generic.py 130 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874287528762877287828792880288128822883288428852886288728882889289028912892289328942895289628972898289929002901290229032904290529062907290829092910291129122913291429152916291729182919292029212922292329242925292629272928292929302931293229332934293529362937293829392940294129422943294429452946294729482949295029512952295329542955295629572958295929602961296229632964296529662967296829692970297129722973297429752976297729782979298029812982298329842985298629872988298929902991299229932994299529962997299829993000300130023003300430053006300730083009301030113012301330143015301630173018301930203021302230233024302530263027302830293030303130323033303430353036303730383039304030413042304330443045304630473048304930503051305230533054305530563057305830593060306130623063306430653066306730683069307030713072307330743075307630773078307930803081308230833084308530863087308830893090309130923093309430953096309730983099310031013102310331043105310631073108310931103111311231133114311531163117311831193120312131223123312431253126312731283129313031313132313331343135313631373138313931403141314231433144314531463147314831493150315131523153315431553156315731583159316031613162316331643165316631673168316931703171317231733174317531763177317831793180318131823183318431853186318731883189319031913192319331943195319631973198319932003201320232033204
  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. is_html,
  21. js_to_json,
  22. KNOWN_EXTENSIONS,
  23. mimetype2ext,
  24. orderedSet,
  25. sanitized_Request,
  26. smuggle_url,
  27. unescapeHTML,
  28. unified_strdate,
  29. unsmuggle_url,
  30. UnsupportedError,
  31. xpath_text,
  32. )
  33. from .commonprotocols import RtmpIE
  34. from .brightcove import (
  35. BrightcoveLegacyIE,
  36. BrightcoveNewIE,
  37. )
  38. from .nexx import (
  39. NexxIE,
  40. NexxEmbedIE,
  41. )
  42. from .nbc import NBCSportsVPlayerIE
  43. from .ooyala import OoyalaIE
  44. from .rutv import RUTVIE
  45. from .tvc import TVCIE
  46. from .sportbox import SportBoxEmbedIE
  47. from .smotri import SmotriIE
  48. from .myvi import MyviIE
  49. from .condenast import CondeNastIE
  50. from .udn import UDNEmbedIE
  51. from .senateisvp import SenateISVPIE
  52. from .svt import SVTIE
  53. from .pornhub import PornHubIE
  54. from .xhamster import XHamsterEmbedIE
  55. from .tnaflix import TNAFlixNetworkEmbedIE
  56. from .drtuber import DrTuberIE
  57. from .redtube import RedTubeIE
  58. from .vimeo import VimeoIE
  59. from .dailymotion import DailymotionIE
  60. from .dailymail import DailyMailIE
  61. from .onionstudios import OnionStudiosIE
  62. from .viewlift import ViewLiftEmbedIE
  63. from .mtv import MTVServicesEmbeddedIE
  64. from .pladform import PladformIE
  65. from .videomore import VideomoreIE
  66. from .webcaster import WebcasterFeedIE
  67. from .googledrive import GoogleDriveIE
  68. from .jwplatform import JWPlatformIE
  69. from .digiteka import DigitekaIE
  70. from .arkena import ArkenaIE
  71. from .instagram import InstagramIE
  72. from .liveleak import LiveLeakIE
  73. from .threeqsdn import ThreeQSDNIE
  74. from .theplatform import ThePlatformIE
  75. from .vessel import VesselIE
  76. from .kaltura import KalturaIE
  77. from .eagleplatform import EaglePlatformIE
  78. from .facebook import FacebookIE
  79. from .soundcloud import SoundcloudIE
  80. from .tunein import TuneInBaseIE
  81. from .vbox7 import Vbox7IE
  82. from .dbtv import DBTVIE
  83. from .piksel import PikselIE
  84. from .videa import VideaIE
  85. from .twentymin import TwentyMinutenIE
  86. from .ustream import UstreamIE
  87. from .openload import OpenloadIE
  88. from .videopress import VideoPressIE
  89. from .rutube import RutubeIE
  90. from .limelight import LimelightBaseIE
  91. from .anvato import AnvatoIE
  92. from .washingtonpost import WashingtonPostIE
  93. from .wistia import WistiaIE
  94. from .mediaset import MediasetIE
  95. from .joj import JojIE
  96. from .megaphone import MegaphoneIE
  97. from .vzaar import VzaarIE
  98. from .channel9 import Channel9IE
  99. from .vshare import VShareIE
  100. from .mediasite import MediasiteIE
  101. from .springboardplatform import SpringboardPlatformIE
  102. class GenericIE(InfoExtractor):
  103. IE_DESC = 'Generic downloader that works on some sites'
  104. _VALID_URL = r'.*'
  105. IE_NAME = 'generic'
  106. _TESTS = [
  107. # Direct link to a video
  108. {
  109. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  110. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  111. 'info_dict': {
  112. 'id': 'trailer',
  113. 'ext': 'mp4',
  114. 'title': 'trailer',
  115. 'upload_date': '20100513',
  116. }
  117. },
  118. # Direct link to media delivered compressed (until Accept-Encoding is *)
  119. {
  120. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  121. 'md5': '128c42e68b13950268b648275386fc74',
  122. 'info_dict': {
  123. 'id': 'FictionJunction-Parallel_Hearts',
  124. 'ext': 'flac',
  125. 'title': 'FictionJunction-Parallel_Hearts',
  126. 'upload_date': '20140522',
  127. },
  128. 'expected_warnings': [
  129. 'URL could be a direct video link, returning it as such.'
  130. ],
  131. 'skip': 'URL invalid',
  132. },
  133. # Direct download with broken HEAD
  134. {
  135. 'url': 'http://ai-radio.org:8000/radio.opus',
  136. 'info_dict': {
  137. 'id': 'radio',
  138. 'ext': 'opus',
  139. 'title': 'radio',
  140. },
  141. 'params': {
  142. 'skip_download': True, # infinite live stream
  143. },
  144. 'expected_warnings': [
  145. r'501.*Not Implemented',
  146. r'400.*Bad Request',
  147. ],
  148. },
  149. # Direct link with incorrect MIME type
  150. {
  151. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  152. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  153. 'info_dict': {
  154. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  155. 'id': '5_Lennart_Poettering_-_Systemd',
  156. 'ext': 'webm',
  157. 'title': '5_Lennart_Poettering_-_Systemd',
  158. 'upload_date': '20141120',
  159. },
  160. 'expected_warnings': [
  161. 'URL could be a direct video link, returning it as such.'
  162. ]
  163. },
  164. # RSS feed
  165. {
  166. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  167. 'info_dict': {
  168. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  169. 'title': 'Zero Punctuation',
  170. 'description': 're:.*groundbreaking video review series.*'
  171. },
  172. 'playlist_mincount': 11,
  173. },
  174. # RSS feed with enclosure
  175. {
  176. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  177. 'info_dict': {
  178. 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  179. 'ext': 'm4v',
  180. 'upload_date': '20150228',
  181. 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  182. }
  183. },
  184. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  185. {
  186. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  187. 'info_dict': {
  188. 'id': 'smil',
  189. 'ext': 'mp4',
  190. 'title': 'Automatics, robotics and biocybernetics',
  191. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  192. 'upload_date': '20130627',
  193. 'formats': 'mincount:16',
  194. 'subtitles': 'mincount:1',
  195. },
  196. 'params': {
  197. 'force_generic_extractor': True,
  198. 'skip_download': True,
  199. },
  200. },
  201. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  202. {
  203. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  204. 'info_dict': {
  205. 'id': 'hds',
  206. 'ext': 'flv',
  207. 'title': 'hds',
  208. 'formats': 'mincount:1',
  209. },
  210. 'params': {
  211. 'skip_download': True,
  212. },
  213. },
  214. # SMIL from https://www.restudy.dk/video/play/id/1637
  215. {
  216. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  217. 'info_dict': {
  218. 'id': 'video_1637',
  219. 'ext': 'flv',
  220. 'title': 'video_1637',
  221. 'formats': 'mincount:3',
  222. },
  223. 'params': {
  224. 'skip_download': True,
  225. },
  226. },
  227. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  228. {
  229. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  230. 'info_dict': {
  231. 'id': 'smil-service',
  232. 'ext': 'flv',
  233. 'title': 'smil-service',
  234. 'formats': 'mincount:1',
  235. },
  236. 'params': {
  237. 'skip_download': True,
  238. },
  239. },
  240. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  241. {
  242. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  243. 'info_dict': {
  244. 'id': '4719370',
  245. 'ext': 'mp4',
  246. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  247. 'formats': 'mincount:3',
  248. },
  249. 'params': {
  250. 'skip_download': True,
  251. },
  252. },
  253. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  254. {
  255. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  256. 'info_dict': {
  257. 'id': 'mZlp2ctYIUEB',
  258. 'ext': 'mp4',
  259. 'title': 'Tikibad ontruimd wegens brand',
  260. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  261. 'thumbnail': r're:^https?://.*\.jpg$',
  262. 'duration': 33,
  263. },
  264. 'params': {
  265. 'skip_download': True,
  266. },
  267. },
  268. # MPD from http://dash-mse-test.appspot.com/media.html
  269. {
  270. 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
  271. 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
  272. 'info_dict': {
  273. 'id': 'car-20120827-manifest',
  274. 'ext': 'mp4',
  275. 'title': 'car-20120827-manifest',
  276. 'formats': 'mincount:9',
  277. 'upload_date': '20130904',
  278. },
  279. 'params': {
  280. 'format': 'bestvideo',
  281. },
  282. },
  283. # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
  284. {
  285. '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',
  286. 'info_dict': {
  287. 'id': 'content',
  288. 'ext': 'mp4',
  289. 'title': 'content',
  290. 'formats': 'mincount:8',
  291. },
  292. 'params': {
  293. # m3u8 downloads
  294. 'skip_download': True,
  295. },
  296. 'skip': 'video gone',
  297. },
  298. # m3u8 served with Content-Type: text/plain
  299. {
  300. 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
  301. 'info_dict': {
  302. 'id': 'index',
  303. 'ext': 'mp4',
  304. 'title': 'index',
  305. 'upload_date': '20140720',
  306. 'formats': 'mincount:11',
  307. },
  308. 'params': {
  309. # m3u8 downloads
  310. 'skip_download': True,
  311. },
  312. 'skip': 'video gone',
  313. },
  314. # google redirect
  315. {
  316. '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',
  317. 'info_dict': {
  318. 'id': 'cmQHVoWB5FY',
  319. 'ext': 'mp4',
  320. 'upload_date': '20130224',
  321. 'uploader_id': 'TheVerge',
  322. 'description': r're:^Chris Ziegler takes a look at the\.*',
  323. 'uploader': 'The Verge',
  324. 'title': 'First Firefox OS phones side-by-side',
  325. },
  326. 'params': {
  327. 'skip_download': False,
  328. }
  329. },
  330. {
  331. # redirect in Refresh HTTP header
  332. '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',
  333. 'info_dict': {
  334. 'id': 'pO8h3EaFRdo',
  335. 'ext': 'mp4',
  336. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  337. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  338. 'upload_date': '20150917',
  339. 'uploader_id': 'brtvofficial',
  340. 'uploader': 'Boiler Room',
  341. },
  342. 'params': {
  343. 'skip_download': False,
  344. },
  345. },
  346. {
  347. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  348. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  349. 'info_dict': {
  350. 'id': '13601338388002',
  351. 'ext': 'mp4',
  352. 'uploader': 'www.hodiho.fr',
  353. 'title': 'R\u00e9gis plante sa Jeep',
  354. }
  355. },
  356. # bandcamp page with custom domain
  357. {
  358. 'add_ie': ['Bandcamp'],
  359. 'url': 'http://bronyrock.com/track/the-pony-mash',
  360. 'info_dict': {
  361. 'id': '3235767654',
  362. 'ext': 'mp3',
  363. 'title': 'The Pony Mash',
  364. 'uploader': 'M_Pallante',
  365. },
  366. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  367. },
  368. {
  369. # embedded brightcove video
  370. # it also tests brightcove videos that need to set the 'Referer'
  371. # in the http requests
  372. 'add_ie': ['BrightcoveLegacy'],
  373. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  374. 'info_dict': {
  375. 'id': '2765128793001',
  376. 'ext': 'mp4',
  377. 'title': 'Le cours de bourse : l’analyse technique',
  378. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  379. 'uploader': 'BFM BUSINESS',
  380. },
  381. 'params': {
  382. 'skip_download': True,
  383. },
  384. },
  385. {
  386. # embedded with itemprop embedURL and video id spelled as `idVideo`
  387. 'add_id': ['BrightcoveLegacy'],
  388. 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
  389. 'info_dict': {
  390. 'id': '5255628253001',
  391. 'ext': 'mp4',
  392. 'title': 'md5:37c519b1128915607601e75a87995fc0',
  393. 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
  394. 'uploader': 'BFM BUSINESS',
  395. 'uploader_id': '876450612001',
  396. 'timestamp': 1482255315,
  397. 'upload_date': '20161220',
  398. },
  399. 'params': {
  400. 'skip_download': True,
  401. },
  402. },
  403. {
  404. # https://github.com/rg3/youtube-dl/issues/2253
  405. 'url': 'http://bcove.me/i6nfkrc3',
  406. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  407. 'info_dict': {
  408. 'id': '3101154703001',
  409. 'ext': 'mp4',
  410. 'title': 'Still no power',
  411. 'uploader': 'thestar.com',
  412. '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.',
  413. },
  414. 'add_ie': ['BrightcoveLegacy'],
  415. 'skip': 'video gone',
  416. },
  417. {
  418. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  419. 'md5': 'fb973ecf6e4a78a67453647444222983',
  420. 'info_dict': {
  421. 'id': '3414141473001',
  422. 'ext': 'mp4',
  423. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  424. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  425. 'uploader': 'Championat',
  426. },
  427. },
  428. {
  429. # https://github.com/rg3/youtube-dl/issues/3541
  430. 'add_ie': ['BrightcoveLegacy'],
  431. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  432. 'info_dict': {
  433. 'id': '3866516442001',
  434. 'ext': 'mp4',
  435. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  436. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  437. 'uploader': 'SBS Broadcasting',
  438. },
  439. 'skip': 'Restricted to Netherlands',
  440. 'params': {
  441. 'skip_download': True, # m3u8 download
  442. },
  443. },
  444. {
  445. # Brightcove video in <iframe>
  446. 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
  447. 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
  448. 'info_dict': {
  449. 'id': '5360463607001',
  450. 'ext': 'mp4',
  451. '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',
  452. '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。',
  453. 'uploader': 'United Nations',
  454. 'uploader_id': '1362235914001',
  455. 'timestamp': 1489593889,
  456. 'upload_date': '20170315',
  457. },
  458. 'add_ie': ['BrightcoveLegacy'],
  459. },
  460. {
  461. # Brightcove with alternative playerID key
  462. 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
  463. 'info_dict': {
  464. 'id': 'nmeth.2062_SV1',
  465. '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',
  466. },
  467. 'playlist': [{
  468. 'info_dict': {
  469. 'id': '2228375078001',
  470. 'ext': 'mp4',
  471. 'title': 'nmeth.2062-sv1',
  472. 'description': 'nmeth.2062-sv1',
  473. 'timestamp': 1363357591,
  474. 'upload_date': '20130315',
  475. 'uploader': 'Nature Publishing Group',
  476. 'uploader_id': '1964492299001',
  477. },
  478. }],
  479. },
  480. {
  481. # Brightcove with UUID in videoPlayer
  482. 'url': 'http://www8.hp.com/cn/zh/home.html',
  483. 'info_dict': {
  484. 'id': '5255815316001',
  485. 'ext': 'mp4',
  486. 'title': 'Sprocket Video - China',
  487. 'description': 'Sprocket Video - China',
  488. 'uploader': 'HP-Video Gallery',
  489. 'timestamp': 1482263210,
  490. 'upload_date': '20161220',
  491. 'uploader_id': '1107601872001',
  492. },
  493. 'params': {
  494. 'skip_download': True, # m3u8 download
  495. },
  496. 'skip': 'video rotates...weekly?',
  497. },
  498. {
  499. # Brightcove:new type [2].
