generic.py 141 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874287528762877287828792880288128822883288428852886288728882889289028912892289328942895289628972898289929002901290229032904290529062907290829092910291129122913291429152916291729182919292029212922292329242925292629272928292929302931293229332934293529362937293829392940294129422943294429452946294729482949295029512952295329542955295629572958295929602961296229632964296529662967296829692970297129722973297429752976297729782979298029812982298329842985298629872988298929902991299229932994299529962997299829993000300130023003300430053006300730083009301030113012301330143015301630173018301930203021302230233024302530263027302830293030303130323033303430353036303730383039304030413042304330443045304630473048304930503051305230533054305530563057305830593060306130623063306430653066306730683069307030713072307330743075307630773078307930803081308230833084308530863087308830893090309130923093309430953096309730983099310031013102310331043105310631073108310931103111311231133114311531163117311831193120312131223123312431253126312731283129313031313132313331343135313631373138313931403141314231433144314531463147314831493150315131523153315431553156315731583159316031613162316331643165316631673168316931703171317231733174317531763177317831793180318131823183318431853186318731883189319031913192319331943195319631973198319932003201320232033204320532063207320832093210321132123213321432153216321732183219322032213222322332243225322632273228322932303231323232333234323532363237323832393240324132423243324432453246324732483249325032513252325332543255325632573258325932603261326232633264326532663267326832693270327132723273327432753276327732783279328032813282328332843285328632873288328932903291329232933294329532963297329832993300330133023303330433053306330733083309331033113312331333143315331633173318331933203321332233233324332533263327332833293330333133323333333433353336333733383339334033413342334333443345334633473348334933503351335233533354335533563357335833593360336133623363336433653366336733683369337033713372337333743375337633773378337933803381338233833384338533863387338833893390339133923393339433953396339733983399340034013402340334043405340634073408340934103411341234133414341534163417341834193420342134223423342434253426342734283429343034313432343334343435343634373438343934403441344234433444344534463447344834493450345134523453345434553456345734583459346034613462346334643465346634673468346934703471347234733474347534763477347834793480348134823483348434853486348734883489349034913492349334943495
  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_str,
  11. compat_urllib_parse_unquote,
  12. compat_urlparse,
  13. compat_xml_parse_error,
  14. )
  15. from ..utils import (
  16. determine_ext,
  17. ExtractorError,
  18. float_or_none,
  19. HEADRequest,
  20. int_or_none,
  21. is_html,
  22. js_to_json,
  23. KNOWN_EXTENSIONS,
  24. merge_dicts,
  25. mimetype2ext,
  26. orderedSet,
  27. parse_duration,
  28. sanitized_Request,
  29. smuggle_url,
  30. unescapeHTML,
  31. unified_timestamp,
  32. unsmuggle_url,
  33. UnsupportedError,
  34. url_or_none,
  35. xpath_text,
  36. xpath_with_ns,
  37. )
  38. from .commonprotocols import RtmpIE
  39. from .brightcove import (
  40. BrightcoveLegacyIE,
  41. BrightcoveNewIE,
  42. )
  43. from .nexx import (
  44. NexxIE,
  45. NexxEmbedIE,
  46. )
  47. from .nbc import NBCSportsVPlayerIE
  48. from .ooyala import OoyalaIE
  49. from .rutv import RUTVIE
  50. from .tvc import TVCIE
  51. from .sportbox import SportBoxIE
  52. from .myvi import MyviIE
  53. from .condenast import CondeNastIE
  54. from .udn import UDNEmbedIE
  55. from .senateisvp import SenateISVPIE
  56. from .svt import SVTIE
  57. from .pornhub import PornHubIE
  58. from .xhamster import XHamsterEmbedIE
  59. from .tnaflix import TNAFlixNetworkEmbedIE
  60. from .drtuber import DrTuberIE
  61. from .redtube import RedTubeIE
  62. from .tube8 import Tube8IE
  63. from .mofosex import MofosexEmbedIE
  64. from .spankwire import SpankwireIE
  65. from .youporn import YouPornIE
  66. from .vimeo import VimeoIE
  67. from .dailymotion import DailymotionIE
  68. from .dailymail import DailyMailIE
  69. from .onionstudios import OnionStudiosIE
  70. from .viewlift import ViewLiftEmbedIE
  71. from .mtv import MTVServicesEmbeddedIE
  72. from .pladform import PladformIE
  73. from .videomore import VideomoreIE
  74. from .webcaster import WebcasterFeedIE
  75. from .googledrive import GoogleDriveIE
  76. from .jwplatform import JWPlatformIE
  77. from .digiteka import DigitekaIE
  78. from .arkena import ArkenaIE
  79. from .instagram import InstagramIE
  80. from .liveleak import LiveLeakIE
  81. from .threeqsdn import ThreeQSDNIE
  82. from .theplatform import ThePlatformIE
  83. from .kaltura import KalturaIE
  84. from .eagleplatform import EaglePlatformIE
  85. from .facebook import FacebookIE
  86. from .soundcloud import SoundcloudEmbedIE
  87. from .tunein import TuneInBaseIE
  88. from .vbox7 import Vbox7IE
  89. from .dbtv import DBTVIE
  90. from .piksel import PikselIE
  91. from .videa import VideaIE
  92. from .twentymin import TwentyMinutenIE
  93. from .ustream import UstreamIE
  94. from .arte import ArteTVEmbedIE
  95. from .videopress import VideoPressIE
  96. from .rutube import RutubeIE
  97. from .limelight import LimelightBaseIE
  98. from .anvato import AnvatoIE
  99. from .washingtonpost import WashingtonPostIE
  100. from .wistia import WistiaIE
  101. from .mediaset import MediasetIE
  102. from .joj import JojIE
  103. from .megaphone import MegaphoneIE
  104. from .vzaar import VzaarIE
  105. from .channel9 import Channel9IE
  106. from .vshare import VShareIE
  107. from .mediasite import MediasiteIE
  108. from .springboardplatform import SpringboardPlatformIE
  109. from .yapfiles import YapFilesIE
  110. from .vice import ViceIE
  111. from .xfileshare import XFileShareIE
  112. from .cloudflarestream import CloudflareStreamIE
  113. from .peertube import PeerTubeIE
  114. from .teachable import TeachableIE
  115. from .indavideo import IndavideoEmbedIE
  116. from .apa import APAIE
  117. from .foxnews import FoxNewsIE
  118. from .viqeo import ViqeoIE
  119. from .expressen import ExpressenIE
  120. from .zype import ZypeIE
  121. from .odnoklassniki import OdnoklassnikiIE
  122. from .kinja import KinjaEmbedIE
  123. class GenericIE(InfoExtractor):
  124. IE_DESC = 'Generic downloader that works on some sites'
  125. _VALID_URL = r'.*'
  126. IE_NAME = 'generic'
  127. _TESTS = [
  128. # Direct link to a video
  129. {
  130. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  131. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  132. 'info_dict': {
  133. 'id': 'trailer',
  134. 'ext': 'mp4',
  135. 'title': 'trailer',
  136. 'upload_date': '20100513',
  137. }
  138. },
  139. # Direct link to media delivered compressed (until Accept-Encoding is *)
  140. {
  141. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  142. 'md5': '128c42e68b13950268b648275386fc74',
  143. 'info_dict': {
  144. 'id': 'FictionJunction-Parallel_Hearts',
  145. 'ext': 'flac',
  146. 'title': 'FictionJunction-Parallel_Hearts',
  147. 'upload_date': '20140522',
  148. },
  149. 'expected_warnings': [
  150. 'URL could be a direct video link, returning it as such.'
  151. ],
  152. 'skip': 'URL invalid',
  153. },
  154. # Direct download with broken HEAD
  155. {
  156. 'url': 'http://ai-radio.org:8000/radio.opus',
  157. 'info_dict': {
  158. 'id': 'radio',
  159. 'ext': 'opus',
  160. 'title': 'radio',
  161. },
  162. 'params': {
  163. 'skip_download': True, # infinite live stream
  164. },
  165. 'expected_warnings': [
  166. r'501.*Not Implemented',
  167. r'400.*Bad Request',
  168. ],
  169. },
  170. # Direct link with incorrect MIME type
  171. {
  172. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  173. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  174. 'info_dict': {
  175. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  176. 'id': '5_Lennart_Poettering_-_Systemd',
  177. 'ext': 'webm',
  178. 'title': '5_Lennart_Poettering_-_Systemd',
  179. 'upload_date': '20141120',
  180. },
  181. 'expected_warnings': [
  182. 'URL could be a direct video link, returning it as such.'
  183. ]
  184. },
  185. # RSS feed
  186. {
  187. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  188. 'info_dict': {
  189. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  190. 'title': 'Zero Punctuation',
  191. 'description': 're:.*groundbreaking video review series.*'
  192. },
  193. 'playlist_mincount': 11,
  194. },
  195. # RSS feed with enclosure
  196. {
  197. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  198. 'info_dict': {
  199. 'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  200. 'title': 'MSNBC Rachel Maddow (video)',
  201. 'description': 're:.*her unique approach to storytelling.*',
  202. },
  203. 'playlist': [{
  204. 'info_dict': {
  205. 'ext': 'mov',
  206. 'id': 'pdv_maddow_netcast_mov-12-04-2020-224335',
  207. 'title': 're:MSNBC Rachel Maddow',
  208. 'description': 're:.*her unique approach to storytelling.*',
  209. 'timestamp': int,
  210. 'upload_date': compat_str,
  211. 'duration': float,
  212. },
  213. }],
  214. },
  215. # RSS feed with enclosures and unsupported link URLs
  216. {
  217. 'url': 'http://www.hellointernet.fm/podcast?format=rss',
  218. 'info_dict': {
  219. 'id': 'http://www.hellointernet.fm/podcast?format=rss',
  220. 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
  221. 'title': 'Hello Internet',
  222. },
  223. 'playlist_mincount': 100,
  224. },
  225. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  226. {
  227. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  228. 'info_dict': {
  229. 'id': 'smil',
  230. 'ext': 'mp4',
  231. 'title': 'Automatics, robotics and biocybernetics',
  232. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  233. 'upload_date': '20130627',
  234. 'formats': 'mincount:16',
  235. 'subtitles': 'mincount:1',
  236. },
  237. 'params': {
  238. 'force_generic_extractor': True,
  239. 'skip_download': True,
  240. },
  241. },
  242. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  243. {
  244. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  245. 'info_dict': {
  246. 'id': 'hds',
  247. 'ext': 'flv',
  248. 'title': 'hds',
  249. 'formats': 'mincount:1',
  250. },
  251. 'params': {
  252. 'skip_download': True,
  253. },
  254. },
  255. # SMIL from https://www.restudy.dk/video/play/id/1637
  256. {
  257. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  258. 'info_dict': {
  259. 'id': 'video_1637',
  260. 'ext': 'flv',
  261. 'title': 'video_1637',
  262. 'formats': 'mincount:3',
  263. },
  264. 'params': {
  265. 'skip_download': True,
  266. },
  267. },
  268. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  269. {
  270. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  271. 'info_dict': {
  272. 'id': 'smil-service',
  273. 'ext': 'flv',
  274. 'title': 'smil-service',
  275. 'formats': 'mincount:1',
  276. },
  277. 'params': {
  278. 'skip_download': True,
  279. },
  280. },
  281. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  282. {
  283. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  284. 'info_dict': {
  285. 'id': '4719370',
  286. 'ext': 'mp4',
  287. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  288. 'formats': 'mincount:3',
  289. },
  290. 'params': {
  291. 'skip_download': True,
  292. },
  293. },
  294. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  295. {
  296. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  297. 'info_dict': {
  298. 'id': 'mZlp2ctYIUEB',
  299. 'ext': 'mp4',
  300. 'title': 'Tikibad ontruimd wegens brand',
  301. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  302. 'thumbnail': r're:^https?://.*\.jpg$',
  303. 'duration': 33,
  304. },
  305. 'params': {
  306. 'skip_download': True,
  307. },
  308. },
  309. # MPD from http://dash-mse-test.appspot.com/media.html
  310. {
  311. 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
  312. 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
  313. 'info_dict': {
  314. 'id': 'car-20120827-manifest',
  315. 'ext': 'mp4',
  316. 'title': 'car-20120827-manifest',
  317. 'formats': 'mincount:9',
  318. 'upload_date': '20130904',
  319. },
  320. 'params': {
  321. 'format': 'bestvideo',
  322. },
  323. },
  324. # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
  325. {
  326. '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',
  327. 'info_dict': {
  328. 'id': 'content',
  329. 'ext': 'mp4',
  330. 'title': 'content',
  331. 'formats': 'mincount:8',
  332. },
  333. 'params': {
  334. # m3u8 downloads
  335. 'skip_download': True,
  336. },
  337. 'skip': 'video gone',
  338. },
  339. # m3u8 served with Content-Type: text/plain
  340. {
  341. 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
  342. 'info_dict': {
  343. 'id': 'index',
  344. 'ext': 'mp4',
  345. 'title': 'index',
  346. 'upload_date': '20140720',
  347. 'formats': 'mincount:11',
  348. },
  349. 'params': {
  350. # m3u8 downloads
  351. 'skip_download': True,
  352. },
  353. 'skip': 'video gone',
  354. },
  355. # google redirect
  356. {
  357. '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',
  358. 'info_dict': {
  359. 'id': 'cmQHVoWB5FY',
  360. 'ext': 'mp4',
  361. 'upload_date': '20130224',
  362. 'uploader_id': 'TheVerge',
  363. 'description': r're:^Chris Ziegler takes a look at the\.*',
  364. 'uploader': 'The Verge',
  365. 'title': 'First Firefox OS phones side-by-side',
  366. },
  367. 'params': {
  368. 'skip_download': False,
  369. }
  370. },
  371. {
  372. # redirect in Refresh HTTP header
  373. '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',
  374. 'info_dict': {
  375. 'id': 'pO8h3EaFRdo',
  376. 'ext': 'mp4',
