generic.py 78 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947
  1. # encoding: utf-8
  2. from __future__ import unicode_literals
  3. import os
  4. import re
  5. import sys
  6. from .common import InfoExtractor
  7. from .youtube import YoutubeIE
  8. from ..compat import (
  9. compat_etree_fromstring,
  10. compat_urllib_parse_unquote,
  11. compat_urlparse,
  12. compat_xml_parse_error,
  13. )
  14. from ..utils import (
  15. determine_ext,
  16. ExtractorError,
  17. float_or_none,
  18. HEADRequest,
  19. is_html,
  20. orderedSet,
  21. sanitized_Request,
  22. smuggle_url,
  23. unescapeHTML,
  24. unified_strdate,
  25. unsmuggle_url,
  26. UnsupportedError,
  27. url_basename,
  28. xpath_text,
  29. )
  30. from .brightcove import (
  31. BrightcoveLegacyIE,
  32. BrightcoveNewIE,
  33. )
  34. from .nbc import NBCSportsVPlayerIE
  35. from .ooyala import OoyalaIE
  36. from .rutv import RUTVIE
  37. from .tvc import TVCIE
  38. from .sportbox import SportBoxEmbedIE
  39. from .smotri import SmotriIE
  40. from .myvi import MyviIE
  41. from .condenast import CondeNastIE
  42. from .udn import UDNEmbedIE
  43. from .senateisvp import SenateISVPIE
  44. from .svt import SVTIE
  45. from .pornhub import PornHubIE
  46. from .xhamster import XHamsterEmbedIE
  47. from .vimeo import VimeoIE
  48. from .dailymotion import DailymotionCloudIE
  49. from .onionstudios import OnionStudiosIE
  50. from .snagfilms import SnagFilmsEmbedIE
  51. from .screenwavemedia import ScreenwaveMediaIE
  52. from .mtv import MTVServicesEmbeddedIE
  53. from .pladform import PladformIE
  54. from .googledrive import GoogleDriveIE
  55. from .jwplatform import JWPlatformIE
  56. from .ultimedia import UltimediaIE
  57. class GenericIE(InfoExtractor):
  58. IE_DESC = 'Generic downloader that works on some sites'
  59. _VALID_URL = r'.*'
  60. IE_NAME = 'generic'
  61. _TESTS = [
  62. # Direct link to a video
  63. {
  64. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  65. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  66. 'info_dict': {
  67. 'id': 'trailer',
  68. 'ext': 'mp4',
  69. 'title': 'trailer',
  70. 'upload_date': '20100513',
  71. }
  72. },
  73. # Direct link to media delivered compressed (until Accept-Encoding is *)
  74. {
  75. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  76. 'md5': '128c42e68b13950268b648275386fc74',
  77. 'info_dict': {
  78. 'id': 'FictionJunction-Parallel_Hearts',
  79. 'ext': 'flac',
  80. 'title': 'FictionJunction-Parallel_Hearts',
  81. 'upload_date': '20140522',
  82. },
  83. 'expected_warnings': [
  84. 'URL could be a direct video link, returning it as such.'
  85. ]
  86. },
  87. # Direct download with broken HEAD
  88. {
  89. 'url': 'http://ai-radio.org:8000/radio.opus',
  90. 'info_dict': {
  91. 'id': 'radio',
  92. 'ext': 'opus',
  93. 'title': 'radio',
  94. },
  95. 'params': {
  96. 'skip_download': True, # infinite live stream
  97. },
  98. 'expected_warnings': [
  99. r'501.*Not Implemented'
  100. ],
  101. },
  102. # Direct link with incorrect MIME type
  103. {
  104. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  105. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  106. 'info_dict': {
  107. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  108. 'id': '5_Lennart_Poettering_-_Systemd',
  109. 'ext': 'webm',
  110. 'title': '5_Lennart_Poettering_-_Systemd',
  111. 'upload_date': '20141120',
  112. },
  113. 'expected_warnings': [
  114. 'URL could be a direct video link, returning it as such.'
  115. ]
  116. },
  117. # RSS feed
  118. {
  119. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  120. 'info_dict': {
  121. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  122. 'title': 'Zero Punctuation',
  123. 'description': 're:.*groundbreaking video review series.*'
  124. },
  125. 'playlist_mincount': 11,
  126. },
  127. # RSS feed with enclosure
  128. {
  129. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  130. 'info_dict': {
  131. 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  132. 'ext': 'm4v',
  133. 'upload_date': '20150228',
  134. 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  135. }
  136. },
  137. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  138. {
  139. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  140. 'info_dict': {
  141. 'id': 'smil',
  142. 'ext': 'mp4',
  143. 'title': 'Automatics, robotics and biocybernetics',
  144. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  145. 'upload_date': '20130627',
  146. 'formats': 'mincount:16',
  147. 'subtitles': 'mincount:1',
  148. },
  149. 'params': {
  150. 'force_generic_extractor': True,
  151. 'skip_download': True,
  152. },
  153. },
  154. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  155. {
  156. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  157. 'info_dict': {
  158. 'id': 'hds',
  159. 'ext': 'flv',
  160. 'title': 'hds',
  161. 'formats': 'mincount:1',
  162. },
  163. 'params': {
  164. 'skip_download': True,
  165. },
  166. },
  167. # SMIL from https://www.restudy.dk/video/play/id/1637
  168. {
  169. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  170. 'info_dict': {
  171. 'id': 'video_1637',
  172. 'ext': 'flv',
  173. 'title': 'video_1637',
  174. 'formats': 'mincount:3',
  175. },
  176. 'params': {
  177. 'skip_download': True,
  178. },
  179. },
  180. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  181. {
  182. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  183. 'info_dict': {
  184. 'id': 'smil-service',
  185. 'ext': 'flv',
  186. 'title': 'smil-service',
  187. 'formats': 'mincount:1',
  188. },
  189. 'params': {
  190. 'skip_download': True,
  191. },
  192. },
  193. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  194. {
  195. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  196. 'info_dict': {
  197. 'id': '4719370',
  198. 'ext': 'mp4',
  199. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  200. 'formats': 'mincount:3',
  201. },
  202. 'params': {
  203. 'skip_download': True,
  204. },
  205. },
  206. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  207. {
  208. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  209. 'info_dict': {
  210. 'id': 'mZlp2ctYIUEB',
  211. 'ext': 'mp4',
  212. 'title': 'Tikibad ontruimd wegens brand',
  213. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  214. 'thumbnail': 're:^https?://.*\.jpg$',
  215. 'duration': 33,
  216. },
  217. 'params': {
  218. 'skip_download': True,
  219. },
  220. },
  221. # google redirect
  222. {
  223. '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',
  224. 'info_dict': {
  225. 'id': 'cmQHVoWB5FY',
  226. 'ext': 'mp4',
  227. 'upload_date': '20130224',
  228. 'uploader_id': 'TheVerge',
  229. 'description': 're:^Chris Ziegler takes a look at the\.*',
  230. 'uploader': 'The Verge',
  231. 'title': 'First Firefox OS phones side-by-side',
  232. },
  233. 'params': {
  234. 'skip_download': False,
  235. }
  236. },
  237. {
  238. # redirect in Refresh HTTP header
  239. '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',
  240. 'info_dict': {
  241. 'id': 'pO8h3EaFRdo',
  242. 'ext': 'mp4',
  243. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  244. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  245. 'upload_date': '20150917',
  246. 'uploader_id': 'brtvofficial',
  247. 'uploader': 'Boiler Room',
  248. },
  249. 'params': {
  250. 'skip_download': False,
  251. },
  252. },
  253. {
  254. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  255. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  256. 'info_dict': {
  257. 'id': '13601338388002',
  258. 'ext': 'mp4',
  259. 'uploader': 'www.hodiho.fr',
  260. 'title': 'R\u00e9gis plante sa Jeep',
  261. }
  262. },
  263. # bandcamp page with custom domain
  264. {
  265. 'add_ie': ['Bandcamp'],
  266. 'url': 'http://bronyrock.com/track/the-pony-mash',
  267. 'info_dict': {
  268. 'id': '3235767654',
  269. 'ext': 'mp3',
