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.

2275 lines
91 KiB

10 years ago
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
10 years ago
10 years ago
10 years ago
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
10 years ago
10 years ago
  1. # encoding: utf-8
  2. from __future__ import unicode_literals
  3. import os
  4. import re
  5. import sys
  6. from .common import InfoExtractor
  7. from .youtube import YoutubeIE
  8. from ..compat import (
  9. compat_etree_fromstring,
  10. compat_urllib_parse_unquote,
  11. compat_urlparse,
  12. compat_xml_parse_error,
  13. )
  14. from ..utils import (
  15. determine_ext,
  16. ExtractorError,
  17. float_or_none,
  18. HEADRequest,
  19. is_html,
  20. orderedSet,
  21. sanitized_Request,
  22. smuggle_url,
  23. unescapeHTML,
  24. unified_strdate,
  25. unsmuggle_url,
  26. UnsupportedError,
  27. url_basename,
  28. xpath_text,
  29. )
  30. from .brightcove import (
  31. BrightcoveLegacyIE,
  32. BrightcoveNewIE,
  33. )
  34. from .nbc import NBCSportsVPlayerIE
  35. from .ooyala import OoyalaIE
  36. from .rutv import RUTVIE
  37. from .tvc import TVCIE
  38. from .sportbox import SportBoxEmbedIE
  39. from .smotri import SmotriIE
  40. from .myvi import MyviIE
  41. from .condenast import CondeNastIE
  42. from .udn import UDNEmbedIE
  43. from .senateisvp import SenateISVPIE
  44. from .svt import SVTIE
  45. from .pornhub import PornHubIE
  46. from .xhamster import XHamsterEmbedIE
  47. from .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. from .vessel import VesselIE
  64. from .kaltura import KalturaIE
  65. from .eagleplatform import EaglePlatformIE
  66. from .facebook import FacebookIE
  67. class GenericIE(InfoExtractor):
  68. IE_DESC = 'Generic downloader that works on some sites'
  69. _VALID_URL = r'.*'
  70. IE_NAME = 'generic'
  71. _TESTS = [
  72. # Direct link to a video
  73. {
  74. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  75. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  76. 'info_dict': {
  77. 'id': 'trailer',
  78. 'ext': 'mp4',
  79. 'title': 'trailer',
  80. 'upload_date': '20100513',
  81. }
  82. },
  83. # Direct link to media delivered compressed (until Accept-Encoding is *)
  84. {
  85. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  86. 'md5': '128c42e68b13950268b648275386fc74',
  87. 'info_dict': {
  88. 'id': 'FictionJunction-Parallel_Hearts',
  89. 'ext': 'flac',
  90. 'title': 'FictionJunction-Parallel_Hearts',
  91. 'upload_date': '20140522',
  92. },
  93. 'expected_warnings': [
  94. 'URL could be a direct video link, returning it as such.'
  95. ]
  96. },
  97. # Direct download with broken HEAD
  98. {
  99. 'url': 'http://ai-radio.org:8000/radio.opus',
  100. 'info_dict': {
  101. 'id': 'radio',
  102. 'ext': 'opus',
  103. 'title': 'radio',
  104. },
  105. 'params': {
  106. 'skip_download': True, # infinite live stream
  107. },
  108. 'expected_warnings': [
  109. r'501.*Not Implemented',
  110. r'400.*Bad Request',
  111. ],
  112. },
  113. # Direct link with incorrect MIME type
  114. {
  115. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  116. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  117. 'info_dict': {
  118. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  119. 'id': '5_Lennart_Poettering_-_Systemd',
  120. 'ext': 'webm',
  121. 'title': '5_Lennart_Poettering_-_Systemd',
  122. 'upload_date': '20141120',
  123. },
  124. 'expected_warnings': [
  125. 'URL could be a direct video link, returning it as such.'
  126. ]
  127. },
  128. # RSS feed
  129. {
  130. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  131. 'info_dict': {
  132. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  133. 'title': 'Zero Punctuation',
  134. 'description': 're:.*groundbreaking video review series.*'
  135. },
  136. 'playlist_mincount': 11,
  137. },
  138. # RSS feed with enclosure
  139. {
  140. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  141. 'info_dict': {
  142. 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  143. 'ext': 'm4v',
  144. 'upload_date': '20150228',
  145. 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  146. }
  147. },
  148. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  149. {
  150. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  151. 'info_dict': {
  152. 'id': 'smil',
  153. 'ext': 'mp4',
  154. 'title': 'Automatics, robotics and biocybernetics',
  155. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  156. 'upload_date': '20130627',
  157. 'formats': 'mincount:16',
  158. 'subtitles': 'mincount:1',
  159. },
  160. 'params': {
  161. 'force_generic_extractor': True,
  162. 'skip_download': True,
  163. },
  164. },
  165. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  166. {
  167. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  168. 'info_dict': {
  169. 'id': 'hds',
  170. 'ext': 'flv',
  171. 'title': 'hds',
  172. 'formats': 'mincount:1',
  173. },
  174. 'params': {
  175. 'skip_download': True,
  176. },
  177. },
  178. # SMIL from https://www.restudy.dk/video/play/id/1637
  179. {
  180. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  181. 'info_dict': {
  182. 'id': 'video_1637',
  183. 'ext': 'flv',
  184. 'title': 'video_1637',
  185. 'formats': 'mincount:3',
  186. },
  187. 'params': {
  188. 'skip_download': True,
  189. },
  190. },
  191. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  192. {
  193. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  194. 'info_dict': {
  195. 'id': 'smil-service',
  196. 'ext': 'flv',
  197. 'title': 'smil-service',
  198. 'formats': 'mincount:1',
  199. },
  200. 'params': {
  201. 'skip_download': True,
  202. },
  203. },
  204. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  205. {
  206. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  207. 'info_dict': {
  208. 'id': '4719370',
  209. 'ext': 'mp4',
  210. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  211. 'formats': 'mincount:3',
  212. },
  213. 'params': {
  214. 'skip_download': True,
  215. },
  216. },
  217. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  218. {
  219. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  220. 'info_dict': {
  221. 'id': 'mZlp2ctYIUEB',
  222. 'ext': 'mp4',
  223. 'title': 'Tikibad ontruimd wegens brand',
  224. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  225. 'thumbnail': 're:^https?://.*\.jpg$',
  226. 'duration': 33,
  227. },
  228. 'params': {
  229. 'skip_download': True,
  230. },
  231. },
  232. # MPD from http://dash-mse-test.appspot.com/media.html
  233. {
  234. 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
  235. 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
  236. 'info_dict': {
  237. 'id': 'car-20120827-manifest',
  238. 'ext': 'mp4',
  239. 'title': 'car-20120827-manifest',
  240. 'formats': 'mincount:9',
  241. 'upload_date': '20130904',
  242. },
  243. 'params': {
  244. 'format': 'bestvideo',
  245. },
  246. },
  247. # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
  248. {
  249. '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',
  250. 'info_dict': {
  251. 'id': 'content',
  252. 'ext': 'mp4',
  253. 'title': 'content',
  254. 'formats': 'mincount:8',
  255. },
  256. 'params': {
  257. # m3u8 downloads
  258. 'skip_download': True,
  259. }
  260. },
  261. # m3u8 served with Content-Type: text/plain
  262. {
  263. 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
  264. 'info_dict': {
  265. 'id': 'index',
  266. 'ext': 'mp4',
  267. 'title': 'index',
  268. 'upload_date': '20140720',
  269. 'formats': 'mincount:11',
  270. },
  271. 'params': {
  272. # m3u8 downloads
  273. 'skip_download': True,
  274. }
  275. },
  276. # google redirect
  277. {
  278. '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',
  279. 'info_dict': {
  280. 'id': 'cmQHVoWB5FY',
  281. 'ext': 'mp4',
  282. 'upload_date': '20130224',
  283. 'uploader_id': 'TheVerge',
  284. 'description': 're:^Chris Ziegler takes a look at the\.*',
  285. 'uploader': 'The Verge',
  286. 'title': 'First Firefox OS phones side-by-side',
  287. },
  288. 'params': {
  289. 'skip_download': False,
  290. }
  291. },
  292. {
  293. # redirect in Refresh HTTP header
  294. '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',
  295. 'info_dict': {
  296. 'id': 'pO8h3EaFRdo',
  297. 'ext': 'mp4',
  298. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  299. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  300. 'upload_date': '20150917',
  301. 'uploader_id': 'brtvofficial',
  302. 'uploader': 'Boiler Room',
  303. },
  304. 'params': {
  305. 'skip_download': False,
  306. },
  307. },
  308. {
  309. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  310. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  311. 'info_dict': {
  312. 'id': '13601338388002',
  313. 'ext': 'mp4',
  314. 'uploader': 'www.hodiho.fr',
  315. 'title': 'R\u00e9gis plante sa Jeep',
  316. }