  377. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  378. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  379. 'upload_date': '20150917',
  380. 'uploader_id': 'brtvofficial',
  381. 'uploader': 'Boiler Room',
  382. },
  383. 'params': {
  384. 'skip_download': False,
  385. },
  386. },
  387. {
  388. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  389. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  390. 'info_dict': {
  391. 'id': '13601338388002',
  392. 'ext': 'mp4',
  393. 'uploader': 'www.hodiho.fr',
  394. 'title': 'R\u00e9gis plante sa Jeep',
  395. }
  396. },
  397. # bandcamp page with custom domain
  398. {
  399. 'add_ie': ['Bandcamp'],
  400. 'url': 'http://bronyrock.com/track/the-pony-mash',
  401. 'info_dict': {
  402. 'id': '3235767654',
  403. 'ext': 'mp3',
  404. 'title': 'The Pony Mash',
  405. 'uploader': 'M_Pallante',
  406. },
  407. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  408. },
  409. {
  410. # embedded brightcove video
  411. # it also tests brightcove videos that need to set the 'Referer'
  412. # in the http requests
  413. 'add_ie': ['BrightcoveLegacy'],
  414. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  415. 'info_dict': {
  416. 'id': '2765128793001',
  417. 'ext': 'mp4',
  418. 'title': 'Le cours de bourse : l’analyse technique',
  419. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  420. 'uploader': 'BFM BUSINESS',
  421. },
  422. 'params': {
  423. 'skip_download': True,
  424. },
  425. },
  426. {
  427. # embedded with itemprop embedURL and video id spelled as `idVideo`
  428. 'add_id': ['BrightcoveLegacy'],
  429. 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
  430. 'info_dict': {
  431. 'id': '5255628253001',
  432. 'ext': 'mp4',
  433. 'title': 'md5:37c519b1128915607601e75a87995fc0',
  434. 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
  435. 'uploader': 'BFM BUSINESS',
  436. 'uploader_id': '876450612001',
  437. 'timestamp': 1482255315,
  438. 'upload_date': '20161220',
  439. },
  440. 'params': {
  441. 'skip_download': True,
  442. },
  443. },
  444. {
  445. # https://github.com/ytdl-org/youtube-dl/issues/2253
  446. 'url': 'http://bcove.me/i6nfkrc3',
  447. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  448. 'info_dict': {
  449. 'id': '3101154703001',
  450. 'ext': 'mp4',
  451. 'title': 'Still no power',
  452. 'uploader': 'thestar.com',
  453. '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.',
  454. },
  455. 'add_ie': ['BrightcoveLegacy'],
  456. 'skip': 'video gone',
  457. },
  458. {
  459. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  460. 'md5': 'fb973ecf6e4a78a67453647444222983',
  461. 'info_dict': {
  462. 'id': '3414141473001',
  463. 'ext': 'mp4',
  464. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  465. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  466. 'uploader': 'Championat',
  467. },
  468. },
  469. {
  470. # https://github.com/ytdl-org/youtube-dl/issues/3541
  471. 'add_ie': ['BrightcoveLegacy'],
  472. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  473. 'info_dict': {
  474. 'id': '3866516442001',
  475. 'ext': 'mp4',
  476. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  477. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  478. 'uploader': 'SBS Broadcasting',
  479. },
  480. 'skip': 'Restricted to Netherlands',
  481. 'params': {
  482. 'skip_download': True, # m3u8 download
  483. },
  484. },
  485. {
  486. # Brightcove video in <iframe>
  487. 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
  488. 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
  489. 'info_dict': {
  490. 'id': '5360463607001',
  491. 'ext': 'mp4',
  492. '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',
  493. '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。',
  494. 'uploader': 'United Nations',
  495. 'uploader_id': '1362235914001',
  496. 'timestamp': 1489593889,
  497. 'upload_date': '20170315',
  498. },
  499. 'add_ie': ['BrightcoveLegacy'],
  500. },
  501. {
  502. # Brightcove with alternative playerID key
  503. 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
  504. 'info_dict': {
  505. 'id': 'nmeth.2062_SV1',
  506. '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',
  507. },
  508. 'playlist': [{
  509. 'info_dict': {
  510. 'id': '2228375078001',
  511. 'ext': 'mp4',
  512. 'title': 'nmeth.2062-sv1',
  513. 'description': 'nmeth.2062-sv1',
  514. 'timestamp': 1363357591,
  515. 'upload_date': '20130315',
  516. 'uploader': 'Nature Publishing Group',
  517. 'uploader_id': '1964492299001',
  518. },
  519. }],
  520. },
  521. {
  522. # Brightcove with UUID in videoPlayer
  523. 'url': 'http://www8.hp.com/cn/zh/home.html',
  524. 'info_dict': {
  525. 'id': '5255815316001',
  526. 'ext': 'mp4',
  527. 'title': 'Sprocket Video - China',
  528. 'description': 'Sprocket Video - China',
  529. 'uploader': 'HP-Video Gallery',
  530. 'timestamp': 1482263210,
  531. 'upload_date': '20161220',
  532. 'uploader_id': '1107601872001',
  533. },
  534. 'params': {
  535. 'skip_download': True, # m3u8 download
  536. },
  537. 'skip': 'video rotates...weekly?',
  538. },
  539. {
  540. # Brightcove:new type [2].
  541. 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
  542. 'md5': '2b35148fcf48da41c9fb4591650784f3',
  543. 'info_dict': {
  544. 'id': '5348741021001',
  545. 'ext': 'mp4',
  546. 'upload_date': '20170306',
  547. 'uploader_id': '4191638492001',
  548. 'timestamp': 1488769918,
  549. 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
  550. },
  551. },
  552. {
  553. # Alternative brightcove <video> attributes
  554. '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/',
  555. 'info_dict': {
  556. 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
  557. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
  558. },
  559. 'playlist': [{
  560. 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
  561. 'info_dict': {
  562. 'id': '5311302538001',
  563. 'ext': 'mp4',
  564. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
  565. 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
  566. 'timestamp': 1486321708,
  567. 'upload_date': '20170205',
  568. 'uploader_id': '800000640001',
  569. },
  570. 'only_matching': True,
  571. }],
  572. },
  573. {
  574. # Brightcove with UUID in videoPlayer
  575. 'url': 'http://www8.hp.com/cn/zh/home.html',
  576. 'info_dict': {
  577. 'id': '5255815316001',
  578. 'ext': 'mp4',
  579. 'title': 'Sprocket Video - China',
  580. 'description': 'Sprocket Video - China',
  581. 'uploader': 'HP-Video Gallery',
  582. 'timestamp': 1482263210,
  583. 'upload_date': '20161220',
  584. 'uploader_id': '1107601872001',
  585. },
  586. 'params': {
  587. 'skip_download': True, # m3u8 download
  588. },
  589. },
  590. # ooyala video
  591. {
  592. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  593. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  594. 'info_dict': {
  595. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  596. 'ext': 'mp4',
  597. 'title': '2cc213299525360.mov', # that's what we get
  598. 'duration': 238.231,
  599. },
  600. 'add_ie': ['Ooyala'],
  601. },
  602. {
  603. # ooyala video embedded with http://player.ooyala.com/iframe.js
  604. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  605. 'info_dict': {
  606. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  607. 'ext': 'mp4',
  608. 'title': '"Steve Jobs: Man in the Machine" trailer',
  609. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  610. 'duration': 135.427,
  611. },
  612. 'params': {
  613. 'skip_download': True,
  614. },
  615. 'skip': 'movie expired',
  616. },
  617. # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
  618. {
  619. 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
  620. 'info_dict': {
  621. 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
  622. 'ext': 'mp4',
  623. 'title': 'Steampunk Fest Comes to Honesdale',
  624. 'duration': 43.276,
  625. },
  626. 'params': {
  627. 'skip_download': True,
  628. }
  629. },
  630. # embed.ly video
  631. {
  632. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  633. 'info_dict': {
  634. 'id': '9ODmcdjQcHQ',
  635. 'ext': 'mp4',
  636. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  637. 'upload_date': '20140225',
  638. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  639. 'uploader': 'Tested',
  640. 'uploader_id': 'testedcom',
  641. },
  642. # No need to test YoutubeIE here
  643. 'params': {
  644. 'skip_download': True,
  645. },
  646. },
  647. # funnyordie embed
  648. {
  649. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  650. 'info_dict': {
  651. 'id': '18e820ec3f',
  652. 'ext': 'mp4',
  653. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  654. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  655. },
  656. # HEAD requests lead to endless 301, while GET is OK
  657. 'expected_warnings': ['301'],
  658. },
  659. # RUTV embed
  660. {
  661. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  662. 'info_dict': {
  663. 'id': '776940',
  664. 'ext': 'mp4',
  665. 'title': 'Охотское море стало целиком российским',
  666. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  667. },
  668. 'params': {
  669. # m3u8 download
  670. 'skip_download': True,
  671. },
  672. },
  673. # TVC embed
  674. {
  675. '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/',
  676. 'info_dict': {
  677. 'id': '55304',
  678. 'ext': 'mp4',
  679. 'title': 'Дошкольное воспитание',
  680. },
  681. },
  682. # SportBox embed
  683. {
  684. 'url': 'http://www.vestifinance.ru/articles/25753',
  685. 'info_dict': {
  686. 'id': '25753',
  687. 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  688. },
  689. 'playlist': [{
  690. 'info_dict': {
  691. 'id': '370908',
  692. 'title': 'Госзаказ. День 3',
  693. 'ext': 'mp4',
  694. }
  695. }, {
  696. 'info_dict': {
  697. 'id': '370905',
  698. 'title': 'Госзаказ. День 2',
  699. 'ext': 'mp4',
  700. }
  701. }, {
  702. 'info_dict': {
  703. 'id': '370902',
  704. 'title': 'Госзаказ. День 1',
  705. 'ext': 'mp4',
  706. }
  707. }],
  708. 'params': {
  709. # m3u8 download
  710. 'skip_download': True,
  711. },
  712. },
  713. # Myvi.ru embed
  714. {
  715. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  716. 'info_dict': {
  717. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  718. 'ext': 'mp4',
  719. 'title': 'Ужастики, русский трейлер (2015)',
  720. 'thumbnail': r're:^https?://.*\.jpg$',
  721. 'duration': 153,
  722. }
  723. },
  724. # XHamster embed
  725. {
  726. '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',
  727. 'info_dict': {
  728. 'id': 'showthread',
  729. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  730. },
  731. 'playlist_mincount': 7,
  732. # This forum does not allow <iframe> syntaxes anymore
  733. # Now HTML tags are displayed as-is
  734. 'skip': 'No videos on this page',
  735. },
  736. # Embedded TED video
  737. {
  738. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  739. 'md5': '65fdff94098e4a607385a60c5177c638',
  740. 'info_dict': {
  741. 'id': '1969',
  742. 'ext': 'mp4',
  743. 'title': 'Hidden miracles of the natural world',
  744. 'uploader': 'Louie Schwartzberg',
  745. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  746. }
  747. },
  748. # nowvideo embed hidden behind percent encoding
  749. {
  750. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  751. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  752. 'info_dict': {
  753. 'id': '06e53103ca9aa',
  754. 'ext': 'flv',
  755. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  756. 'description': 'No description',
  757. },
  758. },
  759. # arte embed
  760. {
  761. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  762. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  763. 'info_dict': {
  764. 'id': '048195-004_PLUS7-F',
  765. 'ext': 'flv',
  766. 'title': 'X:enius',
  767. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  768. 'upload_date': '20140320',
  769. },
  770. 'params': {
  771. 'skip_download': 'Requires rtmpdump'
  772. },
  773. 'skip': 'video gone',
  774. },
  775. # francetv embed
  776. {
  777. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  778. 'info_dict': {
  779. 'id': 'EV_30231',
  780. 'ext': 'mp4',
  781. 'title': 'Alcaline, le concert avec Calogero',
  782. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  783. 'upload_date': '20150226',
  784. 'timestamp': 1424989860,
  785. 'duration': 5400,
  786. },
  787. 'params': {
  788. # m3u8 downloads
  789. 'skip_download': True,
  790. },
  791. 'expected_warnings': [
  792. 'Forbidden'
  793. ]
  794. },
  795. # Condé Nast embed
  796. {
  797. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  798. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  799. 'info_dict': {
  800. 'id': '53501be369702d3275860000',
  801. 'ext': 'mp4',
  802. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  803. }
  804. },
  805. # Dailymotion embed
  806. {
  807. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  808. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  809. 'info_dict': {
  810. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  811. 'ext': 'mp4',
  812. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  813. 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
  814. 'uploader': 'Spi0n',
  815. 'uploader_id': 'xgditw',
  816. 'upload_date': '20140425',
  817. 'timestamp': 1398441542,
  818. },
  819. 'add_ie': ['Dailymotion'],
  820. },
  821. # DailyMail embed
  822. {
  823. 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
  824. 'info_dict': {
  825. 'id': '1495629',
  826. 'ext': 'mp4',
  827. 'title': 'Care worker punches elderly dementia patient in head 11 times',
  828. 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
  829. },
  830. 'add_ie': ['DailyMail'],
  831. 'params': {
  832. 'skip_download': True,
  833. },
  834. },
