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  947. 'info_dict': {
  948. 'id': '3519514',
  949. 'ext': 'mp4',
  950. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  951. 'thumbnail': 're:^https?://.*\.png$',
  952. 'duration': 45.115,
  953. },
  954. },
  955. # 5min embed
  956. {
  957. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  958. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  959. 'info_dict': {
  960. 'id': '518726732',
  961. 'ext': 'mp4',
  962. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  963. },
  964. },
  965. # SVT embed
  966. {
  967. 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
  968. 'info_dict': {
  969. 'id': '2900353',
  970. 'ext': 'flv',
  971. 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
  972. 'duration': 27,
  973. 'age_limit': 0,
  974. },
  975. },
  976. # Crooks and Liars embed
  977. {
  978. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  979. 'info_dict': {
  980. 'id': '8RUoRhRi',
  981. 'ext': 'mp4',
  982. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  983. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  984. 'timestamp': 1428207000,
  985. 'upload_date': '20150405',
  986. 'uploader': 'Heather',
  987. },
  988. },
  989. # Crooks and Liars external embed
  990. {
  991. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  992. 'info_dict': {
  993. 'id': 'MTE3MjUtMzQ2MzA',
  994. 'ext': 'mp4',
  995. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  996. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  997. 'timestamp': 1265032391,
  998. 'upload_date': '20100201',
  999. 'uploader': 'Heather',
  1000. },
  1001. },
  1002. # NBC Sports vplayer embed
  1003. {
  1004. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  1005. 'info_dict': {
  1006. 'id': 'ln7x1qSThw4k',
  1007. 'ext': 'flv',
  1008. 'title': "PFT Live: New leader in the 'new-look' defense",
  1009. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  1010. 'uploader': 'NBCU-SPORTS',
  1011. 'upload_date': '20140107',
  1012. 'timestamp': 1389118457,
  1013. },
  1014. },
  1015. # UDN embed
  1016. {
  1017. 'url': 'http://www.udn.com/news/story/7314/822787',
  1018. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  1019. 'info_dict': {
  1020. 'id': '300346',
  1021. 'ext': 'mp4',
  1022. 'title': '中一中男師變性 全校師生力挺',
  1023. 'thumbnail': 're:^https?://.*\.jpg$',
  1024. }
  1025. },
  1026. # Ooyala embed
  1027. {
  1028. 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
  1029. 'info_dict': {
  1030. 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
  1031. 'ext': 'mp4',
  1032. 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
  1033. 'title': 'This is what separates the Excel masters from the wannabes',
  1034. 'duration': 191.933,
  1035. },
  1036. 'params': {
  1037. # m3u8 downloads
  1038. 'skip_download': True,
  1039. }
  1040. },
  1041. # Contains a SMIL manifest
  1042. {
  1043. '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',
  1044. 'info_dict': {
  1045. 'id': 'file',
  1046. 'ext': 'flv',
  1047. 'title': '+ Football: Lottery Champions League Europe',
  1048. 'uploader': 'www.telewebion.com',
  1049. },
  1050. 'params': {
  1051. # rtmpe downloads
  1052. 'skip_download': True,
  1053. }
  1054. },
  1055. # Brightcove URL in single quotes
  1056. {
  1057. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  1058. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  1059. 'info_dict': {
  1060. 'id': '4255764656001',
  1061. 'ext': 'mp4',
  1062. 'title': 'SN Presents: Russell Martin, World Citizen',
  1063. '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.',
  1064. 'uploader': 'Rogers Sportsnet',
  1065. 'uploader_id': '1704050871',
  1066. 'upload_date': '20150525',
  1067. 'timestamp': 1432570283,
  1068. },
  1069. },
  1070. # Dailymotion Cloud video
  1071. {
  1072. 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
  1073. 'md5': '49444254273501a64675a7e68c502681',
  1074. 'info_dict': {
  1075. 'id': '5585de919473990de4bee11b',
  1076. 'ext': 'mp4',
  1077. 'title': 'Le débat',
  1078. 'thumbnail': 're:^https?://.*\.jpe?g$',
  1079. }
  1080. },
  1081. # OnionStudios embed
  1082. {
  1083. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1084. 'info_dict': {
  1085. 'id': '2855',
  1086. 'ext': 'mp4',
  1087. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1088. 'thumbnail': 're:^https?://.*\.jpe?g$',
  1089. 'uploader': 'ClickHole',
  1090. 'uploader_id': 'clickhole',
  1091. }
  1092. },
  1093. # SnagFilms embed
  1094. {
  1095. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1096. 'info_dict': {
  1097. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1098. 'ext': 'mp4',
  1099. 'title': '#whilewewatch',
  1100. }
  1101. },
  1102. # AdobeTVVideo embed
  1103. {
  1104. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1105. 'md5': '43662b577c018ad707a63766462b1e87',
  1106. 'info_dict': {
  1107. 'id': '2456',
  1108. 'ext': 'mp4',
