generic.py 151 KB

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321232223232324232523262327232823292330233123322333233423352336233723382339234023412342234323442345234623472348234923502351235223532354235523562357235823592360236123622363236423652366236723682369237023712372237323742375237623772378237923802381238223832384238523862387238823892390239123922393239423952396239723982399240024012402240324042405240624072408240924102411241224132414241524162417241824192420242124222423242424252426242724282429243024312432243324342435243624372438243924402441244224432444244524462447244824492450245124522453245424552456245724582459246024612462246324642465246624672468246924702471247224732474247524762477247824792480248124822483248424852486248724882489249024912492249324942495249624972498249925002501250225032504250525062507250825092510251125122513251425152516251725182519252025212522252325242525252625272528252925302531253225332534253525362537253825392540254125422543254425452546254725482549255025512552255325542555255625572558255925602561256225632564256525662567256825692570257125722573257425752576257725782579258025812582258325842585258625872588258925902591259225932594259525962597259825992600260126022603260426052606260726082609261026112612261326142615261626172618261926202621262226232624262526262627262826292630263126322633263426352636263726382639264026412642264326442645264626472648264926502651265226532654265526562657265826592660266126622663266426652666266726682669267026712672267326742675267626772678267926802681268226832684268526862687268826892690269126922693269426952696269726982699270027012702270327042705270627072708270927102711271227132714271527162717271827192720272127222723272427252726272727282729273027312732273327342735273627372738273927402741274227432744274527462747274827492750275127522753275427552756275727582759276027612762276327642765276627672768276927702771277227732774277527762777277827792780278127822783278427852786278727882789279027912792279327942795279627972798279928002801280228032804280528062807280828092810281128122813281428152816281728182819282028212822282328242825282628272828282928302831283228332834283528362837283828392840284128422843284428452846284728482849285028512852285328542855285628572858285928602861286228632864286528662867286828692870287128722873287428752876287728782879288028812882288328842885288628872888288928902891289228932894289528962897289828992900290129022903290429052906290729082909291029112912291329142915291629172918291929202921292229232924292529262927292829292930293129322933293429352936293729382939294029412942294329442945294629472948294929502951295229532954295529562957295829592960296129622963296429652966296729682969297029712972297329742975297629772978297929802981298229832984298529862987298829892990299129922993299429952996299729982999300030013002300330043005300630073008300930103011301230133014301530163017301830193020302130223023302430253026302730283029303030313032303330343035303630373038303930403041304230433044304530463047304830493050305130523053305430553056305730583059306030613062306330643065306630673068306930703071307230733074307530763077307830793080308130823083308430853086308730883089309030913092309330943095309630973098309931003101310231033104310531063107310831093110311131123113311431153116311731183119312031213122312331243125312631273128312931303131313231333134313531363137313831393140314131423143314431453146314731483149315031513152315331543155315631573158315931603161316231633164316531663167316831693170317131723173317431753176317731783179318031813182318331843185318631873188318931903191319231933194319531963197319831993200320132023203320432053206320732083209321032113212321332143215321632173218321932203221322232233224322532263227322832293230323132323233323432353236323732383239324032413242324332443245324632473248324932503251325232533254325532563257325832593260326132623263326432653266326732683269327032713272327332743275327632773278327932803281328232833284328532863287328832893290329132923293329432953296329732983299330033013302330333043305330633073308330933103311331233133314331533163317331833193320332133223323332433253326332733283329333033313332333333343335333633373338333933403341334233433344334533463347334833493350335133523353335433553356335733583359336033613362336333643365336633673368336933703371337233733374337533763377337833793380338133823383338433853386338733883389339033913392339333943395339633973398339934003401340234033404340534063407340834093410341134123413341434153416341734183419342034213422342334243425342634273428342934303431343234333434343534363437343834393440344134423443344434453446344734483449345034513452345334543455345634573458345934603461346234633464346534663467346834693470347134723473347434753476347734783479348034813482348334843485348634873488348934903491349234933494349534963497349834993500350135023503350435053506350735083509351035113512351335143515351635173518351935203521352235233524352535263527352835293530353135323533353435353536353735383539354035413542354335443545354635473548354935503551355235533554355535563557355835593560356135623563356435653566356735683569357035713572357335743575357635773578357935803581358235833584358535863587358835893590359135923593359435953596359735983599360036013602360336043605360636073608360936103611361236133614361536163617361836193620362136223623362436253626362736283629363036313632363336343635363636373638363936403641364236433644364536463647364836493650365136523653365436553656365736583659366036613662366336643665366636673668366936703671367236733674367536763677367836793680368136823683368436853686368736883689369036913692369336943695369636973698369937003701370237033704370537063707370837093710371137123713371437153716371737183719372037213722372337243725372637273728372937303731373237333734373537363737373837393740374137423743374437453746374737483749
  1. # coding: utf-8
  2. from __future__ import unicode_literals
  3. import os
  4. import re
  5. import sys
  6. from .common import InfoExtractor
  7. from .youtube import YoutubeIE
  8. from ..compat import (
  9. compat_etree_fromstring,
  10. compat_str,
  11. compat_urllib_parse_unquote,
  12. compat_urlparse,
  13. compat_xml_parse_error,
  14. )
  15. from ..utils import (
  16. determine_ext,
  17. ExtractorError,
  18. float_or_none,
  19. HEADRequest,
  20. int_or_none,
  21. is_html,
  22. js_to_json,
  23. KNOWN_EXTENSIONS,
  24. merge_dicts,
  25. mimetype2ext,
  26. orderedSet,
  27. parse_duration,
  28. parse_resolution,
  29. sanitized_Request,
  30. smuggle_url,
  31. unescapeHTML,
  32. unified_timestamp,
  33. unsmuggle_url,
  34. UnsupportedError,
  35. url_or_none,
  36. xpath_attr,
  37. xpath_text,
  38. xpath_with_ns,
  39. )
  40. from .commonprotocols import RtmpIE
  41. from .brightcove import (
  42. BrightcoveLegacyIE,
  43. BrightcoveNewIE,
  44. )
  45. from .nexx import (
  46. NexxIE,
  47. NexxEmbedIE,
  48. )
  49. from .nbc import NBCSportsVPlayerIE
  50. from .ooyala import OoyalaIE
  51. from .rutv import RUTVIE
  52. from .tvc import TVCIE
  53. from .sportbox import SportBoxIE
  54. from .myvi import MyviIE
  55. from .condenast import CondeNastIE
  56. from .udn import UDNEmbedIE
  57. from .senateisvp import SenateISVPIE
  58. from .svt import SVTIE
  59. from .pornhub import PornHubIE
  60. from .xhamster import XHamsterEmbedIE
  61. from .tnaflix import TNAFlixNetworkEmbedIE
  62. from .drtuber import DrTuberIE
  63. from .redtube import RedTubeIE
  64. from .tube8 import Tube8IE
  65. from .mofosex import MofosexEmbedIE
  66. from .spankwire import SpankwireIE
  67. from .youporn import YouPornIE
  68. from .vimeo import (
  69. VimeoIE,
  70. VHXEmbedIE,
  71. )
  72. from .dailymotion import DailymotionIE
  73. from .dailymail import DailyMailIE
  74. from .onionstudios import OnionStudiosIE
  75. from .viewlift import ViewLiftEmbedIE
  76. from .mtv import MTVServicesEmbeddedIE
  77. from .pladform import PladformIE
  78. from .videomore import VideomoreIE
  79. from .webcaster import WebcasterFeedIE
  80. from .googledrive import GoogleDriveIE
  81. from .jwplatform import JWPlatformIE
  82. from .digiteka import DigitekaIE
  83. from .arkena import ArkenaIE
  84. from .instagram import InstagramIE
  85. from .threeqsdn import ThreeQSDNIE
  86. from .theplatform import ThePlatformIE
  87. from .kaltura import KalturaIE
  88. from .eagleplatform import EaglePlatformIE
  89. from .facebook import FacebookIE
  90. from .soundcloud import SoundcloudEmbedIE
  91. from .tunein import TuneInBaseIE
  92. from .vbox7 import Vbox7IE
  93. from .dbtv import DBTVIE
  94. from .piksel import PikselIE
  95. from .videa import VideaIE
  96. from .twentymin import TwentyMinutenIE
  97. from .ustream import UstreamIE
  98. from .arte import ArteTVEmbedIE
  99. from .videopress import VideoPressIE
  100. from .rutube import RutubeIE
  101. from .limelight import LimelightBaseIE
  102. from .anvato import AnvatoIE
  103. from .washingtonpost import WashingtonPostIE
  104. from .wistia import WistiaIE
  105. from .mediaset import MediasetIE
  106. from .joj import JojIE
  107. from .megaphone import MegaphoneIE
  108. from .vzaar import VzaarIE
  109. from .channel9 import Channel9IE
  110. from .vshare import VShareIE
  111. from .mediasite import MediasiteIE
  112. from .springboardplatform import SpringboardPlatformIE
  113. from .yapfiles import YapFilesIE
  114. from .vice import ViceIE
  115. from .xfileshare import XFileShareIE
  116. from .cloudflarestream import CloudflareStreamIE
  117. from .peertube import PeerTubeIE
  118. from .teachable import TeachableIE
  119. from .indavideo import IndavideoEmbedIE
  120. from .apa import APAIE
  121. from .foxnews import FoxNewsIE
  122. from .viqeo import ViqeoIE
  123. from .expressen import ExpressenIE
  124. from .zype import ZypeIE
  125. from .odnoklassniki import OdnoklassnikiIE
  126. from .vk import VKIE
  127. from .kinja import KinjaEmbedIE
  128. from .arcpublishing import ArcPublishingIE
  129. from .medialaan import MedialaanIE
  130. from .simplecast import SimplecastIE
  131. class GenericIE(InfoExtractor):
  132. IE_DESC = 'Generic downloader that works on some sites'
  133. _VALID_URL = r'.*'
  134. IE_NAME = 'generic'
  135. _TESTS = [
  136. # Direct link to a video
  137. {
  138. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  139. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  140. 'info_dict': {
  141. 'id': 'trailer',
  142. 'ext': 'mp4',
  143. 'title': 'trailer',
  144. 'upload_date': '20100513',
  145. }
  146. },
  147. # Direct link to media delivered compressed (until Accept-Encoding is *)
  148. {
  149. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  150. 'md5': '128c42e68b13950268b648275386fc74',
  151. 'info_dict': {
  152. 'id': 'FictionJunction-Parallel_Hearts',
  153. 'ext': 'flac',
  154. 'title': 'FictionJunction-Parallel_Hearts',
  155. 'upload_date': '20140522',
  156. },
  157. 'expected_warnings': [
  158. 'URL could be a direct video link, returning it as such.'
  159. ],
  160. 'skip': 'URL invalid',
  161. },
  162. # Direct download with broken HEAD
  163. {
  164. 'url': 'http://ai-radio.org:8000/radio.opus',
  165. 'info_dict': {
  166. 'id': 'radio',
  167. 'ext': 'opus',
  168. 'title': 'radio',
  169. },
  170. 'params': {
  171. 'skip_download': True, # infinite live stream
  172. },
  173. 'expected_warnings': [
  174. r'501.*Not Implemented',
  175. r'400.*Bad Request',
  176. ],
  177. },
  178. # Direct link with incorrect MIME type
  179. {
  180. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  181. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  182. 'info_dict': {
  183. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  184. 'id': '5_Lennart_Poettering_-_Systemd',
  185. 'ext': 'webm',
  186. 'title': '5_Lennart_Poettering_-_Systemd',
  187. 'upload_date': '20141120',
  188. },
  189. 'expected_warnings': [
  190. 'URL could be a direct video link, returning it as such.'
