generic.py 116 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874
  1. # coding: 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. js_to_json,
  21. orderedSet,
  22. sanitized_Request,
  23. smuggle_url,
  24. unescapeHTML,
  25. unified_strdate,
  26. unsmuggle_url,
  27. UnsupportedError,
  28. xpath_text,
  29. )
  30. from .commonprotocols import RtmpIE
  31. from .brightcove import (
  32. BrightcoveLegacyIE,
  33. BrightcoveNewIE,
  34. )
  35. from .nbc import NBCSportsVPlayerIE
  36. from .ooyala import OoyalaIE
  37. from .rutv import RUTVIE
  38. from .tvc import TVCIE
  39. from .sportbox import SportBoxEmbedIE
  40. from .smotri import SmotriIE
  41. from .myvi import MyviIE
  42. from .condenast import CondeNastIE
  43. from .udn import UDNEmbedIE
  44. from .senateisvp import SenateISVPIE
  45. from .svt import SVTIE
  46. from .pornhub import PornHubIE
  47. from .xhamster import XHamsterEmbedIE
  48. from .tnaflix import TNAFlixNetworkEmbedIE
  49. from .drtuber import DrTuberIE
  50. from .redtube import RedTubeIE
  51. from .vimeo import VimeoIE
  52. from .dailymotion import (
  53. DailymotionIE,
  54. DailymotionCloudIE,
  55. )
  56. from .onionstudios import OnionStudiosIE
  57. from .viewlift import ViewLiftEmbedIE
  58. from .mtv import MTVServicesEmbeddedIE
  59. from .pladform import PladformIE
  60. from .videomore import VideomoreIE
  61. from .webcaster import WebcasterFeedIE
  62. from .googledrive import GoogleDriveIE
  63. from .jwplatform import JWPlatformIE
  64. from .digiteka import DigitekaIE
  65. from .arkena import ArkenaIE
  66. from .instagram import InstagramIE
  67. from .liveleak import LiveLeakIE
  68. from .threeqsdn import ThreeQSDNIE
  69. from .theplatform import ThePlatformIE
  70. from .vessel import VesselIE
  71. from .kaltura import KalturaIE
  72. from .eagleplatform import EaglePlatformIE
  73. from .facebook import FacebookIE
  74. from .soundcloud import SoundcloudIE
  75. from .tunein import TuneInBaseIE
  76. from .vbox7 import Vbox7IE
  77. from .dbtv import DBTVIE
  78. from .piksel import PikselIE
  79. from .videa import VideaIE
  80. from .twentymin import TwentyMinutenIE
  81. from .ustream import UstreamIE
  82. from .openload import OpenloadIE
  83. from .videopress import VideoPressIE
  84. from .rutube import RutubeIE
  85. from .limelight import LimelightBaseIE
  86. from .anvato import AnvatoIE
  87. class GenericIE(InfoExtractor):
  88. IE_DESC = 'Generic downloader that works on some sites'
  89. _VALID_URL = r'.*'
  90. IE_NAME = 'generic'
  91. _TESTS = [
  92. # Direct link to a video
  93. {
  94. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  95. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  96. 'info_dict': {
  97. 'id': 'trailer',
  98. 'ext': 'mp4',
  99. 'title': 'trailer',
  100. 'upload_date': '20100513',
  101. }
  102. },
  103. # Direct link to media delivered compressed (until Accept-Encoding is *)
  104. {
  105. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  106. 'md5': '128c42e68b13950268b648275386fc74',
  107. 'info_dict': {
  108. 'id': 'FictionJunction-Parallel_Hearts',
  109. 'ext': 'flac',
  110. 'title': 'FictionJunction-Parallel_Hearts',
  111. 'upload_date': '20140522',
  112. },
  113. 'expected_warnings': [
  114. 'URL could be a direct video link, returning it as such.'
  115. ],
  116. 'skip': 'URL invalid',
  117. },
  118. # Direct download with broken HEAD
  119. {
  120. 'url': 'http://ai-radio.org:8000/radio.opus',
  121. 'info_dict': {
  122. 'id': 'radio',
  123. 'ext': 'opus',
  124. 'title': 'radio',
  125. },
  126. 'params': {
  127. 'skip_download': True, # infinite live stream
  128. },
  129. 'expected_warnings': [
  130. r'501.*Not Implemented',
  131. r'400.*Bad Request',
  132. ],
  133. },
  134. # Direct link with incorrect MIME type
  135. {
  136. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  137. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  138. 'info_dict': {
  139. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  140. 'id': '5_Lennart_Poettering_-_Systemd',
  141. 'ext': 'webm',
  142. 'title': '5_Lennart_Poettering_-_Systemd',
  143. 'upload_date': '20141120',
  144. },
  145. 'expected_warnings': [
  146. 'URL could be a direct video link, returning it as such.'
  147. ]
  148. },
  149. # RSS feed
  150. {
  151. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  152. 'info_dict': {
  153. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  154. 'title': 'Zero Punctuation',
  155. 'description': 're:.*groundbreaking video review series.*'
  156. },
  157. 'playlist_mincount': 11,
  158. },
  159. # RSS feed with enclosure
  160. {
  161. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  162. 'info_dict': {
  163. 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  164. 'ext': 'm4v',
  165. 'upload_date': '20150228',
  166. 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  167. }
  168. },
  169. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  170. {
  171. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  172. 'info_dict': {
  173. 'id': 'smil',
  174. 'ext': 'mp4',
  175. 'title': 'Automatics, robotics and biocybernetics',
  176. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  177. 'upload_date': '20130627',
  178. 'formats': 'mincount:16',
  179. 'subtitles': 'mincount:1',
  180. },
  181. 'params': {
  182. 'force_generic_extractor': True,
  183. 'skip_download': True,
  184. },
  185. },
  186. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  187. {
  188. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  189. 'info_dict': {
  190. 'id': 'hds',
  191. 'ext': 'flv',
  192. 'title': 'hds',
  193. 'formats': 'mincount:1',
  194. },
  195. 'params': {
  196. 'skip_download': True,
  197. },
  198. },
  199. # SMIL from https://www.restudy.dk/video/play/id/1637
  200. {
  201. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  202. 'info_dict': {
  203. 'id': 'video_1637',
  204. 'ext': 'flv',
  205. 'title': 'video_1637',
  206. 'formats': 'mincount:3',
  207. },
  208. 'params': {
  209. 'skip_download': True,
  210. },
  211. },
  212. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  213. {
  214. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  215. 'info_dict': {
  216. 'id': 'smil-service',
  217. 'ext': 'flv',
  218. 'title': 'smil-service',
  219. 'formats': 'mincount:1',
  220. },
  221. 'params': {
  222. 'skip_download': True,
  223. },
  224. },
  225. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  226. {
  227. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  228. 'info_dict': {
  229. 'id': '4719370',
  230. 'ext': 'mp4',
  231. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  232. 'formats': 'mincount:3',
  233. },
  234. 'params': {
  235. 'skip_download': True,
  236. },
  237. },
  238. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  239. {
  240. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  241. 'info_dict': {
  242. 'id': 'mZlp2ctYIUEB',
  243. 'ext': 'mp4',
  244. 'title': 'Tikibad ontruimd wegens brand',
  245. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  246. 'thumbnail': r're:^https?://.*\.jpg$',
  247. 'duration': 33,
  248. },
  249. 'params': {
  250. 'skip_download': True,
  251. },
  252. },
  253. # MPD from http://dash-mse-test.appspot.com/media.html
  254. {
  255. 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
  256. 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
  257. 'info_dict': {
  258. 'id': 'car-20120827-manifest',
  259. 'ext': 'mp4',
  260. 'title': 'car-20120827-manifest',
  261. 'formats': 'mincount:9',
  262. 'upload_date': '20130904',
  263. },
  264. 'params': {
  265. 'format': 'bestvideo',
  266. },
  267. },
  268. # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
  269. {
  270. 'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
  271. 'info_dict': {
  272. 'id': 'content',
  273. 'ext': 'mp4',
  274. 'title': 'content',
  275. 'formats': 'mincount:8',
  276. },
  277. 'params': {
  278. # m3u8 downloads
  279. 'skip_download': True,
  280. },
  281. 'skip': 'video gone',
  282. },
  283. # m3u8 served with Content-Type: text/plain
  284. {
  285. 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
  286. 'info_dict': {
  287. 'id': 'index',
  288. 'ext': 'mp4',
  289. 'title': 'index',
  290. 'upload_date': '20140720',
  291. 'formats': 'mincount:11',
  292. },
  293. 'params': {
  294. # m3u8 downloads
  295. 'skip_download': True,
  296. },
  297. 'skip': 'video gone',
  298. },
  299. # google redirect
  300. {
  301. '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',
  302. 'info_dict': {
  303. 'id': 'cmQHVoWB5FY',
  304. 'ext': 'mp4',
  305. 'upload_date': '20130224',
  306. 'uploader_id': 'TheVerge',
  307. 'description': r're:^Chris Ziegler takes a look at the\.*',
  308. 'uploader': 'The Verge',
  309. 'title': 'First Firefox OS phones side-by-side',
  310. },
  311. 'params': {
  312. 'skip_download': False,
  313. }
  314. },
  315. {
  316. # redirect in Refresh HTTP header
  317. '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',
  318. 'info_dict': {
  319. 'id': 'pO8h3EaFRdo',
  320. 'ext': 'mp4',
  321. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  322. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  323. 'upload_date': '20150917',
  324. 'uploader_id': 'brtvofficial',
  325. 'uploader': 'Boiler Room',
  326. },
  327. 'params': {
  328. 'skip_download': False,
  329. },
  330. },
  331. {
  332. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  333. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  334. 'info_dict': {
  335. 'id': '13601338388002',
  336. 'ext': 'mp4',
  337. 'uploader': 'www.hodiho.fr',
  338. 'title': 'R\u00e9gis plante sa Jeep',
  339. }
  340. },
  341. # bandcamp page with custom domain
  342. {
  343. 'add_ie': ['Bandcamp'],
  344. 'url': 'http://bronyrock.com/track/the-pony-mash',
  345. 'info_dict': {
  346. 'id': '3235767654',
  347. 'ext': 'mp3',
  348. 'title': 'The Pony Mash',
  349. 'uploader': 'M_Pallante',
  350. },
  351. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  352. },
  353. {
  354. # embedded brightcove video
  355. # it also tests brightcove videos that need to set the 'Referer'
  356. # in the http requests
  357. 'add_ie': ['BrightcoveLegacy'],
  358. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  359. 'info_dict': {
  360. 'id': '2765128793001',
  361. 'ext': 'mp4',
  362. 'title': 'Le cours de bourse : l’analyse technique',
  363. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  364. 'uploader': 'BFM BUSINESS',
  365. },
  366. 'params': {
  367. 'skip_download': True,
  368. },
  369. },
  370. {
  371. # embedded with itemprop embedURL and video id spelled as `idVideo`
  372. 'add_id': ['BrightcoveLegacy'],
  373. 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
  374. 'info_dict': {
  375. 'id': '5255628253001',
  376. 'ext': 'mp4',
  377. 'title': 'md5:37c519b1128915607601e75a87995fc0',
  378. 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
  379. 'uploader': 'BFM BUSINESS',
  380. 'uploader_id': '876450612001',
  381. 'timestamp': 1482255315,
  382. 'upload_date': '20161220',
  383. },
  384. 'params': {
  385. 'skip_download': True,
  386. },
  387. },
  388. {
  389. # https://github.com/rg3/youtube-dl/issues/2253
  390. 'url': 'http://bcove.me/i6nfkrc3',
  391. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  392. 'info_dict': {
  393. 'id': '3101154703001',
  394. 'ext': 'mp4',
  395. 'title': 'Still no power',
  396. 'uploader': 'thestar.com',
  397. '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.',
