generic.py 77 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926
  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. class GenericIE(InfoExtractor):
  54. IE_DESC = 'Generic downloader that works on some sites'
  55. _VALID_URL = r'.*'
  56. IE_NAME = 'generic'
  57. _TESTS = [
  58. # Direct link to a video
  59. {
  60. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  61. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  62. 'info_dict': {
  63. 'id': 'trailer',
  64. 'ext': 'mp4',
  65. 'title': 'trailer',
  66. 'upload_date': '20100513',
  67. }
  68. },
  69. # Direct link to media delivered compressed (until Accept-Encoding is *)
  70. {
  71. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  72. 'md5': '128c42e68b13950268b648275386fc74',
  73. 'info_dict': {
  74. 'id': 'FictionJunction-Parallel_Hearts',
  75. 'ext': 'flac',
  76. 'title': 'FictionJunction-Parallel_Hearts',
  77. 'upload_date': '20140522',
  78. },
  79. 'expected_warnings': [
  80. 'URL could be a direct video link, returning it as such.'
  81. ]
  82. },
  83. # Direct download with broken HEAD
  84. {
  85. 'url': 'http://ai-radio.org:8000/radio.opus',
  86. 'info_dict': {
  87. 'id': 'radio',
  88. 'ext': 'opus',
  89. 'title': 'radio',
  90. },
  91. 'params': {
  92. 'skip_download': True, # infinite live stream
  93. },
  94. 'expected_warnings': [
  95. r'501.*Not Implemented'
  96. ],
  97. },
  98. # Direct link with incorrect MIME type
  99. {
  100. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  101. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  102. 'info_dict': {
  103. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  104. 'id': '5_Lennart_Poettering_-_Systemd',
  105. 'ext': 'webm',
  106. 'title': '5_Lennart_Poettering_-_Systemd',
  107. 'upload_date': '20141120',
  108. },
  109. 'expected_warnings': [
  110. 'URL could be a direct video link, returning it as such.'
  111. ]
  112. },
  113. # RSS feed
  114. {
  115. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  116. 'info_dict': {
  117. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  118. 'title': 'Zero Punctuation',
  119. 'description': 're:.*groundbreaking video review series.*'
  120. },
  121. 'playlist_mincount': 11,
  122. },
  123. # RSS feed with enclosure
  124. {
  125. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  126. 'info_dict': {
  127. 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  128. 'ext': 'm4v',
  129. 'upload_date': '20150228',
  130. 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  131. }
  132. },
  133. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  134. {
  135. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  136. 'info_dict': {
  137. 'id': 'smil',
  138. 'ext': 'mp4',
  139. 'title': 'Automatics, robotics and biocybernetics',
  140. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  141. 'upload_date': '20130627',
  142. 'formats': 'mincount:16',
  143. 'subtitles': 'mincount:1',
  144. },
  145. 'params': {
  146. 'force_generic_extractor': True,
  147. 'skip_download': True,
  148. },
  149. },
  150. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  151. {
  152. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  153. 'info_dict': {
  154. 'id': 'hds',
  155. 'ext': 'flv',
  156. 'title': 'hds',
  157. 'formats': 'mincount:1',
  158. },
  159. 'params': {
  160. 'skip_download': True,
  161. },
  162. },
  163. # SMIL from https://www.restudy.dk/video/play/id/1637
  164. {
  165. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  166. 'info_dict': {
  167. 'id': 'video_1637',
  168. 'ext': 'flv',
  169. 'title': 'video_1637',
  170. 'formats': 'mincount:3',
  171. },
  172. 'params': {
  173. 'skip_download': True,
  174. },
  175. },
  176. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  177. {
  178. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  179. 'info_dict': {
  180. 'id': 'smil-service',
  181. 'ext': 'flv',
  182. 'title': 'smil-service',
  183. 'formats': 'mincount:1',
  184. },
  185. 'params': {
  186. 'skip_download': True,
  187. },
  188. },
  189. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  190. {
  191. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  192. 'info_dict': {
  193. 'id': '4719370',
  194. 'ext': 'mp4',
  195. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  196. 'formats': 'mincount:3',
  197. },
  198. 'params': {
  199. 'skip_download': True,
  200. },
  201. },
  202. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  203. {
  204. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  205. 'info_dict': {
  206. 'id': 'mZlp2ctYIUEB',
  207. 'ext': 'mp4',
  208. 'title': 'Tikibad ontruimd wegens brand',
  209. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  210. 'thumbnail': 're:^https?://.*\.jpg$',
  211. 'duration': 33,
  212. },
  213. 'params': {
  214. 'skip_download': True,
  215. },
  216. },
  217. # google redirect
  218. {
  219. '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',
  220. 'info_dict': {
  221. 'id': 'cmQHVoWB5FY',
  222. 'ext': 'mp4',
  223. 'upload_date': '20130224',
  224. 'uploader_id': 'TheVerge',
  225. 'description': 're:^Chris Ziegler takes a look at the\.*',
  226. 'uploader': 'The Verge',
  227. 'title': 'First Firefox OS phones side-by-side',
  228. },
  229. 'params': {
  230. 'skip_download': False,
  231. }
  232. },
  233. {
  234. # redirect in Refresh HTTP header
  235. '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',
  236. 'info_dict': {
  237. 'id': 'pO8h3EaFRdo',
  238. 'ext': 'mp4',
  239. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  240. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  241. 'upload_date': '20150917',
  242. 'uploader_id': 'brtvofficial',
  243. 'uploader': 'Boiler Room',
  244. },
  245. 'params': {
  246. 'skip_download': False,
  247. },
  248. },
  249. {
  250. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  251. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  252. 'info_dict': {
  253. 'id': '13601338388002',
  254. 'ext': 'mp4',
  255. 'uploader': 'www.hodiho.fr',
  256. 'title': 'R\u00e9gis plante sa Jeep',
  257. }
  258. },
  259. # bandcamp page with custom domain
  260. {
  261. 'add_ie': ['Bandcamp'],
  262. 'url': 'http://bronyrock.com/track/the-pony-mash',
  263. 'info_dict': {
  264. 'id': '3235767654',
  265. 'ext': 'mp3',
  266. 'title': 'The Pony Mash',
  267. 'uploader': 'M_Pallante',
  268. },
  269. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  270. },
  271. # embedded brightcove video
  272. # it also tests brightcove videos that need to set the 'Referer' in the
  273. # http requests
  274. {
  275. 'add_ie': ['BrightcoveLegacy'],
  276. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  277. 'info_dict': {
  278. 'id': '2765128793001',
  279. 'ext': 'mp4',
  280. 'title': 'Le cours de bourse : l’analyse technique',
  281. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  282. 'uploader': 'BFM BUSINESS',
  283. },
  284. 'params': {
  285. 'skip_download': True,
  286. },
  287. },
  288. {
  289. # https://github.com/rg3/youtube-dl/issues/2253
  290. 'url': 'http://bcove.me/i6nfkrc3',
  291. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  292. 'info_dict': {
  293. 'id': '3101154703001',
  294. 'ext': 'mp4',
  295. 'title': 'Still no power',
  296. 'uploader': 'thestar.com',
  297. '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.',
  298. },
  299. 'add_ie': ['BrightcoveLegacy'],
  300. },
  301. {
  302. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  303. 'md5': 'fb973ecf6e4a78a67453647444222983',