  317. },
  318. # bandcamp page with custom domain
  319. {
  320. 'add_ie': ['Bandcamp'],
  321. 'url': 'http://bronyrock.com/track/the-pony-mash',
  322. 'info_dict': {
  323. 'id': '3235767654',
  324. 'ext': 'mp3',
  325. 'title': 'The Pony Mash',
  326. 'uploader': 'M_Pallante',
  327. },
  328. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  329. },
  330. # embedded brightcove video
  331. # it also tests brightcove videos that need to set the 'Referer' in the
  332. # http requests
  333. {
  334. 'add_ie': ['BrightcoveLegacy'],
  335. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  336. 'info_dict': {
  337. 'id': '2765128793001',
  338. 'ext': 'mp4',
  339. 'title': 'Le cours de bourse : l’analyse technique',
  340. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  341. 'uploader': 'BFM BUSINESS',
  342. },
  343. 'params': {
  344. 'skip_download': True,
  345. },
  346. },
  347. {
  348. # https://github.com/rg3/youtube-dl/issues/2253
  349. 'url': 'http://bcove.me/i6nfkrc3',
  350. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  351. 'info_dict': {
  352. 'id': '3101154703001',
  353. 'ext': 'mp4',
  354. 'title': 'Still no power',
  355. 'uploader': 'thestar.com',
  356. '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.',
  357. },
  358. 'add_ie': ['BrightcoveLegacy'],
  359. },
  360. {
  361. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  362. 'md5': 'fb973ecf6e4a78a67453647444222983',
  363. 'info_dict': {
  364. 'id': '3414141473001',
  365. 'ext': 'mp4',
  366. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  367. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  368. 'uploader': 'Championat',
  369. },
  370. },
  371. {
  372. # https://github.com/rg3/youtube-dl/issues/3541
  373. 'add_ie': ['BrightcoveLegacy'],
  374. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  375. 'info_dict': {
  376. 'id': '3866516442001',
  377. 'ext': 'mp4',
  378. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  379. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  380. 'uploader': 'SBS Broadcasting',
  381. },
  382. 'skip': 'Restricted to Netherlands',
  383. 'params': {
  384. 'skip_download': True, # m3u8 download
  385. },
  386. },
  387. # ooyala video
  388. {
  389. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  390. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  391. 'info_dict': {
  392. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  393. 'ext': 'mp4',
  394. 'title': '2cc213299525360.mov', # that's what we get
  395. 'duration': 238.231,
  396. },
  397. 'add_ie': ['Ooyala'],
  398. },
  399. {
  400. # ooyala video embedded with http://player.ooyala.com/iframe.js
  401. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  402. 'info_dict': {
  403. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  404. 'ext': 'mp4',
  405. 'title': '"Steve Jobs: Man in the Machine" trailer',
  406. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  407. 'duration': 135.427,
  408. },
  409. 'params': {
  410. 'skip_download': True,
  411. },
  412. },
  413. # embed.ly video
  414. {
  415. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  416. 'info_dict': {
  417. 'id': '9ODmcdjQcHQ',
  418. 'ext': 'mp4',
  419. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  420. 'upload_date': '20140225',
  421. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  422. 'uploader': 'Tested',
  423. 'uploader_id': 'testedcom',
  424. },
  425. # No need to test YoutubeIE here
  426. 'params': {
  427. 'skip_download': True,
  428. },
  429. },
  430. # funnyordie embed
  431. {
  432. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  433. 'info_dict': {
  434. 'id': '18e820ec3f',
  435. 'ext': 'mp4',
  436. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  437. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  438. },
  439. },
  440. # RUTV embed
  441. {
  442. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  443. 'info_dict': {
  444. 'id': '776940',
  445. 'ext': 'mp4',
  446. 'title': 'Охотское море стало целиком российским',
  447. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  448. },
  449. 'params': {
  450. # m3u8 download
  451. 'skip_download': True,
  452. },
  453. },
  454. # TVC embed
  455. {
  456. '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/',
  457. 'info_dict': {
  458. 'id': '55304',
  459. 'ext': 'mp4',
  460. 'title': 'Дошкольное воспитание',
  461. },
  462. },
  463. # SportBox embed
  464. {
  465. 'url': 'http://www.vestifinance.ru/articles/25753',
  466. 'info_dict': {
  467. 'id': '25753',
  468. 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  469. },
  470. 'playlist': [{
  471. 'info_dict': {
  472. 'id': '370908',
  473. 'title': 'Госзаказ. День 3',
  474. 'ext': 'mp4',
  475. }
  476. }, {
  477. 'info_dict': {
  478. 'id': '370905',
  479. 'title': 'Госзаказ. День 2',
  480. 'ext': 'mp4',
  481. }
  482. }, {
  483. 'info_dict': {
  484. 'id': '370902',
  485. 'title': 'Госзаказ. День 1',
  486. 'ext': 'mp4',
  487. }
  488. }],
  489. 'params': {
  490. # m3u8 download
  491. 'skip_download': True,
  492. },
  493. },
  494. # Myvi.ru embed
  495. {
  496. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  497. 'info_dict': {
  498. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  499. 'ext': 'mp4',
  500. 'title': 'Ужастики, русский трейлер (2015)',
  501. 'thumbnail': 're:^https?://.*\.jpg$',
  502. 'duration': 153,
  503. }
  504. },
  505. # XHamster embed
  506. {
  507. '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',
  508. 'info_dict': {
  509. 'id': 'showthread',
  510. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  511. },
  512. 'playlist_mincount': 7,
  513. },
  514. # Embedded TED video
  515. {
  516. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  517. 'md5': '65fdff94098e4a607385a60c5177c638',
  518. 'info_dict': {
  519. 'id': '1969',
  520. 'ext': 'mp4',
  521. 'title': 'Hidden miracles of the natural world',
  522. 'uploader': 'Louie Schwartzberg',
  523. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  524. }
  525. },
  526. # Embedded Ustream video
  527. {
  528. 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
  529. 'md5': '27b99cdb639c9b12a79bca876a073417',
  530. 'info_dict': {
  531. 'id': '45734260',
  532. 'ext': 'flv',
  533. 'uploader': 'AU SPA: The NSA and Privacy',
  534. 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
  535. }
  536. },
  537. # nowvideo embed hidden behind percent encoding
  538. {
  539. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  540. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  541. 'info_dict': {
  542. 'id': '06e53103ca9aa',
  543. 'ext': 'flv',
  544. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  545. 'description': 'No description',
  546. },
  547. },
  548. # arte embed
  549. {
  550. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  551. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  552. 'info_dict': {
  553. 'id': '048195-004_PLUS7-F',
  554. 'ext': 'flv',
  555. 'title': 'X:enius',
  556. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  557. 'upload_date': '20140320',
  558. },
  559. 'params': {
  560. 'skip_download': 'Requires rtmpdump'
  561. }
  562. },
  563. # francetv embed
  564. {
  565. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  566. 'info_dict': {
  567. 'id': 'EV_30231',
  568. 'ext': 'mp4',
  569. 'title': 'Alcaline, le concert avec Calogero',
  570. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  571. 'upload_date': '20150226',
  572. 'timestamp': 1424989860,
  573. 'duration': 5400,
  574. },
  575. 'params': {
  576. # m3u8 downloads
  577. 'skip_download': True,
  578. },
  579. 'expected_warnings': [
  580. 'Forbidden'
  581. ]
  582. },
  583. # Condé Nast embed
  584. {
  585. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  586. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  587. 'info_dict': {
  588. 'id': '53501be369702d3275860000',
  589. 'ext': 'mp4',
  590. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  591. }
  592. },
  593. # Dailymotion embed
  594. {
  595. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  596. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  597. 'info_dict': {
  598. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  599. 'ext': 'mp4',
  600. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  601. 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
  602. 'uploader': 'Spi0n',
  603. 'uploader_id': 'xgditw',
  604. 'upload_date': '20140425',
  605. 'timestamp': 1398441542,
  606. },
  607. 'add_ie': ['Dailymotion'],
  608. },
  609. # YouTube embed
  610. {
  611. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  612. 'info_dict': {
  613. 'id': 'FXRb4ykk4S0',
  614. 'ext': 'mp4',
  615. 'title': 'The NBL Auction 2014',
  616. 'uploader': 'BADMINTON England',
  617. 'uploader_id': 'BADMINTONEvents',
  618. 'upload_date': '20140603',