  398. },
  399. 'add_ie': ['BrightcoveLegacy'],
  400. 'skip': 'video gone',
  401. },
  402. {
  403. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  404. 'md5': 'fb973ecf6e4a78a67453647444222983',
  405. 'info_dict': {
  406. 'id': '3414141473001',
  407. 'ext': 'mp4',
  408. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  409. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  410. 'uploader': 'Championat',
  411. },
  412. },
  413. {
  414. # https://github.com/rg3/youtube-dl/issues/3541
  415. 'add_ie': ['BrightcoveLegacy'],
  416. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  417. 'info_dict': {
  418. 'id': '3866516442001',
  419. 'ext': 'mp4',
  420. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  421. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  422. 'uploader': 'SBS Broadcasting',
  423. },
  424. 'skip': 'Restricted to Netherlands',
  425. 'params': {
  426. 'skip_download': True, # m3u8 download
  427. },
  428. },
  429. {
  430. # Brightcove video in <iframe>
  431. 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
  432. 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
  433. 'info_dict': {
  434. 'id': '5360463607001',
  435. 'ext': 'mp4',
  436. 'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
  437. 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼(Zade Dirani)在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》(HEARTBEAT),为受到六年冲突影响的叙利亚儿童发出强烈呐喊,呼吁世界做出共同努力,使叙利亚儿童重新获得享有正常童年生活的权利。',
  438. 'uploader': 'United Nations',
  439. 'uploader_id': '1362235914001',
  440. 'timestamp': 1489593889,
  441. 'upload_date': '20170315',
  442. },
  443. 'add_ie': ['BrightcoveLegacy'],
  444. },
  445. {
  446. # Brightcove with alternative playerID key
  447. 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
  448. 'info_dict': {
  449. 'id': 'nmeth.2062_SV1',
  450. 'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
  451. },
  452. 'playlist': [{
  453. 'info_dict': {
  454. 'id': '2228375078001',
  455. 'ext': 'mp4',
  456. 'title': 'nmeth.2062-sv1',
  457. 'description': 'nmeth.2062-sv1',
  458. 'timestamp': 1363357591,
  459. 'upload_date': '20130315',
  460. 'uploader': 'Nature Publishing Group',
  461. 'uploader_id': '1964492299001',
  462. },
  463. }],
  464. },
  465. {
  466. # Brightcove with UUID in videoPlayer
  467. 'url': 'http://www8.hp.com/cn/zh/home.html',
  468. 'info_dict': {
  469. 'id': '5255815316001',
  470. 'ext': 'mp4',
  471. 'title': 'Sprocket Video - China',
  472. 'description': 'Sprocket Video - China',
  473. 'uploader': 'HP-Video Gallery',
  474. 'timestamp': 1482263210,
  475. 'upload_date': '20161220',
  476. 'uploader_id': '1107601872001',
  477. },
  478. 'params': {
  479. 'skip_download': True, # m3u8 download
  480. },
  481. 'skip': 'video rotates...weekly?',
  482. },
  483. {
  484. # Brightcove:new type [2].
  485. 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
  486. 'md5': '2b35148fcf48da41c9fb4591650784f3',
  487. 'info_dict': {
  488. 'id': '5348741021001',
  489. 'ext': 'mp4',
  490. 'upload_date': '20170306',
  491. 'uploader_id': '4191638492001',
  492. 'timestamp': 1488769918,
  493. 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
  494. },
  495. },
  496. {
  497. # Alternative brightcove <video> attributes
  498. 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
  499. 'info_dict': {
  500. 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
  501. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
  502. },
  503. 'playlist': [{
  504. 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
  505. 'info_dict': {
  506. 'id': '5311302538001',
  507. 'ext': 'mp4',
  508. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
  509. 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
  510. 'timestamp': 1486321708,
  511. 'upload_date': '20170205',
  512. 'uploader_id': '800000640001',
  513. },
  514. 'only_matching': True,
  515. }],
  516. },
  517. {
  518. # Brightcove with UUID in videoPlayer
  519. 'url': 'http://www8.hp.com/cn/zh/home.html',
  520. 'info_dict': {
  521. 'id': '5255815316001',
  522. 'ext': 'mp4',
  523. 'title': 'Sprocket Video - China',
  524. 'description': 'Sprocket Video - China',
  525. 'uploader': 'HP-Video Gallery',
  526. 'timestamp': 1482263210,
  527. 'upload_date': '20161220',
  528. 'uploader_id': '1107601872001',
  529. },
  530. 'params': {
  531. 'skip_download': True, # m3u8 download
  532. },
  533. },
  534. # ooyala video
  535. {
  536. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  537. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  538. 'info_dict': {
  539. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  540. 'ext': 'mp4',
  541. 'title': '2cc213299525360.mov', # that's what we get
  542. 'duration': 238.231,
  543. },
  544. 'add_ie': ['Ooyala'],
  545. },
  546. {
  547. # ooyala video embedded with http://player.ooyala.com/iframe.js
  548. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  549. 'info_dict': {
  550. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  551. 'ext': 'mp4',
  552. 'title': '"Steve Jobs: Man in the Machine" trailer',
  553. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  554. 'duration': 135.427,
  555. },
  556. 'params': {
  557. 'skip_download': True,
  558. },
  559. 'skip': 'movie expired',
  560. },
  561. # embed.ly video
  562. {
  563. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  564. 'info_dict': {
  565. 'id': '9ODmcdjQcHQ',
  566. 'ext': 'mp4',
  567. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  568. 'upload_date': '20140225',
  569. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  570. 'uploader': 'Tested',
  571. 'uploader_id': 'testedcom',
  572. },
  573. # No need to test YoutubeIE here
  574. 'params': {
  575. 'skip_download': True,
  576. },
  577. },
  578. # funnyordie embed
  579. {
  580. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  581. 'info_dict': {
  582. 'id': '18e820ec3f',
  583. 'ext': 'mp4',
  584. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  585. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  586. },
  587. # HEAD requests lead to endless 301, while GET is OK
  588. 'expected_warnings': ['301'],
  589. },
  590. # RUTV embed
  591. {
  592. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  593. 'info_dict': {
  594. 'id': '776940',
  595. 'ext': 'mp4',
  596. 'title': 'Охотское море стало целиком российским',
  597. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  598. },
  599. 'params': {
  600. # m3u8 download
  601. 'skip_download': True,
  602. },
  603. },
  604. # TVC embed
  605. {
  606. '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/',
  607. 'info_dict': {
  608. 'id': '55304',
  609. 'ext': 'mp4',
  610. 'title': 'Дошкольное воспитание',
  611. },
  612. },
  613. # SportBox embed
  614. {
  615. 'url': 'http://www.vestifinance.ru/articles/25753',
  616. 'info_dict': {
  617. 'id': '25753',
  618. 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  619. },
  620. 'playlist': [{
  621. 'info_dict': {
  622. 'id': '370908',
  623. 'title': 'Госзаказ. День 3',
  624. 'ext': 'mp4',
  625. }
  626. }, {
  627. 'info_dict': {
  628. 'id': '370905',
  629. 'title': 'Госзаказ. День 2',
  630. 'ext': 'mp4',
  631. }
  632. }, {
  633. 'info_dict': {
  634. 'id': '370902',
  635. 'title': 'Госзаказ. День 1',
  636. 'ext': 'mp4',
  637. }
  638. }],
  639. 'params': {
  640. # m3u8 download
  641. 'skip_download': True,
  642. },
  643. },
  644. # Myvi.ru embed
  645. {
  646. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  647. 'info_dict': {
  648. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  649. 'ext': 'mp4',
  650. 'title': 'Ужастики, русский трейлер (2015)',
  651. 'thumbnail': r're:^https?://.*\.jpg$',
  652. 'duration': 153,
  653. }
  654. },
  655. # XHamster embed
  656. {
  657. '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',
  658. 'info_dict': {
  659. 'id': 'showthread',
  660. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  661. },
  662. 'playlist_mincount': 7,
  663. # This forum does not allow <iframe> syntaxes anymore
  664. # Now HTML tags are displayed as-is
  665. 'skip': 'No videos on this page',
  666. },
  667. # Embedded TED video
  668. {
  669. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  670. 'md5': '65fdff94098e4a607385a60c5177c638',
  671. 'info_dict': {
  672. 'id': '1969',
  673. 'ext': 'mp4',
  674. 'title': 'Hidden miracles of the natural world',
  675. 'uploader': 'Louie Schwartzberg',
  676. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  677. }
  678. },
  679. # nowvideo embed hidden behind percent encoding
  680. {
  681. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  682. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  683. 'info_dict': {
  684. 'id': '06e53103ca9aa',
  685. 'ext': 'flv',
  686. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  687. 'description': 'No description',
  688. },
  689. },
  690. # arte embed
  691. {
  692. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  693. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  694. 'info_dict': {
  695. 'id': '048195-004_PLUS7-F',
  696. 'ext': 'flv',
  697. 'title': 'X:enius',
  698. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  699. 'upload_date': '20140320',
  700. },
  701. 'params': {
  702. 'skip_download': 'Requires rtmpdump'
  703. },
  704. 'skip': 'video gone',
  705. },
  706. # francetv embed
  707. {
  708. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  709. 'info_dict': {
  710. 'id': 'EV_30231',
  711. 'ext': 'mp4',
  712. 'title': 'Alcaline, le concert avec Calogero',
  713. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  714. 'upload_date': '20150226',
  715. 'timestamp': 1424989860,
  716. 'duration': 5400,
  717. },
  718. 'params': {
  719. # m3u8 downloads
  720. 'skip_download': True,
  721. },
  722. 'expected_warnings': [
  723. 'Forbidden'
  724. ]
  725. },
  726. # Condé Nast embed
  727. {
  728. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  729. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  730. 'info_dict': {
  731. 'id': '53501be369702d3275860000',
  732. 'ext': 'mp4',
  733. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  734. }
  735. },
  736. # Dailymotion embed
  737. {
  738. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  739. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  740. 'info_dict': {
  741. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  742. 'ext': 'mp4',
  743. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  744. 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
  745. 'uploader': 'Spi0n',
  746. 'uploader_id': 'xgditw',
  747. 'upload_date': '20140425',
  748. 'timestamp': 1398441542,
  749. },
  750. 'add_ie': ['Dailymotion'],
  751. },
  752. # YouTube embed
  753. {
  754. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  755. 'info_dict': {
  756. 'id': 'FXRb4ykk4S0',
  757. 'ext': 'mp4',
  758. 'title': 'The NBL Auction 2014',
  759. 'uploader': 'BADMINTON England',
  760. 'uploader_id': 'BADMINTONEvents',
  761. 'upload_date': '20140603',
  762. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  763. },
  764. 'add_ie': ['Youtube'],
  765. 'params': {
  766. 'skip_download': True,
  767. }
  768. },
  769. # MTVSercices embed
  770. {
  771. 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
  772. 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
  773. 'info_dict': {
  774. 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
  775. 'ext': 'mp4',
  776. 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