  500. 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
  501. 'md5': '2b35148fcf48da41c9fb4591650784f3',
  502. 'info_dict': {
  503. 'id': '5348741021001',
  504. 'ext': 'mp4',
  505. 'upload_date': '20170306',
  506. 'uploader_id': '4191638492001',
  507. 'timestamp': 1488769918,
  508. 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
  509. },
  510. },
  511. {
  512. # Alternative brightcove <video> attributes
  513. '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/',
  514. 'info_dict': {
  515. 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
  516. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
  517. },
  518. 'playlist': [{
  519. 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
  520. 'info_dict': {
  521. 'id': '5311302538001',
  522. 'ext': 'mp4',
  523. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
  524. 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
  525. 'timestamp': 1486321708,
  526. 'upload_date': '20170205',
  527. 'uploader_id': '800000640001',
  528. },
  529. 'only_matching': True,
  530. }],
  531. },
  532. {
  533. # Brightcove with UUID in videoPlayer
  534. 'url': 'http://www8.hp.com/cn/zh/home.html',
  535. 'info_dict': {
  536. 'id': '5255815316001',
  537. 'ext': 'mp4',
  538. 'title': 'Sprocket Video - China',
  539. 'description': 'Sprocket Video - China',
  540. 'uploader': 'HP-Video Gallery',
  541. 'timestamp': 1482263210,
  542. 'upload_date': '20161220',
  543. 'uploader_id': '1107601872001',
  544. },
  545. 'params': {
  546. 'skip_download': True, # m3u8 download
  547. },
  548. },
  549. # ooyala video
  550. {
  551. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  552. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  553. 'info_dict': {
  554. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  555. 'ext': 'mp4',
  556. 'title': '2cc213299525360.mov', # that's what we get
  557. 'duration': 238.231,
  558. },
  559. 'add_ie': ['Ooyala'],
  560. },
  561. {
  562. # ooyala video embedded with http://player.ooyala.com/iframe.js
  563. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  564. 'info_dict': {
  565. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  566. 'ext': 'mp4',
  567. 'title': '"Steve Jobs: Man in the Machine" trailer',
  568. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  569. 'duration': 135.427,
  570. },
  571. 'params': {
  572. 'skip_download': True,
  573. },
  574. 'skip': 'movie expired',
  575. },
  576. # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
  577. {
  578. 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
  579. 'info_dict': {
  580. 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
  581. 'ext': 'mp4',
  582. 'title': 'Steampunk Fest Comes to Honesdale',
  583. 'duration': 43.276,
  584. },
  585. 'params': {
  586. 'skip_download': True,
  587. }
  588. },
  589. # embed.ly video
  590. {
  591. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  592. 'info_dict': {
  593. 'id': '9ODmcdjQcHQ',
  594. 'ext': 'mp4',
  595. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  596. 'upload_date': '20140225',
  597. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  598. 'uploader': 'Tested',
  599. 'uploader_id': 'testedcom',
  600. },
  601. # No need to test YoutubeIE here
  602. 'params': {
  603. 'skip_download': True,
  604. },
  605. },
  606. # funnyordie embed
  607. {
  608. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  609. 'info_dict': {
  610. 'id': '18e820ec3f',
  611. 'ext': 'mp4',
  612. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  613. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  614. },
  615. # HEAD requests lead to endless 301, while GET is OK
  616. 'expected_warnings': ['301'],
  617. },
  618. # RUTV embed
  619. {
  620. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  621. 'info_dict': {
  622. 'id': '776940',
  623. 'ext': 'mp4',
  624. 'title': 'Охотское море стало целиком российским',
  625. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  626. },
  627. 'params': {
  628. # m3u8 download
  629. 'skip_download': True,
  630. },
  631. },
  632. # TVC embed
  633. {
  634. '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/',
  635. 'info_dict': {
  636. 'id': '55304',
  637. 'ext': 'mp4',
  638. 'title': 'Дошкольное воспитание',
  639. },
  640. },
  641. # SportBox embed
  642. {
  643. 'url': 'http://www.vestifinance.ru/articles/25753',
  644. 'info_dict': {
  645. 'id': '25753',
  646. 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  647. },
  648. 'playlist': [{
  649. 'info_dict': {
  650. 'id': '370908',
  651. 'title': 'Госзаказ. День 3',
  652. 'ext': 'mp4',
  653. }
  654. }, {
  655. 'info_dict': {
  656. 'id': '370905',
  657. 'title': 'Госзаказ. День 2',
  658. 'ext': 'mp4',
  659. }
  660. }, {
  661. 'info_dict': {
  662. 'id': '370902',
  663. 'title': 'Госзаказ. День 1',
  664. 'ext': 'mp4',
  665. }
  666. }],
  667. 'params': {
  668. # m3u8 download
  669. 'skip_download': True,
  670. },
  671. },
  672. # Myvi.ru embed
  673. {
  674. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  675. 'info_dict': {
  676. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  677. 'ext': 'mp4',
  678. 'title': 'Ужастики, русский трейлер (2015)',
  679. 'thumbnail': r're:^https?://.*\.jpg$',
  680. 'duration': 153,
  681. }
  682. },
  683. # XHamster embed
  684. {
  685. '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',
  686. 'info_dict': {
  687. 'id': 'showthread',
  688. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  689. },
  690. 'playlist_mincount': 7,
  691. # This forum does not allow <iframe> syntaxes anymore
  692. # Now HTML tags are displayed as-is
  693. 'skip': 'No videos on this page',
  694. },
  695. # Embedded TED video
  696. {
  697. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  698. 'md5': '65fdff94098e4a607385a60c5177c638',
  699. 'info_dict': {
  700. 'id': '1969',
  701. 'ext': 'mp4',
  702. 'title': 'Hidden miracles of the natural world',
  703. 'uploader': 'Louie Schwartzberg',
  704. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  705. }
  706. },
  707. # nowvideo embed hidden behind percent encoding
  708. {
  709. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  710. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  711. 'info_dict': {
  712. 'id': '06e53103ca9aa',
  713. 'ext': 'flv',
  714. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  715. 'description': 'No description',
  716. },
  717. },
  718. # arte embed
  719. {
  720. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  721. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  722. 'info_dict': {
  723. 'id': '048195-004_PLUS7-F',
  724. 'ext': 'flv',
  725. 'title': 'X:enius',
  726. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  727. 'upload_date': '20140320',
  728. },
  729. 'params': {
  730. 'skip_download': 'Requires rtmpdump'
  731. },
  732. 'skip': 'video gone',
  733. },
  734. # francetv embed
  735. {
  736. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  737. 'info_dict': {
  738. 'id': 'EV_30231',
  739. 'ext': 'mp4',
  740. 'title': 'Alcaline, le concert avec Calogero',
  741. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  742. 'upload_date': '20150226',
  743. 'timestamp': 1424989860,
  744. 'duration': 5400,
  745. },
  746. 'params': {
  747. # m3u8 downloads
  748. 'skip_download': True,
  749. },
  750. 'expected_warnings': [
  751. 'Forbidden'
  752. ]
  753. },
  754. # Condé Nast embed
  755. {
  756. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  757. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  758. 'info_dict': {
  759. 'id': '53501be369702d3275860000',
  760. 'ext': 'mp4',
  761. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  762. }
  763. },
  764. # Dailymotion embed
  765. {
  766. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  767. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  768. 'info_dict': {
  769. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  770. 'ext': 'mp4',
  771. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  772. 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
  773. 'uploader': 'Spi0n',
  774. 'uploader_id': 'xgditw',
  775. 'upload_date': '20140425',
  776. 'timestamp': 1398441542,
  777. },
  778. 'add_ie': ['Dailymotion'],
  779. },
  780. # DailyMail embed
  781. {
  782. 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
  783. 'info_dict': {
  784. 'id': '1495629',
  785. 'ext': 'mp4',
  786. 'title': 'Care worker punches elderly dementia patient in head 11 times',
  787. 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
  788. },
  789. 'add_ie': ['DailyMail'],
  790. 'params': {
  791. 'skip_download': True,
  792. },
  793. },
  794. # YouTube embed
  795. {
  796. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  797. 'info_dict': {
  798. 'id': 'FXRb4ykk4S0',
  799. 'ext': 'mp4',
  800. 'title': 'The NBL Auction 2014',
  801. 'uploader': 'BADMINTON England',
  802. 'uploader_id': 'BADMINTONEvents',
  803. 'upload_date': '20140603',
  804. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  805. },
  806. 'add_ie': ['Youtube'],
  807. 'params': {
  808. 'skip_download': True,
  809. }
  810. },
  811. # MTVSercices embed
  812. {
  813. 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
  814. 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
  815. 'info_dict': {
  816. 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
  817. 'ext': 'mp4',
  818. 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
  819. 'description': 'Two valets share their love for movie star Liam Neesons.',
  820. 'timestamp': 1349922600,
  821. 'upload_date': '20121011',
  822. },
  823. },
  824. # YouTube embed via <data-embed-url="">
  825. {
  826. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  827. 'info_dict': {
  828. 'id': '4vAffPZIT44',
  829. 'ext': 'mp4',
  830. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  831. 'uploader': 'Gameloft',
  832. 'uploader_id': 'gameloft',
  833. 'upload_date': '20140828',
  834. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  835. },
  836. 'params': {
  837. 'skip_download': True,
  838. }
  839. },
  840. # YouTube <object> embed
  841. {
  842. 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
  843. 'md5': '516718101ec834f74318df76259fb3cc',
  844. 'info_dict': {
  845. 'id': 'msN87y-iEx0',
  846. 'ext': 'webm',
  847. 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
  848. 'upload_date': '20080526',
  849. 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
  850. 'uploader': 'Christopher Sykes',
  851. 'uploader_id': 'ChristopherJSykes',
  852. },
  853. 'add_ie': ['Youtube'],
  854. },
  855. # Camtasia studio
  856. {
  857. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  858. 'playlist': [{
  859. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  860. 'info_dict': {
  861. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  862. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  863. 'ext': 'flv',
  864. 'duration': 2235.90,
  865. }
  866. }, {
  867. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  868. 'info_dict': {
  869. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  870. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  871. 'ext': 'flv',
  872. 'duration': 2235.93,
  873. }
  874. }],
  875. 'info_dict': {
  876. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  877. }