  191. ]
  192. },
  193. # RSS feed
  194. {
  195. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  196. 'info_dict': {
  197. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  198. 'title': 'Zero Punctuation',
  199. 'description': 're:.*groundbreaking video review series.*'
  200. },
  201. 'playlist_mincount': 11,
  202. },
  203. # RSS feed with enclosure
  204. {
  205. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  206. 'info_dict': {
  207. 'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  208. 'title': 'MSNBC Rachel Maddow (video)',
  209. 'description': 're:.*her unique approach to storytelling.*',
  210. },
  211. 'playlist': [{
  212. 'info_dict': {
  213. 'ext': 'mov',
  214. 'id': 'pdv_maddow_netcast_mov-12-04-2020-224335',
  215. 'title': 're:MSNBC Rachel Maddow',
  216. 'description': 're:.*her unique approach to storytelling.*',
  217. 'timestamp': int,
  218. 'upload_date': compat_str,
  219. 'duration': float,
  220. },
  221. }],
  222. },
  223. # RSS feed with item with description and thumbnails
  224. {
  225. 'url': 'https://anchor.fm/s/dd00e14/podcast/rss',
  226. 'info_dict': {
  227. 'id': 'https://anchor.fm/s/dd00e14/podcast/rss',
  228. 'title': 're:.*100% Hydrogen.*',
  229. 'description': 're:.*In this episode.*',
  230. },
  231. 'playlist': [{
  232. 'info_dict': {
  233. 'ext': 'm4a',
  234. 'id': 'c1c879525ce2cb640b344507e682c36d',
  235. 'title': 're:Hydrogen!',
  236. 'description': 're:.*In this episode we are going.*',
  237. 'timestamp': 1567977776,
  238. 'upload_date': '20190908',
  239. 'duration': 459,
  240. 'thumbnail': r're:^https?://.*\.jpg$',
  241. 'episode_number': 1,
  242. 'season_number': 1,
  243. 'age_limit': 0,
  244. },
  245. }],
  246. 'params': {
  247. 'skip_download': True,
  248. },
  249. },
  250. # RSS feed with enclosures and unsupported link URLs
  251. {
  252. 'url': 'http://www.hellointernet.fm/podcast?format=rss',
  253. 'info_dict': {
  254. 'id': 'http://www.hellointernet.fm/podcast?format=rss',
  255. 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
  256. 'title': 'Hello Internet',
  257. },
  258. 'playlist_mincount': 100,
  259. },
  260. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  261. {
  262. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  263. 'info_dict': {
  264. 'id': 'smil',
  265. 'ext': 'mp4',
  266. 'title': 'Automatics, robotics and biocybernetics',
  267. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  268. 'upload_date': '20130627',
  269. 'formats': 'mincount:16',
  270. 'subtitles': 'mincount:1',
  271. },
  272. 'params': {
  273. 'force_generic_extractor': True,
  274. 'skip_download': True,
  275. },
  276. },
  277. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  278. {
  279. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  280. 'info_dict': {
  281. 'id': 'hds',
  282. 'ext': 'flv',
  283. 'title': 'hds',
  284. 'formats': 'mincount:1',
  285. },
  286. 'params': {
  287. 'skip_download': True,
  288. },
  289. },
  290. # SMIL from https://www.restudy.dk/video/play/id/1637
  291. {
  292. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  293. 'info_dict': {
  294. 'id': 'video_1637',
  295. 'ext': 'flv',
  296. 'title': 'video_1637',
  297. 'formats': 'mincount:3',
  298. },
  299. 'params': {
  300. 'skip_download': True,
  301. },
  302. },
  303. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  304. {
  305. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  306. 'info_dict': {
  307. 'id': 'smil-service',
  308. 'ext': 'flv',
  309. 'title': 'smil-service',
  310. 'formats': 'mincount:1',
  311. },
  312. 'params': {
  313. 'skip_download': True,
  314. },
  315. },
  316. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  317. {
  318. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  319. 'info_dict': {
  320. 'id': '4719370',
  321. 'ext': 'mp4',
  322. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  323. 'formats': 'mincount:3',
  324. },
  325. 'params': {
  326. 'skip_download': True,
  327. },
  328. },
  329. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  330. {
  331. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  332. 'info_dict': {
  333. 'id': 'mZlp2ctYIUEB',
  334. 'ext': 'mp4',
  335. 'title': 'Tikibad ontruimd wegens brand',
  336. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  337. 'thumbnail': r're:^https?://.*\.jpg$',
  338. 'duration': 33,
  339. },
  340. 'params': {
  341. 'skip_download': True,
  342. },
  343. },
  344. # MPD from http://dash-mse-test.appspot.com/media.html
  345. {
  346. 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
  347. 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
  348. 'info_dict': {
  349. 'id': 'car-20120827-manifest',
  350. 'ext': 'mp4',
  351. 'title': 'car-20120827-manifest',
  352. 'formats': 'mincount:9',
  353. 'upload_date': '20130904',
  354. },
  355. 'params': {
  356. 'format': 'bestvideo',
  357. },
  358. },
  359. # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
  360. {
  361. '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',
  362. 'info_dict': {
  363. 'id': 'content',
  364. 'ext': 'mp4',
  365. 'title': 'content',
  366. 'formats': 'mincount:8',
  367. },
  368. 'params': {
  369. # m3u8 downloads
  370. 'skip_download': True,
  371. },
  372. 'skip': 'video gone',
  373. },
  374. # m3u8 served with Content-Type: text/plain
  375. {
  376. 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
  377. 'info_dict': {
  378. 'id': 'index',
  379. 'ext': 'mp4',
  380. 'title': 'index',
  381. 'upload_date': '20140720',
  382. 'formats': 'mincount:11',
  383. },
  384. 'params': {
  385. # m3u8 downloads
  386. 'skip_download': True,
  387. },
  388. 'skip': 'video gone',
  389. },
  390. # google redirect
  391. {
  392. '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',
  393. 'info_dict': {
  394. 'id': 'cmQHVoWB5FY',
  395. 'ext': 'mp4',
  396. 'upload_date': '20130224',
  397. 'uploader_id': 'TheVerge',
  398. 'description': r're:^Chris Ziegler takes a look at the\.*',
  399. 'uploader': 'The Verge',
  400. 'title': 'First Firefox OS phones side-by-side',
  401. },
  402. 'params': {
  403. 'skip_download': False,
  404. }
  405. },
  406. {
  407. # redirect in Refresh HTTP header
  408. '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',
  409. 'info_dict': {
  410. 'id': 'pO8h3EaFRdo',
  411. 'ext': 'mp4',
  412. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  413. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  414. 'upload_date': '20150917',
  415. 'uploader_id': 'brtvofficial',
  416. 'uploader': 'Boiler Room',
  417. },
  418. 'params': {
  419. 'skip_download': False,
  420. },
  421. },
  422. {
  423. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  424. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  425. 'info_dict': {
  426. 'id': '13601338388002',
  427. 'ext': 'mp4',
  428. 'uploader': 'www.hodiho.fr',
  429. 'title': 'R\u00e9gis plante sa Jeep',
  430. }
  431. },
  432. # bandcamp page with custom domain
  433. {
  434. 'add_ie': ['Bandcamp'],
  435. 'url': 'http://bronyrock.com/track/the-pony-mash',
  436. 'info_dict': {
  437. 'id': '3235767654',
  438. 'ext': 'mp3',
  439. 'title': 'The Pony Mash',
  440. 'uploader': 'M_Pallante',
  441. },
  442. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  443. },
  444. {
  445. # embedded brightcove video
  446. # it also tests brightcove videos that need to set the 'Referer'
  447. # in the http requests
  448. 'add_ie': ['BrightcoveLegacy'],
  449. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  450. 'info_dict': {
  451. 'id': '2765128793001',
  452. 'ext': 'mp4',
  453. 'title': 'Le cours de bourse : l’analyse technique',
  454. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  455. 'uploader': 'BFM BUSINESS',
  456. },
  457. 'params': {
  458. 'skip_download': True,
  459. },
  460. },
  461. {
  462. # embedded with itemprop embedURL and video id spelled as `idVideo`
  463. 'add_id': ['BrightcoveLegacy'],
  464. 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
  465. 'info_dict': {
  466. 'id': '5255628253001',
  467. 'ext': 'mp4',
  468. 'title': 'md5:37c519b1128915607601e75a87995fc0',
  469. 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
  470. 'uploader': 'BFM BUSINESS',
  471. 'uploader_id': '876450612001',
  472. 'timestamp': 1482255315,
  473. 'upload_date': '20161220',
  474. },
  475. 'params': {
  476. 'skip_download': True,
  477. },
  478. },
  479. {
  480. # https://github.com/ytdl-org/youtube-dl/issues/2253
  481. 'url': 'http://bcove.me/i6nfkrc3',
  482. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  483. 'info_dict': {
  484. 'id': '3101154703001',
  485. 'ext': 'mp4',
  486. 'title': 'Still no power',
  487. 'uploader': 'thestar.com',
  488. '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.',
  489. },
  490. 'add_ie': ['BrightcoveLegacy'],
  491. 'skip': 'video gone',
  492. },
  493. {
  494. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  495. 'md5': 'fb973ecf6e4a78a67453647444222983',
  496. 'info_dict': {
  497. 'id': '3414141473001',
  498. 'ext': 'mp4',
  499. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  500. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  501. 'uploader': 'Championat',
  502. },
  503. },
  504. {
  505. # https://github.com/ytdl-org/youtube-dl/issues/3541
  506. 'add_ie': ['BrightcoveLegacy'],
  507. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  508. 'info_dict': {
  509. 'id': '3866516442001',
  510. 'ext': 'mp4',
  511. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  512. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  513. 'uploader': 'SBS Broadcasting',
  514. },
  515. 'skip': 'Restricted to Netherlands',
  516. 'params': {
  517. 'skip_download': True, # m3u8 download
  518. },
  519. },
  520. {
  521. # Brightcove video in <iframe>
  522. 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
  523. 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
  524. 'info_dict': {
  525. 'id': '5360463607001',
  526. 'ext': 'mp4',
  527. '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',
  528. '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。',
  529. 'uploader': 'United Nations',
  530. 'uploader_id': '1362235914001',
  531. 'timestamp': 1489593889,
  532. 'upload_date': '20170315',
  533. },
  534. 'add_ie': ['BrightcoveLegacy'],
  535. },
  536. {
  537. # Brightcove with alternative playerID key
  538. 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
  539. 'info_dict': {
  540. 'id': 'nmeth.2062_SV1',
  541. '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',
  542. },
  543. 'playlist': [{
  544. 'info_dict': {
  545. 'id': '2228375078001',
  546. 'ext': 'mp4',
  547. 'title': 'nmeth.2062-sv1',
  548. 'description': 'nmeth.2062-sv1',
  549. 'timestamp': 1363357591,
  550. 'upload_date': '20130315',
  551. 'uploader': 'Nature Publishing Group',
  552. 'uploader_id': '1964492299001',
  553. },
  554. }],
  555. },
  556. {
  557. # Brightcove with UUID in videoPlayer
  558. 'url': 'http://www8.hp.com/cn/zh/home.html',
  559. 'info_dict': {
  560. 'id': '5255815316001',
  561. 'ext': 'mp4',
  562. 'title': 'Sprocket Video - China',
  563. 'description': 'Sprocket Video - China',
  564. 'uploader': 'HP-Video Gallery',
  565. 'timestamp': 1482263210,
  566. 'upload_date': '20161220',
  567. 'uploader_id': '1107601872001',
  568. },
  569. 'params': {
  570. 'skip_download': True, # m3u8 download
  571. },
  572. 'skip': 'video rotates...weekly?',
  573. },
  574. {
  575. # Brightcove:new type [2].
  576. 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
  577. 'md5': '2b35148fcf48da41c9fb4591650784f3',
  578. 'info_dict': {
  579. 'id': '5348741021001',
  580. 'ext': 'mp4',
  581. 'upload_date': '20170306',
  582. 'uploader_id': '4191638492001',
  583. 'timestamp': 1488769918,
  584. 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
  585. },
  586. },
  587. {
  588. # Alternative brightcove <video> attributes
  589. '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/',
  590. 'info_dict': {
  591. 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
  592. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
  593. },
  594. 'playlist': [{
  595. 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
  596. 'info_dict': {
  597. 'id': '5311302538001',
  598. 'ext': 'mp4',
  599. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
  600. 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
  601. 'timestamp': 1486321708,
  602. 'upload_date': '20170205',
  603. 'uploader_id': '800000640001',
  604. },
  605. 'only_matching': True,
  606. }],
  607. },
  608. {
  609. # Brightcove with UUID in videoPlayer
  610. 'url': 'http://www8.hp.com/cn/zh/home.html',
  611. 'info_dict': {
  612. 'id': '5255815316001',
  613. 'ext': 'mp4',
  614. 'title': 'Sprocket Video - China',
  615. 'description': 'Sprocket Video - China',
  616. 'uploader': 'HP-Video Gallery',
  617. 'timestamp': 1482263210,
  618. 'upload_date': '20161220',
  619. 'uploader_id': '1107601872001',
  620. },
  621. 'params': {
  622. 'skip_download': True, # m3u8 download
  623. },
  624. },
  625. # ooyala video
  626. {
  627. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  628. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  629. 'info_dict': {
  630. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  631. 'ext': 'mp4',
  632. 'title': '2cc213299525360.mov', # that's what we get
  633. 'duration': 238.231,
  634. },
  635. 'add_ie': ['Ooyala'],
  636. },
  637. {
  638. # ooyala video embedded with http://player.ooyala.com/iframe.js
  639. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  640. 'info_dict': {
  641. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  642. 'ext': 'mp4',
  643. 'title': '"Steve Jobs: Man in the Machine" trailer',
  644. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  645. 'duration': 135.427,
  646. },
  647. 'params': {
  648. 'skip_download': True,
  649. },
  650. 'skip': 'movie expired',
  651. },
  652. # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
  653. {
  654. 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
  655. 'info_dict': {
  656. 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
  657. 'ext': 'mp4',
  658. 'title': 'Steampunk Fest Comes to Honesdale',
  659. 'duration': 43.276,
  660. },
  661. 'params': {
  662. 'skip_download': True,
  663. }
  664. },
  665. # embed.ly video
  666. {
  667. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  668. 'info_dict': {
  669. 'id': '9ODmcdjQcHQ',
  670. 'ext': 'mp4',
  671. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  672. 'upload_date': '20140225',
  673. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  674. 'uploader': 'Tested',
  675. 'uploader_id': 'testedcom',
  676. },
  677. # No need to test YoutubeIE here
  678. 'params': {
  679. 'skip_download': True,
  680. },
  681. },
  682. # funnyordie embed
  683. {
  684. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  685. 'info_dict': {
  686. 'id': '18e820ec3f',
  687. 'ext': 'mp4',
  688. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  689. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  690. },
  691. # HEAD requests lead to endless 301, while GET is OK
  692. 'expected_warnings': ['301'],
  693. },
  694. # RUTV embed
  695. {
  696. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  697. 'info_dict': {
  698. 'id': '776940',
  699. 'ext': 'mp4',
  700. 'title': 'Охотское море стало целиком российским',
  701. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  702. },
  703. 'params': {
  704. # m3u8 download
  705. 'skip_download': True,
  706. },
  707. },
  708. # TVC embed
  709. {
  710. '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/',
  711. 'info_dict': {
  712. 'id': '55304',
  713. 'ext': 'mp4',
  714. 'title': 'Дошкольное воспитание',
  715. },
  716. },
  717. # SportBox embed
  718. {
  719. 'url': 'http://www.vestifinance.ru/articles/25753',
  720. 'info_dict': {
  721. 'id': '25753',
  722. 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  723. },
  724. 'playlist': [{
  725. 'info_dict': {
  726. 'id': '370908',
  727. 'title': 'Госзаказ. День 3',
  728. 'ext': 'mp4',
  729. }
  730. }, {
  731. 'info_dict': {
  732. 'id': '370905',
  733. 'title': 'Госзаказ. День 2',
  734. 'ext': 'mp4',
  735. }
  736. }, {
  737. 'info_dict': {
  738. 'id': '370902',
  739. 'title': 'Госзаказ. День 1',
  740. 'ext': 'mp4',
  741. }