  619. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  620. },
  621. 'add_ie': ['Youtube'],
  622. 'params': {
  623. 'skip_download': True,
  624. }
  625. },
  626. # MTVSercices embed
  627. {
  628. 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
  629. 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
  630. 'info_dict': {
  631. 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
  632. 'ext': 'mp4',
  633. 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
  634. 'description': 'Two valets share their love for movie star Liam Neesons.',
  635. },
  636. },
  637. # YouTube embed via <data-embed-url="">
  638. {
  639. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  640. 'info_dict': {
  641. 'id': '4vAffPZIT44',
  642. 'ext': 'mp4',
  643. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  644. 'uploader': 'Gameloft',
  645. 'uploader_id': 'gameloft',
  646. 'upload_date': '20140828',
  647. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  648. },
  649. 'params': {
  650. 'skip_download': True,
  651. }
  652. },
  653. # Camtasia studio
  654. {
  655. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  656. 'playlist': [{
  657. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  658. 'info_dict': {
  659. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  660. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  661. 'ext': 'flv',
  662. 'duration': 2235.90,
  663. }
  664. }, {
  665. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  666. 'info_dict': {
  667. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  668. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  669. 'ext': 'flv',
  670. 'duration': 2235.93,
  671. }
  672. }],
  673. 'info_dict': {
  674. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  675. }
  676. },
  677. # Flowplayer
  678. {
  679. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  680. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  681. 'info_dict': {
  682. 'id': '5123ea6d5e5a7',
  683. 'ext': 'mp4',
  684. 'age_limit': 18,
  685. 'uploader': 'www.handjobhub.com',
  686. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  687. }
  688. },
  689. # Multiple brightcove videos
  690. # https://github.com/rg3/youtube-dl/issues/2283
  691. {
  692. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  693. 'info_dict': {
  694. 'id': 'always-never',
  695. 'title': 'Always / Never - The New Yorker',
  696. },
  697. 'playlist_count': 3,
  698. 'params': {
  699. 'extract_flat': False,
  700. 'skip_download': True,
  701. }
  702. },
  703. # MLB embed
  704. {
  705. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  706. 'md5': '96f09a37e44da40dd083e12d9a683327',
  707. 'info_dict': {
  708. 'id': '33322633',
  709. 'ext': 'mp4',
  710. 'title': 'Ump changes call to ball',
  711. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  712. 'duration': 48,
  713. 'timestamp': 1401537900,
  714. 'upload_date': '20140531',
  715. 'thumbnail': 're:^https?://.*\.jpg$',
  716. },
  717. },
  718. # Wistia embed
  719. {
  720. 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  721. 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
  722. 'info_dict': {
  723. 'id': '6e2wtrbdaf',
  724. 'ext': 'mov',
  725. 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
  726. 'description': 'a Paywall Videos video from Remilon',
  727. 'duration': 644.072,
  728. 'uploader': 'study.com',
  729. 'timestamp': 1459678540,
  730. 'upload_date': '20160403',
  731. 'filesize': 24687186,
  732. },
  733. },
  734. {
  735. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  736. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  737. 'info_dict': {
  738. 'id': 'uxjb0lwrcz',
  739. 'ext': 'mp4',
  740. 'title': 'Conversation about Hexagonal Rails Part 1',
  741. 'description': 'a Martin Fowler video from ThoughtWorks',
  742. 'duration': 1715.0,
  743. 'uploader': 'thoughtworks.wistia.com',
  744. 'timestamp': 1401832161,
  745. 'upload_date': '20140603',
  746. },
  747. },
  748. # Wistia standard embed (async)
  749. {
  750. 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
  751. 'info_dict': {
  752. 'id': '807fafadvk',
  753. 'ext': 'mp4',
  754. 'title': 'Drip Brennan Dunn Workshop',
  755. 'description': 'a JV Webinars video from getdrip-1',
  756. 'duration': 4986.95,
  757. 'timestamp': 1463607249,
  758. 'upload_date': '20160518',
  759. },
  760. 'params': {
  761. 'skip_download': True,
  762. }
  763. },
  764. # Soundcloud embed
  765. {
  766. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  767. 'info_dict': {
  768. 'id': '174391317',
  769. 'ext': 'mp3',
  770. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  771. 'uploader': 'Sophos Security',
  772. 'title': 'Chet Chat 171 - Oct 29, 2014',
  773. 'upload_date': '20141029',
  774. }
  775. },
  776. # Livestream embed
  777. {
  778. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  779. 'info_dict': {
  780. 'id': '67864563',
  781. 'ext': 'flv',
  782. 'upload_date': '20141112',
  783. 'title': 'Rosetta #CometLanding webcast HL 10',
  784. }
  785. },
  786. # Another Livestream embed, without 'new.' in URL
  787. {
  788. 'url': 'https://www.freespeech.org/',
  789. 'info_dict': {
  790. 'id': '123537347',
  791. 'ext': 'mp4',
  792. 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  793. },
  794. 'params': {
  795. # Live stream
  796. 'skip_download': True,
  797. },
  798. },
  799. # LazyYT
  800. {
  801. 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
  802. 'info_dict': {
  803. 'id': '1986',
  804. 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
  805. },
  806. 'playlist_mincount': 2,
  807. },
  808. # Cinchcast embed
  809. {
  810. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  811. 'info_dict': {
  812. 'id': '7141703',
  813. 'ext': 'mp3',
  814. 'upload_date': '20141126',
  815. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  816. }
  817. },
  818. # Cinerama player
  819. {
  820. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  821. 'info_dict': {
  822. 'id': '730m_DandD_1901_512k',
  823. 'ext': 'mp4',
  824. 'uploader': 'www.abc.net.au',
  825. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  826. }
  827. },
  828. # embedded viddler video
  829. {
  830. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  831. 'info_dict': {
  832. 'id': '4d03aad9',
  833. 'ext': 'mp4',
  834. 'uploader': 'deadspin',
  835. 'title': 'WALL-TO-GORTAT',
  836. 'timestamp': 1422285291,
  837. 'upload_date': '20150126',
  838. },
  839. 'add_ie': ['Viddler'],
  840. },
  841. # Libsyn embed
  842. {
  843. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  844. 'info_dict': {
  845. 'id': '3377616',
  846. 'ext': 'mp3',
  847. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  848. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  849. 'upload_date': '20150220',
  850. },
  851. },
  852. # jwplayer YouTube
  853. {
  854. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  855. 'info_dict': {
  856. 'id': 'Mrj4DVp2zeA',
  857. 'ext': 'mp4',
  858. 'upload_date': '20150212',
  859. 'uploader': 'The National Archives UK',
  860. 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
  861. 'uploader_id': 'NationalArchives08',
  862. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  863. },
  864. },
  865. # rtl.nl embed
  866. {
  867. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  868. 'playlist_mincount': 5,
  869. 'info_dict': {
  870. 'id': 'aanslagen-kopenhagen',
  871. 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
  872. }
  873. },
  874. # Zapiks embed
  875. {
  876. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  877. 'info_dict': {
  878. 'id': '118046',
  879. 'ext': 'mp4',
  880. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  881. }
  882. },
  883. # Kaltura embed (different embed code)
  884. {
  885. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  886. 'info_dict': {
  887. 'id': '1_a52wc67y',
  888. 'ext': 'flv',
  889. 'upload_date': '20150127',
  890. 'uploader_id': 'PremierMedia',
  891. 'timestamp': int,
  892. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  893. },
  894. },
  895. # Kaltura embed protected with referrer
  896. {
  897. 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
  898. 'info_dict': {
  899. 'id': '1_g4fbemnq',
  900. 'ext': 'mp4',
  901. 'title': 'Violetta - Achter De Schermen - Ruggero',
  902. 'description': 'Achter de schermen met Ruggero',
  903. 'timestamp': 1435133761,
  904. 'upload_date': '20150624',
  905. 'uploader_id': 'echojecka',
  906. },
  907. },
  908. # Kaltura embed with single quotes
  909. {
  910. 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
  911. 'info_dict': {
  912. 'id': '0_izeg5utt',
  913. 'ext': 'mp4',
  914. 'title': '35871',
  915. 'timestamp': 1355743100,
  916. 'upload_date': '20121217',
  917. 'uploader_id': 'batchUser',
  918. },
  919. 'add_ie': ['Kaltura'],
  920. },
  921. {