  835. # YouTube embed
  836. {
  837. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  838. 'info_dict': {
  839. 'id': 'FXRb4ykk4S0',
  840. 'ext': 'mp4',
  841. 'title': 'The NBL Auction 2014',
  842. 'uploader': 'BADMINTON England',
  843. 'uploader_id': 'BADMINTONEvents',
  844. 'upload_date': '20140603',
  845. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  846. },
  847. 'add_ie': ['Youtube'],
  848. 'params': {
  849. 'skip_download': True,
  850. }
  851. },
  852. # MTVServices embed
  853. {
  854. 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
  855. 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
  856. 'info_dict': {
  857. 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
  858. 'ext': 'mp4',
  859. 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
  860. 'description': 'Two valets share their love for movie star Liam Neesons.',
  861. 'timestamp': 1349922600,
  862. 'upload_date': '20121011',
  863. },
  864. },
  865. # YouTube embed via <data-embed-url="">
  866. {
  867. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  868. 'info_dict': {
  869. 'id': '4vAffPZIT44',
  870. 'ext': 'mp4',
  871. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  872. 'uploader': 'Gameloft',
  873. 'uploader_id': 'gameloft',
  874. 'upload_date': '20140828',
  875. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  876. },
  877. 'params': {
  878. 'skip_download': True,
  879. }
  880. },
  881. # YouTube <object> embed
  882. {
  883. 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
  884. 'md5': '516718101ec834f74318df76259fb3cc',
  885. 'info_dict': {
  886. 'id': 'msN87y-iEx0',
  887. 'ext': 'webm',
  888. 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
  889. 'upload_date': '20080526',
  890. 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
  891. 'uploader': 'Christopher Sykes',
  892. 'uploader_id': 'ChristopherJSykes',
  893. },
  894. 'add_ie': ['Youtube'],
  895. },
  896. # Camtasia studio
  897. {
  898. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  899. 'playlist': [{
  900. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  901. 'info_dict': {
  902. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  903. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  904. 'ext': 'flv',
  905. 'duration': 2235.90,
  906. }
  907. }, {
  908. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  909. 'info_dict': {
  910. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  911. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  912. 'ext': 'flv',
  913. 'duration': 2235.93,
  914. }
  915. }],
  916. 'info_dict': {
  917. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  918. }
  919. },
  920. # Flowplayer
  921. {
  922. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  923. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  924. 'info_dict': {
  925. 'id': '5123ea6d5e5a7',
  926. 'ext': 'mp4',
  927. 'age_limit': 18,
  928. 'uploader': 'www.handjobhub.com',
  929. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  930. }
  931. },
  932. # Multiple brightcove videos
  933. # https://github.com/ytdl-org/youtube-dl/issues/2283
  934. {
  935. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  936. 'info_dict': {
  937. 'id': 'always-never',
  938. 'title': 'Always / Never - The New Yorker',
  939. },
  940. 'playlist_count': 3,
  941. 'params': {
  942. 'extract_flat': False,
  943. 'skip_download': True,
  944. }
  945. },
  946. # MLB embed
  947. {
  948. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  949. 'md5': '96f09a37e44da40dd083e12d9a683327',
  950. 'info_dict': {
  951. 'id': '33322633',
  952. 'ext': 'mp4',
  953. 'title': 'Ump changes call to ball',
  954. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  955. 'duration': 48,
  956. 'timestamp': 1401537900,
  957. 'upload_date': '20140531',
  958. 'thumbnail': r're:^https?://.*\.jpg$',
  959. },
  960. },
  961. # Wistia embed
  962. {
  963. 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  964. 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
  965. 'info_dict': {
  966. 'id': '6e2wtrbdaf',
  967. 'ext': 'mov',
  968. 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
  969. 'description': 'a Paywall Videos video from Remilon',
  970. 'duration': 644.072,
  971. 'uploader': 'study.com',
  972. 'timestamp': 1459678540,
  973. 'upload_date': '20160403',
  974. 'filesize': 24687186,
  975. },
  976. },
  977. {
  978. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  979. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  980. 'info_dict': {
  981. 'id': 'uxjb0lwrcz',
  982. 'ext': 'mp4',
  983. 'title': 'Conversation about Hexagonal Rails Part 1',
  984. 'description': 'a Martin Fowler video from ThoughtWorks',
  985. 'duration': 1715.0,
  986. 'uploader': 'thoughtworks.wistia.com',
  987. 'timestamp': 1401832161,
  988. 'upload_date': '20140603',
  989. },
  990. },
  991. # Wistia standard embed (async)
  992. {
  993. 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
  994. 'info_dict': {
  995. 'id': '807fafadvk',
  996. 'ext': 'mp4',
  997. 'title': 'Drip Brennan Dunn Workshop',
  998. 'description': 'a JV Webinars video from getdrip-1',
  999. 'duration': 4986.95,
  1000. 'timestamp': 1463607249,
  1001. 'upload_date': '20160518',
  1002. },
  1003. 'params': {
  1004. 'skip_download': True,
  1005. }
  1006. },
  1007. # Soundcloud embed
  1008. {
  1009. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  1010. 'info_dict': {
  1011. 'id': '174391317',
  1012. 'ext': 'mp3',
  1013. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  1014. 'uploader': 'Sophos Security',
  1015. 'title': 'Chet Chat 171 - Oct 29, 2014',
  1016. 'upload_date': '20141029',
  1017. }
  1018. },
  1019. # Soundcloud multiple embeds
  1020. {
  1021. 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
  1022. 'info_dict': {
  1023. 'id': '52809',
  1024. 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
  1025. },
  1026. 'playlist_mincount': 7,
  1027. },
  1028. # TuneIn station embed
  1029. {
  1030. 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
  1031. 'info_dict': {
  1032. 'id': '204146',
  1033. 'ext': 'mp3',
  1034. 'title': 'CNRV',
  1035. 'location': 'Paris, France',
  1036. 'is_live': True,
  1037. },
  1038. 'params': {
  1039. # Live stream
  1040. 'skip_download': True,
  1041. },
  1042. },
  1043. # Livestream embed
  1044. {
  1045. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  1046. 'info_dict': {
  1047. 'id': '67864563',
  1048. 'ext': 'flv',
  1049. 'upload_date': '20141112',
  1050. 'title': 'Rosetta #CometLanding webcast HL 10',
  1051. }
  1052. },
  1053. # Another Livestream embed, without 'new.' in URL
  1054. {
  1055. 'url': 'https://www.freespeech.org/',
  1056. 'info_dict': {
  1057. 'id': '123537347',
  1058. 'ext': 'mp4',
  1059. 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  1060. },
  1061. 'params': {
  1062. # Live stream
  1063. 'skip_download': True,
  1064. },
  1065. },
  1066. # LazyYT
  1067. {
  1068. 'url': 'https://skiplagged.com/',
  1069. 'info_dict': {
  1070. 'id': 'skiplagged',
  1071. 'title': 'Skiplagged: The smart way to find cheap flights',
  1072. },
  1073. 'playlist_mincount': 1,
  1074. 'add_ie': ['Youtube'],
  1075. },
  1076. # Cinchcast embed
  1077. {
  1078. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  1079. 'info_dict': {
  1080. 'id': '7141703',
  1081. 'ext': 'mp3',
  1082. 'upload_date': '20141126',
  1083. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  1084. }
  1085. },
  1086. # Cinerama player
  1087. {
  1088. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  1089. 'info_dict': {
  1090. 'id': '730m_DandD_1901_512k',
  1091. 'ext': 'mp4',
  1092. 'uploader': 'www.abc.net.au',
  1093. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  1094. }
  1095. },
  1096. # embedded viddler video
  1097. {
  1098. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  1099. 'info_dict': {
  1100. 'id': '4d03aad9',
  1101. 'ext': 'mp4',
  1102. 'uploader': 'deadspin',
  1103. 'title': 'WALL-TO-GORTAT',
  1104. 'timestamp': 1422285291,
  1105. 'upload_date': '20150126',
  1106. },
  1107. 'add_ie': ['Viddler'],
  1108. },
  1109. # Libsyn embed
  1110. {
  1111. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  1112. 'info_dict': {
  1113. 'id': '3377616',
  1114. 'ext': 'mp3',
  1115. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  1116. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  1117. 'upload_date': '20150220',
  1118. },
  1119. 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
  1120. },
  1121. # jwplayer YouTube
  1122. {
  1123. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  1124. 'info_dict': {
  1125. 'id': 'Mrj4DVp2zeA',
  1126. 'ext': 'mp4',
  1127. 'upload_date': '20150212',
  1128. 'uploader': 'The National Archives UK',
  1129. 'description': 'md5:8078af856dca76edc42910b61273dbbf',
  1130. 'uploader_id': 'NationalArchives08',
  1131. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  1132. },
  1133. },
  1134. # jwplayer rtmp
  1135. {
  1136. 'url': 'http://www.suffolk.edu/sjc/live.php',
  1137. 'info_dict': {
  1138. 'id': 'live',
  1139. 'ext': 'flv',
  1140. 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
  1141. 'uploader': 'www.suffolk.edu',
  1142. },
  1143. 'params': {
  1144. 'skip_download': True,
  1145. },
  1146. 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
  1147. },
  1148. # Complex jwplayer
  1149. {
  1150. 'url': 'http://www.indiedb.com/games/king-machine/videos',
  1151. 'info_dict': {
  1152. 'id': 'videos',
  1153. 'ext': 'mp4',
  1154. 'title': 'king machine trailer 1',
  1155. 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
  1156. 'thumbnail': r're:^https?://.*\.jpg$',
  1157. },
  1158. },
  1159. {
  1160. # JWPlayer config passed as variable
  1161. 'url': 'http://www.txxx.com/videos/3326530/ariele/',
  1162. 'info_dict': {
  1163. 'id': '3326530_hq',
  1164. 'ext': 'mp4',
  1165. 'title': 'ARIELE | Tube Cup',
  1166. 'uploader': 'www.txxx.com',
  1167. 'age_limit': 18,
  1168. },
  1169. 'params': {
  1170. 'skip_download': True,
  1171. }
  1172. },
  1173. {
  1174. # JWPlatform iframe
  1175. 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
  1176. 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
  1177. 'info_dict': {
  1178. 'id': 'O0c5JcKT',
  1179. 'ext': 'mp4',
  1180. 'upload_date': '20171122',
  1181. 'timestamp': 1511366290,
  1182. 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
  1183. },
  1184. 'add_ie': [JWPlatformIE.ie_key()],
  1185. },
  1186. {
  1187. # Video.js embed, multiple formats
  1188. 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
  1189. 'info_dict': {
  1190. 'id': 'yygqldloqIk',
  1191. 'ext': 'mp4',
  1192. 'title': 'SolidWorks. Урок 6 Настройка чертежа',
  1193. 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
  1194. 'upload_date': '20130314',
  1195. 'uploader': 'PROстое3D',
  1196. 'uploader_id': 'PROstoe3D',
  1197. },
  1198. 'params': {
  1199. 'skip_download': True,
  1200. },
  1201. },
  1202. {
  1203. # Video.js embed, single format
  1204. 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
  1205. 'info_dict': {
  1206. 'id': 'watch',
  1207. 'ext': 'mp4',
  1208. 'title': 'Step 1 - Good Foundation',
  1209. 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
  1210. },
  1211. 'params': {
  1212. 'skip_download': True,
  1213. },
  1214. },
  1215. # rtl.nl embed
  1216. {
  1217. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  1218. 'playlist_mincount': 5,
  1219. 'info_dict': {
  1220. 'id': 'aanslagen-kopenhagen',
  1221. 'title': 'Aanslagen Kopenhagen',
  1222. }
  1223. },
  1224. # Zapiks embed
  1225. {
  1226. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  1227. 'info_dict': {
  1228. 'id': '118046',
  1229. 'ext': 'mp4',
  1230. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  1231. }
  1232. },
  1233. # Kaltura embed (different embed code)
  1234. {
  1235. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  1236. 'info_dict': {
  1237. 'id': '1_a52wc67y',
  1238. 'ext': 'flv',
  1239. 'upload_date': '20150127',
  1240. 'uploader_id': 'PremierMedia',
  1241. 'timestamp': int,
  1242. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  1243. },
  1244. },
  1245. # Kaltura embed with single quotes
  1246. {
  1247. 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
  1248. 'info_dict': {
  1249. 'id': '0_izeg5utt',
  1250. 'ext': 'mp4',
  1251. 'title': '35871',
  1252. 'timestamp': 1355743100,
  1253. 'upload_date': '20121217',
  1254. 'uploader_id': 'cplapp@learn360.com',
  1255. },
  1256. 'add_ie': ['Kaltura'],
  1257. },
  1258. {
  1259. # Kaltura embedded via quoted entry_id
  1260. 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
  1261. 'info_dict': {
  1262. 'id': '0_utuok90b',
  1263. 'ext': 'mp4',
  1264. 'title': '06_matthew_brender_raj_dutt',
  1265. 'timestamp': 1466638791,
  1266. 'upload_date': '20160622',
  1267. },
  1268. 'add_ie': ['Kaltura'],
  1269. 'expected_warnings': [
  1270. 'Could not send HEAD request'
  1271. ],
  1272. 'params': {
  1273. 'skip_download': True,
  1274. }
  1275. },
  1276. {
  1277. # Kaltura embedded, some fileExt broken (#11480)
  1278. 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
  1279. 'info_dict': {
  1280. 'id': '1_sgtvehim',
  1281. 'ext': 'mp4',
  1282. 'title': 'Our "Standard Models" of particle physics and cosmology',
  1283. 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
  1284. 'timestamp': 1321158993,
  1285. 'upload_date': '20111113',
  1286. 'uploader_id': 'kps1',
  1287. },
  1288. 'add_ie': ['Kaltura'],
  1289. },
  1290. {
  1291. # Kaltura iframe embed
  1292. 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
  1293. 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
  1294. 'info_dict': {
  1295. 'id': '0_f2cfbpwy',
  1296. 'ext': 'mp4',
