import os
import re
+import sys
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..compat import (
- compat_urllib_parse,
+ compat_etree_fromstring,
+ compat_urllib_parse_unquote,
compat_urlparse,
compat_xml_parse_error,
)
ExtractorError,
float_or_none,
HEADRequest,
+ is_html,
orderedSet,
- parse_xml,
+ sanitized_Request,
smuggle_url,
unescapeHTML,
unified_strdate,
unsmuggle_url,
+ UnsupportedError,
url_basename,
+ xpath_text,
)
-from .brightcove import BrightcoveIE
+from .brightcove import (
+ BrightcoveLegacyIE,
+ BrightcoveNewIE,
+)
+from .nbc import NBCSportsVPlayerIE
from .ooyala import OoyalaIE
from .rutv import RUTVIE
+from .tvc import TVCIE
+from .sportbox import SportBoxEmbedIE
from .smotri import SmotriIE
+from .myvi import MyviIE
from .condenast import CondeNastIE
+from .udn import UDNEmbedIE
+from .senateisvp import SenateISVPIE
+from .svt import SVTIE
+from .pornhub import PornHubIE
+from .xhamster import XHamsterEmbedIE
+from .tnaflix import TNAFlixNetworkEmbedIE
+from .vimeo import VimeoIE
+from .dailymotion import DailymotionCloudIE
+from .onionstudios import OnionStudiosIE
+from .viewlift import ViewLiftEmbedIE
+from .screenwavemedia import ScreenwaveMediaIE
+from .mtv import MTVServicesEmbeddedIE
+from .pladform import PladformIE
+from .videomore import VideomoreIE
+from .googledrive import GoogleDriveIE
+from .jwplatform import JWPlatformIE
+from .digiteka import DigitekaIE
+from .instagram import InstagramIE
+from .liveleak import LiveLeakIE
+from .threeqsdn import ThreeQSDNIE
+from .theplatform import ThePlatformIE
+from .vessel import VesselIE
class GenericIE(InfoExtractor):
_VALID_URL = r'.*'
IE_NAME = 'generic'
_TESTS = [
+ # Direct link to a video
+ {
+ 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
+ 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
+ 'info_dict': {
+ 'id': 'trailer',
+ 'ext': 'mp4',
+ 'title': 'trailer',
+ 'upload_date': '20100513',
+ }
+ },
+ # Direct link to media delivered compressed (until Accept-Encoding is *)
+ {
+ 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
+ 'md5': '128c42e68b13950268b648275386fc74',
+ 'info_dict': {
+ 'id': 'FictionJunction-Parallel_Hearts',
+ 'ext': 'flac',
+ 'title': 'FictionJunction-Parallel_Hearts',
+ 'upload_date': '20140522',
+ },
+ 'expected_warnings': [
+ 'URL could be a direct video link, returning it as such.'
+ ]
+ },
+ # Direct download with broken HEAD
+ {
+ 'url': 'http://ai-radio.org:8000/radio.opus',
+ 'info_dict': {
+ 'id': 'radio',
+ 'ext': 'opus',
+ 'title': 'radio',
+ },
+ 'params': {
+ 'skip_download': True, # infinite live stream
+ },
+ 'expected_warnings': [
+ r'501.*Not Implemented',
+ r'400.*Bad Request',
+ ],
+ },
+ # Direct link with incorrect MIME type
+ {
+ 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
+ 'md5': '4ccbebe5f36706d85221f204d7eb5913',
+ 'info_dict': {
+ 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
+ 'id': '5_Lennart_Poettering_-_Systemd',
+ 'ext': 'webm',
+ 'title': '5_Lennart_Poettering_-_Systemd',
+ 'upload_date': '20141120',
+ },
+ 'expected_warnings': [
+ 'URL could be a direct video link, returning it as such.'
+ ]
+ },
+ # RSS feed
+ {
+ 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
+ 'info_dict': {
+ 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
+ 'title': 'Zero Punctuation',
+ 'description': 're:.*groundbreaking video review series.*'
+ },
+ 'playlist_mincount': 11,
+ },
+ # RSS feed with enclosure
+ {
+ 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
+ 'info_dict': {
+ 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
+ 'ext': 'm4v',
+ 'upload_date': '20150228',
+ 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
+ }
+ },
+ # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
+ {
+ 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
+ 'info_dict': {
+ 'id': 'smil',
+ 'ext': 'mp4',
+ 'title': 'Automatics, robotics and biocybernetics',
+ 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
+ 'upload_date': '20130627',
+ 'formats': 'mincount:16',
+ 'subtitles': 'mincount:1',
+ },
+ 'params': {
+ 'force_generic_extractor': True,
+ 'skip_download': True,
+ },
+ },
+ # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
+ {
+ 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
+ 'info_dict': {
+ 'id': 'hds',
+ 'ext': 'flv',
+ 'title': 'hds',
+ 'formats': 'mincount:1',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
+ # SMIL from https://www.restudy.dk/video/play/id/1637
+ {
+ 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
+ 'info_dict': {
+ 'id': 'video_1637',
+ 'ext': 'flv',
+ 'title': 'video_1637',
+ 'formats': 'mincount:3',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
+ # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
+ {
+ 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
+ 'info_dict': {
+ 'id': 'smil-service',
+ 'ext': 'flv',
+ 'title': 'smil-service',
+ 'formats': 'mincount:1',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
+ # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
+ {
+ 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
+ 'info_dict': {
+ 'id': '4719370',
+ 'ext': 'mp4',
+ 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
+ 'formats': 'mincount:3',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
+ # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
+ {
+ 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
+ 'info_dict': {
+ 'id': 'mZlp2ctYIUEB',
+ 'ext': 'mp4',
+ 'title': 'Tikibad ontruimd wegens brand',
+ 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 33,
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
+ # MPD from http://dash-mse-test.appspot.com/media.html
+ {
+ 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
+ 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
+ 'info_dict': {
+ 'id': 'car-20120827-manifest',
+ 'ext': 'mp4',
+ 'title': 'car-20120827-manifest',
+ 'formats': 'mincount:9',
+ 'upload_date': '20130904',
+ },
+ 'params': {
+ 'format': 'bestvideo',
+ },
+ },
+ # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
+ {
+ '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',
+ 'info_dict': {
+ 'id': 'content',
+ 'ext': 'mp4',
+ 'title': 'content',
+ 'formats': 'mincount:8',
+ },
+ 'params': {
+ # m3u8 downloads
+ 'skip_download': True,
+ }
+ },
+ # m3u8 served with Content-Type: text/plain
+ {