  777. 'description': 'Two valets share their love for movie star Liam Neesons.',
  778. 'timestamp': 1349922600,
  779. 'upload_date': '20121011',
  780. },
  781. },
  782. # YouTube embed via <data-embed-url="">
  783. {
  784. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  785. 'info_dict': {
  786. 'id': '4vAffPZIT44',
  787. 'ext': 'mp4',
  788. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  789. 'uploader': 'Gameloft',
  790. 'uploader_id': 'gameloft',
  791. 'upload_date': '20140828',
  792. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  793. },
  794. 'params': {
  795. 'skip_download': True,
  796. }
  797. },
  798. # YouTube <object> embed
  799. {
  800. 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
  801. 'md5': '516718101ec834f74318df76259fb3cc',
  802. 'info_dict': {
  803. 'id': 'msN87y-iEx0',
  804. 'ext': 'webm',
  805. 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
  806. 'upload_date': '20080526',
  807. 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
  808. 'uploader': 'Christopher Sykes',
  809. 'uploader_id': 'ChristopherJSykes',
  810. },
  811. 'add_ie': ['Youtube'],
  812. },
  813. # Camtasia studio
  814. {
  815. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  816. 'playlist': [{
  817. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  818. 'info_dict': {
  819. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  820. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  821. 'ext': 'flv',
  822. 'duration': 2235.90,
  823. }
  824. }, {
  825. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  826. 'info_dict': {
  827. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  828. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  829. 'ext': 'flv',
  830. 'duration': 2235.93,
  831. }
  832. }],
  833. 'info_dict': {
  834. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  835. }
  836. },
  837. # Flowplayer
  838. {
  839. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  840. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  841. 'info_dict': {
  842. 'id': '5123ea6d5e5a7',
  843. 'ext': 'mp4',
  844. 'age_limit': 18,
  845. 'uploader': 'www.handjobhub.com',
  846. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  847. }
  848. },
  849. # Multiple brightcove videos
  850. # https://github.com/rg3/youtube-dl/issues/2283
  851. {
  852. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  853. 'info_dict': {
  854. 'id': 'always-never',
  855. 'title': 'Always / Never - The New Yorker',
  856. },
  857. 'playlist_count': 3,
  858. 'params': {
  859. 'extract_flat': False,
  860. 'skip_download': True,
  861. }
  862. },
  863. # MLB embed
  864. {
  865. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  866. 'md5': '96f09a37e44da40dd083e12d9a683327',
  867. 'info_dict': {
  868. 'id': '33322633',
  869. 'ext': 'mp4',
  870. 'title': 'Ump changes call to ball',
  871. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  872. 'duration': 48,
  873. 'timestamp': 1401537900,
  874. 'upload_date': '20140531',
  875. 'thumbnail': r're:^https?://.*\.jpg$',
  876. },
  877. },
  878. # Wistia embed
  879. {
  880. 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  881. 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
  882. 'info_dict': {
  883. 'id': '6e2wtrbdaf',
  884. 'ext': 'mov',
  885. 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
  886. 'description': 'a Paywall Videos video from Remilon',
  887. 'duration': 644.072,
  888. 'uploader': 'study.com',
  889. 'timestamp': 1459678540,
  890. 'upload_date': '20160403',
  891. 'filesize': 24687186,
  892. },
  893. },
  894. {
  895. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  896. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  897. 'info_dict': {
  898. 'id': 'uxjb0lwrcz',
  899. 'ext': 'mp4',
  900. 'title': 'Conversation about Hexagonal Rails Part 1',
  901. 'description': 'a Martin Fowler video from ThoughtWorks',
  902. 'duration': 1715.0,
  903. 'uploader': 'thoughtworks.wistia.com',
  904. 'timestamp': 1401832161,
  905. 'upload_date': '20140603',
  906. },
  907. },
  908. # Wistia standard embed (async)
  909. {
  910. 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
  911. 'info_dict': {
  912. 'id': '807fafadvk',
  913. 'ext': 'mp4',
  914. 'title': 'Drip Brennan Dunn Workshop',
  915. 'description': 'a JV Webinars video from getdrip-1',
  916. 'duration': 4986.95,
  917. 'timestamp': 1463607249,
  918. 'upload_date': '20160518',
  919. },
  920. 'params': {
  921. 'skip_download': True,
  922. }
  923. },
  924. # Soundcloud embed
  925. {
  926. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  927. 'info_dict': {
  928. 'id': '174391317',
  929. 'ext': 'mp3',
  930. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  931. 'uploader': 'Sophos Security',
  932. 'title': 'Chet Chat 171 - Oct 29, 2014',
  933. 'upload_date': '20141029',
  934. }
  935. },
  936. # Soundcloud multiple embeds
  937. {
  938. 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
  939. 'info_dict': {
  940. 'id': '52809',
  941. 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
  942. },
  943. 'playlist_mincount': 7,
  944. },
  945. # TuneIn station embed
  946. {
  947. 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
  948. 'info_dict': {
  949. 'id': '204146',
  950. 'ext': 'mp3',
  951. 'title': 'CNRV',
  952. 'location': 'Paris, France',
  953. 'is_live': True,
  954. },
  955. 'params': {
  956. # Live stream
  957. 'skip_download': True,
  958. },
  959. },
  960. # Livestream embed
  961. {
  962. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  963. 'info_dict': {
  964. 'id': '67864563',
  965. 'ext': 'flv',
  966. 'upload_date': '20141112',
  967. 'title': 'Rosetta #CometLanding webcast HL 10',
  968. }
  969. },
  970. # Another Livestream embed, without 'new.' in URL
  971. {
  972. 'url': 'https://www.freespeech.org/',
  973. 'info_dict': {
  974. 'id': '123537347',
  975. 'ext': 'mp4',
  976. 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  977. },
  978. 'params': {
  979. # Live stream
  980. 'skip_download': True,
  981. },
  982. },
  983. # LazyYT
  984. {
  985. 'url': 'https://skiplagged.com/',
  986. 'info_dict': {
  987. 'id': 'skiplagged',
  988. 'title': 'Skiplagged: The smart way to find cheap flights',
  989. },
  990. 'playlist_mincount': 1,
  991. 'add_ie': ['Youtube'],
  992. },
  993. # Cinchcast embed
  994. {
  995. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  996. 'info_dict': {
  997. 'id': '7141703',
  998. 'ext': 'mp3',
  999. 'upload_date': '20141126',
  1000. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  1001. }
  1002. },
  1003. # Cinerama player
  1004. {
  1005. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  1006. 'info_dict': {
  1007. 'id': '730m_DandD_1901_512k',
  1008. 'ext': 'mp4',
  1009. 'uploader': 'www.abc.net.au',
  1010. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  1011. }
  1012. },
  1013. # embedded viddler video
  1014. {
  1015. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  1016. 'info_dict': {
  1017. 'id': '4d03aad9',
  1018. 'ext': 'mp4',
  1019. 'uploader': 'deadspin',
  1020. 'title': 'WALL-TO-GORTAT',
  1021. 'timestamp': 1422285291,
  1022. 'upload_date': '20150126',
  1023. },
  1024. 'add_ie': ['Viddler'],
  1025. },
  1026. # Libsyn embed
  1027. {
  1028. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  1029. 'info_dict': {
  1030. 'id': '3377616',
  1031. 'ext': 'mp3',
  1032. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  1033. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  1034. 'upload_date': '20150220',
  1035. },
  1036. 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
  1037. },
  1038. # jwplayer YouTube
  1039. {
  1040. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  1041. 'info_dict': {
  1042. 'id': 'Mrj4DVp2zeA',
  1043. 'ext': 'mp4',
  1044. 'upload_date': '20150212',
  1045. 'uploader': 'The National Archives UK',
  1046. 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
  1047. 'uploader_id': 'NationalArchives08',
  1048. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  1049. },
  1050. },
  1051. # jwplayer rtmp
  1052. {
  1053. 'url': 'http://www.suffolk.edu/sjc/',
  1054. 'info_dict': {
  1055. 'id': 'sjclive',
  1056. 'ext': 'flv',
  1057. 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
  1058. 'uploader': 'www.suffolk.edu',
  1059. },
  1060. 'params': {
  1061. 'skip_download': True,
  1062. }
  1063. },
  1064. # Complex jwplayer
  1065. {
  1066. 'url': 'http://www.indiedb.com/games/king-machine/videos',
  1067. 'info_dict': {
  1068. 'id': 'videos',
  1069. 'ext': 'mp4',
  1070. 'title': 'king machine trailer 1',
  1071. 'thumbnail': r're:^https?://.*\.jpg$',
  1072. },
  1073. },
  1074. {
  1075. # JWPlayer config passed as variable
  1076. 'url': 'http://www.txxx.com/videos/3326530/ariele/',
  1077. 'info_dict': {
  1078. 'id': '3326530_hq',
  1079. 'ext': 'mp4',
  1080. 'title': 'ARIELE | Tube Cup',
  1081. 'uploader': 'www.txxx.com',
  1082. 'age_limit': 18,
  1083. },
  1084. 'params': {
  1085. 'skip_download': True,
  1086. }
  1087. },
  1088. # rtl.nl embed
  1089. {
  1090. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  1091. 'playlist_mincount': 5,
  1092. 'info_dict': {
  1093. 'id': 'aanslagen-kopenhagen',
  1094. 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
  1095. }
  1096. },
  1097. # Zapiks embed
  1098. {
  1099. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  1100. 'info_dict': {
  1101. 'id': '118046',
  1102. 'ext': 'mp4',
  1103. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  1104. }
  1105. },
  1106. # Kaltura embed (different embed code)
  1107. {
  1108. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  1109. 'info_dict': {
  1110. 'id': '1_a52wc67y',
  1111. 'ext': 'flv',
  1112. 'upload_date': '20150127',
  1113. 'uploader_id': 'PremierMedia',
  1114. 'timestamp': int,
  1115. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  1116. },
  1117. },
  1118. # Kaltura embed with single quotes
  1119. {
  1120. 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
  1121. 'info_dict': {
  1122. 'id': '0_izeg5utt',
  1123. 'ext': 'mp4',
  1124. 'title': '35871',
  1125. 'timestamp': 1355743100,
  1126. 'upload_date': '20121217',
  1127. 'uploader_id': 'batchUser',
  1128. },
  1129. 'add_ie': ['Kaltura'],
  1130. },
  1131. {
  1132. # Kaltura embedded via quoted entry_id
  1133. 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
  1134. 'info_dict': {
  1135. 'id': '0_utuok90b',
  1136. 'ext': 'mp4',
  1137. 'title': '06_matthew_brender_raj_dutt',
  1138. 'timestamp': 1466638791,
  1139. 'upload_date': '20160622',
  1140. },
  1141. 'add_ie': ['Kaltura'],
  1142. 'expected_warnings': [
  1143. 'Could not send HEAD request'
  1144. ],
  1145. 'params': {
  1146. 'skip_download': True,
  1147. }
  1148. },
  1149. {
  1150. # Kaltura embedded, some fileExt broken (#11480)
  1151. 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
  1152. 'info_dict': {
  1153. 'id': '1_sgtvehim',
  1154. 'ext': 'mp4',
  1155. 'title': 'Our "Standard Models" of particle physics and cosmology',
  1156. 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
  1157. 'timestamp': 1321158993,
  1158. 'upload_date': '20111113',
  1159. 'uploader_id': 'kps1',
  1160. },
  1161. 'add_ie': ['Kaltura'],
  1162. },
  1163. {
  1164. # Kaltura iframe embed
  1165. 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
  1166. 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
  1167. 'info_dict': {
  1168. 'id': '0_f2cfbpwy',