  1297. 'title': 'I. M. Pei: A Centennial Celebration',
  1298. 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
  1299. 'upload_date': '20170403',
  1300. 'uploader_id': 'batchUser',
  1301. 'timestamp': 1491232186,
  1302. },
  1303. 'add_ie': ['Kaltura'],
  1304. },
  1305. {
  1306. # Kaltura iframe embed, more sophisticated
  1307. 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
  1308. 'info_dict': {
  1309. 'id': '1_9gzouybz',
  1310. 'ext': 'mp4',
  1311. 'title': 'lecture-05sep2017',
  1312. 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
  1313. 'upload_date': '20170913',
  1314. 'uploader_id': 'eps2',
  1315. 'timestamp': 1505340777,
  1316. },
  1317. 'params': {
  1318. 'skip_download': True,
  1319. },
  1320. 'add_ie': ['Kaltura'],
  1321. },
  1322. {
  1323. # meta twitter:player
  1324. 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
  1325. 'info_dict': {
  1326. 'id': '0_01b42zps',
  1327. 'ext': 'mp4',
  1328. 'title': 'Main Twerk (Video)',
  1329. 'upload_date': '20171208',
  1330. 'uploader_id': 'sebastian.salinas@thechive.com',
  1331. 'timestamp': 1512713057,
  1332. },
  1333. 'params': {
  1334. 'skip_download': True,
  1335. },
  1336. 'add_ie': ['Kaltura'],
  1337. },
  1338. # referrer protected EaglePlatform embed
  1339. {
  1340. 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
  1341. 'info_dict': {
  1342. 'id': '582306',
  1343. 'ext': 'mp4',
  1344. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1345. 'thumbnail': r're:^https?://.*\.jpg$',
  1346. 'duration': 3382,
  1347. 'view_count': int,
  1348. },
  1349. 'params': {
  1350. 'skip_download': True,
  1351. },
  1352. },
  1353. # ClipYou (EaglePlatform) embed (custom URL)
  1354. {
  1355. 'url': 'http://muz-tv.ru/play/7129/',
  1356. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  1357. 'info_dict': {
  1358. 'id': '12820',
  1359. 'ext': 'mp4',
  1360. 'title': "'O Sole Mio",
  1361. 'thumbnail': r're:^https?://.*\.jpg$',
  1362. 'duration': 216,
  1363. 'view_count': int,
  1364. },
  1365. 'params': {
  1366. 'skip_download': True,
  1367. },
  1368. 'skip': 'This video is unavailable.',
  1369. },
  1370. # Pladform embed
  1371. {
  1372. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  1373. 'info_dict': {
  1374. 'id': '100183293',
  1375. 'ext': 'mp4',
  1376. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  1377. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  1378. 'thumbnail': r're:^https?://.*\.jpg$',
  1379. 'duration': 694,
  1380. 'age_limit': 0,
  1381. },
  1382. 'skip': 'HTTP Error 404: Not Found',
  1383. },
  1384. # Playwire embed
  1385. {
  1386. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  1387. 'info_dict': {
  1388. 'id': '3519514',
  1389. 'ext': 'mp4',
  1390. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  1391. 'thumbnail': r're:^https?://.*\.png$',
  1392. 'duration': 45.115,
  1393. },
  1394. },
  1395. # 5min embed
  1396. {
  1397. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  1398. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  1399. 'info_dict': {
  1400. 'id': '518726732',
  1401. 'ext': 'mp4',
  1402. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  1403. 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
  1404. 'timestamp': 1427237531,
  1405. 'uploader': 'Crunch Report',
  1406. 'upload_date': '20150324',
  1407. },
  1408. 'params': {
  1409. # m3u8 download
  1410. 'skip_download': True,
  1411. },
  1412. },
  1413. # Crooks and Liars embed
  1414. {
  1415. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  1416. 'info_dict': {
  1417. 'id': '8RUoRhRi',
  1418. 'ext': 'mp4',
  1419. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  1420. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  1421. 'timestamp': 1428207000,
  1422. 'upload_date': '20150405',
  1423. 'uploader': 'Heather',
  1424. },
  1425. },
  1426. # Crooks and Liars external embed
  1427. {
  1428. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  1429. 'info_dict': {
  1430. 'id': 'MTE3MjUtMzQ2MzA',
  1431. 'ext': 'mp4',
  1432. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  1433. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  1434. 'timestamp': 1265032391,
  1435. 'upload_date': '20100201',
  1436. 'uploader': 'Heather',
  1437. },
  1438. },
  1439. # NBC Sports vplayer embed
  1440. {
  1441. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  1442. 'info_dict': {
  1443. 'id': 'ln7x1qSThw4k',
  1444. 'ext': 'flv',
  1445. 'title': "PFT Live: New leader in the 'new-look' defense",
  1446. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  1447. 'uploader': 'NBCU-SPORTS',
  1448. 'upload_date': '20140107',
  1449. 'timestamp': 1389118457,
  1450. },
  1451. 'skip': 'Invalid Page URL',
  1452. },
  1453. # NBC News embed
  1454. {
  1455. 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
  1456. 'md5': '1aa589c675898ae6d37a17913cf68d66',
  1457. 'info_dict': {
  1458. 'id': 'x_dtl_oa_LettermanliftPR_160608',
  1459. 'ext': 'mp4',
  1460. 'title': 'David Letterman: A Preview',
  1461. '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.',
  1462. 'upload_date': '20160609',
  1463. 'timestamp': 1465431544,
  1464. 'uploader': 'NBCU-NEWS',
  1465. },
  1466. },
  1467. # UDN embed
  1468. {
  1469. 'url': 'https://video.udn.com/news/300346',
  1470. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  1471. 'info_dict': {
  1472. 'id': '300346',
  1473. 'ext': 'mp4',
  1474. 'title': '中一中男師變性 全校師生力挺',
  1475. 'thumbnail': r're:^https?://.*\.jpg$',
  1476. },
  1477. 'params': {
  1478. # m3u8 download
  1479. 'skip_download': True,
  1480. },
  1481. 'expected_warnings': ['Failed to parse JSON Expecting value'],
  1482. },
  1483. # Brightcove URL in single quotes
  1484. {
  1485. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  1486. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  1487. 'info_dict': {
  1488. 'id': '4255764656001',
  1489. 'ext': 'mp4',
  1490. 'title': 'SN Presents: Russell Martin, World Citizen',
  1491. '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.',
  1492. 'uploader': 'Rogers Sportsnet',
  1493. 'uploader_id': '1704050871',
  1494. 'upload_date': '20150525',
  1495. 'timestamp': 1432570283,
  1496. },
  1497. },
  1498. # Kinja embed
  1499. {
  1500. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1501. 'info_dict': {
  1502. 'id': '106351',
  1503. 'ext': 'mp4',
  1504. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1505. 'description': 'Migrated from OnionStudios',
  1506. 'thumbnail': r're:^https?://.*\.jpe?g$',
  1507. 'uploader': 'clickhole',
  1508. 'upload_date': '20150527',
  1509. 'timestamp': 1432744860,
  1510. }
  1511. },
  1512. # SnagFilms embed
  1513. {
  1514. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1515. 'info_dict': {
  1516. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1517. 'ext': 'mp4',
  1518. 'title': '#whilewewatch',
  1519. }
  1520. },
  1521. # AdobeTVVideo embed
  1522. {
  1523. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1524. 'md5': '43662b577c018ad707a63766462b1e87',
  1525. 'info_dict': {
  1526. 'id': '2456',
  1527. 'ext': 'mp4',
  1528. 'title': 'New experience with Acrobat DC',
  1529. 'description': 'New experience with Acrobat DC',
  1530. 'duration': 248.667,
  1531. },
  1532. },
  1533. # BrightcoveInPageEmbed embed
  1534. {
  1535. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1536. 'info_dict': {
  1537. 'id': '4238694884001',
  1538. 'ext': 'flv',
  1539. 'title': 'Tabletop: Dread, Last Thoughts',
  1540. 'description': 'Tabletop: Dread, Last Thoughts',
  1541. 'duration': 51690,
  1542. },
  1543. },
  1544. # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
  1545. # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
  1546. {
  1547. 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
  1548. 'info_dict': {
  1549. 'id': '4785848093001',
  1550. 'ext': 'mp4',
  1551. 'title': 'The Cardinal Pell Interview',
  1552. 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
  1553. 'uploader': 'GlobeCast Australia - GlobeStream',
  1554. 'uploader_id': '2733773828001',
  1555. 'upload_date': '20160304',
  1556. 'timestamp': 1457083087,
  1557. },
  1558. 'params': {
  1559. # m3u8 downloads
  1560. 'skip_download': True,
  1561. },
  1562. },
  1563. {
  1564. # Brightcove embed with whitespace around attribute names
  1565. 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
  1566. 'info_dict': {
  1567. 'id': '3167554373001',
  1568. 'ext': 'mp4',
  1569. 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
  1570. 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
  1571. 'uploader_id': '1079349493',
  1572. 'upload_date': '20140207',
  1573. 'timestamp': 1391810548,
  1574. },
  1575. 'params': {
  1576. 'skip_download': True,
  1577. },
  1578. },
  1579. # Another form of arte.tv embed
  1580. {
  1581. 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
  1582. 'md5': '850bfe45417ddf221288c88a0cffe2e2',
  1583. 'info_dict': {
  1584. 'id': '030273-562_PLUS7-F',
  1585. 'ext': 'mp4',
  1586. 'title': 'ARTE Reportage - Nulle part, en France',
  1587. 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
  1588. 'upload_date': '20160409',
  1589. },
  1590. },
  1591. # LiveLeak embed
  1592. {
  1593. 'url': 'http://www.wykop.pl/link/3088787/',
  1594. 'md5': '7619da8c820e835bef21a1efa2a0fc71',
  1595. 'info_dict': {
  1596. 'id': '874_1459135191',
  1597. 'ext': 'mp4',
  1598. 'title': 'Man shows poor quality of new apartment building',
  1599. 'description': 'The wall is like a sand pile.',
  1600. 'uploader': 'Lake8737',
  1601. },
  1602. 'add_ie': [LiveLeakIE.ie_key()],
  1603. },
  1604. # Another LiveLeak embed pattern (#13336)
  1605. {
  1606. 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
  1607. 'info_dict': {
  1608. 'id': '2eb_1496309988',
  1609. 'ext': 'mp4',
  1610. 'title': 'Thief robs place where everyone was armed',
  1611. 'description': 'md5:694d73ee79e535953cf2488562288eee',
  1612. 'uploader': 'brazilwtf',
  1613. },
  1614. 'add_ie': [LiveLeakIE.ie_key()],
  1615. },
  1616. # Duplicated embedded video URLs
  1617. {
  1618. 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
  1619. 'info_dict': {
  1620. 'id': '149298443_480_16c25b74_2',
  1621. 'ext': 'mp4',
  1622. 'title': 'vs. Blue Orange Spring Game',
  1623. 'uploader': 'www.hudl.com',
  1624. },
  1625. },
  1626. # twitter:player:stream embed
  1627. {
  1628. 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
  1629. 'info_dict': {
  1630. 'id': 'master',
  1631. 'ext': 'mp4',
  1632. 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
  1633. 'uploader': 'www.rtl.be',
  1634. },
  1635. 'params': {
  1636. # m3u8 downloads
  1637. 'skip_download': True,
  1638. },
  1639. },
  1640. # twitter:player embed
  1641. {
  1642. 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
  1643. 'md5': 'a3e0df96369831de324f0778e126653c',
  1644. 'info_dict': {
  1645. 'id': '4909620399001',
  1646. 'ext': 'mp4',
  1647. 'title': 'What Do Black Holes Sound Like?',
  1648. 'description': 'what do black holes sound like',
  1649. 'upload_date': '20160524',
  1650. 'uploader_id': '29913724001',
  1651. 'timestamp': 1464107587,
  1652. 'uploader': 'TheAtlantic',
  1653. },
  1654. 'add_ie': ['BrightcoveLegacy'],
  1655. },
  1656. # Facebook <iframe> embed
  1657. {
  1658. 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
  1659. 'md5': 'fbcde74f534176ecb015849146dd3aee',
  1660. 'info_dict': {
  1661. 'id': '599637780109885',
  1662. 'ext': 'mp4',
  1663. 'title': 'Facebook video #599637780109885',
  1664. },
  1665. },
  1666. # Facebook <iframe> embed, plugin video
  1667. {
  1668. 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
  1669. 'info_dict': {
  1670. 'id': '1754168231264132',
  1671. 'ext': 'mp4',
  1672. 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
  1673. 'uploader': 'Tariq Ramadan (official)',
  1674. 'timestamp': 1496758379,
  1675. 'upload_date': '20170606',
  1676. },
  1677. 'params': {
  1678. 'skip_download': True,
  1679. },
  1680. },
  1681. # Facebook API embed
  1682. {
  1683. 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
  1684. 'md5': 'a47372ee61b39a7b90287094d447d94e',
  1685. 'info_dict': {
  1686. 'id': '10153467542406923',
  1687. 'ext': 'mp4',
  1688. 'title': 'Facebook video #10153467542406923',
  1689. },
  1690. },
  1691. # Wordpress "YouTube Video Importer" plugin
  1692. {
  1693. 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
  1694. 'md5': 'd16797741b560b485194eddda8121b48',
  1695. 'info_dict': {
  1696. 'id': 'HNTXWDXV9Is',
  1697. 'ext': 'mp4',
  1698. 'title': 'Blue Devils Drumline Stanford lot 2016',
  1699. 'upload_date': '20160627',
  1700. 'uploader_id': 'GENOCIDE8GENERAL10',
  1701. 'uploader': 'cylus cyrus',
  1702. },
  1703. },
  1704. {
  1705. # video stored on custom kaltura server
  1706. 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
  1707. 'md5': '537617d06e64dfed891fa1593c4b30cc',
  1708. 'info_dict': {
  1709. 'id': '0_1iotm5bh',
  1710. 'ext': 'mp4',
  1711. 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
  1712. 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
  1713. 'uploader_id': 'videos.expansion@el-mundo.net',
  1714. 'upload_date': '20150429',
  1715. 'timestamp': 1430303472,
  1716. },
  1717. 'add_ie': ['Kaltura'],
  1718. },
  1719. {
  1720. # multiple kaltura embeds, nsfw
  1721. 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
  1722. 'info_dict': {
  1723. 'id': 'kamila-avec-video-jaime-sadomie',
  1724. 'title': "Kamila avec vídeo “J'aime sadomie”",
  1725. },
  1726. 'playlist_count': 8,
  1727. },
  1728. {
  1729. # Non-standard Vimeo embed
  1730. 'url': 'https://openclassrooms.com/courses/understanding-the-web',
  1731. 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
  1732. 'info_dict': {
  1733. 'id': '148867247',
  1734. 'ext': 'mp4',