  878. },
  879. # Flowplayer
  880. {
  881. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  882. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  883. 'info_dict': {
  884. 'id': '5123ea6d5e5a7',
  885. 'ext': 'mp4',
  886. 'age_limit': 18,
  887. 'uploader': 'www.handjobhub.com',
  888. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  889. }
  890. },
  891. # Multiple brightcove videos
  892. # https://github.com/rg3/youtube-dl/issues/2283
  893. {
  894. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  895. 'info_dict': {
  896. 'id': 'always-never',
  897. 'title': 'Always / Never - The New Yorker',
  898. },
  899. 'playlist_count': 3,
  900. 'params': {
  901. 'extract_flat': False,
  902. 'skip_download': True,
  903. }
  904. },
  905. # MLB embed
  906. {
  907. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  908. 'md5': '96f09a37e44da40dd083e12d9a683327',
  909. 'info_dict': {
  910. 'id': '33322633',
  911. 'ext': 'mp4',
  912. 'title': 'Ump changes call to ball',
  913. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  914. 'duration': 48,
  915. 'timestamp': 1401537900,
  916. 'upload_date': '20140531',
  917. 'thumbnail': r're:^https?://.*\.jpg$',
  918. },
  919. },
  920. # Wistia embed
  921. {
  922. 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  923. 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
  924. 'info_dict': {
  925. 'id': '6e2wtrbdaf',
  926. 'ext': 'mov',
  927. 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
  928. 'description': 'a Paywall Videos video from Remilon',
  929. 'duration': 644.072,
  930. 'uploader': 'study.com',
  931. 'timestamp': 1459678540,
  932. 'upload_date': '20160403',
  933. 'filesize': 24687186,
  934. },
  935. },
  936. {
  937. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  938. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  939. 'info_dict': {
  940. 'id': 'uxjb0lwrcz',
  941. 'ext': 'mp4',
  942. 'title': 'Conversation about Hexagonal Rails Part 1',
  943. 'description': 'a Martin Fowler video from ThoughtWorks',
  944. 'duration': 1715.0,
  945. 'uploader': 'thoughtworks.wistia.com',
  946. 'timestamp': 1401832161,
  947. 'upload_date': '20140603',
  948. },
  949. },
  950. # Wistia standard embed (async)
  951. {
  952. 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
  953. 'info_dict': {
  954. 'id': '807fafadvk',
  955. 'ext': 'mp4',
  956. 'title': 'Drip Brennan Dunn Workshop',
  957. 'description': 'a JV Webinars video from getdrip-1',
  958. 'duration': 4986.95,
  959. 'timestamp': 1463607249,
  960. 'upload_date': '20160518',
  961. },
  962. 'params': {
  963. 'skip_download': True,
  964. }
  965. },
  966. # Soundcloud embed
  967. {
  968. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  969. 'info_dict': {
  970. 'id': '174391317',
  971. 'ext': 'mp3',
  972. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  973. 'uploader': 'Sophos Security',
  974. 'title': 'Chet Chat 171 - Oct 29, 2014',
  975. 'upload_date': '20141029',
  976. }
  977. },
  978. # Soundcloud multiple embeds
  979. {
  980. 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
  981. 'info_dict': {
  982. 'id': '52809',
  983. 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
  984. },
  985. 'playlist_mincount': 7,
  986. },
  987. # TuneIn station embed
  988. {
  989. 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
  990. 'info_dict': {
  991. 'id': '204146',
  992. 'ext': 'mp3',
  993. 'title': 'CNRV',
  994. 'location': 'Paris, France',
  995. 'is_live': True,
  996. },
  997. 'params': {
  998. # Live stream
  999. 'skip_download': True,
  1000. },
  1001. },
  1002. # Livestream embed
  1003. {
  1004. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  1005. 'info_dict': {
  1006. 'id': '67864563',
  1007. 'ext': 'flv',
  1008. 'upload_date': '20141112',
  1009. 'title': 'Rosetta #CometLanding webcast HL 10',
  1010. }
  1011. },
  1012. # Another Livestream embed, without 'new.' in URL
  1013. {
  1014. 'url': 'https://www.freespeech.org/',
  1015. 'info_dict': {
  1016. 'id': '123537347',
  1017. 'ext': 'mp4',
  1018. 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  1019. },
  1020. 'params': {
  1021. # Live stream
  1022. 'skip_download': True,
  1023. },
  1024. },
  1025. # LazyYT
  1026. {
  1027. 'url': 'https://skiplagged.com/',
  1028. 'info_dict': {
  1029. 'id': 'skiplagged',
  1030. 'title': 'Skiplagged: The smart way to find cheap flights',
  1031. },
  1032. 'playlist_mincount': 1,
  1033. 'add_ie': ['Youtube'],
  1034. },
  1035. # Cinchcast embed
  1036. {
  1037. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  1038. 'info_dict': {
  1039. 'id': '7141703',
  1040. 'ext': 'mp3',
  1041. 'upload_date': '20141126',
  1042. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  1043. }
  1044. },
  1045. # Cinerama player
  1046. {
  1047. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  1048. 'info_dict': {
  1049. 'id': '730m_DandD_1901_512k',
  1050. 'ext': 'mp4',
  1051. 'uploader': 'www.abc.net.au',
  1052. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  1053. }
  1054. },
  1055. # embedded viddler video
  1056. {
  1057. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  1058. 'info_dict': {
  1059. 'id': '4d03aad9',
  1060. 'ext': 'mp4',
  1061. 'uploader': 'deadspin',
  1062. 'title': 'WALL-TO-GORTAT',
  1063. 'timestamp': 1422285291,
  1064. 'upload_date': '20150126',
  1065. },
  1066. 'add_ie': ['Viddler'],
  1067. },
  1068. # Libsyn embed
  1069. {
  1070. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  1071. 'info_dict': {
  1072. 'id': '3377616',
  1073. 'ext': 'mp3',
  1074. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  1075. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  1076. 'upload_date': '20150220',
  1077. },
  1078. 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
  1079. },
  1080. # jwplayer YouTube
  1081. {
  1082. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  1083. 'info_dict': {
  1084. 'id': 'Mrj4DVp2zeA',
  1085. 'ext': 'mp4',
  1086. 'upload_date': '20150212',
  1087. 'uploader': 'The National Archives UK',
  1088. 'description': 'md5:8078af856dca76edc42910b61273dbbf',
  1089. 'uploader_id': 'NationalArchives08',
  1090. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  1091. },
  1092. },
  1093. # jwplayer rtmp
  1094. {
  1095. 'url': 'http://www.suffolk.edu/sjc/live.php',
  1096. 'info_dict': {
  1097. 'id': 'live',
  1098. 'ext': 'flv',
  1099. 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
  1100. 'uploader': 'www.suffolk.edu',
  1101. },
  1102. 'params': {
  1103. 'skip_download': True,
  1104. },
  1105. 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
  1106. },
  1107. # Complex jwplayer
  1108. {
  1109. 'url': 'http://www.indiedb.com/games/king-machine/videos',
  1110. 'info_dict': {
  1111. 'id': 'videos',
  1112. 'ext': 'mp4',
  1113. 'title': 'king machine trailer 1',
  1114. 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
  1115. 'thumbnail': r're:^https?://.*\.jpg$',
  1116. },
  1117. },
  1118. {
  1119. # JWPlayer config passed as variable
  1120. 'url': 'http://www.txxx.com/videos/3326530/ariele/',
  1121. 'info_dict': {
  1122. 'id': '3326530_hq',
  1123. 'ext': 'mp4',
  1124. 'title': 'ARIELE | Tube Cup',
  1125. 'uploader': 'www.txxx.com',
  1126. 'age_limit': 18,
  1127. },
  1128. 'params': {
  1129. 'skip_download': True,
  1130. }
  1131. },
  1132. {
  1133. # JWPlatform iframe
  1134. 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
  1135. 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
  1136. 'info_dict': {
  1137. 'id': 'O0c5JcKT',
  1138. 'ext': 'mp4',
  1139. 'upload_date': '20171122',
  1140. 'timestamp': 1511366290,
  1141. 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
  1142. },
  1143. 'add_ie': [JWPlatformIE.ie_key()],
  1144. },
  1145. {
  1146. # Video.js embed, multiple formats
  1147. 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
  1148. 'info_dict': {
  1149. 'id': 'yygqldloqIk',
  1150. 'ext': 'mp4',
  1151. 'title': 'SolidWorks. Урок 6 Настройка чертежа',
  1152. 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
  1153. 'upload_date': '20130314',
  1154. 'uploader': 'PROстое3D',
  1155. 'uploader_id': 'PROstoe3D',
  1156. },
  1157. 'params': {
  1158. 'skip_download': True,
  1159. },
  1160. },
  1161. {
  1162. # Video.js embed, single format
  1163. 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
  1164. 'info_dict': {
  1165. 'id': 'watch',
  1166. 'ext': 'mp4',
  1167. 'title': 'Step 1 - Good Foundation',
  1168. 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
  1169. },
  1170. 'params': {
  1171. 'skip_download': True,
  1172. },
  1173. },
  1174. # rtl.nl embed
  1175. {
  1176. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  1177. 'playlist_mincount': 5,
  1178. 'info_dict': {
  1179. 'id': 'aanslagen-kopenhagen',
  1180. 'title': 'Aanslagen Kopenhagen',
  1181. }
  1182. },
  1183. # Zapiks embed
  1184. {
  1185. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  1186. 'info_dict': {
  1187. 'id': '118046',
  1188. 'ext': 'mp4',
  1189. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  1190. }
  1191. },
  1192. # Kaltura embed (different embed code)
  1193. {
  1194. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  1195. 'info_dict': {
  1196. 'id': '1_a52wc67y',
  1197. 'ext': 'flv',
  1198. 'upload_date': '20150127',
  1199. 'uploader_id': 'PremierMedia',
  1200. 'timestamp': int,
  1201. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  1202. },
  1203. },
  1204. # Kaltura embed with single quotes
  1205. {
  1206. 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
  1207. 'info_dict': {
  1208. 'id': '0_izeg5utt',
  1209. 'ext': 'mp4',
  1210. 'title': '35871',
  1211. 'timestamp': 1355743100,
  1212. 'upload_date': '20121217',
  1213. 'uploader_id': 'batchUser',
  1214. },
  1215. 'add_ie': ['Kaltura'],
  1216. },
  1217. {
  1218. # Kaltura embedded via quoted entry_id
  1219. 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
  1220. 'info_dict': {
  1221. 'id': '0_utuok90b',
  1222. 'ext': 'mp4',
  1223. 'title': '06_matthew_brender_raj_dutt',
  1224. 'timestamp': 1466638791,
  1225. 'upload_date': '20160622',
  1226. },
  1227. 'add_ie': ['Kaltura'],
  1228. 'expected_warnings': [
  1229. 'Could not send HEAD request'
  1230. ],
  1231. 'params': {
  1232. 'skip_download': True,
  1233. }
  1234. },
  1235. {
  1236. # Kaltura embedded, some fileExt broken (#11480)
  1237. 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
  1238. 'info_dict': {
  1239. 'id': '1_sgtvehim',
  1240. 'ext': 'mp4',
  1241. 'title': 'Our "Standard Models" of particle physics and cosmology',
  1242. 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
  1243. 'timestamp': 1321158993,
  1244. 'upload_date': '20111113',
  1245. 'uploader_id': 'kps1',
  1246. },
  1247. 'add_ie': ['Kaltura'],
  1248. },
  1249. {
  1250. # Kaltura iframe embed
  1251. 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
  1252. 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
  1253. 'info_dict': {
  1254. 'id': '0_f2cfbpwy',
  1255. 'ext': 'mp4',
  1256. 'title': 'I. M. Pei: A Centennial Celebration',
  1257. 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
  1258. 'upload_date': '20170403',
  1259. 'uploader_id': 'batchUser',
  1260. 'timestamp': 1491232186,
  1261. },
  1262. 'add_ie': ['Kaltura'],
  1263. },
  1264. # EaglePlatform embed (generic URL)