  1169. 'ext': 'mp4',
  1170. 'title': 'I. M. Pei: A Centennial Celebration',
  1171. 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
  1172. 'upload_date': '20170403',
  1173. 'uploader_id': 'batchUser',
  1174. 'timestamp': 1491232186,
  1175. },
  1176. 'add_ie': ['Kaltura'],
  1177. },
  1178. # Eagle.Platform embed (generic URL)
  1179. {
  1180. 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
  1181. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  1182. 'info_dict': {
  1183. 'id': '227304',
  1184. 'ext': 'mp4',
  1185. 'title': 'Навальный вышел на свободу',
  1186. 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
  1187. 'thumbnail': r're:^https?://.*\.jpg$',
  1188. 'duration': 87,
  1189. 'view_count': int,
  1190. 'age_limit': 0,
  1191. },
  1192. },
  1193. # ClipYou (Eagle.Platform) embed (custom URL)
  1194. {
  1195. 'url': 'http://muz-tv.ru/play/7129/',
  1196. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  1197. 'info_dict': {
  1198. 'id': '12820',
  1199. 'ext': 'mp4',
  1200. 'title': "'O Sole Mio",
  1201. 'thumbnail': r're:^https?://.*\.jpg$',
  1202. 'duration': 216,
  1203. 'view_count': int,
  1204. },
  1205. },
  1206. # Pladform embed
  1207. {
  1208. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  1209. 'info_dict': {
  1210. 'id': '100183293',
  1211. 'ext': 'mp4',
  1212. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  1213. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  1214. 'thumbnail': r're:^https?://.*\.jpg$',
  1215. 'duration': 694,
  1216. 'age_limit': 0,
  1217. },
  1218. },
  1219. # Playwire embed
  1220. {
  1221. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  1222. 'info_dict': {
  1223. 'id': '3519514',
  1224. 'ext': 'mp4',
  1225. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  1226. 'thumbnail': r're:^https?://.*\.png$',
  1227. 'duration': 45.115,
  1228. },
  1229. },
  1230. # 5min embed
  1231. {
  1232. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  1233. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  1234. 'info_dict': {
  1235. 'id': '518726732',
  1236. 'ext': 'mp4',
  1237. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  1238. },
  1239. },
  1240. # SVT embed
  1241. {
  1242. 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
  1243. 'info_dict': {
  1244. 'id': '2900353',
  1245. 'ext': 'flv',
  1246. 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
  1247. 'duration': 27,
  1248. 'age_limit': 0,
  1249. },
  1250. },
  1251. # Crooks and Liars embed
  1252. {
  1253. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  1254. 'info_dict': {
  1255. 'id': '8RUoRhRi',
  1256. 'ext': 'mp4',
  1257. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  1258. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  1259. 'timestamp': 1428207000,
  1260. 'upload_date': '20150405',
  1261. 'uploader': 'Heather',
  1262. },
  1263. },
  1264. # Crooks and Liars external embed
  1265. {
  1266. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  1267. 'info_dict': {
  1268. 'id': 'MTE3MjUtMzQ2MzA',
  1269. 'ext': 'mp4',
  1270. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  1271. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  1272. 'timestamp': 1265032391,
  1273. 'upload_date': '20100201',
  1274. 'uploader': 'Heather',
  1275. },
  1276. },
  1277. # NBC Sports vplayer embed
  1278. {
  1279. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  1280. 'info_dict': {
  1281. 'id': 'ln7x1qSThw4k',
  1282. 'ext': 'flv',
  1283. 'title': "PFT Live: New leader in the 'new-look' defense",
  1284. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  1285. 'uploader': 'NBCU-SPORTS',
  1286. 'upload_date': '20140107',
  1287. 'timestamp': 1389118457,
  1288. },
  1289. },
  1290. # NBC News embed
  1291. {
  1292. 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
  1293. 'md5': '1aa589c675898ae6d37a17913cf68d66',
  1294. 'info_dict': {
  1295. 'id': '701714499682',
  1296. 'ext': 'mp4',
  1297. 'title': 'PREVIEW: On Assignment: David Letterman',
  1298. 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
  1299. },
  1300. },
  1301. # UDN embed
  1302. {
  1303. 'url': 'https://video.udn.com/news/300346',
  1304. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  1305. 'info_dict': {
  1306. 'id': '300346',
  1307. 'ext': 'mp4',
  1308. 'title': '中一中男師變性 全校師生力挺',
  1309. 'thumbnail': r're:^https?://.*\.jpg$',
  1310. },
  1311. 'params': {
  1312. # m3u8 download
  1313. 'skip_download': True,
  1314. },
  1315. },
  1316. # Ooyala embed
  1317. {
  1318. 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
  1319. 'info_dict': {
  1320. 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
  1321. 'ext': 'mp4',
  1322. 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
  1323. 'title': 'This is what separates the Excel masters from the wannabes',
  1324. 'duration': 191.933,
  1325. },
  1326. 'params': {
  1327. # m3u8 downloads
  1328. 'skip_download': True,
  1329. }
  1330. },
  1331. # Brightcove URL in single quotes
  1332. {
  1333. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  1334. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  1335. 'info_dict': {
  1336. 'id': '4255764656001',
  1337. 'ext': 'mp4',
  1338. 'title': 'SN Presents: Russell Martin, World Citizen',
  1339. '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.',
  1340. 'uploader': 'Rogers Sportsnet',
  1341. 'uploader_id': '1704050871',
  1342. 'upload_date': '20150525',
  1343. 'timestamp': 1432570283,
  1344. },
  1345. },
  1346. # Dailymotion Cloud video
  1347. {
  1348. 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
  1349. 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
  1350. 'info_dict': {
  1351. 'id': 'x2uy8t3',
  1352. 'ext': 'mp4',
  1353. 'title': 'Sauvons les abeilles ! - Le débat',
  1354. 'description': 'md5:d9082128b1c5277987825d684939ca26',
  1355. 'thumbnail': r're:^https?://.*\.jpe?g$',
  1356. 'timestamp': 1434970506,
  1357. 'upload_date': '20150622',
  1358. 'uploader': 'Public Sénat',
  1359. 'uploader_id': 'xa9gza',
  1360. }
  1361. },
  1362. # OnionStudios embed
  1363. {
  1364. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1365. 'info_dict': {
  1366. 'id': '2855',
  1367. 'ext': 'mp4',
  1368. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1369. 'thumbnail': r're:^https?://.*\.jpe?g$',
  1370. 'uploader': 'ClickHole',
  1371. 'uploader_id': 'clickhole',
  1372. }
  1373. },
  1374. # SnagFilms embed
  1375. {
  1376. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1377. 'info_dict': {
  1378. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1379. 'ext': 'mp4',
  1380. 'title': '#whilewewatch',
  1381. }
  1382. },
  1383. # AdobeTVVideo embed
  1384. {
  1385. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1386. 'md5': '43662b577c018ad707a63766462b1e87',
  1387. 'info_dict': {
  1388. 'id': '2456',
  1389. 'ext': 'mp4',
  1390. 'title': 'New experience with Acrobat DC',
  1391. 'description': 'New experience with Acrobat DC',
  1392. 'duration': 248.667,
  1393. },
  1394. },
  1395. # BrightcoveInPageEmbed embed
  1396. {
  1397. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1398. 'info_dict': {
  1399. 'id': '4238694884001',
  1400. 'ext': 'flv',
  1401. 'title': 'Tabletop: Dread, Last Thoughts',
  1402. 'description': 'Tabletop: Dread, Last Thoughts',
  1403. 'duration': 51690,
  1404. },
  1405. },
  1406. # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
  1407. # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
  1408. {
  1409. 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
  1410. 'info_dict': {
  1411. 'id': '4785848093001',
  1412. 'ext': 'mp4',
  1413. 'title': 'The Cardinal Pell Interview',
  1414. 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
  1415. 'uploader': 'GlobeCast Australia - GlobeStream',
  1416. 'uploader_id': '2733773828001',
  1417. 'upload_date': '20160304',
  1418. 'timestamp': 1457083087,
  1419. },
  1420. 'params': {
  1421. # m3u8 downloads
  1422. 'skip_download': True,
  1423. },
  1424. },
  1425. # Another form of arte.tv embed
  1426. {
  1427. 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
  1428. 'md5': '850bfe45417ddf221288c88a0cffe2e2',
  1429. 'info_dict': {
  1430. 'id': '030273-562_PLUS7-F',
  1431. 'ext': 'mp4',
  1432. 'title': 'ARTE Reportage - Nulle part, en France',
  1433. 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
  1434. 'upload_date': '20160409',
  1435. },
  1436. },
  1437. # LiveLeak embed
  1438. {
  1439. 'url': 'http://www.wykop.pl/link/3088787/',
  1440. 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
  1441. 'info_dict': {
  1442. 'id': '874_1459135191',
  1443. 'ext': 'mp4',
  1444. 'title': 'Man shows poor quality of new apartment building',
  1445. 'description': 'The wall is like a sand pile.',
  1446. 'uploader': 'Lake8737',
  1447. }
  1448. },
  1449. # Duplicated embedded video URLs
  1450. {
  1451. 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
  1452. 'info_dict': {
  1453. 'id': '149298443_480_16c25b74_2',
  1454. 'ext': 'mp4',
  1455. 'title': 'vs. Blue Orange Spring Game',
  1456. 'uploader': 'www.hudl.com',
  1457. },
  1458. },
  1459. # twitter:player:stream embed
  1460. {
  1461. 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
  1462. 'info_dict': {
  1463. 'id': 'master',
  1464. 'ext': 'mp4',
  1465. 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
  1466. 'uploader': 'www.rtl.be',
  1467. },
  1468. 'params': {
  1469. # m3u8 downloads
  1470. 'skip_download': True,
  1471. },
  1472. },
  1473. # twitter:player embed
  1474. {
  1475. 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
  1476. 'md5': 'a3e0df96369831de324f0778e126653c',
  1477. 'info_dict': {
  1478. 'id': '4909620399001',
  1479. 'ext': 'mp4',
  1480. 'title': 'What Do Black Holes Sound Like?',
  1481. 'description': 'what do black holes sound like',
  1482. 'upload_date': '20160524',
  1483. 'uploader_id': '29913724001',
  1484. 'timestamp': 1464107587,
  1485. 'uploader': 'TheAtlantic',
  1486. },
  1487. 'add_ie': ['BrightcoveLegacy'],
  1488. },
  1489. # Facebook <iframe> embed
  1490. {
  1491. 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
  1492. 'md5': 'fbcde74f534176ecb015849146dd3aee',
  1493. 'info_dict': {
  1494. 'id': '599637780109885',
  1495. 'ext': 'mp4',
  1496. 'title': 'Facebook video #599637780109885',
  1497. },
  1498. },
  1499. # Facebook API embed
  1500. {
  1501. 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
  1502. 'md5': 'a47372ee61b39a7b90287094d447d94e',
  1503. 'info_dict': {
  1504. 'id': '10153467542406923',
  1505. 'ext': 'mp4',
  1506. 'title': 'Facebook video #10153467542406923',
  1507. },
  1508. },
  1509. # Wordpress "YouTube Video Importer" plugin
  1510. {
  1511. 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
  1512. 'md5': 'd16797741b560b485194eddda8121b48',
  1513. 'info_dict': {
  1514. 'id': 'HNTXWDXV9Is',
  1515. 'ext': 'mp4',
  1516. 'title': 'Blue Devils Drumline Stanford lot 2016',
  1517. 'upload_date': '20160627',
  1518. 'uploader_id': 'GENOCIDE8GENERAL10',
  1519. 'uploader': 'cylus cyrus',
  1520. },
  1521. },
  1522. {
  1523. # video stored on custom kaltura server
  1524. 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
  1525. 'md5': '537617d06e64dfed891fa1593c4b30cc',
  1526. 'info_dict': {
  1527. 'id': '0_1iotm5bh',
  1528. 'ext': 'mp4',
  1529. 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
  1530. 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
  1531. 'uploader_id': 'videos.expansion@el-mundo.net',
