2016-10-02 13:39:18 +02:00
# coding: utf-8
2013-07-10 17:49:11 +02:00
2014-01-06 01:47:52 +01:00
from __future__ import unicode_literals
2013-06-23 20:31:45 +02:00
import os
import re
2015-09-20 11:16:12 +06:00
import sys
2013-06-23 20:31:45 +02:00
from . common import InfoExtractor
2014-01-06 01:42:58 +01:00
from . youtube import YoutubeIE
2014-11-02 11:23:40 +01:00
from . . compat import (
2015-10-26 16:41:24 +01:00
compat_etree_fromstring ,
2017-06-10 23:55:05 +07:00
compat_str ,
2015-05-31 01:23:58 +06:00
compat_urllib_parse_unquote ,
2013-08-28 12:47:27 +02:00
compat_urlparse ,
2014-02-21 16:59:10 +01:00
compat_xml_parse_error ,
2014-11-02 11:23:40 +01:00
)
from . . utils import (
2014-08-28 01:00:59 +02:00
determine_ext ,
2013-06-23 20:31:45 +02:00
ExtractorError ,
2014-08-24 02:02:17 +02:00
float_or_none ,
2013-12-20 17:05:28 +01:00
HEADRequest ,
2015-01-23 01:21:30 +01:00
is_html ,
2017-02-16 23:42:36 +08:00
js_to_json ,
2017-09-28 00:29:42 +07:00
KNOWN_EXTENSIONS ,
2018-04-28 02:47:17 +07:00
merge_dicts ,
2017-09-28 00:29:42 +07:00
mimetype2ext ,
2014-08-22 18:19:56 +02:00
orderedSet ,
2015-11-21 22:18:17 +06:00
sanitized_Request ,
2013-10-15 12:05:13 +02:00
smuggle_url ,
unescapeHTML ,
2013-12-17 12:33:55 +01:00
unified_strdate ,
2014-08-24 04:47:18 +02:00
unsmuggle_url ,
2014-12-30 19:35:35 +01:00
UnsupportedError ,
2015-03-02 15:21:11 +01:00
xpath_text ,
2013-06-23 20:31:45 +02:00
)
2017-02-06 23:23:40 +07:00
from . commonprotocols import RtmpIE
2015-09-11 04:46:21 +01:00
from . brightcove import (
2015-11-14 05:54:16 +06:00
BrightcoveLegacyIE ,
2015-11-14 05:55:59 +06:00
BrightcoveNewIE ,
2015-09-11 04:46:21 +01:00
)
2017-07-16 04:32:37 +07:00
from . nexx import (
NexxIE ,
NexxEmbedIE ,
)
2015-03-31 03:36:09 +08:00
from . nbc import NBCSportsVPlayerIE
2013-12-19 20:28:52 +01:00
from . ooyala import OoyalaIE
2014-03-17 02:00:31 +07:00
from . rutv import RUTVIE
2015-06-12 16:24:13 +06:00
from . tvc import TVCIE
2018-10-29 00:20:29 +07:00
from . sportbox import SportBoxIE
2014-03-28 19:58:49 +07:00
from . smotri import SmotriIE
2015-07-10 00:27:44 +06:00
from . myvi import MyviIE
2014-10-13 19:59:35 +07:00
from . condenast import CondeNastIE
2015-04-08 17:26:51 +08:00
from . udn import UDNEmbedIE
2015-04-21 03:18:38 +08:00
from . senateisvp import SenateISVPIE
2015-05-09 00:23:35 +06:00
from . svt import SVTIE
2015-06-13 03:36:16 +06:00
from . pornhub import PornHubIE
2015-06-21 23:11:25 +06:00
from . xhamster import XHamsterEmbedIE
2016-02-27 17:15:49 +06:00
from . tnaflix import TNAFlixNetworkEmbedIE
2016-11-06 21:33:51 +07:00
from . drtuber import DrTuberIE
2016-11-06 21:42:41 +07:00
from . redtube import RedTubeIE
2018-04-09 00:37:15 +07:00
from . tube8 import Tube8IE
2015-06-21 18:23:58 +08:00
from . vimeo import VimeoIE
2017-12-06 10:54:20 +01:00
from . dailymotion import DailymotionIE
2017-07-09 20:06:24 +07:00
from . dailymail import DailyMailIE
2015-06-24 23:19:50 +06:00
from . onionstudios import OnionStudiosIE
2016-04-29 11:14:42 +01:00
from . viewlift import ViewLiftEmbedIE
2015-09-26 19:47:20 +06:00
from . mtv import MTVServicesEmbeddedIE
2015-12-07 22:03:21 +06:00
from . pladform import PladformIE
2015-12-29 23:58:23 +06:00
from . videomore import VideomoreIE
2016-11-27 19:56:32 +07:00
from . webcaster import WebcasterFeedIE
2015-12-21 03:05:34 +01:00
from . googledrive import GoogleDriveIE
2015-12-21 04:24:58 +01:00
from . jwplatform import JWPlatformIE
2016-01-19 21:51:46 +06:00
from . digiteka import DigitekaIE
2016-07-23 17:56:48 +07:00
from . arkena import ArkenaIE
2016-03-24 16:32:27 +08:00
from . instagram import InstagramIE
2016-03-31 20:42:55 +02:00
from . liveleak import LiveLeakIE
2016-05-14 23:40:34 +06:00
from . threeqsdn import ThreeQSDNIE
2016-05-22 06:52:39 +06:00
from . theplatform import ThePlatformIE
2016-06-09 04:02:27 +07:00
from . vessel import VesselIE
2016-06-27 22:45:26 +07:00
from . kaltura import KalturaIE
2016-06-29 23:01:34 +07:00
from . eagleplatform import EaglePlatformIE
2016-07-02 21:33:23 +08:00
from . facebook import FacebookIE
2016-07-28 22:15:15 +07:00
from . soundcloud import SoundcloudIE
2017-01-03 01:45:59 +07:00
from . tunein import TuneInBaseIE
2016-08-17 01:02:59 +07:00
from . vbox7 import Vbox7IE
2016-08-17 12:45:24 +02:00
from . dbtv import DBTVIE
2016-12-20 12:34:46 +01:00
from . piksel import PikselIE
2016-12-31 22:04:29 +07:00
from . videa import VideaIE
2017-01-18 22:08:31 +07:00
from . twentymin import TwentyMinutenIE
2017-01-20 21:59:24 +08:00
from . ustream import UstreamIE
2017-01-25 23:27:22 +07:00
from . openload import OpenloadIE
2017-02-05 13:37:27 +07:00
from . videopress import VideoPressIE
2017-03-04 00:46:33 +07:00
from . rutube import RutubeIE
2017-04-17 00:23:16 +07:00
from . limelight import LimelightBaseIE
2017-04-29 19:49:04 +07:00
from . anvato import AnvatoIE
2017-04-10 01:09:10 -04:00
from . washingtonpost import WashingtonPostIE
2017-05-13 21:51:58 +07:00
from . wistia import WistiaIE
2017-05-14 06:29:16 +07:00
from . mediaset import MediasetIE
2017-07-09 19:05:18 +07:00
from . joj import JojIE
2017-07-28 12:13:19 +02:00
from . megaphone import MegaphoneIE
2017-08-11 17:00:39 +02:00
from . vzaar import VzaarIE
2017-10-11 21:59:30 +07:00
from . channel9 import Channel9IE
2017-11-14 16:34:45 +01:00
from . vshare import VShareIE
2017-12-30 07:28:18 +07:00
from . mediasite import MediasiteIE
2018-01-20 00:33:45 +07:00
from . springboardplatform import SpringboardPlatformIE
2018-03-03 01:24:36 +07:00
from . yapfiles import YapFilesIE
2018-03-03 23:07:29 +07:00
from . vice import ViceIE
2018-03-17 23:57:07 +07:00
from . xfileshare import XFileShareIE
2018-05-05 01:21:52 +07:00
from . cloudflarestream import CloudflareStreamIE
2018-05-26 00:28:30 +07:00
from . peertube import PeerTubeIE
2018-12-09 22:28:24 +07:00
from . teachable import TeachableIE
2018-05-26 01:25:40 +07:00
from . indavideo import IndavideoEmbedIE
2018-05-27 18:24:37 +07:00
from . apa import APAIE
2018-06-20 23:51:14 +07:00
from . foxnews import FoxNewsIE
2018-07-30 03:05:36 +07:00
from . viqeo import ViqeoIE
2018-08-14 22:51:44 +07:00
from . expressen import ExpressenIE
2018-11-11 00:44:49 +07:00
from . zype import ZypeIE
2013-06-23 20:31:45 +02:00
2013-08-24 22:49:52 +02:00
2013-06-23 20:31:45 +02:00
class GenericIE ( InfoExtractor ) :
2014-01-06 01:47:52 +01:00
IE_DESC = ' Generic downloader that works on some sites '
2013-06-23 20:31:45 +02:00
_VALID_URL = r ' .* '
2014-01-06 01:47:52 +01:00
IE_NAME = ' generic '
2013-07-10 17:49:11 +02:00
_TESTS = [
2015-05-31 02:22:29 +06:00
# 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 ' ,
}
} ,
2015-05-31 02:36:20 +06:00
# Direct link to media delivered compressed (until Accept-Encoding is *)
2015-05-31 02:22:29 +06:00
{
' 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. '
2016-08-28 15:46:11 +08:00
] ,
' skip ' : ' URL invalid ' ,
2015-05-31 02:22:29 +06:00
} ,
# 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 ' : [
2016-04-16 19:44:12 +08:00
r ' 501.*Not Implemented ' ,
r ' 400.*Bad Request ' ,
2015-05-31 02:22:29 +06:00
] ,
} ,
# 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 ' ,
}
} ,
2018-04-29 17:14:37 +02:00
# RSS feed with enclosures and unsupported link URLs
{
' url ' : ' http://www.hellointernet.fm/podcast?format=rss ' ,
' info_dict ' : {
' id ' : ' http://www.hellointernet.fm/podcast?format=rss ' ,
' description ' : ' CGP Grey and Brady Haran talk about YouTube, life, work, whatever. ' ,
' title ' : ' Hello Internet ' ,
} ,
' playlist_mincount ' : 100 ,
} ,
2015-08-02 01:16:21 +06:00
# 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 ' ,
2015-10-31 23:05:30 +06:00
' upload_date ' : ' 20130627 ' ,
2015-08-02 01:16:21 +06:00
' 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 ,
} ,
} ,
2015-08-09 19:47:08 +06:00
# 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 ' ,
2017-01-02 20:08:07 +08:00
' thumbnail ' : r ' re:^https?://.* \ .jpg$ ' ,
2015-08-09 19:47:08 +06:00
' duration ' : 33 ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
} ,
2016-02-13 00:36:47 +06:00
# 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 ' ,
2016-04-24 20:44:52 +08:00
' upload_date ' : ' 20130904 ' ,
2016-02-13 00:36:47 +06:00
} ,
' params ' : {
' format ' : ' bestvideo ' ,
} ,
} ,
2016-03-18 21:54:33 +06:00
# 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 ,
2016-08-28 15:46:11 +08:00
} ,
' skip ' : ' video gone ' ,
2016-03-18 21:54:33 +06:00
} ,
2016-03-18 22:49:11 +06:00
# 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 ,
2016-08-28 15:46:11 +08:00
} ,
' skip ' : ' video gone ' ,
2016-03-18 22:49:11 +06:00
} ,
2015-05-31 02:22:29 +06:00
# 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 %2F www.youtube.com %2F watch %3F v % 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 ' ,
2017-01-02 20:08:07 +08:00
' description ' : r ' re:^Chris Ziegler takes a look at the \ .* ' ,
2015-05-31 02:22:29 +06:00
' uploader ' : ' The Verge ' ,
' title ' : ' First Firefox OS phones side-by-side ' ,
} ,
' params ' : {
' skip_download ' : False ,
}
} ,
2015-09-20 11:16:12 +06:00
{
# redirect in Refresh HTTP header
' url ' : ' https://www.facebook.com/l.php?u=https % 3A %2F %2F www.youtube.com %2F watch %3F v % 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 ,
} ,
} ,
2013-07-10 17:49:11 +02:00
{
2014-01-06 01:47:52 +01:00
' url ' : ' http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html ' ,
2014-04-14 18:51:46 +07:00
' md5 ' : ' 85b90ccc9d73b4acd9138d3af4c27f89 ' ,
2014-01-06 01:47:52 +01:00
' info_dict ' : {
2014-04-14 18:51:46 +07:00
' id ' : ' 13601338388002 ' ,
' ext ' : ' mp4 ' ,
2014-01-06 01:47:52 +01:00
' uploader ' : ' www.hodiho.fr ' ,
' title ' : ' R \u00e9 gis plante sa Jeep ' ,
2013-07-10 17:49:11 +02:00
}
} ,
2013-10-27 14:40:25 +01:00
# bandcamp page with custom domain
{
2014-01-06 01:47:52 +01:00
' add_ie ' : [ ' Bandcamp ' ] ,
' url ' : ' http://bronyrock.com/track/the-pony-mash ' ,
' info_dict ' : {
2014-04-14 18:56:29 +07:00
' id ' : ' 3235767654 ' ,
' ext ' : ' mp3 ' ,
2014-01-06 01:47:52 +01:00
' title ' : ' The Pony Mash ' ,
' uploader ' : ' M_Pallante ' ,
2013-10-27 14:40:25 +01:00
} ,
2014-01-06 01:47:52 +01:00
' skip ' : ' There is a limit of 200 free downloads / month for the test song ' ,
2013-10-27 14:40:25 +01:00
} ,
2013-11-06 16:40:24 +01:00
{
2016-12-24 22:46:27 +07:00
# embedded brightcove video
# it also tests brightcove videos that need to set the 'Referer'
# in the http requests
2015-11-14 06:05:46 +06:00
' add_ie ' : [ ' BrightcoveLegacy ' ] ,
2014-01-06 01:47:52 +01:00
' url ' : ' http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/ ' ,
' info_dict ' : {
' id ' : ' 2765128793001 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Le cours de bourse : l’ ' ,
' description ' : ' md5:7e9ad046e968cb2d1114004aba466fd9 ' ,
' uploader ' : ' BFM BUSINESS ' ,
2013-11-06 16:40:24 +01:00
} ,
2014-01-06 01:47:52 +01:00
' params ' : {
' skip_download ' : True ,
2013-11-06 16:40:24 +01:00
} ,
} ,
2016-12-24 22:46:27 +07:00
{
# embedded with itemprop embedURL and video id spelled as `idVideo`
' add_id ' : [ ' BrightcoveLegacy ' ] ,
' url ' : ' http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/ ' ,
' info_dict ' : {
' id ' : ' 5255628253001 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' md5:37c519b1128915607601e75a87995fc0 ' ,
' description ' : ' md5:37f7f888b434bb8f8cc8dbd4f7a4cf26 ' ,
' uploader ' : ' BFM BUSINESS ' ,
' uploader_id ' : ' 876450612001 ' ,
' timestamp ' : 1482255315 ,
' upload_date ' : ' 20161220 ' ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
} ,
2014-01-28 03:35:32 +01:00
{
2019-03-09 19:14:41 +07:00
# https://github.com/ytdl-org/youtube-dl/issues/2253
2014-01-28 03:35:32 +01:00
' url ' : ' http://bcove.me/i6nfkrc3 ' ,
' md5 ' : ' 0ba9446db037002366bab3b3eb30c88c ' ,
' info_dict ' : {
2014-04-14 18:56:29 +07:00
' id ' : ' 3101154703001 ' ,
' ext ' : ' mp4 ' ,
2014-01-28 03:35:32 +01:00
' title ' : ' Still no power ' ,