  1109. 'title': 'New experience with Acrobat DC',
  1110. 'description': 'New experience with Acrobat DC',
  1111. 'duration': 248.667,
  1112. },
  1113. },
  1114. # ScreenwaveMedia embed
  1115. {
  1116. 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
  1117. 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
  1118. 'info_dict': {
  1119. 'id': 'cinemasnob-55d26273809dd',
  1120. 'ext': 'mp4',
  1121. 'title': 'cinemasnob',
  1122. },
  1123. },
  1124. # BrightcoveInPageEmbed embed
  1125. {
  1126. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1127. 'info_dict': {
  1128. 'id': '4238694884001',
  1129. 'ext': 'flv',
  1130. 'title': 'Tabletop: Dread, Last Thoughts',
  1131. 'description': 'Tabletop: Dread, Last Thoughts',
  1132. 'duration': 51690,
  1133. },
  1134. },
  1135. # JWPlayer with M3U8
  1136. {
  1137. 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
  1138. 'info_dict': {
  1139. 'id': 'playlist',
  1140. 'ext': 'mp4',
  1141. 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
  1142. 'uploader': 'ren.tv',
  1143. },
  1144. 'params': {
  1145. # m3u8 downloads
  1146. 'skip_download': True,
  1147. }
  1148. },
  1149. # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
  1150. # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
  1151. {
  1152. 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
  1153. 'info_dict': {
  1154. 'id': '4785848093001',
  1155. 'ext': 'mp4',
  1156. 'title': 'The Cardinal Pell Interview',
  1157. 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
  1158. 'uploader': 'GlobeCast Australia - GlobeStream',
  1159. 'uploader_id': '2733773828001',
  1160. 'upload_date': '20160304',
  1161. 'timestamp': 1457083087,
  1162. },
  1163. 'params': {
  1164. # m3u8 downloads
  1165. 'skip_download': True,
  1166. },
  1167. },
  1168. # Another form of arte.tv embed
  1169. {
  1170. 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
  1171. 'md5': '850bfe45417ddf221288c88a0cffe2e2',
  1172. 'info_dict': {
  1173. 'id': '030273-562_PLUS7-F',
  1174. 'ext': 'mp4',
  1175. 'title': 'ARTE Reportage - Nulle part, en France',
  1176. 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
  1177. 'upload_date': '20160409',
  1178. },
  1179. },
  1180. # LiveLeak embed
  1181. {
  1182. 'url': 'http://www.wykop.pl/link/3088787/',
  1183. 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
  1184. 'info_dict': {
  1185. 'id': '874_1459135191',
  1186. 'ext': 'mp4',
  1187. 'title': 'Man shows poor quality of new apartment building',
  1188. 'description': 'The wall is like a sand pile.',
  1189. 'uploader': 'Lake8737',
  1190. }
  1191. },
  1192. ]
  1193. def report_following_redirect(self, new_url):
  1194. """Report information extraction."""
  1195. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  1196. def _extract_rss(self, url, video_id, doc):
  1197. playlist_title = doc.find('./channel/title').text
  1198. playlist_desc_el = doc.find('./channel/description')
  1199. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  1200. entries = []
  1201. for it in doc.findall('./channel/item'):
  1202. next_url = xpath_text(it, 'link', fatal=False)
  1203. if not next_url:
  1204. enclosure_nodes = it.findall('./enclosure')
  1205. for e in enclosure_nodes:
  1206. next_url = e.attrib.get('url')
  1207. if next_url:
  1208. break
  1209. if not next_url:
  1210. continue
  1211. entries.append({
  1212. '_type': 'url',
  1213. 'url': next_url,
  1214. 'title': it.find('title').text,
  1215. })
  1216. return {
  1217. '_type': 'playlist',
  1218. 'id': url,
  1219. 'title': playlist_title,
  1220. 'description': playlist_desc,
  1221. 'entries': entries,
  1222. }
  1223. def _extract_camtasia(self, url, video_id, webpage):
  1224. """ Returns None if no camtasia video can be found. """
  1225. camtasia_cfg = self._search_regex(
  1226. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  1227. webpage, 'camtasia configuration file', default=None)
  1228. if camtasia_cfg is None:
  1229. return None
  1230. title = self._html_search_meta('DC.title', webpage, fatal=True)
  1231. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  1232. camtasia_cfg = self._download_xml(
  1233. camtasia_url, video_id,
  1234. note='Downloading camtasia configuration',
  1235. errnote='Failed to download camtasia configuration')
  1236. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  1237. entries = []
  1238. for n in fileset_node.getchildren():
  1239. url_n = n.find('./uri')
  1240. if url_n is None:
  1241. continue
  1242. entries.append({
  1243. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  1244. 'title': '%s - %s' % (title, n.tag),
  1245. 'url': compat_urlparse.urljoin(url, url_n.text),
  1246. 'duration': float_or_none(n.find('./duration').text),
  1247. })
  1248. return {
  1249. '_type': 'playlist',
  1250. 'entries': entries,
  1251. 'title': title,
  1252. }
  1253. def _real_extract(self, url):
  1254. if url.startswith('//'):