  270. 'title': 'The Pony Mash',
  271. 'uploader': 'M_Pallante',
  272. },
  273. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  274. },
  275. # embedded brightcove video
  276. # it also tests brightcove videos that need to set the 'Referer' in the
  277. # http requests
  278. {
  279. 'add_ie': ['BrightcoveLegacy'],
  280. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  281. 'info_dict': {
  282. 'id': '2765128793001',
  283. 'ext': 'mp4',
  284. 'title': 'Le cours de bourse : l’analyse technique',
  285. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  286. 'uploader': 'BFM BUSINESS',
  287. },
  288. 'params': {
  289. 'skip_download': True,
  290. },
  291. },
  292. {
  293. # https://github.com/rg3/youtube-dl/issues/2253
  294. 'url': 'http://bcove.me/i6nfkrc3',
  295. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  296. 'info_dict': {
  297. 'id': '3101154703001',
  298. 'ext': 'mp4',
  299. 'title': 'Still no power',
  300. 'uploader': 'thestar.com',
  301. '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.',
  302. },
  303. 'add_ie': ['BrightcoveLegacy'],
  304. },
  305. {
  306. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  307. 'md5': 'fb973ecf6e4a78a67453647444222983',
  308. 'info_dict': {
  309. 'id': '3414141473001',
  310. 'ext': 'mp4',
  311. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  312. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  313. 'uploader': 'Championat',
  314. },
  315. },
  316. {
  317. # https://github.com/rg3/youtube-dl/issues/3541
  318. 'add_ie': ['BrightcoveLegacy'],
  319. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  320. 'info_dict': {
  321. 'id': '3866516442001',
  322. 'ext': 'mp4',
  323. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  324. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  325. 'uploader': 'SBS Broadcasting',
  326. },
  327. 'skip': 'Restricted to Netherlands',
  328. 'params': {
  329. 'skip_download': True, # m3u8 download
  330. },
  331. },
  332. # ooyala video
  333. {
  334. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  335. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  336. 'info_dict': {
  337. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  338. 'ext': 'mp4',
  339. 'title': '2cc213299525360.mov', # that's what we get
  340. 'duration': 238.231,
  341. },
  342. 'add_ie': ['Ooyala'],
  343. },
  344. {
  345. # ooyala video embedded with http://player.ooyala.com/iframe.js
  346. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  347. 'info_dict': {
  348. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  349. 'ext': 'mp4',
  350. 'title': '"Steve Jobs: Man in the Machine" trailer',
  351. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  352. 'duration': 135.427,
  353. },
  354. 'params': {
  355. 'skip_download': True,
  356. },
  357. },
  358. # multiple ooyala embeds on SBN network websites
  359. {
  360. 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
  361. 'info_dict': {
  362. 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
  363. 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
  364. },
  365. 'playlist_mincount': 3,
  366. 'params': {
  367. 'skip_download': True,
  368. },
  369. 'add_ie': ['Ooyala'],
  370. },
  371. # embed.ly video
  372. {
  373. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  374. 'info_dict': {
  375. 'id': '9ODmcdjQcHQ',
  376. 'ext': 'mp4',
  377. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  378. 'upload_date': '20140225',
  379. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  380. 'uploader': 'Tested',
  381. 'uploader_id': 'testedcom',
  382. },
  383. # No need to test YoutubeIE here
  384. 'params': {
  385. 'skip_download': True,
  386. },
  387. },
  388. # funnyordie embed
  389. {
  390. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  391. 'info_dict': {
  392. 'id': '18e820ec3f',
  393. 'ext': 'mp4',
  394. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  395. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  396. },
  397. },
  398. # RUTV embed
  399. {
  400. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  401. 'info_dict': {
  402. 'id': '776940',
  403. 'ext': 'mp4',
  404. 'title': 'Охотское море стало целиком российским',
  405. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  406. },
  407. 'params': {
  408. # m3u8 download
  409. 'skip_download': True,
  410. },
  411. },
  412. # TVC embed
  413. {
  414. '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/',
  415. 'info_dict': {
  416. 'id': '55304',
  417. 'ext': 'mp4',
  418. 'title': 'Дошкольное воспитание',
  419. },
  420. },
  421. # SportBox embed
  422. {
  423. 'url': 'http://www.vestifinance.ru/articles/25753',
  424. 'info_dict': {
  425. 'id': '25753',
  426. 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  427. },
  428. 'playlist': [{
  429. 'info_dict': {
  430. 'id': '370908',
  431. 'title': 'Госзаказ. День 3',
  432. 'ext': 'mp4',
  433. }
  434. }, {
  435. 'info_dict': {
  436. 'id': '370905',
  437. 'title': 'Госзаказ. День 2',
  438. 'ext': 'mp4',
  439. }
  440. }, {
  441. 'info_dict': {
  442. 'id': '370902',
  443. 'title': 'Госзаказ. День 1',
  444. 'ext': 'mp4',
  445. }
  446. }],
  447. 'params': {
  448. # m3u8 download
  449. 'skip_download': True,
  450. },
  451. },
  452. # Myvi.ru embed
  453. {
  454. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  455. 'info_dict': {
  456. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  457. 'ext': 'mp4',
  458. 'title': 'Ужастики, русский трейлер (2015)',
  459. 'thumbnail': 're:^https?://.*\.jpg$',
  460. 'duration': 153,
  461. }
  462. },
  463. # XHamster embed
  464. {
  465. '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',
  466. 'info_dict': {
  467. 'id': 'showthread',
  468. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  469. },
  470. 'playlist_mincount': 7,
  471. },
  472. # Embedded TED video
  473. {
  474. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  475. 'md5': '65fdff94098e4a607385a60c5177c638',
  476. 'info_dict': {
  477. 'id': '1969',
  478. 'ext': 'mp4',
  479. 'title': 'Hidden miracles of the natural world',
  480. 'uploader': 'Louie Schwartzberg',
  481. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  482. }
  483. },
  484. # Embeded Ustream video
  485. {
  486. 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
  487. 'md5': '27b99cdb639c9b12a79bca876a073417',
  488. 'info_dict': {
  489. 'id': '45734260',
  490. 'ext': 'flv',
  491. 'uploader': 'AU SPA: The NSA and Privacy',
  492. 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
  493. }
  494. },
  495. # nowvideo embed hidden behind percent encoding
  496. {
  497. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  498. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  499. 'info_dict': {
  500. 'id': '06e53103ca9aa',
  501. 'ext': 'flv',
  502. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  503. 'description': 'No description',
  504. },
  505. },
  506. # arte embed
  507. {
  508. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  509. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  510. 'info_dict': {
  511. 'id': '048195-004_PLUS7-F',
  512. 'ext': 'flv',
  513. 'title': 'X:enius',
  514. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  515. 'upload_date': '20140320',
  516. },
  517. 'params': {
  518. 'skip_download': 'Requires rtmpdump'
  519. }
  520. },
  521. # francetv embed
  522. {
  523. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  524. 'info_dict': {
  525. 'id': 'EV_30231',
  526. 'ext': 'mp4',
  527. 'title': 'Alcaline, le concert avec Calogero',
  528. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  529. 'upload_date': '20150226',
  530. 'timestamp': 1424989860,
  531. 'duration': 5400,
  532. },
  533. 'params': {
  534. # m3u8 downloads
  535. 'skip_download': True,
  536. },
  537. 'expected_warnings': [
  538. 'Forbidden'
  539. ]
  540. },
  541. # Condé Nast embed
  542. {