' 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. ' ,
} ,
2015-11-14 06:05:46 +06:00
' add_ie ' : [ ' BrightcoveLegacy ' ] ,
2016-08-28 15:46:11 +08:00
' skip ' : ' video gone ' ,
2014-01-28 03:35:32 +01:00
} ,
2014-04-01 20:17:35 +07:00
{
' url ' : ' http://www.championat.com/video/football/v/87/87499.html ' ,
' md5 ' : ' fb973ecf6e4a78a67453647444222983 ' ,
' info_dict ' : {
' id ' : ' 3414141473001 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Видео. Удаление Дзагоева (ЦСКА) ' ,
' description ' : ' Онлайн-трансляция матча ЦСКА - " Волга " ' ,
' uploader ' : ' Championat ' ,
} ,
} ,
2014-11-03 23:13:46 +02:00
{
2019-03-09 19:14:41 +07:00
# https://github.com/ytdl-org/youtube-dl/issues/3541
2015-11-14 06:05:46 +06:00
' add_ie ' : [ ' BrightcoveLegacy ' ] ,
2014-11-03 23:13:46 +02:00
' url ' : ' http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1 ' ,
' info_dict ' : {
' id ' : ' 3866516442001 ' ,
2014-11-06 00:14:33 +02:00
' ext ' : ' mp4 ' ,
2014-11-03 23:13:46 +02:00
' title ' : ' Leer mij vrouwen kennen: Aflevering 1 ' ,
' description ' : ' Leer mij vrouwen kennen: Aflevering 1 ' ,
' uploader ' : ' SBS Broadcasting ' ,
} ,
2014-11-06 00:14:33 +02:00
' skip ' : ' Restricted to Netherlands ' ,
2014-11-03 23:13:46 +02:00
' params ' : {
2014-11-06 00:14:33 +02:00
' skip_download ' : True , # m3u8 download
2014-11-03 23:13:46 +02:00
} ,
} ,
2017-04-18 23:03:03 +08:00
{
# Brightcove video in <iframe>
' url ' : ' http://www.un.org/chinese/News/story.asp?NewsID=27724 ' ,
' md5 ' : ' 36d74ef5e37c8b4a2ce92880d208b968 ' ,
' info_dict ' : {
' id ' : ' 5360463607001 ' ,
' ext ' : ' mp4 ' ,
' 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 ' ,
' 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（ ） （ ） ， ， ， ' ,
' uploader ' : ' United Nations ' ,
' uploader_id ' : ' 1362235914001 ' ,
' timestamp ' : 1489593889 ,
' upload_date ' : ' 20170315 ' ,
} ,
' add_ie ' : [ ' BrightcoveLegacy ' ] ,
} ,
2017-01-16 00:06:52 +08:00
{
# Brightcove with alternative playerID key
' url ' : ' http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html ' ,
' info_dict ' : {
' id ' : ' nmeth.2062_SV1 ' ,
' 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 ' ,
} ,
' playlist ' : [ {
' info_dict ' : {
' id ' : ' 2228375078001 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' nmeth.2062-sv1 ' ,
' description ' : ' nmeth.2062-sv1 ' ,
' timestamp ' : 1363357591 ,
' upload_date ' : ' 20130315 ' ,
' uploader ' : ' Nature Publishing Group ' ,
' uploader_id ' : ' 1964492299001 ' ,
} ,
} ] ,
} ,
2017-02-12 08:26:36 -05:00
{
# Brightcove with UUID in videoPlayer
' url ' : ' http://www8.hp.com/cn/zh/home.html ' ,
' info_dict ' : {
' id ' : ' 5255815316001 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Sprocket Video - China ' ,
' description ' : ' Sprocket Video - China ' ,
' uploader ' : ' HP-Video Gallery ' ,
' timestamp ' : 1482263210 ,
' upload_date ' : ' 20161220 ' ,
' uploader_id ' : ' 1107601872001 ' ,
} ,
' params ' : {
' skip_download ' : True , # m3u8 download
} ,
' skip ' : ' video rotates...weekly? ' ,
} ,
{
# Brightcove:new type [2].
' url ' : ' http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis ' ,
' md5 ' : ' 2b35148fcf48da41c9fb4591650784f3 ' ,
' info_dict ' : {
' id ' : ' 5348741021001 ' ,
' ext ' : ' mp4 ' ,
' upload_date ' : ' 20170306 ' ,
' uploader_id ' : ' 4191638492001 ' ,
' timestamp ' : 1488769918 ,
' title ' : ' VIDEO: St. Thomas More earns first trip to basketball semis ' ,
} ,
} ,
{
# Alternative brightcove <video> attributes
' 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/ ' ,
' info_dict ' : {
' id ' : ' 81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche ' ,
' title ' : " Guillaume Canet évoque les rumeurs d ' infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs " ,
} ,
' playlist ' : [ {
' md5 ' : ' 732d22ba3d33f2f3fc253c39f8f36523 ' ,
' info_dict ' : {
' id ' : ' 5311302538001 ' ,
' ext ' : ' mp4 ' ,
' title ' : " Guillaume Canet évoque les rumeurs d ' infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche " ,
' description ' : " Guillaume Canet évoque les rumeurs d ' infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017) " ,
' timestamp ' : 1486321708 ,
' upload_date ' : ' 20170205 ' ,
' uploader_id ' : ' 800000640001 ' ,
} ,
' only_matching ' : True ,
} ] ,
} ,
2017-03-07 23:00:21 +07:00
{
# Brightcove with UUID in videoPlayer
' url ' : ' http://www8.hp.com/cn/zh/home.html ' ,
' info_dict ' : {
' id ' : ' 5255815316001 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Sprocket Video - China ' ,
' description ' : ' Sprocket Video - China ' ,
' uploader ' : ' HP-Video Gallery ' ,
' timestamp ' : 1482263210 ,
' upload_date ' : ' 20161220 ' ,
' uploader_id ' : ' 1107601872001 ' ,
} ,
' params ' : {
' skip_download ' : True , # m3u8 download
} ,
} ,
2013-12-19 20:28:52 +01:00
# ooyala video
{
2014-01-06 01:47:52 +01:00
' url ' : ' http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219 ' ,
2015-01-05 13:07:24 +01:00
' md5 ' : ' 166dd577b433b4d4ebfee10b0824d8ff ' ,
2014-01-06 01:47:52 +01:00
' info_dict ' : {
' id ' : ' BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ ' ,
' ext ' : ' mp4 ' ,
2014-01-21 01:40:34 +01:00
' title ' : ' 2cc213299525360.mov ' , # that's what we get
2015-12-04 16:18:02 +01:00
' duration ' : 238.231 ,
2013-12-19 20:28:52 +01:00
} ,
2015-01-05 13:07:24 +01:00
' add_ie ' : [ ' Ooyala ' ] ,
2013-12-19 20:28:52 +01:00
} ,
2015-08-08 02:00:49 +06:00
{
# 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 ' : ' p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB ' ,
' ext ' : ' mp4 ' ,
' title ' : ' " Steve Jobs: Man in the Machine " trailer ' ,
' description ' : ' The first trailer for the Alex Gibney documentary " Steve Jobs: Man in the Machine. " ' ,
2015-12-04 16:18:02 +01:00
' duration ' : 135.427 ,
2015-08-08 02:00:49 +06:00
} ,
' params ' : {
' skip_download ' : True ,
} ,
2016-08-28 15:46:11 +08:00
' skip ' : ' movie expired ' ,
2015-08-08 02:00:49 +06:00
} ,
2017-07-29 20:30:04 +02:00
# ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
{
' url ' : ' http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/ ' ,
' info_dict ' : {
' id ' : ' lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Steampunk Fest Comes to Honesdale ' ,
' duration ' : 43.276 ,
} ,
' params ' : {
' skip_download ' : True ,
}
} ,
2014-02-24 01:15:51 +01:00
# embed.ly video
{
' url ' : ' http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/ ' ,
' info_dict ' : {
' id ' : ' 9ODmcdjQcHQ ' ,
' ext ' : ' mp4 ' ,
2014-03-05 14:05:44 +01:00
' title ' : ' Tested: Grinding Coffee at 2000 Frames Per Second ' ,
' upload_date ' : ' 20140225 ' ,
' description ' : ' md5:06a40fbf30b220468f1e0957c0f558ff ' ,
' uploader ' : ' Tested ' ,
' uploader_id ' : ' testedcom ' ,
2014-02-24 01:15:51 +01:00
} ,
# No need to test YoutubeIE here
' params ' : {
' skip_download ' : True ,
} ,
} ,
2014-03-11 16:51:36 +01:00
# funnyordie embed
{
' url ' : ' http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns ' ,
' info_dict ' : {
' id ' : ' 18e820ec3f ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Between Two Ferns with Zach Galifianakis: President Barack Obama ' ,
' description ' : ' Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet. ' ,
2014-03-17 02:00:31 +07:00
} ,
2016-08-28 15:46:11 +08:00
# HEAD requests lead to endless 301, while GET is OK
' expected_warnings ' : [ ' 301 ' ] ,
2014-03-11 16:51:36 +01:00
} ,
2014-03-17 02:00:31 +07:00
# RUTV embed
{
' url ' : ' http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html ' ,
' info_dict ' : {
' id ' : ' 776940 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Охотское море стало целиком российским ' ,
' description ' : ' md5:5ed62483b14663e2a95ebbe115eb8f43 ' ,
} ,
' params ' : {
# m3u8 download
' skip_download ' : True ,
} ,
2014-03-20 16:33:23 +01:00
} ,
2015-06-12 16:28:45 +06:00
# 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 ' ,
} ,
} ,
2015-05-15 23:18:21 +06:00
# SportBox embed
{
' url ' : ' http://www.vestifinance.ru/articles/25753 ' ,
' info_dict ' : {
' id ' : ' 25753 ' ,
2016-07-26 11:11:36 +08:00
' title ' : ' Прямые трансляции с " Госзаказ-2013 " ' ,
2015-05-15 23:18:21 +06:00
} ,
' 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 ,
} ,
} ,
2015-07-10 01:15:55 +06:00
# 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) ' ,
2017-01-02 20:08:07 +08:00
' thumbnail ' : r ' re:^https?://.* \ .jpg$ ' ,
2015-07-10 01:15:55 +06:00
' duration ' : 153 ,
}
} ,
2015-06-21 23:18:28 +06:00
# 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 ,
2016-08-28 15:46:11 +08:00
# This forum does not allow <iframe> syntaxes anymore
# Now HTML tags are displayed as-is
' skip ' : ' No videos on this page ' ,
2015-06-21 23:18:28 +06:00
} ,
2014-03-20 16:33:23 +01:00
# Embedded TED video
{
' url ' : ' http://en.support.wordpress.com/videos/ted-talks/ ' ,
2014-09-29 05:12:57 +02:00
' md5 ' : ' 65fdff94098e4a607385a60c5177c638 ' ,
2014-03-20 16:33:23 +01:00
' info_dict ' : {
2014-09-29 05:12:57 +02:00
' id ' : ' 1969 ' ,
2014-03-20 16:33:23 +01:00
' ext ' : ' mp4 ' ,
2014-09-29 05:12:57 +02:00
' title ' : ' Hidden miracles of the natural world ' ,
' uploader ' : ' Louie Schwartzberg ' ,
' description ' : ' md5:8145d19d320ff3e52f28401f4c4283b9 ' ,
2014-03-20 16:33:23 +01:00
}
2014-03-11 16:51:36 +01:00
} ,
2014-03-15 04:39:53 +07:00
# nowvideo embed hidden behind percent encoding
{
' url ' : ' http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/ ' ,
' md5 ' : ' 2baf4ddd70f697d94b1c18cf796d5107 ' ,
' info_dict ' : {
' id ' : ' 06e53103ca9aa ' ,
' ext ' : ' flv ' ,
' title ' : ' Macross Episode 001 Watch Macross Episode 001 onl ' ,
' description ' : ' No description ' ,
} ,
2014-03-21 22:14:24 +01:00
} ,
2014-03-24 22:01:47 +01:00
# arte embed
{
' url ' : ' http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html ' ,
' md5 ' : ' 7653032cbb25bf6c80d80f217055fa43 ' ,
' info_dict ' : {
' id ' : ' 048195-004_PLUS7-F ' ,
' ext ' : ' flv ' ,
' title ' : ' X:enius ' ,
' description ' : ' md5:d5fdf32ef6613cdbfd516ae658abf168 ' ,
' upload_date ' : ' 20140320 ' ,
} ,
' params ' : {
' skip_download ' : ' Requires rtmpdump '
2016-08-28 15:46:11 +08:00
} ,
' skip ' : ' video gone ' ,
2014-03-24 22:01:47 +01:00
} ,
2015-07-18 22:56:00 +06:00
# 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 '
]
} ,
2014-04-21 05:47:52 +02:00
# Condé Nast embed
{
' url ' : ' http://www.wired.com/2014/04/honda-asimo/ ' ,
' md5 ' : ' ba0dfe966fa007657bd1443ee672db0f ' ,
' info_dict ' : {
' id ' : ' 53501be369702d3275860000 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Honda’ ' ,
}
2014-04-30 01:46:06 +02:00
} ,
# Dailymotion embed
{
' url ' : ' http://www.spi0n.com/zap-spi0n-com-n216/ ' ,
' md5 ' : ' 441aeeb82eb72c422c7f14ec533999cd ' ,
' info_dict ' : {
' id ' : ' k2mm4bCdJ6CQ2i7c8o2 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Le Zap de Spi0n n°216 - Zapping du Web ' ,
2016-04-24 20:44:52 +08:00
' description ' : ' md5:faf028e48a461b8b7fad38f1e104b119 ' ,
2014-04-30 01:46:06 +02:00
' uploader ' : ' Spi0n ' ,
2016-04-24 20:44:52 +08:00
' uploader_id ' : ' xgditw ' ,
' upload_date ' : ' 20140425 ' ,
' timestamp ' : 1398441542 ,
2014-04-30 01:46:06 +02:00
} ,
' add_ie ' : [ ' Dailymotion ' ] ,
2014-06-09 22:06:45 +02:00
} ,
2017-07-09 20:06:24 +07:00
# DailyMail embed
{
' url ' : ' http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot ' ,
' info_dict ' : {
' id ' : ' 1495629 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Care worker punches elderly dementia patient in head 11 times ' ,
' description ' : ' md5:3a743dee84e57e48ec68bf67113199a5 ' ,
} ,
' add_ie ' : [ ' DailyMail ' ] ,
' params ' : {
' skip_download ' : True ,
} ,
} ,
2014-06-09 22:06:45 +02:00
# YouTube embed
{
' url ' : ' http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html ' ,
' info_dict ' : {
' id ' : ' FXRb4ykk4S0 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' The NBL Auction 2014 ' ,