  304. 'info_dict': {
  305. 'id': '3414141473001',
  306. 'ext': 'mp4',
  307. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  308. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  309. 'uploader': 'Championat',
  310. },
  311. },
  312. {
  313. # https://github.com/rg3/youtube-dl/issues/3541
  314. 'add_ie': ['BrightcoveLegacy'],
  315. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  316. 'info_dict': {
  317. 'id': '3866516442001',
  318. 'ext': 'mp4',
  319. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  320. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  321. 'uploader': 'SBS Broadcasting',
  322. },
  323. 'skip': 'Restricted to Netherlands',
  324. 'params': {
  325. 'skip_download': True, # m3u8 download
  326. },
  327. },
  328. # ooyala video
  329. {
  330. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  331. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  332. 'info_dict': {
  333. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  334. 'ext': 'mp4',
  335. 'title': '2cc213299525360.mov', # that's what we get
  336. },
  337. 'add_ie': ['Ooyala'],
  338. },
  339. {
  340. # ooyala video embedded with http://player.ooyala.com/iframe.js
  341. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  342. 'info_dict': {
  343. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  344. 'ext': 'mp4',
  345. 'title': '"Steve Jobs: Man in the Machine" trailer',
  346. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  347. },
  348. 'params': {
  349. 'skip_download': True,
  350. },
  351. },
  352. # multiple ooyala embeds on SBN network websites
  353. {
  354. 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
  355. 'info_dict': {
  356. 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
  357. 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
  358. },
  359. 'playlist_mincount': 3,
  360. 'params': {
  361. 'skip_download': True,
  362. },
  363. 'add_ie': ['Ooyala'],
  364. },
  365. # embed.ly video
  366. {
  367. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  368. 'info_dict': {
  369. 'id': '9ODmcdjQcHQ',
  370. 'ext': 'mp4',
  371. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  372. 'upload_date': '20140225',
  373. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  374. 'uploader': 'Tested',
  375. 'uploader_id': 'testedcom',
  376. },
  377. # No need to test YoutubeIE here
  378. 'params': {
  379. 'skip_download': True,
  380. },
  381. },
  382. # funnyordie embed
  383. {
  384. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  385. 'info_dict': {
  386. 'id': '18e820ec3f',
  387. 'ext': 'mp4',
  388. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  389. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  390. },
  391. },
  392. # RUTV embed
  393. {
  394. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  395. 'info_dict': {
  396. 'id': '776940',
  397. 'ext': 'mp4',
  398. 'title': 'Охотское море стало целиком российским',
  399. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  400. },
  401. 'params': {
  402. # m3u8 download
  403. 'skip_download': True,
  404. },
  405. },
  406. # TVC embed
  407. {
  408. '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/',
  409. 'info_dict': {
  410. 'id': '55304',
  411. 'ext': 'mp4',
  412. 'title': 'Дошкольное воспитание',
  413. },
  414. },
  415. # SportBox embed
  416. {
  417. 'url': 'http://www.vestifinance.ru/articles/25753',
  418. 'info_dict': {
  419. 'id': '25753',
  420. 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  421. },
  422. 'playlist': [{
  423. 'info_dict': {
  424. 'id': '370908',
  425. 'title': 'Госзаказ. День 3',
  426. 'ext': 'mp4',
  427. }
  428. }, {
  429. 'info_dict': {
  430. 'id': '370905',
  431. 'title': 'Госзаказ. День 2',
  432. 'ext': 'mp4',
  433. }
  434. }, {
  435. 'info_dict': {
  436. 'id': '370902',
  437. 'title': 'Госзаказ. День 1',
  438. 'ext': 'mp4',
  439. }
  440. }],
  441. 'params': {
  442. # m3u8 download
  443. 'skip_download': True,
  444. },
  445. },
  446. # Myvi.ru embed
  447. {
  448. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  449. 'info_dict': {
  450. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  451. 'ext': 'mp4',
  452. 'title': 'Ужастики, русский трейлер (2015)',
  453. 'thumbnail': 're:^https?://.*\.jpg$',
  454. 'duration': 153,
  455. }
  456. },
  457. # XHamster embed
  458. {
  459. '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',
  460. 'info_dict': {
  461. 'id': 'showthread',
  462. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  463. },
  464. 'playlist_mincount': 7,
  465. },
  466. # Embedded TED video
  467. {
  468. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  469. 'md5': '65fdff94098e4a607385a60c5177c638',
  470. 'info_dict': {
  471. 'id': '1969',
  472. 'ext': 'mp4',
  473. 'title': 'Hidden miracles of the natural world',
  474. 'uploader': 'Louie Schwartzberg',
  475. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  476. }
  477. },
  478. # Embeded Ustream video
  479. {
  480. 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
  481. 'md5': '27b99cdb639c9b12a79bca876a073417',
  482. 'info_dict': {
  483. 'id': '45734260',
  484. 'ext': 'flv',
  485. 'uploader': 'AU SPA: The NSA and Privacy',
  486. 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
  487. }
  488. },
  489. # nowvideo embed hidden behind percent encoding
  490. {
  491. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  492. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  493. 'info_dict': {
  494. 'id': '06e53103ca9aa',
  495. 'ext': 'flv',
  496. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  497. 'description': 'No description',
  498. },
  499. },
  500. # arte embed
  501. {
  502. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  503. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  504. 'info_dict': {
  505. 'id': '048195-004_PLUS7-F',
  506. 'ext': 'flv',
  507. 'title': 'X:enius',
  508. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  509. 'upload_date': '20140320',
  510. },
  511. 'params': {
  512. 'skip_download': 'Requires rtmpdump'
  513. }
  514. },
  515. # francetv embed
  516. {
  517. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  518. 'info_dict': {
  519. 'id': 'EV_30231',
  520. 'ext': 'mp4',
  521. 'title': 'Alcaline, le concert avec Calogero',
  522. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  523. 'upload_date': '20150226',
  524. 'timestamp': 1424989860,
  525. 'duration': 5400,
  526. },
  527. 'params': {
  528. # m3u8 downloads
  529. 'skip_download': True,
  530. },
  531. 'expected_warnings': [
  532. 'Forbidden'
  533. ]
  534. },
  535. # Condé Nast embed
  536. {
  537. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  538. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  539. 'info_dict': {
  540. 'id': '53501be369702d3275860000',
  541. 'ext': 'mp4',
  542. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  543. }
  544. },
  545. # Dailymotion embed
  546. {
  547. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  548. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  549. 'info_dict': {
  550. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  551. 'ext': 'mp4',
  552. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  553. 'uploader': 'Spi0n',
  554. },
  555. 'add_ie': ['Dailymotion'],
  556. },
  557. # YouTube embed
  558. {
  559. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  560. 'info_dict': {
  561. 'id': 'FXRb4ykk4S0',