+ 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
+ 'info_dict': {
+ 'id': 'index',
+ 'ext': 'mp4',
+ 'title': 'index',
+ 'upload_date': '20140720',
+ 'formats': 'mincount:11',
+ },
+ 'params': {
+ # m3u8 downloads
+ 'skip_download': True,
+ }
+ },
+ # google redirect
+ {
+ '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',
+ 'info_dict': {
+ 'id': 'cmQHVoWB5FY',
+ 'ext': 'mp4',
+ 'upload_date': '20130224',
+ 'uploader_id': 'TheVerge',
+ 'description': 're:^Chris Ziegler takes a look at the\.*',
+ 'uploader': 'The Verge',
+ 'title': 'First Firefox OS phones side-by-side',
+ },
+ 'params': {
+ 'skip_download': False,
+ }
+ },
+ {
+ # redirect in Refresh HTTP header
+ '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',
+ 'info_dict': {
+ 'id': 'pO8h3EaFRdo',
+ 'ext': 'mp4',
+ 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
+ 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
+ 'upload_date': '20150917',
+ 'uploader_id': 'brtvofficial',
+ 'uploader': 'Boiler Room',
+ },
+ 'params': {
+ 'skip_download': False,
+ },
+ },
{
'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
# it also tests brightcove videos that need to set the 'Referer' in the
# http requests
{
- 'add_ie': ['Brightcove'],
+ 'add_ie': ['BrightcoveLegacy'],
'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
'info_dict': {
'id': '2765128793001',
'uploader': 'thestar.com',
'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.',
},
- 'add_ie': ['Brightcove'],
+ 'add_ie': ['BrightcoveLegacy'],
},
{
'url': 'http://www.championat.com/video/football/v/87/87499.html',
},
{
# https://github.com/rg3/youtube-dl/issues/3541
- 'add_ie': ['Brightcove'],
+ 'add_ie': ['BrightcoveLegacy'],
'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
'info_dict': {
'id': '3866516442001',
'skip_download': True, # m3u8 download
},
},
- # Direct link to a video
- {
- 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
- 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
- 'info_dict': {
- 'id': 'trailer',
- 'ext': 'mp4',
- 'title': 'trailer',
- 'upload_date': '20100513',
- }
- },
# ooyala video
{
'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
- 'md5': '5644c6ca5d5782c1d0d350dad9bd840c',
+ 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
'info_dict': {
'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
'ext': 'mp4',
'title': '2cc213299525360.mov', # that's what we get
+ 'duration': 238.231,
},
+ 'add_ie': ['Ooyala'],
},
- # google redirect
{
- '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',
+ # ooyala video embedded with http://player.ooyala.com/iframe.js
+ 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
'info_dict': {
- 'id': 'cmQHVoWB5FY',
+ 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
'ext': 'mp4',
- 'upload_date': '20130224',
- 'uploader_id': 'TheVerge',
- 'description': 'Chris Ziegler takes a look at the Alcatel OneTouch Fire and the ZTE Open; two of the first Firefox OS handsets to be officially announced.',
- 'uploader': 'The Verge',
- 'title': 'First Firefox OS phones side-by-side',
+ 'title': '"Steve Jobs: Man in the Machine" trailer',
+ 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
+ 'duration': 135.427,
},
'params': {
- 'skip_download': False,
- }
+ 'skip_download': True,
+ },
},
# embed.ly video
{
'skip_download': True,
},
},
+ # TVC embed
+ {
+ '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/',
+ 'info_dict': {
+ 'id': '55304',
+ 'ext': 'mp4',
+ 'title': 'Дошкольное воспитание',
+ },
+ },
+ # SportBox embed
+ {
+ 'url': 'http://www.vestifinance.ru/articles/25753',
+ 'info_dict': {
+ 'id': '25753',
+ 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
+ },
+ 'playlist': [{
+ 'info_dict': {
+ 'id': '370908',
+ 'title': 'Госзаказ. День 3',
+ 'ext': 'mp4',
+ }
+ }, {
+ 'info_dict': {
+ 'id': '370905',
+ 'title': 'Госзаказ. День 2',
+ 'ext': 'mp4',
+ }
+ }, {
+ 'info_dict': {
+ 'id': '370902',
+ 'title': 'Госзаказ. День 1',
+ 'ext': 'mp4',
+ }
+ }],
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ },
+ # Myvi.ru embed
+ {
+ 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
+ 'info_dict': {
+ 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
+ 'ext': 'mp4',
+ 'title': 'Ужастики, русский трейлер (2015)',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 153,
+ }
+ },
+ # XHamster embed
+ {
+ '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',
+ 'info_dict': {
+ 'id': 'showthread',
+ 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
+ },
+ 'playlist_mincount': 7,
+ },
# Embedded TED video
{
'url': 'http://en.support.wordpress.com/videos/ted-talks/',
'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
}
},
- # Embeded Ustream video
+ # Embedded Ustream video
{
'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
'md5': '27b99cdb639c9b12a79bca876a073417',
'skip_download': 'Requires rtmpdump'
}
},
+ # francetv embed
+ {
+ 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
+ 'info_dict': {
+ 'id': 'EV_30231',
+ 'ext': 'mp4',
+ 'title': 'Alcaline, le concert avec Calogero',
+ 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
+ 'upload_date': '20150226',
+ 'timestamp': 1424989860,
+ 'duration': 5400,
+ },
+ 'params': {
+ # m3u8 downloads
+ 'skip_download': True,
+ },
+ 'expected_warnings': [
+ 'Forbidden'
+ ]
+ },
# Condé Nast embed
{
'url': 'http://www.wired.com/2014/04/honda-asimo/',
'id': 'k2mm4bCdJ6CQ2i7c8o2',
'ext': 'mp4',
'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
+ 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
'uploader': 'Spi0n',
+ 'uploader_id': 'xgditw',
+ 'upload_date': '20140425',
+ 'timestamp': 1398441542,
},
'add_ie': ['Dailymotion'],
},
},
# MTVSercices embed
{
- 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
- 'md5': '35727f82f58c76d996fc188f9755b0d5',
+ 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
+ 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
'info_dict': {
- 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
+ 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
'ext': 'mp4',
- 'title': 'Review',
- 'description': 'Mario\'s life in the fast lane has never looked so good.',
+ 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
+ 'description': 'Two valets share their love for movie star Liam Neesons.',
},
},
# YouTube embed via <data-embed-url="">
}
}],
'info_dict': {
- 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