' uploader ' : ' BADMINTON England ' ,
' uploader_id ' : ' BADMINTONEvents ' ,
' upload_date ' : ' 20140603 ' ,
' description ' : ' md5:9ef128a69f1e262a700ed83edb163a73 ' ,
} ,
' add_ie ' : [ ' Youtube ' ] ,
' params ' : {
' skip_download ' : True ,
}
} ,
2014-06-22 21:38:04 +02:00
# MTVSercices embed
{
2016-06-10 16:39:31 +08:00
' url ' : ' http://www.vulture.com/2016/06/new-key-peele-sketches-released.html ' ,
' md5 ' : ' ca1aef97695ef2c1d6973256a57e5252 ' ,
2014-06-22 21:38:04 +02:00
' info_dict ' : {
2016-06-10 16:39:31 +08:00
' id ' : ' 769f7ec0-0692-4d62-9b45-0d88074bffc1 ' ,
2014-06-22 21:38:04 +02:00
' ext ' : ' mp4 ' ,
2016-06-10 16:39:31 +08:00
' title ' : ' Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored ' ,
' description ' : ' Two valets share their love for movie star Liam Neesons. ' ,
2016-07-26 11:11:36 +08:00
' timestamp ' : 1349922600 ,
' upload_date ' : ' 20121011 ' ,
2014-06-22 21:38:04 +02:00
} ,
} ,
2014-05-21 19:25:37 +09:30
# YouTube embed via <data-embed-url="">
{
' url ' : ' https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM ' ,
' info_dict ' : {
2014-09-29 05:12:57 +02:00
' id ' : ' 4vAffPZIT44 ' ,
2014-05-21 19:25:37 +09:30
' ext ' : ' mp4 ' ,
2014-09-29 05:12:57 +02:00
' title ' : ' Asphalt 8: Airborne - Update - Welcome to Dubai! ' ,
2014-08-22 18:19:56 +02:00
' uploader ' : ' Gameloft ' ,
' uploader_id ' : ' gameloft ' ,
2014-09-29 05:12:57 +02:00
' upload_date ' : ' 20140828 ' ,
' description ' : ' md5:c80da9ed3d83ae6d1876c834de03e1c4 ' ,
2014-08-22 18:19:56 +02:00
} ,
' params ' : {
' skip_download ' : True ,
2014-05-21 19:25:37 +09:30
}
2014-08-24 02:02:17 +02:00
} ,
2017-04-10 13:04:32 -04:00
# YouTube <object> embed
{
' url ' : ' http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/ ' ,
' md5 ' : ' 516718101ec834f74318df76259fb3cc ' ,
' info_dict ' : {
' id ' : ' msN87y-iEx0 ' ,
' ext ' : ' webm ' ,
' title ' : ' Feynman: Mirrors FUN TO IMAGINE 6 ' ,
' upload_date ' : ' 20080526 ' ,
' description ' : ' md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d ' ,
' uploader ' : ' Christopher Sykes ' ,
' uploader_id ' : ' ChristopherJSykes ' ,
} ,
' add_ie ' : [ ' Youtube ' ] ,
} ,
2014-08-24 02:02:17 +02:00
# Camtasia studio
{
' url ' : ' http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/ ' ,
' playlist ' : [ {
' md5 ' : ' 0c5e352edabf715d762b0ad4e6d9ee67 ' ,
' info_dict ' : {
' id ' : ' Fenn-AA_PA_Radar_Course_Lecture_1c_Final ' ,
' title ' : ' Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1 ' ,
' ext ' : ' flv ' ,
' duration ' : 2235.90 ,
}
} , {
' md5 ' : ' 10e4bb3aaca9fd630e273ff92d9f3c63 ' ,
' info_dict ' : {
' id ' : ' Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP ' ,
' title ' : ' Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip ' ,
' ext ' : ' flv ' ,
' duration ' : 2235.93 ,
}
} ] ,
' info_dict ' : {
' title ' : ' Fenn-AA_PA_Radar_Course_Lecture_1c_Final ' ,
}
2014-08-24 05:31:32 +02:00
} ,
# 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 ' ,
2014-10-27 00:45:15 +01:00
' title ' : ' Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com ' ,
2014-08-24 05:31:32 +02:00
}
2014-08-25 18:03:01 +02:00
} ,
2014-08-28 00:58:24 +02:00
# Multiple brightcove videos
2019-03-09 19:14:41 +07:00
# https://github.com/ytdl-org/youtube-dl/issues/2283
2014-08-28 00:58:24 +02:00
{
' 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 ,
}
2014-09-02 20:19:28 +07:00
} ,
# 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 ' ,
2017-01-02 20:08:07 +08:00
' thumbnail ' : r ' re:^https?://.* \ .jpg$ ' ,
2014-09-02 20:19:28 +07:00
} ,
} ,
2014-09-20 03:02:11 +03:00
# Wistia embed
{
2016-05-20 21:55:35 +06:00
' url ' : ' http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson ' ,
' md5 ' : ' 1953f3a698ab51cfc948ed3992a0b7ff ' ,
2014-09-20 03:02:11 +03:00
' info_dict ' : {
2016-05-20 21:55:35 +06:00
' id ' : ' 6e2wtrbdaf ' ,
2014-09-20 03:02:11 +03:00
' ext ' : ' mov ' ,
2016-05-20 21:55:35 +06:00
' 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 ,
2014-09-20 03:02:11 +03:00
} ,
} ,
2014-10-23 20:27:13 +05:30
{
' url ' : ' http://thoughtworks.wistia.com/medias/uxjb0lwrcz ' ,
' md5 ' : ' baf49c2baa8a7de5f3fc145a8506dcd4 ' ,
' info_dict ' : {
' id ' : ' uxjb0lwrcz ' ,
' ext ' : ' mp4 ' ,
2016-05-20 21:55:35 +06:00
' title ' : ' Conversation about Hexagonal Rails Part 1 ' ,
2016-04-24 20:44:52 +08:00
' description ' : ' a Martin Fowler video from ThoughtWorks ' ,
2014-10-23 20:27:13 +05:30
' duration ' : 1715.0 ,
2014-10-23 21:23:56 +05:30
' uploader ' : ' thoughtworks.wistia.com ' ,
2016-04-24 20:44:52 +08:00
' timestamp ' : 1401832161 ,
2016-05-20 21:55:35 +06:00
' upload_date ' : ' 20140603 ' ,
2014-10-26 20:49:51 +01:00
} ,
2014-10-23 20:27:13 +05:30
} ,
2016-05-20 21:43:36 +06:00
# 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 ,
2016-05-20 21:55:35 +06:00
' upload_date ' : ' 20160518 ' ,
2016-05-20 21:43:36 +06:00
} ,
' params ' : {
' skip_download ' : True ,
}
} ,
2014-10-29 20:27:58 +01:00
# 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 ' ,
}
2014-11-13 16:12:51 +01:00
} ,
2016-07-28 22:20:08 +07:00
# Soundcloud multiple embeds
{
' url ' : ' http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809 ' ,
' info_dict ' : {
' id ' : ' 52809 ' ,
' title ' : ' Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO ' ,
} ,
' playlist_mincount ' : 7 ,
} ,
2017-01-03 01:45:59 +07:00
# TuneIn station embed
{
' url ' : ' http://radiocnrv.com/promouvoir-radio-cnrv/ ' ,
' info_dict ' : {
' id ' : ' 204146 ' ,
' ext ' : ' mp3 ' ,
' title ' : ' CNRV ' ,
' location ' : ' Paris, France ' ,
' is_live ' : True ,
} ,
' params ' : {
# Live stream
' skip_download ' : True ,
} ,
} ,
2014-11-13 16:12:51 +01:00
# 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 ' ,
}
} ,
2016-05-23 01:39:09 +08:00
# 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 ,
} ,
} ,
2014-11-25 14:34:19 +01:00
# LazyYT
{
2017-03-19 20:52:25 -04:00
' url ' : ' https://skiplagged.com/ ' ,
2014-11-25 14:34:19 +01:00
' info_dict ' : {
2017-03-19 20:52:25 -04:00
' id ' : ' skiplagged ' ,
' title ' : ' Skiplagged: The smart way to find cheap flights ' ,
2014-11-25 14:34:19 +01:00
} ,
2017-03-19 20:52:25 -04:00
' playlist_mincount ' : 1 ,
' add_ie ' : [ ' Youtube ' ] ,
2014-11-26 10:44:39 +01:00
} ,
2014-12-12 02:57:36 +01:00
# 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 ' ,
}
} ,
2015-01-23 12:00:25 +01:00
# 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 ' ,
}
2015-01-28 00:08:19 -05:00
} ,
# 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 ' ] ,
2015-02-09 10:42:25 +01:00
} ,
2015-03-22 08:20:27 +06:00
# 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 ' ,
} ,
2016-07-26 13:16:04 +08:00
' skip ' : ' All The Daily Show URLs now redirect to http://www.cc.com/shows/ ' ,
2015-03-22 08:20:27 +06:00
} ,
2015-02-09 10:42:25 +01:00
# jwplayer YouTube
{
' url ' : ' http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/ ' ,
' info_dict ' : {
' id ' : ' Mrj4DVp2zeA ' ,
' ext ' : ' mp4 ' ,
2015-02-19 02:00:50 +01:00
' upload_date ' : ' 20150212 ' ,
2015-02-09 10:42:25 +01:00
' uploader ' : ' The National Archives UK ' ,
2017-10-12 16:14:43 +00:00
' description ' : ' md5:8078af856dca76edc42910b61273dbbf ' ,
2015-02-09 10:42:25 +01:00
' uploader_id ' : ' NationalArchives08 ' ,
' title ' : ' Webinar: Using Discovery, The National Archives’ ' ,
} ,
2015-02-16 15:45:01 +01:00
} ,
2017-02-06 23:31:58 +07:00
# jwplayer rtmp
{
2017-11-22 11:56:47 -05:00
' url ' : ' http://www.suffolk.edu/sjc/live.php ' ,
2017-02-06 23:31:58 +07:00
' info_dict ' : {
2017-11-22 11:56:47 -05:00
' id ' : ' live ' ,
2017-02-06 23:31:58 +07:00
' ext ' : ' flv ' ,
' title ' : ' Massachusetts Supreme Judicial Court Oral Arguments ' ,
' uploader ' : ' www.suffolk.edu ' ,
} ,
' params ' : {
' skip_download ' : True ,
2017-10-12 16:14:43 +00:00
} ,
2017-11-22 11:56:47 -05:00
' skip ' : ' Only has video a few mornings per month, see http://www.suffolk.edu/sjc/ ' ,
2017-02-06 23:31:58 +07:00
} ,
2017-02-16 23:42:36 +08:00
# Complex jwplayer
{
' url ' : ' http://www.indiedb.com/games/king-machine/videos ' ,
' info_dict ' : {
' id ' : ' videos ' ,
' ext ' : ' mp4 ' ,
' title ' : ' king machine trailer 1 ' ,
2017-10-12 16:14:43 +00:00
' description ' : ' Browse King Machine videos & audio for sweet media. Your eyes will thank you. ' ,
2017-02-16 23:42:36 +08:00
' thumbnail ' : r ' re:^https?://.* \ .jpg$ ' ,
} ,
} ,
2017-03-25 19:37:45 +01:00
{
# JWPlayer config passed as variable
' url ' : ' http://www.txxx.com/videos/3326530/ariele/ ' ,
' info_dict ' : {
' id ' : ' 3326530_hq ' ,
' ext ' : ' mp4 ' ,
' title ' : ' ARIELE | Tube Cup ' ,
' uploader ' : ' www.txxx.com ' ,
' age_limit ' : 18 ,
} ,
' params ' : {
' skip_download ' : True ,
}
} ,
2017-11-22 11:47:02 -05:00
{
# JWPlatform iframe
' url ' : ' https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/ ' ,
' md5 ' : ' ca00a040364b5b439230e7ebfd02c4e9 ' ,
' info_dict ' : {
' id ' : ' O0c5JcKT ' ,
' ext ' : ' mp4 ' ,
' upload_date ' : ' 20171122 ' ,
' timestamp ' : 1511366290 ,
' title ' : ' Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone ' ,
} ,
2017-11-24 08:11:32 -05:00
' add_ie ' : [ JWPlatformIE . ie_key ( ) ] ,
2017-11-22 11:47:02 -05:00
} ,
2017-09-28 00:29:42 +07:00
{
2017-10-01 07:01:21 +07:00
# Video.js embed, multiple formats
2017-09-28 00:29:42 +07:00
' url ' : ' http://ortcam.com/solidworks-урок-6-настройка-че р е а ' ,
' info_dict ' : {
' id ' : ' yygqldloqIk ' ,
' ext ' : ' mp4 ' ,
' title ' : ' SolidWorks. Урок 6 Настройка чертежа ' ,
' description ' : ' md5:baf95267792646afdbf030e4d06b2ab3 ' ,
' upload_date ' : ' 20130314 ' ,
' uploader ' : ' PROс о е ' ,
' uploader_id ' : ' PROstoe3D ' ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
} ,
2017-10-01 07:01:21 +07:00
{
# Video.js embed, single format
' url ' : ' https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg= ' ,
' info_dict ' : {
' id ' : ' watch ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Step 1 - Good Foundation ' ,
' description ' : ' md5:d1e7ff33a29fc3eb1673d6c270d344f4 ' ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
} ,
2015-02-16 15:45:01 +01:00
# rtl.nl embed
{
' url ' : ' http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen ' ,
' playlist_mincount ' : 5 ,
' info_dict ' : {
' id ' : ' aanslagen-kopenhagen ' ,
2017-10-12 16:14:43 +00:00
' title ' : ' Aanslagen Kopenhagen ' ,
2015-02-16 15:45:01 +01:00
}
2015-02-22 01:39:26 +06:00
} ,
# 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 ! ' ,
}
} ,
2015-07-02 21:39:46 +06:00
# 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 ' ,
} ,
} ,
2016-06-01 18:37:34 +08:00
# 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 ' ,
2018-04-18 01:24:02 +07:00
' uploader_id ' : ' cplapp@learn360.com ' ,
2016-06-01 18:37:34 +08:00
} ,
' add_ie ' : [ ' Kaltura ' ] ,
} ,
2016-06-27 04:11:53 +07:00
{
# Kaltura embedded via quoted entry_id
' url ' : ' https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures ' ,
' info_dict ' : {
' id ' : ' 0_utuok90b ' ,
' ext ' : ' mp4 ' ,
' title ' : ' 06_matthew_brender_raj_dutt ' ,
' timestamp ' : 1466638791 ,
' upload_date ' : ' 20160622 ' ,
} ,
' add_ie ' : [ ' Kaltura ' ] ,
' expected_warnings ' : [
' Could not send HEAD request '
] ,
' params ' : {
' skip_download ' : True ,
}
} ,
2016-12-20 18:45:52 +08:00
{
# Kaltura embedded, some fileExt broken (#11480)
' url ' : ' http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics ' ,
' info_dict ' : {
' id ' : ' 1_sgtvehim ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Our " Standard Models " of particle physics and cosmology ' ,
' description ' : ' md5:67ea74807b8c4fea92a6f38d6d323861 ' ,
' timestamp ' : 1321158993 ,
' upload_date ' : ' 20111113 ' ,
' uploader_id ' : ' kps1 ' ,
} ,
' add_ie ' : [ ' Kaltura ' ] ,
} ,
2017-04-08 05:40:57 -04:00
{
# Kaltura iframe embed
' url ' : ' http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/ ' ,