  562. 'ext': 'mp4',
  563. 'title': 'The NBL Auction 2014',
  564. 'uploader': 'BADMINTON England',
  565. 'uploader_id': 'BADMINTONEvents',
  566. 'upload_date': '20140603',
  567. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  568. },
  569. 'add_ie': ['Youtube'],
  570. 'params': {
  571. 'skip_download': True,
  572. }
  573. },
  574. # MTVSercices embed
  575. {
  576. 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
  577. 'md5': '35727f82f58c76d996fc188f9755b0d5',
  578. 'info_dict': {
  579. 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
  580. 'ext': 'mp4',
  581. 'title': 'Review',
  582. 'description': 'Mario\'s life in the fast lane has never looked so good.',
  583. },
  584. },
  585. # YouTube embed via <data-embed-url="">
  586. {
  587. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  588. 'info_dict': {
  589. 'id': '4vAffPZIT44',
  590. 'ext': 'mp4',
  591. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  592. 'uploader': 'Gameloft',
  593. 'uploader_id': 'gameloft',
  594. 'upload_date': '20140828',
  595. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  596. },
  597. 'params': {
  598. 'skip_download': True,
  599. }
  600. },
  601. # Camtasia studio
  602. {
  603. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  604. 'playlist': [{
  605. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  606. 'info_dict': {
  607. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  608. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  609. 'ext': 'flv',
  610. 'duration': 2235.90,
  611. }
  612. }, {
  613. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  614. 'info_dict': {
  615. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  616. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  617. 'ext': 'flv',
  618. 'duration': 2235.93,
  619. }
  620. }],
  621. 'info_dict': {
  622. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  623. }
  624. },
  625. # Flowplayer
  626. {
  627. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  628. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  629. 'info_dict': {
  630. 'id': '5123ea6d5e5a7',
  631. 'ext': 'mp4',
  632. 'age_limit': 18,
  633. 'uploader': 'www.handjobhub.com',
  634. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  635. }
  636. },
  637. # Multiple brightcove videos
  638. # https://github.com/rg3/youtube-dl/issues/2283
  639. {
  640. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  641. 'info_dict': {
  642. 'id': 'always-never',
  643. 'title': 'Always / Never - The New Yorker',
  644. },
  645. 'playlist_count': 3,
  646. 'params': {
  647. 'extract_flat': False,
  648. 'skip_download': True,
  649. }
  650. },
  651. # MLB embed
  652. {
  653. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  654. 'md5': '96f09a37e44da40dd083e12d9a683327',
  655. 'info_dict': {
  656. 'id': '33322633',
  657. 'ext': 'mp4',
  658. 'title': 'Ump changes call to ball',
  659. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  660. 'duration': 48,
  661. 'timestamp': 1401537900,
  662. 'upload_date': '20140531',
  663. 'thumbnail': 're:^https?://.*\.jpg$',
  664. },
  665. },
  666. # Wistia embed
  667. {
  668. 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  669. 'md5': '8788b683c777a5cf25621eaf286d0c23',
  670. 'info_dict': {
  671. 'id': '1cfaf6b7ea',
  672. 'ext': 'mov',
  673. 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
  674. 'duration': 643.0,
  675. 'filesize': 182808282,
  676. 'uploader': 'education-portal.com',
  677. },
  678. },
  679. {
  680. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  681. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  682. 'info_dict': {
  683. 'id': 'uxjb0lwrcz',
  684. 'ext': 'mp4',
  685. 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
  686. 'duration': 1715.0,
  687. 'uploader': 'thoughtworks.wistia.com',
  688. },
  689. },
  690. # Soundcloud embed
  691. {
  692. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  693. 'info_dict': {
  694. 'id': '174391317',
  695. 'ext': 'mp3',
  696. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  697. 'uploader': 'Sophos Security',
  698. 'title': 'Chet Chat 171 - Oct 29, 2014',
  699. 'upload_date': '20141029',
  700. }
  701. },
  702. # Livestream embed
  703. {
  704. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  705. 'info_dict': {
  706. 'id': '67864563',
  707. 'ext': 'flv',
  708. 'upload_date': '20141112',
  709. 'title': 'Rosetta #CometLanding webcast HL 10',
  710. }
  711. },
  712. # LazyYT
  713. {
  714. 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
  715. 'info_dict': {
  716. 'id': '1986',
  717. 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
  718. },
  719. 'playlist_mincount': 2,
  720. },
  721. # Cinchcast embed
  722. {
  723. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  724. 'info_dict': {
  725. 'id': '7141703',
  726. 'ext': 'mp3',
  727. 'upload_date': '20141126',
  728. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  729. }
  730. },
  731. # Cinerama player
  732. {
  733. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  734. 'info_dict': {
  735. 'id': '730m_DandD_1901_512k',
  736. 'ext': 'mp4',
  737. 'uploader': 'www.abc.net.au',
  738. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  739. }
  740. },
  741. # embedded viddler video
  742. {
  743. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  744. 'info_dict': {
  745. 'id': '4d03aad9',
  746. 'ext': 'mp4',
  747. 'uploader': 'deadspin',
  748. 'title': 'WALL-TO-GORTAT',
  749. 'timestamp': 1422285291,
  750. 'upload_date': '20150126',
  751. },
  752. 'add_ie': ['Viddler'],
  753. },
  754. # Libsyn embed
  755. {
  756. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  757. 'info_dict': {
  758. 'id': '3377616',
  759. 'ext': 'mp3',
  760. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  761. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  762. 'upload_date': '20150220',
  763. },
  764. },
  765. # jwplayer YouTube
  766. {
  767. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  768. 'info_dict': {
  769. 'id': 'Mrj4DVp2zeA',
  770. 'ext': 'mp4',
  771. 'upload_date': '20150212',
  772. 'uploader': 'The National Archives UK',
  773. 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
  774. 'uploader_id': 'NationalArchives08',
  775. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  776. },
  777. },
  778. # rtl.nl embed
  779. {
  780. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  781. 'playlist_mincount': 5,
  782. 'info_dict': {
  783. 'id': 'aanslagen-kopenhagen',
  784. 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
  785. }
  786. },
  787. # Zapiks embed
  788. {
  789. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  790. 'info_dict': {
  791. 'id': '118046',
  792. 'ext': 'mp4',
  793. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  794. }
  795. },
  796. # Kaltura embed
  797. {
  798. 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
  799. 'info_dict': {
  800. 'id': '1_eergr3h1',
  801. 'ext': 'mp4',
  802. 'upload_date': '20150226',
  803. 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
  804. 'timestamp': int,
  805. 'title': 'John Carlson Postgame 2/25/15',
  806. },
  807. },
  808. # Kaltura embed (different embed code)
  809. {
  810. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  811. 'info_dict': {
  812. 'id': '1_a52wc67y',
  813. 'ext': 'flv',
  814. 'upload_date': '20150127',
  815. 'uploader_id': 'PremierMedia',
  816. 'timestamp': int,
  817. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  818. },