  922. # Kaltura embedded via quoted entry_id
  923. 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
  924. 'info_dict': {
  925. 'id': '0_utuok90b',
  926. 'ext': 'mp4',
  927. 'title': '06_matthew_brender_raj_dutt',
  928. 'timestamp': 1466638791,
  929. 'upload_date': '20160622',
  930. },
  931. 'add_ie': ['Kaltura'],
  932. 'expected_warnings': [
  933. 'Could not send HEAD request'
  934. ],
  935. 'params': {
  936. 'skip_download': True,
  937. }
  938. },
  939. # Eagle.Platform embed (generic URL)
  940. {
  941. 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
  942. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  943. 'info_dict': {
  944. 'id': '227304',
  945. 'ext': 'mp4',
  946. 'title': 'Навальный вышел на свободу',
  947. 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
  948. 'thumbnail': 're:^https?://.*\.jpg$',
  949. 'duration': 87,
  950. 'view_count': int,
  951. 'age_limit': 0,
  952. },
  953. },
  954. # ClipYou (Eagle.Platform) embed (custom URL)
  955. {
  956. 'url': 'http://muz-tv.ru/play/7129/',
  957. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  958. 'info_dict': {
  959. 'id': '12820',
  960. 'ext': 'mp4',
  961. 'title': "'O Sole Mio",
  962. 'thumbnail': 're:^https?://.*\.jpg$',
  963. 'duration': 216,
  964. 'view_count': int,
  965. },
  966. },
  967. # Pladform embed
  968. {
  969. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  970. 'info_dict': {
  971. 'id': '100183293',
  972. 'ext': 'mp4',
  973. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  974. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  975. 'thumbnail': 're:^https?://.*\.jpg$',
  976. 'duration': 694,
  977. 'age_limit': 0,
  978. },
  979. },
  980. # Playwire embed
  981. {
  982. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  983. 'info_dict': {
  984. 'id': '3519514',
  985. 'ext': 'mp4',
  986. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  987. 'thumbnail': 're:^https?://.*\.png$',
  988. 'duration': 45.115,
  989. },
  990. },
  991. # 5min embed
  992. {
  993. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  994. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  995. 'info_dict': {
  996. 'id': '518726732',
  997. 'ext': 'mp4',
  998. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  999. },
  1000. },
  1001. # SVT embed
  1002. {
  1003. 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
  1004. 'info_dict': {
  1005. 'id': '2900353',
  1006. 'ext': 'flv',
  1007. 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
  1008. 'duration': 27,
  1009. 'age_limit': 0,
  1010. },
  1011. },
  1012. # Crooks and Liars embed
  1013. {
  1014. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  1015. 'info_dict': {
  1016. 'id': '8RUoRhRi',
  1017. 'ext': 'mp4',
  1018. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  1019. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  1020. 'timestamp': 1428207000,
  1021. 'upload_date': '20150405',
  1022. 'uploader': 'Heather',
  1023. },
  1024. },
  1025. # Crooks and Liars external embed
  1026. {
  1027. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  1028. 'info_dict': {
  1029. 'id': 'MTE3MjUtMzQ2MzA',
  1030. 'ext': 'mp4',
  1031. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  1032. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  1033. 'timestamp': 1265032391,
  1034. 'upload_date': '20100201',
  1035. 'uploader': 'Heather',
  1036. },
  1037. },
  1038. # NBC Sports vplayer embed
  1039. {
  1040. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  1041. 'info_dict': {
  1042. 'id': 'ln7x1qSThw4k',
  1043. 'ext': 'flv',
  1044. 'title': "PFT Live: New leader in the 'new-look' defense",
  1045. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  1046. 'uploader': 'NBCU-SPORTS',
  1047. 'upload_date': '20140107',
  1048. 'timestamp': 1389118457,
  1049. },
  1050. },
  1051. # NBC News embed
  1052. {
  1053. 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
  1054. 'md5': '1aa589c675898ae6d37a17913cf68d66',
  1055. 'info_dict': {
  1056. 'id': '701714499682',
  1057. 'ext': 'mp4',
  1058. 'title': 'PREVIEW: On Assignment: David Letterman',
  1059. 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
  1060. },
  1061. },
  1062. # UDN embed
  1063. {
  1064. 'url': 'https://video.udn.com/news/300346',
  1065. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  1066. 'info_dict': {
  1067. 'id': '300346',
  1068. 'ext': 'mp4',
  1069. 'title': '中一中男師變性 全校師生力挺',
  1070. 'thumbnail': 're:^https?://.*\.jpg$',
  1071. },
  1072. 'params': {
  1073. # m3u8 download
  1074. 'skip_download': True,
  1075. },
  1076. },
  1077. # Ooyala embed
  1078. {
  1079. 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
  1080. 'info_dict': {
  1081. 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
  1082. 'ext': 'mp4',
  1083. 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
  1084. 'title': 'This is what separates the Excel masters from the wannabes',
  1085. 'duration': 191.933,
  1086. },
  1087. 'params': {
  1088. # m3u8 downloads
  1089. 'skip_download': True,
  1090. }
  1091. },
  1092. # Brightcove URL in single quotes
  1093. {
  1094. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  1095. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  1096. 'info_dict': {
  1097. 'id': '4255764656001',
  1098. 'ext': 'mp4',
  1099. 'title': 'SN Presents: Russell Martin, World Citizen',
  1100. 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
  1101. 'uploader': 'Rogers Sportsnet',
  1102. 'uploader_id': '1704050871',
  1103. 'upload_date': '20150525',
  1104. 'timestamp': 1432570283,
  1105. },
  1106. },
  1107. # Dailymotion Cloud video
  1108. {
  1109. 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
  1110. 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
  1111. 'info_dict': {
  1112. 'id': 'x2uy8t3',
  1113. 'ext': 'mp4',
  1114. 'title': 'Sauvons les abeilles ! - Le débat',
  1115. 'description': 'md5:d9082128b1c5277987825d684939ca26',
  1116. 'thumbnail': 're:^https?://.*\.jpe?g$',
  1117. 'timestamp': 1434970506,
  1118. 'upload_date': '20150622',
  1119. 'uploader': 'Public Sénat',
  1120. 'uploader_id': 'xa9gza',
  1121. }
  1122. },
  1123. # OnionStudios embed
  1124. {
  1125. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1126. 'info_dict': {
  1127. 'id': '2855',
  1128. 'ext': 'mp4',
  1129. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1130. 'thumbnail': 're:^https?://.*\.jpe?g$',
  1131. 'uploader': 'ClickHole',
  1132. 'uploader_id': 'clickhole',
  1133. }
  1134. },
  1135. # SnagFilms embed
  1136. {
  1137. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1138. 'info_dict': {
  1139. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1140. 'ext': 'mp4',
  1141. 'title': '#whilewewatch',
  1142. }
  1143. },
  1144. # AdobeTVVideo embed
  1145. {
  1146. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1147. 'md5': '43662b577c018ad707a63766462b1e87',
  1148. 'info_dict': {
  1149. 'id': '2456',
  1150. 'ext': 'mp4',
  1151. 'title': 'New experience with Acrobat DC',
  1152. 'description': 'New experience with Acrobat DC',
  1153. 'duration': 248.667,
  1154. },
  1155. },
  1156. # ScreenwaveMedia embed
  1157. {
  1158. 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
  1159. 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
  1160. 'info_dict': {
  1161. 'id': 'cinemasnob-55d26273809dd',
  1162. 'ext': 'mp4',
  1163. 'title': 'cinemasnob',
  1164. },
  1165. },
  1166. # BrightcoveInPageEmbed embed
  1167. {
  1168. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1169. 'info_dict': {
  1170. 'id': '4238694884001',
  1171. 'ext': 'flv',
  1172. 'title': 'Tabletop: Dread, Last Thoughts',
  1173. 'description': 'Tabletop: Dread, Last Thoughts',
  1174. 'duration': 51690,
  1175. },
  1176. },
  1177. # JWPlayer with M3U8
  1178. {
  1179. 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
  1180. 'info_dict': {
  1181. 'id': 'playlist',
  1182. 'ext': 'mp4',
  1183. 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
  1184. 'uploader': 'ren.tv',
  1185. },
  1186. 'params': {
  1187. # m3u8 downloads
  1188. 'skip_download': True,
  1189. }
  1190. },
  1191. # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
  1192. # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
  1193. {
  1194. 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
  1195. 'info_dict': {
  1196. 'id': '4785848093001',
  1197. 'ext': 'mp4',
  1198. 'title': 'The Cardinal Pell Interview',
  1199. 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
  1200. 'uploader': 'GlobeCast Australia - GlobeStream',
  1201. 'uploader_id': '2733773828001',
  1202. 'upload_date': '20160304',
  1203. 'timestamp': 1457083087,
  1204. },
  1205. 'params': {
  1206. # m3u8 downloads
  1207. 'skip_download': True,
  1208. },
  1209. },
  1210. # Another form of arte.tv embed
  1211. {
  1212. 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