' md5 ' : ' ae5ace8eb09dc1a35d03b579a9c2cc44 ' ,
' info_dict ' : {
' id ' : ' 0_f2cfbpwy ' ,
' ext ' : ' mp4 ' ,
' title ' : ' I. M. Pei: A Centennial Celebration ' ,
' description ' : ' md5:1db8f40c69edc46ca180ba30c567f37c ' ,
' upload_date ' : ' 20170403 ' ,
' uploader_id ' : ' batchUser ' ,
' timestamp ' : 1491232186 ,
} ,
' add_ie ' : [ ' Kaltura ' ] ,
} ,
2018-05-01 03:09:04 +07:00
{
# Kaltura iframe embed, more sophisticated
' url ' : ' http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html ' ,
' info_dict ' : {
' id ' : ' 1_9gzouybz ' ,
' ext ' : ' mp4 ' ,
' title ' : ' lecture-05sep2017 ' ,
' description ' : ' md5:40f347d91fd4ba047e511c5321064b49 ' ,
' upload_date ' : ' 20170913 ' ,
' uploader_id ' : ' eps2 ' ,
' timestamp ' : 1505340777 ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
' add_ie ' : [ ' Kaltura ' ] ,
} ,
2018-04-18 01:24:02 +07:00
{
# meta twitter:player
' url ' : ' http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/ ' ,
' info_dict ' : {
' id ' : ' 0_01b42zps ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Main Twerk (Video) ' ,
' upload_date ' : ' 20171208 ' ,
' uploader_id ' : ' sebastian.salinas@thechive.com ' ,
' timestamp ' : 1512713057 ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
' add_ie ' : [ ' Kaltura ' ] ,
} ,
2017-07-09 16:02:38 +07:00
# referrer protected EaglePlatform embed
{
' url ' : ' https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/ ' ,
' info_dict ' : {
' id ' : ' 582306 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Стас Намин: «Мы нарушили девственность Кремля» ' ,
' thumbnail ' : r ' re:^https?://.* \ .jpg$ ' ,
' duration ' : 3382 ,
' view_count ' : int ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
2015-03-07 22:22:57 +06:00
} ,
2017-07-09 15:57:33 +07:00
# ClipYou (EaglePlatform) embed (custom URL)
2015-03-07 22:34:44 +06:00
{
' url ' : ' http://muz-tv.ru/play/7129/ ' ,
2016-04-25 22:48:17 +08:00
# Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
2015-03-07 22:34:44 +06:00
' info_dict ' : {
' id ' : ' 12820 ' ,
' ext ' : ' mp4 ' ,
' title ' : " ' O Sole Mio " ,
2017-01-02 20:08:07 +08:00
' thumbnail ' : r ' re:^https?://.* \ .jpg$ ' ,
2015-03-07 22:34:44 +06:00
' duration ' : 216 ,
' view_count ' : int ,
} ,
2017-07-09 16:02:38 +07:00
' params ' : {
' skip_download ' : True ,
} ,
2017-10-12 16:14:43 +00:00
' skip ' : ' This video is unavailable. ' ,
2015-03-07 22:34:44 +06:00
} ,
2015-03-08 18:07:10 +06:00
# Pladform embed
{
' url ' : ' http://muz-tv.ru/kinozal/view/7400/ ' ,
' info_dict ' : {
' id ' : ' 100183293 ' ,
' ext ' : ' mp4 ' ,
2015-04-16 21:37:15 +06:00
' title ' : ' Тайны перевала Дятлова • 1 серия 2 часть ' ,
2015-03-08 18:07:10 +06:00
' description ' : ' Документальный сериал-расследование одной из самых жутких тайн Х Х ' ,
2017-01-02 20:08:07 +08:00
' thumbnail ' : r ' re:^https?://.* \ .jpg$ ' ,
2015-03-08 18:07:10 +06:00
' duration ' : 694 ,
' age_limit ' : 0 ,
} ,
2017-10-12 16:14:43 +00:00
' skip ' : ' HTTP Error 404: Not Found ' ,
2015-03-08 18:07:10 +06:00
} ,
2015-04-15 22:13:01 +06:00
# 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 ' ,
2017-01-02 20:08:07 +08:00
' thumbnail ' : r ' re:^https?://.* \ .png$ ' ,
2015-04-15 22:13:01 +06:00
' duration ' : 45.115 ,
} ,
} ,
2015-03-29 04:57:37 +03:00
# 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 ' ,
2017-10-12 16:14:43 +00:00
' description ' : ' Amazon updates Fire TV line, Tesla \' s Model X spotted in the wild ' ,
' timestamp ' : 1427237531 ,
' uploader ' : ' Crunch Report ' ,
' upload_date ' : ' 20150324 ' ,
} ,
' params ' : {
# m3u8 download
' skip_download ' : True ,
2015-03-29 04:57:37 +03:00
} ,
} ,
2015-04-11 20:26:42 +06:00
# 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 ' ,
} ,
} ,
2015-03-31 20:11:14 +06:00
# NBC Sports vplayer embed
2015-03-31 03:36:09 +08:00
{
2015-03-31 20:11:14 +06:00
' url ' : ' http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a ' ,
2015-03-31 03:36:09 +08:00
' info_dict ' : {
2015-03-31 20:11:14 +06:00
' id ' : ' ln7x1qSThw4k ' ,
' ext ' : ' flv ' ,
' title ' : " PFT Live: New leader in the ' new-look ' defense " ,
' description ' : ' md5:65a19b4bbfb3b0c0c5768bed1dfad74e ' ,
2016-04-24 20:44:52 +08:00
' uploader ' : ' NBCU-SPORTS ' ,
' upload_date ' : ' 20140107 ' ,
' timestamp ' : 1389118457 ,
2015-03-31 03:36:09 +08:00
} ,
2017-10-12 16:14:43 +00:00
' skip ' : ' Invalid Page URL ' ,
2015-04-08 17:26:51 +08:00
} ,
2016-06-10 13:32:59 +08:00
# NBC News embed
{
' url ' : ' http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html ' ,
' md5 ' : ' 1aa589c675898ae6d37a17913cf68d66 ' ,
' info_dict ' : {
2017-10-12 16:14:43 +00:00
' id ' : ' x_dtl_oa_LettermanliftPR_160608 ' ,
2016-06-10 13:32:59 +08:00
' ext ' : ' mp4 ' ,
2017-10-12 16:14:43 +00:00
' title ' : ' David Letterman: A Preview ' ,
2016-06-10 13:32:59 +08:00
' 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. ' ,
2017-10-12 16:14:43 +00:00
' upload_date ' : ' 20160609 ' ,
' timestamp ' : 1465431544 ,
' uploader ' : ' NBCU-NEWS ' ,
2016-06-10 13:32:59 +08:00
} ,
} ,
2015-04-08 17:26:51 +08:00
# UDN embed
{
2016-06-01 19:23:44 +08:00
' url ' : ' https://video.udn.com/news/300346 ' ,
2015-04-14 13:10:10 +08:00
' md5 ' : ' fd2060e988c326991037b9aff9df21a6 ' ,
2015-04-08 17:26:51 +08:00
' info_dict ' : {
2015-04-14 13:10:10 +08:00
' id ' : ' 300346 ' ,
2015-04-08 17:26:51 +08:00
' ext ' : ' mp4 ' ,
2015-04-14 13:10:10 +08:00
' title ' : ' 中一中男師變性 全校師生力挺 ' ,
2017-01-02 20:08:07 +08:00
' thumbnail ' : r ' re:^https?://.* \ .jpg$ ' ,
2016-06-01 19:23:44 +08:00
} ,
' params ' : {
# m3u8 download
' skip_download ' : True ,
} ,
2017-10-12 16:14:43 +00:00
' expected_warnings ' : [ ' Failed to parse JSON Expecting value ' ] ,
2015-04-14 12:45:43 +08:00
} ,
2015-06-07 15:29:17 +08:00
# 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’ ' ,
' uploader ' : ' Rogers Sportsnet ' ,
2016-04-24 20:44:52 +08:00
' uploader_id ' : ' 1704050871 ' ,
' upload_date ' : ' 20150525 ' ,
' timestamp ' : 1432570283 ,
2015-06-07 15:29:17 +08:00
} ,
2015-06-21 21:30:34 +08:00
} ,
2015-06-24 23:23:16 +06:00
# OnionStudios embed
{
' url ' : ' http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537 ' ,
' info_dict ' : {
' id ' : ' 2855 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Don’ ' ,
2017-01-02 20:08:07 +08:00
' thumbnail ' : r ' re:^https?://.* \ .jpe?g$ ' ,
2015-06-24 23:23:16 +06:00
' uploader ' : ' ClickHole ' ,
' uploader_id ' : ' clickhole ' ,
}
} ,
2015-06-27 18:28:10 +06:00
# SnagFilms embed
{
' url ' : ' http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html ' ,
' info_dict ' : {
' id ' : ' 74849a00-85a9-11e1-9660-123139220831 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' #whilewewatch ' ,
}
} ,
2015-06-22 15:02:53 +08:00
# AdobeTVVideo embed
{
' url ' : ' https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners ' ,
' md5 ' : ' 43662b577c018ad707a63766462b1e87 ' ,
' info_dict ' : {
' id ' : ' 2456 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' New experience with Acrobat DC ' ,
' description ' : ' New experience with Acrobat DC ' ,
' duration ' : 248.667 ,
} ,
2015-08-29 19:12:38 +06:00
} ,
2015-09-11 04:46:21 +01:00
# BrightcoveInPageEmbed embed
{
' url ' : ' http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/ ' ,
' info_dict ' : {
' id ' : ' 4238694884001 ' ,
' ext ' : ' flv ' ,
' title ' : ' Tabletop: Dread, Last Thoughts ' ,
' description ' : ' Tabletop: Dread, Last Thoughts ' ,
' duration ' : 51690 ,
} ,
2015-11-21 16:43:01 +08:00
} ,
2016-03-26 18:30:43 +08:00
# 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 ' : ' https://dl.dropboxusercontent.com/u/29092637/interview.html ' ,
' info_dict ' : {
' 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 ' ,
2016-04-24 20:44:52 +08:00
' uploader_id ' : ' 2733773828001 ' ,
' upload_date ' : ' 20160304 ' ,
' timestamp ' : 1457083087 ,
2016-03-26 18:30:43 +08:00
} ,
' params ' : {
# m3u8 downloads
' skip_download ' : True ,
} ,
} ,
2017-05-01 01:03:47 +07:00
{
# Brightcove embed with whitespace around attribute names
' url ' : ' http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill ' ,
' info_dict ' : {
' id ' : ' 3167554373001 ' ,
' ext ' : ' mp4 ' ,
' title ' : " Learn to Hit Open Three-Pointers With Damian Lillard ' s Baseline Drift Drill " ,
' description ' : ' md5:57bacb0e0f29349de4972bfda3191713 ' ,
' uploader_id ' : ' 1079349493 ' ,
' upload_date ' : ' 20140207 ' ,
' timestamp ' : 1391810548 ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
} ,
2016-04-11 19:17:11 +08:00
# Another form of arte.tv embed
{
' url ' : ' http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html ' ,
' md5 ' : ' 850bfe45417ddf221288c88a0cffe2e2 ' ,
' info_dict ' : {
' id ' : ' 030273-562_PLUS7-F ' ,
' ext ' : ' mp4 ' ,
' title ' : ' ARTE Reportage - Nulle part, en France ' ,
' description ' : ' md5:e3a0e8868ed7303ed509b9e3af2b870d ' ,
' upload_date ' : ' 20160409 ' ,
} ,
} ,
2016-03-31 20:42:55 +02:00
# LiveLeak embed
{
' url ' : ' http://www.wykop.pl/link/3088787/ ' ,
2017-08-19 22:27:53 +08:00
' md5 ' : ' 7619da8c820e835bef21a1efa2a0fc71 ' ,
2016-03-31 20:42:55 +02:00
' info_dict ' : {
' id ' : ' 874_1459135191 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Man shows poor quality of new apartment building ' ,
' description ' : ' The wall is like a sand pile. ' ,
' uploader ' : ' Lake8737 ' ,
2017-08-19 22:27:53 +08:00
} ,
' add_ie ' : [ LiveLeakIE . ie_key ( ) ] ,
} ,
# Another LiveLeak embed pattern (#13336)
{
' url ' : ' https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/ ' ,
' info_dict ' : {
' id ' : ' 2eb_1496309988 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Thief robs place where everyone was armed ' ,
' description ' : ' md5:694d73ee79e535953cf2488562288eee ' ,
' uploader ' : ' brazilwtf ' ,
} ,
' add_ie ' : [ LiveLeakIE . ie_key ( ) ] ,
2016-03-31 20:42:55 +02:00
} ,
2016-05-22 22:22:27 +08:00
# Duplicated embedded video URLs
{
' url ' : ' http://www.hudl.com/athlete/2538180/highlights/149298443 ' ,
' info_dict ' : {
' id ' : ' 149298443_480_16c25b74_2 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' vs. Blue Orange Spring Game ' ,
' uploader ' : ' www.hudl.com ' ,
} ,
} ,
2016-07-16 15:59:43 +07:00
# twitter:player:stream embed
{
' url ' : ' http://www.rtl.be/info/video/589263.aspx?CategoryID=288 ' ,
' info_dict ' : {
' id ' : ' master ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Une nouvelle espèce de dinosaure découverte en Argentine ' ,
' uploader ' : ' www.rtl.be ' ,
} ,
' params ' : {
# m3u8 downloads
' skip_download ' : True ,
} ,
} ,
2016-06-30 12:01:30 +01:00
# twitter:player embed
{
' url ' : ' http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/ ' ,
' md5 ' : ' a3e0df96369831de324f0778e126653c ' ,
' info_dict ' : {
' id ' : ' 4909620399001 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' What Do Black Holes Sound Like? ' ,
' description ' : ' what do black holes sound like ' ,
' upload_date ' : ' 20160524 ' ,
' uploader_id ' : ' 29913724001 ' ,
' timestamp ' : 1464107587 ,
' uploader ' : ' TheAtlantic ' ,
} ,
' add_ie ' : [ ' BrightcoveLegacy ' ] ,
2016-07-02 21:33:23 +08:00
} ,
# Facebook <iframe> embed
{
' url ' : ' https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html ' ,
2016-07-02 21:57:06 +08:00
' md5 ' : ' fbcde74f534176ecb015849146dd3aee ' ,
2016-07-02 21:33:23 +08:00
' info_dict ' : {
' id ' : ' 599637780109885 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Facebook video #599637780109885 ' ,
} ,
} ,
2017-06-27 22:36:54 +07:00
# Facebook <iframe> embed, plugin video
{
' url ' : ' http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/ ' ,
' info_dict ' : {
' id ' : ' 1754168231264132 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' About the Imams and Religious leaders refusing to perform funeral prayers for... ' ,
' uploader ' : ' Tariq Ramadan (official) ' ,
' timestamp ' : 1496758379 ,
' upload_date ' : ' 20170606 ' ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