  1532. 'upload_date': '20150429',
  1533. 'timestamp': 1430303472,
  1534. },
  1535. 'add_ie': ['Kaltura'],
  1536. },
  1537. {
  1538. # Non-standard Vimeo embed
  1539. 'url': 'https://openclassrooms.com/courses/understanding-the-web',
  1540. 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
  1541. 'info_dict': {
  1542. 'id': '148867247',
  1543. 'ext': 'mp4',
  1544. 'title': 'Understanding the web - Teaser',
  1545. 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
  1546. 'upload_date': '20151214',
  1547. 'uploader': 'OpenClassrooms',
  1548. 'uploader_id': 'openclassrooms',
  1549. },
  1550. 'add_ie': ['Vimeo'],
  1551. },
  1552. {
  1553. # generic vimeo embed that requires original URL passed as Referer
  1554. 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
  1555. 'only_matching': True,
  1556. },
  1557. {
  1558. 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
  1559. 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
  1560. 'info_dict': {
  1561. 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
  1562. 'ext': 'mp4',
  1563. 'title': 'Big Buck Bunny',
  1564. 'description': 'Royalty free test video',
  1565. 'timestamp': 1432816365,
  1566. 'upload_date': '20150528',
  1567. 'is_live': False,
  1568. },
  1569. 'params': {
  1570. 'skip_download': True,
  1571. },
  1572. 'add_ie': [ArkenaIE.ie_key()],
  1573. },
  1574. {
  1575. 'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
  1576. 'info_dict': {
  1577. 'id': '1c7141f46c',
  1578. 'ext': 'mp4',
  1579. 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
  1580. },
  1581. 'params': {
  1582. 'skip_download': True,
  1583. },
  1584. 'add_ie': [Vbox7IE.ie_key()],
  1585. },
  1586. {
  1587. # DBTV embeds
  1588. 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
  1589. 'info_dict': {
  1590. 'id': '43254897',
  1591. 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
  1592. },
  1593. 'playlist_mincount': 3,
  1594. },
  1595. {
  1596. # Videa embeds
  1597. 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
  1598. 'info_dict': {
  1599. 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
  1600. 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
  1601. },
  1602. 'playlist_mincount': 2,
  1603. },
  1604. {
  1605. # 20 minuten embed
  1606. 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
  1607. 'info_dict': {
  1608. 'id': '523629',
  1609. 'ext': 'mp4',
  1610. 'title': 'So kommen Sie bei Eis und Schnee sicher an',
  1611. 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
  1612. },
  1613. 'params': {
  1614. 'skip_download': True,
  1615. },
  1616. 'add_ie': [TwentyMinutenIE.ie_key()],
  1617. },
  1618. {
  1619. # VideoPress embed
  1620. 'url': 'https://en.support.wordpress.com/videopress/',
  1621. 'info_dict': {
  1622. 'id': 'OcobLTqC',
  1623. 'ext': 'm4v',
  1624. 'title': 'IMG_5786',
  1625. 'timestamp': 1435711927,
  1626. 'upload_date': '20150701',
  1627. },
  1628. 'params': {
  1629. 'skip_download': True,
  1630. },
  1631. 'add_ie': [VideoPressIE.ie_key()],
  1632. },
  1633. {
  1634. # Rutube embed
  1635. 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
  1636. 'info_dict': {
  1637. 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
  1638. 'ext': 'flv',
  1639. 'title': 'Магаззино: Казань 2',
  1640. 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
  1641. 'uploader': 'Магаззино',
  1642. 'upload_date': '20170228',
  1643. 'uploader_id': '996642',
  1644. },
  1645. 'params': {
  1646. 'skip_download': True,
  1647. },
  1648. 'add_ie': [RutubeIE.ie_key()],
  1649. },
  1650. {
  1651. # ThePlatform embedded with whitespaces in URLs
  1652. 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
  1653. 'only_matching': True,
  1654. },
  1655. {
  1656. # Senate ISVP iframe https
  1657. 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
  1658. 'md5': 'fb8c70b0b515e5037981a2492099aab8',
  1659. 'info_dict': {
  1660. 'id': 'govtaff020316',
  1661. 'ext': 'mp4',
  1662. 'title': 'Integrated Senate Video Player',
  1663. },
  1664. 'add_ie': [SenateISVPIE.ie_key()],
  1665. },
  1666. {
  1667. # Limelight embeds (1 channel embed + 4 media embeds)
  1668. 'url': 'http://www.sedona.com/FacilitatorTraining2017',
  1669. 'info_dict': {
  1670. 'id': 'FacilitatorTraining2017',
  1671. 'title': 'Facilitator Training 2017',
  1672. },
  1673. 'playlist_mincount': 5,
  1674. },
  1675. {
  1676. 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
  1677. 'info_dict': {
  1678. 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
  1679. 'title': 'Standoff with Walnut Creek murder suspect ends',
  1680. 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
  1681. },
  1682. 'playlist_mincount': 4,
  1683. },
  1684. # {
  1685. # # TODO: find another test
  1686. # # http://schema.org/VideoObject
  1687. # 'url': 'https://flipagram.com/f/nyvTSJMKId',
  1688. # 'md5': '888dcf08b7ea671381f00fab74692755',
  1689. # 'info_dict': {
  1690. # 'id': 'nyvTSJMKId',
  1691. # 'ext': 'mp4',
  1692. # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
  1693. # 'description': '#love for cats.',
  1694. # 'timestamp': 1461244995,
  1695. # 'upload_date': '20160421',
  1696. # },
  1697. # 'params': {
  1698. # 'force_generic_extractor': True,
  1699. # },
  1700. # }
  1701. ]
  1702. def report_following_redirect(self, new_url):
  1703. """Report information extraction."""
  1704. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  1705. def _extract_rss(self, url, video_id, doc):
  1706. playlist_title = doc.find('./channel/title').text
  1707. playlist_desc_el = doc.find('./channel/description')
  1708. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  1709. entries = []
  1710. for it in doc.findall('./channel/item'):
  1711. next_url = xpath_text(it, 'link', fatal=False)
  1712. if not next_url:
  1713. enclosure_nodes = it.findall('./enclosure')
  1714. for e in enclosure_nodes:
  1715. next_url = e.attrib.get('url')
  1716. if next_url:
  1717. break
  1718. if not next_url:
  1719. continue
  1720. entries.append({
  1721. '_type': 'url_transparent',
  1722. 'url': next_url,
  1723. 'title': it.find('title').text,
  1724. })
  1725. return {
  1726. '_type': 'playlist',
  1727. 'id': url,
  1728. 'title': playlist_title,
  1729. 'description': playlist_desc,
  1730. 'entries': entries,
  1731. }
  1732. def _extract_camtasia(self, url, video_id, webpage):
  1733. """ Returns None if no camtasia video can be found. """
  1734. camtasia_cfg = self._search_regex(
  1735. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  1736. webpage, 'camtasia configuration file', default=None)
  1737. if camtasia_cfg is None:
  1738. return None
  1739. title = self._html_search_meta('DC.title', webpage, fatal=True)
  1740. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  1741. camtasia_cfg = self._download_xml(
  1742. camtasia_url, video_id,
  1743. note='Downloading camtasia configuration',
  1744. errnote='Failed to download camtasia configuration')
  1745. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  1746. entries = []
  1747. for n in fileset_node.getchildren():
  1748. url_n = n.find('./uri')
  1749. if url_n is None:
  1750. continue
  1751. entries.append({
  1752. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  1753. 'title': '%s - %s' % (title, n.tag),
  1754. 'url': compat_urlparse.urljoin(url, url_n.text),
  1755. 'duration': float_or_none(n.find('./duration').text),
  1756. })
  1757. return {
  1758. '_type': 'playlist',
  1759. 'entries': entries,
  1760. 'title': title,
  1761. }
  1762. def _real_extract(self, url):
  1763. if url.startswith('//'):
  1764. return {
  1765. '_type': 'url',
  1766. 'url': self.http_scheme() + url,
  1767. }
  1768. parsed_url = compat_urlparse.urlparse(url)
  1769. if not parsed_url.scheme:
  1770. default_search = self._downloader.params.get('default_search')
  1771. if default_search is None:
  1772. default_search = 'fixup_error'
  1773. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  1774. if '/' in url:
  1775. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  1776. return self.url_result('http://' + url)
  1777. elif default_search != 'fixup_error':
  1778. if default_search == 'auto_warning':
  1779. if re.match(r'^(?:url|URL)$', url):
  1780. raise ExtractorError(
  1781. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  1782. expected=True)
  1783. else:
  1784. self._downloader.report_warning(
  1785. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  1786. return self.url_result('ytsearch:' + url)
  1787. if default_search in ('error', 'fixup_error'):
  1788. raise ExtractorError(
  1789. '%r is not a valid URL. '
  1790. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  1791. % (url, url), expected=True)
  1792. else:
  1793. if ':' not in default_search:
  1794. default_search += ':'
  1795. return self.url_result(default_search + url)
  1796. url, smuggled_data = unsmuggle_url(url)
  1797. force_videoid = None
  1798. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  1799. if smuggled_data and 'force_videoid' in smuggled_data:
  1800. force_videoid = smuggled_data['force_videoid']
  1801. video_id = force_videoid
  1802. else:
  1803. video_id = self._generic_id(url)
  1804. self.to_screen('%s: Requesting header' % video_id)
  1805. head_req = HEADRequest(url)
  1806. head_response = self._request_webpage(
  1807. head_req, video_id,
  1808. note=False, errnote='Could not send HEAD request to %s' % url,
  1809. fatal=False)
  1810. if head_response is not False:
  1811. # Check for redirect
  1812. new_url = head_response.geturl()
  1813. if url != new_url:
  1814. self.report_following_redirect(new_url)
  1815. if force_videoid:
  1816. new_url = smuggle_url(
  1817. new_url, {'force_videoid': force_videoid})
  1818. return self.url_result(new_url)
  1819. full_response = None
  1820. if head_response is False:
  1821. request = sanitized_Request(url)
  1822. request.add_header('Accept-Encoding', '*')
  1823. full_response = self._request_webpage(request, video_id)
  1824. head_response = full_response
  1825. info_dict = {
  1826. 'id': video_id,
  1827. 'title': self._generic_title(url),
  1828. 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
  1829. }
  1830. # Check for direct link to a video
  1831. content_type = head_response.headers.get('Content-Type', '').lower()
  1832. m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
  1833. if m:
  1834. format_id = m.group('format_id')
  1835. if format_id.endswith('mpegurl'):
  1836. formats = self._extract_m3u8_formats(url, video_id, 'mp4')
  1837. elif format_id == 'f4m':
  1838. formats = self._extract_f4m_formats(url, video_id)
  1839. else:
  1840. formats = [{
  1841. 'format_id': m.group('format_id'),
  1842. 'url': url,
  1843. 'vcodec': 'none' if m.group('type') == 'audio' else None
  1844. }]
  1845. info_dict['direct'] = True
  1846. self._sort_formats(formats)
  1847. info_dict['formats'] = formats
  1848. return info_dict
  1849. if not self._downloader.params.get('test', False) and not is_intentional:
  1850. force = self._downloader.params.get('force_generic_extractor', False)
  1851. self._downloader.report_warning(
  1852. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  1853. if not full_response:
  1854. request = sanitized_Request(url)
  1855. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  1856. # making it impossible to download only chunk of the file (yet we need only 512kB to
  1857. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  1858. # that will always result in downloading the whole file that is not desirable.