  1735. 'title': 'Understanding the web - Teaser',
  1736. 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
  1737. 'upload_date': '20151214',
  1738. 'uploader': 'OpenClassrooms',
  1739. 'uploader_id': 'openclassrooms',
  1740. },
  1741. 'add_ie': ['Vimeo'],
  1742. },
  1743. {
  1744. # generic vimeo embed that requires original URL passed as Referer
  1745. 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
  1746. 'only_matching': True,
  1747. },
  1748. {
  1749. 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
  1750. 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
  1751. 'info_dict': {
  1752. 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
  1753. 'ext': 'mp4',
  1754. 'title': 'Big Buck Bunny',
  1755. 'description': 'Royalty free test video',
  1756. 'timestamp': 1432816365,
  1757. 'upload_date': '20150528',
  1758. 'is_live': False,
  1759. },
  1760. 'params': {
  1761. 'skip_download': True,
  1762. },
  1763. 'add_ie': [ArkenaIE.ie_key()],
  1764. },
  1765. {
  1766. '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/',
  1767. 'info_dict': {
  1768. 'id': '1c7141f46c',
  1769. 'ext': 'mp4',
  1770. 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
  1771. },
  1772. 'params': {
  1773. 'skip_download': True,
  1774. },
  1775. 'add_ie': [Vbox7IE.ie_key()],
  1776. },
  1777. {
  1778. # DBTV embeds
  1779. 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
  1780. 'info_dict': {
  1781. 'id': '43254897',
  1782. 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
  1783. },
  1784. 'playlist_mincount': 3,
  1785. },
  1786. {
  1787. # Videa embeds
  1788. 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
  1789. 'info_dict': {
  1790. 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
  1791. 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
  1792. },
  1793. 'playlist_mincount': 2,
  1794. },
  1795. {
  1796. # 20 minuten embed
  1797. 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
  1798. 'info_dict': {
  1799. 'id': '523629',
  1800. 'ext': 'mp4',
  1801. 'title': 'So kommen Sie bei Eis und Schnee sicher an',
  1802. 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
  1803. },
  1804. 'params': {
  1805. 'skip_download': True,
  1806. },
  1807. 'add_ie': [TwentyMinutenIE.ie_key()],
  1808. },
  1809. {
  1810. # VideoPress embed
  1811. 'url': 'https://en.support.wordpress.com/videopress/',
  1812. 'info_dict': {
  1813. 'id': 'OcobLTqC',
  1814. 'ext': 'm4v',
  1815. 'title': 'IMG_5786',
  1816. 'timestamp': 1435711927,
  1817. 'upload_date': '20150701',
  1818. },
  1819. 'params': {
  1820. 'skip_download': True,
  1821. },
  1822. 'add_ie': [VideoPressIE.ie_key()],
  1823. },
  1824. {
  1825. # Rutube embed
  1826. 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
  1827. 'info_dict': {
  1828. 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
  1829. 'ext': 'flv',
  1830. 'title': 'Магаззино: Казань 2',
  1831. 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
  1832. 'uploader': 'Магаззино',
  1833. 'upload_date': '20170228',
  1834. 'uploader_id': '996642',
  1835. },
  1836. 'params': {
  1837. 'skip_download': True,
  1838. },
  1839. 'add_ie': [RutubeIE.ie_key()],
  1840. },
  1841. {
  1842. # ThePlatform embedded with whitespaces in URLs
  1843. 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
  1844. 'only_matching': True,
  1845. },
  1846. {
  1847. # Senate ISVP iframe https
  1848. 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
  1849. 'md5': 'fb8c70b0b515e5037981a2492099aab8',
  1850. 'info_dict': {
  1851. 'id': 'govtaff020316',
  1852. 'ext': 'mp4',
  1853. 'title': 'Integrated Senate Video Player',
  1854. },
  1855. 'add_ie': [SenateISVPIE.ie_key()],
  1856. },
  1857. {
  1858. # Limelight embeds (1 channel embed + 4 media embeds)
  1859. 'url': 'http://www.sedona.com/FacilitatorTraining2017',
  1860. 'info_dict': {
  1861. 'id': 'FacilitatorTraining2017',
  1862. 'title': 'Facilitator Training 2017',
  1863. },
  1864. 'playlist_mincount': 5,
  1865. },
  1866. {
  1867. # Limelight embed (LimelightPlayerUtil.embed)
  1868. 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
  1869. 'info_dict': {
  1870. 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
  1871. 'ext': 'mp4',
  1872. 'title': '07448641',
  1873. 'timestamp': 1499890639,
  1874. 'upload_date': '20170712',
  1875. },
  1876. 'params': {
  1877. 'skip_download': True,
  1878. },
  1879. 'add_ie': ['LimelightMedia'],
  1880. },
  1881. {
  1882. 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
  1883. 'info_dict': {
  1884. 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
  1885. 'title': 'Standoff with Walnut Creek murder suspect ends',
  1886. 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
  1887. },
  1888. 'playlist_mincount': 4,
  1889. },
  1890. {
  1891. # WashingtonPost embed
  1892. 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
  1893. 'info_dict': {
  1894. 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
  1895. 'ext': 'mp4',
  1896. 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
  1897. 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
  1898. 'timestamp': 1455216756,
  1899. 'uploader': 'The Washington Post',
  1900. 'upload_date': '20160211',
  1901. },
  1902. 'add_ie': [WashingtonPostIE.ie_key()],
  1903. },
  1904. {
  1905. # Mediaset embed
  1906. 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
  1907. 'info_dict': {
  1908. 'id': '720642',
  1909. 'ext': 'mp4',
  1910. 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
  1911. },
  1912. 'params': {
  1913. 'skip_download': True,
  1914. },
  1915. 'add_ie': [MediasetIE.ie_key()],
  1916. },
  1917. {
  1918. # JOJ.sk embeds
  1919. 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1920. 'info_dict': {
  1921. 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1922. 'title': 'Slovenskom sa prehnala vlna silných búrok',
  1923. },
  1924. 'playlist_mincount': 5,
  1925. 'add_ie': [JojIE.ie_key()],
  1926. },
  1927. {
  1928. # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
  1929. 'url': 'https://tvrain.ru/amp/418921/',
  1930. 'md5': 'cc00413936695987e8de148b67d14f1d',
  1931. 'info_dict': {
  1932. 'id': '418921',
  1933. 'ext': 'mp4',
  1934. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1935. },
  1936. },
  1937. {
  1938. # vzaar embed
  1939. 'url': 'http://help.vzaar.com/article/165-embedding-video',
  1940. 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
  1941. 'info_dict': {
  1942. 'id': '8707641',
  1943. 'ext': 'mp4',
  1944. 'title': 'Building A Business Online: Principal Chairs Q & A',
  1945. },
  1946. },
  1947. {
  1948. # multiple HTML5 videos on one page
  1949. 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
  1950. 'info_dict': {
  1951. 'id': 'keyscenarios',
  1952. 'title': 'Rescue Kit 14 Free Edition - Getting started',
  1953. },
  1954. 'playlist_count': 4,
  1955. },
  1956. {
  1957. # vshare embed
  1958. 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
  1959. 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
  1960. 'info_dict': {
  1961. 'id': '0f64ce6',
  1962. 'title': 'vl14062007715967',
  1963. 'ext': 'mp4',
  1964. }
  1965. },
  1966. {
  1967. 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
  1968. 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
  1969. 'info_dict': {
  1970. 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
  1971. 'ext': 'mp4',
  1972. 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
  1973. 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
  1974. 'timestamp': 1474354800,
  1975. 'upload_date': '20160920',
  1976. }
  1977. },
  1978. {
  1979. 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
  1980. 'info_dict': {
  1981. 'id': '1731611',
  1982. 'ext': 'mp4',
  1983. 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
  1984. 'description': 'md5:eb5f23826a027ba95277d105f248b825',
  1985. 'timestamp': 1516100691,
  1986. 'upload_date': '20180116',
  1987. },
  1988. 'params': {
  1989. 'skip_download': True,
  1990. },
  1991. 'add_ie': [SpringboardPlatformIE.ie_key()],
  1992. },
  1993. {
  1994. 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
  1995. 'info_dict': {
  1996. 'id': 'uPDB5I9wfp8',
  1997. 'ext': 'webm',
  1998. 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
  1999. 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
  2000. 'upload_date': '20160219',
  2001. 'uploader': 'Pocoyo - Português (BR)',
  2002. 'uploader_id': 'PocoyoBrazil',
  2003. },
  2004. 'add_ie': [YoutubeIE.ie_key()],
  2005. 'params': {
  2006. 'skip_download': True,
  2007. },
  2008. },
  2009. {
  2010. 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
  2011. 'info_dict': {
  2012. 'id': 'vMDE4NzI1Mjgt690b',
  2013. 'ext': 'mp4',
  2014. 'title': 'Котята',
  2015. },
  2016. 'add_ie': [YapFilesIE.ie_key()],
  2017. 'params': {
  2018. 'skip_download': True,
  2019. },
  2020. },
  2021. {
  2022. # CloudflareStream embed
  2023. 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
  2024. 'info_dict': {
  2025. 'id': '31c9291ab41fac05471db4e73aa11717',
  2026. 'ext': 'mp4',
  2027. 'title': '31c9291ab41fac05471db4e73aa11717',
  2028. },
  2029. 'add_ie': [CloudflareStreamIE.ie_key()],
  2030. 'params': {
  2031. 'skip_download': True,
  2032. },
  2033. },
  2034. {
  2035. # PeerTube embed
  2036. 'url': 'https://joinpeertube.org/fr/home/',
  2037. 'info_dict': {
  2038. 'id': 'home',
  2039. 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
  2040. },
  2041. 'playlist_count': 2,
  2042. },
  2043. {
  2044. # Indavideo embed
  2045. 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
  2046. 'info_dict': {
  2047. 'id': '1693903',
  2048. 'ext': 'mp4',
  2049. 'title': 'Így kell otthon hamburgert sütni',
  2050. 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
  2051. 'timestamp': 1426330212,
  2052. 'upload_date': '20150314',
  2053. 'uploader': 'StreetKitchen',
  2054. 'uploader_id': '546363',
  2055. },
  2056. 'add_ie': [IndavideoEmbedIE.ie_key()],
  2057. 'params': {
  2058. 'skip_download': True,
  2059. },
  2060. },
  2061. {
  2062. # APA embed via JWPlatform embed
  2063. 'url': 'http://www.vol.at/blue-man-group/5593454',
  2064. 'info_dict': {
  2065. 'id': 'jjv85FdZ',
  2066. 'ext': 'mp4',
  2067. 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
  2068. 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  2069. 'thumbnail': r're:^https?://.*\.jpg$',
  2070. 'duration': 254,
  2071. 'timestamp': 1519211149,
  2072. 'upload_date': '20180221',
  2073. },
  2074. 'params': {
  2075. 'skip_download': True,
  2076. },
  2077. },
  2078. {
  2079. 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
  2080. 'md5': 'b68d276de422ab07ee1d49388103f457',
  2081. 'info_dict': {
  2082. 'id': '83645793',
  2083. 'title': 'Lock up and get excited',
  2084. 'ext': 'mp4'
  2085. },
  2086. 'skip': 'TODO: fix nested playlists processing in tests',
  2087. },
  2088. {
  2089. # Viqeo embeds
  2090. 'url': 'https://viqeo.tv/',
  2091. 'info_dict': {
  2092. 'id': 'viqeo',
  2093. 'title': 'All-new video platform',
  2094. },
  2095. 'playlist_count': 6,
  2096. },
  2097. {
  2098. # Squarespace video embed, 2019-08-28
  2099. 'url': 'http://ootboxford.com',
  2100. 'info_dict': {
  2101. 'id': 'Tc7b_JGdZfw',
  2102. 'title': 'Out of the Blue, at Childish Things 10',
  2103. 'ext': 'mp4',
  2104. 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
  2105. 'uploader_id': 'helendouglashouse',
  2106. 'uploader': 'Helen & Douglas House',
  2107. 'upload_date': '20140328',
  2108. },
  2109. 'params': {
  2110. 'skip_download': True,
  2111. },
  2112. },
  2113. # {
  2114. # # Zype embed
  2115. # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
  2116. # 'info_dict': {
  2117. # 'id': '5b400b834b32992a310622b9',
  2118. # 'ext': 'mp4',
  2119. # 'title': 'Smoky Barbecue Favorites',
  2120. # 'thumbnail': r're:^https?://.*\.jpe?g',
  2121. # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
  2122. # 'upload_date': '20170909',
  2123. # 'timestamp': 1504915200,
  2124. # },
  2125. # 'add_ie': [ZypeIE.ie_key()],
  2126. # 'params': {
  2127. # 'skip_download': True,
  2128. # },
  2129. # },
  2130. {
  2131. # videojs embed
  2132. 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
  2133. 'info_dict': {
  2134. 'id': 'shell',
  2135. 'ext': 'mp4',
  2136. 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
  2137. 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
  2138. 'thumbnail': r're:^https?://.*\.jpg$',
  2139. },
  2140. 'params': {
  2141. 'skip_download': True,
  2142. },
  2143. 'expected_warnings': ['Failed to download MPD manifest'],
  2144. },
  2145. {
  2146. # DailyMotion embed with DM.player
  2147. 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
  2148. 'info_dict': {
  2149. 'id': 'k6aKkGHd9FJs4mtJN39',
  2150. 'ext': 'mp4',
  2151. 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
  2152. 'description': 'This video is private.',
  2153. 'uploader_id': 'x1jf30l',
  2154. 'uploader': 'beIN SPORTS USA',
  2155. 'upload_date': '20190528',
  2156. 'timestamp': 1559062971,
  2157. },
  2158. 'params': {
  2159. 'skip_download': True,
  2160. },
  2161. },
  2162. # {
  2163. # # TODO: find another test
  2164. # # http://schema.org/VideoObject
  2165. # 'url': 'https://flipagram.com/f/nyvTSJMKId',
  2166. # 'md5': '888dcf08b7ea671381f00fab74692755',
  2167. # 'info_dict': {
  2168. # 'id': 'nyvTSJMKId',
  2169. # 'ext': 'mp4',
  2170. # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
  2171. # 'description': '#love for cats.',
  2172. # 'timestamp': 1461244995,
  2173. # 'upload_date': '20160421',
  2174. # },
  2175. # 'params': {
  2176. # 'force_generic_extractor': True,
  2177. # },
  2178. # }
  2179. ]
  2180. def report_following_redirect(self, new_url):
  2181. """Report information extraction."""