  742. }],
  743. 'params': {
  744. # m3u8 download
  745. 'skip_download': True,
  746. },
  747. },
  748. # Myvi.ru embed
  749. {
  750. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  751. 'info_dict': {
  752. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  753. 'ext': 'mp4',
  754. 'title': 'Ужастики, русский трейлер (2015)',
  755. 'thumbnail': r're:^https?://.*\.jpg$',
  756. 'duration': 153,
  757. }
  758. },
  759. # XHamster embed
  760. {
  761. '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',
  762. 'info_dict': {
  763. 'id': 'showthread',
  764. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  765. },
  766. 'playlist_mincount': 7,
  767. # This forum does not allow <iframe> syntaxes anymore
  768. # Now HTML tags are displayed as-is
  769. 'skip': 'No videos on this page',
  770. },
  771. # Embedded TED video
  772. {
  773. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  774. 'md5': '65fdff94098e4a607385a60c5177c638',
  775. 'info_dict': {
  776. 'id': '1969',
  777. 'ext': 'mp4',
  778. 'title': 'Hidden miracles of the natural world',
  779. 'uploader': 'Louie Schwartzberg',
  780. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  781. }
  782. },
  783. # nowvideo embed hidden behind percent encoding
  784. {
  785. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  786. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  787. 'info_dict': {
  788. 'id': '06e53103ca9aa',
  789. 'ext': 'flv',
  790. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  791. 'description': 'No description',
  792. },
  793. },
  794. # arte embed
  795. {
  796. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  797. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  798. 'info_dict': {
  799. 'id': '048195-004_PLUS7-F',
  800. 'ext': 'flv',
  801. 'title': 'X:enius',
  802. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  803. 'upload_date': '20140320',
  804. },
  805. 'params': {
  806. 'skip_download': 'Requires rtmpdump'
  807. },
  808. 'skip': 'video gone',
  809. },
  810. # francetv embed
  811. {
  812. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  813. 'info_dict': {
  814. 'id': 'EV_30231',
  815. 'ext': 'mp4',
  816. 'title': 'Alcaline, le concert avec Calogero',
  817. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  818. 'upload_date': '20150226',
  819. 'timestamp': 1424989860,
  820. 'duration': 5400,
  821. },
  822. 'params': {
  823. # m3u8 downloads
  824. 'skip_download': True,
  825. },
  826. 'expected_warnings': [
  827. 'Forbidden'
  828. ]
  829. },
  830. # Condé Nast embed
  831. {
  832. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  833. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  834. 'info_dict': {
  835. 'id': '53501be369702d3275860000',
  836. 'ext': 'mp4',
  837. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  838. }
  839. },
  840. # Dailymotion embed
  841. {
  842. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  843. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  844. 'info_dict': {
  845. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  846. 'ext': 'mp4',
  847. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  848. 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
  849. 'uploader': 'Spi0n',
  850. 'uploader_id': 'xgditw',
  851. 'upload_date': '20140425',
  852. 'timestamp': 1398441542,
  853. },
  854. 'add_ie': ['Dailymotion'],
  855. },
  856. # DailyMail embed
  857. {
  858. 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
  859. 'info_dict': {
  860. 'id': '1495629',
  861. 'ext': 'mp4',
  862. 'title': 'Care worker punches elderly dementia patient in head 11 times',
  863. 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
  864. },
  865. 'add_ie': ['DailyMail'],
  866. 'params': {
  867. 'skip_download': True,
  868. },
  869. },
  870. # YouTube embed
  871. {
  872. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  873. 'info_dict': {
  874. 'id': 'FXRb4ykk4S0',
  875. 'ext': 'mp4',
  876. 'title': 'The NBL Auction 2014',
  877. 'uploader': 'BADMINTON England',
  878. 'uploader_id': 'BADMINTONEvents',
  879. 'upload_date': '20140603',
  880. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  881. },
  882. 'add_ie': ['Youtube'],
  883. 'params': {
  884. 'skip_download': True,
  885. }
  886. },
  887. # MTVServices embed
  888. {
  889. 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
  890. 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
  891. 'info_dict': {
  892. 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
  893. 'ext': 'mp4',
  894. 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
  895. 'description': 'Two valets share their love for movie star Liam Neesons.',
  896. 'timestamp': 1349922600,
  897. 'upload_date': '20121011',
  898. },
  899. },
  900. # YouTube embed via <data-embed-url="">
  901. {
  902. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  903. 'info_dict': {
  904. 'id': '4vAffPZIT44',
  905. 'ext': 'mp4',
  906. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  907. 'uploader': 'Gameloft',
  908. 'uploader_id': 'gameloft',
  909. 'upload_date': '20140828',
  910. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  911. },
  912. 'params': {
  913. 'skip_download': True,
  914. }
  915. },
  916. # YouTube <object> embed
  917. {
  918. 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
  919. 'md5': '516718101ec834f74318df76259fb3cc',
  920. 'info_dict': {
  921. 'id': 'msN87y-iEx0',
  922. 'ext': 'webm',
  923. 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
  924. 'upload_date': '20080526',
  925. 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
  926. 'uploader': 'Christopher Sykes',
  927. 'uploader_id': 'ChristopherJSykes',
  928. },
  929. 'add_ie': ['Youtube'],
  930. },
  931. # Camtasia studio
  932. {
  933. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  934. 'playlist': [{
  935. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  936. 'info_dict': {
  937. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  938. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  939. 'ext': 'flv',
  940. 'duration': 2235.90,
  941. }
  942. }, {
  943. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  944. 'info_dict': {
  945. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  946. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  947. 'ext': 'flv',
  948. 'duration': 2235.93,
  949. }
  950. }],
  951. 'info_dict': {
  952. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  953. }
  954. },
  955. # Flowplayer
  956. {
  957. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  958. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  959. 'info_dict': {
  960. 'id': '5123ea6d5e5a7',
  961. 'ext': 'mp4',
  962. 'age_limit': 18,
  963. 'uploader': 'www.handjobhub.com',
  964. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  965. }
  966. },
  967. # Multiple brightcove videos
  968. # https://github.com/ytdl-org/youtube-dl/issues/2283
  969. {
  970. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  971. 'info_dict': {
  972. 'id': 'always-never',
  973. 'title': 'Always / Never - The New Yorker',
  974. },
  975. 'playlist_count': 3,
  976. 'params': {
  977. 'extract_flat': False,
  978. 'skip_download': True,
  979. }
  980. },
  981. # MLB embed
  982. {
  983. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  984. 'md5': '96f09a37e44da40dd083e12d9a683327',
  985. 'info_dict': {
  986. 'id': '33322633',
  987. 'ext': 'mp4',
  988. 'title': 'Ump changes call to ball',
  989. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  990. 'duration': 48,
  991. 'timestamp': 1401537900,
  992. 'upload_date': '20140531',
  993. 'thumbnail': r're:^https?://.*\.jpg$',
  994. },
  995. },
  996. # Wistia embed
  997. {
  998. 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  999. 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
  1000. 'info_dict': {
  1001. 'id': '6e2wtrbdaf',
  1002. 'ext': 'mov',
  1003. 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
  1004. 'description': 'a Paywall Videos video from Remilon',
  1005. 'duration': 644.072,
  1006. 'uploader': 'study.com',
  1007. 'timestamp': 1459678540,
  1008. 'upload_date': '20160403',
  1009. 'filesize': 24687186,
  1010. },
  1011. },
  1012. {
  1013. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  1014. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  1015. 'info_dict': {
  1016. 'id': 'uxjb0lwrcz',
  1017. 'ext': 'mp4',
  1018. 'title': 'Conversation about Hexagonal Rails Part 1',
  1019. 'description': 'a Martin Fowler video from ThoughtWorks',
  1020. 'duration': 1715.0,
  1021. 'uploader': 'thoughtworks.wistia.com',
  1022. 'timestamp': 1401832161,
  1023. 'upload_date': '20140603',
  1024. },
  1025. },
  1026. # Wistia standard embed (async)
  1027. {
  1028. 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
  1029. 'info_dict': {
  1030. 'id': '807fafadvk',
  1031. 'ext': 'mp4',
  1032. 'title': 'Drip Brennan Dunn Workshop',
  1033. 'description': 'a JV Webinars video from getdrip-1',
  1034. 'duration': 4986.95,
  1035. 'timestamp': 1463607249,
  1036. 'upload_date': '20160518',
  1037. },
  1038. 'params': {
  1039. 'skip_download': True,
  1040. }
  1041. },
  1042. # Soundcloud embed
  1043. {
  1044. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  1045. 'info_dict': {
  1046. 'id': '174391317',
  1047. 'ext': 'mp3',
  1048. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  1049. 'uploader': 'Sophos Security',
  1050. 'title': 'Chet Chat 171 - Oct 29, 2014',
  1051. 'upload_date': '20141029',
  1052. }
  1053. },
  1054. # Soundcloud multiple embeds
  1055. {
  1056. 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
  1057. 'info_dict': {
  1058. 'id': '52809',
  1059. 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
  1060. },
  1061. 'playlist_mincount': 7,
  1062. },
  1063. # TuneIn station embed
  1064. {
  1065. 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
  1066. 'info_dict': {
  1067. 'id': '204146',
  1068. 'ext': 'mp3',
  1069. 'title': 'CNRV',
  1070. 'location': 'Paris, France',
  1071. 'is_live': True,
  1072. },
  1073. 'params': {
  1074. # Live stream
  1075. 'skip_download': True,
  1076. },
  1077. },
  1078. # Livestream embed
  1079. {
  1080. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  1081. 'info_dict': {
  1082. 'id': '67864563',
  1083. 'ext': 'flv',
  1084. 'upload_date': '20141112',
  1085. 'title': 'Rosetta #CometLanding webcast HL 10',
  1086. }
  1087. },
  1088. # Another Livestream embed, without 'new.' in URL
  1089. {
  1090. 'url': 'https://www.freespeech.org/',
  1091. 'info_dict': {
  1092. 'id': '123537347',
  1093. 'ext': 'mp4',
  1094. 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  1095. },
  1096. 'params': {
  1097. # Live stream
  1098. 'skip_download': True,
  1099. },
  1100. },
  1101. # LazyYT
  1102. {
  1103. 'url': 'https://skiplagged.com/',
  1104. 'info_dict': {
  1105. 'id': 'skiplagged',
  1106. 'title': 'Skiplagged: The smart way to find cheap flights',
  1107. },
  1108. 'playlist_mincount': 1,
  1109. 'add_ie': ['Youtube'],
  1110. },
  1111. # Cinchcast embed
  1112. {
  1113. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  1114. 'info_dict': {
  1115. 'id': '7141703',
  1116. 'ext': 'mp3',
  1117. 'upload_date': '20141126',
  1118. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  1119. }
  1120. },
  1121. # Cinerama player
  1122. {
  1123. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  1124. 'info_dict': {
  1125. 'id': '730m_DandD_1901_512k',
  1126. 'ext': 'mp4',
  1127. 'uploader': 'www.abc.net.au',
  1128. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  1129. }
  1130. },
  1131. # embedded viddler video
  1132. {
  1133. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  1134. 'info_dict': {
  1135. 'id': '4d03aad9',
  1136. 'ext': 'mp4',
  1137. 'uploader': 'deadspin',
  1138. 'title': 'WALL-TO-GORTAT',
  1139. 'timestamp': 1422285291,
  1140. 'upload_date': '20150126',
  1141. },
  1142. 'add_ie': ['Viddler'],
  1143. },
  1144. # Libsyn embed
  1145. {
  1146. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  1147. 'info_dict': {
  1148. 'id': '3377616',
  1149. 'ext': 'mp3',
  1150. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  1151. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  1152. 'upload_date': '20150220',
  1153. },
  1154. 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
  1155. },
  1156. # jwplayer YouTube
  1157. {
  1158. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  1159. 'info_dict': {
  1160. 'id': 'Mrj4DVp2zeA',
  1161. 'ext': 'mp4',
  1162. 'upload_date': '20150212',
  1163. 'uploader': 'The National Archives UK',
  1164. 'description': 'md5:8078af856dca76edc42910b61273dbbf',
  1165. 'uploader_id': 'NationalArchives08',
  1166. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  1167. },
  1168. },
  1169. # jwplayer rtmp
  1170. {
  1171. 'url': 'http://www.suffolk.edu/sjc/live.php',
  1172. 'info_dict': {
  1173. 'id': 'live',
  1174. 'ext': 'flv',
  1175. 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
  1176. 'uploader': 'www.suffolk.edu',
  1177. },
  1178. 'params': {
  1179. 'skip_download': True,
  1180. },
  1181. 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
  1182. },
  1183. # Complex jwplayer
  1184. {
  1185. 'url': 'http://www.indiedb.com/games/king-machine/videos',
  1186. 'info_dict': {
  1187. 'id': 'videos',
  1188. 'ext': 'mp4',
  1189. 'title': 'king machine trailer 1',
  1190. 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
  1191. 'thumbnail': r're:^https?://.*\.jpg$',
  1192. },
  1193. },
  1194. {
  1195. # JWPlayer config passed as variable
  1196. 'url': 'http://www.txxx.com/videos/3326530/ariele/',
  1197. 'info_dict': {
  1198. 'id': '3326530_hq',
  1199. 'ext': 'mp4',
  1200. 'title': 'ARIELE | Tube Cup',
  1201. 'uploader': 'www.txxx.com',
  1202. 'age_limit': 18,
  1203. },
  1204. 'params': {
  1205. 'skip_download': True,
  1206. }
  1207. },
  1208. {
  1209. # JWPlatform iframe
  1210. 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
  1211. 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
  1212. 'info_dict': {
  1213. 'id': 'O0c5JcKT',
  1214. 'ext': 'mp4',
  1215. 'upload_date': '20171122',
  1216. 'timestamp': 1511366290,
  1217. 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
  1218. },
  1219. 'add_ie': [JWPlatformIE.ie_key()],
  1220. },
  1221. {
  1222. # Video.js embed, multiple formats
  1223. 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
  1224. 'info_dict': {
  1225. 'id': 'yygqldloqIk',
  1226. 'ext': 'mp4',
  1227. 'title': 'SolidWorks. Урок 6 Настройка чертежа',
  1228. 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
  1229. 'upload_date': '20130314',
  1230. 'uploader': 'PROстое3D',
  1231. 'uploader_id': 'PROstoe3D',
  1232. },
  1233. 'params': {
  1234. 'skip_download': True,
  1235. },
  1236. },
  1237. {
  1238. # Video.js embed, single format
  1239. 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
  1240. 'info_dict': {
  1241. 'id': 'watch',
  1242. 'ext': 'mp4',
  1243. 'title': 'Step 1 - Good Foundation',
  1244. 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
  1245. },
  1246. 'params': {
  1247. 'skip_download': True,
  1248. },
  1249. },
  1250. # rtl.nl embed
  1251. {
  1252. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  1253. 'playlist_mincount': 5,
  1254. 'info_dict': {
  1255. 'id': 'aanslagen-kopenhagen',
  1256. 'title': 'Aanslagen Kopenhagen',
  1257. }
  1258. },
  1259. # Zapiks embed
  1260. {
  1261. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  1262. 'info_dict': {
  1263. 'id': '118046',
  1264. 'ext': 'mp4',
  1265. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  1266. }
  1267. },
  1268. # Kaltura embed (different embed code)
  1269. {
  1270. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  1271. 'info_dict': {
  1272. 'id': '1_a52wc67y',
  1273. 'ext': 'flv',
  1274. 'upload_date': '20150127',
  1275. 'uploader_id': 'PremierMedia',
  1276. 'timestamp': int,
  1277. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  1278. },
  1279. },
  1280. # Kaltura embed with single quotes
  1281. {
  1282. 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
  1283. 'info_dict': {
  1284. 'id': '0_izeg5utt',
  1285. 'ext': 'mp4',
  1286. 'title': '35871',
  1287. 'timestamp': 1355743100,
  1288. 'upload_date': '20121217',
  1289. 'uploader_id': 'cplapp@learn360.com',