  543. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  544. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  545. 'info_dict': {
  546. 'id': '53501be369702d3275860000',
  547. 'ext': 'mp4',
  548. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  549. }
  550. },
  551. # Dailymotion embed
  552. {
  553. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  554. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  555. 'info_dict': {
  556. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  557. 'ext': 'mp4',
  558. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  559. 'uploader': 'Spi0n',
  560. },
  561. 'add_ie': ['Dailymotion'],
  562. },
  563. # YouTube embed
  564. {
  565. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  566. 'info_dict': {
  567. 'id': 'FXRb4ykk4S0',
  568. 'ext': 'mp4',
  569. 'title': 'The NBL Auction 2014',
  570. 'uploader': 'BADMINTON England',
  571. 'uploader_id': 'BADMINTONEvents',
  572. 'upload_date': '20140603',
  573. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  574. },
  575. 'add_ie': ['Youtube'],
  576. 'params': {
  577. 'skip_download': True,
  578. }
  579. },
  580. # MTVSercices embed
  581. {
  582. 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
  583. 'md5': '35727f82f58c76d996fc188f9755b0d5',
  584. 'info_dict': {
  585. 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
  586. 'ext': 'mp4',
  587. 'title': 'Review',
  588. 'description': 'Mario\'s life in the fast lane has never looked so good.',
  589. },
  590. },
  591. # YouTube embed via <data-embed-url="">
  592. {
  593. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  594. 'info_dict': {
  595. 'id': '4vAffPZIT44',
  596. 'ext': 'mp4',
  597. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  598. 'uploader': 'Gameloft',
  599. 'uploader_id': 'gameloft',
  600. 'upload_date': '20140828',
  601. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  602. },
  603. 'params': {
  604. 'skip_download': True,
  605. }
  606. },
  607. # Camtasia studio
  608. {
  609. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  610. 'playlist': [{
  611. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  612. 'info_dict': {
  613. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  614. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  615. 'ext': 'flv',
  616. 'duration': 2235.90,
  617. }
  618. }, {
  619. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  620. 'info_dict': {
  621. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  622. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  623. 'ext': 'flv',
  624. 'duration': 2235.93,
  625. }
  626. }],
  627. 'info_dict': {
  628. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  629. }
  630. },
  631. # Flowplayer
  632. {
  633. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  634. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  635. 'info_dict': {
  636. 'id': '5123ea6d5e5a7',
  637. 'ext': 'mp4',
  638. 'age_limit': 18,
  639. 'uploader': 'www.handjobhub.com',
  640. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  641. }
  642. },
  643. # Multiple brightcove videos
  644. # https://github.com/rg3/youtube-dl/issues/2283
  645. {
  646. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  647. 'info_dict': {
  648. 'id': 'always-never',
  649. 'title': 'Always / Never - The New Yorker',
  650. },
  651. 'playlist_count': 3,
  652. 'params': {
  653. 'extract_flat': False,
  654. 'skip_download': True,
  655. }
  656. },
  657. # MLB embed
  658. {
  659. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  660. 'md5': '96f09a37e44da40dd083e12d9a683327',
  661. 'info_dict': {
  662. 'id': '33322633',
  663. 'ext': 'mp4',
  664. 'title': 'Ump changes call to ball',
  665. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  666. 'duration': 48,
  667. 'timestamp': 1401537900,
  668. 'upload_date': '20140531',
  669. 'thumbnail': 're:^https?://.*\.jpg$',
  670. },
  671. },
  672. # Wistia embed
  673. {
  674. 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  675. 'md5': '8788b683c777a5cf25621eaf286d0c23',
  676. 'info_dict': {
  677. 'id': '1cfaf6b7ea',
  678. 'ext': 'mov',
  679. 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
  680. 'duration': 643.0,
  681. 'filesize': 182808282,
  682. 'uploader': 'education-portal.com',
  683. },
  684. },
  685. {
  686. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  687. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  688. 'info_dict': {
  689. 'id': 'uxjb0lwrcz',
  690. 'ext': 'mp4',
  691. 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
  692. 'duration': 1715.0,
  693. 'uploader': 'thoughtworks.wistia.com',
  694. },
  695. },
  696. # Soundcloud embed
  697. {
  698. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  699. 'info_dict': {
  700. 'id': '174391317',
  701. 'ext': 'mp3',
  702. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  703. 'uploader': 'Sophos Security',
  704. 'title': 'Chet Chat 171 - Oct 29, 2014',
  705. 'upload_date': '20141029',
  706. }
  707. },
  708. # Livestream embed
  709. {
  710. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  711. 'info_dict': {
  712. 'id': '67864563',
  713. 'ext': 'flv',
  714. 'upload_date': '20141112',
  715. 'title': 'Rosetta #CometLanding webcast HL 10',
  716. }
  717. },
  718. # LazyYT
  719. {
  720. 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
  721. 'info_dict': {
  722. 'id': '1986',
  723. 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
  724. },
  725. 'playlist_mincount': 2,
  726. },
  727. # Cinchcast embed
  728. {
  729. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  730. 'info_dict': {
  731. 'id': '7141703',
  732. 'ext': 'mp3',
  733. 'upload_date': '20141126',
  734. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  735. }
  736. },
  737. # Cinerama player
  738. {
  739. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  740. 'info_dict': {
  741. 'id': '730m_DandD_1901_512k',
  742. 'ext': 'mp4',
  743. 'uploader': 'www.abc.net.au',
  744. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  745. }
  746. },
  747. # embedded viddler video
  748. {
  749. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  750. 'info_dict': {
  751. 'id': '4d03aad9',
  752. 'ext': 'mp4',
  753. 'uploader': 'deadspin',
  754. 'title': 'WALL-TO-GORTAT',
  755. 'timestamp': 1422285291,
  756. 'upload_date': '20150126',
  757. },
  758. 'add_ie': ['Viddler'],
  759. },
  760. # Libsyn embed
  761. {
  762. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  763. 'info_dict': {
  764. 'id': '3377616',
  765. 'ext': 'mp3',
  766. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  767. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  768. 'upload_date': '20150220',
  769. },
  770. },
  771. # jwplayer YouTube
  772. {
  773. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  774. 'info_dict': {
  775. 'id': 'Mrj4DVp2zeA',
  776. 'ext': 'mp4',
  777. 'upload_date': '20150212',
  778. 'uploader': 'The National Archives UK',
  779. 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
  780. 'uploader_id': 'NationalArchives08',
  781. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  782. },
  783. },
  784. # rtl.nl embed
  785. {
  786. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  787. 'playlist_mincount': 5,
  788. 'info_dict': {
  789. 'id': 'aanslagen-kopenhagen',
  790. 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
  791. }
  792. },
  793. # Zapiks embed
  794. {
  795. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  796. 'info_dict': {
  797. 'id': '118046',
  798. 'ext': 'mp4',
  799. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  800. }
  801. },
  802. # Kaltura embed
  803. {
  804. 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
  805. 'info_dict': {
  806. 'id': '1_eergr3h1',
  807. 'ext': 'mp4',
  808. 'upload_date': '20150226',
  809. 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
  810. 'timestamp': int,