  1265. {
  1266. 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
  1267. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  1268. 'info_dict': {
  1269. 'id': '227304',
  1270. 'ext': 'mp4',
  1271. 'title': 'Навальный вышел на свободу',
  1272. 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
  1273. 'thumbnail': r're:^https?://.*\.jpg$',
  1274. 'duration': 87,
  1275. 'view_count': int,
  1276. 'age_limit': 0,
  1277. },
  1278. 'params': {
  1279. 'skip_download': True,
  1280. },
  1281. },
  1282. # referrer protected EaglePlatform embed
  1283. {
  1284. 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
  1285. 'info_dict': {
  1286. 'id': '582306',
  1287. 'ext': 'mp4',
  1288. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1289. 'thumbnail': r're:^https?://.*\.jpg$',
  1290. 'duration': 3382,
  1291. 'view_count': int,
  1292. },
  1293. 'params': {
  1294. 'skip_download': True,
  1295. },
  1296. },
  1297. # ClipYou (EaglePlatform) embed (custom URL)
  1298. {
  1299. 'url': 'http://muz-tv.ru/play/7129/',
  1300. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  1301. 'info_dict': {
  1302. 'id': '12820',
  1303. 'ext': 'mp4',
  1304. 'title': "'O Sole Mio",
  1305. 'thumbnail': r're:^https?://.*\.jpg$',
  1306. 'duration': 216,
  1307. 'view_count': int,
  1308. },
  1309. 'params': {
  1310. 'skip_download': True,
  1311. },
  1312. 'skip': 'This video is unavailable.',
  1313. },
  1314. # Pladform embed
  1315. {
  1316. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  1317. 'info_dict': {
  1318. 'id': '100183293',
  1319. 'ext': 'mp4',
  1320. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  1321. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  1322. 'thumbnail': r're:^https?://.*\.jpg$',
  1323. 'duration': 694,
  1324. 'age_limit': 0,
  1325. },
  1326. 'skip': 'HTTP Error 404: Not Found',
  1327. },
  1328. # Playwire embed
  1329. {
  1330. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  1331. 'info_dict': {
  1332. 'id': '3519514',
  1333. 'ext': 'mp4',
  1334. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  1335. 'thumbnail': r're:^https?://.*\.png$',
  1336. 'duration': 45.115,
  1337. },
  1338. },
  1339. # 5min embed
  1340. {
  1341. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  1342. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  1343. 'info_dict': {
  1344. 'id': '518726732',
  1345. 'ext': 'mp4',
  1346. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  1347. 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
  1348. 'timestamp': 1427237531,
  1349. 'uploader': 'Crunch Report',
  1350. 'upload_date': '20150324',
  1351. },
  1352. 'params': {
  1353. # m3u8 download
  1354. 'skip_download': True,
  1355. },
  1356. },
  1357. # SVT embed
  1358. {
  1359. 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
  1360. 'info_dict': {
  1361. 'id': '2900353',
  1362. 'ext': 'flv',
  1363. 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
  1364. 'duration': 27,
  1365. 'age_limit': 0,
  1366. },
  1367. },
  1368. # Crooks and Liars embed
  1369. {
  1370. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  1371. 'info_dict': {
  1372. 'id': '8RUoRhRi',
  1373. 'ext': 'mp4',
  1374. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  1375. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  1376. 'timestamp': 1428207000,
  1377. 'upload_date': '20150405',
  1378. 'uploader': 'Heather',
  1379. },
  1380. },
  1381. # Crooks and Liars external embed
  1382. {
  1383. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  1384. 'info_dict': {
  1385. 'id': 'MTE3MjUtMzQ2MzA',
  1386. 'ext': 'mp4',
  1387. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  1388. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  1389. 'timestamp': 1265032391,
  1390. 'upload_date': '20100201',
  1391. 'uploader': 'Heather',
  1392. },
  1393. },
  1394. # NBC Sports vplayer embed
  1395. {
  1396. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  1397. 'info_dict': {
  1398. 'id': 'ln7x1qSThw4k',
  1399. 'ext': 'flv',
  1400. 'title': "PFT Live: New leader in the 'new-look' defense",
  1401. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  1402. 'uploader': 'NBCU-SPORTS',
  1403. 'upload_date': '20140107',
  1404. 'timestamp': 1389118457,
  1405. },
  1406. 'skip': 'Invalid Page URL',
  1407. },
  1408. # NBC News embed
  1409. {
  1410. 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
  1411. 'md5': '1aa589c675898ae6d37a17913cf68d66',
  1412. 'info_dict': {
  1413. 'id': 'x_dtl_oa_LettermanliftPR_160608',
  1414. 'ext': 'mp4',
  1415. 'title': 'David Letterman: A Preview',
  1416. '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.',
  1417. 'upload_date': '20160609',
  1418. 'timestamp': 1465431544,
  1419. 'uploader': 'NBCU-NEWS',
  1420. },
  1421. },
  1422. # UDN embed
  1423. {
  1424. 'url': 'https://video.udn.com/news/300346',
  1425. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  1426. 'info_dict': {
  1427. 'id': '300346',
  1428. 'ext': 'mp4',
  1429. 'title': '中一中男師變性 全校師生力挺',
  1430. 'thumbnail': r're:^https?://.*\.jpg$',
  1431. },
  1432. 'params': {
  1433. # m3u8 download
  1434. 'skip_download': True,
  1435. },
  1436. 'expected_warnings': ['Failed to parse JSON Expecting value'],
  1437. },
  1438. # Ooyala embed
  1439. {
  1440. 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
  1441. 'info_dict': {
  1442. 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
  1443. 'ext': 'mp4',
  1444. 'description': 'Index/Match versus VLOOKUP.',
  1445. 'title': 'This is what separates the Excel masters from the wannabes',
  1446. 'duration': 191.933,
  1447. },
  1448. 'params': {
  1449. # m3u8 downloads
  1450. 'skip_download': True,
  1451. }
  1452. },
  1453. # Brightcove URL in single quotes
  1454. {
  1455. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  1456. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  1457. 'info_dict': {
  1458. 'id': '4255764656001',
  1459. 'ext': 'mp4',
  1460. 'title': 'SN Presents: Russell Martin, World Citizen',
  1461. 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
  1462. 'uploader': 'Rogers Sportsnet',
  1463. 'uploader_id': '1704050871',
  1464. 'upload_date': '20150525',
  1465. 'timestamp': 1432570283,
  1466. },
  1467. },
  1468. # OnionStudios embed
  1469. {
  1470. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1471. 'info_dict': {
  1472. 'id': '2855',
  1473. 'ext': 'mp4',
  1474. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1475. 'thumbnail': r're:^https?://.*\.jpe?g$',
  1476. 'uploader': 'ClickHole',
  1477. 'uploader_id': 'clickhole',
  1478. }
  1479. },
  1480. # SnagFilms embed
  1481. {
  1482. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1483. 'info_dict': {
  1484. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1485. 'ext': 'mp4',
  1486. 'title': '#whilewewatch',
  1487. }
  1488. },
  1489. # AdobeTVVideo embed
  1490. {
  1491. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1492. 'md5': '43662b577c018ad707a63766462b1e87',
  1493. 'info_dict': {
  1494. 'id': '2456',
  1495. 'ext': 'mp4',
  1496. 'title': 'New experience with Acrobat DC',
  1497. 'description': 'New experience with Acrobat DC',
  1498. 'duration': 248.667,
  1499. },
  1500. },
  1501. # BrightcoveInPageEmbed embed
  1502. {
  1503. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1504. 'info_dict': {
  1505. 'id': '4238694884001',
  1506. 'ext': 'flv',
  1507. 'title': 'Tabletop: Dread, Last Thoughts',
  1508. 'description': 'Tabletop: Dread, Last Thoughts',
  1509. 'duration': 51690,
  1510. },
  1511. },
  1512. # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
  1513. # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
  1514. {
  1515. 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
  1516. 'info_dict': {
  1517. 'id': '4785848093001',
  1518. 'ext': 'mp4',
  1519. 'title': 'The Cardinal Pell Interview',
  1520. 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
  1521. 'uploader': 'GlobeCast Australia - GlobeStream',
  1522. 'uploader_id': '2733773828001',
  1523. 'upload_date': '20160304',
  1524. 'timestamp': 1457083087,
  1525. },
  1526. 'params': {
  1527. # m3u8 downloads
  1528. 'skip_download': True,
  1529. },
  1530. },
  1531. {
  1532. # Brightcove embed with whitespace around attribute names
  1533. 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
  1534. 'info_dict': {
  1535. 'id': '3167554373001',
  1536. 'ext': 'mp4',
  1537. 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
  1538. 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
  1539. 'uploader_id': '1079349493',
  1540. 'upload_date': '20140207',
  1541. 'timestamp': 1391810548,
  1542. },
  1543. 'params': {
  1544. 'skip_download': True,
  1545. },
  1546. },
  1547. # Another form of arte.tv embed
  1548. {
  1549. 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
  1550. 'md5': '850bfe45417ddf221288c88a0cffe2e2',
  1551. 'info_dict': {
  1552. 'id': '030273-562_PLUS7-F',
  1553. 'ext': 'mp4',
  1554. 'title': 'ARTE Reportage - Nulle part, en France',
  1555. 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
  1556. 'upload_date': '20160409',
  1557. },
  1558. },
  1559. # LiveLeak embed
  1560. {
  1561. 'url': 'http://www.wykop.pl/link/3088787/',
  1562. 'md5': '7619da8c820e835bef21a1efa2a0fc71',
  1563. 'info_dict': {
  1564. 'id': '874_1459135191',
  1565. 'ext': 'mp4',
  1566. 'title': 'Man shows poor quality of new apartment building',
  1567. 'description': 'The wall is like a sand pile.',
  1568. 'uploader': 'Lake8737',
  1569. },
  1570. 'add_ie': [LiveLeakIE.ie_key()],
  1571. },
  1572. # Another LiveLeak embed pattern (#13336)
  1573. {
  1574. 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
  1575. 'info_dict': {
  1576. 'id': '2eb_1496309988',
  1577. 'ext': 'mp4',
  1578. 'title': 'Thief robs place where everyone was armed',
  1579. 'description': 'md5:694d73ee79e535953cf2488562288eee',
  1580. 'uploader': 'brazilwtf',
  1581. },
  1582. 'add_ie': [LiveLeakIE.ie_key()],
  1583. },
  1584. # Duplicated embedded video URLs
  1585. {
  1586. 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
  1587. 'info_dict': {
  1588. 'id': '149298443_480_16c25b74_2',
  1589. 'ext': 'mp4',
  1590. 'title': 'vs. Blue Orange Spring Game',
  1591. 'uploader': 'www.hudl.com',
  1592. },
  1593. },
  1594. # twitter:player:stream embed
  1595. {
  1596. 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
  1597. 'info_dict': {
  1598. 'id': 'master',
  1599. 'ext': 'mp4',
  1600. 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
  1601. 'uploader': 'www.rtl.be',
  1602. },
  1603. 'params': {
  1604. # m3u8 downloads
  1605. 'skip_download': True,
  1606. },
  1607. },
  1608. # twitter:player embed
  1609. {
  1610. 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
  1611. 'md5': 'a3e0df96369831de324f0778e126653c',
  1612. 'info_dict': {
  1613. 'id': '4909620399001',
  1614. 'ext': 'mp4',
  1615. 'title': 'What Do Black Holes Sound Like?',
  1616. 'description': 'what do black holes sound like',
  1617. 'upload_date': '20160524',
  1618. 'uploader_id': '29913724001',
  1619. 'timestamp': 1464107587,
  1620. 'uploader': 'TheAtlantic',
  1621. },
  1622. 'add_ie': ['BrightcoveLegacy'],
  1623. },
  1624. # Facebook <iframe> embed
  1625. {
  1626. 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
  1627. 'md5': 'fbcde74f534176ecb015849146dd3aee',