  1290. },
  1291. 'add_ie': ['Kaltura'],
  1292. },
  1293. {
  1294. # Kaltura embedded via quoted entry_id
  1295. 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
  1296. 'info_dict': {
  1297. 'id': '0_utuok90b',
  1298. 'ext': 'mp4',
  1299. 'title': '06_matthew_brender_raj_dutt',
  1300. 'timestamp': 1466638791,
  1301. 'upload_date': '20160622',
  1302. },
  1303. 'add_ie': ['Kaltura'],
  1304. 'expected_warnings': [
  1305. 'Could not send HEAD request'
  1306. ],
  1307. 'params': {
  1308. 'skip_download': True,
  1309. }
  1310. },
  1311. {
  1312. # Kaltura embedded, some fileExt broken (#11480)
  1313. 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
  1314. 'info_dict': {
  1315. 'id': '1_sgtvehim',
  1316. 'ext': 'mp4',
  1317. 'title': 'Our "Standard Models" of particle physics and cosmology',
  1318. 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
  1319. 'timestamp': 1321158993,
  1320. 'upload_date': '20111113',
  1321. 'uploader_id': 'kps1',
  1322. },
  1323. 'add_ie': ['Kaltura'],
  1324. },
  1325. {
  1326. # Kaltura iframe embed
  1327. 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
  1328. 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
  1329. 'info_dict': {
  1330. 'id': '0_f2cfbpwy',
  1331. 'ext': 'mp4',
  1332. 'title': 'I. M. Pei: A Centennial Celebration',
  1333. 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
  1334. 'upload_date': '20170403',
  1335. 'uploader_id': 'batchUser',
  1336. 'timestamp': 1491232186,
  1337. },
  1338. 'add_ie': ['Kaltura'],
  1339. },
  1340. {
  1341. # Kaltura iframe embed, more sophisticated
  1342. 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
  1343. 'info_dict': {
  1344. 'id': '1_9gzouybz',
  1345. 'ext': 'mp4',
  1346. 'title': 'lecture-05sep2017',
  1347. 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
  1348. 'upload_date': '20170913',
  1349. 'uploader_id': 'eps2',
  1350. 'timestamp': 1505340777,
  1351. },
  1352. 'params': {
  1353. 'skip_download': True,
  1354. },
  1355. 'add_ie': ['Kaltura'],
  1356. },
  1357. {
  1358. # meta twitter:player
  1359. 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
  1360. 'info_dict': {
  1361. 'id': '0_01b42zps',
  1362. 'ext': 'mp4',
  1363. 'title': 'Main Twerk (Video)',
  1364. 'upload_date': '20171208',
  1365. 'uploader_id': 'sebastian.salinas@thechive.com',
  1366. 'timestamp': 1512713057,
  1367. },
  1368. 'params': {
  1369. 'skip_download': True,
  1370. },
  1371. 'add_ie': ['Kaltura'],
  1372. },
  1373. # referrer protected EaglePlatform embed
  1374. {
  1375. 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
  1376. 'info_dict': {
  1377. 'id': '582306',
  1378. 'ext': 'mp4',
  1379. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1380. 'thumbnail': r're:^https?://.*\.jpg$',
  1381. 'duration': 3382,
  1382. 'view_count': int,
  1383. },
  1384. 'params': {
  1385. 'skip_download': True,
  1386. },
  1387. },
  1388. # ClipYou (EaglePlatform) embed (custom URL)
  1389. {
  1390. 'url': 'http://muz-tv.ru/play/7129/',
  1391. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  1392. 'info_dict': {
  1393. 'id': '12820',
  1394. 'ext': 'mp4',
  1395. 'title': "'O Sole Mio",
  1396. 'thumbnail': r're:^https?://.*\.jpg$',
  1397. 'duration': 216,
  1398. 'view_count': int,
  1399. },
  1400. 'params': {
  1401. 'skip_download': True,
  1402. },
  1403. 'skip': 'This video is unavailable.',
  1404. },
  1405. # Pladform embed
  1406. {
  1407. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  1408. 'info_dict': {
  1409. 'id': '100183293',
  1410. 'ext': 'mp4',
  1411. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  1412. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  1413. 'thumbnail': r're:^https?://.*\.jpg$',
  1414. 'duration': 694,
  1415. 'age_limit': 0,
  1416. },
  1417. 'skip': 'HTTP Error 404: Not Found',
  1418. },
  1419. # Playwire embed
  1420. {
  1421. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  1422. 'info_dict': {
  1423. 'id': '3519514',
  1424. 'ext': 'mp4',
  1425. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  1426. 'thumbnail': r're:^https?://.*\.png$',
  1427. 'duration': 45.115,
  1428. },
  1429. },
  1430. # 5min embed
  1431. {
  1432. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  1433. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  1434. 'info_dict': {
  1435. 'id': '518726732',
  1436. 'ext': 'mp4',
  1437. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  1438. 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
  1439. 'timestamp': 1427237531,
  1440. 'uploader': 'Crunch Report',
  1441. 'upload_date': '20150324',
  1442. },
  1443. 'params': {
  1444. # m3u8 download
  1445. 'skip_download': True,
  1446. },
  1447. },
  1448. # Crooks and Liars embed
  1449. {
  1450. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  1451. 'info_dict': {
  1452. 'id': '8RUoRhRi',
  1453. 'ext': 'mp4',
  1454. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  1455. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  1456. 'timestamp': 1428207000,
  1457. 'upload_date': '20150405',
  1458. 'uploader': 'Heather',
  1459. },
  1460. },
  1461. # Crooks and Liars external embed
  1462. {
  1463. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  1464. 'info_dict': {
  1465. 'id': 'MTE3MjUtMzQ2MzA',
  1466. 'ext': 'mp4',
  1467. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  1468. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  1469. 'timestamp': 1265032391,
  1470. 'upload_date': '20100201',
  1471. 'uploader': 'Heather',
  1472. },
  1473. },
  1474. # NBC Sports vplayer embed
  1475. {
  1476. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  1477. 'info_dict': {
  1478. 'id': 'ln7x1qSThw4k',
  1479. 'ext': 'flv',
  1480. 'title': "PFT Live: New leader in the 'new-look' defense",
  1481. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  1482. 'uploader': 'NBCU-SPORTS',
  1483. 'upload_date': '20140107',
  1484. 'timestamp': 1389118457,
  1485. },
  1486. 'skip': 'Invalid Page URL',
  1487. },
  1488. # NBC News embed
  1489. {
  1490. 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
  1491. 'md5': '1aa589c675898ae6d37a17913cf68d66',
  1492. 'info_dict': {
  1493. 'id': 'x_dtl_oa_LettermanliftPR_160608',
  1494. 'ext': 'mp4',
  1495. 'title': 'David Letterman: A Preview',
  1496. '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.',
  1497. 'upload_date': '20160609',
  1498. 'timestamp': 1465431544,
  1499. 'uploader': 'NBCU-NEWS',
  1500. },
  1501. },
  1502. # UDN embed
  1503. {
  1504. 'url': 'https://video.udn.com/news/300346',
  1505. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  1506. 'info_dict': {
  1507. 'id': '300346',
  1508. 'ext': 'mp4',
  1509. 'title': '中一中男師變性 全校師生力挺',
  1510. 'thumbnail': r're:^https?://.*\.jpg$',
  1511. },
  1512. 'params': {
  1513. # m3u8 download
  1514. 'skip_download': True,
  1515. },
  1516. 'expected_warnings': ['Failed to parse JSON Expecting value'],
  1517. },
  1518. # Brightcove URL in single quotes
  1519. {
  1520. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  1521. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  1522. 'info_dict': {
  1523. 'id': '4255764656001',
  1524. 'ext': 'mp4',
  1525. 'title': 'SN Presents: Russell Martin, World Citizen',
  1526. 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
  1527. 'uploader': 'Rogers Sportsnet',
  1528. 'uploader_id': '1704050871',
  1529. 'upload_date': '20150525',
  1530. 'timestamp': 1432570283,
  1531. },
  1532. },
  1533. # Kinja embed
  1534. {
  1535. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1536. 'info_dict': {
  1537. 'id': '106351',
  1538. 'ext': 'mp4',
  1539. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1540. 'description': 'Migrated from OnionStudios',
  1541. 'thumbnail': r're:^https?://.*\.jpe?g$',
  1542. 'uploader': 'clickhole',
  1543. 'upload_date': '20150527',
  1544. 'timestamp': 1432744860,
  1545. }
  1546. },
  1547. # SnagFilms embed
  1548. {
  1549. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1550. 'info_dict': {
  1551. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1552. 'ext': 'mp4',
  1553. 'title': '#whilewewatch',
  1554. }
  1555. },
  1556. # AdobeTVVideo embed
  1557. {
  1558. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1559. 'md5': '43662b577c018ad707a63766462b1e87',
  1560. 'info_dict': {
  1561. 'id': '2456',
  1562. 'ext': 'mp4',
  1563. 'title': 'New experience with Acrobat DC',
  1564. 'description': 'New experience with Acrobat DC',
  1565. 'duration': 248.667,
  1566. },
  1567. },
  1568. # BrightcoveInPageEmbed embed
  1569. {
  1570. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1571. 'info_dict': {
  1572. 'id': '4238694884001',
  1573. 'ext': 'flv',
  1574. 'title': 'Tabletop: Dread, Last Thoughts',
  1575. 'description': 'Tabletop: Dread, Last Thoughts',
  1576. 'duration': 51690,
  1577. },
  1578. },
  1579. # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
  1580. # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
  1581. {
  1582. 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
  1583. 'info_dict': {
  1584. 'id': '4785848093001',
  1585. 'ext': 'mp4',
  1586. 'title': 'The Cardinal Pell Interview',
  1587. 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
  1588. 'uploader': 'GlobeCast Australia - GlobeStream',
  1589. 'uploader_id': '2733773828001',
  1590. 'upload_date': '20160304',
  1591. 'timestamp': 1457083087,
  1592. },
  1593. 'params': {
  1594. # m3u8 downloads
  1595. 'skip_download': True,
  1596. },
  1597. },
  1598. {
  1599. # Brightcove embed with whitespace around attribute names
  1600. 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
  1601. 'info_dict': {
  1602. 'id': '3167554373001',
  1603. 'ext': 'mp4',
  1604. 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
  1605. 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
  1606. 'uploader_id': '1079349493',
  1607. 'upload_date': '20140207',
  1608. 'timestamp': 1391810548,
  1609. },
  1610. 'params': {
  1611. 'skip_download': True,
  1612. },
  1613. },
  1614. # Another form of arte.tv embed
  1615. {
  1616. 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
  1617. 'md5': '850bfe45417ddf221288c88a0cffe2e2',
  1618. 'info_dict': {
  1619. 'id': '030273-562_PLUS7-F',
  1620. 'ext': 'mp4',
  1621. 'title': 'ARTE Reportage - Nulle part, en France',
  1622. 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
  1623. 'upload_date': '20160409',
  1624. },
  1625. },
  1626. # Duplicated embedded video URLs
  1627. {
  1628. 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
  1629. 'info_dict': {
  1630. 'id': '149298443_480_16c25b74_2',
  1631. 'ext': 'mp4',
  1632. 'title': 'vs. Blue Orange Spring Game',
  1633. 'uploader': 'www.hudl.com',
  1634. },
  1635. },
  1636. # twitter:player:stream embed
  1637. {
  1638. 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
  1639. 'info_dict': {
  1640. 'id': 'master',
  1641. 'ext': 'mp4',
  1642. 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
  1643. 'uploader': 'www.rtl.be',
  1644. },
  1645. 'params': {
  1646. # m3u8 downloads
  1647. 'skip_download': True,
  1648. },
  1649. },
  1650. # twitter:player embed
  1651. {
  1652. 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
  1653. 'md5': 'a3e0df96369831de324f0778e126653c',
  1654. 'info_dict': {
  1655. 'id': '4909620399001',
  1656. 'ext': 'mp4',
  1657. 'title': 'What Do Black Holes Sound Like?',
  1658. 'description': 'what do black holes sound like',
  1659. 'upload_date': '20160524',
  1660. 'uploader_id': '29913724001',
  1661. 'timestamp': 1464107587,
  1662. 'uploader': 'TheAtlantic',
  1663. },
  1664. 'add_ie': ['BrightcoveLegacy'],
  1665. },
  1666. # Facebook <iframe> embed
  1667. {
  1668. 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
  1669. 'md5': 'fbcde74f534176ecb015849146dd3aee',
  1670. 'info_dict': {
  1671. 'id': '599637780109885',
  1672. 'ext': 'mp4',
  1673. 'title': 'Facebook video #599637780109885',
  1674. },
  1675. },
  1676. # Facebook <iframe> embed, plugin video
  1677. {
  1678. 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
  1679. 'info_dict': {
  1680. 'id': '1754168231264132',
  1681. 'ext': 'mp4',
  1682. 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
  1683. 'uploader': 'Tariq Ramadan (official)',
  1684. 'timestamp': 1496758379,
  1685. 'upload_date': '20170606',
  1686. },
  1687. 'params': {
  1688. 'skip_download': True,
  1689. },
  1690. },
  1691. # Facebook API embed
  1692. {
  1693. 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
  1694. 'md5': 'a47372ee61b39a7b90287094d447d94e',
  1695. 'info_dict': {
  1696. 'id': '10153467542406923',
  1697. 'ext': 'mp4',
  1698. 'title': 'Facebook video #10153467542406923',
  1699. },
  1700. },
  1701. # Wordpress "YouTube Video Importer" plugin
  1702. {
  1703. 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
  1704. 'md5': 'd16797741b560b485194eddda8121b48',
  1705. 'info_dict': {
  1706. 'id': 'HNTXWDXV9Is',
  1707. 'ext': 'mp4',
  1708. 'title': 'Blue Devils Drumline Stanford lot 2016',
  1709. 'upload_date': '20160627',
  1710. 'uploader_id': 'GENOCIDE8GENERAL10',
  1711. 'uploader': 'cylus cyrus',
  1712. },
  1713. },
  1714. {
  1715. # video stored on custom kaltura server
  1716. 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
  1717. 'md5': '537617d06e64dfed891fa1593c4b30cc',
  1718. 'info_dict': {
  1719. 'id': '0_1iotm5bh',
  1720. 'ext': 'mp4',
  1721. 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
  1722. 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
  1723. 'uploader_id': 'videos.expansion@el-mundo.net',
  1724. 'upload_date': '20150429',
  1725. 'timestamp': 1430303472,
  1726. },
  1727. 'add_ie': ['Kaltura'],
  1728. },
  1729. {
  1730. # multiple kaltura embeds, nsfw
  1731. 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
  1732. 'info_dict': {
  1733. 'id': 'kamila-avec-video-jaime-sadomie',
  1734. 'title': "Kamila avec vídeo “J'aime sadomie”",
  1735. },
  1736. 'playlist_count': 8,
  1737. },
  1738. {
  1739. # Non-standard Vimeo embed
  1740. 'url': 'https://openclassrooms.com/courses/understanding-the-web',
  1741. 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
  1742. 'info_dict': {
  1743. 'id': '148867247',
  1744. 'ext': 'mp4',
  1745. 'title': 'Understanding the web - Teaser',
  1746. 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
  1747. 'upload_date': '20151214',
  1748. 'uploader': 'OpenClassrooms',
  1749. 'uploader_id': 'openclassrooms',
  1750. },
  1751. 'add_ie': ['Vimeo'],
  1752. },
  1753. {
  1754. # generic vimeo embed that requires original URL passed as Referer
  1755. 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
  1756. 'only_matching': True,
  1757. },
  1758. {
  1759. 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
  1760. 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
  1761. 'info_dict': {
  1762. 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
  1763. 'ext': 'mp4',
  1764. 'title': 'Big Buck Bunny',
  1765. 'description': 'Royalty free test video',
  1766. 'timestamp': 1432816365,
  1767. 'upload_date': '20150528',
  1768. 'is_live': False,
  1769. },
  1770. 'params': {
  1771. 'skip_download': True,
  1772. },
  1773. 'add_ie': [ArkenaIE.ie_key()],
  1774. },
  1775. {
  1776. '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/',
  1777. 'info_dict': {
  1778. 'id': '1c7141f46c',
  1779. 'ext': 'mp4',
  1780. 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
  1781. },
  1782. 'params': {
  1783. 'skip_download': True,
  1784. },
  1785. 'add_ie': [Vbox7IE.ie_key()],
  1786. },
  1787. {
  1788. # DBTV embeds
  1789. 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
  1790. 'info_dict': {
  1791. 'id': '43254897',
  1792. 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
  1793. },
  1794. 'playlist_mincount': 3,
  1795. },
  1796. {
  1797. # Videa embeds
  1798. 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
  1799. 'info_dict': {
  1800. 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
  1801. 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
  1802. },
  1803. 'playlist_mincount': 2,
  1804. },
  1805. {
  1806. # 20 minuten embed
  1807. 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
  1808. 'info_dict': {
  1809. 'id': '523629',
  1810. 'ext': 'mp4',
  1811. 'title': 'So kommen Sie bei Eis und Schnee sicher an',
  1812. 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