  1255. return {
  1256. '_type': 'url',
  1257. 'url': self.http_scheme() + url,
  1258. }
  1259. parsed_url = compat_urlparse.urlparse(url)
  1260. if not parsed_url.scheme:
  1261. default_search = self._downloader.params.get('default_search')
  1262. if default_search is None:
  1263. default_search = 'fixup_error'
  1264. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  1265. if '/' in url:
  1266. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  1267. return self.url_result('http://' + url)
  1268. elif default_search != 'fixup_error':
  1269. if default_search == 'auto_warning':
  1270. if re.match(r'^(?:url|URL)$', url):
  1271. raise ExtractorError(
  1272. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  1273. expected=True)
  1274. else:
  1275. self._downloader.report_warning(
  1276. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  1277. return self.url_result('ytsearch:' + url)
  1278. if default_search in ('error', 'fixup_error'):
  1279. raise ExtractorError(
  1280. '%r is not a valid URL. '
  1281. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  1282. % (url, url), expected=True)
  1283. else:
  1284. if ':' not in default_search:
  1285. default_search += ':'
  1286. return self.url_result(default_search + url)
  1287. url, smuggled_data = unsmuggle_url(url)
  1288. force_videoid = None
  1289. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  1290. if smuggled_data and 'force_videoid' in smuggled_data:
  1291. force_videoid = smuggled_data['force_videoid']
  1292. video_id = force_videoid
  1293. else:
  1294. video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
  1295. self.to_screen('%s: Requesting header' % video_id)
  1296. head_req = HEADRequest(url)
  1297. head_response = self._request_webpage(
  1298. head_req, video_id,
  1299. note=False, errnote='Could not send HEAD request to %s' % url,
  1300. fatal=False)
  1301. if head_response is not False:
  1302. # Check for redirect
  1303. new_url = head_response.geturl()
  1304. if url != new_url:
  1305. self.report_following_redirect(new_url)
  1306. if force_videoid:
  1307. new_url = smuggle_url(
  1308. new_url, {'force_videoid': force_videoid})
  1309. return self.url_result(new_url)
  1310. full_response = None
  1311. if head_response is False:
  1312. request = sanitized_Request(url)
  1313. request.add_header('Accept-Encoding', '*')
  1314. full_response = self._request_webpage(request, video_id)
  1315. head_response = full_response
  1316. info_dict = {
  1317. 'id': video_id,
  1318. 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
  1319. 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
  1320. }
  1321. # Check for direct link to a video
  1322. content_type = head_response.headers.get('Content-Type', '').lower()
  1323. m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
  1324. if m:
  1325. format_id = m.group('format_id')
  1326. if format_id.endswith('mpegurl'):
  1327. formats = self._extract_m3u8_formats(url, video_id, 'mp4')
  1328. elif format_id == 'f4m':
  1329. formats = self._extract_f4m_formats(url, video_id)
  1330. else:
  1331. formats = [{
  1332. 'format_id': m.group('format_id'),
  1333. 'url': url,
  1334. 'vcodec': 'none' if m.group('type') == 'audio' else None
  1335. }]
  1336. info_dict['direct'] = True
  1337. self._sort_formats(formats)
  1338. info_dict['formats'] = formats
  1339. return info_dict
  1340. if not self._downloader.params.get('test', False) and not is_intentional:
  1341. force = self._downloader.params.get('force_generic_extractor', False)
  1342. self._downloader.report_warning(
  1343. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  1344. if not full_response:
  1345. request = sanitized_Request(url)
  1346. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  1347. # making it impossible to download only chunk of the file (yet we need only 512kB to
  1348. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  1349. # that will always result in downloading the whole file that is not desirable.
  1350. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  1351. # to accept raw bytes and being able to download only a chunk.
  1352. # It may probably better to solve this by checking Content-Type for application/octet-stream
  1353. # after HEAD request finishes, but not sure if we can rely on this.
  1354. request.add_header('Accept-Encoding', '*')
  1355. full_response = self._request_webpage(request, video_id)
  1356. first_bytes = full_response.read(512)
  1357. # Is it an M3U playlist?
  1358. if first_bytes.startswith(b'#EXTM3U'):
  1359. info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
  1360. self._sort_formats(info_dict['formats'])
  1361. return info_dict
  1362. # Maybe it's a direct link to a video?
  1363. # Be careful not to download the whole thing!
  1364. if not is_html(first_bytes):
  1365. self._downloader.report_warning(
  1366. 'URL could be a direct video link, returning it as such.')