  819. },
  820. # Kaltura embed protected with referrer
  821. {
  822. 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
  823. 'info_dict': {
  824. 'id': '1_g4fbemnq',
  825. 'ext': 'mp4',
  826. 'title': 'Violetta - Achter De Schermen - Ruggero',
  827. 'description': 'Achter de schermen met Ruggero',
  828. 'timestamp': 1435133761,
  829. 'upload_date': '20150624',
  830. 'uploader_id': 'echojecka',
  831. },
  832. },
  833. # Eagle.Platform embed (generic URL)
  834. {
  835. 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
  836. 'info_dict': {
  837. 'id': '227304',
  838. 'ext': 'mp4',
  839. 'title': 'Навальный вышел на свободу',
  840. 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
  841. 'thumbnail': 're:^https?://.*\.jpg$',
  842. 'duration': 87,
  843. 'view_count': int,
  844. 'age_limit': 0,
  845. },
  846. },
  847. # ClipYou (Eagle.Platform) embed (custom URL)
  848. {
  849. 'url': 'http://muz-tv.ru/play/7129/',
  850. 'info_dict': {
  851. 'id': '12820',
  852. 'ext': 'mp4',
  853. 'title': "'O Sole Mio",
  854. 'thumbnail': 're:^https?://.*\.jpg$',
  855. 'duration': 216,
  856. 'view_count': int,
  857. },
  858. },
  859. # Pladform embed
  860. {
  861. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  862. 'info_dict': {
  863. 'id': '100183293',
  864. 'ext': 'mp4',
  865. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  866. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  867. 'thumbnail': 're:^https?://.*\.jpg$',
  868. 'duration': 694,
  869. 'age_limit': 0,
  870. },
  871. },
  872. # Playwire embed
  873. {
  874. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  875. 'info_dict': {
  876. 'id': '3519514',
  877. 'ext': 'mp4',
  878. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  879. 'thumbnail': 're:^https?://.*\.png$',
  880. 'duration': 45.115,
  881. },
  882. },
  883. # 5min embed
  884. {
  885. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  886. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  887. 'info_dict': {
  888. 'id': '518726732',
  889. 'ext': 'mp4',
  890. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  891. },
  892. },
  893. # SVT embed
  894. {
  895. 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
  896. 'info_dict': {
  897. 'id': '2900353',
  898. 'ext': 'flv',
  899. 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
  900. 'duration': 27,
  901. 'age_limit': 0,
  902. },
  903. },
  904. # Crooks and Liars embed
  905. {
  906. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  907. 'info_dict': {
  908. 'id': '8RUoRhRi',
  909. 'ext': 'mp4',
  910. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  911. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  912. 'timestamp': 1428207000,
  913. 'upload_date': '20150405',
  914. 'uploader': 'Heather',
  915. },
  916. },
  917. # Crooks and Liars external embed
  918. {
  919. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  920. 'info_dict': {
  921. 'id': 'MTE3MjUtMzQ2MzA',
  922. 'ext': 'mp4',
  923. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  924. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  925. 'timestamp': 1265032391,
  926. 'upload_date': '20100201',
  927. 'uploader': 'Heather',
  928. },
  929. },
  930. # NBC Sports vplayer embed
  931. {
  932. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  933. 'info_dict': {
  934. 'id': 'ln7x1qSThw4k',
  935. 'ext': 'flv',
  936. 'title': "PFT Live: New leader in the 'new-look' defense",
  937. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  938. },
  939. },
  940. # UDN embed
  941. {
  942. 'url': 'http://www.udn.com/news/story/7314/822787',
  943. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  944. 'info_dict': {
  945. 'id': '300346',
  946. 'ext': 'mp4',
  947. 'title': '中一中男師變性 全校師生力挺',
  948. 'thumbnail': 're:^https?://.*\.jpg$',
  949. }
  950. },
  951. # Ooyala embed
  952. {
  953. 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
  954. 'info_dict': {
  955. 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
  956. 'ext': 'mp4',
  957. 'description': 'VIDEO: Index/Match versus VLOOKUP.',
  958. 'title': 'This is what separates the Excel masters from the wannabes',
  959. },
  960. 'params': {
  961. # m3u8 downloads
  962. 'skip_download': True,
  963. }
  964. },
  965. # Contains a SMIL manifest
  966. {
  967. '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',
  968. 'info_dict': {
  969. 'id': 'file',
  970. 'ext': 'flv',
  971. 'title': '+ Football: Lottery Champions League Europe',
  972. 'uploader': 'www.telewebion.com',
  973. },
  974. 'params': {
  975. # rtmpe downloads
  976. 'skip_download': True,
  977. }
  978. },
  979. # Brightcove URL in single quotes
  980. {
  981. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  982. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  983. 'info_dict': {
  984. 'id': '4255764656001',
  985. 'ext': 'mp4',
  986. 'title': 'SN Presents: Russell Martin, World Citizen',
  987. '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.',
  988. 'uploader': 'Rogers Sportsnet',
  989. },
  990. },
  991. # Dailymotion Cloud video
  992. {
  993. 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
  994. 'md5': '49444254273501a64675a7e68c502681',
  995. 'info_dict': {
  996. 'id': '5585de919473990de4bee11b',
  997. 'ext': 'mp4',
  998. 'title': 'Le débat',
  999. 'thumbnail': 're:^https?://.*\.jpe?g$',
  1000. }
  1001. },
  1002. # OnionStudios embed
  1003. {
  1004. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1005. 'info_dict': {
  1006. 'id': '2855',
  1007. 'ext': 'mp4',
  1008. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1009. 'thumbnail': 're:^https?://.*\.jpe?g$',
  1010. 'uploader': 'ClickHole',
  1011. 'uploader_id': 'clickhole',
  1012. }
  1013. },
  1014. # SnagFilms embed
  1015. {
  1016. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1017. 'info_dict': {
  1018. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1019. 'ext': 'mp4',
  1020. 'title': '#whilewewatch',
  1021. }
  1022. },
  1023. # AdobeTVVideo embed
  1024. {
  1025. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1026. 'md5': '43662b577c018ad707a63766462b1e87',
  1027. 'info_dict': {
  1028. 'id': '2456',
  1029. 'ext': 'mp4',
  1030. 'title': 'New experience with Acrobat DC',
  1031. 'description': 'New experience with Acrobat DC',
  1032. 'duration': 248.667,
  1033. },
  1034. },
  1035. # ScreenwaveMedia embed
  1036. {
  1037. 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
  1038. 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
  1039. 'info_dict': {
  1040. 'id': 'cinemasnob-55d26273809dd',
  1041. 'ext': 'mp4',
  1042. 'title': 'cinemasnob',
  1043. },
  1044. },
  1045. # BrightcoveInPageEmbed embed
  1046. {
  1047. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1048. 'info_dict': {
  1049. 'id': '4238694884001',
  1050. 'ext': 'flv',
  1051. 'title': 'Tabletop: Dread, Last Thoughts',
  1052. 'description': 'Tabletop: Dread, Last Thoughts',
  1053. 'duration': 51690,
  1054. },
  1055. },
  1056. # JWPlayer with M3U8
  1057. {
  1058. 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
  1059. 'info_dict': {
  1060. 'id': 'playlist',
  1061. 'ext': 'mp4',
  1062. 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
  1063. 'uploader': 'ren.tv',
  1064. },
  1065. 'params': {
  1066. # m3u8 downloads
  1067. 'skip_download': True,
  1068. }
  1069. }
  1070. ]
  1071. def report_following_redirect(self, new_url):
  1072. """Report information extraction."""