  1813. },
  1814. 'params': {
  1815. 'skip_download': True,
  1816. },
  1817. 'add_ie': [TwentyMinutenIE.ie_key()],
  1818. },
  1819. {
  1820. # VideoPress embed
  1821. 'url': 'https://en.support.wordpress.com/videopress/',
  1822. 'info_dict': {
  1823. 'id': 'OcobLTqC',
  1824. 'ext': 'm4v',
  1825. 'title': 'IMG_5786',
  1826. 'timestamp': 1435711927,
  1827. 'upload_date': '20150701',
  1828. },
  1829. 'params': {
  1830. 'skip_download': True,
  1831. },
  1832. 'add_ie': [VideoPressIE.ie_key()],
  1833. },
  1834. {
  1835. # Rutube embed
  1836. 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
  1837. 'info_dict': {
  1838. 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
  1839. 'ext': 'flv',
  1840. 'title': 'Магаззино: Казань 2',
  1841. 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
  1842. 'uploader': 'Магаззино',
  1843. 'upload_date': '20170228',
  1844. 'uploader_id': '996642',
  1845. },
  1846. 'params': {
  1847. 'skip_download': True,
  1848. },
  1849. 'add_ie': [RutubeIE.ie_key()],
  1850. },
  1851. {
  1852. # ThePlatform embedded with whitespaces in URLs
  1853. 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
  1854. 'only_matching': True,
  1855. },
  1856. {
  1857. # Senate ISVP iframe https
  1858. 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
  1859. 'md5': 'fb8c70b0b515e5037981a2492099aab8',
  1860. 'info_dict': {
  1861. 'id': 'govtaff020316',
  1862. 'ext': 'mp4',
  1863. 'title': 'Integrated Senate Video Player',
  1864. },
  1865. 'add_ie': [SenateISVPIE.ie_key()],
  1866. },
  1867. {
  1868. # Limelight embeds (1 channel embed + 4 media embeds)
  1869. 'url': 'http://www.sedona.com/FacilitatorTraining2017',
  1870. 'info_dict': {
  1871. 'id': 'FacilitatorTraining2017',
  1872. 'title': 'Facilitator Training 2017',
  1873. },
  1874. 'playlist_mincount': 5,
  1875. },
  1876. {
  1877. # Limelight embed (LimelightPlayerUtil.embed)
  1878. 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
  1879. 'info_dict': {
  1880. 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
  1881. 'ext': 'mp4',
  1882. 'title': '07448641',
  1883. 'timestamp': 1499890639,
  1884. 'upload_date': '20170712',
  1885. },
  1886. 'params': {
  1887. 'skip_download': True,
  1888. },
  1889. 'add_ie': ['LimelightMedia'],
  1890. },
  1891. {
  1892. 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
  1893. 'info_dict': {
  1894. 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
  1895. 'title': 'Standoff with Walnut Creek murder suspect ends',
  1896. 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
  1897. },
  1898. 'playlist_mincount': 4,
  1899. },
  1900. {
  1901. # WashingtonPost embed
  1902. 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
  1903. 'info_dict': {
  1904. 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
  1905. 'ext': 'mp4',
  1906. 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
  1907. '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.',
  1908. 'timestamp': 1455216756,
  1909. 'uploader': 'The Washington Post',
  1910. 'upload_date': '20160211',
  1911. },
  1912. 'add_ie': [WashingtonPostIE.ie_key()],
  1913. },
  1914. {
  1915. # Mediaset embed
  1916. 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
  1917. 'info_dict': {
  1918. 'id': '720642',
  1919. 'ext': 'mp4',
  1920. 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
  1921. },
  1922. 'params': {
  1923. 'skip_download': True,
  1924. },
  1925. 'add_ie': [MediasetIE.ie_key()],
  1926. },
  1927. {
  1928. # JOJ.sk embeds
  1929. 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1930. 'info_dict': {
  1931. 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1932. 'title': 'Slovenskom sa prehnala vlna silných búrok',
  1933. },
  1934. 'playlist_mincount': 5,
  1935. 'add_ie': [JojIE.ie_key()],
  1936. },
  1937. {
  1938. # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
  1939. 'url': 'https://tvrain.ru/amp/418921/',
  1940. 'md5': 'cc00413936695987e8de148b67d14f1d',
  1941. 'info_dict': {
  1942. 'id': '418921',
  1943. 'ext': 'mp4',
  1944. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1945. },
  1946. },
  1947. {
  1948. # vzaar embed
  1949. 'url': 'http://help.vzaar.com/article/165-embedding-video',
  1950. 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
  1951. 'info_dict': {
  1952. 'id': '8707641',
  1953. 'ext': 'mp4',
  1954. 'title': 'Building A Business Online: Principal Chairs Q & A',
  1955. },
  1956. },
  1957. {
  1958. # multiple HTML5 videos on one page
  1959. 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
  1960. 'info_dict': {
  1961. 'id': 'keyscenarios',
  1962. 'title': 'Rescue Kit 14 Free Edition - Getting started',
  1963. },
  1964. 'playlist_count': 4,
  1965. },
  1966. {
  1967. # vshare embed
  1968. 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
  1969. 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
  1970. 'info_dict': {
  1971. 'id': '0f64ce6',
  1972. 'title': 'vl14062007715967',
  1973. 'ext': 'mp4',
  1974. }
  1975. },
  1976. {
  1977. 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
  1978. 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
  1979. 'info_dict': {
  1980. 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
  1981. 'ext': 'mp4',
  1982. 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
  1983. 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
  1984. 'timestamp': 1474354800,
  1985. 'upload_date': '20160920',
  1986. }
  1987. },
  1988. {
  1989. 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
  1990. 'info_dict': {
  1991. 'id': '1731611',
  1992. 'ext': 'mp4',
  1993. 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
  1994. 'description': 'md5:eb5f23826a027ba95277d105f248b825',
  1995. 'timestamp': 1516100691,
  1996. 'upload_date': '20180116',
  1997. },
  1998. 'params': {
  1999. 'skip_download': True,
  2000. },
  2001. 'add_ie': [SpringboardPlatformIE.ie_key()],
  2002. },
  2003. {
  2004. 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
  2005. 'info_dict': {
  2006. 'id': 'vMDE4NzI1Mjgt690b',
  2007. 'ext': 'mp4',
  2008. 'title': 'Котята',
  2009. },
  2010. 'add_ie': [YapFilesIE.ie_key()],
  2011. 'params': {
  2012. 'skip_download': True,
  2013. },
  2014. },
  2015. {
  2016. # CloudflareStream embed
  2017. 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
  2018. 'info_dict': {
  2019. 'id': '31c9291ab41fac05471db4e73aa11717',
  2020. 'ext': 'mp4',
  2021. 'title': '31c9291ab41fac05471db4e73aa11717',
  2022. },
  2023. 'add_ie': [CloudflareStreamIE.ie_key()],
  2024. 'params': {
  2025. 'skip_download': True,
  2026. },
  2027. },
  2028. {
  2029. # PeerTube embed
  2030. 'url': 'https://joinpeertube.org/fr/home/',
  2031. 'info_dict': {
  2032. 'id': 'home',
  2033. 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
  2034. },
  2035. 'playlist_count': 2,
  2036. },
  2037. {
  2038. # Indavideo embed
  2039. 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
  2040. 'info_dict': {
  2041. 'id': '1693903',
  2042. 'ext': 'mp4',
  2043. 'title': 'Így kell otthon hamburgert sütni',
  2044. 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
  2045. 'timestamp': 1426330212,
  2046. 'upload_date': '20150314',
  2047. 'uploader': 'StreetKitchen',
  2048. 'uploader_id': '546363',
  2049. },
  2050. 'add_ie': [IndavideoEmbedIE.ie_key()],
  2051. 'params': {
  2052. 'skip_download': True,
  2053. },
  2054. },
  2055. {
  2056. # APA embed via JWPlatform embed
  2057. 'url': 'http://www.vol.at/blue-man-group/5593454',
  2058. 'info_dict': {
  2059. 'id': 'jjv85FdZ',
  2060. 'ext': 'mp4',
  2061. 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
  2062. 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  2063. 'thumbnail': r're:^https?://.*\.jpg$',
  2064. 'duration': 254,
  2065. 'timestamp': 1519211149,
  2066. 'upload_date': '20180221',
  2067. },
  2068. 'params': {
  2069. 'skip_download': True,
  2070. },
  2071. },
  2072. {
  2073. 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
  2074. 'md5': 'b68d276de422ab07ee1d49388103f457',
  2075. 'info_dict': {
  2076. 'id': '83645793',
  2077. 'title': 'Lock up and get excited',
  2078. 'ext': 'mp4'
  2079. },
  2080. 'skip': 'TODO: fix nested playlists processing in tests',
  2081. },
  2082. {
  2083. # Viqeo embeds
  2084. 'url': 'https://viqeo.tv/',
  2085. 'info_dict': {
  2086. 'id': 'viqeo',
  2087. 'title': 'All-new video platform',
  2088. },
  2089. 'playlist_count': 6,
  2090. },
  2091. {
  2092. # Squarespace video embed, 2019-08-28
  2093. 'url': 'http://ootboxford.com',
  2094. 'info_dict': {
  2095. 'id': 'Tc7b_JGdZfw',
  2096. 'title': 'Out of the Blue, at Childish Things 10',
  2097. 'ext': 'mp4',
  2098. 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
  2099. 'uploader_id': 'helendouglashouse',
  2100. 'uploader': 'Helen & Douglas House',
  2101. 'upload_date': '20140328',
  2102. },
  2103. 'params': {
  2104. 'skip_download': True,
  2105. },
  2106. },
  2107. # {
  2108. # # Zype embed
  2109. # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
  2110. # 'info_dict': {
  2111. # 'id': '5b400b834b32992a310622b9',
  2112. # 'ext': 'mp4',
  2113. # 'title': 'Smoky Barbecue Favorites',
  2114. # 'thumbnail': r're:^https?://.*\.jpe?g',
  2115. # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
  2116. # 'upload_date': '20170909',
  2117. # 'timestamp': 1504915200,
  2118. # },
  2119. # 'add_ie': [ZypeIE.ie_key()],
  2120. # 'params': {
  2121. # 'skip_download': True,
  2122. # },
  2123. # },
  2124. {
  2125. # videojs embed
  2126. 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
  2127. 'info_dict': {
  2128. 'id': 'shell',
  2129. 'ext': 'mp4',
  2130. 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
  2131. 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
  2132. 'thumbnail': r're:^https?://.*\.jpg$',
  2133. },
  2134. 'params': {
  2135. 'skip_download': True,
  2136. },
  2137. 'expected_warnings': ['Failed to download MPD manifest'],
  2138. },
  2139. {
  2140. # DailyMotion embed with DM.player
  2141. 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
  2142. 'info_dict': {
  2143. 'id': 'k6aKkGHd9FJs4mtJN39',
  2144. 'ext': 'mp4',
  2145. 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
  2146. 'description': 'This video is private.',
  2147. 'uploader_id': 'x1jf30l',
  2148. 'uploader': 'beIN SPORTS USA',
  2149. 'upload_date': '20190528',
  2150. 'timestamp': 1559062971,
  2151. },
  2152. 'params': {
  2153. 'skip_download': True,
  2154. },
  2155. },
  2156. # {
  2157. # # TODO: find another test
  2158. # # http://schema.org/VideoObject
  2159. # 'url': 'https://flipagram.com/f/nyvTSJMKId',
  2160. # 'md5': '888dcf08b7ea671381f00fab74692755',
  2161. # 'info_dict': {
  2162. # 'id': 'nyvTSJMKId',
  2163. # 'ext': 'mp4',
  2164. # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
  2165. # 'description': '#love for cats.',
  2166. # 'timestamp': 1461244995,
  2167. # 'upload_date': '20160421',
  2168. # },
  2169. # 'params': {
  2170. # 'force_generic_extractor': True,
  2171. # },
  2172. # },
  2173. {
  2174. # VHX Embed
  2175. 'url': 'https://demo.vhx.tv/category-c/videos/file-example-mp4-480-1-5mg-copy',
  2176. 'info_dict': {
  2177. 'id': '858208',
  2178. 'ext': 'mp4',
  2179. 'title': 'Untitled',
  2180. 'uploader_id': 'user80538407',
  2181. 'uploader': 'OTT Videos',
  2182. },
  2183. },
  2184. {
  2185. # ArcPublishing PoWa video player
  2186. 'url': 'https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/',
  2187. 'md5': 'b03b2fac8680e1e5a7cc81a5c27e71b3',
  2188. 'info_dict': {
  2189. 'id': '8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
  2190. 'ext': 'mp4',
  2191. 'title': 'Senate candidates wave to voters on Anchorage streets',
  2192. 'description': 'md5:91f51a6511f090617353dc720318b20e',
  2193. 'timestamp': 1604378735,
  2194. 'upload_date': '20201103',
  2195. 'duration': 1581,
  2196. },
  2197. },
  2198. {
  2199. # MyChannels SDK embed
  2200. # https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen
  2201. 'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/',
  2202. 'md5': '90c0699c37006ef18e198c032d81739c',
  2203. 'info_dict': {
  2204. 'id': '194165',
  2205. 'ext': 'mp4',
  2206. 'title': 'Burgemeester Aboutaleb spreekt relschoppers toe',
  2207. 'timestamp': 1611740340,
  2208. 'upload_date': '20210127',
  2209. 'duration': 159,
  2210. },
  2211. },
  2212. {
  2213. # Simplecast player embed
  2214. 'url': 'https://www.bio.org/podcast',
  2215. 'info_dict': {
  2216. 'id': 'podcast',
  2217. 'title': 'I AM BIO Podcast | BIO',
  2218. },
  2219. 'playlist_mincount': 52,
  2220. },
  2221. {
  2222. # Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
  2223. 'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
  2224. 'only_matching': True,
  2225. }, {
  2226. # KVS Player
  2227. 'url': 'https://www.kvs-demo.com/videos/105/kelis-4th-of-july/',
  2228. 'info_dict': {
  2229. 'id': '105',
  2230. 'display_id': 'kelis-4th-of-july',
  2231. 'ext': 'mp4',
  2232. 'title': 'Kelis - 4th Of July',
  2233. 'thumbnail': r're:https://(?:www\.)?kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
  2234. },
  2235. }, {
  2236. # KVS Player
  2237. 'url': 'https://www.kvs-demo.com/embed/105/',
  2238. 'info_dict': {
  2239. 'id': '105',
  2240. 'display_id': 'kelis-4th-of-july',
  2241. 'ext': 'mp4',
  2242. 'title': 'Kelis - 4th Of July / Embed Player',
  2243. 'thumbnail': r're:https://(?:www\.)?kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
  2244. },
  2245. 'params': {
  2246. 'skip_download': True,
  2247. },
  2248. }, {
  2249. # KVS Player
  2250. 'url': 'https://thisvid.com/videos/fruit-is-healthy/',
  2251. 'md5': 'f83e52f409b9139a7efee58ef926a72e',
  2252. 'info_dict': {
  2253. 'id': '7079579',
  2254. 'display_id': 'fruit-is-healthy',
  2255. 'ext': 'mp4',
  2256. 'title': 'Fruit is healthy - ThisVid.com',
  2257. 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/7079000/7079579/preview.jpg',
  2258. }
  2259. }, {
  2260. # KVS Player
  2261. 'url': 'https://thisvid.com/embed/7079579/',
  2262. 'info_dict': {
  2263. 'id': '7079579',
  2264. 'display_id': 'fruit-is-healthy',
  2265. 'ext': 'mp4',
  2266. 'title': 'Fruit is healthy - ThisVid.com',
  2267. 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/7079000/7079579/preview.jpg',
  2268. },
  2269. 'params': {
  2270. 'skip_download': True,
  2271. },
  2272. }, {
  2273. # KVS Player
  2274. 'url': 'https://youix.com/video/leningrad-zoj/',
  2275. 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
  2276. 'info_dict': {
  2277. 'id': '18485',
  2278. 'display_id': 'leningrad-zoj',
  2279. 'ext': 'mp4',
  2280. 'title': 'Клип: Ленинград - ЗОЖ скачать, смотреть онлайн | Youix.com',
  2281. 'thumbnail': r're:https://youix.com/contents/videos_screenshots/18000/18485/preview(?:_480x320_youix_com.mp4)?\.jpg',
  2282. },
  2283. }, {
  2284. # KVS Player
  2285. 'url': 'https://youix.com/embed/18485',
  2286. 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
  2287. 'info_dict': {
  2288. 'id': '18485',
  2289. 'display_id': 'leningrad-zoj',
  2290. 'ext': 'mp4',
  2291. 'title': 'Ленинград - ЗОЖ',
  2292. 'thumbnail': r're:https://youix.com/contents/videos_screenshots/18000/18485/preview(?:_480x320_youix_com.mp4)?\.jpg',
  2293. },
  2294. }, {
  2295. # KVS Player
  2296. 'url': 'https://bogmedia.org/videos/21217/40-nochey-40-nights-2016/',
  2297. 'md5': '94166bdb26b4cb1fb9214319a629fc51',
  2298. 'info_dict': {
  2299. 'id': '21217',
  2300. 'display_id': '40-nochey-2016',
  2301. 'ext': 'mp4',
  2302. 'title': '40 ночей (2016) - BogMedia.org',
  2303. 'thumbnail': 'https://bogmedia.org/contents/videos_screenshots/21000/21217/preview_480p.mp4.jpg',
  2304. },
  2305. }, {
  2306. # KVS Player (for sites that serve kt_player.js via non-https urls)
  2307. 'url': 'http://www.camhub.world/embed/389508',
  2308. 'md5': 'fbe89af4cfb59c8fd9f34a202bb03e32',
  2309. 'info_dict': {
  2310. 'id': '389508',
  2311. 'display_id': 'syren-de-mer-onlyfans-05-07-2020have-a-happy-safe-holiday5f014e68a220979bdb8cd-source',
  2312. 'ext': 'mp4',
  2313. 'title': 'Syren De Mer onlyfans_05-07-2020Have_a_happy_safe_holiday5f014e68a220979bdb8cd_source / Embed плеер',
  2314. 'thumbnail': r're:https?://www\.camhub\.world/contents/videos_screenshots/389000/389508/preview\.mp4\.jpg',
  2315. },
  2316. },
  2317. ]
  2318. def report_following_redirect(self, new_url):
  2319. """Report information extraction."""