  1859. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  1860. # to accept raw bytes and being able to download only a chunk.
  1861. # It may probably better to solve this by checking Content-Type for application/octet-stream
  1862. # after HEAD request finishes, but not sure if we can rely on this.
  1863. request.add_header('Accept-Encoding', '*')
  1864. full_response = self._request_webpage(request, video_id)
  1865. first_bytes = full_response.read(512)
  1866. # Is it an M3U playlist?
  1867. if first_bytes.startswith(b'#EXTM3U'):
  1868. info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
  1869. self._sort_formats(info_dict['formats'])
  1870. return info_dict
  1871. # Maybe it's a direct link to a video?
  1872. # Be careful not to download the whole thing!
  1873. if not is_html(first_bytes):
  1874. self._downloader.report_warning(
  1875. 'URL could be a direct video link, returning it as such.')
  1876. info_dict.update({
  1877. 'direct': True,
  1878. 'url': url,
  1879. })
  1880. return info_dict
  1881. webpage = self._webpage_read_content(
  1882. full_response, url, video_id, prefix=first_bytes)
  1883. self.report_extraction(video_id)
  1884. # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
  1885. try:
  1886. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  1887. if doc.tag == 'rss':
  1888. return self._extract_rss(url, video_id, doc)
  1889. elif doc.tag == 'SmoothStreamingMedia':
  1890. info_dict['formats'] = self._parse_ism_formats(doc, url)
  1891. self._sort_formats(info_dict['formats'])
  1892. return info_dict
  1893. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  1894. smil = self._parse_smil(doc, url, video_id)
  1895. self._sort_formats(smil['formats'])
  1896. return smil
  1897. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  1898. return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
  1899. elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
  1900. info_dict['formats'] = self._parse_mpd_formats(
  1901. doc, video_id,
  1902. mpd_base_url=full_response.geturl().rpartition('/')[0],
  1903. mpd_url=url)
  1904. self._sort_formats(info_dict['formats'])
  1905. return info_dict
  1906. elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
  1907. info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
  1908. self._sort_formats(info_dict['formats'])
  1909. return info_dict
  1910. except compat_xml_parse_error:
  1911. pass
  1912. # Is it a Camtasia project?
  1913. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  1914. if camtasia_res is not None:
  1915. return camtasia_res
  1916. # Sometimes embedded video player is hidden behind percent encoding
  1917. # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
  1918. # Unescaping the whole page allows to handle those cases in a generic way
  1919. webpage = compat_urllib_parse_unquote(webpage)
  1920. # it's tempting to parse this further, but you would
  1921. # have to take into account all the variations like
  1922. # Video Title - Site Name
  1923. # Site Name | Video Title
  1924. # Video Title - Tagline | Site Name
  1925. # and so on and so forth; it's just not practical
  1926. video_title = self._og_search_title(
  1927. webpage, default=None) or self._html_search_regex(
  1928. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  1929. default='video')
  1930. # Try to detect age limit automatically
  1931. age_limit = self._rta_search(webpage)
  1932. # And then there are the jokers who advertise that they use RTA,
  1933. # but actually don't.
  1934. AGE_LIMIT_MARKERS = [
  1935. r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
  1936. ]
  1937. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  1938. age_limit = 18
  1939. # video uploader is domain name
  1940. video_uploader = self._search_regex(
  1941. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  1942. video_description = self._og_search_description(webpage, default=None)
  1943. video_thumbnail = self._og_search_thumbnail(webpage, default=None)
  1944. # Look for Brightcove Legacy Studio embeds
  1945. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  1946. if bc_urls:
  1947. entries = [{
  1948. '_type': 'url',
  1949. 'url': smuggle_url(bc_url, {'Referer': url}),
  1950. 'ie_key': 'BrightcoveLegacy'
  1951. } for bc_url in bc_urls]
  1952. return {
  1953. '_type': 'playlist',
  1954. 'title': video_title,
  1955. 'id': video_id,
  1956. 'entries': entries,
  1957. }
  1958. # Look for Brightcove New Studio embeds
  1959. bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
  1960. if bc_urls:
  1961. return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
  1962. # Look for ThePlatform embeds
  1963. tp_urls = ThePlatformIE._extract_urls(webpage)
  1964. if tp_urls:
  1965. return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
  1966. # Look for Vessel embeds
  1967. vessel_urls = VesselIE._extract_urls(webpage)
  1968. if vessel_urls:
  1969. return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
  1970. # Look for embedded rtl.nl player
  1971. matches = re.findall(
  1972. r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
  1973. webpage)
  1974. if matches:
  1975. return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
  1976. vimeo_urls = VimeoIE._extract_urls(url, webpage)
  1977. if vimeo_urls:
  1978. return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
  1979. vid_me_embed_url = self._search_regex(
  1980. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  1981. webpage, 'vid.me embed', default=None)
  1982. if vid_me_embed_url is not None:
  1983. return self.url_result(vid_me_embed_url, 'Vidme')
  1984. # Look for embedded YouTube player
  1985. matches = re.findall(r'''(?x)
  1986. (?:
  1987. <iframe[^>]+?src=|
  1988. data-video-url=|
  1989. <embed[^>]+?src=|
  1990. embedSWF\(?:\s*|
  1991. <object[^>]+data=|
  1992. new\s+SWFObject\(
  1993. )
  1994. (["\'])
  1995. (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
  1996. (?:embed|v|p)/.+?)
  1997. \1''', webpage)
  1998. if matches:
  1999. return self.playlist_from_matches(
  2000. matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
  2001. # Look for lazyYT YouTube embed
  2002. matches = re.findall(
  2003. r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
  2004. if matches:
  2005. return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
  2006. # Look for Wordpress "YouTube Video Importer" plugin
  2007. matches = re.findall(r'''(?x)<div[^>]+
  2008. class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
  2009. data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
  2010. if matches:
  2011. return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
  2012. matches = DailymotionIE._extract_urls(webpage)
  2013. if matches:
  2014. return self.playlist_from_matches(matches, video_id, video_title)
  2015. # Look for embedded Dailymotion playlist player (#3822)
  2016. m = re.search(
  2017. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  2018. if m:
  2019. playlists = re.findall(
  2020. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  2021. if playlists:
  2022. return self.playlist_from_matches(
  2023. playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
  2024. # Look for embedded Wistia player
  2025. match = re.search(
  2026. r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
  2027. if match:
  2028. embed_url = self._proto_relative_url(
  2029. unescapeHTML(match.group('url')))
  2030. return {
  2031. '_type': 'url_transparent',
  2032. 'url': embed_url,
  2033. 'ie_key': 'Wistia',
  2034. 'uploader': video_uploader,
  2035. }
  2036. match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
  2037. if match:
  2038. return {
  2039. '_type': 'url_transparent',
  2040. 'url': 'wistia:%s' % match.group('id'),
  2041. 'ie_key': 'Wistia',
  2042. 'uploader': video_uploader,
  2043. }
  2044. match = re.search(
  2045. r'''(?sx)
  2046. <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
  2047. <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
  2048. ''', webpage)
  2049. if match:
  2050. return self.url_result(self._proto_relative_url(
  2051. 'wistia:%s' % match.group('id')), 'Wistia')
  2052. # Look for SVT player
  2053. svt_url = SVTIE._extract_url(webpage)
  2054. if svt_url:
  2055. return self.url_result(svt_url, 'SVT')
  2056. # Look for embedded condenast player
  2057. matches = re.findall(
  2058. r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
  2059. webpage)
  2060. if matches:
  2061. return {
  2062. '_type': 'playlist',
  2063. 'entries': [{
  2064. '_type': 'url',
  2065. 'ie_key': 'CondeNast',
  2066. 'url': ma,
  2067. } for ma in matches],
  2068. 'title': video_title,
  2069. 'id': video_id,
  2070. }
  2071. # Look for Bandcamp pages with custom domain
  2072. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  2073. if mobj is not None:
  2074. burl = unescapeHTML(mobj.group(1))
  2075. # Don't set the extractor because it can be a track url or an album
  2076. return self.url_result(burl)
  2077. # Look for embedded Vevo player
  2078. mobj = re.search(
  2079. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  2080. if mobj is not None:
  2081. return self.url_result(mobj.group('url'))
  2082. # Look for embedded Viddler player
  2083. mobj = re.search(
  2084. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  2085. webpage)
  2086. if mobj is not None:
  2087. return self.url_result(mobj.group('url'))
  2088. # Look for NYTimes player
  2089. mobj = re.search(
  2090. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  2091. webpage)
  2092. if mobj is not None:
  2093. return self.url_result(mobj.group('url'))
  2094. # Look for Libsyn player
  2095. mobj = re.search(
  2096. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  2097. if mobj is not None:
  2098. return self.url_result(mobj.group('url'))
  2099. # Look for Ooyala videos
  2100. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
  2101. re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
  2102. re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
  2103. re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  2104. if mobj is not None:
  2105. embed_token = self._search_regex(
  2106. r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
  2107. webpage, 'ooyala embed token', default=None)
  2108. return OoyalaIE._build_url_result(smuggle_url(
  2109. mobj.group('ec'), {
  2110. 'domain': url,
  2111. 'embed_token': embed_token,
  2112. }))
  2113. # Look for multiple Ooyala embeds on SBN network websites
  2114. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  2115. if mobj is not None:
  2116. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  2117. if embeds:
  2118. return self.playlist_from_matches(
  2119. embeds, video_id, video_title,
  2120. getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  2121. # Look for Aparat videos
  2122. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  2123. if mobj is not None:
  2124. return self.url_result(mobj.group(1), 'Aparat')
  2125. # Look for MPORA videos
  2126. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  2127. if mobj is not None:
  2128. return self.url_result(mobj.group(1), 'Mpora')
  2129. # Look for embedded NovaMov-based player
  2130. mobj = re.search(
  2131. r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
  2132. (?P<url>http://(?:(?:embed|www)\.)?