  1367. info_dict.update({
  1368. 'direct': True,
  1369. 'url': url,
  1370. })
  1371. return info_dict
  1372. webpage = self._webpage_read_content(
  1373. full_response, url, video_id, prefix=first_bytes)
  1374. self.report_extraction(video_id)
  1375. # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
  1376. try:
  1377. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  1378. if doc.tag == 'rss':
  1379. return self._extract_rss(url, video_id, doc)
  1380. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  1381. smil = self._parse_smil(doc, url, video_id)
  1382. self._sort_formats(smil['formats'])
  1383. return smil
  1384. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  1385. return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
  1386. elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
  1387. info_dict['formats'] = self._parse_mpd_formats(
  1388. doc, video_id, mpd_base_url=url.rpartition('/')[0])
  1389. self._sort_formats(info_dict['formats'])
  1390. return info_dict
  1391. elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
  1392. info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
  1393. self._sort_formats(info_dict['formats'])
  1394. return info_dict
  1395. except compat_xml_parse_error:
  1396. pass
  1397. # Is it a Camtasia project?
  1398. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  1399. if camtasia_res is not None:
  1400. return camtasia_res
  1401. # Sometimes embedded video player is hidden behind percent encoding
  1402. # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
  1403. # Unescaping the whole page allows to handle those cases in a generic way
  1404. webpage = compat_urllib_parse_unquote(webpage)
  1405. # it's tempting to parse this further, but you would
  1406. # have to take into account all the variations like
  1407. # Video Title - Site Name
  1408. # Site Name | Video Title
  1409. # Video Title - Tagline | Site Name
  1410. # and so on and so forth; it's just not practical
  1411. video_title = self._og_search_title(
  1412. webpage, default=None) or self._html_search_regex(
  1413. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  1414. default='video')
  1415. # Try to detect age limit automatically
  1416. age_limit = self._rta_search(webpage)
  1417. # And then there are the jokers who advertise that they use RTA,
  1418. # but actually don't.
  1419. AGE_LIMIT_MARKERS = [
  1420. r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
  1421. ]
  1422. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  1423. age_limit = 18
  1424. # video uploader is domain name
  1425. video_uploader = self._search_regex(
  1426. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  1427. video_description = self._og_search_description(webpage, default=None)
  1428. video_thumbnail = self._og_search_thumbnail(webpage, default=None)
  1429. # Helper method
  1430. def _playlist_from_matches(matches, getter=None, ie=None):
  1431. urlrs = orderedSet(
  1432. self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
  1433. for m in matches)
  1434. return self.playlist_result(
  1435. urlrs, playlist_id=video_id, playlist_title=video_title)
  1436. # Look for Brightcove Legacy Studio embeds
  1437. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  1438. if bc_urls:
  1439. self.to_screen('Brightcove video detected.')
  1440. entries = [{
  1441. '_type': 'url',
  1442. 'url': smuggle_url(bc_url, {'Referer': url}),
  1443. 'ie_key': 'BrightcoveLegacy'
  1444. } for bc_url in bc_urls]
  1445. return {
  1446. '_type': 'playlist',
  1447. 'title': video_title,
  1448. 'id': video_id,
  1449. 'entries': entries,
  1450. }
  1451. # Look for Brightcove New Studio embeds
  1452. bc_urls = BrightcoveNewIE._extract_urls(webpage)
  1453. if bc_urls:
  1454. return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
  1455. # Look for ThePlatform embeds
  1456. tp_urls = ThePlatformIE._extract_urls(webpage)
  1457. if tp_urls:
  1458. return _playlist_from_matches(tp_urls, ie='ThePlatform')
  1459. # Look for embedded rtl.nl player
  1460. matches = re.findall(
  1461. r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
  1462. webpage)
  1463. if matches:
  1464. return _playlist_from_matches(matches, ie='RtlNl')
  1465. vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
  1466. if vimeo_url is not None:
  1467. return self.url_result(vimeo_url)
  1468. vid_me_embed_url = self._search_regex(
  1469. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  1470. webpage, 'vid.me embed', default=None)
  1471. if vid_me_embed_url is not None:
  1472. return self.url_result(vid_me_embed_url, 'Vidme')
  1473. # Look for embedded YouTube player
  1474. matches = re.findall(r'''(?x)
  1475. (?:
  1476. <iframe[^>]+?src=|
  1477. data-video-url=|
  1478. <embed[^>]+?src=|
  1479. embedSWF\(?:\s*|
  1480. new\s+SWFObject\(
  1481. )
  1482. (["\'])
  1483. (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
  1484. (?:embed|v|p)/.+?)