  2320. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  2321. def _extract_rss(self, url, video_id, doc):
  2322. playlist_title = doc.find('./channel/title').text
  2323. playlist_desc_el = doc.find('./channel/description')
  2324. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  2325. NS_MAP = {
  2326. 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
  2327. }
  2328. entries = []
  2329. for it in doc.findall('./channel/item'):
  2330. next_url = None
  2331. enclosure_nodes = it.findall('./enclosure')
  2332. for e in enclosure_nodes:
  2333. next_url = e.attrib.get('url')
  2334. if next_url:
  2335. break
  2336. if not next_url:
  2337. next_url = xpath_text(it, 'link', fatal=False)
  2338. if not next_url:
  2339. continue
  2340. def itunes(key):
  2341. return xpath_text(
  2342. it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
  2343. default=None)
  2344. duration = itunes('duration')
  2345. explicit = (itunes('explicit') or '').lower()
  2346. if explicit in ('true', 'yes'):
  2347. age_limit = 18
  2348. elif explicit in ('false', 'no'):
  2349. age_limit = 0
  2350. else:
  2351. age_limit = None
  2352. entries.append({
  2353. '_type': 'url_transparent',
  2354. 'url': next_url,
  2355. 'title': it.find('title').text,
  2356. 'description': xpath_text(it, 'description', default=None),
  2357. 'timestamp': unified_timestamp(
  2358. xpath_text(it, 'pubDate', default=None)),
  2359. 'duration': int_or_none(duration) or parse_duration(duration),
  2360. 'thumbnail': url_or_none(xpath_attr(it, xpath_with_ns('./itunes:image', NS_MAP), 'href')),
  2361. 'episode': itunes('title'),
  2362. 'episode_number': int_or_none(itunes('episode')),
  2363. 'season_number': int_or_none(itunes('season')),
  2364. 'age_limit': age_limit,
  2365. })
  2366. return {
  2367. '_type': 'playlist',
  2368. 'id': url,
  2369. 'title': playlist_title,
  2370. 'description': playlist_desc,
  2371. 'entries': entries,
  2372. }
  2373. def _extract_camtasia(self, url, video_id, webpage):
  2374. """ Returns None if no camtasia video can be found. """
  2375. camtasia_cfg = self._search_regex(
  2376. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  2377. webpage, 'camtasia configuration file', default=None)
  2378. if camtasia_cfg is None:
  2379. return None
  2380. title = self._html_search_meta('DC.title', webpage, fatal=True)
  2381. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  2382. camtasia_cfg = self._download_xml(
  2383. camtasia_url, video_id,
  2384. note='Downloading camtasia configuration',
  2385. errnote='Failed to download camtasia configuration')
  2386. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  2387. entries = []
  2388. for n in fileset_node.getchildren():
  2389. url_n = n.find('./uri')
  2390. if url_n is None:
  2391. continue
  2392. entries.append({
  2393. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  2394. 'title': '%s - %s' % (title, n.tag),
  2395. 'url': compat_urlparse.urljoin(url, url_n.text),
  2396. 'duration': float_or_none(n.find('./duration').text),
  2397. })
  2398. return {
  2399. '_type': 'playlist',
  2400. 'entries': entries,
  2401. 'title': title,
  2402. }
  2403. def _extract_kvs(self, url, webpage, video_id):
  2404. def getlicensetoken(license):
  2405. modlicense = license.replace('$', '').replace('0', '1')
  2406. center = int(len(modlicense) / 2)
  2407. fronthalf = int(modlicense[:center + 1])
  2408. backhalf = int(modlicense[center:])
  2409. modlicense = compat_str(4 * abs(fronthalf - backhalf))
  2410. def parts():
  2411. for o in range(0, center + 1):
  2412. for i in range(1, 5):
  2413. yield compat_str((int(license[o + i]) + int(modlicense[o])) % 10)
  2414. return ''.join(parts())
  2415. def getrealurl(video_url, license_code):
  2416. if not video_url.startswith('function/0/'):
  2417. return video_url # not obfuscated
  2418. url_path, _, url_query = video_url.partition('?')
  2419. urlparts = url_path.split('/')[2:]
  2420. license = getlicensetoken(license_code)
  2421. newmagic = urlparts[5][:32]
  2422. def spells(x, o):
  2423. l = (o + sum(int(n) for n in license[o:])) % 32
  2424. for i in range(0, len(x)):
  2425. yield {l: x[o], o: x[l]}.get(i, x[i])
  2426. for o in range(len(newmagic) - 1, -1, -1):
  2427. newmagic = ''.join(spells(newmagic, o))
  2428. urlparts[5] = newmagic + urlparts[5][32:]
  2429. return '/'.join(urlparts) + '?' + url_query
  2430. flashvars = self._search_regex(
  2431. r'(?s)<script\b[^>]*>.*?var\s+flashvars\s*=\s*(\{.+?\});.*?</script>',
  2432. webpage, 'flashvars')
  2433. flashvars = self._parse_json(flashvars, video_id, transform_source=js_to_json)
  2434. # extract the part after the last / as the display_id from the
  2435. # canonical URL.
  2436. display_id = self._search_regex(
  2437. r'(?:<link href="https?://[^"]+/(.+?)/?" rel="canonical"\s*/?>'
  2438. r'|<link rel="canonical" href="https?://[^"]+/(.+?)/?"\s*/?>)',
  2439. webpage, 'display_id', fatal=False
  2440. )
  2441. title = self._html_search_regex(r'<(?:h1|title)>(?:Video: )?(.+?)</(?:h1|title)>', webpage, 'title')
  2442. thumbnail = flashvars['preview_url']
  2443. if thumbnail.startswith('//'):
  2444. protocol, _, _ = url.partition('/')
  2445. thumbnail = protocol + thumbnail
  2446. url_keys = list(filter(re.compile(r'^video_(?:url|alt_url\d*)$').match, flashvars.keys()))
  2447. formats = []
  2448. for key in url_keys:
  2449. if '/get_file/' not in flashvars[key]:
  2450. continue
  2451. format_id = flashvars.get(key + '_text', key)
  2452. formats.append(merge_dicts(
  2453. parse_resolution(format_id) or parse_resolution(flashvars[key]), {
  2454. 'url': getrealurl(flashvars[key], flashvars['license_code']),
  2455. 'format_id': format_id,
  2456. 'ext': 'mp4',
  2457. }))
  2458. if not formats[-1].get('height'):
  2459. formats[-1]['quality'] = 1
  2460. self._sort_formats(formats)
  2461. return {
  2462. 'id': flashvars['video_id'],
  2463. 'display_id': display_id,
  2464. 'title': title,
  2465. 'thumbnail': thumbnail,
  2466. 'formats': formats,
  2467. }
  2468. def _real_extract(self, url):
  2469. if url.startswith('//'):
  2470. return self.url_result(self.http_scheme() + url)
  2471. parsed_url = compat_urlparse.urlparse(url)
  2472. if not parsed_url.scheme:
  2473. default_search = self._downloader.params.get('default_search')
  2474. if default_search is None:
  2475. default_search = 'fixup_error'
  2476. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  2477. if re.match(r'^[^\s/]+\.[^\s/]+/', url):
  2478. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  2479. return self.url_result('http://' + url)
  2480. elif default_search != 'fixup_error':
  2481. if default_search == 'auto_warning':
  2482. if re.match(r'^(?:url|URL)$', url):
  2483. raise ExtractorError(
  2484. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  2485. expected=True)
  2486. else:
  2487. self._downloader.report_warning(
  2488. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  2489. return self.url_result('ytsearch:' + url)
  2490. if default_search in ('error', 'fixup_error'):
  2491. raise ExtractorError(
  2492. '%r is not a valid URL. '
  2493. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  2494. % (url, url), expected=True)
  2495. else:
  2496. if ':' not in default_search:
  2497. default_search += ':'
  2498. return self.url_result(default_search + url)
  2499. url, smuggled_data = unsmuggle_url(url)
  2500. force_videoid = None
  2501. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  2502. if smuggled_data and 'force_videoid' in smuggled_data:
  2503. force_videoid = smuggled_data['force_videoid']
  2504. video_id = force_videoid
  2505. else:
  2506. video_id = self._generic_id(url)
  2507. self.to_screen('%s: Requesting header' % video_id)
  2508. head_req = HEADRequest(url)
  2509. head_response = self._request_webpage(
  2510. head_req, video_id,
  2511. note=False, errnote='Could not send HEAD request to %s' % url,
  2512. fatal=False)
  2513. if head_response is not False:
  2514. # Check for redirect
  2515. new_url = head_response.geturl()
  2516. if url != new_url:
  2517. self.report_following_redirect(new_url)
  2518. if force_videoid:
  2519. new_url = smuggle_url(
  2520. new_url, {'force_videoid': force_videoid})
  2521. return self.url_result(new_url)
  2522. full_response = None
  2523. if head_response is False:
  2524. request = sanitized_Request(url)
  2525. request.add_header('Accept-Encoding', '*')
  2526. full_response = self._request_webpage(request, video_id)
  2527. head_response = full_response
  2528. info_dict = {
  2529. 'id': video_id,
  2530. 'title': self._generic_title(url),
  2531. 'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
  2532. }
  2533. # Check for direct link to a video
  2534. content_type = head_response.headers.get('Content-Type', '').lower()
  2535. m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
  2536. if m:
  2537. format_id = compat_str(m.group('format_id'))
  2538. if format_id.endswith('mpegurl'):
  2539. formats = self._extract_m3u8_formats(url, video_id, 'mp4')
  2540. elif format_id == 'f4m':
  2541. formats = self._extract_f4m_formats(url, video_id)
  2542. else:
  2543. formats = [{
  2544. 'format_id': format_id,
  2545. 'url': url,
  2546. 'vcodec': 'none' if m.group('type') == 'audio' else None
  2547. }]
  2548. info_dict['direct'] = True
  2549. self._sort_formats(formats)
  2550. info_dict['formats'] = formats
  2551. return info_dict
  2552. if not self._downloader.params.get('test', False) and not is_intentional:
  2553. force = self._downloader.params.get('force_generic_extractor', False)
  2554. self._downloader.report_warning(
  2555. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  2556. if not full_response:
  2557. request = sanitized_Request(url)
  2558. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  2559. # making it impossible to download only chunk of the file (yet we need only 512kB to
  2560. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  2561. # that will always result in downloading the whole file that is not desirable.
  2562. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  2563. # to accept raw bytes and being able to download only a chunk.
  2564. # It may probably better to solve this by checking Content-Type for application/octet-stream
  2565. # after HEAD request finishes, but not sure if we can rely on this.
  2566. request.add_header('Accept-Encoding', '*')
  2567. full_response = self._request_webpage(request, video_id)
  2568. first_bytes = full_response.read(512)
  2569. # Is it an M3U playlist?
  2570. if first_bytes.startswith(b'#EXTM3U'):
  2571. info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
  2572. self._sort_formats(info_dict['formats'])
  2573. return info_dict
  2574. # Maybe it's a direct link to a video?
  2575. # Be careful not to download the whole thing!
  2576. if not is_html(first_bytes):
  2577. self._downloader.report_warning(
  2578. 'URL could be a direct video link, returning it as such.')
  2579. info_dict.update({
  2580. 'direct': True,
  2581. 'url': url,
  2582. })
  2583. return info_dict
  2584. webpage = self._webpage_read_content(
  2585. full_response, url, video_id, prefix=first_bytes)
  2586. if '<title>DPG Media Privacy Gate</title>' in webpage:
  2587. webpage = self._download_webpage(url, video_id)
  2588. self.report_extraction(video_id)
  2589. # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
  2590. try:
  2591. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  2592. if doc.tag == 'rss':
  2593. return self._extract_rss(url, video_id, doc)
  2594. elif doc.tag == 'SmoothStreamingMedia':
  2595. info_dict['formats'] = self._parse_ism_formats(doc, url)
  2596. self._sort_formats(info_dict['formats'])
  2597. return info_dict
  2598. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  2599. smil = self._parse_smil(doc, url, video_id)
  2600. self._sort_formats(smil['formats'])
  2601. return smil
  2602. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  2603. return self.playlist_result(
  2604. self._parse_xspf(
  2605. doc, video_id, xspf_url=url,
  2606. xspf_base_url=full_response.geturl()),
  2607. video_id)
  2608. elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
  2609. info_dict['formats'] = self._parse_mpd_formats(
  2610. doc,
  2611. mpd_base_url=full_response.geturl().rpartition('/')[0],
  2612. mpd_url=url)
  2613. self._sort_formats(info_dict['formats'])
  2614. return info_dict
  2615. elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
  2616. info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
  2617. self._sort_formats(info_dict['formats'])
  2618. return info_dict
  2619. except compat_xml_parse_error:
  2620. pass
  2621. # Is it a Camtasia project?
  2622. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  2623. if camtasia_res is not None:
  2624. return camtasia_res
  2625. # Sometimes embedded video player is hidden behind percent encoding
  2626. # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
  2627. # Unescaping the whole page allows to handle those cases in a generic way
  2628. # FIXME: unescaping the whole page may break URLs, commenting out for now.
  2629. # There probably should be a second run of generic extractor on unescaped webpage.
  2630. # webpage = compat_urllib_parse_unquote(webpage)
  2631. # Unescape squarespace embeds to be detected by generic extractor,
  2632. # see https://github.com/ytdl-org/youtube-dl/issues/21294
  2633. webpage = re.sub(
  2634. r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
  2635. lambda x: unescapeHTML(x.group(0)), webpage)
  2636. # it's tempting to parse this further, but you would
  2637. # have to take into account all the variations like
  2638. # Video Title - Site Name
  2639. # Site Name | Video Title
  2640. # Video Title - Tagline | Site Name
  2641. # and so on and so forth; it's just not practical
  2642. video_title = self._og_search_title(
  2643. webpage, default=None) or self._html_search_regex(
  2644. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  2645. default='video')
  2646. # Try to detect age limit automatically
  2647. age_limit = self._rta_search(webpage)
  2648. # And then there are the jokers who advertise that they use RTA,
  2649. # but actually don't.