  2182. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  2183. def _extract_rss(self, url, video_id, doc):
  2184. playlist_title = doc.find('./channel/title').text
  2185. playlist_desc_el = doc.find('./channel/description')
  2186. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  2187. NS_MAP = {
  2188. 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
  2189. }
  2190. entries = []
  2191. for it in doc.findall('./channel/item'):
  2192. next_url = None
  2193. enclosure_nodes = it.findall('./enclosure')
  2194. for e in enclosure_nodes:
  2195. next_url = e.attrib.get('url')
  2196. if next_url:
  2197. break
  2198. if not next_url:
  2199. next_url = xpath_text(it, 'link', fatal=False)
  2200. if not next_url:
  2201. continue
  2202. def itunes(key):
  2203. return xpath_text(
  2204. it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
  2205. default=None)
  2206. duration = itunes('duration')
  2207. explicit = itunes('explicit')
  2208. if explicit == 'true':
  2209. age_limit = 18
  2210. elif explicit == 'false':
  2211. age_limit = 0
  2212. else:
  2213. age_limit = None
  2214. entries.append({
  2215. '_type': 'url_transparent',
  2216. 'url': next_url,
  2217. 'title': it.find('title').text,
  2218. 'description': xpath_text(it, 'description', default=None),
  2219. 'timestamp': unified_timestamp(
  2220. xpath_text(it, 'pubDate', default=None)),
  2221. 'duration': int_or_none(duration) or parse_duration(duration),
  2222. 'thumbnail': url_or_none(itunes('image')),
  2223. 'episode': itunes('title'),
  2224. 'episode_number': int_or_none(itunes('episode')),
  2225. 'season_number': int_or_none(itunes('season')),
  2226. 'age_limit': age_limit,
  2227. })
  2228. return {
  2229. '_type': 'playlist',
  2230. 'id': url,
  2231. 'title': playlist_title,
  2232. 'description': playlist_desc,
  2233. 'entries': entries,
  2234. }
  2235. def _extract_camtasia(self, url, video_id, webpage):
  2236. """ Returns None if no camtasia video can be found. """
  2237. camtasia_cfg = self._search_regex(
  2238. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  2239. webpage, 'camtasia configuration file', default=None)
  2240. if camtasia_cfg is None:
  2241. return None
  2242. title = self._html_search_meta('DC.title', webpage, fatal=True)
  2243. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  2244. camtasia_cfg = self._download_xml(
  2245. camtasia_url, video_id,
  2246. note='Downloading camtasia configuration',
  2247. errnote='Failed to download camtasia configuration')
  2248. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  2249. entries = []
  2250. for n in fileset_node.getchildren():
  2251. url_n = n.find('./uri')
  2252. if url_n is None:
  2253. continue
  2254. entries.append({
  2255. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  2256. 'title': '%s - %s' % (title, n.tag),
  2257. 'url': compat_urlparse.urljoin(url, url_n.text),
  2258. 'duration': float_or_none(n.find('./duration').text),
  2259. })
  2260. return {
  2261. '_type': 'playlist',
  2262. 'entries': entries,
  2263. 'title': title,
  2264. }
  2265. def _real_extract(self, url):
  2266. if url.startswith('//'):
  2267. return self.url_result(self.http_scheme() + url)
  2268. parsed_url = compat_urlparse.urlparse(url)
  2269. if not parsed_url.scheme:
  2270. default_search = self._downloader.params.get('default_search')
  2271. if default_search is None:
  2272. default_search = 'fixup_error'
  2273. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  2274. if re.match(r'^[^\s/]+\.[^\s/]+/', url):
  2275. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  2276. return self.url_result('http://' + url)
  2277. elif default_search != 'fixup_error':
  2278. if default_search == 'auto_warning':
  2279. if re.match(r'^(?:url|URL)$', url):
  2280. raise ExtractorError(
  2281. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  2282. expected=True)
  2283. else:
  2284. self._downloader.report_warning(
  2285. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  2286. return self.url_result('ytsearch:' + url)
  2287. if default_search in ('error', 'fixup_error'):
  2288. raise ExtractorError(
  2289. '%r is not a valid URL. '
  2290. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  2291. % (url, url), expected=True)
  2292. else:
  2293. if ':' not in default_search:
  2294. default_search += ':'
  2295. return self.url_result(default_search + url)
  2296. url, smuggled_data = unsmuggle_url(url)
  2297. force_videoid = None
  2298. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  2299. if smuggled_data and 'force_videoid' in smuggled_data:
  2300. force_videoid = smuggled_data['force_videoid']
  2301. video_id = force_videoid
  2302. else:
  2303. video_id = self._generic_id(url)
  2304. self.to_screen('%s: Requesting header' % video_id)
  2305. head_req = HEADRequest(url)
  2306. head_response = self._request_webpage(
  2307. head_req, video_id,
  2308. note=False, errnote='Could not send HEAD request to %s' % url,
  2309. fatal=False)
  2310. if head_response is not False:
  2311. # Check for redirect
  2312. new_url = head_response.geturl()
  2313. if url != new_url:
  2314. self.report_following_redirect(new_url)
  2315. if force_videoid:
  2316. new_url = smuggle_url(
  2317. new_url, {'force_videoid': force_videoid})
  2318. return self.url_result(new_url)
  2319. full_response = None
  2320. if head_response is False:
  2321. request = sanitized_Request(url)
  2322. request.add_header('Accept-Encoding', '*')
  2323. full_response = self._request_webpage(request, video_id)
  2324. head_response = full_response
  2325. info_dict = {
  2326. 'id': video_id,
  2327. 'title': self._generic_title(url),
  2328. 'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
  2329. }
  2330. # Check for direct link to a video
  2331. content_type = head_response.headers.get('Content-Type', '').lower()
  2332. m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
  2333. if m:
  2334. format_id = compat_str(m.group('format_id'))
  2335. if format_id.endswith('mpegurl'):
  2336. formats = self._extract_m3u8_formats(url, video_id, 'mp4')
  2337. elif format_id == 'f4m':
  2338. formats = self._extract_f4m_formats(url, video_id)
  2339. else:
  2340. formats = [{
  2341. 'format_id': format_id,
  2342. 'url': url,
  2343. 'vcodec': 'none' if m.group('type') == 'audio' else None
  2344. }]
  2345. info_dict['direct'] = True
  2346. self._sort_formats(formats)
  2347. info_dict['formats'] = formats
  2348. return info_dict
  2349. if not self._downloader.params.get('test', False) and not is_intentional:
  2350. force = self._downloader.params.get('force_generic_extractor', False)
  2351. self._downloader.report_warning(
  2352. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  2353. if not full_response:
  2354. request = sanitized_Request(url)
  2355. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  2356. # making it impossible to download only chunk of the file (yet we need only 512kB to
  2357. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  2358. # that will always result in downloading the whole file that is not desirable.
  2359. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  2360. # to accept raw bytes and being able to download only a chunk.
  2361. # It may probably better to solve this by checking Content-Type for application/octet-stream
  2362. # after HEAD request finishes, but not sure if we can rely on this.
  2363. request.add_header('Accept-Encoding', '*')
  2364. full_response = self._request_webpage(request, video_id)
  2365. first_bytes = full_response.read(512)
  2366. # Is it an M3U playlist?
  2367. if first_bytes.startswith(b'#EXTM3U'):
  2368. info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
  2369. self._sort_formats(info_dict['formats'])
  2370. return info_dict
  2371. # Maybe it's a direct link to a video?
  2372. # Be careful not to download the whole thing!
  2373. if not is_html(first_bytes):
  2374. self._downloader.report_warning(
  2375. 'URL could be a direct video link, returning it as such.')
  2376. info_dict.update({
  2377. 'direct': True,
  2378. 'url': url,
  2379. })
  2380. return info_dict
  2381. webpage = self._webpage_read_content(
  2382. full_response, url, video_id, prefix=first_bytes)
  2383. self.report_extraction(video_id)
  2384. # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
  2385. try:
  2386. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  2387. if doc.tag == 'rss':
  2388. return self._extract_rss(url, video_id, doc)
  2389. elif doc.tag == 'SmoothStreamingMedia':
  2390. info_dict['formats'] = self._parse_ism_formats(doc, url)
  2391. self._sort_formats(info_dict['formats'])
  2392. return info_dict
  2393. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  2394. smil = self._parse_smil(doc, url, video_id)
  2395. self._sort_formats(smil['formats'])
  2396. return smil
  2397. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  2398. return self.playlist_result(
  2399. self._parse_xspf(
  2400. doc, video_id, xspf_url=url,
  2401. xspf_base_url=full_response.geturl()),
  2402. video_id)
  2403. elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
  2404. info_dict['formats'] = self._parse_mpd_formats(
  2405. doc,
  2406. mpd_base_url=full_response.geturl().rpartition('/')[0],
  2407. mpd_url=url)
  2408. self._sort_formats(info_dict['formats'])
  2409. return info_dict
  2410. elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
  2411. info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
  2412. self._sort_formats(info_dict['formats'])
  2413. return info_dict
  2414. except compat_xml_parse_error:
  2415. pass
  2416. # Is it a Camtasia project?
  2417. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  2418. if camtasia_res is not None:
  2419. return camtasia_res
  2420. # Sometimes embedded video player is hidden behind percent encoding
  2421. # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
  2422. # Unescaping the whole page allows to handle those cases in a generic way
  2423. # FIXME: unescaping the whole page may break URLs, commenting out for now.
  2424. # There probably should be a second run of generic extractor on unescaped webpage.
  2425. # webpage = compat_urllib_parse_unquote(webpage)
  2426. # Unescape squarespace embeds to be detected by generic extractor,
  2427. # see https://github.com/ytdl-org/youtube-dl/issues/21294
  2428. webpage = re.sub(
  2429. r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
  2430. lambda x: unescapeHTML(x.group(0)), webpage)
  2431. # it's tempting to parse this further, but you would
  2432. # have to take into account all the variations like
  2433. # Video Title - Site Name
  2434. # Site Name | Video Title
  2435. # Video Title - Tagline | Site Name
  2436. # and so on and so forth; it's just not practical
  2437. video_title = self._og_search_title(
  2438. webpage, default=None) or self._html_search_regex(
  2439. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  2440. default='video')
  2441. # Try to detect age limit automatically
  2442. age_limit = self._rta_search(webpage)
  2443. # And then there are the jokers who advertise that they use RTA,
  2444. # but actually don't.