  1485. \1''', webpage)
  1486. if matches:
  1487. return _playlist_from_matches(
  1488. matches, lambda m: unescapeHTML(m[1]))
  1489. # Look for lazyYT YouTube embed
  1490. matches = re.findall(
  1491. r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
  1492. if matches:
  1493. return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
  1494. # Look for embedded Dailymotion player
  1495. matches = re.findall(
  1496. r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
  1497. if matches:
  1498. return _playlist_from_matches(
  1499. matches, lambda m: unescapeHTML(m[1]))
  1500. # Look for embedded Dailymotion playlist player (#3822)
  1501. m = re.search(
  1502. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  1503. if m:
  1504. playlists = re.findall(
  1505. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  1506. if playlists:
  1507. return _playlist_from_matches(
  1508. playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
  1509. # Look for embedded Wistia player
  1510. match = re.search(
  1511. r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
  1512. if match:
  1513. embed_url = self._proto_relative_url(
  1514. unescapeHTML(match.group('url')))
  1515. return {
  1516. '_type': 'url_transparent',
  1517. 'url': embed_url,
  1518. 'ie_key': 'Wistia',
  1519. 'uploader': video_uploader,
  1520. }
  1521. match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
  1522. if match:
  1523. return {
  1524. '_type': 'url_transparent',
  1525. 'url': 'wistia:%s' % match.group('id'),
  1526. 'ie_key': 'Wistia',
  1527. 'uploader': video_uploader,
  1528. }
  1529. match = re.search(
  1530. r'''(?sx)
  1531. <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
  1532. <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
  1533. ''', webpage)
  1534. if match:
  1535. return self.url_result(self._proto_relative_url(
  1536. 'wistia:%s' % match.group('id')), 'Wistia')
  1537. # Look for SVT player
  1538. svt_url = SVTIE._extract_url(webpage)
  1539. if svt_url:
  1540. return self.url_result(svt_url, 'SVT')
  1541. # Look for embedded condenast player
  1542. matches = re.findall(
  1543. r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
  1544. webpage)
  1545. if matches:
  1546. return {
  1547. '_type': 'playlist',
  1548. 'entries': [{
  1549. '_type': 'url',
  1550. 'ie_key': 'CondeNast',
  1551. 'url': ma,
  1552. } for ma in matches],
  1553. 'title': video_title,
  1554. 'id': video_id,
  1555. }
  1556. # Look for Bandcamp pages with custom domain
  1557. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  1558. if mobj is not None:
  1559. burl = unescapeHTML(mobj.group(1))
  1560. # Don't set the extractor because it can be a track url or an album
  1561. return self.url_result(burl)
  1562. # Look for embedded Vevo player
  1563. mobj = re.search(
  1564. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  1565. if mobj is not None:
  1566. return self.url_result(mobj.group('url'))
  1567. # Look for embedded Viddler player
  1568. mobj = re.search(
  1569. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  1570. webpage)
  1571. if mobj is not None:
  1572. return self.url_result(mobj.group('url'))
  1573. # Look for NYTimes player
  1574. mobj = re.search(
  1575. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  1576. webpage)
  1577. if mobj is not None:
  1578. return self.url_result(mobj.group('url'))
  1579. # Look for Libsyn player
  1580. mobj = re.search(
  1581. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  1582. if mobj is not None:
  1583. return self.url_result(mobj.group('url'))
  1584. # Look for Ooyala videos
  1585. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
  1586. re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
  1587. re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
  1588. re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  1589. if mobj is not None:
  1590. return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
  1591. # Look for multiple Ooyala embeds on SBN network websites
  1592. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  1593. if mobj is not None:
  1594. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  1595. if embeds:
  1596. return _playlist_from_matches(
  1597. embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  1598. # Look for Aparat videos
  1599. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  1600. if mobj is not None:
  1601. return self.url_result(mobj.group(1), 'Aparat')
  1602. # Look for MPORA videos
  1603. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  1604. if mobj is not None:
  1605. return self.url_result(mobj.group(1), 'Mpora')
  1606. # Look for embedded NovaMov-based player
  1607. mobj = re.search(
  1608. r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
  1609. (?P<url>http://(?:(?:embed|www)\.)?