  2650. AGE_LIMIT_MARKERS = [
  2651. r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
  2652. ]
  2653. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  2654. age_limit = 18
  2655. # video uploader is domain name
  2656. video_uploader = self._search_regex(
  2657. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  2658. video_description = self._og_search_description(webpage, default=None)
  2659. video_thumbnail = self._og_search_thumbnail(webpage, default=None)
  2660. info_dict.update({
  2661. 'title': video_title,
  2662. 'description': video_description,
  2663. 'thumbnail': video_thumbnail,
  2664. 'age_limit': age_limit,
  2665. })
  2666. # Look for Brightcove Legacy Studio embeds
  2667. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  2668. if bc_urls:
  2669. entries = [{
  2670. '_type': 'url',
  2671. 'url': smuggle_url(bc_url, {'Referer': url}),
  2672. 'ie_key': 'BrightcoveLegacy'
  2673. } for bc_url in bc_urls]
  2674. return {
  2675. '_type': 'playlist',
  2676. 'title': video_title,
  2677. 'id': video_id,
  2678. 'entries': entries,
  2679. }
  2680. # Look for Brightcove New Studio embeds
  2681. bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
  2682. if bc_urls:
  2683. return self.playlist_from_matches(
  2684. bc_urls, video_id, video_title,
  2685. getter=lambda x: smuggle_url(x, {'referrer': url}),
  2686. ie='BrightcoveNew')
  2687. # Look for Nexx embeds
  2688. nexx_urls = NexxIE._extract_urls(webpage)
  2689. if nexx_urls:
  2690. return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
  2691. # Look for Nexx iFrame embeds
  2692. nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
  2693. if nexx_embed_urls:
  2694. return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
  2695. # Look for ThePlatform embeds
  2696. tp_urls = ThePlatformIE._extract_urls(webpage)
  2697. if tp_urls:
  2698. return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
  2699. arc_urls = ArcPublishingIE._extract_urls(webpage)
  2700. if arc_urls:
  2701. return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
  2702. mychannels_urls = MedialaanIE._extract_urls(webpage)
  2703. if mychannels_urls:
  2704. return self.playlist_from_matches(
  2705. mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key())
  2706. # Look for embedded rtl.nl player
  2707. matches = re.findall(
  2708. r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
  2709. webpage)
  2710. if matches:
  2711. return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
  2712. vimeo_urls = VimeoIE._extract_urls(url, webpage)
  2713. if vimeo_urls:
  2714. return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
  2715. vhx_url = VHXEmbedIE._extract_url(webpage)
  2716. if vhx_url:
  2717. return self.url_result(vhx_url, VHXEmbedIE.ie_key())
  2718. vid_me_embed_url = self._search_regex(
  2719. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  2720. webpage, 'vid.me embed', default=None)
  2721. if vid_me_embed_url is not None:
  2722. return self.url_result(vid_me_embed_url, 'Vidme')
  2723. # Look for YouTube embeds
  2724. youtube_urls = YoutubeIE._extract_urls(webpage)
  2725. if youtube_urls:
  2726. return self.playlist_from_matches(
  2727. youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
  2728. matches = DailymotionIE._extract_urls(webpage)
  2729. if matches:
  2730. return self.playlist_from_matches(matches, video_id, video_title)
  2731. # Look for embedded Dailymotion playlist player (#3822)
  2732. m = re.search(
  2733. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  2734. if m:
  2735. playlists = re.findall(
  2736. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  2737. if playlists:
  2738. return self.playlist_from_matches(
  2739. playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
  2740. # Look for DailyMail embeds
  2741. dailymail_urls = DailyMailIE._extract_urls(webpage)
  2742. if dailymail_urls:
  2743. return self.playlist_from_matches(
  2744. dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
  2745. # Look for Teachable embeds, must be before Wistia
  2746. teachable_url = TeachableIE._extract_url(webpage, url)
  2747. if teachable_url:
  2748. return self.url_result(teachable_url)
  2749. # Look for embedded Wistia player
  2750. wistia_urls = WistiaIE._extract_urls(webpage)
  2751. if wistia_urls:
  2752. playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
  2753. for entry in playlist['entries']:
  2754. entry.update({
  2755. '_type': 'url_transparent',
  2756. 'uploader': video_uploader,
  2757. })
  2758. return playlist
  2759. # Look for SVT player
  2760. svt_url = SVTIE._extract_url(webpage)
  2761. if svt_url:
  2762. return self.url_result(svt_url, 'SVT')
  2763. # Look for Bandcamp pages with custom domain
  2764. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  2765. if mobj is not None:
  2766. burl = unescapeHTML(mobj.group(1))
  2767. # Don't set the extractor because it can be a track url or an album
  2768. return self.url_result(burl)
  2769. # Look for embedded Vevo player
  2770. mobj = re.search(
  2771. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  2772. if mobj is not None:
  2773. return self.url_result(mobj.group('url'))
  2774. # Look for embedded Viddler player
  2775. mobj = re.search(
  2776. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  2777. webpage)
  2778. if mobj is not None:
  2779. return self.url_result(mobj.group('url'))
  2780. # Look for NYTimes player
  2781. mobj = re.search(
  2782. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  2783. webpage)
  2784. if mobj is not None:
  2785. return self.url_result(mobj.group('url'))
  2786. # Look for Libsyn player
  2787. mobj = re.search(
  2788. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  2789. if mobj is not None:
  2790. return self.url_result(mobj.group('url'))
  2791. # Look for Ooyala videos
  2792. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
  2793. or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
  2794. or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
  2795. or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
  2796. or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  2797. if mobj is not None:
  2798. embed_token = self._search_regex(
  2799. r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
  2800. webpage, 'ooyala embed token', default=None)
  2801. return OoyalaIE._build_url_result(smuggle_url(
  2802. mobj.group('ec'), {
  2803. 'domain': url,
  2804. 'embed_token': embed_token,
  2805. }))
  2806. # Look for multiple Ooyala embeds on SBN network websites
  2807. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  2808. if mobj is not None:
  2809. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  2810. if embeds:
  2811. return self.playlist_from_matches(
  2812. embeds, video_id, video_title,
  2813. getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  2814. # Look for Aparat videos
  2815. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  2816. if mobj is not None:
  2817. return self.url_result(mobj.group(1), 'Aparat')
  2818. # Look for MPORA videos
  2819. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  2820. if mobj is not None:
  2821. return self.url_result(mobj.group(1), 'Mpora')
  2822. # Look for embedded Facebook player
  2823. facebook_urls = FacebookIE._extract_urls(webpage)
  2824. if facebook_urls:
  2825. return self.playlist_from_matches(facebook_urls, video_id, video_title)
  2826. # Look for embedded VK player
  2827. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  2828. if mobj is not None:
  2829. return self.url_result(mobj.group('url'), 'VK')
  2830. # Look for embedded Odnoklassniki player
  2831. odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
  2832. if odnoklassniki_url:
  2833. return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
  2834. # Look for sibnet embedded player
  2835. sibnet_urls = VKIE._extract_sibnet_urls(webpage)
  2836. if sibnet_urls:
  2837. return self.playlist_from_matches(sibnet_urls, video_id, video_title)
  2838. # Look for embedded ivi player
  2839. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  2840. if mobj is not None:
  2841. return self.url_result(mobj.group('url'), 'Ivi')
  2842. # Look for embedded Huffington Post player
  2843. mobj = re.search(
  2844. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  2845. if mobj is not None:
  2846. return self.url_result(mobj.group('url'), 'HuffPost')
  2847. # Look for embed.ly
  2848. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  2849. if mobj is not None:
  2850. return self.url_result(mobj.group('url'))
  2851. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  2852. if mobj is not None:
  2853. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  2854. # Look for funnyordie embed
  2855. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  2856. if matches:
  2857. return self.playlist_from_matches(
  2858. matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
  2859. # Look for Simplecast embeds
  2860. simplecast_urls = SimplecastIE._extract_urls(webpage)
  2861. if simplecast_urls:
  2862. return self.playlist_from_matches(
  2863. simplecast_urls, video_id, video_title)
  2864. # Look for BBC iPlayer embed
  2865. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  2866. if matches:
  2867. return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
  2868. # Look for embedded RUTV player
  2869. rutv_url = RUTVIE._extract_url(webpage)
  2870. if rutv_url:
  2871. return self.url_result(rutv_url, 'RUTV')
  2872. # Look for embedded TVC player
  2873. tvc_url = TVCIE._extract_url(webpage)
  2874. if tvc_url:
  2875. return self.url_result(tvc_url, 'TVC')
  2876. # Look for embedded SportBox player
  2877. sportbox_urls = SportBoxIE._extract_urls(webpage)
  2878. if sportbox_urls:
  2879. return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
  2880. # Look for embedded XHamster player
  2881. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  2882. if xhamster_urls:
  2883. return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
  2884. # Look for embedded TNAFlixNetwork player
  2885. tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
  2886. if tnaflix_urls:
  2887. return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
  2888. # Look for embedded PornHub player
  2889. pornhub_urls = PornHubIE._extract_urls(webpage)
  2890. if pornhub_urls:
  2891. return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
  2892. # Look for embedded DrTuber player
  2893. drtuber_urls = DrTuberIE._extract_urls(webpage)
  2894. if drtuber_urls:
  2895. return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
  2896. # Look for embedded RedTube player
  2897. redtube_urls = RedTubeIE._extract_urls(webpage)
  2898. if redtube_urls:
  2899. return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
  2900. # Look for embedded Tube8 player
  2901. tube8_urls = Tube8IE._extract_urls(webpage)
  2902. if tube8_urls:
  2903. return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
  2904. # Look for embedded Mofosex player
  2905. mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
  2906. if mofosex_urls:
  2907. return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
  2908. # Look for embedded Spankwire player
  2909. spankwire_urls = SpankwireIE._extract_urls(webpage)
  2910. if spankwire_urls:
  2911. return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
  2912. # Look for embedded YouPorn player
  2913. youporn_urls = YouPornIE._extract_urls(webpage)
  2914. if youporn_urls:
  2915. return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
  2916. # Look for embedded Tvigle player
  2917. mobj = re.search(
  2918. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  2919. if mobj is not None:
  2920. return self.url_result(mobj.group('url'), 'Tvigle')
  2921. # Look for embedded TED player
  2922. mobj = re.search(
  2923. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  2924. if mobj is not None:
  2925. return self.url_result(mobj.group('url'), 'TED')
  2926. # Look for embedded Ustream videos
  2927. ustream_url = UstreamIE._extract_url(webpage)
  2928. if ustream_url:
  2929. return self.url_result(ustream_url, UstreamIE.ie_key())
  2930. # Look for embedded arte.tv player
  2931. arte_urls = ArteTVEmbedIE._extract_urls(webpage)
  2932. if arte_urls:
  2933. return self.playlist_from_matches(arte_urls, video_id, video_title)
  2934. # Look for embedded francetv player
  2935. mobj = re.search(
  2936. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  2937. webpage)
  2938. if mobj is not None:
  2939. return self.url_result(mobj.group('url'))
  2940. # Look for embedded Myvi.ru player
  2941. myvi_url = MyviIE._extract_url(webpage)
  2942. if myvi_url:
  2943. return self.url_result(myvi_url)
  2944. # Look for embedded soundcloud player
  2945. soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
  2946. if soundcloud_urls:
  2947. return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
  2948. # Look for tunein player
  2949. tunein_urls = TuneInBaseIE._extract_urls(webpage)
  2950. if tunein_urls:
  2951. return self.playlist_from_matches(tunein_urls, video_id, video_title)
  2952. # Look for embedded mtvservices player
  2953. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  2954. if mtvservices_url:
  2955. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  2956. # Look for embedded yahoo player
  2957. mobj = re.search(
  2958. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  2959. webpage)
  2960. if mobj is not None:
  2961. return self.url_result(mobj.group('url'), 'Yahoo')
  2962. # Look for embedded sbs.com.au player
  2963. mobj = re.search(
  2964. r'''(?x)
  2965. (?:
  2966. <meta\s+property="og:video"\s+content=|
  2967. <iframe[^>]+?src=
  2968. )
  2969. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  2970. webpage)
  2971. if mobj is not None:
  2972. return self.url_result(mobj.group('url'), 'SBS')
  2973. # Look for embedded Cinchcast player
  2974. mobj = re.search(
  2975. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  2976. webpage)
  2977. if mobj is not None:
  2978. return self.url_result(mobj.group('url'), 'Cinchcast')
  2979. mobj = re.search(
  2980. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  2981. webpage)
  2982. if not mobj:
  2983. mobj = re.search(
  2984. r'data-video-link=["\'](?P<url>http://m\.mlb\.com/video/[^"\']+)',
  2985. webpage)
  2986. if mobj is not None:
  2987. return self.url_result(mobj.group('url'), 'MLB')
  2988. mobj = re.search(
  2989. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  2990. webpage)
  2991. if mobj is not None:
  2992. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  2993. mobj = re.search(
  2994. r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
  2995. webpage)
  2996. if mobj is not None:
  2997. return self.url_result(mobj.group('url'), 'Livestream')
  2998. # Look for Zapiks embed
  2999. mobj = re.search(
  3000. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  3001. if mobj is not None:
  3002. return self.url_result(mobj.group('url'), 'Zapiks')
  3003. # Look for Kaltura embeds
  3004. kaltura_urls = KalturaIE._extract_urls(webpage)
  3005. if kaltura_urls:
  3006. return self.playlist_from_matches(
  3007. kaltura_urls, video_id, video_title,
  3008. getter=lambda x: smuggle_url(x, {'source_url': url}),
  3009. ie=KalturaIE.ie_key())
  3010. # Look for EaglePlatform embeds
  3011. eagleplatform_url = EaglePlatformIE._extract_url(webpage)
  3012. if eagleplatform_url:
  3013. return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
  3014. # Look for ClipYou (uses EaglePlatform) embeds
  3015. mobj = re.search(
  3016. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  3017. if mobj is not None:
  3018. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  3019. # Look for Pladform embeds
  3020. pladform_url = PladformIE._extract_url(webpage)
  3021. if pladform_url:
  3022. return self.url_result(pladform_url)
  3023. # Look for Videomore embeds
  3024. videomore_url = VideomoreIE._extract_url(webpage)
  3025. if videomore_url:
  3026. return self.url_result(videomore_url)
  3027. # Look for Webcaster embeds
  3028. webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
  3029. if webcaster_url:
  3030. return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
  3031. # Look for Playwire embeds
  3032. mobj = re.search(
  3033. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  3034. if mobj is not None:
  3035. return self.url_result(mobj.group('url'))
  3036. # Look for 5min embeds
  3037. mobj = re.search(
  3038. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  3039. if mobj is not None:
  3040. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  3041. # Look for Crooks and Liars embeds
  3042. mobj = re.search(
  3043. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  3044. if mobj is not None:
  3045. return self.url_result(mobj.group('url'))
  3046. # Look for NBC Sports VPlayer embeds
  3047. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  3048. if nbc_sports_url:
  3049. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  3050. # Look for NBC News embeds
  3051. nbc_news_embed_url = re.search(
  3052. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
  3053. if nbc_news_embed_url:
  3054. return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
  3055. # Look for Google Drive embeds
  3056. google_drive_url = GoogleDriveIE._extract_url(webpage)
  3057. if google_drive_url:
  3058. return self.url_result(google_drive_url, 'GoogleDrive')
  3059. # Look for UDN embeds
  3060. mobj = re.search(
  3061. r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  3062. if mobj is not None:
  3063. return self.url_result(
  3064. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  3065. # Look for Senate ISVP iframe
  3066. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  3067. if senate_isvp_url:
  3068. return self.url_result(senate_isvp_url, 'SenateISVP')
  3069. # Look for Kinja embeds
  3070. kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
  3071. if kinja_embed_urls:
  3072. return self.playlist_from_matches(
  3073. kinja_embed_urls, video_id, video_title)
  3074. # Look for OnionStudios embeds
  3075. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  3076. if onionstudios_url:
  3077. return self.url_result(onionstudios_url)
  3078. # Look for ViewLift embeds
  3079. viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
  3080. if viewlift_url:
  3081. return self.url_result(viewlift_url)
  3082. # Look for JWPlatform embeds
  3083. jwplatform_urls = JWPlatformIE._extract_urls(webpage)
  3084. if jwplatform_urls:
  3085. return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