  1628. 'info_dict': {
  1629. 'id': '599637780109885',
  1630. 'ext': 'mp4',
  1631. 'title': 'Facebook video #599637780109885',
  1632. },
  1633. },
  1634. # Facebook <iframe> embed, plugin video
  1635. {
  1636. 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
  1637. 'info_dict': {
  1638. 'id': '1754168231264132',
  1639. 'ext': 'mp4',
  1640. 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
  1641. 'uploader': 'Tariq Ramadan (official)',
  1642. 'timestamp': 1496758379,
  1643. 'upload_date': '20170606',
  1644. },
  1645. 'params': {
  1646. 'skip_download': True,
  1647. },
  1648. },
  1649. # Facebook API embed
  1650. {
  1651. 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
  1652. 'md5': 'a47372ee61b39a7b90287094d447d94e',
  1653. 'info_dict': {
  1654. 'id': '10153467542406923',
  1655. 'ext': 'mp4',
  1656. 'title': 'Facebook video #10153467542406923',
  1657. },
  1658. },
  1659. # Wordpress "YouTube Video Importer" plugin
  1660. {
  1661. 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
  1662. 'md5': 'd16797741b560b485194eddda8121b48',
  1663. 'info_dict': {
  1664. 'id': 'HNTXWDXV9Is',
  1665. 'ext': 'mp4',
  1666. 'title': 'Blue Devils Drumline Stanford lot 2016',
  1667. 'upload_date': '20160627',
  1668. 'uploader_id': 'GENOCIDE8GENERAL10',
  1669. 'uploader': 'cylus cyrus',
  1670. },
  1671. },
  1672. {
  1673. # video stored on custom kaltura server
  1674. 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
  1675. 'md5': '537617d06e64dfed891fa1593c4b30cc',
  1676. 'info_dict': {
  1677. 'id': '0_1iotm5bh',
  1678. 'ext': 'mp4',
  1679. 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
  1680. 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
  1681. 'uploader_id': 'videos.expansion@el-mundo.net',
  1682. 'upload_date': '20150429',
  1683. 'timestamp': 1430303472,
  1684. },
  1685. 'add_ie': ['Kaltura'],
  1686. },
  1687. {
  1688. # Non-standard Vimeo embed
  1689. 'url': 'https://openclassrooms.com/courses/understanding-the-web',
  1690. 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
  1691. 'info_dict': {
  1692. 'id': '148867247',
  1693. 'ext': 'mp4',
  1694. 'title': 'Understanding the web - Teaser',
  1695. 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
  1696. 'upload_date': '20151214',
  1697. 'uploader': 'OpenClassrooms',
  1698. 'uploader_id': 'openclassrooms',
  1699. },
  1700. 'add_ie': ['Vimeo'],
  1701. },
  1702. {
  1703. # generic vimeo embed that requires original URL passed as Referer
  1704. 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
  1705. 'only_matching': True,
  1706. },
  1707. {
  1708. 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
  1709. 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
  1710. 'info_dict': {
  1711. 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
  1712. 'ext': 'mp4',
  1713. 'title': 'Big Buck Bunny',
  1714. 'description': 'Royalty free test video',
  1715. 'timestamp': 1432816365,
  1716. 'upload_date': '20150528',
  1717. 'is_live': False,
  1718. },
  1719. 'params': {
  1720. 'skip_download': True,
  1721. },
  1722. 'add_ie': [ArkenaIE.ie_key()],
  1723. },
  1724. {
  1725. '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/',
  1726. 'info_dict': {
  1727. 'id': '1c7141f46c',
  1728. 'ext': 'mp4',
  1729. 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
  1730. },
  1731. 'params': {
  1732. 'skip_download': True,
  1733. },
  1734. 'add_ie': [Vbox7IE.ie_key()],
  1735. },
  1736. {
  1737. # DBTV embeds
  1738. 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
  1739. 'info_dict': {
  1740. 'id': '43254897',
  1741. 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
  1742. },
  1743. 'playlist_mincount': 3,
  1744. },
  1745. {
  1746. # Videa embeds
  1747. 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
  1748. 'info_dict': {
  1749. 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
  1750. 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
  1751. },
  1752. 'playlist_mincount': 2,
  1753. },
  1754. {
  1755. # 20 minuten embed
  1756. 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
  1757. 'info_dict': {
  1758. 'id': '523629',
  1759. 'ext': 'mp4',
  1760. 'title': 'So kommen Sie bei Eis und Schnee sicher an',
  1761. 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
  1762. },
  1763. 'params': {
  1764. 'skip_download': True,
  1765. },
  1766. 'add_ie': [TwentyMinutenIE.ie_key()],
  1767. },
  1768. {
  1769. # VideoPress embed
  1770. 'url': 'https://en.support.wordpress.com/videopress/',
  1771. 'info_dict': {
  1772. 'id': 'OcobLTqC',
  1773. 'ext': 'm4v',
  1774. 'title': 'IMG_5786',
  1775. 'timestamp': 1435711927,
  1776. 'upload_date': '20150701',
  1777. },
  1778. 'params': {
  1779. 'skip_download': True,
  1780. },
  1781. 'add_ie': [VideoPressIE.ie_key()],
  1782. },
  1783. {
  1784. # Rutube embed
  1785. 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
  1786. 'info_dict': {
  1787. 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
  1788. 'ext': 'flv',
  1789. 'title': 'Магаззино: Казань 2',
  1790. 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
  1791. 'uploader': 'Магаззино',
  1792. 'upload_date': '20170228',
  1793. 'uploader_id': '996642',
  1794. },
  1795. 'params': {
  1796. 'skip_download': True,
  1797. },
  1798. 'add_ie': [RutubeIE.ie_key()],
  1799. },
  1800. {
  1801. # ThePlatform embedded with whitespaces in URLs
  1802. 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
  1803. 'only_matching': True,
  1804. },
  1805. {
  1806. # Senate ISVP iframe https
  1807. 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
  1808. 'md5': 'fb8c70b0b515e5037981a2492099aab8',
  1809. 'info_dict': {
  1810. 'id': 'govtaff020316',
  1811. 'ext': 'mp4',
  1812. 'title': 'Integrated Senate Video Player',
  1813. },
  1814. 'add_ie': [SenateISVPIE.ie_key()],
  1815. },
  1816. {
  1817. # Limelight embeds (1 channel embed + 4 media embeds)
  1818. 'url': 'http://www.sedona.com/FacilitatorTraining2017',
  1819. 'info_dict': {
  1820. 'id': 'FacilitatorTraining2017',
  1821. 'title': 'Facilitator Training 2017',
  1822. },
  1823. 'playlist_mincount': 5,
  1824. },
  1825. {
  1826. # Limelight embed (LimelightPlayerUtil.embed)
  1827. 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
  1828. 'info_dict': {
  1829. 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
  1830. 'ext': 'mp4',
  1831. 'title': '07448641',
  1832. 'timestamp': 1499890639,
  1833. 'upload_date': '20170712',
  1834. },
  1835. 'params': {
  1836. 'skip_download': True,
  1837. },
  1838. 'add_ie': ['LimelightMedia'],
  1839. },
  1840. {
  1841. 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
  1842. 'info_dict': {
  1843. 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
  1844. 'title': 'Standoff with Walnut Creek murder suspect ends',
  1845. 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
  1846. },
  1847. 'playlist_mincount': 4,
  1848. },
  1849. {
  1850. # WashingtonPost embed
  1851. 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
  1852. 'info_dict': {
  1853. 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
  1854. 'ext': 'mp4',
  1855. 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
  1856. '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.',
  1857. 'timestamp': 1455216756,
  1858. 'uploader': 'The Washington Post',
  1859. 'upload_date': '20160211',
  1860. },
  1861. 'add_ie': [WashingtonPostIE.ie_key()],
  1862. },
  1863. {
  1864. # Mediaset embed
  1865. 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
  1866. 'info_dict': {
  1867. 'id': '720642',
  1868. 'ext': 'mp4',
  1869. 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
  1870. },
  1871. 'params': {
  1872. 'skip_download': True,
  1873. },
  1874. 'add_ie': [MediasetIE.ie_key()],
  1875. },
  1876. {
  1877. # JOJ.sk embeds
  1878. 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1879. 'info_dict': {
  1880. 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1881. 'title': 'Slovenskom sa prehnala vlna silných búrok',
  1882. },
  1883. 'playlist_mincount': 5,
  1884. 'add_ie': [JojIE.ie_key()],
  1885. },
  1886. {
  1887. # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
  1888. 'url': 'https://tvrain.ru/amp/418921/',
  1889. 'md5': 'cc00413936695987e8de148b67d14f1d',
  1890. 'info_dict': {
  1891. 'id': '418921',
  1892. 'ext': 'mp4',
  1893. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1894. },
  1895. },
  1896. {
  1897. # vzaar embed
  1898. 'url': 'http://help.vzaar.com/article/165-embedding-video',
  1899. 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
  1900. 'info_dict': {
  1901. 'id': '8707641',
  1902. 'ext': 'mp4',
  1903. 'title': 'Building A Business Online: Principal Chairs Q & A',
  1904. },
  1905. },
  1906. {
  1907. # multiple HTML5 videos on one page
  1908. 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
  1909. 'info_dict': {
  1910. 'id': 'keyscenarios',
  1911. 'title': 'Rescue Kit 14 Free Edition - Getting started',
  1912. },
  1913. 'playlist_count': 4,
  1914. },
  1915. {
  1916. # vshare embed
  1917. 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
  1918. 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
  1919. 'info_dict': {
  1920. 'id': '0f64ce6',
  1921. 'title': 'vl14062007715967',
  1922. 'ext': 'mp4',
  1923. }
  1924. },
  1925. {
  1926. 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
  1927. 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
  1928. 'info_dict': {
  1929. 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
  1930. 'ext': 'mp4',
  1931. 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
  1932. 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
  1933. 'timestamp': 1474354800,
  1934. 'upload_date': '20160920',
  1935. }
  1936. },
  1937. {
  1938. 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
  1939. 'info_dict': {
  1940. 'id': '1731611',
  1941. 'ext': 'mp4',
  1942. 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
  1943. 'description': 'md5:eb5f23826a027ba95277d105f248b825',
  1944. 'timestamp': 1516100691,
  1945. 'upload_date': '20180116',
  1946. },
  1947. 'params': {
  1948. 'skip_download': True,
  1949. },
  1950. 'add_ie': [SpringboardPlatformIE.ie_key()],
  1951. },
  1952. {
  1953. 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
  1954. 'info_dict': {
  1955. 'id': 'uPDB5I9wfp8',
  1956. 'ext': 'webm',
  1957. 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
  1958. 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
  1959. 'upload_date': '20160219',
  1960. 'uploader': 'Pocoyo - Português (BR)',
  1961. 'uploader_id': 'PocoyoBrazil',
  1962. },
  1963. 'add_ie': [YoutubeIE.ie_key()],
  1964. 'params': {
  1965. 'skip_download': True,
  1966. },
  1967. }
  1968. # {
  1969. # # TODO: find another test
  1970. # # http://schema.org/VideoObject
  1971. # 'url': 'https://flipagram.com/f/nyvTSJMKId',
  1972. # 'md5': '888dcf08b7ea671381f00fab74692755',
  1973. # 'info_dict': {
  1974. # 'id': 'nyvTSJMKId',
  1975. # 'ext': 'mp4',
  1976. # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
  1977. # 'description': '#love for cats.',
  1978. # 'timestamp': 1461244995,
  1979. # 'upload_date': '20160421',
  1980. # },
  1981. # 'params': {
  1982. # 'force_generic_extractor': True,
  1983. # },
  1984. # }
  1985. ]
  1986. def report_following_redirect(self, new_url):
  1987. """Report information extraction."""