} ,
2016-07-02 21:33:23 +08:00
# Facebook API embed
{
' url ' : ' http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/ ' ,
2016-07-02 21:57:06 +08:00
' md5 ' : ' a47372ee61b39a7b90287094d447d94e ' ,
2016-07-02 21:33:23 +08:00
' info_dict ' : {
' id ' : ' 10153467542406923 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Facebook video #10153467542406923 ' ,
} ,
2016-07-02 21:50:17 +08:00
} ,
# Wordpress "YouTube Video Importer" plugin
{
' url ' : ' http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/ ' ,
2016-07-02 21:57:06 +08:00
' md5 ' : ' d16797741b560b485194eddda8121b48 ' ,
2016-07-02 21:50:17 +08:00
' info_dict ' : {
' id ' : ' HNTXWDXV9Is ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Blue Devils Drumline Stanford lot 2016 ' ,
' upload_date ' : ' 20160627 ' ,
' uploader_id ' : ' GENOCIDE8GENERAL10 ' ,
' uploader ' : ' cylus cyrus ' ,
} ,
} ,
2016-07-04 17:57:44 +01:00
{
# video stored on custom kaltura server
' url ' : ' http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv ' ,
' md5 ' : ' 537617d06e64dfed891fa1593c4b30cc ' ,
' info_dict ' : {
' id ' : ' 0_1iotm5bh ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Elecciones británicas: 5 lecciones para Rajoy ' ,
' description ' : ' md5:435a89d68b9760b92ce67ed227055f16 ' ,
' uploader_id ' : ' videos.expansion@el-mundo.net ' ,
' upload_date ' : ' 20150429 ' ,
' timestamp ' : 1430303472 ,
} ,
' add_ie ' : [ ' Kaltura ' ] ,
} ,
2016-07-09 14:39:01 +08:00
{
# Non-standard Vimeo embed
' url ' : ' https://openclassrooms.com/courses/understanding-the-web ' ,
' md5 ' : ' 64d86f1c7d369afd9a78b38cbb88d80a ' ,
' info_dict ' : {
' id ' : ' 148867247 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Understanding the web - Teaser ' ,
' description ' : ' This is " Understanding the web - Teaser " by openclassrooms on Vimeo, the home for high quality videos and the people who love them. ' ,
' upload_date ' : ' 20151214 ' ,
' uploader ' : ' OpenClassrooms ' ,
' uploader_id ' : ' openclassrooms ' ,
} ,
' add_ie ' : [ ' Vimeo ' ] ,
} ,
2016-09-12 21:49:31 +07:00
{
# generic vimeo embed that requires original URL passed as Referer
' url ' : ' http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/ ' ,
' only_matching ' : True ,
} ,
2016-07-23 17:56:48 +07:00
{
' url ' : ' https://support.arkena.com/display/PLAY/Ways+to+embed+your+video ' ,
' md5 ' : ' b96f2f71b359a8ecd05ce4e1daa72365 ' ,
' info_dict ' : {
' id ' : ' b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Big Buck Bunny ' ,
' description ' : ' Royalty free test video ' ,
' timestamp ' : 1432816365 ,
' upload_date ' : ' 20150528 ' ,
' is_live ' : False ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
' add_ie ' : [ ArkenaIE . ie_key ( ) ] ,
} ,
2016-08-17 01:02:59 +07:00
{
' 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/ ' ,
' info_dict ' : {
' id ' : ' 1c7141f46c ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Н А О Т ' ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
' add_ie ' : [ Vbox7IE . ie_key ( ) ] ,
} ,
2016-08-17 12:45:24 +02:00
{
# DBTV embeds
' url ' : ' http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/ ' ,
2016-08-18 21:35:41 +07:00
' info_dict ' : {
' id ' : ' 43254897 ' ,
' title ' : ' Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans ' ,
} ,
2016-08-17 12:45:24 +02:00
' playlist_mincount ' : 3 ,
} ,
2016-12-31 22:04:29 +07:00
{
# Videa embeds
' url ' : ' http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html ' ,
' info_dict ' : {
' id ' : ' 623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style ' ,
' title ' : ' Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum ' ,
} ,
' playlist_mincount ' : 2 ,
} ,
2017-01-18 22:08:31 +07:00
{
# 20 minuten embed
' url ' : ' http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552 ' ,
' info_dict ' : {
' id ' : ' 523629 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' So kommen Sie bei Eis und Schnee sicher an ' ,
' description ' : ' md5:117c212f64b25e3d95747e5276863f7d ' ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
' add_ie ' : [ TwentyMinutenIE . ie_key ( ) ] ,
2017-02-05 13:37:27 +07:00
} ,
{
# VideoPress embed
' url ' : ' https://en.support.wordpress.com/videopress/ ' ,
' info_dict ' : {
' id ' : ' OcobLTqC ' ,
' ext ' : ' m4v ' ,
' title ' : ' IMG_5786 ' ,
' timestamp ' : 1435711927 ,
' upload_date ' : ' 20150701 ' ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
' add_ie ' : [ VideoPressIE . ie_key ( ) ] ,
2017-02-17 23:13:51 +08:00
} ,
2017-03-04 00:46:33 +07:00
{
# Rutube embed
' url ' : ' http://magazzino.friday.ru/videos/vipuski/kazan-2 ' ,
' info_dict ' : {
' id ' : ' 9b3d5bee0a8740bf70dfd29d3ea43541 ' ,
' ext ' : ' flv ' ,
' title ' : ' Магаззино: Казань 2 ' ,
' description ' : ' md5:99bccdfac2269f0e8fdbc4bbc9db184a ' ,
' uploader ' : ' Магаззино ' ,
' upload_date ' : ' 20170228 ' ,
' uploader_id ' : ' 996642 ' ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
' add_ie ' : [ RutubeIE . ie_key ( ) ] ,
} ,
2017-02-17 23:13:51 +08:00
{
# ThePlatform embedded with whitespaces in URLs
' url ' : ' http://www.golfchannel.com/topics/shows/golftalkcentral.htm ' ,
' only_matching ' : True ,
} ,
2017-03-21 13:12:14 -04:00
{
# Senate ISVP iframe https
' url ' : ' https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security ' ,
' md5 ' : ' fb8c70b0b515e5037981a2492099aab8 ' ,
' info_dict ' : {
' id ' : ' govtaff020316 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Integrated Senate Video Player ' ,
} ,
' add_ie ' : [ SenateISVPIE . ie_key ( ) ] ,
} ,
2017-04-17 00:36:59 +07:00
{
# Limelight embeds (1 channel embed + 4 media embeds)
' url ' : ' http://www.sedona.com/FacilitatorTraining2017 ' ,
' info_dict ' : {
' id ' : ' FacilitatorTraining2017 ' ,
' title ' : ' Facilitator Training 2017 ' ,
} ,
' playlist_mincount ' : 5 ,
} ,
2017-08-13 01:11:27 +07:00
{
# Limelight embed (LimelightPlayerUtil.embed)
' url ' : ' https://tv5.ca/videos?v=xuu8qowr291ri ' ,
' info_dict ' : {
' id ' : ' 95d035dc5c8a401588e9c0e6bd1e9c92 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' 07448641 ' ,
' timestamp ' : 1499890639 ,
' upload_date ' : ' 20170712 ' ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
' add_ie ' : [ ' LimelightMedia ' ] ,
} ,
2017-04-29 19:49:04 +07:00
{
' url ' : ' http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/ ' ,
' info_dict ' : {
' id ' : ' standoff-with-walnut-creek-murder-suspect-ends-with-arrest ' ,
' title ' : ' Standoff with Walnut Creek murder suspect ends ' ,
' description ' : ' md5:3ccc48a60fc9441eeccfc9c469ebf788 ' ,
} ,
' playlist_mincount ' : 4 ,
} ,
2017-04-10 01:09:10 -04:00
{
# WashingtonPost embed
' url ' : ' http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches ' ,
' info_dict ' : {
' id ' : ' 8caf6e88-d0ec-11e5-90d3-34c2c42653ac ' ,
' ext ' : ' mp4 ' ,
' title ' : " No one has seen the drama series based on Trump ' s life \u2014 until now " ,
' 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. ' ,
' timestamp ' : 1455216756 ,
' uploader ' : ' The Washington Post ' ,
' upload_date ' : ' 20160211 ' ,
} ,
' add_ie ' : [ WashingtonPostIE . ie_key ( ) ] ,
} ,
2017-05-14 06:40:19 +07:00
{
# Mediaset embed
' url ' : ' http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml ' ,
' info_dict ' : {
' id ' : ' 720642 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Serracchiani: " Voglio vivere in una società aperta, con tutela del patto di fiducia " ' ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
' add_ie ' : [ MediasetIE . ie_key ( ) ] ,
} ,
2017-07-09 19:05:18 +07:00
{
# JOJ.sk embeds
' url ' : ' https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok ' ,
' info_dict ' : {
' id ' : ' 238543-slovenskom-sa-prehnala-vlna-silnych-burok ' ,
' title ' : ' Slovenskom sa prehnala vlna silných búrok ' ,
} ,
' playlist_mincount ' : 5 ,
' add_ie ' : [ JojIE . ie_key ( ) ] ,
} ,
2017-07-09 16:29:52 +07:00
{
# AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
' url ' : ' https://tvrain.ru/amp/418921/ ' ,
' md5 ' : ' cc00413936695987e8de148b67d14f1d ' ,
' info_dict ' : {
' id ' : ' 418921 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Стас Намин: «Мы нарушили девственность Кремля» ' ,
} ,
} ,
2017-08-11 17:00:39 +02:00
{
# vzaar embed
2017-08-11 22:02:00 +07:00
' url ' : ' http://help.vzaar.com/article/165-embedding-video ' ,
' md5 ' : ' 7e3919d9d2620b89e3e00bec7fe8c9d4 ' ,
2017-08-11 17:00:39 +02:00
' info_dict ' : {
2017-08-11 22:02:00 +07:00
' id ' : ' 8707641 ' ,
2017-08-11 17:00:39 +02:00
' ext ' : ' mp4 ' ,
2017-08-11 22:02:00 +07:00
' title ' : ' Building A Business Online: Principal Chairs Q & A ' ,
2017-08-11 17:00:39 +02:00
} ,
} ,
2017-09-22 22:49:48 +00:00
{
# multiple HTML5 videos on one page
' url ' : ' https://www.paragon-software.com/home/rk-free/keyscenarios.html ' ,
' info_dict ' : {
' id ' : ' keyscenarios ' ,
' title ' : ' Rescue Kit 14 Free Edition - Getting started ' ,
} ,
' playlist_count ' : 4 ,
2017-11-14 16:34:45 +01:00
} ,
{
# vshare embed
' url ' : ' https://youtube-dl-demo.neocities.org/vshare.html ' ,
' md5 ' : ' 17b39f55b5497ae8b59f5fbce8e35886 ' ,
' info_dict ' : {
' id ' : ' 0f64ce6 ' ,
' title ' : ' vl14062007715967 ' ,
' ext ' : ' mp4 ' ,
}
2017-12-30 07:28:18 +07:00
} ,
{
' url ' : ' http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/ ' ,
' md5 ' : ' aecd089f55b1cb5a59032cb049d3a356 ' ,
' info_dict ' : {
' id ' : ' 90227f51a80c4d8f86c345a7fa62bd9a1d ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Lecture: Friday, September 23, 2016 - Sir Tony Hoare ' ,
' description ' : ' md5:5a51db84a62def7b7054df2ade403c6c ' ,
' timestamp ' : 1474354800 ,
' upload_date ' : ' 20160920 ' ,
}
2018-01-20 00:33:45 +07:00
} ,
{
' url ' : ' http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton ' ,
' info_dict ' : {
' id ' : ' 1731611 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Official Trailer | TROLLS: THE BEAT GOES ON! ' ,
' description ' : ' md5:eb5f23826a027ba95277d105f248b825 ' ,
' timestamp ' : 1516100691 ,
' upload_date ' : ' 20180116 ' ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
' add_ie ' : [ SpringboardPlatformIE . ie_key ( ) ] ,
2018-02-15 22:33:11 +07:00
} ,
{
' url ' : ' https://www.youtube.com/shared?ci=1nEzmT-M4fU ' ,
' info_dict ' : {
' id ' : ' uPDB5I9wfp8 ' ,
' ext ' : ' webm ' ,
' title ' : ' Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3 ' ,
' description ' : ' md5:d9e4d9346a2dfff4c7dc4c8cec0f546d ' ,
' upload_date ' : ' 20160219 ' ,
' uploader ' : ' Pocoyo - Português (BR) ' ,
' uploader_id ' : ' PocoyoBrazil ' ,
} ,
' add_ie ' : [ YoutubeIE . ie_key ( ) ] ,
' params ' : {
' skip_download ' : True ,
} ,
2018-03-03 01:24:36 +07:00
} ,
{
' url ' : ' https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html ' ,
' info_dict ' : {
' id ' : ' vMDE4NzI1Mjgt690b ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Котята ' ,
} ,
' add_ie ' : [ YapFilesIE . ie_key ( ) ] ,
' params ' : {
' skip_download ' : True ,
} ,
2018-04-09 00:19:23 +07:00
} ,
2018-05-05 01:21:52 +07:00
{
# CloudflareStream embed
' url ' : ' https://www.cloudflare.com/products/cloudflare-stream/ ' ,
' info_dict ' : {
' id ' : ' 31c9291ab41fac05471db4e73aa11717 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' 31c9291ab41fac05471db4e73aa11717 ' ,
} ,
' add_ie ' : [ CloudflareStreamIE . ie_key ( ) ] ,
' params ' : {
' skip_download ' : True ,
} ,
} ,
2018-05-26 00:28:30 +07:00
{
# PeerTube embed
' url ' : ' https://joinpeertube.org/fr/home/ ' ,
' info_dict ' : {
' id ' : ' home ' ,
' title ' : ' Reprenez le contrôle de vos vidéos ! #JoinPeertube ' ,
} ,
' playlist_count ' : 2 ,
} ,
2018-05-26 01:25:40 +07:00
{
# Indavideo embed
' url ' : ' https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/ ' ,
' info_dict ' : {
' id ' : ' 1693903 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Így kell otthon hamburgert sütni ' ,
' description ' : ' md5:f5a730ecf900a5c852e1e00540bbb0f7 ' ,