+ 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
+ }
+ },
+ # Flowplayer
+ {
+ 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
+ 'md5': '9d65602bf31c6e20014319c7d07fba27',
+ 'info_dict': {
+ 'id': '5123ea6d5e5a7',
+ 'ext': 'mp4',
+ 'age_limit': 18,
+ 'uploader': 'www.handjobhub.com',
+ 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
+ }
+ },
+ # Multiple brightcove videos
+ # https://github.com/rg3/youtube-dl/issues/2283
+ {
+ 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
+ 'info_dict': {
+ 'id': 'always-never',
+ 'title': 'Always / Never - The New Yorker',
+ },
+ 'playlist_count': 3,
+ 'params': {
+ 'extract_flat': False,
+ 'skip_download': True,
+ }
+ },
+ # MLB embed
+ {
+ 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
+ 'md5': '96f09a37e44da40dd083e12d9a683327',
+ 'info_dict': {
+ 'id': '33322633',
+ 'ext': 'mp4',
+ 'title': 'Ump changes call to ball',
+ 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
+ 'duration': 48,
+ 'timestamp': 1401537900,
+ 'upload_date': '20140531',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ },
+ },
+ # Wistia embed
+ {
+ 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
+ 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
+ 'info_dict': {
+ 'id': '6e2wtrbdaf',
+ 'ext': 'mov',
+ 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
+ 'description': 'a Paywall Videos video from Remilon',
+ 'duration': 644.072,
+ 'uploader': 'study.com',
+ 'timestamp': 1459678540,
+ 'upload_date': '20160403',
+ 'filesize': 24687186,
+ },
+ },
+ {
+ 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
+ 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
+ 'info_dict': {
+ 'id': 'uxjb0lwrcz',
+ 'ext': 'mp4',
+ 'title': 'Conversation about Hexagonal Rails Part 1',
+ 'description': 'a Martin Fowler video from ThoughtWorks',
+ 'duration': 1715.0,
+ 'uploader': 'thoughtworks.wistia.com',
+ 'timestamp': 1401832161,
+ 'upload_date': '20140603',
+ },
+ },
+ # Wistia standard embed (async)
+ {
+ 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
+ 'info_dict': {
+ 'id': '807fafadvk',
+ 'ext': 'mp4',
+ 'title': 'Drip Brennan Dunn Workshop',
+ 'description': 'a JV Webinars video from getdrip-1',
+ 'duration': 4986.95,
+ 'timestamp': 1463607249,
+ 'upload_date': '20160518',
+ },
+ 'params': {
+ 'skip_download': True,
+ }
+ },
+ # Soundcloud embed
+ {
+ 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
+ 'info_dict': {
+ 'id': '174391317',
+ 'ext': 'mp3',
+ 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
+ 'uploader': 'Sophos Security',
+ 'title': 'Chet Chat 171 - Oct 29, 2014',
+ 'upload_date': '20141029',
+ }
+ },
+ # Livestream embed
+ {
+ 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
+ 'info_dict': {
+ 'id': '67864563',
+ 'ext': 'flv',
+ 'upload_date': '20141112',
+ 'title': 'Rosetta #CometLanding webcast HL 10',
+ }
+ },
+ # Another Livestream embed, without 'new.' in URL
+ {
+ 'url': 'https://www.freespeech.org/',
+ 'info_dict': {
+ 'id': '123537347',
+ 'ext': 'mp4',
+ 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+ },
+ 'params': {
+ # Live stream
+ 'skip_download': True,
+ },
+ },
+ # LazyYT
+ {
+ 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
+ 'info_dict': {
+ 'id': '1986',
+ 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
+ },
+ 'playlist_mincount': 2,
+ },
+ # Cinchcast embed
+ {
+ 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
+ 'info_dict': {
+ 'id': '7141703',
+ 'ext': 'mp3',
+ 'upload_date': '20141126',
+ 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
+ }
+ },
+ # Cinerama player
+ {
+ 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
+ 'info_dict': {
+ 'id': '730m_DandD_1901_512k',
+ 'ext': 'mp4',
+ 'uploader': 'www.abc.net.au',
+ 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
+ }
+ },
+ # embedded viddler video
+ {
+ 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
+ 'info_dict': {
+ 'id': '4d03aad9',
+ 'ext': 'mp4',
+ 'uploader': 'deadspin',
+ 'title': 'WALL-TO-GORTAT',
+ 'timestamp': 1422285291,
+ 'upload_date': '20150126',
+ },
+ 'add_ie': ['Viddler'],
+ },
+ # Libsyn embed
+ {
+ 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
+ 'info_dict': {
+ 'id': '3377616',
+ 'ext': 'mp3',
+ 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
+ 'description': 'md5:601cb790edd05908957dae8aaa866465',
+ 'upload_date': '20150220',
+ },
+ },
+ # jwplayer YouTube
+ {
+ 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
+ 'info_dict': {
+ 'id': 'Mrj4DVp2zeA',
+ 'ext': 'mp4',
+ 'upload_date': '20150212',
+ 'uploader': 'The National Archives UK',
+ 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
+ 'uploader_id': 'NationalArchives08',
+ 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
+ },
+ },
+ # rtl.nl embed
+ {
+ 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
+ 'playlist_mincount': 5,
+ 'info_dict': {
+ 'id': 'aanslagen-kopenhagen',
+ 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
+ }
+ },
+ # Zapiks embed
+ {
+ 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
+ 'info_dict': {
+ 'id': '118046',
+ 'ext': 'mp4',
+ 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
+ }
+ },
+ # Kaltura embed (different embed code)
+ {
+ 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
+ 'info_dict': {
+ 'id': '1_a52wc67y',
+ 'ext': 'flv',
+ 'upload_date': '20150127',
+ 'uploader_id': 'PremierMedia',
+ 'timestamp': int,
+ 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
+ },
+ },
+ # Kaltura embed protected with referrer
+ {
+ 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
+ 'info_dict': {
+ 'id': '1_g4fbemnq',
+ 'ext': 'mp4',
+ 'title': 'Violetta - Achter De Schermen - Ruggero',
+ 'description': 'Achter de schermen met Ruggero',
+ 'timestamp': 1435133761,
+ 'upload_date': '20150624',
+ 'uploader_id': 'echojecka',
+ },
+ },
+ # Kaltura embed with single quotes
+ {
+ 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
+ 'info_dict': {
+ 'id': '0_izeg5utt',
+ 'ext': 'mp4',
+ 'title': '35871',
+ 'timestamp': 1355743100,
+ 'upload_date': '20121217',
+ 'uploader_id': 'batchUser',
+ },
+ 'add_ie': ['Kaltura'],
+ },
+ # Eagle.Platform embed (generic URL)
+ {
+ 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
+ # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
+ 'info_dict': {
+ 'id': '227304',
+ 'ext': 'mp4',
+ 'title': 'Навальный вышел на свободу',