  1988. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  1989. def _extract_rss(self, url, video_id, doc):
  1990. playlist_title = doc.find('./channel/title').text
  1991. playlist_desc_el = doc.find('./channel/description')
  1992. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  1993. entries = []
  1994. for it in doc.findall('./channel/item'):
  1995. next_url = xpath_text(it, 'link', fatal=False)
  1996. if not next_url:
  1997. enclosure_nodes = it.findall('./enclosure')
  1998. for e in enclosure_nodes:
  1999. next_url = e.attrib.get('url')
  2000. if next_url:
  2001. break
  2002. if not next_url:
  2003. continue
  2004. entries.append({
  2005. '_type': 'url_transparent',
  2006. 'url': next_url,
  2007. 'title': it.find('title').text,
  2008. })
  2009. return {
  2010. '_type': 'playlist',
  2011. 'id': url,
  2012. 'title': playlist_title,
  2013. 'description': playlist_desc,
  2014. 'entries': entries,
  2015. }
  2016. def _extract_camtasia(self, url, video_id, webpage):
  2017. """ Returns None if no camtasia video can be found. """
  2018. camtasia_cfg = self._search_regex(
  2019. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  2020. webpage, 'camtasia configuration file', default=None)
  2021. if camtasia_cfg is None:
  2022. return None
  2023. title = self._html_search_meta('DC.title', webpage, fatal=True)
  2024. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  2025. camtasia_cfg = self._download_xml(
  2026. camtasia_url, video_id,
  2027. note='Downloading camtasia configuration',
  2028. errnote='Failed to download camtasia configuration')
  2029. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  2030. entries = []
  2031. for n in fileset_node.getchildren():
  2032. url_n = n.find('./uri')
  2033. if url_n is None:
  2034. continue
  2035. entries.append({
  2036. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  2037. 'title': '%s - %s' % (title, n.tag),
  2038. 'url': compat_urlparse.urljoin(url, url_n.text),
  2039. 'duration': float_or_none(n.find('./duration').text),
  2040. })
  2041. return {
  2042. '_type': 'playlist',
  2043. 'entries': entries,
  2044. 'title': title,
  2045. }
  2046. def _real_extract(self, url):
  2047. if url.startswith('//'):
  2048. return {
  2049. '_type': 'url',
  2050. 'url': self.http_scheme() + url,
  2051. }
  2052. parsed_url = compat_urlparse.urlparse(url)
  2053. if not parsed_url.scheme:
  2054. default_search = self._downloader.params.get('default_search')
  2055. if default_search is None:
  2056. default_search = 'fixup_error'
  2057. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  2058. if '/' in url:
  2059. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  2060. return self.url_result('http://' + url)
  2061. elif default_search != 'fixup_error':
  2062. if default_search == 'auto_warning':
  2063. if re.match(r'^(?:url|URL)$', url):
  2064. raise ExtractorError(
  2065. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  2066. expected=True)
  2067. else:
  2068. self._downloader.report_warning(
  2069. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  2070. return self.url_result('ytsearch:' + url)
  2071. if default_search in ('error', 'fixup_error'):
  2072. raise ExtractorError(
  2073. '%r is not a valid URL. '
  2074. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  2075. % (url, url), expected=True)
  2076. else:
  2077. if ':' not in default_search:
  2078. default_search += ':'
  2079. return self.url_result(default_search + url)
  2080. url, smuggled_data = unsmuggle_url(url)
  2081. force_videoid = None
  2082. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  2083. if smuggled_data and 'force_videoid' in smuggled_data:
  2084. force_videoid = smuggled_data['force_videoid']
  2085. video_id = force_videoid
  2086. else:
  2087. video_id = self._generic_id(url)
  2088. self.to_screen('%s: Requesting header' % video_id)
  2089. head_req = HEADRequest(url)
  2090. head_response = self._request_webpage(
  2091. head_req, video_id,
  2092. note=False, errnote='Could not send HEAD request to %s' % url,
  2093. fatal=False)
  2094. if head_response is not False:
  2095. # Check for redirect
  2096. new_url = compat_str(head_response.geturl())
  2097. if url != new_url:
  2098. self.report_following_redirect(new_url)
  2099. if force_videoid:
  2100. new_url = smuggle_url(
  2101. new_url, {'force_videoid': force_videoid})
  2102. return self.url_result(new_url)
  2103. full_response = None
  2104. if head_response is False:
  2105. request = sanitized_Request(url)
  2106. request.add_header('Accept-Encoding', '*')
  2107. full_response = self._request_webpage(request, video_id)
  2108. head_response = full_response
  2109. info_dict = {
  2110. 'id': video_id,
  2111. 'title': self._generic_title(url),
  2112. 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
  2113. }
  2114. # Check for direct link to a video
  2115. content_type = head_response.headers.get('Content-Type', '').lower()
  2116. m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
  2117. if m:
  2118. format_id = compat_str(m.group('format_id'))
  2119. if format_id.endswith('mpegurl'):
  2120. formats = self._extract_m3u8_formats(url, video_id, 'mp4')
  2121. elif format_id == 'f4m':
  2122. formats = self._extract_f4m_formats(url, video_id)
  2123. else:
  2124. formats = [{
  2125. 'format_id': format_id,
  2126. 'url': url,
  2127. 'vcodec': 'none' if m.group('type') == 'audio' else None
  2128. }]
  2129. info_dict['direct'] = True
  2130. self._sort_formats(formats)
  2131. info_dict['formats'] = formats
  2132. return info_dict
  2133. if not self._downloader.params.get('test', False) and not is_intentional:
  2134. force = self._downloader.params.get('force_generic_extractor', False)
  2135. self._downloader.report_warning(
  2136. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  2137. if not full_response:
  2138. request = sanitized_Request(url)
  2139. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  2140. # making it impossible to download only chunk of the file (yet we need only 512kB to
  2141. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  2142. # that will always result in downloading the whole file that is not desirable.
  2143. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  2144. # to accept raw bytes and being able to download only a chunk.
  2145. # It may probably better to solve this by checking Content-Type for application/octet-stream
  2146. # after HEAD request finishes, but not sure if we can rely on this.
  2147. request.add_header('Accept-Encoding', '*')
  2148. full_response = self._request_webpage(request, video_id)
  2149. first_bytes = full_response.read(512)
  2150. # Is it an M3U playlist?
  2151. if first_bytes.startswith(b'#EXTM3U'):
  2152. info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
  2153. self._sort_formats(info_dict['formats'])
  2154. return info_dict
  2155. # Maybe it's a direct link to a video?
  2156. # Be careful not to download the whole thing!
  2157. if not is_html(first_bytes):
  2158. self._downloader.report_warning(
  2159. 'URL could be a direct video link, returning it as such.')
  2160. info_dict.update({
  2161. 'direct': True,
  2162. 'url': url,
  2163. })
  2164. return info_dict
  2165. webpage = self._webpage_read_content(
  2166. full_response, url, video_id, prefix=first_bytes)
  2167. self.report_extraction(video_id)
  2168. # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
  2169. try:
  2170. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  2171. if doc.tag == 'rss':
  2172. return self._extract_rss(url, video_id, doc)
  2173. elif doc.tag == 'SmoothStreamingMedia':
  2174. info_dict['formats'] = self._parse_ism_formats(doc, url)
  2175. self._sort_formats(info_dict['formats'])
  2176. return info_dict
  2177. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  2178. smil = self._parse_smil(doc, url, video_id)
  2179. self._sort_formats(smil['formats'])
  2180. return smil
  2181. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  2182. return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
  2183. elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
  2184. info_dict['formats'] = self._parse_mpd_formats(
  2185. doc,
  2186. mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
  2187. mpd_url=url)
  2188. self._sort_formats(info_dict['formats'])
  2189. return info_dict
  2190. elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
  2191. info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
  2192. self._sort_formats(info_dict['formats'])
  2193. return info_dict
  2194. except compat_xml_parse_error:
  2195. pass
  2196. # Is it a Camtasia project?
  2197. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  2198. if camtasia_res is not None:
  2199. return camtasia_res
  2200. # Sometimes embedded video player is hidden behind percent encoding
  2201. # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
  2202. # Unescaping the whole page allows to handle those cases in a generic way
  2203. webpage = compat_urllib_parse_unquote(webpage)
  2204. # it's tempting to parse this further, but you would
  2205. # have to take into account all the variations like
  2206. # Video Title - Site Name
  2207. # Site Name | Video Title
  2208. # Video Title - Tagline | Site Name
  2209. # and so on and so forth; it's just not practical
  2210. video_title = self._og_search_title(
  2211. webpage, default=None) or self._html_search_regex(
  2212. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  2213. default='video')
  2214. # Try to detect age limit automatically
  2215. age_limit = self._rta_search(webpage)
  2216. # And then there are the jokers who advertise that they use RTA,
  2217. # but actually don't.
  2218. AGE_LIMIT_MARKERS = [
  2219. r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
  2220. ]
  2221. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  2222. age_limit = 18
  2223. # video uploader is domain name
  2224. video_uploader = self._search_regex(
  2225. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  2226. video_description = self._og_search_description(webpage, default=None)
  2227. video_thumbnail = self._og_search_thumbnail(webpage, default=None)
  2228. info_dict.update({
  2229. 'title': video_title,
  2230. 'description': video_description,
  2231. 'thumbnail': video_thumbnail,
  2232. 'age_limit': age_limit,
  2233. })
  2234. # Look for Brightcove Legacy Studio embeds
  2235. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  2236. if bc_urls:
  2237. entries = [{
  2238. '_type': 'url',
  2239. 'url': smuggle_url(bc_url, {'Referer': url}),
  2240. 'ie_key': 'BrightcoveLegacy'
  2241. } for bc_url in bc_urls]
  2242. return {
  2243. '_type': 'playlist',
  2244. 'title': video_title,
  2245. 'id': video_id,
  2246. 'entries': entries,
  2247. }
  2248. # Look for Brightcove New Studio embeds
  2249. bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
  2250. if bc_urls:
  2251. return self.playlist_from_matches(
  2252. bc_urls, video_id, video_title,
  2253. getter=lambda x: smuggle_url(x, {'referrer': url}),
  2254. ie='BrightcoveNew')
  2255. # Look for Nexx embeds
  2256. nexx_urls = NexxIE._extract_urls(webpage)
  2257. if nexx_urls:
  2258. return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
  2259. # Look for Nexx iFrame embeds
  2260. nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
  2261. if nexx_embed_urls:
  2262. return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
  2263. # Look for ThePlatform embeds
  2264. tp_urls = ThePlatformIE._extract_urls(webpage)
  2265. if tp_urls:
  2266. return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
  2267. # Look for Vessel embeds
  2268. vessel_urls = VesselIE._extract_urls(webpage)
  2269. if vessel_urls:
  2270. return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
  2271. # Look for embedded rtl.nl player
  2272. matches = re.findall(
  2273. r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
  2274. webpage)
  2275. if matches:
  2276. return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
  2277. vimeo_urls = VimeoIE._extract_urls(url, webpage)
  2278. if vimeo_urls:
  2279. return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
  2280. vid_me_embed_url = self._search_regex(
  2281. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  2282. webpage, 'vid.me embed', default=None)
  2283. if vid_me_embed_url is not None:
  2284. return self.url_result(vid_me_embed_url, 'Vidme')
  2285. # Look for YouTube embeds
  2286. youtube_urls = YoutubeIE._extract_urls(webpage)
  2287. if youtube_urls:
  2288. return self.playlist_from_matches(
  2289. youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
  2290. matches = DailymotionIE._extract_urls(webpage)
  2291. if matches:
  2292. return self.playlist_from_matches(matches, video_id, video_title)
  2293. # Look for embedded Dailymotion playlist player (#3822)
  2294. m = re.search(
  2295. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  2296. if m:
  2297. playlists = re.findall(
  2298. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  2299. if playlists:
  2300. return self.playlist_from_matches(
  2301. playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
  2302. # Look for DailyMail embeds
  2303. dailymail_urls = DailyMailIE._extract_urls(webpage)
  2304. if dailymail_urls:
  2305. return self.playlist_from_matches(
  2306. dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
  2307. # Look for embedded Wistia player
  2308. wistia_url = WistiaIE._extract_url(webpage)
  2309. if wistia_url:
  2310. return {
  2311. '_type': 'url_transparent',
  2312. 'url': self._proto_relative_url(wistia_url),
  2313. 'ie_key': WistiaIE.ie_key(),
  2314. 'uploader': video_uploader,
  2315. }
  2316. # Look for SVT player
  2317. svt_url = SVTIE._extract_url(webpage)
  2318. if svt_url:
  2319. return self.url_result(svt_url, 'SVT')
  2320. # Look for Bandcamp pages with custom domain
  2321. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  2322. if mobj is not None:
  2323. burl = unescapeHTML(mobj.group(1))
  2324. # Don't set the extractor because it can be a track url or an album
  2325. return self.url_result(burl)
  2326. # Look for embedded Vevo player
  2327. mobj = re.search(
  2328. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  2329. if mobj is not None:
  2330. return self.url_result(mobj.group('url'))
  2331. # Look for embedded Viddler player
  2332. mobj = re.search(
  2333. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  2334. webpage)
  2335. if mobj is not None:
  2336. return self.url_result(mobj.group('url'))
  2337. # Look for NYTimes player
  2338. mobj = re.search(
  2339. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  2340. webpage)
  2341. if mobj is not None:
  2342. return self.url_result(mobj.group('url'))
  2343. # Look for Libsyn player
  2344. mobj = re.search(
  2345. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  2346. if mobj is not None:
  2347. return self.url_result(mobj.group('url'))
  2348. # Look for Ooyala videos
  2349. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
  2350. re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
  2351. re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
  2352. re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
  2353. re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  2354. if mobj is not None:
  2355. embed_token = self._search_regex(
  2356. r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
  2357. webpage, 'ooyala embed token', default=None)
  2358. return OoyalaIE._build_url_result(smuggle_url(
  2359. mobj.group('ec'), {
  2360. 'domain': url,
  2361. 'embed_token': embed_token,
  2362. }))
  2363. # Look for multiple Ooyala embeds on SBN network websites
  2364. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  2365. if mobj is not None:
  2366. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  2367. if embeds:
  2368. return self.playlist_from_matches(
  2369. embeds, video_id, video_title,
  2370. getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  2371. # Look for Aparat videos
  2372. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  2373. if mobj is not None:
  2374. return self.url_result(mobj.group(1), 'Aparat')
  2375. # Look for MPORA videos
  2376. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  2377. if mobj is not None:
  2378. return self.url_result(mobj.group(1), 'Mpora')
  2379. # Look for embedded NovaMov-based player
  2380. mobj = re.search(
  2381. r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
  2382. (?P<url>http://(?:(?:embed|www)\.)?