  811. 'title': 'John Carlson Postgame 2/25/15',
  812. },
  813. },
  814. # Kaltura embed (different embed code)
  815. {
  816. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  817. 'info_dict': {
  818. 'id': '1_a52wc67y',
  819. 'ext': 'flv',
  820. 'upload_date': '20150127',
  821. 'uploader_id': 'PremierMedia',
  822. 'timestamp': int,
  823. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  824. },
  825. },
  826. # Kaltura embed protected with referrer
  827. {
  828. 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
  829. 'info_dict': {
  830. 'id': '1_g4fbemnq',
  831. 'ext': 'mp4',
  832. 'title': 'Violetta - Achter De Schermen - Ruggero',
  833. 'description': 'Achter de schermen met Ruggero',
  834. 'timestamp': 1435133761,
  835. 'upload_date': '20150624',
  836. 'uploader_id': 'echojecka',
  837. },
  838. },
  839. # Eagle.Platform embed (generic URL)
  840. {
  841. 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
  842. 'info_dict': {
  843. 'id': '227304',
  844. 'ext': 'mp4',
  845. 'title': 'Навальный вышел на свободу',
  846. 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
  847. 'thumbnail': 're:^https?://.*\.jpg$',
  848. 'duration': 87,
  849. 'view_count': int,
  850. 'age_limit': 0,
  851. },
  852. },
  853. # ClipYou (Eagle.Platform) embed (custom URL)
  854. {
  855. 'url': 'http://muz-tv.ru/play/7129/',
  856. 'info_dict': {
  857. 'id': '12820',
  858. 'ext': 'mp4',
  859. 'title': "'O Sole Mio",
  860. 'thumbnail': 're:^https?://.*\.jpg$',
  861. 'duration': 216,
  862. 'view_count': int,
  863. },
  864. },
  865. # Pladform embed
  866. {
  867. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  868. 'info_dict': {
  869. 'id': '100183293',
  870. 'ext': 'mp4',
  871. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  872. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  873. 'thumbnail': 're:^https?://.*\.jpg$',
  874. 'duration': 694,
  875. 'age_limit': 0,
  876. },
  877. },
  878. # Playwire embed
  879. {
  880. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  881. 'info_dict': {
  882. 'id': '3519514',
  883. 'ext': 'mp4',
  884. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  885. 'thumbnail': 're:^https?://.*\.png$',
  886. 'duration': 45.115,
  887. },
  888. },
  889. # 5min embed
  890. {
  891. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  892. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  893. 'info_dict': {
  894. 'id': '518726732',
  895. 'ext': 'mp4',
  896. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  897. },
  898. },
  899. # SVT embed
  900. {
  901. 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
  902. 'info_dict': {
  903. 'id': '2900353',
  904. 'ext': 'flv',
  905. 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
  906. 'duration': 27,
  907. 'age_limit': 0,
  908. },
  909. },
  910. # Crooks and Liars embed
  911. {
  912. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  913. 'info_dict': {
  914. 'id': '8RUoRhRi',
  915. 'ext': 'mp4',
  916. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  917. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  918. 'timestamp': 1428207000,
  919. 'upload_date': '20150405',
  920. 'uploader': 'Heather',
  921. },
  922. },
  923. # Crooks and Liars external embed
  924. {
  925. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  926. 'info_dict': {
  927. 'id': 'MTE3MjUtMzQ2MzA',
  928. 'ext': 'mp4',
  929. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  930. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  931. 'timestamp': 1265032391,
  932. 'upload_date': '20100201',
  933. 'uploader': 'Heather',
  934. },
  935. },
  936. # NBC Sports vplayer embed
  937. {
  938. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  939. 'info_dict': {
  940. 'id': 'ln7x1qSThw4k',
  941. 'ext': 'flv',
  942. 'title': "PFT Live: New leader in the 'new-look' defense",
  943. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  944. },
  945. },
  946. # UDN embed
  947. {
  948. 'url': 'http://www.udn.com/news/story/7314/822787',
  949. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  950. 'info_dict': {
  951. 'id': '300346',
  952. 'ext': 'mp4',
  953. 'title': '中一中男師變性 全校師生力挺',
  954. 'thumbnail': 're:^https?://.*\.jpg$',
  955. }
  956. },
  957. # Ooyala embed
  958. {
  959. 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
  960. 'info_dict': {
  961. 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
  962. 'ext': 'mp4',
  963. 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
  964. 'title': 'This is what separates the Excel masters from the wannabes',
  965. 'duration': 191.933,
  966. },
  967. 'params': {
  968. # m3u8 downloads
  969. 'skip_download': True,
  970. }
  971. },
  972. # Contains a SMIL manifest
  973. {
  974. 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
  975. 'info_dict': {
  976. 'id': 'file',
  977. 'ext': 'flv',
  978. 'title': '+ Football: Lottery Champions League Europe',
  979. 'uploader': 'www.telewebion.com',
  980. },
  981. 'params': {
  982. # rtmpe downloads
  983. 'skip_download': True,
  984. }
  985. },
  986. # Brightcove URL in single quotes
  987. {
  988. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  989. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  990. 'info_dict': {
  991. 'id': '4255764656001',
  992. 'ext': 'mp4',
  993. 'title': 'SN Presents: Russell Martin, World Citizen',
  994. '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.',
  995. 'uploader': 'Rogers Sportsnet',
  996. },
  997. },
  998. # Dailymotion Cloud video
  999. {
  1000. 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
  1001. 'md5': '49444254273501a64675a7e68c502681',
  1002. 'info_dict': {
  1003. 'id': '5585de919473990de4bee11b',
  1004. 'ext': 'mp4',
  1005. 'title': 'Le débat',
  1006. 'thumbnail': 're:^https?://.*\.jpe?g$',
  1007. }
  1008. },
  1009. # OnionStudios embed
  1010. {
  1011. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1012. 'info_dict': {
  1013. 'id': '2855',
  1014. 'ext': 'mp4',
  1015. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1016. 'thumbnail': 're:^https?://.*\.jpe?g$',
  1017. 'uploader': 'ClickHole',
  1018. 'uploader_id': 'clickhole',
  1019. }
  1020. },
  1021. # SnagFilms embed
  1022. {
  1023. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1024. 'info_dict': {
  1025. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1026. 'ext': 'mp4',
  1027. 'title': '#whilewewatch',
  1028. }
  1029. },
  1030. # AdobeTVVideo embed
  1031. {
  1032. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1033. 'md5': '43662b577c018ad707a63766462b1e87',
  1034. 'info_dict': {
  1035. 'id': '2456',
  1036. 'ext': 'mp4',
  1037. 'title': 'New experience with Acrobat DC',
  1038. 'description': 'New experience with Acrobat DC',
  1039. 'duration': 248.667,
  1040. },
  1041. },
  1042. # ScreenwaveMedia embed
  1043. {
  1044. 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
  1045. 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
  1046. 'info_dict': {
  1047. 'id': 'cinemasnob-55d26273809dd',
  1048. 'ext': 'mp4',
  1049. 'title': 'cinemasnob',
  1050. },
  1051. },
  1052. # BrightcoveInPageEmbed embed
  1053. {
  1054. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1055. 'info_dict': {
  1056. 'id': '4238694884001',
  1057. 'ext': 'flv',
  1058. 'title': 'Tabletop: Dread, Last Thoughts',
  1059. 'description': 'Tabletop: Dread, Last Thoughts',
  1060. 'duration': 51690,
  1061. },
  1062. },
  1063. # JWPlayer with M3U8
  1064. {
  1065. 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
  1066. 'info_dict': {
  1067. 'id': 'playlist',
  1068. 'ext': 'mp4',
  1069. 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
  1070. 'uploader': 'ren.tv',
  1071. },
  1072. 'params': {
  1073. # m3u8 downloads
  1074. 'skip_download': True,
  1075. }
  1076. }
  1077. ]
  1078. def report_following_redirect(self, new_url):
  1079. """Report information extraction."""