  2133. (?:novamov\.com|
  2134. nowvideo\.(?:ch|sx|eu|at|ag|co)|
  2135. videoweed\.(?:es|com)|
  2136. movshare\.(?:net|sx|ag)|
  2137. divxstage\.(?:eu|net|ch|co|at|ag))
  2138. /embed\.php.+?)\1''', webpage)
  2139. if mobj is not None:
  2140. return self.url_result(mobj.group('url'))
  2141. # Look for embedded Facebook player
  2142. facebook_url = FacebookIE._extract_url(webpage)
  2143. if facebook_url is not None:
  2144. return self.url_result(facebook_url, 'Facebook')
  2145. # Look for embedded VK player
  2146. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  2147. if mobj is not None:
  2148. return self.url_result(mobj.group('url'), 'VK')
  2149. # Look for embedded Odnoklassniki player
  2150. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
  2151. if mobj is not None:
  2152. return self.url_result(mobj.group('url'), 'Odnoklassniki')
  2153. # Look for embedded ivi player
  2154. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  2155. if mobj is not None:
  2156. return self.url_result(mobj.group('url'), 'Ivi')
  2157. # Look for embedded Huffington Post player
  2158. mobj = re.search(
  2159. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  2160. if mobj is not None:
  2161. return self.url_result(mobj.group('url'), 'HuffPost')
  2162. # Look for embed.ly
  2163. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  2164. if mobj is not None:
  2165. return self.url_result(mobj.group('url'))
  2166. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  2167. if mobj is not None:
  2168. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  2169. # Look for funnyordie embed
  2170. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  2171. if matches:
  2172. return self.playlist_from_matches(
  2173. matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
  2174. # Look for BBC iPlayer embed
  2175. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  2176. if matches:
  2177. return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
  2178. # Look for embedded RUTV player
  2179. rutv_url = RUTVIE._extract_url(webpage)
  2180. if rutv_url:
  2181. return self.url_result(rutv_url, 'RUTV')
  2182. # Look for embedded TVC player
  2183. tvc_url = TVCIE._extract_url(webpage)
  2184. if tvc_url:
  2185. return self.url_result(tvc_url, 'TVC')
  2186. # Look for embedded SportBox player
  2187. sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
  2188. if sportbox_urls:
  2189. return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
  2190. # Look for embedded XHamster player
  2191. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  2192. if xhamster_urls:
  2193. return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
  2194. # Look for embedded TNAFlixNetwork player
  2195. tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
  2196. if tnaflix_urls:
  2197. return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
  2198. # Look for embedded PornHub player
  2199. pornhub_urls = PornHubIE._extract_urls(webpage)
  2200. if pornhub_urls:
  2201. return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
  2202. # Look for embedded DrTuber player
  2203. drtuber_urls = DrTuberIE._extract_urls(webpage)
  2204. if drtuber_urls:
  2205. return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
  2206. # Look for embedded RedTube player
  2207. redtube_urls = RedTubeIE._extract_urls(webpage)
  2208. if redtube_urls:
  2209. return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
  2210. # Look for embedded Tvigle player
  2211. mobj = re.search(
  2212. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  2213. if mobj is not None:
  2214. return self.url_result(mobj.group('url'), 'Tvigle')
  2215. # Look for embedded TED player
  2216. mobj = re.search(
  2217. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  2218. if mobj is not None:
  2219. return self.url_result(mobj.group('url'), 'TED')
  2220. # Look for embedded Ustream videos
  2221. ustream_url = UstreamIE._extract_url(webpage)
  2222. if ustream_url:
  2223. return self.url_result(ustream_url, UstreamIE.ie_key())
  2224. # Look for embedded arte.tv player
  2225. mobj = re.search(
  2226. r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
  2227. webpage)
  2228. if mobj is not None:
  2229. return self.url_result(mobj.group('url'), 'ArteTVEmbed')
  2230. # Look for embedded francetv player
  2231. mobj = re.search(
  2232. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  2233. webpage)
  2234. if mobj is not None:
  2235. return self.url_result(mobj.group('url'))
  2236. # Look for embedded smotri.com player
  2237. smotri_url = SmotriIE._extract_url(webpage)
  2238. if smotri_url:
  2239. return self.url_result(smotri_url, 'Smotri')
  2240. # Look for embedded Myvi.ru player
  2241. myvi_url = MyviIE._extract_url(webpage)
  2242. if myvi_url:
  2243. return self.url_result(myvi_url)
  2244. # Look for embedded soundcloud player
  2245. soundcloud_urls = SoundcloudIE._extract_urls(webpage)
  2246. if soundcloud_urls:
  2247. return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
  2248. # Look for tunein player
  2249. tunein_urls = TuneInBaseIE._extract_urls(webpage)
  2250. if tunein_urls:
  2251. return self.playlist_from_matches(tunein_urls, video_id, video_title)
  2252. # Look for embedded mtvservices player
  2253. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  2254. if mtvservices_url:
  2255. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  2256. # Look for embedded yahoo player
  2257. mobj = re.search(
  2258. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  2259. webpage)
  2260. if mobj is not None:
  2261. return self.url_result(mobj.group('url'), 'Yahoo')
  2262. # Look for embedded sbs.com.au player
  2263. mobj = re.search(
  2264. r'''(?x)
  2265. (?:
  2266. <meta\s+property="og:video"\s+content=|
  2267. <iframe[^>]+?src=
  2268. )
  2269. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  2270. webpage)
  2271. if mobj is not None:
  2272. return self.url_result(mobj.group('url'), 'SBS')
  2273. # Look for embedded Cinchcast player
  2274. mobj = re.search(
  2275. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  2276. webpage)
  2277. if mobj is not None:
  2278. return self.url_result(mobj.group('url'), 'Cinchcast')
  2279. mobj = re.search(
  2280. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  2281. webpage)
  2282. if not mobj:
  2283. mobj = re.search(
  2284. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  2285. webpage)
  2286. if mobj is not None:
  2287. return self.url_result(mobj.group('url'), 'MLB')
  2288. mobj = re.search(
  2289. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  2290. webpage)
  2291. if mobj is not None:
  2292. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  2293. mobj = re.search(
  2294. r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
  2295. webpage)
  2296. if mobj is not None:
  2297. return self.url_result(mobj.group('url'), 'Livestream')
  2298. # Look for Zapiks embed
  2299. mobj = re.search(
  2300. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  2301. if mobj is not None:
  2302. return self.url_result(mobj.group('url'), 'Zapiks')
  2303. # Look for Kaltura embeds
  2304. kaltura_url = KalturaIE._extract_url(webpage)
  2305. if kaltura_url:
  2306. return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
  2307. # Look for Eagle.Platform embeds
  2308. eagleplatform_url = EaglePlatformIE._extract_url(webpage)
  2309. if eagleplatform_url:
  2310. return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
  2311. # Look for ClipYou (uses Eagle.Platform) embeds
  2312. mobj = re.search(
  2313. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  2314. if mobj is not None:
  2315. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  2316. # Look for Pladform embeds
  2317. pladform_url = PladformIE._extract_url(webpage)
  2318. if pladform_url:
  2319. return self.url_result(pladform_url)
  2320. # Look for Videomore embeds
  2321. videomore_url = VideomoreIE._extract_url(webpage)
  2322. if videomore_url:
  2323. return self.url_result(videomore_url)
  2324. # Look for Webcaster embeds
  2325. webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
  2326. if webcaster_url:
  2327. return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
  2328. # Look for Playwire embeds
  2329. mobj = re.search(
  2330. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  2331. if mobj is not None:
  2332. return self.url_result(mobj.group('url'))
  2333. # Look for 5min embeds
  2334. mobj = re.search(
  2335. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  2336. if mobj is not None:
  2337. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  2338. # Look for Crooks and Liars embeds
  2339. mobj = re.search(
  2340. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  2341. if mobj is not None:
  2342. return self.url_result(mobj.group('url'))
  2343. # Look for NBC Sports VPlayer embeds
  2344. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  2345. if nbc_sports_url:
  2346. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  2347. # Look for NBC News embeds
  2348. nbc_news_embed_url = re.search(
  2349. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
  2350. if nbc_news_embed_url:
  2351. return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
  2352. # Look for Google Drive embeds
  2353. google_drive_url = GoogleDriveIE._extract_url(webpage)
  2354. if google_drive_url:
  2355. return self.url_result(google_drive_url, 'GoogleDrive')
  2356. # Look for UDN embeds
  2357. mobj = re.search(
  2358. r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  2359. if mobj is not None:
  2360. return self.url_result(
  2361. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  2362. # Look for Senate ISVP iframe
  2363. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  2364. if senate_isvp_url:
  2365. return self.url_result(senate_isvp_url, 'SenateISVP')
  2366. # Look for Dailymotion Cloud videos
  2367. dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
  2368. if dmcloud_url:
  2369. return self.url_result(dmcloud_url, 'DailymotionCloud')
  2370. # Look for OnionStudios embeds
  2371. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  2372. if onionstudios_url:
  2373. return self.url_result(onionstudios_url)
  2374. # Look for ViewLift embeds
  2375. viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
  2376. if viewlift_url:
  2377. return self.url_result(viewlift_url)
  2378. # Look for JWPlatform embeds
  2379. jwplatform_url = JWPlatformIE._extract_url(webpage)
  2380. if jwplatform_url:
  2381. return self.url_result(jwplatform_url, 'JWPlatform')
  2382. # Look for Digiteka embeds
  2383. digiteka_url = DigitekaIE._extract_url(webpage)
  2384. if digiteka_url:
  2385. return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
  2386. # Look for Arkena embeds
  2387. arkena_url = ArkenaIE._extract_url(webpage)
  2388. if arkena_url:
  2389. return self.url_result(arkena_url, ArkenaIE.ie_key())
  2390. # Look for Piksel embeds
  2391. piksel_url = PikselIE._extract_url(webpage)
  2392. if piksel_url:
  2393. return self.url_result(piksel_url, PikselIE.ie_key())
  2394. # Look for Limelight embeds
  2395. limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
  2396. if limelight_urls:
  2397. return self.playlist_result(
  2398. limelight_urls, video_id, video_title, video_description)
  2399. mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
  2400. if mobj:
  2401. lm = {
  2402. 'Media': 'media',
  2403. 'Channel': 'channel',
  2404. 'ChannelList': 'channel_list',
  2405. }
  2406. return self.url_result(smuggle_url('limelight:%s:%s' % (
  2407. lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
  2408. 'Limelight%s' % mobj.group(1), mobj.group(2))
  2409. mobj = re.search(
  2410. r'''(?sx)
  2411. <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