  2383. (?:novamov\.com|
  2384. nowvideo\.(?:ch|sx|eu|at|ag|co)|
  2385. videoweed\.(?:es|com)|
  2386. movshare\.(?:net|sx|ag)|
  2387. divxstage\.(?:eu|net|ch|co|at|ag))
  2388. /embed\.php.+?)\1''', webpage)
  2389. if mobj is not None:
  2390. return self.url_result(mobj.group('url'))
  2391. # Look for embedded Facebook player
  2392. facebook_urls = FacebookIE._extract_urls(webpage)
  2393. if facebook_urls:
  2394. return self.playlist_from_matches(facebook_urls, video_id, video_title)
  2395. # Look for embedded VK player
  2396. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  2397. if mobj is not None:
  2398. return self.url_result(mobj.group('url'), 'VK')
  2399. # Look for embedded Odnoklassniki player
  2400. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
  2401. if mobj is not None:
  2402. return self.url_result(mobj.group('url'), 'Odnoklassniki')
  2403. # Look for embedded ivi player
  2404. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  2405. if mobj is not None:
  2406. return self.url_result(mobj.group('url'), 'Ivi')
  2407. # Look for embedded Huffington Post player
  2408. mobj = re.search(
  2409. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  2410. if mobj is not None:
  2411. return self.url_result(mobj.group('url'), 'HuffPost')
  2412. # Look for embed.ly
  2413. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  2414. if mobj is not None:
  2415. return self.url_result(mobj.group('url'))
  2416. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  2417. if mobj is not None:
  2418. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  2419. # Look for funnyordie embed
  2420. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  2421. if matches:
  2422. return self.playlist_from_matches(
  2423. matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
  2424. # Look for BBC iPlayer embed
  2425. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  2426. if matches:
  2427. return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
  2428. # Look for embedded RUTV player
  2429. rutv_url = RUTVIE._extract_url(webpage)
  2430. if rutv_url:
  2431. return self.url_result(rutv_url, 'RUTV')
  2432. # Look for embedded TVC player
  2433. tvc_url = TVCIE._extract_url(webpage)
  2434. if tvc_url:
  2435. return self.url_result(tvc_url, 'TVC')
  2436. # Look for embedded SportBox player
  2437. sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
  2438. if sportbox_urls:
  2439. return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
  2440. # Look for embedded XHamster player
  2441. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  2442. if xhamster_urls:
  2443. return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
  2444. # Look for embedded TNAFlixNetwork player
  2445. tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
  2446. if tnaflix_urls:
  2447. return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
  2448. # Look for embedded PornHub player
  2449. pornhub_urls = PornHubIE._extract_urls(webpage)
  2450. if pornhub_urls:
  2451. return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
  2452. # Look for embedded DrTuber player
  2453. drtuber_urls = DrTuberIE._extract_urls(webpage)
  2454. if drtuber_urls:
  2455. return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
  2456. # Look for embedded RedTube player
  2457. redtube_urls = RedTubeIE._extract_urls(webpage)
  2458. if redtube_urls:
  2459. return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
  2460. # Look for embedded Tvigle player
  2461. mobj = re.search(
  2462. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  2463. if mobj is not None:
  2464. return self.url_result(mobj.group('url'), 'Tvigle')
  2465. # Look for embedded TED player
  2466. mobj = re.search(
  2467. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  2468. if mobj is not None:
  2469. return self.url_result(mobj.group('url'), 'TED')
  2470. # Look for embedded Ustream videos
  2471. ustream_url = UstreamIE._extract_url(webpage)
  2472. if ustream_url:
  2473. return self.url_result(ustream_url, UstreamIE.ie_key())
  2474. # Look for embedded arte.tv player
  2475. mobj = re.search(
  2476. r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
  2477. webpage)
  2478. if mobj is not None:
  2479. return self.url_result(mobj.group('url'), 'ArteTVEmbed')
  2480. # Look for embedded francetv player
  2481. mobj = re.search(
  2482. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  2483. webpage)
  2484. if mobj is not None:
  2485. return self.url_result(mobj.group('url'))
  2486. # Look for embedded smotri.com player
  2487. smotri_url = SmotriIE._extract_url(webpage)
  2488. if smotri_url:
  2489. return self.url_result(smotri_url, 'Smotri')
  2490. # Look for embedded Myvi.ru player
  2491. myvi_url = MyviIE._extract_url(webpage)
  2492. if myvi_url:
  2493. return self.url_result(myvi_url)
  2494. # Look for embedded soundcloud player
  2495. soundcloud_urls = SoundcloudIE._extract_urls(webpage)
  2496. if soundcloud_urls:
  2497. return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
  2498. # Look for tunein player
  2499. tunein_urls = TuneInBaseIE._extract_urls(webpage)
  2500. if tunein_urls:
  2501. return self.playlist_from_matches(tunein_urls, video_id, video_title)
  2502. # Look for embedded mtvservices player
  2503. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  2504. if mtvservices_url:
  2505. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  2506. # Look for embedded yahoo player
  2507. mobj = re.search(
  2508. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  2509. webpage)
  2510. if mobj is not None:
  2511. return self.url_result(mobj.group('url'), 'Yahoo')
  2512. # Look for embedded sbs.com.au player
  2513. mobj = re.search(
  2514. r'''(?x)
  2515. (?:
  2516. <meta\s+property="og:video"\s+content=|
  2517. <iframe[^>]+?src=
  2518. )
  2519. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  2520. webpage)
  2521. if mobj is not None:
  2522. return self.url_result(mobj.group('url'), 'SBS')
  2523. # Look for embedded Cinchcast player
  2524. mobj = re.search(
  2525. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  2526. webpage)
  2527. if mobj is not None:
  2528. return self.url_result(mobj.group('url'), 'Cinchcast')
  2529. mobj = re.search(
  2530. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  2531. webpage)
  2532. if not mobj:
  2533. mobj = re.search(
  2534. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  2535. webpage)
  2536. if mobj is not None:
  2537. return self.url_result(mobj.group('url'), 'MLB')
  2538. mobj = re.search(
  2539. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  2540. webpage)
  2541. if mobj is not None:
  2542. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  2543. mobj = re.search(
  2544. r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
  2545. webpage)
  2546. if mobj is not None:
  2547. return self.url_result(mobj.group('url'), 'Livestream')
  2548. # Look for Zapiks embed
  2549. mobj = re.search(
  2550. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  2551. if mobj is not None:
  2552. return self.url_result(mobj.group('url'), 'Zapiks')
  2553. # Look for Kaltura embeds
  2554. kaltura_url = KalturaIE._extract_url(webpage)
  2555. if kaltura_url:
  2556. return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
  2557. # Look for EaglePlatform embeds
  2558. eagleplatform_url = EaglePlatformIE._extract_url(webpage)
  2559. if eagleplatform_url:
  2560. return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
  2561. # Look for ClipYou (uses EaglePlatform) embeds
  2562. mobj = re.search(
  2563. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  2564. if mobj is not None:
  2565. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  2566. # Look for Pladform embeds
  2567. pladform_url = PladformIE._extract_url(webpage)
  2568. if pladform_url:
  2569. return self.url_result(pladform_url)
  2570. # Look for Videomore embeds
  2571. videomore_url = VideomoreIE._extract_url(webpage)
  2572. if videomore_url:
  2573. return self.url_result(videomore_url)
  2574. # Look for Webcaster embeds
  2575. webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
  2576. if webcaster_url:
  2577. return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
  2578. # Look for Playwire embeds
  2579. mobj = re.search(
  2580. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  2581. if mobj is not None:
  2582. return self.url_result(mobj.group('url'))
  2583. # Look for 5min embeds
  2584. mobj = re.search(
  2585. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  2586. if mobj is not None:
  2587. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  2588. # Look for Crooks and Liars embeds
  2589. mobj = re.search(
  2590. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  2591. if mobj is not None:
  2592. return self.url_result(mobj.group('url'))
  2593. # Look for NBC Sports VPlayer embeds
  2594. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  2595. if nbc_sports_url:
  2596. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  2597. # Look for NBC News embeds
  2598. nbc_news_embed_url = re.search(
  2599. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
  2600. if nbc_news_embed_url:
  2601. return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
  2602. # Look for Google Drive embeds
  2603. google_drive_url = GoogleDriveIE._extract_url(webpage)
  2604. if google_drive_url:
  2605. return self.url_result(google_drive_url, 'GoogleDrive')
  2606. # Look for UDN embeds
  2607. mobj = re.search(
  2608. r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  2609. if mobj is not None:
  2610. return self.url_result(
  2611. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  2612. # Look for Senate ISVP iframe
  2613. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  2614. if senate_isvp_url:
  2615. return self.url_result(senate_isvp_url, 'SenateISVP')
  2616. # Look for OnionStudios embeds
  2617. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  2618. if onionstudios_url:
  2619. return self.url_result(onionstudios_url)
  2620. # Look for ViewLift embeds
  2621. viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
  2622. if viewlift_url:
  2623. return self.url_result(viewlift_url)
  2624. # Look for JWPlatform embeds
  2625. jwplatform_urls = JWPlatformIE._extract_urls(webpage)
  2626. if jwplatform_urls:
  2627. return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
  2628. # Look for Digiteka embeds
  2629. digiteka_url = DigitekaIE._extract_url(webpage)
  2630. if digiteka_url:
  2631. return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
  2632. # Look for Arkena embeds
  2633. arkena_url = ArkenaIE._extract_url(webpage)
  2634. if arkena_url:
  2635. return self.url_result(arkena_url, ArkenaIE.ie_key())
  2636. # Look for Piksel embeds
  2637. piksel_url = PikselIE._extract_url(webpage)
  2638. if piksel_url:
  2639. return self.url_result(piksel_url, PikselIE.ie_key())
  2640. # Look for Limelight embeds
  2641. limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
  2642. if limelight_urls:
  2643. return self.playlist_result(
  2644. limelight_urls, video_id, video_title, video_description)
  2645. # Look for Anvato embeds
  2646. anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
  2647. if anvato_urls:
  2648. return self.playlist_result(
  2649. anvato_urls, video_id, video_title, video_description)
  2650. # Look for AdobeTVVideo embeds
  2651. mobj = re.search(
  2652. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  2653. webpage)
  2654. if mobj is not None:
  2655. return self.url_result(
  2656. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  2657. 'AdobeTVVideo')
  2658. # Look for Vine embeds
  2659. mobj = re.search(
  2660. r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
  2661. webpage)
  2662. if mobj is not None:
  2663. return self.url_result(
  2664. self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
  2665. # Look for VODPlatform embeds
  2666. mobj = re.search(
  2667. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
  2668. webpage)
  2669. if mobj is not None:
  2670. return self.url_result(
  2671. self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
  2672. # Look for Mangomolo embeds
  2673. mobj = re.search(
  2674. r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
  2675. (?:
  2676. video\?.*?\bid=(?P<video_id>\d+)|
  2677. index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
  2678. ).+?)\1''', webpage)
  2679. if mobj is not None:
  2680. info = {
  2681. '_type': 'url_transparent',
  2682. 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
  2683. 'title': video_title,
  2684. 'description': video_description,
  2685. 'thumbnail': video_thumbnail,
  2686. 'uploader': video_uploader,
  2687. }
  2688. video_id = mobj.group('video_id')
  2689. if video_id:
  2690. info.update({
  2691. 'ie_key': 'MangomoloVideo',
  2692. 'id': video_id,
  2693. })
  2694. else:
  2695. info.update({
  2696. 'ie_key': 'MangomoloLive',
  2697. 'id': mobj.group('channel_id'),
  2698. })
  2699. return info
  2700. # Look for Instagram embeds
  2701. instagram_embed_url = InstagramIE._extract_embed_url(webpage)
  2702. if instagram_embed_url is not None:
  2703. return self.url_result(
  2704. self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
  2705. # Look for LiveLeak embeds