  1073. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  1074. def _extract_rss(self, url, video_id, doc):
  1075. playlist_title = doc.find('./channel/title').text
  1076. playlist_desc_el = doc.find('./channel/description')
  1077. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  1078. entries = []
  1079. for it in doc.findall('./channel/item'):
  1080. next_url = xpath_text(it, 'link', fatal=False)
  1081. if not next_url:
  1082. enclosure_nodes = it.findall('./enclosure')
  1083. for e in enclosure_nodes:
  1084. next_url = e.attrib.get('url')
  1085. if next_url:
  1086. break
  1087. if not next_url:
  1088. continue
  1089. entries.append({
  1090. '_type': 'url',
  1091. 'url': next_url,
  1092. 'title': it.find('title').text,
  1093. })
  1094. return {
  1095. '_type': 'playlist',
  1096. 'id': url,
  1097. 'title': playlist_title,
  1098. 'description': playlist_desc,
  1099. 'entries': entries,
  1100. }
  1101. def _extract_camtasia(self, url, video_id, webpage):
  1102. """ Returns None if no camtasia video can be found. """
  1103. camtasia_cfg = self._search_regex(
  1104. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  1105. webpage, 'camtasia configuration file', default=None)
  1106. if camtasia_cfg is None:
  1107. return None
  1108. title = self._html_search_meta('DC.title', webpage, fatal=True)
  1109. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  1110. camtasia_cfg = self._download_xml(
  1111. camtasia_url, video_id,
  1112. note='Downloading camtasia configuration',
  1113. errnote='Failed to download camtasia configuration')
  1114. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  1115. entries = []
  1116. for n in fileset_node.getchildren():
  1117. url_n = n.find('./uri')
  1118. if url_n is None:
  1119. continue
  1120. entries.append({
  1121. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  1122. 'title': '%s - %s' % (title, n.tag),
  1123. 'url': compat_urlparse.urljoin(url, url_n.text),
  1124. 'duration': float_or_none(n.find('./duration').text),
  1125. })
  1126. return {
  1127. '_type': 'playlist',
  1128. 'entries': entries,
  1129. 'title': title,
  1130. }
  1131. def _real_extract(self, url):
  1132. if url.startswith('//'):
  1133. return {
  1134. '_type': 'url',
  1135. 'url': self.http_scheme() + url,
  1136. }
  1137. parsed_url = compat_urlparse.urlparse(url)
  1138. if not parsed_url.scheme:
  1139. default_search = self._downloader.params.get('default_search')
  1140. if default_search is None:
  1141. default_search = 'fixup_error'
  1142. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  1143. if '/' in url:
  1144. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  1145. return self.url_result('http://' + url)
  1146. elif default_search != 'fixup_error':
  1147. if default_search == 'auto_warning':
  1148. if re.match(r'^(?:url|URL)$', url):
  1149. raise ExtractorError(
  1150. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  1151. expected=True)
  1152. else:
  1153. self._downloader.report_warning(
  1154. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  1155. return self.url_result('ytsearch:' + url)
  1156. if default_search in ('error', 'fixup_error'):
  1157. raise ExtractorError(
  1158. '%r is not a valid URL. '
  1159. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  1160. % (url, url), expected=True)
  1161. else:
  1162. if ':' not in default_search:
  1163. default_search += ':'
  1164. return self.url_result(default_search + url)
  1165. url, smuggled_data = unsmuggle_url(url)
  1166. force_videoid = None
  1167. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  1168. if smuggled_data and 'force_videoid' in smuggled_data:
  1169. force_videoid = smuggled_data['force_videoid']
  1170. video_id = force_videoid
  1171. else:
  1172. video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
  1173. self.to_screen('%s: Requesting header' % video_id)
  1174. head_req = HEADRequest(url)
  1175. head_response = self._request_webpage(
  1176. head_req, video_id,
  1177. note=False, errnote='Could not send HEAD request to %s' % url,
  1178. fatal=False)
  1179. if head_response is not False:
  1180. # Check for redirect
  1181. new_url = head_response.geturl()
  1182. if url != new_url:
  1183. self.report_following_redirect(new_url)
  1184. if force_videoid:
  1185. new_url = smuggle_url(
  1186. new_url, {'force_videoid': force_videoid})
  1187. return self.url_result(new_url)
  1188. full_response = None
  1189. if head_response is False:
  1190. request = sanitized_Request(url)
  1191. request.add_header('Accept-Encoding', '*')
  1192. full_response = self._request_webpage(request, video_id)
  1193. head_response = full_response
  1194. # Check for direct link to a video
  1195. content_type = head_response.headers.get('Content-Type', '')
  1196. m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
  1197. if m:
  1198. upload_date = unified_strdate(
  1199. head_response.headers.get('Last-Modified'))
  1200. return {
  1201. 'id': video_id,
  1202. 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
  1203. 'direct': True,
  1204. 'formats': [{
  1205. 'format_id': m.group('format_id'),
  1206. 'url': url,
  1207. 'vcodec': 'none' if m.group('type') == 'audio' else None
  1208. }],
  1209. 'upload_date': upload_date,
  1210. }
  1211. if not self._downloader.params.get('test', False) and not is_intentional:
  1212. force = self._downloader.params.get('force_generic_extractor', False)
  1213. self._downloader.report_warning(
  1214. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  1215. if not full_response:
  1216. request = sanitized_Request(url)
  1217. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  1218. # making it impossible to download only chunk of the file (yet we need only 512kB to
  1219. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  1220. # that will always result in downloading the whole file that is not desirable.
  1221. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  1222. # to accept raw bytes and being able to download only a chunk.
  1223. # It may probably better to solve this by checking Content-Type for application/octet-stream
  1224. # after HEAD request finishes, but not sure if we can rely on this.