  3086. # Look for Digiteka embeds
  3087. digiteka_url = DigitekaIE._extract_url(webpage)
  3088. if digiteka_url:
  3089. return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
  3090. # Look for Arkena embeds
  3091. arkena_url = ArkenaIE._extract_url(webpage)
  3092. if arkena_url:
  3093. return self.url_result(arkena_url, ArkenaIE.ie_key())
  3094. # Look for Piksel embeds
  3095. piksel_url = PikselIE._extract_url(webpage)
  3096. if piksel_url:
  3097. return self.url_result(piksel_url, PikselIE.ie_key())
  3098. # Look for Limelight embeds
  3099. limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
  3100. if limelight_urls:
  3101. return self.playlist_result(
  3102. limelight_urls, video_id, video_title, video_description)
  3103. # Look for Anvato embeds
  3104. anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
  3105. if anvato_urls:
  3106. return self.playlist_result(
  3107. anvato_urls, video_id, video_title, video_description)
  3108. # Look for AdobeTVVideo embeds
  3109. mobj = re.search(
  3110. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  3111. webpage)
  3112. if mobj is not None:
  3113. return self.url_result(
  3114. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  3115. 'AdobeTVVideo')
  3116. # Look for Vine embeds
  3117. mobj = re.search(
  3118. r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
  3119. webpage)
  3120. if mobj is not None:
  3121. return self.url_result(
  3122. self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
  3123. # Look for VODPlatform embeds
  3124. mobj = re.search(
  3125. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
  3126. webpage)
  3127. if mobj is not None:
  3128. return self.url_result(
  3129. self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
  3130. # Look for Mangomolo embeds
  3131. mobj = re.search(
  3132. r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
  3133. (?:
  3134. admin\.mangomolo\.com/analytics/index\.php/customers/embed|
  3135. player\.mangomolo\.com/v1
  3136. )/
  3137. (?:
  3138. video\?.*?\bid=(?P<video_id>\d+)|
  3139. (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
  3140. ).+?)\1''', webpage)
  3141. if mobj is not None:
  3142. info = {
  3143. '_type': 'url_transparent',
  3144. 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
  3145. 'title': video_title,
  3146. 'description': video_description,
  3147. 'thumbnail': video_thumbnail,
  3148. 'uploader': video_uploader,
  3149. }
  3150. video_id = mobj.group('video_id')
  3151. if video_id:
  3152. info.update({
  3153. 'ie_key': 'MangomoloVideo',
  3154. 'id': video_id,
  3155. })
  3156. else:
  3157. info.update({
  3158. 'ie_key': 'MangomoloLive',
  3159. 'id': mobj.group('channel_id'),
  3160. })
  3161. return info
  3162. # Look for Instagram embeds
  3163. instagram_embed_url = InstagramIE._extract_embed_url(webpage)
  3164. if instagram_embed_url is not None:
  3165. return self.url_result(
  3166. self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
  3167. # Look for 3Q SDN embeds
  3168. threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
  3169. if threeqsdn_url:
  3170. return {
  3171. '_type': 'url_transparent',
  3172. 'ie_key': ThreeQSDNIE.ie_key(),
  3173. 'url': self._proto_relative_url(threeqsdn_url),
  3174. 'title': video_title,
  3175. 'description': video_description,
  3176. 'thumbnail': video_thumbnail,
  3177. 'uploader': video_uploader,
  3178. }
  3179. # Look for VBOX7 embeds
  3180. vbox7_url = Vbox7IE._extract_url(webpage)
  3181. if vbox7_url:
  3182. return self.url_result(vbox7_url, Vbox7IE.ie_key())
  3183. # Look for DBTV embeds
  3184. dbtv_urls = DBTVIE._extract_urls(webpage)
  3185. if dbtv_urls:
  3186. return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
  3187. # Look for Videa embeds
  3188. videa_urls = VideaIE._extract_urls(webpage)
  3189. if videa_urls:
  3190. return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
  3191. # Look for 20 minuten embeds
  3192. twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
  3193. if twentymin_urls:
  3194. return self.playlist_from_matches(
  3195. twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
  3196. # Look for VideoPress embeds
  3197. videopress_urls = VideoPressIE._extract_urls(webpage)
  3198. if videopress_urls:
  3199. return self.playlist_from_matches(
  3200. videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
  3201. # Look for Rutube embeds
  3202. rutube_urls = RutubeIE._extract_urls(webpage)
  3203. if rutube_urls:
  3204. return self.playlist_from_matches(
  3205. rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
  3206. # Look for WashingtonPost embeds
  3207. wapo_urls = WashingtonPostIE._extract_urls(webpage)
  3208. if wapo_urls:
  3209. return self.playlist_from_matches(
  3210. wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
  3211. # Look for Mediaset embeds
  3212. mediaset_urls = MediasetIE._extract_urls(self, webpage)
  3213. if mediaset_urls:
  3214. return self.playlist_from_matches(
  3215. mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
  3216. # Look for JOJ.sk embeds
  3217. joj_urls = JojIE._extract_urls(webpage)
  3218. if joj_urls:
  3219. return self.playlist_from_matches(
  3220. joj_urls, video_id, video_title, ie=JojIE.ie_key())
  3221. # Look for megaphone.fm embeds
  3222. mpfn_urls = MegaphoneIE._extract_urls(webpage)
  3223. if mpfn_urls:
  3224. return self.playlist_from_matches(
  3225. mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
  3226. # Look for vzaar embeds
  3227. vzaar_urls = VzaarIE._extract_urls(webpage)
  3228. if vzaar_urls:
  3229. return self.playlist_from_matches(
  3230. vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
  3231. channel9_urls = Channel9IE._extract_urls(webpage)
  3232. if channel9_urls:
  3233. return self.playlist_from_matches(
  3234. channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
  3235. vshare_urls = VShareIE._extract_urls(webpage)
  3236. if vshare_urls:
  3237. return self.playlist_from_matches(
  3238. vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
  3239. # Look for Mediasite embeds
  3240. mediasite_urls = MediasiteIE._extract_urls(webpage)
  3241. if mediasite_urls:
  3242. entries = [
  3243. self.url_result(smuggle_url(
  3244. compat_urlparse.urljoin(url, mediasite_url),
  3245. {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
  3246. for mediasite_url in mediasite_urls]
  3247. return self.playlist_result(entries, video_id, video_title)
  3248. springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
  3249. if springboardplatform_urls:
  3250. return self.playlist_from_matches(
  3251. springboardplatform_urls, video_id, video_title,
  3252. ie=SpringboardPlatformIE.ie_key())
  3253. yapfiles_urls = YapFilesIE._extract_urls(webpage)
  3254. if yapfiles_urls:
  3255. return self.playlist_from_matches(
  3256. yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
  3257. vice_urls = ViceIE._extract_urls(webpage)
  3258. if vice_urls:
  3259. return self.playlist_from_matches(
  3260. vice_urls, video_id, video_title, ie=ViceIE.ie_key())
  3261. xfileshare_urls = XFileShareIE._extract_urls(webpage)
  3262. if xfileshare_urls:
  3263. return self.playlist_from_matches(
  3264. xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
  3265. cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
  3266. if cloudflarestream_urls:
  3267. return self.playlist_from_matches(
  3268. cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
  3269. peertube_urls = PeerTubeIE._extract_urls(webpage, url)
  3270. if peertube_urls:
  3271. return self.playlist_from_matches(
  3272. peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
  3273. indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
  3274. if indavideo_urls:
  3275. return self.playlist_from_matches(
  3276. indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
  3277. apa_urls = APAIE._extract_urls(webpage)
  3278. if apa_urls:
  3279. return self.playlist_from_matches(
  3280. apa_urls, video_id, video_title, ie=APAIE.ie_key())
  3281. foxnews_urls = FoxNewsIE._extract_urls(webpage)
  3282. if foxnews_urls:
  3283. return self.playlist_from_matches(
  3284. foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
  3285. sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
  3286. r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
  3287. webpage)]
  3288. if sharevideos_urls:
  3289. return self.playlist_from_matches(
  3290. sharevideos_urls, video_id, video_title)
  3291. viqeo_urls = ViqeoIE._extract_urls(webpage)
  3292. if viqeo_urls:
  3293. return self.playlist_from_matches(
  3294. viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
  3295. expressen_urls = ExpressenIE._extract_urls(webpage)
  3296. if expressen_urls:
  3297. return self.playlist_from_matches(
  3298. expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
  3299. zype_urls = ZypeIE._extract_urls(webpage)
  3300. if zype_urls:
  3301. return self.playlist_from_matches(
  3302. zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
  3303. # Look for HTML5 media
  3304. entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
  3305. if entries:
  3306. if len(entries) == 1:
  3307. entries[0].update({
  3308. 'id': video_id,
  3309. 'title': video_title,
  3310. })
  3311. else:
  3312. for num, entry in enumerate(entries, start=1):
  3313. entry.update({
  3314. 'id': '%s-%s' % (video_id, num),
  3315. 'title': '%s (%d)' % (video_title, num),
  3316. })
  3317. for entry in entries:
  3318. self._sort_formats(entry['formats'])
  3319. return self.playlist_result(entries, video_id, video_title)
  3320. jwplayer_data = self._find_jwplayer_data(
  3321. webpage, video_id, transform_source=js_to_json)
  3322. if jwplayer_data:
  3323. try:
  3324. info = self._parse_jwplayer_data(
  3325. jwplayer_data, video_id, require_title=False, base_url=url)
  3326. return merge_dicts(info, info_dict)
  3327. except ExtractorError:
  3328. # See https://github.com/ytdl-org/youtube-dl/pull/16735
  3329. pass
  3330. # Video.js embed
  3331. mobj = re.search(
  3332. r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
  3333. webpage)
  3334. if mobj is not None:
  3335. sources = self._parse_json(
  3336. mobj.group(1), video_id, transform_source=js_to_json,
  3337. fatal=False) or []
  3338. if not isinstance(sources, list):
  3339. sources = [sources]
  3340. formats = []
  3341. for source in sources:
  3342. src = source.get('src')
  3343. if not src or not isinstance(src, compat_str):
  3344. continue
  3345. src = compat_urlparse.urljoin(url, src)
  3346. src_type = source.get('type')
  3347. if isinstance(src_type, compat_str):
  3348. src_type = src_type.lower()
  3349. ext = determine_ext(src).lower()
  3350. if src_type == 'video/youtube':
  3351. return self.url_result(src, YoutubeIE.ie_key())
  3352. if src_type == 'application/dash+xml' or ext == 'mpd':
  3353. formats.extend(self._extract_mpd_formats(
  3354. src, video_id, mpd_id='dash', fatal=False))
  3355. elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
  3356. formats.extend(self._extract_m3u8_formats(
  3357. src, video_id, 'mp4', entry_protocol='m3u8_native',
  3358. m3u8_id='hls', fatal=False))
  3359. else:
  3360. formats.append({
  3361. 'url': src,
  3362. 'ext': (mimetype2ext(src_type)
  3363. or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
  3364. 'http_headers': {
  3365. 'Referer': full_response.geturl(),
  3366. },
  3367. })
  3368. if formats:
  3369. self._sort_formats(formats)
  3370. info_dict['formats'] = formats
  3371. return info_dict
  3372. # Look for generic KVS player (before ld+json for tests)
  3373. found = re.search(
  3374. r'<script\b[^>]+?\bsrc\s*=\s*(["\'])https?://(?:\S+?/)+kt_player\.js\?v=(?P<ver>(?P<maj_ver>\d+)(\.\d+)+)\1[^>]*>',
  3375. webpage)
  3376. if found:
  3377. self.report_extraction('KVS Player')
  3378. if found.group('maj_ver') not in ('4', '5', '6'):
  3379. self.report_warning('Untested major version (%s) in player engine - download may fail.' % (found.group('ver'), ))
  3380. return self._extract_kvs(url, webpage, video_id)
  3381. # Looking for http://schema.org/VideoObject
  3382. json_ld = self._search_json_ld(
  3383. webpage, video_id, default={}, expected_type='VideoObject')
  3384. if json_ld.get('url'):
  3385. return merge_dicts(json_ld, info_dict)
  3386. def check_video(vurl):
  3387. if YoutubeIE.suitable(vurl):
  3388. return True
  3389. if RtmpIE.suitable(vurl):
  3390. return True
  3391. vpath = compat_urlparse.urlparse(vurl).path
  3392. vext = determine_ext(vpath)
  3393. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
  3394. def filter_video(urls):
  3395. return list(filter(check_video, urls))
  3396. # Start with something easy: JW Player in SWFObject
  3397. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  3398. if not found:
  3399. # Look for gorilla-vid style embedding
  3400. found = filter_video(re.findall(r'''(?sx)
  3401. (?:
  3402. jw_plugins|
  3403. JWPlayerOptions|
  3404. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  3405. )
  3406. .*?
  3407. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  3408. if not found:
  3409. # Broaden the search a little bit
  3410. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  3411. if not found:
  3412. # Broaden the findall a little bit: JWPlayer JS loader
  3413. found = filter_video(re.findall(
  3414. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  3415. if not found:
  3416. # Flow player
  3417. found = filter_video(re.findall(r'''(?xs)
  3418. flowplayer\("[^"]+",\s*
  3419. \{[^}]+?\}\s*,
  3420. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  3421. ["']?url["']?\s*:\s*["']([^"']+)["']
  3422. ''', webpage))
  3423. if not found:
  3424. # Cinerama player
  3425. found = re.findall(
  3426. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  3427. if not found:
  3428. # Try to find twitter cards info
  3429. # twitter:player:stream should be checked before twitter:player since
  3430. # it is expected to contain a raw stream (see
  3431. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  3432. found = filter_video(re.findall(
  3433. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  3434. if not found:
  3435. # We look for Open Graph info:
  3436. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  3437. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  3438. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  3439. if m_video_type is not None:
  3440. found = filter_video(re.findall(r'<meta.*?property="og:(?:video|audio)".*?content="(.*?)"', webpage))
  3441. if not found:
  3442. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  3443. found = re.search(
  3444. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  3445. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  3446. webpage)
  3447. if not found:
  3448. # Look also in Refresh HTTP header
  3449. refresh_header = head_response.headers.get('Refresh')
  3450. if refresh_header:
  3451. # In python 2 response HTTP headers are bytestrings
  3452. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  3453. refresh_header = refresh_header.decode('iso-8859-1')
  3454. found = re.search(REDIRECT_REGEX, refresh_header)
  3455. if found:
  3456. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  3457. if new_url != url:
  3458. self.report_following_redirect(new_url)
  3459. return {
  3460. '_type': 'url',
  3461. 'url': new_url,
  3462. }
  3463. else:
  3464. found = None
  3465. if not found:
  3466. # twitter:player is a https URL to iframe player that may or may not
  3467. # be supported by youtube-dl thus this is checked the very last (see
  3468. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  3469. embed_url = self._html_search_meta('twitter:player', webpage, default=None)
  3470. if embed_url and embed_url != url:
  3471. return self.url_result(embed_url)
  3472. if not found:
  3473. raise UnsupportedError(url)
  3474. entries = []
  3475. for video_url in orderedSet(found):
  3476. video_url = unescapeHTML(video_url)
  3477. video_url = video_url.replace('\\/', '/')
  3478. video_url = compat_urlparse.urljoin(url, video_url)
  3479. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  3480. # Sometimes, jwplayer extraction will result in a YouTube URL
  3481. if YoutubeIE.suitable(video_url):
  3482. entries.append(self.url_result(video_url, 'Youtube'))
  3483. continue
  3484. # here's a fun little line of code for you:
  3485. video_id = os.path.splitext(video_id)[0]
  3486. entry_info_dict = {
  3487. 'id': video_id,
  3488. 'uploader': video_uploader,
  3489. 'title': video_title,
  3490. 'age_limit': age_limit,
  3491. }
  3492. if RtmpIE.suitable(video_url):
  3493. entry_info_dict.update({
  3494. '_type': 'url_transparent',
  3495. 'ie_key': RtmpIE.ie_key(),
  3496. 'url': video_url,
  3497. })
  3498. entries.append(entry_info_dict)
  3499. continue
  3500. ext = determine_ext(video_url)
  3501. if ext == 'smil':
  3502. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  3503. elif ext == 'xspf':
  3504. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  3505. elif ext == 'm3u8':
  3506. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  3507. elif ext == 'mpd':
  3508. entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
  3509. elif ext == 'f4m':
  3510. entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
  3511. elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
  3512. # Just matching .ism/manifest is not enough to be reliably sure
  3513. # whether it's actually an ISM manifest or some other streaming
  3514. # manifest since there are various streaming URL formats
  3515. # possible (see [1]) as well as some other shenanigans like
  3516. # .smil/manifest URLs that actually serve an ISM (see [2]) and
  3517. # so on.
  3518. # Thus the most reasonable way to solve this is to delegate
  3519. # to generic extractor in order to look into the contents of
  3520. # the manifest itself.
  3521. # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
  3522. # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
  3523. entry_info_dict = self.url_result(
  3524. smuggle_url(video_url, {'to_generic': True}),
  3525. GenericIE.ie_key())
  3526. else:
  3527. entry_info_dict['url'] = video_url
  3528. if entry_info_dict.get('formats'):
  3529. self._sort_formats(entry_info_dict['formats'])
  3530. entries.append(entry_info_dict)
  3531. if len(entries) == 1:
  3532. return entries[0]
  3533. else:
  3534. for num, e in enumerate(entries, start=1):
  3535. # 'url' results don't have a title
  3536. if e.get('title') is not None:
  3537. e['title'] = '%s (%d)' % (e['title'], num)
  3538. return {
  3539. '_type': 'playlist',
  3540. 'entries': entries,
  3541. }