+ 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 87,
+ 'view_count': int,
+ 'age_limit': 0,
+ },
+ },
+ # ClipYou (Eagle.Platform) embed (custom URL)
+ {
+ 'url': 'http://muz-tv.ru/play/7129/',
+ # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
+ 'info_dict': {
+ 'id': '12820',
+ 'ext': 'mp4',
+ 'title': "'O Sole Mio",
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 216,
+ 'view_count': int,
+ },
+ },
+ # Pladform embed
+ {
+ 'url': 'http://muz-tv.ru/kinozal/view/7400/',
+ 'info_dict': {
+ 'id': '100183293',
+ 'ext': 'mp4',
+ 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
+ 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 694,
+ 'age_limit': 0,
+ },
+ },
+ # Playwire embed
+ {
+ 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
+ 'info_dict': {
+ 'id': '3519514',
+ 'ext': 'mp4',
+ 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
+ 'thumbnail': 're:^https?://.*\.png$',
+ 'duration': 45.115,
+ },
+ },
+ # 5min embed
+ {
+ 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
+ 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
+ 'info_dict': {
+ 'id': '518726732',
+ 'ext': 'mp4',
+ 'title': 'Facebook Creates "On This Day" | Crunch Report',
+ },
+ },
+ # SVT embed
+ {
+ 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
+ 'info_dict': {
+ 'id': '2900353',
+ 'ext': 'flv',
+ 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
+ 'duration': 27,
+ 'age_limit': 0,
+ },
+ },
+ # Crooks and Liars embed
+ {
+ 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
+ 'info_dict': {
+ 'id': '8RUoRhRi',
+ 'ext': 'mp4',
+ 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
+ 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
+ 'timestamp': 1428207000,
+ 'upload_date': '20150405',
+ 'uploader': 'Heather',
+ },
+ },
+ # Crooks and Liars external embed
+ {
+ 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
+ 'info_dict': {
+ 'id': 'MTE3MjUtMzQ2MzA',
+ 'ext': 'mp4',
+ 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
+ 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
+ 'timestamp': 1265032391,
+ 'upload_date': '20100201',
+ 'uploader': 'Heather',
+ },
+ },
+ # NBC Sports vplayer embed
+ {
+ 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
+ 'info_dict': {
+ 'id': 'ln7x1qSThw4k',
+ 'ext': 'flv',
+ 'title': "PFT Live: New leader in the 'new-look' defense",
+ 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
+ 'uploader': 'NBCU-SPORTS',
+ 'upload_date': '20140107',
+ 'timestamp': 1389118457,
+ },
+ },
+ # NBC News embed
+ {
+ 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
+ 'md5': '1aa589c675898ae6d37a17913cf68d66',
+ 'info_dict': {
+ 'id': '701714499682',
+ 'ext': 'mp4',
+ 'title': 'PREVIEW: On Assignment: David Letterman',
+ '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.',
+ },
+ },
+ # UDN embed
+ {
+ 'url': 'https://video.udn.com/news/300346',
+ 'md5': 'fd2060e988c326991037b9aff9df21a6',
+ 'info_dict': {
+ 'id': '300346',
+ 'ext': 'mp4',
+ 'title': '中一中男師變性 全校師生力挺',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ },
+ # Ooyala embed
+ {
+ 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
+ 'info_dict': {
+ 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
+ 'ext': 'mp4',
+ 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
+ 'title': 'This is what separates the Excel masters from the wannabes',
+ 'duration': 191.933,
+ },
+ 'params': {
+ # m3u8 downloads
+ 'skip_download': True,
+ }
+ },
+ # Brightcove URL in single quotes
+ {
+ 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
+ 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
+ 'info_dict': {
+ 'id': '4255764656001',
+ 'ext': 'mp4',
+ 'title': 'SN Presents: Russell Martin, World Citizen',
+ 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
+ 'uploader': 'Rogers Sportsnet',
+ 'uploader_id': '1704050871',
+ 'upload_date': '20150525',
+ 'timestamp': 1432570283,
+ },
+ },
+ # Dailymotion Cloud video
+ {
+ 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
+ 'md5': '49444254273501a64675a7e68c502681',
+ 'info_dict': {
+ 'id': '5585de919473990de4bee11b',
+ 'ext': 'mp4',
+ 'title': 'Le débat',
+ 'thumbnail': 're:^https?://.*\.jpe?g$',
}
},
- # Flowplayer
+ # OnionStudios embed
{
- 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
- 'md5': '9d65602bf31c6e20014319c7d07fba27',
+ 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
'info_dict': {
- 'id': '5123ea6d5e5a7',
+ 'id': '2855',
'ext': 'mp4',
- 'age_limit': 18,
- 'uploader': 'www.handjobhub.com',
- 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
+ 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
+ 'thumbnail': 're:^https?://.*\.jpe?g$',
+ 'uploader': 'ClickHole',
+ 'uploader_id': 'clickhole',
}
},
- # RSS feed
+ # SnagFilms embed
{
- 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
+ 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
'info_dict': {
- 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
- 'title': 'Zero Punctuation',
- 'description': 're:'
- },
- 'playlist_mincount': 11,
+ 'id': '74849a00-85a9-11e1-9660-123139220831',
+ 'ext': 'mp4',
+ 'title': '#whilewewatch',
+ }
},
- # Multiple brightcove videos
- # https://github.com/rg3/youtube-dl/issues/2283
+ # AdobeTVVideo embed
{
- 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
+ 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
+ 'md5': '43662b577c018ad707a63766462b1e87',
'info_dict': {
- 'id': 'always-never',
- 'title': 'Always / Never - The New Yorker',
+ 'id': '2456',
+ 'ext': 'mp4',
+ 'title': 'New experience with Acrobat DC',
+ 'description': 'New experience with Acrobat DC',
+ 'duration': 248.667,
},
- 'playlist_count': 3,
- 'params': {
- 'extract_flat': False,
- 'skip_download': True,
- }
},
- # MLB embed
+ # ScreenwaveMedia embed
{
- 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
- 'md5': '96f09a37e44da40dd083e12d9a683327',
+ 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
+ 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
'info_dict': {
- 'id': '33322633',
+ 'id': 'cinemasnob-55d26273809dd',
'ext': 'mp4',
- 'title': 'Ump changes call to ball',
- 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
- 'duration': 48,
- 'timestamp': 1401537900,
- 'upload_date': '20140531',
- 'thumbnail': 're:^https?://.*\.jpg$',
+ 'title': 'cinemasnob',
},
},
- # Wistia embed
+ # BrightcoveInPageEmbed embed