  1610. (?:novamov\.com|
  1611. nowvideo\.(?:ch|sx|eu|at|ag|co)|
  1612. videoweed\.(?:es|com)|
  1613. movshare\.(?:net|sx|ag)|
  1614. divxstage\.(?:eu|net|ch|co|at|ag))
  1615. /embed\.php.+?)\1''', webpage)
  1616. if mobj is not None:
  1617. return self.url_result(mobj.group('url'))
  1618. # Look for embedded Facebook player
  1619. mobj = re.search(
  1620. r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
  1621. if mobj is not None:
  1622. return self.url_result(mobj.group('url'), 'Facebook')
  1623. # Look for embedded VK player
  1624. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  1625. if mobj is not None:
  1626. return self.url_result(mobj.group('url'), 'VK')
  1627. # Look for embedded Odnoklassniki player
  1628. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
  1629. if mobj is not None:
  1630. return self.url_result(mobj.group('url'), 'Odnoklassniki')
  1631. # Look for embedded ivi player
  1632. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  1633. if mobj is not None:
  1634. return self.url_result(mobj.group('url'), 'Ivi')
  1635. # Look for embedded Huffington Post player
  1636. mobj = re.search(
  1637. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  1638. if mobj is not None:
  1639. return self.url_result(mobj.group('url'), 'HuffPost')
  1640. # Look for embed.ly
  1641. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  1642. if mobj is not None:
  1643. return self.url_result(mobj.group('url'))
  1644. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  1645. if mobj is not None:
  1646. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  1647. # Look for funnyordie embed
  1648. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  1649. if matches:
  1650. return _playlist_from_matches(
  1651. matches, getter=unescapeHTML, ie='FunnyOrDie')
  1652. # Look for BBC iPlayer embed
  1653. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  1654. if matches:
  1655. return _playlist_from_matches(matches, ie='BBCCoUk')
  1656. # Look for embedded RUTV player
  1657. rutv_url = RUTVIE._extract_url(webpage)
  1658. if rutv_url:
  1659. return self.url_result(rutv_url, 'RUTV')
  1660. # Look for embedded TVC player
  1661. tvc_url = TVCIE._extract_url(webpage)
  1662. if tvc_url:
  1663. return self.url_result(tvc_url, 'TVC')
  1664. # Look for embedded SportBox player
  1665. sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
  1666. if sportbox_urls:
  1667. return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
  1668. # Look for embedded PornHub player
  1669. pornhub_url = PornHubIE._extract_url(webpage)
  1670. if pornhub_url:
  1671. return self.url_result(pornhub_url, 'PornHub')
  1672. # Look for embedded XHamster player
  1673. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  1674. if xhamster_urls:
  1675. return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
  1676. # Look for embedded TNAFlixNetwork player
  1677. tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
  1678. if tnaflix_urls:
  1679. return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
  1680. # Look for embedded Tvigle player
  1681. mobj = re.search(
  1682. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  1683. if mobj is not None:
  1684. return self.url_result(mobj.group('url'), 'Tvigle')
  1685. # Look for embedded TED player
  1686. mobj = re.search(
  1687. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  1688. if mobj is not None:
  1689. return self.url_result(mobj.group('url'), 'TED')
  1690. # Look for embedded Ustream videos
  1691. mobj = re.search(
  1692. r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
  1693. if mobj is not None:
  1694. return self.url_result(mobj.group('url'), 'Ustream')
  1695. # Look for embedded arte.tv player
  1696. mobj = re.search(
  1697. r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
  1698. webpage)
  1699. if mobj is not None:
  1700. return self.url_result(mobj.group('url'), 'ArteTVEmbed')
  1701. # Look for embedded francetv player
  1702. mobj = re.search(
  1703. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  1704. webpage)
  1705. if mobj is not None:
  1706. return self.url_result(mobj.group('url'))
  1707. # Look for embedded smotri.com player
  1708. smotri_url = SmotriIE._extract_url(webpage)
  1709. if smotri_url:
  1710. return self.url_result(smotri_url, 'Smotri')
  1711. # Look for embedded Myvi.ru player
  1712. myvi_url = MyviIE._extract_url(webpage)
  1713. if myvi_url:
  1714. return self.url_result(myvi_url)
  1715. # Look for embedded soundcloud player
  1716. mobj = re.search(
  1717. r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
  1718. webpage)
  1719. if mobj is not None:
  1720. url = unescapeHTML(mobj.group('url'))
  1721. return self.url_result(url)
  1722. # Look for embedded vulture.com player
  1723. mobj = re.search(
  1724. r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
  1725. webpage)
  1726. if mobj is not None:
  1727. url = unescapeHTML(mobj.group('url'))
  1728. return self.url_result(url, ie='Vulture')
  1729. # Look for embedded mtvservices player
  1730. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  1731. if mtvservices_url:
  1732. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  1733. # Look for embedded yahoo player
  1734. mobj = re.search(
  1735. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  1736. webpage)
  1737. if mobj is not None:
  1738. return self.url_result(mobj.group('url'), 'Yahoo')
  1739. # Look for embedded sbs.com.au player
  1740. mobj = re.search(
  1741. r'''(?x)
  1742. (?:
  1743. <meta\s+property="og:video"\s+content=|
  1744. <iframe[^>]+?src=
  1745. )
  1746. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  1747. webpage)
  1748. if mobj is not None:
  1749. return self.url_result(mobj.group('url'), 'SBS')
  1750. # Look for embedded Cinchcast player
  1751. mobj = re.search(
  1752. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  1753. webpage)
  1754. if mobj is not None:
  1755. return self.url_result(mobj.group('url'), 'Cinchcast')
  1756. mobj = re.search(
  1757. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  1758. webpage)
  1759. if not mobj:
  1760. mobj = re.search(
  1761. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  1762. webpage)
  1763. if mobj is not None:
  1764. return self.url_result(mobj.group('url'), 'MLB')
  1765. mobj = re.search(
  1766. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  1767. webpage)
  1768. if mobj is not None:
  1769. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  1770. mobj = re.search(
  1771. r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
  1772. webpage)
  1773. if mobj is not None:
  1774. return self.url_result(mobj.group('url'), 'Livestream')
  1775. # Look for Zapiks embed
  1776. mobj = re.search(
  1777. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  1778. if mobj is not None:
  1779. return self.url_result(mobj.group('url'), 'Zapiks')
  1780. # Look for Kaltura embeds
  1781. mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
  1782. 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))
  1783. if mobj is not None:
  1784. return self.url_result(smuggle_url(
  1785. 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
  1786. {'source_url': url}), 'Kaltura')
  1787. # Look for Eagle.Platform embeds
  1788. mobj = re.search(
  1789. r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
  1790. if mobj is not None:
  1791. return self.url_result(mobj.group('url'), 'EaglePlatform')
  1792. # Look for ClipYou (uses Eagle.Platform) embeds
  1793. mobj = re.search(
  1794. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  1795. if mobj is not None:
  1796. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  1797. # Look for Pladform embeds
  1798. pladform_url = PladformIE._extract_url(webpage)
  1799. if pladform_url:
  1800. return self.url_result(pladform_url)
  1801. # Look for Videomore embeds
  1802. videomore_url = VideomoreIE._extract_url(webpage)
  1803. if videomore_url:
  1804. return self.url_result(videomore_url)
  1805. # Look for Playwire embeds
  1806. mobj = re.search(
  1807. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  1808. if mobj is not None:
  1809. return self.url_result(mobj.group('url'))
  1810. # Look for 5min embeds
  1811. mobj = re.search(
  1812. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  1813. if mobj is not None:
  1814. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  1815. # Look for Crooks and Liars embeds
  1816. mobj = re.search(
  1817. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  1818. if mobj is not None:
  1819. return self.url_result(mobj.group('url'))
  1820. # Look for NBC Sports VPlayer embeds
  1821. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  1822. if nbc_sports_url:
  1823. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  1824. # Look for Google Drive embeds
  1825. google_drive_url = GoogleDriveIE._extract_url(webpage)
  1826. if google_drive_url:
  1827. return self.url_result(google_drive_url, 'GoogleDrive')
  1828. # Look for UDN embeds
  1829. mobj = re.search(
  1830. r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  1831. if mobj is not None:
  1832. return self.url_result(
  1833. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  1834. # Look for Senate ISVP iframe
  1835. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  1836. if senate_isvp_url:
  1837. return self.url_result(senate_isvp_url, 'SenateISVP')
  1838. # Look for Dailymotion Cloud videos
  1839. dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
  1840. if dmcloud_url:
  1841. return self.url_result(dmcloud_url, 'DailymotionCloud')
  1842. # Look for OnionStudios embeds
  1843. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  1844. if onionstudios_url:
  1845. return self.url_result(onionstudios_url)
  1846. # Look for ViewLift embeds
  1847. viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
  1848. if viewlift_url:
  1849. return self.url_result(viewlift_url)
  1850. # Look for JWPlatform embeds
  1851. jwplatform_url = JWPlatformIE._extract_url(webpage)
  1852. if jwplatform_url:
  1853. return self.url_result(jwplatform_url, 'JWPlatform')
  1854. # Look for ScreenwaveMedia embeds
  1855. mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
  1856. if mobj is not None:
  1857. return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
  1858. # Look for Digiteka embeds
  1859. digiteka_url = DigitekaIE._extract_url(webpage)
  1860. if digiteka_url:
  1861. return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
  1862. # Look for Limelight embeds
  1863. mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
  1864. if mobj:
  1865. lm = {
  1866. 'Media': 'media',
  1867. 'Channel': 'channel',
  1868. 'ChannelList': 'channel_list',
  1869. }
  1870. return self.url_result('limelight:%s:%s' % (
  1871. lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
  1872. # Look for AdobeTVVideo embeds
  1873. mobj = re.search(
  1874. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  1875. webpage)
  1876. if mobj is not None:
  1877. return self.url_result(
  1878. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  1879. 'AdobeTVVideo')
  1880. # Look for Vine embeds
  1881. mobj = re.search(
  1882. r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
  1883. webpage)
  1884. if mobj is not None:
  1885. return self.url_result(
  1886. self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
  1887. # Look for Instagram embeds
  1888. instagram_embed_url = InstagramIE._extract_embed_url(webpage)
  1889. if instagram_embed_url is not None:
  1890. return self.url_result(
  1891. self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
  1892. # Look for LiveLeak embeds
  1893. liveleak_url = LiveLeakIE._extract_url(webpage)
  1894. if liveleak_url:
  1895. return self.url_result(liveleak_url, 'LiveLeak')
  1896. # Look for 3Q SDN embeds
  1897. threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
  1898. if threeqsdn_url:
  1899. return {
  1900. '_type': 'url_transparent',
  1901. 'ie_key': ThreeQSDNIE.ie_key(),
  1902. 'url': self._proto_relative_url(threeqsdn_url),
  1903. 'title': video_title,
  1904. 'description': video_description,
  1905. 'thumbnail': video_thumbnail,
  1906. 'uploader': video_uploader,
  1907. }
  1908. def check_video(vurl):
  1909. if YoutubeIE.suitable(vurl):
  1910. return True
  1911. vpath = compat_urlparse.urlparse(vurl).path
  1912. vext = determine_ext(vpath)
  1913. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
  1914. def filter_video(urls):
  1915. return list(filter(check_video, urls))
  1916. # Start with something easy: JW Player in SWFObject
  1917. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  1918. if not found:
  1919. # Look for gorilla-vid style embedding
  1920. found = filter_video(re.findall(r'''(?sx)
  1921. (?:
  1922. jw_plugins|
  1923. JWPlayerOptions|
  1924. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  1925. )
  1926. .*?