  1080. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  1081. def _extract_rss(self, url, video_id, doc):
  1082. playlist_title = doc.find('./channel/title').text
  1083. playlist_desc_el = doc.find('./channel/description')
  1084. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  1085. entries = []
  1086. for it in doc.findall('./channel/item'):
  1087. next_url = xpath_text(it, 'link', fatal=False)
  1088. if not next_url:
  1089. enclosure_nodes = it.findall('./enclosure')
  1090. for e in enclosure_nodes:
  1091. next_url = e.attrib.get('url')
  1092. if next_url:
  1093. break
  1094. if not next_url:
  1095. continue
  1096. entries.append({
  1097. '_type': 'url',
  1098. 'url': next_url,
  1099. 'title': it.find('title').text,
  1100. })
  1101. return {
  1102. '_type': 'playlist',
  1103. 'id': url,
  1104. 'title': playlist_title,
  1105. 'description': playlist_desc,
  1106. 'entries': entries,
  1107. }
  1108. def _extract_camtasia(self, url, video_id, webpage):
  1109. """ Returns None if no camtasia video can be found. """
  1110. camtasia_cfg = self._search_regex(
  1111. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  1112. webpage, 'camtasia configuration file', default=None)
  1113. if camtasia_cfg is None:
  1114. return None
  1115. title = self._html_search_meta('DC.title', webpage, fatal=True)
  1116. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  1117. camtasia_cfg = self._download_xml(
  1118. camtasia_url, video_id,
  1119. note='Downloading camtasia configuration',
  1120. errnote='Failed to download camtasia configuration')
  1121. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  1122. entries = []
  1123. for n in fileset_node.getchildren():
  1124. url_n = n.find('./uri')
  1125. if url_n is None:
  1126. continue
  1127. entries.append({
  1128. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  1129. 'title': '%s - %s' % (title, n.tag),
  1130. 'url': compat_urlparse.urljoin(url, url_n.text),
  1131. 'duration': float_or_none(n.find('./duration').text),
  1132. })
  1133. return {
  1134. '_type': 'playlist',
  1135. 'entries': entries,
  1136. 'title': title,
  1137. }
  1138. def _real_extract(self, url):
  1139. if url.startswith('//'):
  1140. return {
  1141. '_type': 'url',
  1142. 'url': self.http_scheme() + url,
  1143. }
  1144. parsed_url = compat_urlparse.urlparse(url)
  1145. if not parsed_url.scheme:
  1146. default_search = self._downloader.params.get('default_search')
  1147. if default_search is None:
  1148. default_search = 'fixup_error'
  1149. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  1150. if '/' in url:
  1151. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  1152. return self.url_result('http://' + url)
  1153. elif default_search != 'fixup_error':
  1154. if default_search == 'auto_warning':
  1155. if re.match(r'^(?:url|URL)$', url):
  1156. raise ExtractorError(
  1157. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  1158. expected=True)
  1159. else:
  1160. self._downloader.report_warning(
  1161. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  1162. return self.url_result('ytsearch:' + url)
  1163. if default_search in ('error', 'fixup_error'):
  1164. raise ExtractorError(
  1165. '%r is not a valid URL. '
  1166. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  1167. % (url, url), expected=True)
  1168. else:
  1169. if ':' not in default_search:
  1170. default_search += ':'
  1171. return self.url_result(default_search + url)
  1172. url, smuggled_data = unsmuggle_url(url)
  1173. force_videoid = None
  1174. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  1175. if smuggled_data and 'force_videoid' in smuggled_data:
  1176. force_videoid = smuggled_data['force_videoid']
  1177. video_id = force_videoid
  1178. else:
  1179. video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
  1180. self.to_screen('%s: Requesting header' % video_id)
  1181. head_req = HEADRequest(url)
  1182. head_response = self._request_webpage(
  1183. head_req, video_id,
  1184. note=False, errnote='Could not send HEAD request to %s' % url,
  1185. fatal=False)
  1186. if head_response is not False:
  1187. # Check for redirect
  1188. new_url = head_response.geturl()
  1189. if url != new_url:
  1190. self.report_following_redirect(new_url)
  1191. if force_videoid:
  1192. new_url = smuggle_url(
  1193. new_url, {'force_videoid': force_videoid})
  1194. return self.url_result(new_url)
  1195. full_response = None
  1196. if head_response is False:
  1197. request = sanitized_Request(url)
  1198. request.add_header('Accept-Encoding', '*')
  1199. full_response = self._request_webpage(request, video_id)
  1200. head_response = full_response
  1201. # Check for direct link to a video
  1202. content_type = head_response.headers.get('Content-Type', '')
  1203. m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
  1204. if m:
  1205. upload_date = unified_strdate(
  1206. head_response.headers.get('Last-Modified'))
  1207. return {
  1208. 'id': video_id,
  1209. 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
  1210. 'direct': True,
  1211. 'formats': [{
  1212. 'format_id': m.group('format_id'),
  1213. 'url': url,
  1214. 'vcodec': 'none' if m.group('type') == 'audio' else None
  1215. }],
  1216. 'upload_date': upload_date,
  1217. }
  1218. if not self._downloader.params.get('test', False) and not is_intentional:
  1219. force = self._downloader.params.get('force_generic_extractor', False)
  1220. self._downloader.report_warning(
  1221. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  1222. if not full_response:
  1223. request = sanitized_Request(url)
  1224. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  1225. # making it impossible to download only chunk of the file (yet we need only 512kB to
  1226. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  1227. # that will always result in downloading the whole file that is not desirable.