  1213. 'md5': '850bfe45417ddf221288c88a0cffe2e2',
  1214. 'info_dict': {
  1215. 'id': '030273-562_PLUS7-F',
  1216. 'ext': 'mp4',
  1217. 'title': 'ARTE Reportage - Nulle part, en France',
  1218. 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
  1219. 'upload_date': '20160409',
  1220. },
  1221. },
  1222. # LiveLeak embed
  1223. {
  1224. 'url': 'http://www.wykop.pl/link/3088787/',
  1225. 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
  1226. 'info_dict': {
  1227. 'id': '874_1459135191',
  1228. 'ext': 'mp4',
  1229. 'title': 'Man shows poor quality of new apartment building',
  1230. 'description': 'The wall is like a sand pile.',
  1231. 'uploader': 'Lake8737',
  1232. }
  1233. },
  1234. # Duplicated embedded video URLs
  1235. {
  1236. 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
  1237. 'info_dict': {
  1238. 'id': '149298443_480_16c25b74_2',
  1239. 'ext': 'mp4',
  1240. 'title': 'vs. Blue Orange Spring Game',
  1241. 'uploader': 'www.hudl.com',
  1242. },
  1243. },
  1244. # twitter:player embed
  1245. {
  1246. 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
  1247. 'md5': 'a3e0df96369831de324f0778e126653c',
  1248. 'info_dict': {
  1249. 'id': '4909620399001',
  1250. 'ext': 'mp4',
  1251. 'title': 'What Do Black Holes Sound Like?',
  1252. 'description': 'what do black holes sound like',
  1253. 'upload_date': '20160524',
  1254. 'uploader_id': '29913724001',
  1255. 'timestamp': 1464107587,
  1256. 'uploader': 'TheAtlantic',
  1257. },
  1258. 'add_ie': ['BrightcoveLegacy'],
  1259. },
  1260. # Facebook <iframe> embed
  1261. {
  1262. 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
  1263. 'md5': 'fbcde74f534176ecb015849146dd3aee',
  1264. 'info_dict': {
  1265. 'id': '599637780109885',
  1266. 'ext': 'mp4',
  1267. 'title': 'Facebook video #599637780109885',
  1268. },
  1269. },
  1270. # Facebook API embed
  1271. {
  1272. 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
  1273. 'md5': 'a47372ee61b39a7b90287094d447d94e',
  1274. 'info_dict': {
  1275. 'id': '10153467542406923',
  1276. 'ext': 'mp4',
  1277. 'title': 'Facebook video #10153467542406923',
  1278. },
  1279. },
  1280. # Wordpress "YouTube Video Importer" plugin
  1281. {
  1282. 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
  1283. 'md5': 'd16797741b560b485194eddda8121b48',
  1284. 'info_dict': {
  1285. 'id': 'HNTXWDXV9Is',
  1286. 'ext': 'mp4',
  1287. 'title': 'Blue Devils Drumline Stanford lot 2016',
  1288. 'upload_date': '20160627',
  1289. 'uploader_id': 'GENOCIDE8GENERAL10',
  1290. 'uploader': 'cylus cyrus',
  1291. },
  1292. },
  1293. ]
  1294. def report_following_redirect(self, new_url):
  1295. """Report information extraction."""
  1296. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  1297. def _extract_rss(self, url, video_id, doc):
  1298. playlist_title = doc.find('./channel/title').text
  1299. playlist_desc_el = doc.find('./channel/description')
  1300. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  1301. entries = []
  1302. for it in doc.findall('./channel/item'):
  1303. next_url = xpath_text(it, 'link', fatal=False)
  1304. if not next_url:
  1305. enclosure_nodes = it.findall('./enclosure')
  1306. for e in enclosure_nodes:
  1307. next_url = e.attrib.get('url')
  1308. if next_url:
  1309. break
  1310. if not next_url:
  1311. continue
  1312. entries.append({
  1313. '_type': 'url',
  1314. 'url': next_url,
  1315. 'title': it.find('title').text,
  1316. })
  1317. return {
  1318. '_type': 'playlist',
  1319. 'id': url,
  1320. 'title': playlist_title,
  1321. 'description': playlist_desc,
  1322. 'entries': entries,
  1323. }
  1324. def _extract_camtasia(self, url, video_id, webpage):
  1325. """ Returns None if no camtasia video can be found. """
  1326. camtasia_cfg = self._search_regex(
  1327. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  1328. webpage, 'camtasia configuration file', default=None)
  1329. if camtasia_cfg is None:
  1330. return None
  1331. title = self._html_search_meta('DC.title', webpage, fatal=True)
  1332. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  1333. camtasia_cfg = self._download_xml(
  1334. camtasia_url, video_id,
  1335. note='Downloading camtasia configuration',
  1336. errnote='Failed to download camtasia configuration')
  1337. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  1338. entries = []
  1339. for n in fileset_node.getchildren():
  1340. url_n = n.find('./uri')
  1341. if url_n is None:
  1342. continue
  1343. entries.append({
  1344. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  1345. 'title': '%s - %s' % (title, n.tag),
  1346. 'url': compat_urlparse.urljoin(url, url_n.text),
  1347. 'duration': float_or_none(n.find('./duration').text),
  1348. })
  1349. return {
  1350. '_type': 'playlist',
  1351. 'entries': entries,
  1352. 'title': title,
  1353. }
  1354. def _real_extract(self, url):
  1355. if url.startswith('//'):
  1356. return {
  1357. '_type': 'url',
  1358. 'url': self.http_scheme() + url,
  1359. }
  1360. parsed_url = compat_urlparse.urlparse(url)
  1361. if not parsed_url.scheme:
  1362. default_search = self._downloader.params.get('default_search')
  1363. if default_search is None:
  1364. default_search = 'fixup_error'
  1365. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  1366. if '/' in url:
  1367. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  1368. return self.url_result('http://' + url)
  1369. elif default_search != 'fixup_error':
  1370. if default_search == 'auto_warning':
  1371. if re.match(r'^(?:url|URL)$', url):
  1372. raise ExtractorError(
  1373. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  1374. expected=True)
  1375. else:
  1376. self._downloader.report_warning(
  1377. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  1378. return self.url_result('ytsearch:' + url)
  1379. if default_search in ('error', 'fixup_error'):
  1380. raise ExtractorError(
  1381. '%r is not a valid URL. '
  1382. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  1383. % (url, url), expected=True)
  1384. else:
  1385. if ':' not in default_search:
  1386. default_search += ':'
  1387. return self.url_result(default_search + url)
  1388. url, smuggled_data = unsmuggle_url(url)
  1389. force_videoid = None
  1390. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  1391. if smuggled_data and 'force_videoid' in smuggled_data:
  1392. force_videoid = smuggled_data['force_videoid']
  1393. video_id = force_videoid
  1394. else:
  1395. video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
  1396. self.to_screen('%s: Requesting header' % video_id)
  1397. head_req = HEADRequest(url)
  1398. head_response = self._request_webpage(
  1399. head_req, video_id,
  1400. note=False, errnote='Could not send HEAD request to %s' % url,
  1401. fatal=False)
  1402. if head_response is not False:
  1403. # Check for redirect
  1404. new_url = head_response.geturl()
  1405. if url != new_url:
  1406. self.report_following_redirect(new_url)
  1407. if force_videoid:
  1408. new_url = smuggle_url(
  1409. new_url, {'force_videoid': force_videoid})
  1410. return self.url_result(new_url)
  1411. full_response = None
  1412. if head_response is False:
  1413. request = sanitized_Request(url)
  1414. request.add_header('Accept-Encoding', '*')
  1415. full_response = self._request_webpage(request, video_id)
  1416. head_response = full_response
  1417. info_dict = {
  1418. 'id': video_id,
  1419. 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
  1420. 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
  1421. }
  1422. # Check for direct link to a video
  1423. content_type = head_response.headers.get('Content-Type', '').lower()
  1424. m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
  1425. if m:
  1426. format_id = m.group('format_id')
  1427. if format_id.endswith('mpegurl'):
  1428. formats = self._extract_m3u8_formats(url, video_id, 'mp4')
  1429. elif format_id == 'f4m':
  1430. formats = self._extract_f4m_formats(url, video_id)
  1431. else:
  1432. formats = [{
  1433. 'format_id': m.group('format_id'),
  1434. 'url': url,
  1435. 'vcodec': 'none' if m.group('type') == 'audio' else None
  1436. }]
  1437. info_dict['direct'] = True
  1438. self._sort_formats(formats)
  1439. info_dict['formats'] = formats
  1440. return info_dict
  1441. if not self._downloader.params.get('test', False) and not is_intentional:
  1442. force = self._downloader.params.get('force_generic_extractor', False)
  1443. self._downloader.report_warning(
  1444. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  1445. if not full_response:
  1446. request = sanitized_Request(url)
  1447. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  1448. # making it impossible to download only chunk of the file (yet we need only 512kB to
  1449. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  1450. # that will always result in downloading the whole file that is not desirable.