  2445. AGE_LIMIT_MARKERS = [
  2446. r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
  2447. ]
  2448. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  2449. age_limit = 18
  2450. # video uploader is domain name
  2451. video_uploader = self._search_regex(
  2452. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  2453. video_description = self._og_search_description(webpage, default=None)
  2454. video_thumbnail = self._og_search_thumbnail(webpage, default=None)
  2455. info_dict.update({
  2456. 'title': video_title,
  2457. 'description': video_description,
  2458. 'thumbnail': video_thumbnail,
  2459. 'age_limit': age_limit,
  2460. })
  2461. # Look for Brightcove Legacy Studio embeds
  2462. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  2463. if bc_urls:
  2464. entries = [{
  2465. '_type': 'url',
  2466. 'url': smuggle_url(bc_url, {'Referer': url}),
  2467. 'ie_key': 'BrightcoveLegacy'
  2468. } for bc_url in bc_urls]
  2469. return {
  2470. '_type': 'playlist',
  2471. 'title': video_title,
  2472. 'id': video_id,
  2473. 'entries': entries,
  2474. }
  2475. # Look for Brightcove New Studio embeds
  2476. bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
  2477. if bc_urls:
  2478. return self.playlist_from_matches(
  2479. bc_urls, video_id, video_title,
  2480. getter=lambda x: smuggle_url(x, {'referrer': url}),
  2481. ie='BrightcoveNew')
  2482. # Look for Nexx embeds
  2483. nexx_urls = NexxIE._extract_urls(webpage)
  2484. if nexx_urls:
  2485. return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
  2486. # Look for Nexx iFrame embeds
  2487. nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
  2488. if nexx_embed_urls:
  2489. return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
  2490. # Look for ThePlatform embeds
  2491. tp_urls = ThePlatformIE._extract_urls(webpage)
  2492. if tp_urls:
  2493. return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
  2494. # Look for embedded rtl.nl player
  2495. matches = re.findall(
  2496. r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
  2497. webpage)
  2498. if matches:
  2499. return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
  2500. vimeo_urls = VimeoIE._extract_urls(url, webpage)
  2501. if vimeo_urls:
  2502. return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
  2503. vid_me_embed_url = self._search_regex(
  2504. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  2505. webpage, 'vid.me embed', default=None)
  2506. if vid_me_embed_url is not None:
  2507. return self.url_result(vid_me_embed_url, 'Vidme')
  2508. # Look for YouTube embeds
  2509. youtube_urls = YoutubeIE._extract_urls(webpage)
  2510. if youtube_urls:
  2511. return self.playlist_from_matches(
  2512. youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
  2513. matches = DailymotionIE._extract_urls(webpage)
  2514. if matches:
  2515. return self.playlist_from_matches(matches, video_id, video_title)
  2516. # Look for embedded Dailymotion playlist player (#3822)
  2517. m = re.search(
  2518. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  2519. if m:
  2520. playlists = re.findall(
  2521. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  2522. if playlists:
  2523. return self.playlist_from_matches(
  2524. playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
  2525. # Look for DailyMail embeds
  2526. dailymail_urls = DailyMailIE._extract_urls(webpage)
  2527. if dailymail_urls:
  2528. return self.playlist_from_matches(
  2529. dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
  2530. # Look for Teachable embeds, must be before Wistia
  2531. teachable_url = TeachableIE._extract_url(webpage, url)
  2532. if teachable_url:
  2533. return self.url_result(teachable_url)
  2534. # Look for embedded Wistia player
  2535. wistia_urls = WistiaIE._extract_urls(webpage)
  2536. if wistia_urls:
  2537. playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
  2538. for entry in playlist['entries']:
  2539. entry.update({
  2540. '_type': 'url_transparent',
  2541. 'uploader': video_uploader,
  2542. })
  2543. return playlist
  2544. # Look for SVT player
  2545. svt_url = SVTIE._extract_url(webpage)
  2546. if svt_url:
  2547. return self.url_result(svt_url, 'SVT')
  2548. # Look for Bandcamp pages with custom domain
  2549. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  2550. if mobj is not None:
  2551. burl = unescapeHTML(mobj.group(1))
  2552. # Don't set the extractor because it can be a track url or an album
  2553. return self.url_result(burl)
  2554. # Look for embedded Vevo player
  2555. mobj = re.search(
  2556. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  2557. if mobj is not None:
  2558. return self.url_result(mobj.group('url'))
  2559. # Look for embedded Viddler player
  2560. mobj = re.search(
  2561. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  2562. webpage)
  2563. if mobj is not None:
  2564. return self.url_result(mobj.group('url'))
  2565. # Look for NYTimes player
  2566. mobj = re.search(
  2567. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  2568. webpage)
  2569. if mobj is not None:
  2570. return self.url_result(mobj.group('url'))
  2571. # Look for Libsyn player
  2572. mobj = re.search(
  2573. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  2574. if mobj is not None:
  2575. return self.url_result(mobj.group('url'))
  2576. # Look for Ooyala videos
  2577. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
  2578. or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
  2579. or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
  2580. or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
  2581. or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  2582. if mobj is not None:
  2583. embed_token = self._search_regex(
  2584. r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
  2585. webpage, 'ooyala embed token', default=None)
  2586. return OoyalaIE._build_url_result(smuggle_url(
  2587. mobj.group('ec'), {
  2588. 'domain': url,
  2589. 'embed_token': embed_token,
  2590. }))
  2591. # Look for multiple Ooyala embeds on SBN network websites
  2592. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  2593. if mobj is not None:
  2594. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  2595. if embeds:
  2596. return self.playlist_from_matches(
  2597. embeds, video_id, video_title,
  2598. getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  2599. # Look for Aparat videos
  2600. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  2601. if mobj is not None:
  2602. return self.url_result(mobj.group(1), 'Aparat')
  2603. # Look for MPORA videos
  2604. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  2605. if mobj is not None:
  2606. return self.url_result(mobj.group(1), 'Mpora')
  2607. # Look for embedded Facebook player
  2608. facebook_urls = FacebookIE._extract_urls(webpage)
  2609. if facebook_urls:
  2610. return self.playlist_from_matches(facebook_urls, video_id, video_title)
  2611. # Look for embedded VK player
  2612. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  2613. if mobj is not None:
  2614. return self.url_result(mobj.group('url'), 'VK')
  2615. # Look for embedded Odnoklassniki player
  2616. odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
  2617. if odnoklassniki_url:
  2618. return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
  2619. # Look for embedded ivi player
  2620. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  2621. if mobj is not None:
  2622. return self.url_result(mobj.group('url'), 'Ivi')
  2623. # Look for embedded Huffington Post player
  2624. mobj = re.search(
  2625. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  2626. if mobj is not None:
  2627. return self.url_result(mobj.group('url'), 'HuffPost')
  2628. # Look for embed.ly
  2629. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  2630. if mobj is not None:
  2631. return self.url_result(mobj.group('url'))
  2632. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  2633. if mobj is not None:
  2634. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  2635. # Look for funnyordie embed
  2636. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  2637. if matches:
  2638. return self.playlist_from_matches(
  2639. matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
  2640. # Look for BBC iPlayer embed
  2641. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  2642. if matches:
  2643. return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
  2644. # Look for embedded RUTV player
  2645. rutv_url = RUTVIE._extract_url(webpage)
  2646. if rutv_url:
  2647. return self.url_result(rutv_url, 'RUTV')
  2648. # Look for embedded TVC player
  2649. tvc_url = TVCIE._extract_url(webpage)
  2650. if tvc_url:
  2651. return self.url_result(tvc_url, 'TVC')
  2652. # Look for embedded SportBox player
  2653. sportbox_urls = SportBoxIE._extract_urls(webpage)
  2654. if sportbox_urls:
  2655. return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
  2656. # Look for embedded XHamster player
  2657. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  2658. if xhamster_urls:
  2659. return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
  2660. # Look for embedded TNAFlixNetwork player
  2661. tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
  2662. if tnaflix_urls:
  2663. return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
  2664. # Look for embedded PornHub player
  2665. pornhub_urls = PornHubIE._extract_urls(webpage)
  2666. if pornhub_urls:
  2667. return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
  2668. # Look for embedded DrTuber player
  2669. drtuber_urls = DrTuberIE._extract_urls(webpage)
  2670. if drtuber_urls:
  2671. return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
  2672. # Look for embedded RedTube player
  2673. redtube_urls = RedTubeIE._extract_urls(webpage)
  2674. if redtube_urls:
  2675. return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
  2676. # Look for embedded Tube8 player
  2677. tube8_urls = Tube8IE._extract_urls(webpage)
  2678. if tube8_urls:
  2679. return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
  2680. # Look for embedded Mofosex player
  2681. mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
  2682. if mofosex_urls:
  2683. return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
  2684. # Look for embedded Spankwire player
  2685. spankwire_urls = SpankwireIE._extract_urls(webpage)
  2686. if spankwire_urls:
  2687. return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
  2688. # Look for embedded YouPorn player
  2689. youporn_urls = YouPornIE._extract_urls(webpage)
  2690. if youporn_urls:
  2691. return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
  2692. # Look for embedded Tvigle player
  2693. mobj = re.search(
  2694. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  2695. if mobj is not None:
  2696. return self.url_result(mobj.group('url'), 'Tvigle')
  2697. # Look for embedded TED player
  2698. mobj = re.search(
  2699. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  2700. if mobj is not None:
  2701. return self.url_result(mobj.group('url'), 'TED')
  2702. # Look for embedded Ustream videos
  2703. ustream_url = UstreamIE._extract_url(webpage)
  2704. if ustream_url:
  2705. return self.url_result(ustream_url, UstreamIE.ie_key())
  2706. # Look for embedded arte.tv player
  2707. arte_urls = ArteTVEmbedIE._extract_urls(webpage)
  2708. if arte_urls:
  2709. return self.playlist_from_matches(arte_urls, video_id, video_title)
  2710. # Look for embedded francetv player
  2711. mobj = re.search(
  2712. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  2713. webpage)
  2714. if mobj is not None:
  2715. return self.url_result(mobj.group('url'))
  2716. # Look for embedded Myvi.ru player
  2717. myvi_url = MyviIE._extract_url(webpage)
  2718. if myvi_url:
  2719. return self.url_result(myvi_url)
  2720. # Look for embedded soundcloud player
  2721. soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
  2722. if soundcloud_urls:
  2723. return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
  2724. # Look for tunein player
  2725. tunein_urls = TuneInBaseIE._extract_urls(webpage)
  2726. if tunein_urls:
  2727. return self.playlist_from_matches(tunein_urls, video_id, video_title)
  2728. # Look for embedded mtvservices player
  2729. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  2730. if mtvservices_url:
  2731. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  2732. # Look for embedded yahoo player
  2733. mobj = re.search(
  2734. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  2735. webpage)
  2736. if mobj is not None:
  2737. return self.url_result(mobj.group('url'), 'Yahoo')
  2738. # Look for embedded sbs.com.au player
  2739. mobj = re.search(
  2740. r'''(?x)
  2741. (?:
  2742. <meta\s+property="og:video"\s+content=|
  2743. <iframe[^>]+?src=
  2744. )
  2745. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  2746. webpage)
  2747. if mobj is not None:
  2748. return self.url_result(mobj.group('url'), 'SBS')
  2749. # Look for embedded Cinchcast player
  2750. mobj = re.search(
  2751. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  2752. webpage)
  2753. if mobj is not None:
  2754. return self.url_result(mobj.group('url'), 'Cinchcast')
  2755. mobj = re.search(
  2756. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  2757. webpage)
  2758. if not mobj:
  2759. mobj = re.search(
  2760. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  2761. webpage)
  2762. if mobj is not None:
  2763. return self.url_result(mobj.group('url'), 'MLB')
  2764. mobj = re.search(
  2765. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  2766. webpage)
  2767. if mobj is not None:
  2768. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  2769. mobj = re.search(
  2770. r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
  2771. webpage)
  2772. if mobj is not None:
  2773. return self.url_result(mobj.group('url'), 'Livestream')
  2774. # Look for Zapiks embed
  2775. mobj = re.search(
  2776. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  2777. if mobj is not None:
  2778. return self.url_result(mobj.group('url'), 'Zapiks')
  2779. # Look for Kaltura embeds
  2780. kaltura_urls = KalturaIE._extract_urls(webpage)
  2781. if kaltura_urls:
  2782. return self.playlist_from_matches(
  2783. kaltura_urls, video_id, video_title,
  2784. getter=lambda x: smuggle_url(x, {'source_url': url}),
  2785. ie=KalturaIE.ie_key())
  2786. # Look for EaglePlatform embeds
  2787. eagleplatform_url = EaglePlatformIE._extract_url(webpage)
  2788. if eagleplatform_url:
  2789. return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
  2790. # Look for ClipYou (uses EaglePlatform) embeds
  2791. mobj = re.search(
  2792. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  2793. if mobj is not None:
  2794. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  2795. # Look for Pladform embeds
  2796. pladform_url = PladformIE._extract_url(webpage)
  2797. if pladform_url:
  2798. return self.url_result(pladform_url)
  2799. # Look for Videomore embeds
  2800. videomore_url = VideomoreIE._extract_url(webpage)
  2801. if videomore_url:
  2802. return self.url_result(videomore_url)
  2803. # Look for Webcaster embeds
  2804. webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
  2805. if webcaster_url:
  2806. return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
  2807. # Look for Playwire embeds
  2808. mobj = re.search(
  2809. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  2810. if mobj is not None:
  2811. return self.url_result(mobj.group('url'))
  2812. # Look for 5min embeds
  2813. mobj = re.search(
  2814. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  2815. if mobj is not None:
  2816. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  2817. # Look for Crooks and Liars embeds
  2818. mobj = re.search(
  2819. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  2820. if mobj is not None:
  2821. return self.url_result(mobj.group('url'))
  2822. # Look for NBC Sports VPlayer embeds
  2823. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  2824. if nbc_sports_url:
  2825. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  2826. # Look for NBC News embeds
  2827. nbc_news_embed_url = re.search(
  2828. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
  2829. if nbc_news_embed_url:
  2830. return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
  2831. # Look for Google Drive embeds
  2832. google_drive_url = GoogleDriveIE._extract_url(webpage)
  2833. if google_drive_url:
  2834. return self.url_result(google_drive_url, 'GoogleDrive')
  2835. # Look for UDN embeds
  2836. mobj = re.search(
  2837. r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  2838. if mobj is not None:
  2839. return self.url_result(
  2840. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  2841. # Look for Senate ISVP iframe
  2842. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  2843. if senate_isvp_url:
  2844. return self.url_result(senate_isvp_url, 'SenateISVP')
  2845. # Look for Kinja embeds
  2846. kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
  2847. if kinja_embed_urls:
  2848. return self.playlist_from_matches(
  2849. kinja_embed_urls, video_id, video_title)
  2850. # Look for OnionStudios embeds
  2851. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  2852. if onionstudios_url:
  2853. return self.url_result(onionstudios_url)
  2854. # Look for ViewLift embeds
  2855. viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
  2856. if viewlift_url:
  2857. return self.url_result(viewlift_url)
  2858. # Look for JWPlatform embeds
  2859. jwplatform_urls = JWPlatformIE._extract_urls(webpage)
  2860. if jwplatform_urls:
  2861. return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
  2862. # Look for Digiteka embeds
  2863. digiteka_url = DigitekaIE._extract_url(webpage)
  2864. if digiteka_url:
  2865. return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
  2866. # Look for Arkena embeds