' timestamp ' : 1426330212 ,
' upload_date ' : ' 20150314 ' ,
' uploader ' : ' StreetKitchen ' ,
' uploader_id ' : ' 546363 ' ,
} ,
' add_ie ' : [ IndavideoEmbedIE . ie_key ( ) ] ,
' params ' : {
' skip_download ' : True ,
} ,
} ,
2018-05-27 18:24:37 +07:00
{
# APA embed via JWPlatform embed
' url ' : ' http://www.vol.at/blue-man-group/5593454 ' ,
' info_dict ' : {
' id ' : ' jjv85FdZ ' ,
' ext ' : ' mp4 ' ,
' title ' : ' " Blau ist mysteriös " : Die Blue Man Group im Interview ' ,
' description ' : ' md5:d41d8cd98f00b204e9800998ecf8427e ' ,
' thumbnail ' : r ' re:^https?://.* \ .jpg$ ' ,
' duration ' : 254 ,
' timestamp ' : 1519211149 ,
' upload_date ' : ' 20180221 ' ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
} ,
2018-04-09 00:19:23 +07:00
{
' url ' : ' http://share-videos.se/auto/video/83645793?uid=13 ' ,
' md5 ' : ' b68d276de422ab07ee1d49388103f457 ' ,
' info_dict ' : {
' id ' : ' 83645793 ' ,
' title ' : ' Lock up and get excited ' ,
' ext ' : ' mp4 '
2018-04-09 00:25:44 +07:00
} ,
' skip ' : ' TODO: fix nested playlists processing in tests ' ,
} ,
2018-07-30 03:05:36 +07:00
{
# Viqeo embeds
' url ' : ' https://viqeo.tv/ ' ,
' info_dict ' : {
' id ' : ' viqeo ' ,
' title ' : ' All-new video platform ' ,
} ,
' playlist_count ' : 6 ,
} ,
2018-11-11 00:44:49 +07:00
{
# Zype embed
' url ' : ' https://www.cookscountry.com/episode/554-smoky-barbecue-favorites ' ,
' info_dict ' : {
' id ' : ' 5b400b834b32992a310622b9 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Smoky Barbecue Favorites ' ,
' thumbnail ' : r ' re:^https?://.* \ .jpe?g ' ,
} ,
' add_ie ' : [ ZypeIE . ie_key ( ) ] ,
' params ' : {
' skip_download ' : True ,
} ,
} ,
2018-08-24 23:12:53 +07:00
{
# videojs embed
' url ' : ' https://video.sibnet.ru/shell.php?videoid=3422904 ' ,
' info_dict ' : {
' id ' : ' shell ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Доставщик пиццы спросил разрешения сыграть на фортепиано ' ,
' description ' : ' md5:89209cdc587dab1e4a090453dbaa2cb1 ' ,
' thumbnail ' : r ' re:^https?://.* \ .jpg$ ' ,
} ,
' params ' : {
' skip_download ' : True ,
} ,
' expected_warnings ' : [ ' Failed to download MPD manifest ' ] ,
} ,
2019-03-14 16:28:35 +01:00
{
# page with multiple LD-JSON objects
' url ' : ' https://www.antena3.com/noticias/sociedad/grupo-personas-descuelga-pancarta-lazo-amarillo-ayuntamiento-barcelona-video_201903145c8a02c70cf2b779bc2dca9b.html ' ,
' md5 ' : ' 5a9a0d6c788f0a4cee05d2c077b3637c ' ,
' info_dict ' : {
' id ' : ' grupo-personas-descuelga-pancarta-lazo-amarillo-ayuntamiento-barcelona-video_201903145c8a02c70cf2b779bc2dca9b ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Un grupo de personas descuelga una pancarta con un lazo amarillo del Ayuntamiento de Barcelona y operarios la vuelven a colocar ' ,
' timestamp ' : 1552548539 ,
' description ' : ' La retirada de la pancarta con el lazo amarillo en la fachada del Ayuntamiento de Barcelona ha durado poco. Tras su retirada por parte de un grupo de personas esta madrugada un grupo de operarios ha vuelto a colocarla. ' ,
' upload_date ' : ' 20190314 ' ,
} ,
} ,
2016-07-09 08:32:55 +07:00
# {
# # TODO: find another test
# # http://schema.org/VideoObject
# 'url': 'https://flipagram.com/f/nyvTSJMKId',
# 'md5': '888dcf08b7ea671381f00fab74692755',
# 'info_dict': {
# 'id': 'nyvTSJMKId',
# 'ext': 'mp4',
# 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
# 'description': '#love for cats.',
# 'timestamp': 1461244995,
# 'upload_date': '20160421',
# },
# 'params': {
# 'force_generic_extractor': True,
# },
# }
2013-07-10 17:49:11 +02:00
]
2013-06-23 20:31:45 +02:00
def report_following_redirect ( self , new_url ) :
""" Report information extraction. """
2014-01-06 01:47:52 +01:00
self . _downloader . to_screen ( ' [redirect] Following redirect to %s ' % new_url )
2013-06-23 20:31:45 +02:00
2014-02-20 13:14:05 +01:00
def _extract_rss ( self , url , video_id , doc ) :
playlist_title = doc . find ( ' ./channel/title ' ) . text
playlist_desc_el = doc . find ( ' ./channel/description ' )
playlist_desc = None if playlist_desc_el is None else playlist_desc_el . text
2015-03-02 15:21:11 +01:00
entries = [ ]
for it in doc . findall ( ' ./channel/item ' ) :
2018-04-29 17:14:37 +02:00
next_url = None
enclosure_nodes = it . findall ( ' ./enclosure ' )
for e in enclosure_nodes :
next_url = e . attrib . get ( ' url ' )
if next_url :
break
2015-03-02 15:21:11 +01:00
if not next_url :
2018-04-29 17:14:37 +02:00
next_url = xpath_text ( it , ' link ' , fatal = False )
2015-03-02 15:21:11 +01:00
if not next_url :
continue
entries . append ( {
2017-04-16 00:52:15 +07:00
' _type ' : ' url_transparent ' ,
2015-03-02 15:21:11 +01:00
' url ' : next_url ,
' title ' : it . find ( ' title ' ) . text ,
} )
2014-02-20 13:14:05 +01:00
return {
' _type ' : ' playlist ' ,
' id ' : url ,
' title ' : playlist_title ,
' description ' : playlist_desc ,
' entries ' : entries ,
}
2014-08-24 02:02:17 +02:00
def _extract_camtasia ( self , url , video_id , webpage ) :
""" Returns None if no camtasia video can be found. """
camtasia_cfg = self . _search_regex (
r ' fo \ .addVariable \ ( \ s* " csConfigFile " , \ s* " ([^ " ]+) " \ s* \ ); ' ,
webpage , ' camtasia configuration file ' , default = None )
if camtasia_cfg is None :
return None
title = self . _html_search_meta ( ' DC.title ' , webpage , fatal = True )
camtasia_url = compat_urlparse . urljoin ( url , camtasia_cfg )
camtasia_cfg = self . _download_xml (
camtasia_url , video_id ,
note = ' Downloading camtasia configuration ' ,
errnote = ' Failed to download camtasia configuration ' )
fileset_node = camtasia_cfg . find ( ' ./playlist/array/fileset ' )
entries = [ ]
for n in fileset_node . getchildren ( ) :
url_n = n . find ( ' ./uri ' )
if url_n is None :
continue
entries . append ( {
' id ' : os . path . splitext ( url_n . text . rpartition ( ' / ' ) [ 2 ] ) [ 0 ] ,
' title ' : ' %s - %s ' % ( title , n . tag ) ,
' url ' : compat_urlparse . urljoin ( url , url_n . text ) ,
' duration ' : float_or_none ( n . find ( ' ./duration ' ) . text ) ,
} )
return {
' _type ' : ' playlist ' ,
' entries ' : entries ,
' title ' : title ,
}
2013-06-23 20:31:45 +02:00
def _real_extract ( self , url ) :
2014-04-30 01:46:06 +02:00
if url . startswith ( ' // ' ) :
2019-01-01 18:56:05 +02:00
return self . url_result ( self . http_scheme ( ) + url )
2014-04-30 01:46:06 +02:00
2013-09-06 18:39:35 +02:00
parsed_url = compat_urlparse . urlparse ( url )
if not parsed_url . scheme :
2014-01-22 14:16:43 +01:00
default_search = self . _downloader . params . get ( ' default_search ' )
if default_search is None :
2014-07-29 17:17:43 +02:00
default_search = ' fixup_error '
2014-01-22 14:16:43 +01:00
2014-07-29 17:17:43 +02:00
if default_search in ( ' auto ' , ' auto_warning ' , ' fixup_error ' ) :
2014-01-22 14:16:43 +01:00
if ' / ' in url :
self . _downloader . report_warning ( ' The url doesn \' t specify the protocol, trying with http ' )
return self . url_result ( ' http:// ' + url )
2014-07-29 17:17:43 +02:00
elif default_search != ' fixup_error ' :
2014-03-30 15:57:31 +02:00
if default_search == ' auto_warning ' :
2014-05-19 17:10:11 +02:00
if re . match ( r ' ^(?:url|URL)$ ' , url ) :
raise ExtractorError (
' Invalid URL: %r . Call youtube-dl like this: youtube-dl -v " https://www.youtube.com/watch?v=BaW_jenozKc " ' % url ,
expected = True )
else :
self . _downloader . report_warning (
2014-07-06 11:22:44 +02:00
' Falling back to youtube search for %s . Set --default-search " auto " to suppress this warning. ' % url )
2014-01-22 14:16:43 +01:00
return self . url_result ( ' ytsearch: ' + url )
2014-07-29 17:17:43 +02:00
if default_search in ( ' error ' , ' fixup_error ' ) :
2014-07-06 11:22:44 +02:00
raise ExtractorError (
2014-11-23 22:21:46 +01:00
' %r is not a valid URL. '
' Set --default-search " ytsearch " (or run youtube-dl " ytsearch: %s " ) to search YouTube '
% ( url , url ) , expected = True )
2014-01-22 14:16:43 +01:00
else :
2014-10-23 21:13:45 +02:00
if ' : ' not in default_search :
default_search + = ' : '
2014-01-22 14:16:43 +01:00
return self . url_result ( default_search + url )
2014-08-24 04:47:18 +02:00
url , smuggled_data = unsmuggle_url ( url )
force_videoid = None
2014-09-28 12:14:16 +02:00
is_intentional = smuggled_data and smuggled_data . get ( ' to_generic ' )
2014-08-24 04:47:18 +02:00
if smuggled_data and ' force_videoid ' in smuggled_data :
force_videoid = smuggled_data [ ' force_videoid ' ]
video_id = force_videoid
else :
2016-10-07 19:22:30 +08:00
video_id = self . _generic_id ( url )
2016-10-07 17:50:45 +08:00
2014-01-06 01:47:52 +01:00
self . to_screen ( ' %s : Requesting header ' % video_id )
2013-12-27 08:38:42 +01:00
2014-08-24 06:58:11 +02:00
head_req = HEADRequest ( url )
2014-10-26 17:05:44 +01:00
head_response = self . _request_webpage (
2014-08-24 06:58:11 +02:00
head_req , video_id ,
note = False , errnote = ' Could not send HEAD request to %s ' % url ,
fatal = False )
2013-12-17 12:33:55 +01:00
2014-10-26 17:05:44 +01:00
if head_response is not False :
2013-12-17 12:33:55 +01:00
# Check for redirect
2017-08-17 23:57:48 +07:00
new_url = compat_str ( head_response . geturl ( ) )
2013-12-17 12:33:55 +01:00
if url != new_url :
self . report_following_redirect ( new_url )
2014-08-24 04:47:18 +02:00
if force_videoid :
new_url = smuggle_url (
new_url , { ' force_videoid ' : force_videoid } )
2013-12-17 12:04:33 +01:00
return self . url_result ( new_url )
2013-12-17 12:33:55 +01:00
2014-10-26 17:05:44 +01:00
full_response = None
if head_response is False :
2015-11-21 22:18:17 +06:00
request = sanitized_Request ( url )
2015-05-31 00:44:54 +06:00
request . add_header ( ' Accept-Encoding ' , ' * ' )
full_response = self . _request_webpage ( request , video_id )
2014-10-26 17:05:44 +01:00
head_response = full_response
2016-03-13 03:17:25 +06:00
info_dict = {
' id ' : video_id ,
2016-10-07 19:22:30 +08:00
' title ' : self . _generic_title ( url ) ,
2016-03-18 22:41:16 +06:00
' upload_date ' : unified_strdate ( head_response . headers . get ( ' Last-Modified ' ) )
2016-03-13 03:17:25 +06:00
}
2014-10-26 17:05:44 +01:00
# Check for direct link to a video
2016-03-18 21:50:44 +06:00
content_type = head_response . headers . get ( ' Content-Type ' , ' ' ) . lower ( )
2016-03-18 21:50:10 +06:00
m = re . match ( r ' ^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd \ .apple \ .|x-)?mpegurl)))/(?P<format_id>[^; \ s]+) ' , content_type )
2014-10-26 17:05:44 +01:00
if m :
2017-06-10 23:55:05 +07:00
format_id = compat_str ( m . group ( ' format_id ' ) )
2016-03-13 03:17:25 +06:00
if format_id . endswith ( ' mpegurl ' ) :
2016-02-04 01:25:36 +01:00
formats = self . _extract_m3u8_formats ( url , video_id , ' mp4 ' )
2016-03-13 03:17:25 +06:00
elif format_id == ' f4m ' :
formats = self . _extract_f4m_formats ( url , video_id )
2016-02-04 01:25:36 +01:00
else :
formats = [ {
2017-06-10 23:55:05 +07:00
' format_id ' : format_id ,
2016-02-04 01:25:36 +01:00
' url ' : url ,
' vcodec ' : ' none ' if m . group ( ' type ' ) == ' audio ' else None
} ]
2016-03-18 22:43:07 +06:00
info_dict [ ' direct ' ] = True
2016-03-27 07:03:08 +06:00
self . _sort_formats ( formats )
2016-03-18 22:43:07 +06:00
info_dict [ ' formats ' ] = formats
2016-03-13 03:17:25 +06:00
return info_dict
2013-12-17 12:33:55 +01:00
2014-09-28 12:14:16 +02:00
if not self . _downloader . params . get ( ' test ' , False ) and not is_intentional :
2015-06-24 03:08:24 +06:00
force = self . _downloader . params . get ( ' force_generic_extractor ' , False )
self . _downloader . report_warning (
' %s on generic information extractor. ' % ( ' Forcing ' if force else ' Falling back ' ) )
2014-09-28 12:14:16 +02:00
2014-11-26 10:44:39 +01:00
if not full_response :
2015-11-21 22:18:17 +06:00
request = sanitized_Request ( url )
2015-05-31 00:44:54 +06:00
# 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 )
2014-11-26 10:44:39 +01:00
2016-03-18 22:45:28 +06:00
first_bytes = full_response . read ( 512 )