  1228. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  1229. # to accept raw bytes and being able to download only a chunk.
  1230. # It may probably better to solve this by checking Content-Type for application/octet-stream
  1231. # after HEAD request finishes, but not sure if we can rely on this.
  1232. request.add_header('Accept-Encoding', '*')
  1233. full_response = self._request_webpage(request, video_id)
  1234. # Maybe it's a direct link to a video?
  1235. # Be careful not to download the whole thing!
  1236. first_bytes = full_response.read(512)
  1237. if not is_html(first_bytes):
  1238. self._downloader.report_warning(
  1239. 'URL could be a direct video link, returning it as such.')
  1240. upload_date = unified_strdate(
  1241. head_response.headers.get('Last-Modified'))
  1242. return {
  1243. 'id': video_id,
  1244. 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
  1245. 'direct': True,
  1246. 'url': url,
  1247. 'upload_date': upload_date,
  1248. }
  1249. webpage = self._webpage_read_content(
  1250. full_response, url, video_id, prefix=first_bytes)
  1251. self.report_extraction(video_id)
  1252. # Is it an RSS feed, a SMIL file or a XSPF playlist?
  1253. try:
  1254. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  1255. if doc.tag == 'rss':
  1256. return self._extract_rss(url, video_id, doc)
  1257. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  1258. return self._parse_smil(doc, url, video_id)
  1259. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  1260. return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
  1261. except compat_xml_parse_error:
  1262. pass
  1263. # Is it a Camtasia project?
  1264. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  1265. if camtasia_res is not None:
  1266. return camtasia_res
  1267. # Sometimes embedded video player is hidden behind percent encoding
  1268. # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
  1269. # Unescaping the whole page allows to handle those cases in a generic way
  1270. webpage = compat_urllib_parse_unquote(webpage)
  1271. # it's tempting to parse this further, but you would
  1272. # have to take into account all the variations like
  1273. # Video Title - Site Name
  1274. # Site Name | Video Title
  1275. # Video Title - Tagline | Site Name
  1276. # and so on and so forth; it's just not practical
  1277. video_title = self._html_search_regex(
  1278. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  1279. default='video')
  1280. # Try to detect age limit automatically
  1281. age_limit = self._rta_search(webpage)
  1282. # And then there are the jokers who advertise that they use RTA,
  1283. # but actually don't.
  1284. AGE_LIMIT_MARKERS = [
  1285. r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
  1286. ]
  1287. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  1288. age_limit = 18
  1289. # video uploader is domain name
  1290. video_uploader = self._search_regex(
  1291. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  1292. # Helper method
  1293. def _playlist_from_matches(matches, getter=None, ie=None):
  1294. urlrs = orderedSet(
  1295. self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
  1296. for m in matches)
  1297. return self.playlist_result(
  1298. urlrs, playlist_id=video_id, playlist_title=video_title)
  1299. # Look for Brightcove Legacy Studio embeds
  1300. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  1301. if bc_urls:
  1302. self.to_screen('Brightcove video detected.')
  1303. entries = [{
  1304. '_type': 'url',
  1305. 'url': smuggle_url(bc_url, {'Referer': url}),
  1306. 'ie_key': 'BrightcoveLegacy'
  1307. } for bc_url in bc_urls]
  1308. return {
  1309. '_type': 'playlist',
  1310. 'title': video_title,
  1311. 'id': video_id,
  1312. 'entries': entries,
  1313. }
  1314. # Look for Brightcove New Studio embeds
  1315. bc_urls = BrightcoveNewIE._extract_urls(webpage)
  1316. if bc_urls:
  1317. return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
  1318. # Look for embedded rtl.nl player
  1319. matches = re.findall(
  1320. r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
  1321. webpage)
  1322. if matches:
  1323. return _playlist_from_matches(matches, ie='RtlNl')
  1324. vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
  1325. if vimeo_url is not None:
  1326. return self.url_result(vimeo_url)
  1327. vid_me_embed_url = self._search_regex(
  1328. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  1329. webpage, 'vid.me embed', default=None)
  1330. if vid_me_embed_url is not None:
  1331. return self.url_result(vid_me_embed_url, 'Vidme')
  1332. # Look for embedded YouTube player
  1333. matches = re.findall(r'''(?x)
  1334. (?:
  1335. <iframe[^>]+?src=|
  1336. data-video-url=|
  1337. <embed[^>]+?src=|
  1338. embedSWF\(?:\s*|
  1339. new\s+SWFObject\(
  1340. )
  1341. (["\'])
  1342. (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
  1343. (?:embed|v|p)/.+?)
  1344. \1''', webpage)
  1345. if matches:
  1346. return _playlist_from_matches(
  1347. matches, lambda m: unescapeHTML(m[1]))
  1348. # Look for lazyYT YouTube embed
  1349. matches = re.findall(
  1350. r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
  1351. if matches:
  1352. return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
  1353. # Look for embedded Dailymotion player
  1354. matches = re.findall(
  1355. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
  1356. if matches:
  1357. return _playlist_from_matches(
  1358. matches, lambda m: unescapeHTML(m[1]))
  1359. # Look for embedded Dailymotion playlist player (#3822)
  1360. m = re.search(
  1361. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  1362. if m:
  1363. playlists = re.findall(
  1364. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  1365. if playlists:
  1366. return _playlist_from_matches(
  1367. playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
  1368. # Look for embedded Wistia player
  1369. match = re.search(
  1370. r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
  1371. if match:
  1372. embed_url = self._proto_relative_url(
  1373. unescapeHTML(match.group('url')))
  1374. return {
  1375. '_type': 'url_transparent',
  1376. 'url': embed_url,
  1377. 'ie_key': 'Wistia',
  1378. 'uploader': video_uploader,
  1379. 'title': video_title,
  1380. 'id': video_id,
  1381. }
  1382. match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
  1383. if match:
  1384. return {
  1385. '_type': 'url_transparent',
  1386. 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
  1387. 'ie_key': 'Wistia',
  1388. 'uploader': video_uploader,
  1389. 'title': video_title,
  1390. 'id': match.group('id')
  1391. }
  1392. # Look for SVT player
  1393. svt_url = SVTIE._extract_url(webpage)
  1394. if svt_url:
  1395. return self.url_result(svt_url, 'SVT')
  1396. # Look for embedded condenast player
  1397. matches = re.findall(
  1398. r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
  1399. webpage)
  1400. if matches:
  1401. return {
  1402. '_type': 'playlist',
  1403. 'entries': [{
  1404. '_type': 'url',
  1405. 'ie_key': 'CondeNast',
  1406. 'url': ma,
  1407. } for ma in matches],
  1408. 'title': video_title,
  1409. 'id': video_id,
  1410. }
  1411. # Look for Bandcamp pages with custom domain
  1412. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  1413. if mobj is not None:
  1414. burl = unescapeHTML(mobj.group(1))
  1415. # Don't set the extractor because it can be a track url or an album
  1416. return self.url_result(burl)
  1417. # Look for embedded Vevo player
  1418. mobj = re.search(
  1419. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  1420. if mobj is not None:
  1421. return self.url_result(mobj.group('url'))
  1422. # Look for embedded Viddler player
  1423. mobj = re.search(
  1424. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  1425. webpage)
  1426. if mobj is not None:
  1427. return self.url_result(mobj.group('url'))
  1428. # Look for NYTimes player
  1429. mobj = re.search(
  1430. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  1431. webpage)
  1432. if mobj is not None:
  1433. return self.url_result(mobj.group('url'))
  1434. # Look for Libsyn player
  1435. mobj = re.search(
  1436. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  1437. if mobj is not None:
  1438. return self.url_result(mobj.group('url'))
  1439. # Look for Ooyala videos
  1440. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
  1441. re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
  1442. re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
  1443. re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  1444. if mobj is not None:
  1445. return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
  1446. # Look for multiple Ooyala embeds on SBN network websites
  1447. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  1448. if mobj is not None:
  1449. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  1450. if embeds:
  1451. return _playlist_from_matches(
  1452. embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  1453. # Look for Aparat videos
  1454. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  1455. if mobj is not None:
  1456. return self.url_result(mobj.group(1), 'Aparat')
  1457. # Look for MPORA videos
  1458. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  1459. if mobj is not None:
  1460. return self.url_result(mobj.group(1), 'Mpora')
  1461. # Look for embedded NovaMov-based player
  1462. mobj = re.search(
  1463. r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
  1464. (?P<url>http://(?:(?:embed|www)\.)?