{
- 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
- 'md5': '8788b683c777a5cf25621eaf286d0c23',
+ 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
'info_dict': {
- 'id': '1cfaf6b7ea',
- 'ext': 'mov',
- 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
- 'duration': 643.0,
- 'filesize': 182808282,
- 'uploader': 'education-portal.com',
+ 'id': '4238694884001',
+ 'ext': 'flv',
+ 'title': 'Tabletop: Dread, Last Thoughts',
+ 'description': 'Tabletop: Dread, Last Thoughts',
+ 'duration': 51690,
},
},
+ # JWPlayer with M3U8
{
- 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
- 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
+ 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
'info_dict': {
- 'id': 'uxjb0lwrcz',
+ 'id': 'playlist',
'ext': 'mp4',
- 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
- 'duration': 1715.0,
- 'uploader': 'thoughtworks.wistia.com',
+ 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
+ 'uploader': 'ren.tv',
},
+ 'params': {
+ # m3u8 downloads
+ 'skip_download': True,
+ }
},
- # Direct download with broken HEAD
+ # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
+ # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
{
- 'url': 'http://ai-radio.org:8000/radio.opus',
+ 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
'info_dict': {
- 'id': 'radio',
- 'ext': 'opus',
- 'title': 'radio',
+ 'id': '4785848093001',
+ 'ext': 'mp4',
+ 'title': 'The Cardinal Pell Interview',
+ 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
+ 'uploader': 'GlobeCast Australia - GlobeStream',
+ 'uploader_id': '2733773828001',
+ 'upload_date': '20160304',
+ 'timestamp': 1457083087,
},
'params': {
- 'skip_download': True, # infinite live stream
+ # m3u8 downloads
+ 'skip_download': True,
},
- 'expected_warnings': [
- r'501.*Not Implemented'
- ],
},
- # Soundcloud embed
+ # Another form of arte.tv embed
{
- 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
+ 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
+ 'md5': '850bfe45417ddf221288c88a0cffe2e2',
'info_dict': {
- 'id': '174391317',
- 'ext': 'mp3',
- 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
- 'uploader': 'Sophos Security',
- 'title': 'Chet Chat 171 - Oct 29, 2014',
- 'upload_date': '20141029',
- }
+ 'id': '030273-562_PLUS7-F',
+ 'ext': 'mp4',
+ 'title': 'ARTE Reportage - Nulle part, en France',
+ 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
+ 'upload_date': '20160409',
+ },
},
- # Livestream embed
+ # LiveLeak embed
{
- 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
+ 'url': 'http://www.wykop.pl/link/3088787/',
+ 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
'info_dict': {
- 'id': '67864563',
- 'ext': 'flv',
- 'upload_date': '20141112',
- 'title': 'Rosetta #CometLanding webcast HL 10',
+ 'id': '874_1459135191',
+ 'ext': 'mp4',
+ 'title': 'Man shows poor quality of new apartment building',
+ 'description': 'The wall is like a sand pile.',
+ 'uploader': 'Lake8737',
}
},
- # LazyYT
+ # Duplicated embedded video URLs
{
- 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
+ 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
'info_dict': {
- 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
+ 'id': '149298443_480_16c25b74_2',
+ 'ext': 'mp4',
+ 'title': 'vs. Blue Orange Spring Game',
+ 'uploader': 'www.hudl.com',
},
- 'playlist_mincount': 2,
},
- # Direct link with incorrect MIME type
- {
- 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
- 'md5': '4ccbebe5f36706d85221f204d7eb5913',
- 'info_dict': {
- 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
- 'id': '5_Lennart_Poettering_-_Systemd',
- 'ext': 'webm',
- 'title': '5_Lennart_Poettering_-_Systemd',
- 'upload_date': '20141120',
- },
- 'expected_warnings': [
- 'URL could be a direct video link, returning it as such.'
- ]
- }
-
]
def report_following_redirect(self, new_url):
playlist_desc_el = doc.find('./channel/description')
playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
- entries = [{
- '_type': 'url',
- 'url': e.find('link').text,
- 'title': e.find('title').text,
- } for e in doc.findall('./channel/item')]
+ entries = []
+ for it in doc.findall('./channel/item'):
+ next_url = xpath_text(it, 'link', fatal=False)
+ if not next_url:
+ enclosure_nodes = it.findall('./enclosure')
+ for e in enclosure_nodes:
+ next_url = e.attrib.get('url')
+ if next_url:
+ break
+
+ if not next_url:
+ continue
+
+ entries.append({
+ '_type': 'url',
+ 'url': next_url,
+ 'title': it.find('title').text,
+ })
return {
'_type': 'playlist',
force_videoid = smuggled_data['force_videoid']
video_id = force_videoid
else:
- video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0]
+ video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
self.to_screen('%s: Requesting header' % video_id)
full_response = None
if head_response is False:
- full_response = self._request_webpage(url, video_id)
+ request = sanitized_Request(url)
+ request.add_header('Accept-Encoding', '*')
+ full_response = self._request_webpage(request, video_id)
head_response = full_response
+ info_dict = {
+ 'id': video_id,
+ 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
+ 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
+ }
+
# Check for direct link to a video
- content_type = head_response.headers.get('Content-Type', '')
- m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
+ content_type = head_response.headers.get('Content-Type', '').lower()
+ m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
if m:
- upload_date = unified_strdate(
- head_response.headers.get('Last-Modified'))
- return {
- 'id': video_id,
- 'title': os.path.splitext(url_basename(url))[0],
- 'direct': True,
- 'formats': [{
+ format_id = m.group('format_id')
+ if format_id.endswith('mpegurl'):
+ formats = self._extract_m3u8_formats(url, video_id, 'mp4')
+ elif format_id == 'f4m':
+ formats = self._extract_f4m_formats(url, video_id)
+ else:
+ formats = [{
'format_id': m.group('format_id'),
'url': url,
'vcodec': 'none' if m.group('type') == 'audio' else None
- }],
- 'upload_date': upload_date,
- }
+ }]
+ info_dict['direct'] = True
+ self._sort_formats(formats)
+ info_dict['formats'] = formats
+ return info_dict
if not self._downloader.params.get('test', False) and not is_intentional:
- self._downloader.report_warning('Falling back on generic information extractor.')