# Is it an M3U playlist?
2016-03-19 05:43:43 +06:00
if first_bytes . startswith ( b ' #EXTM3U ' ) :
2016-03-18 22:45:28 +06:00
info_dict [ ' formats ' ] = self . _extract_m3u8_formats ( url , video_id , ' mp4 ' )
2016-03-27 07:03:08 +06:00
self . _sort_formats ( info_dict [ ' formats ' ] )
2016-03-18 22:45:28 +06:00
return info_dict
2014-11-26 10:44:39 +01:00
# Maybe it's a direct link to a video?
# Be careful not to download the whole thing!
2015-01-23 01:21:30 +01:00
if not is_html ( first_bytes ) :
2014-11-26 10:44:39 +01:00
self . _downloader . report_warning (
' URL could be a direct video link, returning it as such. ' )
2016-03-13 03:17:25 +06:00
info_dict . update ( {
2014-11-26 10:44:39 +01:00
' direct ' : True ,
' url ' : url ,
2016-03-13 03:17:25 +06:00
} )
return info_dict
2014-11-26 10:44:39 +01:00
webpage = self . _webpage_read_content (
full_response , url , video_id , prefix = first_bytes )
2013-06-23 20:31:45 +02:00
self . report_extraction ( video_id )
2013-11-18 13:28:26 +01:00
2016-02-06 19:35:32 +06:00
# Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2014-02-20 13:14:05 +01:00
try :
2015-10-26 16:41:24 +01:00
doc = compat_etree_fromstring ( webpage . encode ( ' utf-8 ' ) )
2014-02-20 13:14:05 +01:00
if doc . tag == ' rss ' :
return self . _extract_rss ( url , video_id , doc )
2016-11-02 03:01:13 +07:00
elif doc . tag == ' SmoothStreamingMedia ' :
info_dict [ ' formats ' ] = self . _parse_ism_formats ( doc , url )
self . _sort_formats ( info_dict [ ' formats ' ] )
return info_dict
2015-08-02 01:13:59 +06:00
elif re . match ( r ' ^(?: { [^}]+})?smil$ ' , doc . tag ) :
2016-03-27 07:03:08 +06:00
smil = self . _parse_smil ( doc , url , video_id )
self . _sort_formats ( smil [ ' formats ' ] )
return smil
2015-08-09 19:43:42 +06:00
elif doc . tag == ' { http://xspf.org/ns/0/}playlist ' :
2018-03-07 21:31:53 +00:00
return self . playlist_result (
2018-03-18 02:46:50 +07:00
self . _parse_xspf (
doc , video_id , xspf_url = url ,
xspf_base_url = compat_str ( full_response . geturl ( ) ) ) ,
2018-03-07 21:31:53 +00:00
video_id )
2016-02-06 19:35:32 +06:00
elif re . match ( r ' (?i)^(?: { [^}]+})?MPD$ ' , doc . tag ) :
2016-03-13 03:17:25 +06:00
info_dict [ ' formats ' ] = self . _parse_mpd_formats (
2017-12-05 23:11:15 +07:00
doc ,
2017-08-17 23:57:48 +07:00
mpd_base_url = compat_str ( full_response . geturl ( ) ) . rpartition ( ' / ' ) [ 0 ] ,
2016-09-17 20:35:22 +07:00
mpd_url = url )
2016-03-27 07:03:08 +06:00
self . _sort_formats ( info_dict [ ' formats ' ] )
2016-03-13 03:17:25 +06:00
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 )
2016-03-27 07:03:08 +06:00
self . _sort_formats ( info_dict [ ' formats ' ] )
2016-03-13 03:17:25 +06:00
return info_dict
2014-02-21 16:59:10 +01:00
except compat_xml_parse_error :
2014-02-20 13:14:05 +01:00
pass
2014-08-24 02:02:17 +02:00
# Is it a Camtasia project?
camtasia_res = self . _extract_camtasia ( url , video_id , webpage )
if camtasia_res is not None :
return camtasia_res
2014-03-15 04:38:49 +07:00
# Sometimes embedded video player is hidden behind percent encoding
2019-03-09 19:14:41 +07:00
# (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2014-03-15 04:38:49 +07:00
# Unescaping the whole page allows to handle those cases in a generic way
2015-07-15 15:30:47 -05:00
webpage = compat_urllib_parse_unquote ( webpage )
2014-02-24 23:44:31 +07:00
2013-11-18 13:28:26 +01:00
# it's tempting to parse this further, but you would
# have to take into account all the variations like
# Video Title - Site Name
# Site Name | Video Title
# Video Title - Tagline | Site Name
# and so on and so forth; it's just not practical
2016-05-14 23:58:25 +06:00
video_title = self . _og_search_title (
webpage , default = None ) or self . _html_search_regex (
2014-01-06 01:47:52 +01:00
r ' (?s)<title>(.*?)</title> ' , webpage , ' video title ' ,
default = ' video ' )
2013-12-06 09:15:04 +01:00
2014-08-24 05:31:32 +02:00
# Try to detect age limit automatically
age_limit = self . _rta_search ( webpage )
# And then there are the jokers who advertise that they use RTA,
# but actually don't.
AGE_LIMIT_MARKERS = [
2017-10-09 23:50:53 +07:00
r ' Proudly Labeled <a href= " http://www \ .rtalabel \ .org/ " title= " Restricted to Adults " >RTA</a> ' ,
2014-08-24 05:31:32 +02:00
]
if any ( re . search ( marker , webpage ) for marker in AGE_LIMIT_MARKERS ) :
age_limit = 18
2013-12-06 09:15:04 +01:00
# video uploader is domain name
video_uploader = self . _search_regex (
2014-01-06 01:47:52 +01:00
r ' ^(?:https?://)?([^/]*)/.* ' , url , ' video uploader ' )
2013-11-18 13:28:26 +01:00
2016-05-14 23:58:25 +06:00
video_description = self . _og_search_description ( webpage , default = None )
video_thumbnail = self . _og_search_thumbnail ( webpage , default = None )
2017-06-30 21:41:05 +07:00
info_dict . update ( {
' title ' : video_title ,
' description ' : video_description ,
' thumbnail ' : video_thumbnail ,
' age_limit ' : age_limit ,
} )
2015-11-14 06:03:32 +06:00
# Look for Brightcove Legacy Studio embeds
2015-11-14 05:54:16 +06:00
bc_urls = BrightcoveLegacyIE . _extract_brightcove_urls ( webpage )
2014-02-03 15:19:40 +01:00
if bc_urls :
entries = [ {
' _type ' : ' url ' ,
' url ' : smuggle_url ( bc_url , { ' Referer ' : url } ) ,
2015-11-14 06:05:46 +06:00
' ie_key ' : ' BrightcoveLegacy '
2014-02-03 15:19:40 +01:00
} for bc_url in bc_urls ]
return {
' _type ' : ' playlist ' ,
' title ' : video_title ,
' id ' : video_id ,
' entries ' : entries ,
}
2013-07-10 17:49:11 +02:00
2015-11-14 06:03:07 +06:00
# Look for Brightcove New Studio embeds
2017-04-15 20:30:51 +07:00
bc_urls = BrightcoveNewIE . _extract_urls ( self , webpage )
2015-11-14 06:03:07 +06:00
if bc_urls :
2018-02-04 07:52:50 +07:00
return self . playlist_from_matches (
bc_urls , video_id , video_title ,
getter = lambda x : smuggle_url ( x , { ' referrer ' : url } ) ,
ie = ' BrightcoveNew ' )
2015-09-11 04:46:21 +01:00
2017-07-15 06:48:12 +07:00
# Look for Nexx embeds
nexx_urls = NexxIE . _extract_urls ( webpage )
if nexx_urls :
return self . playlist_from_matches ( nexx_urls , video_id , video_title , ie = NexxIE . ie_key ( ) )
2017-07-16 04:32:37 +07:00
# Look for Nexx iFrame embeds
nexx_embed_urls = NexxEmbedIE . _extract_urls ( webpage )
if nexx_embed_urls :
return self . playlist_from_matches ( nexx_embed_urls , video_id , video_title , ie = NexxEmbedIE . ie_key ( ) )
2016-05-22 06:52:39 +06:00
# Look for ThePlatform embeds
tp_urls = ThePlatformIE . _extract_urls ( webpage )
if tp_urls :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches ( tp_urls , video_id , video_title , ie = ' ThePlatform ' )
2016-05-22 06:52:39 +06:00
2016-06-09 04:02:27 +07:00
# Look for Vessel embeds
vessel_urls = VesselIE . _extract_urls ( webpage )
if vessel_urls :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches ( vessel_urls , video_id , video_title , ie = VesselIE . ie_key ( ) )
2016-06-09 04:02:27 +07:00
2015-02-16 15:45:01 +01:00
# Look for embedded rtl.nl player
matches = re . findall (
2017-10-12 16:14:43 +00:00
r ' <iframe[^>]+?src= " ((?:https?:)?//(?:(?:www|static) \ .)?rtl \ .nl/(?:system/videoplayer/[^ " ]+(?:video_)?)?embed[^ " ]+) " ' ,
2015-02-16 15:45:01 +01:00
webpage )
if matches :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches ( matches , video_id , video_title , ie = ' RtlNl ' )
2015-02-16 15:45:01 +01:00
2016-10-06 23:22:52 +07:00
vimeo_urls = VimeoIE . _extract_urls ( url , webpage )
if vimeo_urls :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches ( vimeo_urls , video_id , video_title , ie = VimeoIE . ie_key ( ) )
2013-12-22 03:34:13 +01:00
2015-07-20 18:49:53 +08:00
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 ' )
2017-09-06 00:48:37 +07:00
# Look for YouTube embeds
youtube_urls = YoutubeIE . _extract_urls ( webpage )
if youtube_urls :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches (
2017-09-06 00:48:37 +07:00
youtube_urls , video_id , video_title , ie = YoutubeIE . ie_key ( ) )
2016-07-02 21:50:17 +08:00
2016-07-06 23:37:54 +08:00
matches = DailymotionIE . _extract_urls ( webpage )
2013-12-01 01:21:33 +01:00
if matches :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches ( matches , video_id , video_title )
2013-12-01 01:21:33 +01:00
2014-10-02 21:42:45 +03:00
# Look for embedded Dailymotion playlist player (#3822)
m = re . search (
r ' <iframe[^>]+?src=([ " \' ])(?P<url>(?:https?:)?//(?:www \ .)?dailymotion \ .[a-z] { 2,3}/widget/jukebox \ ?.+?) \ 1 ' , webpage )
if m :
playlists = re . findall (
r ' list \ [ \ ]=/playlist/([^/]+)/ ' , unescapeHTML ( m . group ( ' url ' ) ) )
if playlists :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches (
playlists , video_id , video_title , lambda p : ' //dailymotion.com/playlist/ %s ' % p )
2014-10-02 21:42:45 +03:00
2017-07-09 20:06:24 +07:00
# Look for DailyMail embeds
dailymail_urls = DailyMailIE . _extract_urls ( webpage )
if dailymail_urls :
return self . playlist_from_matches (
dailymail_urls , video_id , video_title , ie = DailyMailIE . ie_key ( ) )
2013-12-06 09:15:04 +01:00
# Look for embedded Wistia player
2017-05-13 21:51:58 +07:00
wistia_url = WistiaIE . _extract_url ( webpage )
if wistia_url :
2013-12-06 09:15:04 +01:00
return {
' _type ' : ' url_transparent ' ,
2017-05-13 21:51:58 +07:00
' url ' : self . _proto_relative_url ( wistia_url ) ,
' ie_key ' : WistiaIE . ie_key ( ) ,
2013-12-06 09:15:04 +01:00
' uploader ' : video_uploader ,
}
2014-11-23 20:41:03 +01:00
2015-05-09 00:23:35 +06:00
# Look for SVT player
svt_url = SVTIE . _extract_url ( webpage )
if svt_url :
return self . url_result ( svt_url , ' SVT ' )
2013-10-27 14:40:25 +01:00
# Look for Bandcamp pages with custom domain
mobj = re . search ( r ' <meta property= " og:url " [^>]*?content= " (.*?bandcamp \ .com.*?) " ' , webpage )
if mobj is not None :
burl = unescapeHTML ( mobj . group ( 1 ) )
2013-11-22 16:05:14 +01:00
# Don't set the extractor because it can be a track url or an album
return self . url_result ( burl )
2013-10-27 14:40:25 +01:00
2013-12-16 21:45:21 +01:00
# Look for embedded Vevo player
mobj = re . search (
r ' <iframe[^>]+?src=([ " \' ])(?P<url>(?:https?:)?//(?:cache \ .)?vevo \ .com/.+?) \ 1 ' , webpage )
if mobj is not None :
return self . url_result ( mobj . group ( ' url ' ) )
2015-01-28 00:08:19 -05:00
# Look for embedded Viddler player
2015-01-28 23:07:37 +06:00
mobj = re . search (
r ' <(?:iframe[^>]+?src|param[^>]+?value)=([ " \' ])(?P<url>(?:https?:)?//(?:www \ .)?viddler \ .com/(?:embed|player)/.+?) \ 1 ' ,
webpage )
2015-01-28 00:08:19 -05:00
if mobj is not None :
return self . url_result ( mobj . group ( ' url ' ) )
2013-12-16 21:45:21 +01:00
2015-03-19 21:26:57 +06:00
# 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 ' ) )
2015-03-22 08:18:13 +06:00
# 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 ' ) )
2013-12-19 20:28:52 +01:00
# Look for Ooyala videos
2015-08-08 01:55:59 +06:00
mobj = ( re . search ( r ' player \ .ooyala \ .com/[^ " ?]+[?#][^ " ]*?(?:embedCode|ec)=(?P<ec>[^ " &]+) ' , webpage ) or
2015-02-04 15:33:37 +02:00
re . search ( r ' OO \ .Player \ .create \ ([ \' " ].*?[ \' " ], \ s*[ \' " ](?P<ec>. {32} )[ \' " ] ' , webpage ) or
2017-07-29 20:30:04 +02:00
re . search ( r ' OO \ .Player \ .create \ .apply \ ( \ s*OO \ .Player \ s*, \ s*op \ ( \ s* \ [ \ s*[ \' " ][^ \' " ]*[ \' " ] \ s*, \ s*[ \' " ](?P<ec>. {32} )[ \' " ] ' , webpage ) or
2015-04-14 12:45:43 +08:00
re . search ( r ' SBN \ .VideoLinkset \ .ooyala \ ([ \' " ](?P<ec>. {32} )[ \' " ] \ ) ' , webpage ) or
re . search ( r ' data-ooyala-video-id \ s*= \ s*[ \' " ](?P<ec>. {32} )[ \' " ] ' , webpage ) )
2013-12-19 20:28:52 +01:00
if mobj is not None :
2017-01-13 23:02:50 +01:00
embed_token = self . _search_regex (
r ' embedToken[ \' " ]? \ s*: \ s*[ \' " ]([^ \' " ]+) ' ,
webpage , ' ooyala embed token ' , default = None )
return OoyalaIE . _build_url_result ( smuggle_url (
mobj . group ( ' ec ' ) , {
' domain ' : url ,
' embed_token ' : embed_token ,
} ) )
2013-12-19 20:28:52 +01:00
2015-02-04 15:33:37 +02:00
# Look for multiple Ooyala embeds on SBN network websites
mobj = re . search ( r ' SBN \ .VideoLinkset \ .entryGroup \ (( \ [.*? \ ]) ' , webpage )
if mobj is not None :
embeds = self . _parse_json ( mobj . group ( 1 ) , video_id , fatal = False )
if embeds :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches (
embeds , video_id , video_title ,
getter = lambda v : OoyalaIE . _url_for_embed_code ( smuggle_url ( v [ ' provider_video_id ' ] , { ' domain ' : url } ) ) , ie = ' Ooyala ' )
2015-02-04 15:33:37 +02:00
2013-12-20 17:05:28 +01:00
# Look for Aparat videos
2014-04-21 12:37:41 +02:00
mobj = re . search ( r ' <iframe .*?src= " (http://www \ .aparat \ .com/video/[^ " ]+) " ' , webpage )
2013-12-20 17:05:28 +01:00
if mobj is not None :
return self . url_result ( mobj . group ( 1 ) , ' Aparat ' )
2014-01-07 08:07:46 +01:00
# Look for MPORA videos
2014-01-30 04:26:46 +07:00
mobj = re . search ( r ' <iframe .*?src= " (http://mpora \ .(?:com|de)/videos/[^ " ]+) " ' , webpage )
2014-01-07 08:07:46 +01:00
if mobj is not None :
return self . url_result ( mobj . group ( 1 ) , ' Mpora ' )
2014-01-08 08:11:46 +07:00
2014-04-05 17:20:05 +07:00
# Look for embedded NovaMov-based player
2014-01-08 08:07:11 +07:00
mobj = re . search (
2014-05-17 18:12:12 +07:00
r ''' (?x)<(?:pagespeed_)?iframe[^>]+?src=([ " \ ' ])
2014-04-05 17:20:05 +07:00
( ? P < url > http : / / ( ? : ( ? : embed | www ) \. ) ?