  1451. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  1452. # to accept raw bytes and being able to download only a chunk.
  1453. # It may probably better to solve this by checking Content-Type for application/octet-stream
  1454. # after HEAD request finishes, but not sure if we can rely on this.
  1455. request.add_header('Accept-Encoding', '*')
  1456. full_response = self._request_webpage(request, video_id)
  1457. first_bytes = full_response.read(512)
  1458. # Is it an M3U playlist?
  1459. if first_bytes.startswith(b'#EXTM3U'):
  1460. info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
  1461. self._sort_formats(info_dict['formats'])
  1462. return info_dict
  1463. # Maybe it's a direct link to a video?
  1464. # Be careful not to download the whole thing!
  1465. if not is_html(first_bytes):
  1466. self._downloader.report_warning(
  1467. 'URL could be a direct video link, returning it as such.')
  1468. info_dict.update({
  1469. 'direct': True,
  1470. 'url': url,
  1471. })
  1472. return info_dict
  1473. webpage = self._webpage_read_content(
  1474. full_response, url, video_id, prefix=first_bytes)
  1475. self.report_extraction(video_id)
  1476. # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
  1477. try:
  1478. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  1479. if doc.tag == 'rss':
  1480. return self._extract_rss(url, video_id, doc)
  1481. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  1482. smil = self._parse_smil(doc, url, video_id)
  1483. self._sort_formats(smil['formats'])
  1484. return smil
  1485. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  1486. return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
  1487. elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
  1488. info_dict['formats'] = self._parse_mpd_formats(
  1489. doc, video_id, mpd_base_url=url.rpartition('/')[0])
  1490. self._sort_formats(info_dict['formats'])
  1491. return info_dict
  1492. elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
  1493. info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
  1494. self._sort_formats(info_dict['formats'])
  1495. return info_dict
  1496. except compat_xml_parse_error:
  1497. pass
  1498. # Is it a Camtasia project?
  1499. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  1500. if camtasia_res is not None:
  1501. return camtasia_res
  1502. # Sometimes embedded video player is hidden behind percent encoding
  1503. # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
  1504. # Unescaping the whole page allows to handle those cases in a generic way
  1505. webpage = compat_urllib_parse_unquote(webpage)
  1506. # it's tempting to parse this further, but you would
  1507. # have to take into account all the variations like
  1508. # Video Title - Site Name
  1509. # Site Name | Video Title
  1510. # Video Title - Tagline | Site Name
  1511. # and so on and so forth; it's just not practical
  1512. video_title = self._og_search_title(
  1513. webpage, default=None) or self._html_search_regex(
  1514. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  1515. default='video')
  1516. # Try to detect age limit automatically
  1517. age_limit = self._rta_search(webpage)
  1518. # And then there are the jokers who advertise that they use RTA,
  1519. # but actually don't.
  1520. AGE_LIMIT_MARKERS = [
  1521. r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
  1522. ]
  1523. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  1524. age_limit = 18
  1525. # video uploader is domain name
  1526. video_uploader = self._search_regex(
  1527. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  1528. video_description = self._og_search_description(webpage, default=None)
  1529. video_thumbnail = self._og_search_thumbnail(webpage, default=None)
  1530. # Helper method
  1531. def _playlist_from_matches(matches, getter=None, ie=None):
  1532. urlrs = orderedSet(
  1533. self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
  1534. for m in matches)
  1535. return self.playlist_result(
  1536. urlrs, playlist_id=video_id, playlist_title=video_title)
  1537. # Look for Brightcove Legacy Studio embeds
  1538. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  1539. if bc_urls:
  1540. self.to_screen('Brightcove video detected.')
  1541. entries = [{
  1542. '_type': 'url',
  1543. 'url': smuggle_url(bc_url, {'Referer': url}),
  1544. 'ie_key': 'BrightcoveLegacy'
  1545. } for bc_url in bc_urls]
  1546. return {
  1547. '_type': 'playlist',
  1548. 'title': video_title,
  1549. 'id': video_id,
  1550. 'entries': entries,
  1551. }
  1552. # Look for Brightcove New Studio embeds
  1553. bc_urls = BrightcoveNewIE._extract_urls(webpage)
  1554. if bc_urls:
  1555. return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
  1556. # Look for ThePlatform embeds
  1557. tp_urls = ThePlatformIE._extract_urls(webpage)
  1558. if tp_urls:
  1559. return _playlist_from_matches(tp_urls, ie='ThePlatform')
  1560. # Look for Vessel embeds
  1561. vessel_urls = VesselIE._extract_urls(webpage)
  1562. if vessel_urls:
  1563. return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
  1564. # Look for embedded rtl.nl player
  1565. matches = re.findall(
  1566. r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
  1567. webpage)
  1568. if matches:
  1569. return _playlist_from_matches(matches, ie='RtlNl')
  1570. vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
  1571. if vimeo_url is not None:
  1572. return self.url_result(vimeo_url)
  1573. vid_me_embed_url = self._search_regex(
  1574. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  1575. webpage, 'vid.me embed', default=None)
  1576. if vid_me_embed_url is not None:
  1577. return self.url_result(vid_me_embed_url, 'Vidme')
  1578. # Look for embedded YouTube player
  1579. matches = re.findall(r'''(?x)
  1580. (?:
  1581. <iframe[^>]+?src=|
  1582. data-video-url=|
  1583. <embed[^>]+?src=|
  1584. embedSWF\(?:\s*|
  1585. new\s+SWFObject\(
  1586. )
  1587. (["\'])
  1588. (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
  1589. (?:embed|v|p)/.+?)
  1590. \1''', webpage)
  1591. if matches:
  1592. return _playlist_from_matches(
  1593. matches, lambda m: unescapeHTML(m[1]))
  1594. # Look for lazyYT YouTube embed
  1595. matches = re.findall(
  1596. r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
  1597. if matches:
  1598. return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
  1599. # Look for Wordpress "YouTube Video Importer" plugin
  1600. matches = re.findall(r'''(?x)<div[^>]+
  1601. class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
  1602. data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
  1603. if matches:
  1604. return _playlist_from_matches(matches, lambda m: m[-1])
  1605. # Look for embedded Dailymotion player
  1606. matches = re.findall(
  1607. r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
  1608. if matches:
  1609. return _playlist_from_matches(
  1610. matches, lambda m: unescapeHTML(m[1]))
  1611. # Look for embedded Dailymotion playlist player (#3822)
  1612. m = re.search(
  1613. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  1614. if m:
  1615. playlists = re.findall(
  1616. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  1617. if playlists:
  1618. return _playlist_from_matches(
  1619. playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
  1620. # Look for embedded Wistia player
  1621. match = re.search(
  1622. r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
  1623. if match:
  1624. embed_url = self._proto_relative_url(
  1625. unescapeHTML(match.group('url')))
  1626. return {
  1627. '_type': 'url_transparent',
  1628. 'url': embed_url,
  1629. 'ie_key': 'Wistia',
  1630. 'uploader': video_uploader,
  1631. }
  1632. match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
  1633. if match:
  1634. return {
  1635. '_type': 'url_transparent',
  1636. 'url': 'wistia:%s' % match.group('id'),
  1637. 'ie_key': 'Wistia',
  1638. 'uploader': video_uploader,
  1639. }
  1640. match = re.search(
  1641. r'''(?sx)
  1642. <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
  1643. <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
  1644. ''', webpage)
  1645. if match:
  1646. return self.url_result(self._proto_relative_url(
  1647. 'wistia:%s' % match.group('id')), 'Wistia')
  1648. # Look for SVT player
  1649. svt_url = SVTIE._extract_url(webpage)
  1650. if svt_url:
  1651. return self.url_result(svt_url, 'SVT')
  1652. # Look for embedded condenast player
  1653. matches = re.findall(
  1654. r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
  1655. webpage)
  1656. if matches:
  1657. return {
  1658. '_type': 'playlist',
  1659. 'entries': [{
  1660. '_type': 'url',
  1661. 'ie_key': 'CondeNast',
  1662. 'url': ma,
  1663. } for ma in matches],
  1664. 'title': video_title,
  1665. 'id': video_id,
  1666. }
  1667. # Look for Bandcamp pages with custom domain
  1668. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  1669. if mobj is not None:
  1670. burl = unescapeHTML(mobj.group(1))
  1671. # Don't set the extractor because it can be a track url or an album
  1672. return self.url_result(burl)
  1673. # Look for embedded Vevo player
  1674. mobj = re.search(
  1675. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  1676. if mobj is not None:
  1677. return self.url_result(mobj.group('url'))
  1678. # Look for embedded Viddler player
  1679. mobj = re.search(
  1680. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  1681. webpage)
  1682. if mobj is not None:
  1683. return self.url_result(mobj.group('url'))
  1684. # Look for NYTimes player
  1685. mobj = re.search(
  1686. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  1687. webpage)
  1688. if mobj is not None:
  1689. return self.url_result(mobj.group('url'))
  1690. # Look for Libsyn player
  1691. mobj = re.search(
  1692. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  1693. if mobj is not None:
  1694. return self.url_result(mobj.group('url'))
  1695. # Look for Ooyala videos
  1696. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
  1697. re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
  1698. re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
  1699. re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  1700. if mobj is not None:
  1701. return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
  1702. # Look for multiple Ooyala embeds on SBN network websites
  1703. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  1704. if mobj is not None:
  1705. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  1706. if embeds:
  1707. return _playlist_from_matches(
  1708. embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  1709. # Look for Aparat videos
  1710. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  1711. if mobj is not None:
  1712. return self.url_result(mobj.group(1), 'Aparat')
  1713. # Look for MPORA videos
  1714. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  1715. if mobj is not None:
  1716. return self.url_result(mobj.group(1), 'Mpora')
  1717. # Look for embedded NovaMov-based player
  1718. mobj = re.search(
  1719. r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
  1720. (?P<url>http://(?:(?:embed|www)\.)?