  1225. request.add_header('Accept-Encoding', '*')
  1226. full_response = self._request_webpage(request, video_id)
  1227. # Maybe it's a direct link to a video?
  1228. # Be careful not to download the whole thing!
  1229. first_bytes = full_response.read(512)
  1230. if not is_html(first_bytes):
  1231. self._downloader.report_warning(
  1232. 'URL could be a direct video link, returning it as such.')
  1233. upload_date = unified_strdate(
  1234. head_response.headers.get('Last-Modified'))
  1235. return {
  1236. 'id': video_id,
  1237. 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
  1238. 'direct': True,
  1239. 'url': url,
  1240. 'upload_date': upload_date,
  1241. }
  1242. webpage = self._webpage_read_content(
  1243. full_response, url, video_id, prefix=first_bytes)
  1244. self.report_extraction(video_id)
  1245. # Is it an RSS feed, a SMIL file or a XSPF playlist?
  1246. try:
  1247. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  1248. if doc.tag == 'rss':
  1249. return self._extract_rss(url, video_id, doc)
  1250. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  1251. return self._parse_smil(doc, url, video_id)
  1252. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  1253. return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
  1254. except compat_xml_parse_error:
  1255. pass
  1256. # Is it a Camtasia project?
  1257. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  1258. if camtasia_res is not None:
  1259. return camtasia_res
  1260. # Sometimes embedded video player is hidden behind percent encoding
  1261. # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
  1262. # Unescaping the whole page allows to handle those cases in a generic way
  1263. webpage = compat_urllib_parse_unquote(webpage)
  1264. # it's tempting to parse this further, but you would
  1265. # have to take into account all the variations like
  1266. # Video Title - Site Name
  1267. # Site Name | Video Title
  1268. # Video Title - Tagline | Site Name
  1269. # and so on and so forth; it's just not practical
  1270. video_title = self._html_search_regex(
  1271. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  1272. default='video')
  1273. # Try to detect age limit automatically
  1274. age_limit = self._rta_search(webpage)
  1275. # And then there are the jokers who advertise that they use RTA,
  1276. # but actually don't.
  1277. AGE_LIMIT_MARKERS = [
  1278. r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
  1279. ]
  1280. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  1281. age_limit = 18
  1282. # video uploader is domain name
  1283. video_uploader = self._search_regex(
  1284. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  1285. # Helper method
  1286. def _playlist_from_matches(matches, getter=None, ie=None):
  1287. urlrs = orderedSet(
  1288. self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
  1289. for m in matches)
  1290. return self.playlist_result(
  1291. urlrs, playlist_id=video_id, playlist_title=video_title)
  1292. # Look for Brightcove Legacy Studio embeds
  1293. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  1294. if bc_urls:
  1295. self.to_screen('Brightcove video detected.')
  1296. entries = [{
  1297. '_type': 'url',
  1298. 'url': smuggle_url(bc_url, {'Referer': url}),
  1299. 'ie_key': 'BrightcoveLegacy'
  1300. } for bc_url in bc_urls]
  1301. return {
  1302. '_type': 'playlist',
  1303. 'title': video_title,
  1304. 'id': video_id,
  1305. 'entries': entries,
  1306. }
  1307. # Look for Brightcove New Studio embeds
  1308. bc_urls = BrightcoveNewIE._extract_urls(webpage)
  1309. if bc_urls:
  1310. return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
  1311. # Look for embedded rtl.nl player
  1312. matches = re.findall(
  1313. r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
  1314. webpage)
  1315. if matches:
  1316. return _playlist_from_matches(matches, ie='RtlNl')
  1317. vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
  1318. if vimeo_url is not None:
  1319. return self.url_result(vimeo_url)
  1320. vid_me_embed_url = self._search_regex(
  1321. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  1322. webpage, 'vid.me embed', default=None)
  1323. if vid_me_embed_url is not None:
  1324. return self.url_result(vid_me_embed_url, 'Vidme')
  1325. # Look for embedded YouTube player
  1326. matches = re.findall(r'''(?x)
  1327. (?:
  1328. <iframe[^>]+?src=|
  1329. data-video-url=|
  1330. <embed[^>]+?src=|
  1331. embedSWF\(?:\s*|
  1332. new\s+SWFObject\(
  1333. )
  1334. (["\'])
  1335. (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
  1336. (?:embed|v|p)/.+?)
  1337. \1''', webpage)
  1338. if matches:
  1339. return _playlist_from_matches(
  1340. matches, lambda m: unescapeHTML(m[1]))
  1341. # Look for lazyYT YouTube embed
  1342. matches = re.findall(
  1343. r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
  1344. if matches:
  1345. return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
  1346. # Look for embedded Dailymotion player
  1347. matches = re.findall(
  1348. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
  1349. if matches:
  1350. return _playlist_from_matches(
  1351. matches, lambda m: unescapeHTML(m[1]))
  1352. # Look for embedded Dailymotion playlist player (#3822)
  1353. m = re.search(
  1354. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  1355. if m:
  1356. playlists = re.findall(
  1357. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  1358. if playlists:
  1359. return _playlist_from_matches(
  1360. playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
  1361. # Look for embedded Wistia player
  1362. match = re.search(
  1363. r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
  1364. if match:
  1365. embed_url = self._proto_relative_url(
  1366. unescapeHTML(match.group('url')))
  1367. return {
  1368. '_type': 'url_transparent',
  1369. 'url': embed_url,
  1370. 'ie_key': 'Wistia',
  1371. 'uploader': video_uploader,
  1372. 'title': video_title,
  1373. 'id': video_id,
  1374. }
  1375. match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
  1376. if match:
  1377. return {
  1378. '_type': 'url_transparent',
  1379. 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
  1380. 'ie_key': 'Wistia',
  1381. 'uploader': video_uploader,
  1382. 'title': video_title,
  1383. 'id': match.group('id')
  1384. }
  1385. # Look for SVT player
  1386. svt_url = SVTIE._extract_url(webpage)
  1387. if svt_url:
  1388. return self.url_result(svt_url, 'SVT')
  1389. # Look for embedded condenast player
  1390. matches = re.findall(
  1391. r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
  1392. webpage)
  1393. if matches:
  1394. return {
  1395. '_type': 'playlist',
  1396. 'entries': [{
  1397. '_type': 'url',
  1398. 'ie_key': 'CondeNast',
  1399. 'url': ma,
  1400. } for ma in matches],
  1401. 'title': video_title,
  1402. 'id': video_id,
  1403. }
  1404. # Look for Bandcamp pages with custom domain
  1405. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  1406. if mobj is not None:
  1407. burl = unescapeHTML(mobj.group(1))
  1408. # Don't set the extractor because it can be a track url or an album
  1409. return self.url_result(burl)
  1410. # Look for embedded Vevo player
  1411. mobj = re.search(
  1412. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  1413. if mobj is not None:
  1414. return self.url_result(mobj.group('url'))
  1415. # Look for embedded Viddler player
  1416. mobj = re.search(
  1417. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  1418. webpage)
  1419. if mobj is not None:
  1420. return self.url_result(mobj.group('url'))
  1421. # Look for NYTimes player
  1422. mobj = re.search(
  1423. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  1424. webpage)
  1425. if mobj is not None:
  1426. return self.url_result(mobj.group('url'))
  1427. # Look for Libsyn player
  1428. mobj = re.search(
  1429. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  1430. if mobj is not None:
  1431. return self.url_result(mobj.group('url'))
  1432. # Look for Ooyala videos
  1433. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
  1434. re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
  1435. re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
  1436. re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  1437. if mobj is not None:
  1438. return OoyalaIE._build_url_result(mobj.group('ec'))
  1439. # Look for multiple Ooyala embeds on SBN network websites
  1440. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  1441. if mobj is not None:
  1442. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  1443. if embeds:
  1444. return _playlist_from_matches(
  1445. embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
  1446. # Look for Aparat videos
  1447. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  1448. if mobj is not None:
  1449. return self.url_result(mobj.group(1), 'Aparat')
  1450. # Look for MPORA videos
  1451. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  1452. if mobj is not None:
  1453. return self.url_result(mobj.group(1), 'Mpora')
  1454. # Look for embedded NovaMov-based player
  1455. mobj = re.search(
  1456. r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
  1457. (?P<url>http://(?:(?:embed|www)\.)?