+ force = self._downloader.params.get('force_generic_extractor', False)
+ self._downloader.report_warning(
+ '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
if not full_response:
- full_response = self._request_webpage(url, video_id)
+ request = sanitized_Request(url)
+ # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
+ # making it impossible to download only chunk of the file (yet we need only 512kB to
+ # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
+ # that will always result in downloading the whole file that is not desirable.
+ # Therefore for extraction pass we have to override Accept-Encoding to any in order
+ # to accept raw bytes and being able to download only a chunk.
+ # It may probably better to solve this by checking Content-Type for application/octet-stream
+ # after HEAD request finishes, but not sure if we can rely on this.
+ request.add_header('Accept-Encoding', '*')
+ full_response = self._request_webpage(request, video_id)
+
+ first_bytes = full_response.read(512)
+
+ # Is it an M3U playlist?
+ if first_bytes.startswith(b'#EXTM3U'):
+ info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
+ self._sort_formats(info_dict['formats'])
+ return info_dict
# Maybe it's a direct link to a video?
# Be careful not to download the whole thing!
- first_bytes = full_response.read(512)
- if not re.match(r'^\s*<', first_bytes.decode('utf-8', 'replace')):
+ if not is_html(first_bytes):
self._downloader.report_warning(
'URL could be a direct video link, returning it as such.')
- upload_date = unified_strdate(
- head_response.headers.get('Last-Modified'))
- return {
- 'id': video_id,
- 'title': os.path.splitext(url_basename(url))[0],
+ info_dict.update({
'direct': True,
'url': url,
- 'upload_date': upload_date,
- }
+ })
+ return info_dict
webpage = self._webpage_read_content(
full_response, url, video_id, prefix=first_bytes)
self.report_extraction(video_id)
- # Is it an RSS feed?
+ # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
try:
- doc = parse_xml(webpage)
+ doc = compat_etree_fromstring(webpage.encode('utf-8'))
if doc.tag == 'rss':
return self._extract_rss(url, video_id, doc)
+ elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
+ smil = self._parse_smil(doc, url, video_id)
+ self._sort_formats(smil['formats'])
+ return smil
+ elif doc.tag == '{http://xspf.org/ns/0/}playlist':
+ return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
+ elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
+ info_dict['formats'] = self._parse_mpd_formats(
+ doc, video_id, mpd_base_url=url.rpartition('/')[0])
+ self._sort_formats(info_dict['formats'])
+ return info_dict
+ elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
+ info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
+ self._sort_formats(info_dict['formats'])
+ return info_dict
except compat_xml_parse_error:
pass
# Sometimes embedded video player is hidden behind percent encoding
# (e.g. https://github.com/rg3/youtube-dl/issues/2448)
# Unescaping the whole page allows to handle those cases in a generic way
- webpage = compat_urllib_parse.unquote(webpage)
+ webpage = compat_urllib_parse_unquote(webpage)
# it's tempting to parse this further, but you would
# have to take into account all the variations like
# Site Name | Video Title
# Video Title - Tagline | Site Name
# and so on and so forth; it's just not practical
- video_title = self._html_search_regex(
+ video_title = self._og_search_title(
+ webpage, default=None) or self._html_search_regex(
r'(?s)<title>(.*?)</title>', webpage, 'video title',
default='video')
video_uploader = self._search_regex(
r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
+ video_description = self._og_search_description(webpage, default=None)
+ video_thumbnail = self._og_search_thumbnail(webpage, default=None)
+
# Helper method
- def _playlist_from_matches(matches, getter, ie=None):
+ def _playlist_from_matches(matches, getter=None, ie=None):
urlrs = orderedSet(
- self.url_result(self._proto_relative_url(getter(m)), ie)
+ self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
for m in matches)
return self.playlist_result(
urlrs, playlist_id=video_id, playlist_title=video_title)
- # Look for BrightCove:
- bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
+ # Look for Brightcove Legacy Studio embeds
+ bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
if bc_urls:
self.to_screen('Brightcove video detected.')
entries = [{
'_type': 'url',
'url': smuggle_url(bc_url, {'Referer': url}),
- 'ie_key': 'Brightcove'
+ 'ie_key': 'BrightcoveLegacy'
} for bc_url in bc_urls]
return {
'entries': entries,
}
- # Look for embedded (iframe) Vimeo player
- mobj = re.search(
- r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
- if mobj:
- player_url = unescapeHTML(mobj.group('url'))
- surl = smuggle_url(player_url, {'Referer': url})
- return self.url_result(surl)
+ # Look for Brightcove New Studio embeds
+ bc_urls = BrightcoveNewIE._extract_urls(webpage)
+ if bc_urls:
+ return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
- # Look for embedded (swf embed) Vimeo player
- mobj = re.search(
- r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
- if mobj:
- return self.url_result(mobj.group(1))
+ # Look for ThePlatform embeds
+ tp_urls = ThePlatformIE._extract_urls(webpage)
+ if tp_urls:
+ return _playlist_from_matches(tp_urls, ie='ThePlatform')
+
+ # Look for Vessel embeds
+ vessel_urls = VesselIE._extract_urls(webpage)
+ if vessel_urls:
+ return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
+
+ # Look for embedded rtl.nl player
+ matches = re.findall(
+ r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
+ webpage)
+ if matches:
+ return _playlist_from_matches(matches, ie='RtlNl')
+
+ vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
+ if vimeo_url is not None:
+ return self.url_result(vimeo_url)
+
+ vid_me_embed_url = self._search_regex(
+ r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
+ webpage, 'vid.me embed', default=None)
+ if vid_me_embed_url is not None:
+ return self.url_result(vid_me_embed_url, 'Vidme')
# Look for embedded YouTube player
matches = re.findall(r'''(?x)
# Look for embedded Dailymotion player
matches = re.findall(
- r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
+ r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
if matches:
return _playlist_from_matches(
matches, lambda m: unescapeHTML(m[1]))
'url': embed_url,
'ie_key': 'Wistia',
'uploader': video_uploader,
- 'title': video_title,
- 'id': video_id,
}
match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
if match:
return {
'_type': 'url_transparent',
- 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
+ 'url': 'wistia:%s' % match.group('id'),
'ie_key': 'Wistia',
'uploader': video_uploader,
- 'title': video_title,
- 'id': match.group('id')
}
- # Look for embedded blip.tv player
- mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
- if mobj:
- return self.url_result('http://blip.tv/a/a-' + mobj.group(1), 'BlipTV')
- mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage)
- if mobj:
- return self.url_result(mobj.group(1), 'BlipTV')
+ match = re.search(
+ r'''(?sx)
+ <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
+ <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
+ ''', webpage)
+ if match:
+ return self.url_result(self._proto_relative_url(
+ 'wistia:%s' % match.group('id')), 'Wistia')
+
+ # Look for SVT player
+ svt_url = SVTIE._extract_url(webpage)
+ if svt_url:
+ return self.url_result(svt_url, 'SVT')