  1465. (?:novamov\.com|
  1466. nowvideo\.(?:ch|sx|eu|at|ag|co)|
  1467. videoweed\.(?:es|com)|
  1468. movshare\.(?:net|sx|ag)|
  1469. divxstage\.(?:eu|net|ch|co|at|ag))
  1470. /embed\.php.+?)\1''', webpage)
  1471. if mobj is not None:
  1472. return self.url_result(mobj.group('url'))
  1473. # Look for embedded Facebook player
  1474. mobj = re.search(
  1475. r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
  1476. if mobj is not None:
  1477. return self.url_result(mobj.group('url'), 'Facebook')
  1478. # Look for embedded VK player
  1479. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  1480. if mobj is not None:
  1481. return self.url_result(mobj.group('url'), 'VK')
  1482. # Look for embedded ivi player
  1483. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  1484. if mobj is not None:
  1485. return self.url_result(mobj.group('url'), 'Ivi')
  1486. # Look for embedded Huffington Post player
  1487. mobj = re.search(
  1488. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  1489. if mobj is not None:
  1490. return self.url_result(mobj.group('url'), 'HuffPost')
  1491. # Look for embed.ly
  1492. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  1493. if mobj is not None:
  1494. return self.url_result(mobj.group('url'))
  1495. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  1496. if mobj is not None:
  1497. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  1498. # Look for funnyordie embed
  1499. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  1500. if matches:
  1501. return _playlist_from_matches(
  1502. matches, getter=unescapeHTML, ie='FunnyOrDie')
  1503. # Look for BBC iPlayer embed
  1504. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  1505. if matches:
  1506. return _playlist_from_matches(matches, ie='BBCCoUk')
  1507. # Look for embedded RUTV player
  1508. rutv_url = RUTVIE._extract_url(webpage)
  1509. if rutv_url:
  1510. return self.url_result(rutv_url, 'RUTV')
  1511. # Look for embedded TVC player
  1512. tvc_url = TVCIE._extract_url(webpage)
  1513. if tvc_url:
  1514. return self.url_result(tvc_url, 'TVC')
  1515. # Look for embedded SportBox player
  1516. sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
  1517. if sportbox_urls:
  1518. return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
  1519. # Look for embedded PornHub player
  1520. pornhub_url = PornHubIE._extract_url(webpage)
  1521. if pornhub_url:
  1522. return self.url_result(pornhub_url, 'PornHub')
  1523. # Look for embedded XHamster player
  1524. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  1525. if xhamster_urls:
  1526. return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
  1527. # Look for embedded Tvigle player
  1528. mobj = re.search(
  1529. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  1530. if mobj is not None:
  1531. return self.url_result(mobj.group('url'), 'Tvigle')
  1532. # Look for embedded TED player
  1533. mobj = re.search(
  1534. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  1535. if mobj is not None:
  1536. return self.url_result(mobj.group('url'), 'TED')
  1537. # Look for embedded Ustream videos
  1538. mobj = re.search(
  1539. r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
  1540. if mobj is not None:
  1541. return self.url_result(mobj.group('url'), 'Ustream')
  1542. # Look for embedded arte.tv player
  1543. mobj = re.search(
  1544. r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
  1545. webpage)
  1546. if mobj is not None:
  1547. return self.url_result(mobj.group('url'), 'ArteTVEmbed')
  1548. # Look for embedded francetv player
  1549. mobj = re.search(
  1550. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  1551. webpage)
  1552. if mobj is not None:
  1553. return self.url_result(mobj.group('url'))
  1554. # Look for embedded smotri.com player
  1555. smotri_url = SmotriIE._extract_url(webpage)
  1556. if smotri_url:
  1557. return self.url_result(smotri_url, 'Smotri')
  1558. # Look for embedded Myvi.ru player
  1559. myvi_url = MyviIE._extract_url(webpage)
  1560. if myvi_url:
  1561. return self.url_result(myvi_url)
  1562. # Look for embeded soundcloud player
  1563. mobj = re.search(
  1564. r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
  1565. webpage)
  1566. if mobj is not None:
  1567. url = unescapeHTML(mobj.group('url'))
  1568. return self.url_result(url)
  1569. # Look for embedded vulture.com player
  1570. mobj = re.search(
  1571. r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
  1572. webpage)
  1573. if mobj is not None:
  1574. url = unescapeHTML(mobj.group('url'))
  1575. return self.url_result(url, ie='Vulture')
  1576. # Look for embedded mtvservices player
  1577. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  1578. if mtvservices_url:
  1579. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  1580. # Look for embedded yahoo player
  1581. mobj = re.search(
  1582. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  1583. webpage)
  1584. if mobj is not None:
  1585. return self.url_result(mobj.group('url'), 'Yahoo')
  1586. # Look for embedded sbs.com.au player
  1587. mobj = re.search(
  1588. r'''(?x)
  1589. (?:
  1590. <meta\s+property="og:video"\s+content=|
  1591. <iframe[^>]+?src=
  1592. )
  1593. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  1594. webpage)
  1595. if mobj is not None:
  1596. return self.url_result(mobj.group('url'), 'SBS')
  1597. # Look for embedded Cinchcast player
  1598. mobj = re.search(
  1599. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  1600. webpage)
  1601. if mobj is not None:
  1602. return self.url_result(mobj.group('url'), 'Cinchcast')
  1603. mobj = re.search(
  1604. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  1605. webpage)
  1606. if not mobj:
  1607. mobj = re.search(
  1608. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  1609. webpage)
  1610. if mobj is not None:
  1611. return self.url_result(mobj.group('url'), 'MLB')
  1612. mobj = re.search(
  1613. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  1614. webpage)
  1615. if mobj is not None:
  1616. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  1617. mobj = re.search(
  1618. r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
  1619. webpage)
  1620. if mobj is not None:
  1621. return self.url_result(mobj.group('url'), 'Livestream')
  1622. # Look for Zapiks embed
  1623. mobj = re.search(
  1624. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  1625. if mobj is not None:
  1626. return self.url_result(mobj.group('url'), 'Zapiks')
  1627. # Look for Kaltura embeds
  1628. mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
  1629. re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
  1630. if mobj is not None:
  1631. return self.url_result(smuggle_url(
  1632. 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
  1633. {'source_url': url}), 'Kaltura')
  1634. # Look for Eagle.Platform embeds
  1635. mobj = re.search(
  1636. r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
  1637. if mobj is not None:
  1638. return self.url_result(mobj.group('url'), 'EaglePlatform')
  1639. # Look for ClipYou (uses Eagle.Platform) embeds
  1640. mobj = re.search(
  1641. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  1642. if mobj is not None:
  1643. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  1644. # Look for Pladform embeds