  2706. liveleak_urls = LiveLeakIE._extract_urls(webpage)
  2707. if liveleak_urls:
  2708. return self.playlist_from_matches(liveleak_urls, video_id, video_title)
  2709. # Look for 3Q SDN embeds
  2710. threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
  2711. if threeqsdn_url:
  2712. return {
  2713. '_type': 'url_transparent',
  2714. 'ie_key': ThreeQSDNIE.ie_key(),
  2715. 'url': self._proto_relative_url(threeqsdn_url),
  2716. 'title': video_title,
  2717. 'description': video_description,
  2718. 'thumbnail': video_thumbnail,
  2719. 'uploader': video_uploader,
  2720. }
  2721. # Look for VBOX7 embeds
  2722. vbox7_url = Vbox7IE._extract_url(webpage)
  2723. if vbox7_url:
  2724. return self.url_result(vbox7_url, Vbox7IE.ie_key())
  2725. # Look for DBTV embeds
  2726. dbtv_urls = DBTVIE._extract_urls(webpage)
  2727. if dbtv_urls:
  2728. return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
  2729. # Look for Videa embeds
  2730. videa_urls = VideaIE._extract_urls(webpage)
  2731. if videa_urls:
  2732. return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
  2733. # Look for 20 minuten embeds
  2734. twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
  2735. if twentymin_urls:
  2736. return self.playlist_from_matches(
  2737. twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
  2738. # Look for Openload embeds
  2739. openload_urls = OpenloadIE._extract_urls(webpage)
  2740. if openload_urls:
  2741. return self.playlist_from_matches(
  2742. openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
  2743. # Look for VideoPress embeds
  2744. videopress_urls = VideoPressIE._extract_urls(webpage)
  2745. if videopress_urls:
  2746. return self.playlist_from_matches(
  2747. videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
  2748. # Look for Rutube embeds
  2749. rutube_urls = RutubeIE._extract_urls(webpage)
  2750. if rutube_urls:
  2751. return self.playlist_from_matches(
  2752. rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
  2753. # Look for WashingtonPost embeds
  2754. wapo_urls = WashingtonPostIE._extract_urls(webpage)
  2755. if wapo_urls:
  2756. return self.playlist_from_matches(
  2757. wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
  2758. # Look for Mediaset embeds
  2759. mediaset_urls = MediasetIE._extract_urls(webpage)
  2760. if mediaset_urls:
  2761. return self.playlist_from_matches(
  2762. mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
  2763. # Look for JOJ.sk embeds
  2764. joj_urls = JojIE._extract_urls(webpage)
  2765. if joj_urls:
  2766. return self.playlist_from_matches(
  2767. joj_urls, video_id, video_title, ie=JojIE.ie_key())
  2768. # Look for megaphone.fm embeds
  2769. mpfn_urls = MegaphoneIE._extract_urls(webpage)
  2770. if mpfn_urls:
  2771. return self.playlist_from_matches(
  2772. mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
  2773. # Look for vzaar embeds
  2774. vzaar_urls = VzaarIE._extract_urls(webpage)
  2775. if vzaar_urls:
  2776. return self.playlist_from_matches(
  2777. vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
  2778. channel9_urls = Channel9IE._extract_urls(webpage)
  2779. if channel9_urls:
  2780. return self.playlist_from_matches(
  2781. channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
  2782. vshare_urls = VShareIE._extract_urls(webpage)
  2783. if vshare_urls:
  2784. return self.playlist_from_matches(
  2785. vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
  2786. # Look for Mediasite embeds
  2787. mediasite_urls = MediasiteIE._extract_urls(webpage)
  2788. if mediasite_urls:
  2789. entries = [
  2790. self.url_result(smuggle_url(
  2791. compat_urlparse.urljoin(url, mediasite_url),
  2792. {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
  2793. for mediasite_url in mediasite_urls]
  2794. return self.playlist_result(entries, video_id, video_title)
  2795. springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
  2796. if springboardplatform_urls:
  2797. return self.playlist_from_matches(
  2798. springboardplatform_urls, video_id, video_title,
  2799. ie=SpringboardPlatformIE.ie_key())
  2800. def merge_dicts(dict1, dict2):
  2801. merged = {}
  2802. for k, v in dict1.items():
  2803. if v is not None:
  2804. merged[k] = v
  2805. for k, v in dict2.items():
  2806. if v is None:
  2807. continue
  2808. if (k not in merged or
  2809. (isinstance(v, compat_str) and v and
  2810. isinstance(merged[k], compat_str) and
  2811. not merged[k])):
  2812. merged[k] = v
  2813. return merged
  2814. # Look for HTML5 media
  2815. entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
  2816. if entries:
  2817. if len(entries) == 1:
  2818. entries[0].update({
  2819. 'id': video_id,
  2820. 'title': video_title,
  2821. })
  2822. else:
  2823. for num, entry in enumerate(entries, start=1):
  2824. entry.update({
  2825. 'id': '%s-%s' % (video_id, num),
  2826. 'title': '%s (%d)' % (video_title, num),
  2827. })
  2828. for entry in entries:
  2829. self._sort_formats(entry['formats'])
  2830. return self.playlist_result(entries, video_id, video_title)
  2831. jwplayer_data = self._find_jwplayer_data(
  2832. webpage, video_id, transform_source=js_to_json)
  2833. if jwplayer_data:
  2834. info = self._parse_jwplayer_data(
  2835. jwplayer_data, video_id, require_title=False, base_url=url)
  2836. return merge_dicts(info, info_dict)
  2837. # Video.js embed
  2838. mobj = re.search(
  2839. r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
  2840. webpage)
  2841. if mobj is not None:
  2842. sources = self._parse_json(
  2843. mobj.group(1), video_id, transform_source=js_to_json,
  2844. fatal=False) or []
  2845. if not isinstance(sources, list):
  2846. sources = [sources]
  2847. formats = []
  2848. for source in sources:
  2849. src = source.get('src')
  2850. if not src or not isinstance(src, compat_str):
  2851. continue
  2852. src = compat_urlparse.urljoin(url, src)
  2853. src_type = source.get('type')
  2854. if isinstance(src_type, compat_str):
  2855. src_type = src_type.lower()
  2856. ext = determine_ext(src).lower()
  2857. if src_type == 'video/youtube':
  2858. return self.url_result(src, YoutubeIE.ie_key())
  2859. if src_type == 'application/dash+xml' or ext == 'mpd':
  2860. formats.extend(self._extract_mpd_formats(
  2861. src, video_id, mpd_id='dash', fatal=False))
  2862. elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
  2863. formats.extend(self._extract_m3u8_formats(
  2864. src, video_id, 'mp4', entry_protocol='m3u8_native',
  2865. m3u8_id='hls', fatal=False))
  2866. else:
  2867. formats.append({
  2868. 'url': src,
  2869. 'ext': (mimetype2ext(src_type) or
  2870. ext if ext in KNOWN_EXTENSIONS else 'mp4'),
  2871. })
  2872. if formats:
  2873. self._sort_formats(formats)
  2874. info_dict['formats'] = formats
  2875. return info_dict
  2876. # Looking for http://schema.org/VideoObject
  2877. json_ld = self._search_json_ld(
  2878. webpage, video_id, default={}, expected_type='VideoObject')
  2879. if json_ld.get('url'):
  2880. return merge_dicts(json_ld, info_dict)
  2881. def check_video(vurl):
  2882. if YoutubeIE.suitable(vurl):
  2883. return True
  2884. if RtmpIE.suitable(vurl):
  2885. return True
  2886. vpath = compat_urlparse.urlparse(vurl).path
  2887. vext = determine_ext(vpath)
  2888. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
  2889. def filter_video(urls):
  2890. return list(filter(check_video, urls))
  2891. # Start with something easy: JW Player in SWFObject
  2892. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  2893. if not found:
  2894. # Look for gorilla-vid style embedding
  2895. found = filter_video(re.findall(r'''(?sx)
  2896. (?:
  2897. jw_plugins|
  2898. JWPlayerOptions|
  2899. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  2900. )
  2901. .*?
  2902. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  2903. if not found:
  2904. # Broaden the search a little bit
  2905. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  2906. if not found:
  2907. # Broaden the findall a little bit: JWPlayer JS loader
  2908. found = filter_video(re.findall(
  2909. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  2910. if not found:
  2911. # Flow player
  2912. found = filter_video(re.findall(r'''(?xs)
  2913. flowplayer\("[^"]+",\s*
  2914. \{[^}]+?\}\s*,
  2915. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  2916. ["']?url["']?\s*:\s*["']([^"']+)["']
  2917. ''', webpage))
  2918. if not found:
  2919. # Cinerama player
  2920. found = re.findall(
  2921. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  2922. if not found:
  2923. # Try to find twitter cards info
  2924. # twitter:player:stream should be checked before twitter:player since
  2925. # it is expected to contain a raw stream (see
  2926. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  2927. found = filter_video(re.findall(
  2928. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  2929. if not found:
  2930. # We look for Open Graph info:
  2931. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  2932. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  2933. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  2934. if m_video_type is not None:
  2935. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  2936. if not found:
  2937. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  2938. found = re.search(
  2939. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  2940. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  2941. webpage)
  2942. if not found:
  2943. # Look also in Refresh HTTP header
  2944. refresh_header = head_response.headers.get('Refresh')
  2945. if refresh_header:
  2946. # In python 2 response HTTP headers are bytestrings
  2947. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  2948. refresh_header = refresh_header.decode('iso-8859-1')
  2949. found = re.search(REDIRECT_REGEX, refresh_header)
  2950. if found:
  2951. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  2952. if new_url != url:
  2953. self.report_following_redirect(new_url)
  2954. return {
  2955. '_type': 'url',
  2956. 'url': new_url,
  2957. }
  2958. else:
  2959. found = None
  2960. if not found:
  2961. # twitter:player is a https URL to iframe player that may or may not
  2962. # be supported by youtube-dl thus this is checked the very last (see
  2963. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  2964. embed_url = self._html_search_meta('twitter:player', webpage, default=None)
  2965. if embed_url and embed_url != url:
  2966. return self.url_result(embed_url)
  2967. if not found:
  2968. raise UnsupportedError(url)
  2969. entries = []
  2970. for video_url in orderedSet(found):
  2971. video_url = unescapeHTML(video_url)
  2972. video_url = video_url.replace('\\/', '/')
  2973. video_url = compat_urlparse.urljoin(url, video_url)
  2974. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  2975. # Sometimes, jwplayer extraction will result in a YouTube URL
  2976. if YoutubeIE.suitable(video_url):
  2977. entries.append(self.url_result(video_url, 'Youtube'))
  2978. continue
  2979. # here's a fun little line of code for you:
  2980. video_id = os.path.splitext(video_id)[0]
  2981. entry_info_dict = {
  2982. 'id': video_id,
  2983. 'uploader': video_uploader,
  2984. 'title': video_title,
  2985. 'age_limit': age_limit,
  2986. }
  2987. if RtmpIE.suitable(video_url):
  2988. entry_info_dict.update({
  2989. '_type': 'url_transparent',
  2990. 'ie_key': RtmpIE.ie_key(),
  2991. 'url': video_url,
  2992. })
  2993. entries.append(entry_info_dict)
  2994. continue
  2995. ext = determine_ext(video_url)
  2996. if ext == 'smil':
  2997. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  2998. elif ext == 'xspf':
  2999. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  3000. elif ext == 'm3u8':
  3001. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  3002. elif ext == 'mpd':
  3003. entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
  3004. elif ext == 'f4m':
  3005. entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
  3006. elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
  3007. # Just matching .ism/manifest is not enough to be reliably sure
  3008. # whether it's actually an ISM manifest or some other streaming
  3009. # manifest since there are various streaming URL formats
  3010. # possible (see [1]) as well as some other shenanigans like
  3011. # .smil/manifest URLs that actually serve an ISM (see [2]) and
  3012. # so on.
  3013. # Thus the most reasonable way to solve this is to delegate
  3014. # to generic extractor in order to look into the contents of
  3015. # the manifest itself.
  3016. # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
  3017. # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
  3018. entry_info_dict = self.url_result(
  3019. smuggle_url(video_url, {'to_generic': True}),
  3020. GenericIE.ie_key())
  3021. else:
  3022. entry_info_dict['url'] = video_url
  3023. if entry_info_dict.get('formats'):
  3024. self._sort_formats(entry_info_dict['formats'])
  3025. entries.append(entry_info_dict)
  3026. if len(entries) == 1:
  3027. return entries[0]
  3028. else:
  3029. for num, e in enumerate(entries, start=1):
  3030. # 'url' results don't have a title
  3031. if e.get('title') is not None:
  3032. e['title'] = '%s (%d)' % (e['title'], num)
  3033. return {
  3034. '_type': 'playlist',
  3035. 'entries': entries,
  3036. }