  2412. <param[^>]+
  2413. name=(["\'])flashVars\2[^>]+
  2414. value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
  2415. ''', webpage)
  2416. if mobj:
  2417. return self.url_result(smuggle_url(
  2418. 'limelight:media:%s' % mobj.group('id'),
  2419. {'source_url': url}), 'LimelightMedia', mobj.group('id'))
  2420. # Look for Anvato embeds
  2421. anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
  2422. if anvato_urls:
  2423. return self.playlist_result(
  2424. anvato_urls, video_id, video_title, video_description)
  2425. # Look for AdobeTVVideo embeds
  2426. mobj = re.search(
  2427. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  2428. webpage)
  2429. if mobj is not None:
  2430. return self.url_result(
  2431. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  2432. 'AdobeTVVideo')
  2433. # Look for Vine embeds
  2434. mobj = re.search(
  2435. r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
  2436. webpage)
  2437. if mobj is not None:
  2438. return self.url_result(
  2439. self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
  2440. # Look for VODPlatform embeds
  2441. mobj = re.search(
  2442. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
  2443. webpage)
  2444. if mobj is not None:
  2445. return self.url_result(
  2446. self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
  2447. # Look for Mangomolo embeds
  2448. mobj = re.search(
  2449. r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
  2450. (?:
  2451. video\?.*?\bid=(?P<video_id>\d+)|
  2452. index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
  2453. ).+?)\1''', webpage)
  2454. if mobj is not None:
  2455. info = {
  2456. '_type': 'url_transparent',
  2457. 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
  2458. 'title': video_title,
  2459. 'description': video_description,
  2460. 'thumbnail': video_thumbnail,
  2461. 'uploader': video_uploader,
  2462. }
  2463. video_id = mobj.group('video_id')
  2464. if video_id:
  2465. info.update({
  2466. 'ie_key': 'MangomoloVideo',
  2467. 'id': video_id,
  2468. })
  2469. else:
  2470. info.update({
  2471. 'ie_key': 'MangomoloLive',
  2472. 'id': mobj.group('channel_id'),
  2473. })
  2474. return info
  2475. # Look for Instagram embeds
  2476. instagram_embed_url = InstagramIE._extract_embed_url(webpage)
  2477. if instagram_embed_url is not None:
  2478. return self.url_result(
  2479. self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
  2480. # Look for LiveLeak embeds
  2481. liveleak_url = LiveLeakIE._extract_url(webpage)
  2482. if liveleak_url:
  2483. return self.url_result(liveleak_url, 'LiveLeak')
  2484. # Look for 3Q SDN embeds
  2485. threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
  2486. if threeqsdn_url:
  2487. return {
  2488. '_type': 'url_transparent',
  2489. 'ie_key': ThreeQSDNIE.ie_key(),
  2490. 'url': self._proto_relative_url(threeqsdn_url),
  2491. 'title': video_title,
  2492. 'description': video_description,
  2493. 'thumbnail': video_thumbnail,
  2494. 'uploader': video_uploader,
  2495. }
  2496. # Look for VBOX7 embeds
  2497. vbox7_url = Vbox7IE._extract_url(webpage)
  2498. if vbox7_url:
  2499. return self.url_result(vbox7_url, Vbox7IE.ie_key())
  2500. # Look for DBTV embeds
  2501. dbtv_urls = DBTVIE._extract_urls(webpage)
  2502. if dbtv_urls:
  2503. return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
  2504. # Look for Videa embeds
  2505. videa_urls = VideaIE._extract_urls(webpage)
  2506. if videa_urls:
  2507. return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
  2508. # Look for 20 minuten embeds
  2509. twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
  2510. if twentymin_urls:
  2511. return self.playlist_from_matches(
  2512. twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
  2513. # Look for Openload embeds
  2514. openload_urls = OpenloadIE._extract_urls(webpage)
  2515. if openload_urls:
  2516. return self.playlist_from_matches(
  2517. openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
  2518. # Look for VideoPress embeds
  2519. videopress_urls = VideoPressIE._extract_urls(webpage)
  2520. if videopress_urls:
  2521. return self.playlist_from_matches(
  2522. videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
  2523. # Look for Rutube embeds
  2524. rutube_urls = RutubeIE._extract_urls(webpage)
  2525. if rutube_urls:
  2526. return self.playlist_from_matches(
  2527. rutube_urls, ie=RutubeIE.ie_key())
  2528. # Looking for http://schema.org/VideoObject
  2529. json_ld = self._search_json_ld(
  2530. webpage, video_id, default={}, expected_type='VideoObject')
  2531. if json_ld.get('url'):
  2532. info_dict.update({
  2533. 'title': video_title or info_dict['title'],
  2534. 'description': video_description,
  2535. 'thumbnail': video_thumbnail,
  2536. 'age_limit': age_limit
  2537. })
  2538. info_dict.update(json_ld)
  2539. return info_dict
  2540. # Look for HTML5 media
  2541. entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
  2542. if entries:
  2543. for entry in entries:
  2544. entry.update({
  2545. 'id': video_id,
  2546. 'title': video_title,
  2547. })
  2548. self._sort_formats(entry['formats'])
  2549. return self.playlist_result(entries)
  2550. jwplayer_data = self._find_jwplayer_data(
  2551. webpage, video_id, transform_source=js_to_json)
  2552. if jwplayer_data:
  2553. info = self._parse_jwplayer_data(
  2554. jwplayer_data, video_id, require_title=False, base_url=url)
  2555. if not info.get('title'):
  2556. info['title'] = video_title
  2557. return info
  2558. def check_video(vurl):
  2559. if YoutubeIE.suitable(vurl):
  2560. return True
  2561. if RtmpIE.suitable(vurl):
  2562. return True
  2563. vpath = compat_urlparse.urlparse(vurl).path
  2564. vext = determine_ext(vpath)
  2565. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
  2566. def filter_video(urls):
  2567. return list(filter(check_video, urls))
  2568. # Start with something easy: JW Player in SWFObject
  2569. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  2570. if not found:
  2571. # Look for gorilla-vid style embedding
  2572. found = filter_video(re.findall(r'''(?sx)
  2573. (?:
  2574. jw_plugins|
  2575. JWPlayerOptions|
  2576. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  2577. )
  2578. .*?
  2579. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  2580. if not found:
  2581. # Broaden the search a little bit
  2582. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  2583. if not found:
  2584. # Broaden the findall a little bit: JWPlayer JS loader
  2585. found = filter_video(re.findall(
  2586. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  2587. if not found:
  2588. # Flow player
  2589. found = filter_video(re.findall(r'''(?xs)
  2590. flowplayer\("[^"]+",\s*
  2591. \{[^}]+?\}\s*,
  2592. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  2593. ["']?url["']?\s*:\s*["']([^"']+)["']
  2594. ''', webpage))
  2595. if not found:
  2596. # Cinerama player
  2597. found = re.findall(
  2598. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  2599. if not found:
  2600. # Try to find twitter cards info
  2601. # twitter:player:stream should be checked before twitter:player since
  2602. # it is expected to contain a raw stream (see
  2603. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  2604. found = filter_video(re.findall(
  2605. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  2606. if not found:
  2607. # We look for Open Graph info:
  2608. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  2609. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  2610. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  2611. if m_video_type is not None:
  2612. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  2613. if not found:
  2614. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  2615. found = re.search(
  2616. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  2617. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  2618. webpage)
  2619. if not found:
  2620. # Look also in Refresh HTTP header
  2621. refresh_header = head_response.headers.get('Refresh')
  2622. if refresh_header:
  2623. # In python 2 response HTTP headers are bytestrings
  2624. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  2625. refresh_header = refresh_header.decode('iso-8859-1')
  2626. found = re.search(REDIRECT_REGEX, refresh_header)
  2627. if found:
  2628. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  2629. if new_url != url:
  2630. self.report_following_redirect(new_url)
  2631. return {
  2632. '_type': 'url',
  2633. 'url': new_url,
  2634. }
  2635. else:
  2636. found = None
  2637. if not found:
  2638. # twitter:player is a https URL to iframe player that may or may not
  2639. # be supported by youtube-dl thus this is checked the very last (see
  2640. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  2641. embed_url = self._html_search_meta('twitter:player', webpage, default=None)
  2642. if embed_url:
  2643. return self.url_result(embed_url)
  2644. if not found:
  2645. raise UnsupportedError(url)
  2646. entries = []
  2647. for video_url in orderedSet(found):
  2648. video_url = unescapeHTML(video_url)
  2649. video_url = video_url.replace('\\/', '/')
  2650. video_url = compat_urlparse.urljoin(url, video_url)
  2651. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  2652. # Sometimes, jwplayer extraction will result in a YouTube URL
  2653. if YoutubeIE.suitable(video_url):
  2654. entries.append(self.url_result(video_url, 'Youtube'))
  2655. continue
  2656. # here's a fun little line of code for you:
  2657. video_id = os.path.splitext(video_id)[0]
  2658. entry_info_dict = {
  2659. 'id': video_id,
  2660. 'uploader': video_uploader,
  2661. 'title': video_title,
  2662. 'age_limit': age_limit,
  2663. }
  2664. if RtmpIE.suitable(video_url):
  2665. entry_info_dict.update({
  2666. '_type': 'url_transparent',
  2667. 'ie_key': RtmpIE.ie_key(),
  2668. 'url': video_url,
  2669. })
  2670. entries.append(entry_info_dict)
  2671. continue
  2672. ext = determine_ext(video_url)
  2673. if ext == 'smil':
  2674. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  2675. elif ext == 'xspf':
  2676. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  2677. elif ext == 'm3u8':
  2678. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  2679. elif ext == 'mpd':
  2680. entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
  2681. elif ext == 'f4m':
  2682. entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
  2683. elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
  2684. # Just matching .ism/manifest is not enough to be reliably sure
  2685. # whether it's actually an ISM manifest or some other streaming
  2686. # manifest since there are various streaming URL formats
  2687. # possible (see [1]) as well as some other shenanigans like
  2688. # .smil/manifest URLs that actually serve an ISM (see [2]) and
  2689. # so on.
  2690. # Thus the most reasonable way to solve this is to delegate
  2691. # to generic extractor in order to look into the contents of
  2692. # the manifest itself.
  2693. # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
  2694. # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
  2695. entry_info_dict = self.url_result(
  2696. smuggle_url(video_url, {'to_generic': True}),
  2697. GenericIE.ie_key())
  2698. else:
  2699. entry_info_dict['url'] = video_url
  2700. if entry_info_dict.get('formats'):
  2701. self._sort_formats(entry_info_dict['formats'])
  2702. entries.append(entry_info_dict)
  2703. if len(entries) == 1:
  2704. return entries[0]
  2705. else:
  2706. for num, e in enumerate(entries, start=1):
  2707. # 'url' results don't have a title
  2708. if e.get('title') is not None:
  2709. e['title'] = '%s (%d)' % (e['title'], num)
  2710. return {
  2711. '_type': 'playlist',
  2712. 'entries': entries,
  2713. }