  1645. pladform_url = PladformIE._extract_url(webpage)
  1646. if pladform_url:
  1647. return self.url_result(pladform_url)
  1648. # Look for Playwire embeds
  1649. mobj = re.search(
  1650. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  1651. if mobj is not None:
  1652. return self.url_result(mobj.group('url'))
  1653. # Look for 5min embeds
  1654. mobj = re.search(
  1655. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  1656. if mobj is not None:
  1657. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  1658. # Look for Crooks and Liars embeds
  1659. mobj = re.search(
  1660. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  1661. if mobj is not None:
  1662. return self.url_result(mobj.group('url'))
  1663. # Look for NBC Sports VPlayer embeds
  1664. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  1665. if nbc_sports_url:
  1666. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  1667. # Look for Google Drive embeds
  1668. google_drive_url = GoogleDriveIE._extract_url(webpage)
  1669. if google_drive_url:
  1670. return self.url_result(google_drive_url, 'GoogleDrive')
  1671. # Look for UDN embeds
  1672. mobj = re.search(
  1673. r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  1674. if mobj is not None:
  1675. return self.url_result(
  1676. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  1677. # Look for Senate ISVP iframe
  1678. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  1679. if senate_isvp_url:
  1680. return self.url_result(senate_isvp_url, 'SenateISVP')
  1681. # Look for Dailymotion Cloud videos
  1682. dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
  1683. if dmcloud_url:
  1684. return self.url_result(dmcloud_url, 'DailymotionCloud')
  1685. # Look for OnionStudios embeds
  1686. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  1687. if onionstudios_url:
  1688. return self.url_result(onionstudios_url)
  1689. # Look for SnagFilms embeds
  1690. snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
  1691. if snagfilms_url:
  1692. return self.url_result(snagfilms_url)
  1693. # Look for JWPlatform embeds
  1694. jwplatform_url = JWPlatformIE._extract_url(webpage)
  1695. if jwplatform_url:
  1696. return self.url_result(jwplatform_url, 'JWPlatform')
  1697. # Look for ScreenwaveMedia embeds
  1698. mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
  1699. if mobj is not None:
  1700. return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
  1701. # Look for Ulltimedia embeds
  1702. ultimedia_url = UltimediaIE._extract_url(webpage)
  1703. if ultimedia_url:
  1704. return self.url_result(self._proto_relative_url(ultimedia_url), 'Ultimedia')
  1705. # Look for AdobeTVVideo embeds
  1706. mobj = re.search(
  1707. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  1708. webpage)
  1709. if mobj is not None:
  1710. return self.url_result(
  1711. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  1712. 'AdobeTVVideo')
  1713. def check_video(vurl):
  1714. if YoutubeIE.suitable(vurl):
  1715. return True
  1716. vpath = compat_urlparse.urlparse(vurl).path
  1717. vext = determine_ext(vpath)
  1718. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
  1719. def filter_video(urls):
  1720. return list(filter(check_video, urls))
  1721. # Start with something easy: JW Player in SWFObject
  1722. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  1723. if not found:
  1724. # Look for gorilla-vid style embedding
  1725. found = filter_video(re.findall(r'''(?sx)
  1726. (?:
  1727. jw_plugins|
  1728. JWPlayerOptions|
  1729. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  1730. )
  1731. .*?
  1732. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  1733. if not found:
  1734. # Broaden the search a little bit
  1735. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  1736. if not found:
  1737. # Broaden the findall a little bit: JWPlayer JS loader
  1738. found = filter_video(re.findall(
  1739. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  1740. if not found:
  1741. # Flow player
  1742. found = filter_video(re.findall(r'''(?xs)
  1743. flowplayer\("[^"]+",\s*
  1744. \{[^}]+?\}\s*,
  1745. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  1746. ["']?url["']?\s*:\s*["']([^"']+)["']
  1747. ''', webpage))
  1748. if not found:
  1749. # Cinerama player
  1750. found = re.findall(
  1751. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  1752. if not found:
  1753. # Try to find twitter cards info
  1754. found = filter_video(re.findall(
  1755. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  1756. if not found:
  1757. # We look for Open Graph info:
  1758. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  1759. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  1760. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  1761. if m_video_type is not None:
  1762. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  1763. if not found:
  1764. # HTML5 video
  1765. found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
  1766. if not found:
  1767. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  1768. found = re.search(
  1769. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  1770. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  1771. webpage)
  1772. if not found:
  1773. # Look also in Refresh HTTP header
  1774. refresh_header = head_response.headers.get('Refresh')
  1775. if refresh_header:
  1776. # In python 2 response HTTP headers are bytestrings
  1777. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  1778. refresh_header = refresh_header.decode('iso-8859-1')
  1779. found = re.search(REDIRECT_REGEX, refresh_header)
  1780. if found:
  1781. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  1782. self.report_following_redirect(new_url)
  1783. return {
  1784. '_type': 'url',
  1785. 'url': new_url,
  1786. }
  1787. if not found:
  1788. raise UnsupportedError(url)
  1789. entries = []
  1790. for video_url in found:
  1791. video_url = video_url.replace('\\/', '/')
  1792. video_url = compat_urlparse.urljoin(url, video_url)
  1793. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  1794. # Sometimes, jwplayer extraction will result in a YouTube URL
  1795. if YoutubeIE.suitable(video_url):
  1796. entries.append(self.url_result(video_url, 'Youtube'))
  1797. continue
  1798. # here's a fun little line of code for you:
  1799. video_id = os.path.splitext(video_id)[0]
  1800. entry_info_dict = {
  1801. 'id': video_id,
  1802. 'uploader': video_uploader,
  1803. 'title': video_title,
  1804. 'age_limit': age_limit,
  1805. }
  1806. ext = determine_ext(video_url)
  1807. if ext == 'smil':
  1808. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  1809. elif ext == 'xspf':
  1810. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  1811. elif ext == 'm3u8':
  1812. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  1813. else:
  1814. entry_info_dict['url'] = video_url
  1815. entries.append(entry_info_dict)
  1816. if len(entries) == 1:
  1817. return entries[0]
  1818. else:
  1819. for num, e in enumerate(entries, start=1):
  1820. # 'url' results don't have a title
  1821. if e.get('title') is not None:
  1822. e['title'] = '%s (%d)' % (e['title'], num)
  1823. return {
  1824. '_type': 'playlist',
  1825. 'entries': entries,
  1826. }