# Look for embedded condenast player
matches = re.findall(
if mobj is not None:
return self.url_result(mobj.group('url'))
+ # Look for embedded Viddler player
+ mobj = re.search(
+ r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
+ webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'))
+
+ # Look for NYTimes player
+ mobj = re.search(
+ r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
+ webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'))
+
+ # Look for Libsyn player
+ mobj = re.search(
+ r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'))
+
# Look for Ooyala videos
- mobj = (re.search(r'player.ooyala.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
- re.search(r'OO.Player.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage))
+ mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
+ re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
+ re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
+ re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
+ if mobj is not None:
+ return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
+
+ # Look for multiple Ooyala embeds on SBN network websites
+ mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
if mobj is not None:
- return OoyalaIE._build_url_result(mobj.group('ec'))
+ embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
+ if embeds:
+ return _playlist_from_matches(
+ embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
# Look for Aparat videos
mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'VK')
+ # Look for embedded Odnoklassniki player
+ mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'Odnoklassniki')
+
# Look for embedded ivi player
mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'))
mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
if mobj is not None:
- return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
+ return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
# Look for funnyordie embed
matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
return _playlist_from_matches(
matches, getter=unescapeHTML, ie='FunnyOrDie')
+ # Look for BBC iPlayer embed
+ matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
+ if matches:
+ return _playlist_from_matches(matches, ie='BBCCoUk')
+
# Look for embedded RUTV player
rutv_url = RUTVIE._extract_url(webpage)
if rutv_url:
return self.url_result(rutv_url, 'RUTV')
+ # Look for embedded TVC player
+ tvc_url = TVCIE._extract_url(webpage)
+ if tvc_url:
+ return self.url_result(tvc_url, 'TVC')
+
+ # Look for embedded SportBox player
+ sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
+ if sportbox_urls:
+ return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
+
+ # Look for embedded PornHub player
+ pornhub_url = PornHubIE._extract_url(webpage)
+ if pornhub_url:
+ return self.url_result(pornhub_url, 'PornHub')
+
+ # Look for embedded XHamster player
+ xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
+ if xhamster_urls:
+ return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
+
+ # Look for embedded TNAFlixNetwork player
+ tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
+ if tnaflix_urls:
+ return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
+
+ # Look for embedded Tvigle player
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'Tvigle')
+
# Look for embedded TED player
mobj = re.search(
- r'<iframe[^>]+?src=(["\'])(?P<url>http://embed\.ted\.com/.+?)\1', webpage)
+ r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'TED')
# Look for embedded arte.tv player
mobj = re.search(
- r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
+ r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'ArteTVEmbed')
+ # Look for embedded francetv player
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
+ webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'))
+
# Look for embedded smotri.com player
smotri_url = SmotriIE._extract_url(webpage)
if smotri_url:
return self.url_result(smotri_url, 'Smotri')
- # Look for embeded soundcloud player
+ # Look for embedded Myvi.ru player
+ myvi_url = MyviIE._extract_url(webpage)
+ if myvi_url:
+ return self.url_result(myvi_url)
+
+ # Look for embedded soundcloud player
mobj = re.search(
r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
webpage)
url = unescapeHTML(mobj.group('url'))
return self.url_result(url)
- # Look for embedded vulture.com player
- mobj = re.search(
- r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
- webpage)
- if mobj is not None:
- url = unescapeHTML(mobj.group('url'))
- return self.url_result(url, ie='Vulture')
-
# Look for embedded mtvservices player
- mobj = re.search(
- r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
- webpage)
- if mobj is not None:
- url = unescapeHTML(mobj.group('url'))
- return self.url_result(url, ie='MTVServicesEmbedded')
+ mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
+ if mtvservices_url:
+ return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
# Look for embedded yahoo player
mobj = re.search(
# Look for embedded sbs.com.au player
mobj = re.search(
- r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:www\.)sbs\.com\.au/ondemand/video/single/.+?)\1',
+ r'''(?x)
+ (?:
+ <meta\s+property="og:video"\s+content=|
+ <iframe[^>]+?src=
+ )
+ (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'SBS')
+ # Look for embedded Cinchcast player
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
+ webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'Cinchcast')
+
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
webpage)
+ if not mobj:
+ mobj = re.search(
+ r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
+ webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'MLB')
mobj = re.search(
- r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
+ r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
webpage)
if mobj is not None:
return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
mobj = re.search(
- r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
+ r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'Livestream')
+ # Look for Zapiks embed
+ mobj = re.search(
+ r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'Zapiks')
+
+ # Look for Kaltura embeds
+ mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?(?P<q1>['\"])wid(?P=q1)\s*:\s*(?P<q2>['\"])_?(?P<partner_id>[^'\"]+)(?P=q2),.*?(?P<q3>['\"])entry_?[Ii]d(?P=q3)\s*:\s*(?P<q4>['\"])(?P<id>[^'\"]+)(?P=q4),", webpage) or
+ re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
+ if mobj is not None:
+ return self.url_result(smuggle_url(
+ 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
+ {'source_url': url}), 'Kaltura')
+
+ # Look for Eagle.Platform embeds
+ mobj = re.search(
+ r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'EaglePlatform')
+
+ # Look for ClipYou (uses Eagle.Platform) embeds
+ mobj = re.search(
+ r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
+ if mobj is not None:
+ return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
+
+ # Look for Pladform embeds
+ pladform_url = PladformIE._extract_url(webpage)
+ if pladform_url:
+ return self.url_result(pladform_url)
+
+ # Look for Videomore embeds
+ videomore_url = VideomoreIE._extract_url(webpage)
+ if videomore_url:
+ return self.url_result(videomore_url)
+
+ # Look for Playwire embeds
+ mobj = re.search(
+ r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'))
+
+ # Look for 5min embeds
+ mobj = re.search(
+ r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
+ if mobj is not None:
+ return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
+
+ # Look for Crooks and Liars embeds
+ mobj = re.search(
+ r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'))
+
+ # Look for NBC Sports VPlayer embeds
+ nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
+ if nbc_sports_url:
+ return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
+
+ # Look for NBC News embeds
+ nbc_news_embed_url = re.search(
+ r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
+ if nbc_news_embed_url:
+ return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
+
+ # Look for Google Drive embeds
+ google_drive_url = GoogleDriveIE._extract_url(webpage)
+ if google_drive_url:
+ return self.url_result(google_drive_url, 'GoogleDrive')
+
+ # Look for UDN embeds
+ mobj = re.search(
+ r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
+ if mobj is not None:
+ return self.url_result(
+ compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
+
+ # Look for Senate ISVP iframe
+ senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
+ if senate_isvp_url:
+ return self.url_result(senate_isvp_url, 'SenateISVP')
+
+ # Look for Dailymotion Cloud videos
+ dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
+ if dmcloud_url:
+ return self.url_result(dmcloud_url, 'DailymotionCloud')
+
+ # Look for OnionStudios embeds
+ onionstudios_url = OnionStudiosIE._extract_url(webpage)
+ if onionstudios_url:
+ return self.url_result(onionstudios_url)
+
+ # Look for ViewLift embeds
+ viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
+ if viewlift_url:
+ return self.url_result(viewlift_url)
+
+ # Look for JWPlatform embeds
+ jwplatform_url = JWPlatformIE._extract_url(webpage)
+ if jwplatform_url:
+ return self.url_result(jwplatform_url, 'JWPlatform')
+
+ # Look for ScreenwaveMedia embeds
+ mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
+ if mobj is not None:
+ return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
+
+ # Look for Digiteka embeds
+ digiteka_url = DigitekaIE._extract_url(webpage)
+ if digiteka_url:
+ return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
+
+ # Look for Limelight embeds
+ mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
+ if mobj:
+ lm = {
+ 'Media': 'media',
+ 'Channel': 'channel',
+ 'ChannelList': 'channel_list',
+ }
+ return self.url_result('limelight:%s:%s' % (
+ lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
+
+ # Look for AdobeTVVideo embeds
+ mobj = re.search(
+ r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
+ webpage)
+ if mobj is not None:
+ return self.url_result(
+ self._proto_relative_url(unescapeHTML(mobj.group(1))),
+ 'AdobeTVVideo')
+
+ # Look for Vine embeds
+ mobj = re.search(
+ r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
+ webpage)
+ if mobj is not None:
+ return self.url_result(
+ self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
+
+ # Look for Instagram embeds
+ instagram_embed_url = InstagramIE._extract_embed_url(webpage)
+ if instagram_embed_url is not None:
+ return self.url_result(
+ self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
+
+ # Look for LiveLeak embeds
+ liveleak_url = LiveLeakIE._extract_url(webpage)
+ if liveleak_url:
+ return self.url_result(liveleak_url, 'LiveLeak')
+
+ # Look for 3Q SDN embeds
+ threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
+ if threeqsdn_url:
+ return {
+ '_type': 'url_transparent',
+ 'ie_key': ThreeQSDNIE.ie_key(),
+ 'url': self._proto_relative_url(threeqsdn_url),
+ 'title': video_title,
+ 'description': video_description,
+ 'thumbnail': video_thumbnail,
+ 'uploader': video_uploader,
+ }
+
def check_video(vurl):
+ if YoutubeIE.suitable(vurl):
+ return True
vpath = compat_urlparse.urlparse(vurl).path
vext = determine_ext(vpath)
return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
JWPlayerOptions|
jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
)
- .*?file\s*:\s*["\'](.*?)["\']''', webpage))
+ .*?
+ ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
if not found:
# Broaden the search a little bit
found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
if not found:
# Broaden the findall a little bit: JWPlayer JS loader
found = filter_video(re.findall(
- r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
+ r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
if not found:
# Flow player
found = filter_video(re.findall(r'''(?xs)
flowplayer\("[^"]+",\s*
\{[^}]+?\}\s*,
- \s*{[^}]+? ["']?clip["']?\s*:\s*\{\s*
+ \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
["']?url["']?\s*:\s*["']([^"']+)["']
''', webpage))
+ if not found:
+ # Cinerama player
+ found = re.findall(
+ r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
if not found:
# Try to find twitter cards info
found = filter_video(re.findall(
found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
if not found:
# HTML5 video
- found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
+ found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
if not found:
+ REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
found = re.search(
r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
- r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'?([^\'"]+)',
+ r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
webpage)
+ if not found:
+ # Look also in Refresh HTTP header
+ refresh_header = head_response.headers.get('Refresh')
+ if refresh_header:
+ # In python 2 response HTTP headers are bytestrings
+ if sys.version_info < (3, 0) and isinstance(refresh_header, str):
+ refresh_header = refresh_header.decode('iso-8859-1')
+ found = re.search(REDIRECT_REGEX, refresh_header)
if found:
- new_url = found.group(1)
+ new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
self.report_following_redirect(new_url)
return {
'_type': 'url',
'url': new_url,
}
if not found:
- raise ExtractorError('Unsupported URL: %s' % url)
+ raise UnsupportedError(url)
entries = []
- for video_url in found:
+ for video_url in orderedSet(found):
+ video_url = unescapeHTML(video_url)
+ video_url = video_url.replace('\\/', '/')
video_url = compat_urlparse.urljoin(url, video_url)
- video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
+ video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
# Sometimes, jwplayer extraction will result in a YouTube URL
if YoutubeIE.suitable(video_url):
# here's a fun little line of code for you:
video_id = os.path.splitext(video_id)[0]
- entries.append({
+ entry_info_dict = {
'id': video_id,
- 'url': video_url,
'uploader': video_uploader,
'title': video_title,
'age_limit': age_limit,
- })
+ }
+
+ ext = determine_ext(video_url)
+ if ext == 'smil':
+ entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
+ elif ext == 'xspf':
+ return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
+ elif ext == 'm3u8':
+ entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
+ elif ext == 'mpd':
+ entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
+ elif ext == 'f4m':
+ entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
+ else:
+ entry_info_dict['url'] = video_url
+
+ if entry_info_dict.get('formats'):
+ self._sort_formats(entry_info_dict['formats'])
+
+ entries.append(entry_info_dict)
if len(entries) == 1:
return entries[0]
else:
for num, e in enumerate(entries, start=1):
- e['title'] = '%s (%d)' % (e['title'], num)
+ # 'url' results don't have a title
+ if e.get('title') is not None:
+ e['title'] = '%s (%d)' % (e['title'], num)
return {
'_type': 'playlist',
'entries': entries,
Rapsys Git / youtubedl / blobdiff