  1927. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  1928. if not found:
  1929. # Broaden the search a little bit
  1930. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  1931. if not found:
  1932. # Broaden the findall a little bit: JWPlayer JS loader
  1933. found = filter_video(re.findall(
  1934. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  1935. if not found:
  1936. # Flow player
  1937. found = filter_video(re.findall(r'''(?xs)
  1938. flowplayer\("[^"]+",\s*
  1939. \{[^}]+?\}\s*,
  1940. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  1941. ["']?url["']?\s*:\s*["']([^"']+)["']
  1942. ''', webpage))
  1943. if not found:
  1944. # Cinerama player
  1945. found = re.findall(
  1946. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  1947. if not found:
  1948. # Try to find twitter cards info
  1949. found = filter_video(re.findall(
  1950. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  1951. if not found:
  1952. # We look for Open Graph info:
  1953. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  1954. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  1955. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  1956. if m_video_type is not None:
  1957. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  1958. if not found:
  1959. # HTML5 video
  1960. found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
  1961. if not found:
  1962. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  1963. found = re.search(
  1964. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  1965. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  1966. webpage)
  1967. if not found:
  1968. # Look also in Refresh HTTP header
  1969. refresh_header = head_response.headers.get('Refresh')
  1970. if refresh_header:
  1971. # In python 2 response HTTP headers are bytestrings
  1972. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  1973. refresh_header = refresh_header.decode('iso-8859-1')
  1974. found = re.search(REDIRECT_REGEX, refresh_header)
  1975. if found:
  1976. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  1977. self.report_following_redirect(new_url)
  1978. return {
  1979. '_type': 'url',
  1980. 'url': new_url,
  1981. }
  1982. if not found:
  1983. raise UnsupportedError(url)
  1984. entries = []
  1985. for video_url in found:
  1986. video_url = unescapeHTML(video_url)
  1987. video_url = video_url.replace('\\/', '/')
  1988. video_url = compat_urlparse.urljoin(url, video_url)
  1989. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  1990. # Sometimes, jwplayer extraction will result in a YouTube URL
  1991. if YoutubeIE.suitable(video_url):
  1992. entries.append(self.url_result(video_url, 'Youtube'))
  1993. continue
  1994. # here's a fun little line of code for you:
  1995. video_id = os.path.splitext(video_id)[0]
  1996. entry_info_dict = {
  1997. 'id': video_id,
  1998. 'uploader': video_uploader,
  1999. 'title': video_title,
  2000. 'age_limit': age_limit,
  2001. }
  2002. ext = determine_ext(video_url)
  2003. if ext == 'smil':
  2004. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  2005. elif ext == 'xspf':
  2006. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  2007. elif ext == 'm3u8':
  2008. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  2009. elif ext == 'mpd':
  2010. entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
  2011. elif ext == 'f4m':
  2012. entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
  2013. else:
  2014. entry_info_dict['url'] = video_url
  2015. if entry_info_dict.get('formats'):
  2016. self._sort_formats(entry_info_dict['formats'])
  2017. entries.append(entry_info_dict)
  2018. if len(entries) == 1:
  2019. return entries[0]
  2020. else:
  2021. for num, e in enumerate(entries, start=1):
  2022. # 'url' results don't have a title
  2023. if e.get('title') is not None:
  2024. e['title'] = '%s (%d)' % (e['title'], num)
  2025. return {
  2026. '_type': 'playlist',
  2027. 'entries': entries,
  2028. }