  1458. (?:novamov\.com|
  1459. nowvideo\.(?:ch|sx|eu|at|ag|co)|
  1460. videoweed\.(?:es|com)|
  1461. movshare\.(?:net|sx|ag)|
  1462. divxstage\.(?:eu|net|ch|co|at|ag))
  1463. /embed\.php.+?)\1''', webpage)
  1464. if mobj is not None:
  1465. return self.url_result(mobj.group('url'))
  1466. # Look for embedded Facebook player
  1467. mobj = re.search(
  1468. r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
  1469. if mobj is not None:
  1470. return self.url_result(mobj.group('url'), 'Facebook')
  1471. # Look for embedded VK player
  1472. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  1473. if mobj is not None:
  1474. return self.url_result(mobj.group('url'), 'VK')
  1475. # Look for embedded ivi player
  1476. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  1477. if mobj is not None:
  1478. return self.url_result(mobj.group('url'), 'Ivi')
  1479. # Look for embedded Huffington Post player
  1480. mobj = re.search(
  1481. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  1482. if mobj is not None:
  1483. return self.url_result(mobj.group('url'), 'HuffPost')
  1484. # Look for embed.ly
  1485. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  1486. if mobj is not None:
  1487. return self.url_result(mobj.group('url'))
  1488. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  1489. if mobj is not None:
  1490. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  1491. # Look for funnyordie embed
  1492. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  1493. if matches:
  1494. return _playlist_from_matches(
  1495. matches, getter=unescapeHTML, ie='FunnyOrDie')
  1496. # Look for BBC iPlayer embed
  1497. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  1498. if matches:
  1499. return _playlist_from_matches(matches, ie='BBCCoUk')
  1500. # Look for embedded RUTV player
  1501. rutv_url = RUTVIE._extract_url(webpage)
  1502. if rutv_url:
  1503. return self.url_result(rutv_url, 'RUTV')
  1504. # Look for embedded TVC player
  1505. tvc_url = TVCIE._extract_url(webpage)
  1506. if tvc_url:
  1507. return self.url_result(tvc_url, 'TVC')
  1508. # Look for embedded SportBox player
  1509. sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
  1510. if sportbox_urls:
  1511. return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
  1512. # Look for embedded PornHub player
  1513. pornhub_url = PornHubIE._extract_url(webpage)
  1514. if pornhub_url:
  1515. return self.url_result(pornhub_url, 'PornHub')
  1516. # Look for embedded XHamster player
  1517. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  1518. if xhamster_urls:
  1519. return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
  1520. # Look for embedded Tvigle player
  1521. mobj = re.search(
  1522. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  1523. if mobj is not None:
  1524. return self.url_result(mobj.group('url'), 'Tvigle')
  1525. # Look for embedded TED player
  1526. mobj = re.search(
  1527. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  1528. if mobj is not None:
  1529. return self.url_result(mobj.group('url'), 'TED')
  1530. # Look for embedded Ustream videos
  1531. mobj = re.search(
  1532. r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
  1533. if mobj is not None:
  1534. return self.url_result(mobj.group('url'), 'Ustream')
  1535. # Look for embedded arte.tv player
  1536. mobj = re.search(
  1537. r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
  1538. webpage)
  1539. if mobj is not None:
  1540. return self.url_result(mobj.group('url'), 'ArteTVEmbed')
  1541. # Look for embedded francetv player
  1542. mobj = re.search(
  1543. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  1544. webpage)
  1545. if mobj is not None:
  1546. return self.url_result(mobj.group('url'))
  1547. # Look for embedded smotri.com player
  1548. smotri_url = SmotriIE._extract_url(webpage)
  1549. if smotri_url:
  1550. return self.url_result(smotri_url, 'Smotri')
  1551. # Look for embedded Myvi.ru player
  1552. myvi_url = MyviIE._extract_url(webpage)
  1553. if myvi_url:
  1554. return self.url_result(myvi_url)
  1555. # Look for embeded soundcloud player
  1556. mobj = re.search(
  1557. r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
  1558. webpage)
  1559. if mobj is not None:
  1560. url = unescapeHTML(mobj.group('url'))
  1561. return self.url_result(url)
  1562. # Look for embedded vulture.com player
  1563. mobj = re.search(
  1564. r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
  1565. webpage)
  1566. if mobj is not None:
  1567. url = unescapeHTML(mobj.group('url'))
  1568. return self.url_result(url, ie='Vulture')
  1569. # Look for embedded mtvservices player
  1570. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  1571. if mtvservices_url:
  1572. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  1573. # Look for embedded yahoo player
  1574. mobj = re.search(
  1575. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  1576. webpage)
  1577. if mobj is not None:
  1578. return self.url_result(mobj.group('url'), 'Yahoo')
  1579. # Look for embedded sbs.com.au player
  1580. mobj = re.search(
  1581. r'''(?x)
  1582. (?:
  1583. <meta\s+property="og:video"\s+content=|
  1584. <iframe[^>]+?src=
  1585. )
  1586. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  1587. webpage)
  1588. if mobj is not None:
  1589. return self.url_result(mobj.group('url'), 'SBS')
  1590. # Look for embedded Cinchcast player
  1591. mobj = re.search(
  1592. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  1593. webpage)
  1594. if mobj is not None:
  1595. return self.url_result(mobj.group('url'), 'Cinchcast')
  1596. mobj = re.search(
  1597. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  1598. webpage)
  1599. if not mobj:
  1600. mobj = re.search(
  1601. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  1602. webpage)
  1603. if mobj is not None:
  1604. return self.url_result(mobj.group('url'), 'MLB')
  1605. mobj = re.search(
  1606. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  1607. webpage)
  1608. if mobj is not None:
  1609. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  1610. mobj = re.search(
  1611. r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
  1612. webpage)
  1613. if mobj is not None:
  1614. return self.url_result(mobj.group('url'), 'Livestream')
  1615. # Look for Zapiks embed
  1616. mobj = re.search(
  1617. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  1618. if mobj is not None:
  1619. return self.url_result(mobj.group('url'), 'Zapiks')
  1620. # Look for Kaltura embeds
  1621. mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
  1622. 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))
  1623. if mobj is not None:
  1624. return self.url_result(smuggle_url(
  1625. 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
  1626. {'source_url': url}), 'Kaltura')
  1627. # Look for Eagle.Platform embeds
  1628. mobj = re.search(
  1629. r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
  1630. if mobj is not None:
  1631. return self.url_result(mobj.group('url'), 'EaglePlatform')