  1721. (?:novamov\.com|
  1722. nowvideo\.(?:ch|sx|eu|at|ag|co)|
  1723. videoweed\.(?:es|com)|
  1724. movshare\.(?:net|sx|ag)|
  1725. divxstage\.(?:eu|net|ch|co|at|ag))
  1726. /embed\.php.+?)\1''', webpage)
  1727. if mobj is not None:
  1728. return self.url_result(mobj.group('url'))
  1729. # Look for embedded Facebook player
  1730. facebook_url = FacebookIE._extract_url(webpage)
  1731. if facebook_url is not None:
  1732. return self.url_result(facebook_url, 'Facebook')
  1733. # Look for embedded VK player
  1734. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  1735. if mobj is not None:
  1736. return self.url_result(mobj.group('url'), 'VK')
  1737. # Look for embedded Odnoklassniki player
  1738. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
  1739. if mobj is not None:
  1740. return self.url_result(mobj.group('url'), 'Odnoklassniki')
  1741. # Look for embedded ivi player
  1742. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  1743. if mobj is not None:
  1744. return self.url_result(mobj.group('url'), 'Ivi')
  1745. # Look for embedded Huffington Post player
  1746. mobj = re.search(
  1747. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  1748. if mobj is not None:
  1749. return self.url_result(mobj.group('url'), 'HuffPost')
  1750. # Look for embed.ly
  1751. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  1752. if mobj is not None:
  1753. return self.url_result(mobj.group('url'))
  1754. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  1755. if mobj is not None:
  1756. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  1757. # Look for funnyordie embed
  1758. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  1759. if matches:
  1760. return _playlist_from_matches(
  1761. matches, getter=unescapeHTML, ie='FunnyOrDie')
  1762. # Look for BBC iPlayer embed
  1763. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  1764. if matches:
  1765. return _playlist_from_matches(matches, ie='BBCCoUk')
  1766. # Look for embedded RUTV player
  1767. rutv_url = RUTVIE._extract_url(webpage)
  1768. if rutv_url:
  1769. return self.url_result(rutv_url, 'RUTV')
  1770. # Look for embedded TVC player
  1771. tvc_url = TVCIE._extract_url(webpage)
  1772. if tvc_url:
  1773. return self.url_result(tvc_url, 'TVC')
  1774. # Look for embedded SportBox player
  1775. sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
  1776. if sportbox_urls:
  1777. return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
  1778. # Look for embedded PornHub player
  1779. pornhub_url = PornHubIE._extract_url(webpage)
  1780. if pornhub_url:
  1781. return self.url_result(pornhub_url, 'PornHub')
  1782. # Look for embedded XHamster player
  1783. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  1784. if xhamster_urls:
  1785. return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
  1786. # Look for embedded TNAFlixNetwork player
  1787. tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
  1788. if tnaflix_urls:
  1789. return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
  1790. # Look for embedded Tvigle player
  1791. mobj = re.search(
  1792. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  1793. if mobj is not None:
  1794. return self.url_result(mobj.group('url'), 'Tvigle')
  1795. # Look for embedded TED player
  1796. mobj = re.search(
  1797. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  1798. if mobj is not None:
  1799. return self.url_result(mobj.group('url'), 'TED')
  1800. # Look for embedded Ustream videos
  1801. mobj = re.search(
  1802. r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
  1803. if mobj is not None:
  1804. return self.url_result(mobj.group('url'), 'Ustream')
  1805. # Look for embedded arte.tv player
  1806. mobj = re.search(
  1807. r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
  1808. webpage)
  1809. if mobj is not None:
  1810. return self.url_result(mobj.group('url'), 'ArteTVEmbed')
  1811. # Look for embedded francetv player
  1812. mobj = re.search(
  1813. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  1814. webpage)
  1815. if mobj is not None:
  1816. return self.url_result(mobj.group('url'))
  1817. # Look for embedded smotri.com player
  1818. smotri_url = SmotriIE._extract_url(webpage)
  1819. if smotri_url:
  1820. return self.url_result(smotri_url, 'Smotri')
  1821. # Look for embedded Myvi.ru player
  1822. myvi_url = MyviIE._extract_url(webpage)
  1823. if myvi_url:
  1824. return self.url_result(myvi_url)
  1825. # Look for embedded soundcloud player
  1826. mobj = re.search(
  1827. r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
  1828. webpage)
  1829. if mobj is not None:
  1830. url = unescapeHTML(mobj.group('url'))
  1831. return self.url_result(url)
  1832. # Look for embedded mtvservices player
  1833. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  1834. if mtvservices_url:
  1835. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  1836. # Look for embedded yahoo player
  1837. mobj = re.search(
  1838. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  1839. webpage)
  1840. if mobj is not None:
  1841. return self.url_result(mobj.group('url'), 'Yahoo')
  1842. # Look for embedded sbs.com.au player
  1843. mobj = re.search(
  1844. r'''(?x)
  1845. (?:
  1846. <meta\s+property="og:video"\s+content=|
  1847. <iframe[^>]+?src=
  1848. )
  1849. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  1850. webpage)
  1851. if mobj is not None:
  1852. return self.url_result(mobj.group('url'), 'SBS')
  1853. # Look for embedded Cinchcast player
  1854. mobj = re.search(
  1855. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  1856. webpage)
  1857. if mobj is not None:
  1858. return self.url_result(mobj.group('url'), 'Cinchcast')
  1859. mobj = re.search(
  1860. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  1861. webpage)
  1862. if not mobj:
  1863. mobj = re.search(
  1864. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  1865. webpage)
  1866. if mobj is not None:
  1867. return self.url_result(mobj.group('url'), 'MLB')
  1868. mobj = re.search(
  1869. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  1870. webpage)
  1871. if mobj is not None:
  1872. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  1873. mobj = re.search(
  1874. r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
  1875. webpage)
  1876. if mobj is not None:
  1877. return self.url_result(mobj.group('url'), 'Livestream')
  1878. # Look for Zapiks embed
  1879. mobj = re.search(
  1880. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  1881. if mobj is not None:
  1882. return self.url_result(mobj.group('url'), 'Zapiks')
  1883. # Look for Kaltura embeds
  1884. kaltura_url = KalturaIE._extract_url(webpage)
  1885. if kaltura_url:
  1886. return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
  1887. # Look for Eagle.Platform embeds
  1888. eagleplatform_url = EaglePlatformIE._extract_url(webpage)
  1889. if eagleplatform_url:
  1890. return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
  1891. # Look for ClipYou (uses Eagle.Platform) embeds
  1892. mobj = re.search(
  1893. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  1894. if mobj is not None:
  1895. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  1896. # Look for Pladform embeds
  1897. pladform_url = PladformIE._extract_url(webpage)
  1898. if pladform_url:
  1899. return self.url_result(pladform_url)
  1900. # Look for Videomore embeds
  1901. videomore_url = VideomoreIE._extract_url(webpage)
  1902. if videomore_url:
  1903. return self.url_result(videomore_url)
  1904. # Look for Playwire embeds
  1905. mobj = re.search(
  1906. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  1907. if mobj is not None:
  1908. return self.url_result(mobj.group('url'))
  1909. # Look for 5min embeds
  1910. mobj = re.search(
  1911. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  1912. if mobj is not None:
  1913. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  1914. # Look for Crooks and Liars embeds
  1915. mobj = re.search(
  1916. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  1917. if mobj is not None:
  1918. return self.url_result(mobj.group('url'))
  1919. # Look for NBC Sports VPlayer embeds
  1920. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  1921. if nbc_sports_url:
  1922. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  1923. # Look for NBC News embeds
  1924. nbc_news_embed_url = re.search(