  2867. arkena_url = ArkenaIE._extract_url(webpage)
  2868. if arkena_url:
  2869. return self.url_result(arkena_url, ArkenaIE.ie_key())
  2870. # Look for Piksel embeds
  2871. piksel_url = PikselIE._extract_url(webpage)
  2872. if piksel_url:
  2873. return self.url_result(piksel_url, PikselIE.ie_key())
  2874. # Look for Limelight embeds
  2875. limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
  2876. if limelight_urls:
  2877. return self.playlist_result(
  2878. limelight_urls, video_id, video_title, video_description)
  2879. # Look for Anvato embeds
  2880. anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
  2881. if anvato_urls:
  2882. return self.playlist_result(
  2883. anvato_urls, video_id, video_title, video_description)
  2884. # Look for AdobeTVVideo embeds
  2885. mobj = re.search(
  2886. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  2887. webpage)
  2888. if mobj is not None:
  2889. return self.url_result(
  2890. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  2891. 'AdobeTVVideo')
  2892. # Look for Vine embeds
  2893. mobj = re.search(
  2894. r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
  2895. webpage)
  2896. if mobj is not None:
  2897. return self.url_result(
  2898. self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
  2899. # Look for VODPlatform embeds
  2900. mobj = re.search(
  2901. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
  2902. webpage)
  2903. if mobj is not None:
  2904. return self.url_result(
  2905. self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
  2906. # Look for Mangomolo embeds
  2907. mobj = re.search(
  2908. r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
  2909. (?:
  2910. admin\.mangomolo\.com/analytics/index\.php/customers/embed|
  2911. player\.mangomolo\.com/v1
  2912. )/
  2913. (?:
  2914. video\?.*?\bid=(?P<video_id>\d+)|
  2915. (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
  2916. ).+?)\1''', webpage)
  2917. if mobj is not None:
  2918. info = {
  2919. '_type': 'url_transparent',
  2920. 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
  2921. 'title': video_title,
  2922. 'description': video_description,
  2923. 'thumbnail': video_thumbnail,
  2924. 'uploader': video_uploader,
  2925. }
  2926. video_id = mobj.group('video_id')
  2927. if video_id:
  2928. info.update({
  2929. 'ie_key': 'MangomoloVideo',
  2930. 'id': video_id,
  2931. })
  2932. else:
  2933. info.update({
  2934. 'ie_key': 'MangomoloLive',
  2935. 'id': mobj.group('channel_id'),
  2936. })
  2937. return info
  2938. # Look for Instagram embeds
  2939. instagram_embed_url = InstagramIE._extract_embed_url(webpage)
  2940. if instagram_embed_url is not None:
  2941. return self.url_result(
  2942. self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
  2943. # Look for LiveLeak embeds
  2944. liveleak_urls = LiveLeakIE._extract_urls(webpage)
  2945. if liveleak_urls:
  2946. return self.playlist_from_matches(liveleak_urls, video_id, video_title)
  2947. # Look for 3Q SDN embeds
  2948. threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
  2949. if threeqsdn_url:
  2950. return {
  2951. '_type': 'url_transparent',
  2952. 'ie_key': ThreeQSDNIE.ie_key(),
  2953. 'url': self._proto_relative_url(threeqsdn_url),
  2954. 'title': video_title,
  2955. 'description': video_description,
  2956. 'thumbnail': video_thumbnail,
  2957. 'uploader': video_uploader,
  2958. }
  2959. # Look for VBOX7 embeds
  2960. vbox7_url = Vbox7IE._extract_url(webpage)
  2961. if vbox7_url:
  2962. return self.url_result(vbox7_url, Vbox7IE.ie_key())
  2963. # Look for DBTV embeds
  2964. dbtv_urls = DBTVIE._extract_urls(webpage)
  2965. if dbtv_urls:
  2966. return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
  2967. # Look for Videa embeds
  2968. videa_urls = VideaIE._extract_urls(webpage)
  2969. if videa_urls:
  2970. return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
  2971. # Look for 20 minuten embeds
  2972. twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
  2973. if twentymin_urls:
  2974. return self.playlist_from_matches(
  2975. twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
  2976. # Look for VideoPress embeds
  2977. videopress_urls = VideoPressIE._extract_urls(webpage)
  2978. if videopress_urls:
  2979. return self.playlist_from_matches(
  2980. videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
  2981. # Look for Rutube embeds
  2982. rutube_urls = RutubeIE._extract_urls(webpage)
  2983. if rutube_urls:
  2984. return self.playlist_from_matches(
  2985. rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
  2986. # Look for WashingtonPost embeds
  2987. wapo_urls = WashingtonPostIE._extract_urls(webpage)
  2988. if wapo_urls:
  2989. return self.playlist_from_matches(
  2990. wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
  2991. # Look for Mediaset embeds
  2992. mediaset_urls = MediasetIE._extract_urls(self, webpage)
  2993. if mediaset_urls:
  2994. return self.playlist_from_matches(
  2995. mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
  2996. # Look for JOJ.sk embeds
  2997. joj_urls = JojIE._extract_urls(webpage)
  2998. if joj_urls:
  2999. return self.playlist_from_matches(
  3000. joj_urls, video_id, video_title, ie=JojIE.ie_key())
  3001. # Look for megaphone.fm embeds
  3002. mpfn_urls = MegaphoneIE._extract_urls(webpage)
  3003. if mpfn_urls:
  3004. return self.playlist_from_matches(
  3005. mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
  3006. # Look for vzaar embeds
  3007. vzaar_urls = VzaarIE._extract_urls(webpage)
  3008. if vzaar_urls:
  3009. return self.playlist_from_matches(
  3010. vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
  3011. channel9_urls = Channel9IE._extract_urls(webpage)
  3012. if channel9_urls:
  3013. return self.playlist_from_matches(
  3014. channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
  3015. vshare_urls = VShareIE._extract_urls(webpage)
  3016. if vshare_urls:
  3017. return self.playlist_from_matches(
  3018. vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
  3019. # Look for Mediasite embeds
  3020. mediasite_urls = MediasiteIE._extract_urls(webpage)
  3021. if mediasite_urls:
  3022. entries = [
  3023. self.url_result(smuggle_url(
  3024. compat_urlparse.urljoin(url, mediasite_url),
  3025. {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
  3026. for mediasite_url in mediasite_urls]
  3027. return self.playlist_result(entries, video_id, video_title)
  3028. springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
  3029. if springboardplatform_urls:
  3030. return self.playlist_from_matches(
  3031. springboardplatform_urls, video_id, video_title,
  3032. ie=SpringboardPlatformIE.ie_key())
  3033. yapfiles_urls = YapFilesIE._extract_urls(webpage)
  3034. if yapfiles_urls:
  3035. return self.playlist_from_matches(
  3036. yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
  3037. vice_urls = ViceIE._extract_urls(webpage)
  3038. if vice_urls:
  3039. return self.playlist_from_matches(
  3040. vice_urls, video_id, video_title, ie=ViceIE.ie_key())
  3041. xfileshare_urls = XFileShareIE._extract_urls(webpage)
  3042. if xfileshare_urls:
  3043. return self.playlist_from_matches(
  3044. xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
  3045. cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
  3046. if cloudflarestream_urls:
  3047. return self.playlist_from_matches(
  3048. cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
  3049. peertube_urls = PeerTubeIE._extract_urls(webpage, url)
  3050. if peertube_urls:
  3051. return self.playlist_from_matches(
  3052. peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
  3053. indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
  3054. if indavideo_urls:
  3055. return self.playlist_from_matches(
  3056. indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
  3057. apa_urls = APAIE._extract_urls(webpage)
  3058. if apa_urls:
  3059. return self.playlist_from_matches(
  3060. apa_urls, video_id, video_title, ie=APAIE.ie_key())
  3061. foxnews_urls = FoxNewsIE._extract_urls(webpage)
  3062. if foxnews_urls:
  3063. return self.playlist_from_matches(
  3064. foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
  3065. sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
  3066. r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
  3067. webpage)]
  3068. if sharevideos_urls:
  3069. return self.playlist_from_matches(
  3070. sharevideos_urls, video_id, video_title)
  3071. viqeo_urls = ViqeoIE._extract_urls(webpage)
  3072. if viqeo_urls:
  3073. return self.playlist_from_matches(
  3074. viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
  3075. expressen_urls = ExpressenIE._extract_urls(webpage)
  3076. if expressen_urls:
  3077. return self.playlist_from_matches(
  3078. expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
  3079. zype_urls = ZypeIE._extract_urls(webpage)
  3080. if zype_urls:
  3081. return self.playlist_from_matches(
  3082. zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
  3083. # Look for HTML5 media
  3084. entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
  3085. if entries:
  3086. if len(entries) == 1:
  3087. entries[0].update({
  3088. 'id': video_id,
  3089. 'title': video_title,
  3090. })
  3091. else:
  3092. for num, entry in enumerate(entries, start=1):
  3093. entry.update({
  3094. 'id': '%s-%s' % (video_id, num),
  3095. 'title': '%s (%d)' % (video_title, num),
  3096. })
  3097. for entry in entries:
  3098. self._sort_formats(entry['formats'])
  3099. return self.playlist_result(entries, video_id, video_title)
  3100. jwplayer_data = self._find_jwplayer_data(
  3101. webpage, video_id, transform_source=js_to_json)
  3102. if jwplayer_data:
  3103. try:
  3104. info = self._parse_jwplayer_data(
  3105. jwplayer_data, video_id, require_title=False, base_url=url)
  3106. return merge_dicts(info, info_dict)
  3107. except ExtractorError:
  3108. # See https://github.com/ytdl-org/youtube-dl/pull/16735
  3109. pass
  3110. # Video.js embed
  3111. mobj = re.search(
  3112. r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
  3113. webpage)
  3114. if mobj is not None:
  3115. sources = self._parse_json(
  3116. mobj.group(1), video_id, transform_source=js_to_json,
  3117. fatal=False) or []
  3118. if not isinstance(sources, list):
  3119. sources = [sources]
  3120. formats = []
  3121. for source in sources:
  3122. src = source.get('src')
  3123. if not src or not isinstance(src, compat_str):
  3124. continue
  3125. src = compat_urlparse.urljoin(url, src)
  3126. src_type = source.get('type')
  3127. if isinstance(src_type, compat_str):
  3128. src_type = src_type.lower()
  3129. ext = determine_ext(src).lower()
  3130. if src_type == 'video/youtube':
  3131. return self.url_result(src, YoutubeIE.ie_key())
  3132. if src_type == 'application/dash+xml' or ext == 'mpd':
  3133. formats.extend(self._extract_mpd_formats(
  3134. src, video_id, mpd_id='dash', fatal=False))
  3135. elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
  3136. formats.extend(self._extract_m3u8_formats(
  3137. src, video_id, 'mp4', entry_protocol='m3u8_native',
  3138. m3u8_id='hls', fatal=False))
  3139. else:
  3140. formats.append({
  3141. 'url': src,
  3142. 'ext': (mimetype2ext(src_type)
  3143. or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
  3144. })
  3145. if formats:
  3146. self._sort_formats(formats)
  3147. info_dict['formats'] = formats
  3148. return info_dict
  3149. # Looking for http://schema.org/VideoObject
  3150. json_ld = self._search_json_ld(
  3151. webpage, video_id, default={}, expected_type='VideoObject')
  3152. if json_ld.get('url'):
  3153. return merge_dicts(json_ld, info_dict)
  3154. def check_video(vurl):
  3155. if YoutubeIE.suitable(vurl):
  3156. return True
  3157. if RtmpIE.suitable(vurl):
  3158. return True
  3159. vpath = compat_urlparse.urlparse(vurl).path
  3160. vext = determine_ext(vpath)
  3161. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
  3162. def filter_video(urls):
  3163. return list(filter(check_video, urls))
  3164. # Start with something easy: JW Player in SWFObject
  3165. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  3166. if not found:
  3167. # Look for gorilla-vid style embedding
  3168. found = filter_video(re.findall(r'''(?sx)
  3169. (?:
  3170. jw_plugins|
  3171. JWPlayerOptions|
  3172. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  3173. )
  3174. .*?
  3175. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  3176. if not found:
  3177. # Broaden the search a little bit
  3178. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  3179. if not found:
  3180. # Broaden the findall a little bit: JWPlayer JS loader
  3181. found = filter_video(re.findall(
  3182. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  3183. if not found:
  3184. # Flow player
  3185. found = filter_video(re.findall(r'''(?xs)
  3186. flowplayer\("[^"]+",\s*
  3187. \{[^}]+?\}\s*,
  3188. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  3189. ["']?url["']?\s*:\s*["']([^"']+)["']
  3190. ''', webpage))
  3191. if not found:
  3192. # Cinerama player
  3193. found = re.findall(
  3194. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  3195. if not found:
  3196. # Try to find twitter cards info
  3197. # twitter:player:stream should be checked before twitter:player since
  3198. # it is expected to contain a raw stream (see
  3199. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  3200. found = filter_video(re.findall(
  3201. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  3202. if not found:
  3203. # We look for Open Graph info:
  3204. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  3205. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  3206. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  3207. if m_video_type is not None:
  3208. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  3209. if not found:
  3210. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  3211. found = re.search(
  3212. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  3213. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  3214. webpage)
  3215. if not found:
  3216. # Look also in Refresh HTTP header
  3217. refresh_header = head_response.headers.get('Refresh')
  3218. if refresh_header:
  3219. # In python 2 response HTTP headers are bytestrings
  3220. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  3221. refresh_header = refresh_header.decode('iso-8859-1')
  3222. found = re.search(REDIRECT_REGEX, refresh_header)
  3223. if found:
  3224. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  3225. if new_url != url:
  3226. self.report_following_redirect(new_url)
  3227. return {
  3228. '_type': 'url',
  3229. 'url': new_url,
  3230. }
  3231. else:
  3232. found = None
  3233. if not found:
  3234. # twitter:player is a https URL to iframe player that may or may not
  3235. # be supported by youtube-dl thus this is checked the very last (see
  3236. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  3237. embed_url = self._html_search_meta('twitter:player', webpage, default=None)
  3238. if embed_url and embed_url != url:
  3239. return self.url_result(embed_url)
  3240. if not found:
  3241. raise UnsupportedError(url)
  3242. entries = []
  3243. for video_url in orderedSet(found):
  3244. video_url = unescapeHTML(video_url)
  3245. video_url = video_url.replace('\\/', '/')
  3246. video_url = compat_urlparse.urljoin(url, video_url)
  3247. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  3248. # Sometimes, jwplayer extraction will result in a YouTube URL
  3249. if YoutubeIE.suitable(video_url):
  3250. entries.append(self.url_result(video_url, 'Youtube'))
  3251. continue
  3252. # here's a fun little line of code for you:
  3253. video_id = os.path.splitext(video_id)[0]
  3254. entry_info_dict = {
  3255. 'id': video_id,
  3256. 'uploader': video_uploader,
  3257. 'title': video_title,
  3258. 'age_limit': age_limit,
  3259. }
  3260. if RtmpIE.suitable(video_url):
  3261. entry_info_dict.update({
  3262. '_type': 'url_transparent',
  3263. 'ie_key': RtmpIE.ie_key(),
  3264. 'url': video_url,
  3265. })
  3266. entries.append(entry_info_dict)
  3267. continue
  3268. ext = determine_ext(video_url)
  3269. if ext == 'smil':
  3270. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  3271. elif ext == 'xspf':
  3272. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  3273. elif ext == 'm3u8':
  3274. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  3275. elif ext == 'mpd':
  3276. entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
  3277. elif ext == 'f4m':
  3278. entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
  3279. elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
  3280. # Just matching .ism/manifest is not enough to be reliably sure
  3281. # whether it's actually an ISM manifest or some other streaming
  3282. # manifest since there are various streaming URL formats
  3283. # possible (see [1]) as well as some other shenanigans like
  3284. # .smil/manifest URLs that actually serve an ISM (see [2]) and
  3285. # so on.
  3286. # Thus the most reasonable way to solve this is to delegate
  3287. # to generic extractor in order to look into the contents of
  3288. # the manifest itself.
  3289. # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
  3290. # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
  3291. entry_info_dict = self.url_result(
  3292. smuggle_url(video_url, {'to_generic': True}),
  3293. GenericIE.ie_key())
  3294. else:
  3295. entry_info_dict['url'] = video_url
  3296. if entry_info_dict.get('formats'):
  3297. self._sort_formats(entry_info_dict['formats'])
  3298. entries.append(entry_info_dict)
  3299. if len(entries) == 1:
  3300. return entries[0]
  3301. else:
  3302. for num, e in enumerate(entries, start=1):
  3303. # 'url' results don't have a title
  3304. if e.get('title') is not None:
  3305. e['title'] = '%s (%d)' % (e['title'], num)
  3306. return {
  3307. '_type': 'playlist',
  3308. 'entries': entries,
  3309. }