  1632. # Look for ClipYou (uses Eagle.Platform) embeds
  1633. mobj = re.search(
  1634. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  1635. if mobj is not None:
  1636. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  1637. # Look for Pladform embeds
  1638. mobj = re.search(
  1639. r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
  1640. if mobj is not None:
  1641. return self.url_result(mobj.group('url'), 'Pladform')
  1642. # Look for Playwire embeds
  1643. mobj = re.search(
  1644. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  1645. if mobj is not None:
  1646. return self.url_result(mobj.group('url'))
  1647. # Look for 5min embeds
  1648. mobj = re.search(
  1649. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  1650. if mobj is not None:
  1651. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  1652. # Look for Crooks and Liars embeds
  1653. mobj = re.search(
  1654. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  1655. if mobj is not None:
  1656. return self.url_result(mobj.group('url'))
  1657. # Look for NBC Sports VPlayer embeds
  1658. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  1659. if nbc_sports_url:
  1660. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  1661. # Look for UDN embeds
  1662. mobj = re.search(
  1663. r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  1664. if mobj is not None:
  1665. return self.url_result(
  1666. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  1667. # Look for Senate ISVP iframe
  1668. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  1669. if senate_isvp_url:
  1670. return self.url_result(senate_isvp_url, 'SenateISVP')
  1671. # Look for Dailymotion Cloud videos
  1672. dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
  1673. if dmcloud_url:
  1674. return self.url_result(dmcloud_url, 'DailymotionCloud')
  1675. # Look for OnionStudios embeds
  1676. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  1677. if onionstudios_url:
  1678. return self.url_result(onionstudios_url)
  1679. # Look for SnagFilms embeds
  1680. snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
  1681. if snagfilms_url:
  1682. return self.url_result(snagfilms_url)
  1683. # Look for ScreenwaveMedia embeds
  1684. mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
  1685. if mobj is not None:
  1686. return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
  1687. # Look for AdobeTVVideo embeds
  1688. mobj = re.search(
  1689. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  1690. webpage)
  1691. if mobj is not None:
  1692. return self.url_result(
  1693. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  1694. 'AdobeTVVideo')
  1695. def check_video(vurl):
  1696. if YoutubeIE.suitable(vurl):
  1697. return True
  1698. vpath = compat_urlparse.urlparse(vurl).path
  1699. vext = determine_ext(vpath)
  1700. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
  1701. def filter_video(urls):
  1702. return list(filter(check_video, urls))
  1703. # Start with something easy: JW Player in SWFObject
  1704. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  1705. if not found:
  1706. # Look for gorilla-vid style embedding
  1707. found = filter_video(re.findall(r'''(?sx)
  1708. (?:
  1709. jw_plugins|
  1710. JWPlayerOptions|
  1711. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  1712. )
  1713. .*?
  1714. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  1715. if not found:
  1716. # Broaden the search a little bit
  1717. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  1718. if not found:
  1719. # Broaden the findall a little bit: JWPlayer JS loader
  1720. found = filter_video(re.findall(
  1721. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  1722. if not found:
  1723. # Flow player
  1724. found = filter_video(re.findall(r'''(?xs)
  1725. flowplayer\("[^"]+",\s*
  1726. \{[^}]+?\}\s*,
  1727. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  1728. ["']?url["']?\s*:\s*["']([^"']+)["']
  1729. ''', webpage))
  1730. if not found:
  1731. # Cinerama player
  1732. found = re.findall(
  1733. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  1734. if not found:
  1735. # Try to find twitter cards info
  1736. found = filter_video(re.findall(
  1737. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  1738. if not found:
  1739. # We look for Open Graph info:
  1740. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  1741. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  1742. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  1743. if m_video_type is not None:
  1744. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  1745. if not found:
  1746. # HTML5 video
  1747. found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
  1748. if not found:
  1749. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  1750. found = re.search(
  1751. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  1752. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  1753. webpage)
  1754. if not found:
  1755. # Look also in Refresh HTTP header
  1756. refresh_header = head_response.headers.get('Refresh')
  1757. if refresh_header:
  1758. # In python 2 response HTTP headers are bytestrings
  1759. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  1760. refresh_header = refresh_header.decode('iso-8859-1')
  1761. found = re.search(REDIRECT_REGEX, refresh_header)
  1762. if found:
  1763. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  1764. self.report_following_redirect(new_url)
  1765. return {
  1766. '_type': 'url',
  1767. 'url': new_url,
  1768. }
  1769. if not found:
  1770. raise UnsupportedError(url)
  1771. entries = []
  1772. for video_url in found:
  1773. video_url = video_url.replace('\\/', '/')
  1774. video_url = compat_urlparse.urljoin(url, video_url)
  1775. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  1776. # Sometimes, jwplayer extraction will result in a YouTube URL
  1777. if YoutubeIE.suitable(video_url):
  1778. entries.append(self.url_result(video_url, 'Youtube'))
  1779. continue
  1780. # here's a fun little line of code for you:
  1781. video_id = os.path.splitext(video_id)[0]
  1782. entry_info_dict = {
  1783. 'id': video_id,
  1784. 'uploader': video_uploader,
  1785. 'title': video_title,
  1786. 'age_limit': age_limit,
  1787. }
  1788. ext = determine_ext(video_url)
  1789. if ext == 'smil':
  1790. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  1791. elif ext == 'xspf':
  1792. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  1793. elif ext == 'm3u8':
  1794. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  1795. else:
  1796. entry_info_dict['url'] = video_url
  1797. entries.append(entry_info_dict)
  1798. if len(entries) == 1:
  1799. return entries[0]
  1800. else:
  1801. for num, e in enumerate(entries, start=1):
  1802. # 'url' results don't have a title
  1803. if e.get('title') is not None:
  1804. e['title'] = '%s (%d)' % (e['title'], num)
  1805. return {
  1806. '_type': 'playlist',
  1807. 'entries': entries,
  1808. }