  1925. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
  1926. if nbc_news_embed_url:
  1927. return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
  1928. # Look for Google Drive embeds
  1929. google_drive_url = GoogleDriveIE._extract_url(webpage)
  1930. if google_drive_url:
  1931. return self.url_result(google_drive_url, 'GoogleDrive')
  1932. # Look for UDN embeds
  1933. mobj = re.search(
  1934. r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  1935. if mobj is not None:
  1936. return self.url_result(
  1937. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  1938. # Look for Senate ISVP iframe
  1939. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  1940. if senate_isvp_url:
  1941. return self.url_result(senate_isvp_url, 'SenateISVP')
  1942. # Look for Dailymotion Cloud videos
  1943. dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
  1944. if dmcloud_url:
  1945. return self.url_result(dmcloud_url, 'DailymotionCloud')
  1946. # Look for OnionStudios embeds
  1947. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  1948. if onionstudios_url:
  1949. return self.url_result(onionstudios_url)
  1950. # Look for ViewLift embeds
  1951. viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
  1952. if viewlift_url:
  1953. return self.url_result(viewlift_url)
  1954. # Look for JWPlatform embeds
  1955. jwplatform_url = JWPlatformIE._extract_url(webpage)
  1956. if jwplatform_url:
  1957. return self.url_result(jwplatform_url, 'JWPlatform')
  1958. # Look for ScreenwaveMedia embeds
  1959. mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
  1960. if mobj is not None:
  1961. return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
  1962. # Look for Digiteka embeds
  1963. digiteka_url = DigitekaIE._extract_url(webpage)
  1964. if digiteka_url:
  1965. return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
  1966. # Look for Limelight embeds
  1967. mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
  1968. if mobj:
  1969. lm = {
  1970. 'Media': 'media',
  1971. 'Channel': 'channel',
  1972. 'ChannelList': 'channel_list',
  1973. }
  1974. return self.url_result('limelight:%s:%s' % (
  1975. lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
  1976. # Look for AdobeTVVideo embeds
  1977. mobj = re.search(
  1978. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  1979. webpage)
  1980. if mobj is not None:
  1981. return self.url_result(
  1982. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  1983. 'AdobeTVVideo')
  1984. # Look for Vine embeds
  1985. mobj = re.search(
  1986. r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
  1987. webpage)
  1988. if mobj is not None:
  1989. return self.url_result(
  1990. self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
  1991. # Look for Instagram embeds
  1992. instagram_embed_url = InstagramIE._extract_embed_url(webpage)
  1993. if instagram_embed_url is not None:
  1994. return self.url_result(
  1995. self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
  1996. # Look for LiveLeak embeds
  1997. liveleak_url = LiveLeakIE._extract_url(webpage)
  1998. if liveleak_url:
  1999. return self.url_result(liveleak_url, 'LiveLeak')
  2000. # Look for 3Q SDN embeds
  2001. threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
  2002. if threeqsdn_url:
  2003. return {
  2004. '_type': 'url_transparent',
  2005. 'ie_key': ThreeQSDNIE.ie_key(),
  2006. 'url': self._proto_relative_url(threeqsdn_url),
  2007. 'title': video_title,
  2008. 'description': video_description,
  2009. 'thumbnail': video_thumbnail,
  2010. 'uploader': video_uploader,
  2011. }
  2012. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser
  2013. embed_url = self._html_search_meta('twitter:player', webpage, default=None)
  2014. if embed_url:
  2015. return self.url_result(embed_url)
  2016. def check_video(vurl):
  2017. if YoutubeIE.suitable(vurl):
  2018. return True
  2019. vpath = compat_urlparse.urlparse(vurl).path
  2020. vext = determine_ext(vpath)
  2021. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
  2022. def filter_video(urls):
  2023. return list(filter(check_video, urls))
  2024. # Start with something easy: JW Player in SWFObject
  2025. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  2026. if not found:
  2027. # Look for gorilla-vid style embedding
  2028. found = filter_video(re.findall(r'''(?sx)
  2029. (?:
  2030. jw_plugins|
  2031. JWPlayerOptions|
  2032. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  2033. )
  2034. .*?
  2035. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  2036. if not found:
  2037. # Broaden the search a little bit
  2038. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  2039. if not found:
  2040. # Broaden the findall a little bit: JWPlayer JS loader
  2041. found = filter_video(re.findall(
  2042. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  2043. if not found:
  2044. # Flow player
  2045. found = filter_video(re.findall(r'''(?xs)
  2046. flowplayer\("[^"]+",\s*
  2047. \{[^}]+?\}\s*,
  2048. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  2049. ["']?url["']?\s*:\s*["']([^"']+)["']
  2050. ''', webpage))
  2051. if not found:
  2052. # Cinerama player
  2053. found = re.findall(
  2054. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  2055. if not found:
  2056. # Try to find twitter cards info
  2057. found = filter_video(re.findall(
  2058. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  2059. if not found:
  2060. # We look for Open Graph info:
  2061. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  2062. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  2063. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  2064. if m_video_type is not None:
  2065. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  2066. if not found:
  2067. # HTML5 video
  2068. found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
  2069. if not found:
  2070. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  2071. found = re.search(
  2072. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  2073. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  2074. webpage)
  2075. if not found:
  2076. # Look also in Refresh HTTP header
  2077. refresh_header = head_response.headers.get('Refresh')
  2078. if refresh_header:
  2079. # In python 2 response HTTP headers are bytestrings
  2080. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  2081. refresh_header = refresh_header.decode('iso-8859-1')
  2082. found = re.search(REDIRECT_REGEX, refresh_header)
  2083. if found:
  2084. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  2085. self.report_following_redirect(new_url)
  2086. return {
  2087. '_type': 'url',
  2088. 'url': new_url,
  2089. }
  2090. if not found:
  2091. raise UnsupportedError(url)
  2092. entries = []
  2093. for video_url in orderedSet(found):
  2094. video_url = unescapeHTML(video_url)
  2095. video_url = video_url.replace('\\/', '/')
  2096. video_url = compat_urlparse.urljoin(url, video_url)
  2097. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  2098. # Sometimes, jwplayer extraction will result in a YouTube URL
  2099. if YoutubeIE.suitable(video_url):
  2100. entries.append(self.url_result(video_url, 'Youtube'))
  2101. continue
  2102. # here's a fun little line of code for you:
  2103. video_id = os.path.splitext(video_id)[0]
  2104. entry_info_dict = {
  2105. 'id': video_id,
  2106. 'uploader': video_uploader,
  2107. 'title': video_title,
  2108. 'age_limit': age_limit,
  2109. }
  2110. ext = determine_ext(video_url)
  2111. if ext == 'smil':
  2112. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  2113. elif ext == 'xspf':
  2114. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  2115. elif ext == 'm3u8':
  2116. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  2117. elif ext == 'mpd':
  2118. entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
  2119. elif ext == 'f4m':
  2120. entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
  2121. else:
  2122. entry_info_dict['url'] = video_url
  2123. if entry_info_dict.get('formats'):
  2124. self._sort_formats(entry_info_dict['formats'])
  2125. entries.append(entry_info_dict)
  2126. if len(entries) == 1:
  2127. return entries[0]
  2128. else:
  2129. for num, e in enumerate(entries, start=1):
  2130. # 'url' results don't have a title
  2131. if e.get('title') is not None:
  2132. e['title'] = '%s (%d)' % (e['title'], num)
  2133. return {
  2134. '_type': 'playlist',
  2135. 'entries': entries,
  2136. }