( ? : novamov \. com |
nowvideo \. ( ? : ch | sx | eu | at | ag | co ) |
videoweed \. ( ? : es | com ) |
movshare \. ( ? : net | sx | ag ) |
divxstage \. ( ? : eu | net | ch | co | at | ag ) )
/ embed \. php . + ? ) \1 ''' , webpage)
2014-01-08 08:07:11 +07:00
if mobj is not None :
2014-04-05 17:20:05 +07:00
return self . url_result ( mobj . group ( ' url ' ) )
2014-04-05 15:49:45 +07:00
2014-01-21 18:10:14 +01:00
# Look for embedded Facebook player
2017-06-27 22:25:34 +07:00
facebook_urls = FacebookIE . _extract_urls ( webpage )
if facebook_urls :
return self . playlist_from_matches ( facebook_urls , video_id , video_title )
2014-01-21 18:10:14 +01:00
2014-02-28 23:51:54 +07:00
# Look for embedded VK player
mobj = re . search ( r ' <iframe[^>]+?src=([ " \' ])(?P<url>https?://vk \ .com/video_ext \ .php.+?) \ 1 ' , webpage )
if mobj is not None :
return self . url_result ( mobj . group ( ' url ' ) , ' VK ' )
2016-02-21 09:51:54 +06:00
# 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 ' )
2014-06-29 20:18:23 +07:00
# 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 ' ) , ' Ivi ' )
2014-01-27 05:47:30 +01:00
# Look for embedded Huffington Post player
mobj = re . search (
2014-01-30 04:26:46 +07:00
r ' <iframe[^>]+?src=([ " \' ])(?P<url>https?://embed \ .live \ .huffingtonpost \ .com/.+?) \ 1 ' , webpage )
2014-01-27 05:47:30 +01:00
if mobj is not None :
return self . url_result ( mobj . group ( ' url ' ) , ' HuffPost ' )
2014-02-24 01:15:51 +01:00
# Look for embed.ly
mobj = re . search ( r ' class=[ " \' ]embedly-card[ " \' ][^>]href=[ " \' ](?P<url>[^ " \' ]+) ' , 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 :
2015-07-17 23:39:32 +06:00
return self . url_result ( compat_urllib_parse_unquote ( mobj . group ( ' url ' ) ) )
2014-02-24 01:15:51 +01:00
2014-03-11 16:51:36 +01:00
# Look for funnyordie embed
matches = re . findall ( r ' <iframe[^>]+?src= " (https?://(?:www \ .)?funnyordie \ .com/embed/[^ " ]+) " ' , webpage )
if matches :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches (
matches , video_id , video_title , getter = unescapeHTML , ie = ' FunnyOrDie ' )
2014-03-11 16:51:36 +01:00
2015-01-02 20:46:17 +06:00
# Look for BBC iPlayer embed
matches = re . findall ( r ' setPlaylist \ ( " (https?://www \ .bbc \ .co \ .uk/iplayer/[^/]+/[ \ da-z] {8} ) " \ ) ' , webpage )
if matches :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches ( matches , video_id , video_title , ie = ' BBCCoUk ' )
2015-01-02 20:46:17 +06:00
2014-03-17 02:00:31 +07:00
# Look for embedded RUTV player
rutv_url = RUTVIE . _extract_url ( webpage )
if rutv_url :
return self . url_result ( rutv_url , ' RUTV ' )
2015-06-12 16:22:46 +06:00
# Look for embedded TVC player
2015-06-12 18:15:30 +06:00
tvc_url = TVCIE . _extract_url ( webpage )
if tvc_url :
return self . url_result ( tvc_url , ' TVC ' )
2015-06-12 16:22:46 +06:00
2015-05-15 23:09:34 +06:00
# Look for embedded SportBox player
2018-10-29 00:20:29 +07:00
sportbox_urls = SportBoxIE . _extract_urls ( webpage )
2015-05-15 23:09:34 +06:00
if sportbox_urls :
2018-10-29 00:20:29 +07:00
return self . playlist_from_matches ( sportbox_urls , video_id , video_title , ie = SportBoxIE . ie_key ( ) )
2015-05-15 23:09:34 +06:00
2015-06-21 23:11:25 +06:00
# Look for embedded XHamster player
xhamster_urls = XHamsterEmbedIE . _extract_urls ( webpage )
if xhamster_urls :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches ( xhamster_urls , video_id , video_title , ie = ' XHamsterEmbed ' )
2015-06-21 23:11:25 +06:00
2016-02-27 17:15:49 +06:00
# Look for embedded TNAFlixNetwork player
tnaflix_urls = TNAFlixNetworkEmbedIE . _extract_urls ( webpage )
if tnaflix_urls :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches ( tnaflix_urls , video_id , video_title , ie = TNAFlixNetworkEmbedIE . ie_key ( ) )
2016-02-27 17:15:49 +06:00
2016-11-06 21:52:00 +07:00
# Look for embedded PornHub player
pornhub_urls = PornHubIE . _extract_urls ( webpage )
if pornhub_urls :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches ( pornhub_urls , video_id , video_title , ie = PornHubIE . ie_key ( ) )
2016-11-06 21:52:00 +07:00
2016-11-06 21:33:51 +07:00
# Look for embedded DrTuber player
drtuber_urls = DrTuberIE . _extract_urls ( webpage )
if drtuber_urls :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches ( drtuber_urls , video_id , video_title , ie = DrTuberIE . ie_key ( ) )
2016-11-06 21:33:51 +07:00
2016-11-06 21:42:41 +07:00
# Look for embedded RedTube player
redtube_urls = RedTubeIE . _extract_urls ( webpage )
if redtube_urls :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches ( redtube_urls , video_id , video_title , ie = RedTubeIE . ie_key ( ) )
2016-11-06 21:42:41 +07:00
2018-04-09 00:37:15 +07:00
# Look for embedded Tube8 player
tube8_urls = Tube8IE . _extract_urls ( webpage )
if tube8_urls :
return self . playlist_from_matches ( tube8_urls , video_id , video_title , ie = Tube8IE . ie_key ( ) )
2015-06-12 18:37:09 +06:00
# 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 ' )
2014-03-22 10:20:44 +01:00
# Look for embedded TED player
mobj = re . search (
2015-01-05 18:16:47 +01:00
r ' <iframe[^>]+?src=([ " \' ])(?P<url>https?://embed(?:-ssl)? \ .ted \ .com/.+?) \ 1 ' , webpage )
2014-03-22 10:20:44 +01:00
if mobj is not None :
return self . url_result ( mobj . group ( ' url ' ) , ' TED ' )
2014-04-05 00:53:09 +10:30
# Look for embedded Ustream videos
2017-01-20 21:59:24 +08:00
ustream_url = UstreamIE . _extract_url ( webpage )
if ustream_url :
return self . url_result ( ustream_url , UstreamIE . ie_key ( ) )
2014-04-05 00:53:09 +10:30
2014-03-24 22:01:47 +01:00
# Look for embedded arte.tv player
mobj = re . search (
2016-04-11 19:17:11 +08:00
r ' <(?:script|iframe) [^>]*?src= " (?P<url>http://www \ .arte \ .tv/(?:playerv2/embed|arte_vp/index)[^ " ]+) " ' ,
2014-03-24 22:01:47 +01:00
webpage )
if mobj is not None :
return self . url_result ( mobj . group ( ' url ' ) , ' ArteTVEmbed ' )
2015-07-18 22:56:00 +06:00
# 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 ' ) )
2014-03-28 19:58:49 +07:00
# Look for embedded smotri.com player
smotri_url = SmotriIE . _extract_url ( webpage )
if smotri_url :
return self . url_result ( smotri_url , ' Smotri ' )
2015-07-10 00:25:36 +06:00
# Look for embedded Myvi.ru player
2015-07-10 00:27:44 +06:00
myvi_url = MyviIE . _extract_url ( webpage )
2015-07-10 00:25:36 +06:00
if myvi_url :
return self . url_result ( myvi_url )
2016-01-10 16:17:47 +01:00
# Look for embedded soundcloud player
2016-07-28 22:15:15 +07:00
soundcloud_urls = SoundcloudIE . _extract_urls ( webpage )
if soundcloud_urls :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches ( soundcloud_urls , video_id , video_title , getter = unescapeHTML , ie = SoundcloudIE . ie_key ( ) )
2014-05-05 03:12:41 +02:00
2017-01-03 01:45:59 +07:00
# Look for tunein player
tunein_urls = TuneInBaseIE . _extract_urls ( webpage )
if tunein_urls :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches ( tunein_urls , video_id , video_title )
2017-01-03 01:45:59 +07:00
2014-06-22 21:38:04 +02:00
# Look for embedded mtvservices player
2015-09-26 19:47:20 +06:00
mtvservices_url = MTVServicesEmbeddedIE . _extract_url ( webpage )
if mtvservices_url :
return self . url_result ( mtvservices_url , ie = ' MTVServicesEmbedded ' )
2014-06-22 21:38:04 +02:00
2014-08-16 13:56:22 +07:00
# Look for embedded yahoo player
mobj = re . search (
r ' <iframe[^>]+?src=([ " \' ])(?P<url>https?://(?:screen|movies) \ .yahoo \ .com/.+? \ .html \ ?format=embed) \ 1 ' ,
webpage )
if mobj is not None :
return self . url_result ( mobj . group ( ' url ' ) , ' Yahoo ' )
2014-08-23 15:20:49 +02:00
# Look for embedded sbs.com.au player
mobj = re . search (
2015-02-09 14:46:10 +01:00
r ''' (?x)
( ? :
< meta \s + property = " og:video " \s + content = |
< iframe [ ^ > ] + ? src =
)
( [ " \' ])(?P<url>https?://(?:www \ .)?sbs \ .com \ .au/ondemand/video/.+?) \1 ' ' ' ,
2014-08-23 15:20:49 +02:00
webpage )
if mobj is not None :
return self . url_result ( mobj . group ( ' url ' ) , ' SBS ' )
2014-12-12 02:57:36 +01:00
# 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 ' )
2014-09-02 20:19:28 +07:00
mobj = re . search (
2014-11-01 04:01:58 +07:00
r ' <iframe[^>]+?src=([ " \' ])(?P<url>https?://m(?:lb)? \ .mlb \ .com/shared/video/embed/embed \ .html \ ?.+?) \ 1 ' ,
2014-09-02 20:19:28 +07:00
webpage )
2015-05-04 02:20:07 +08:00
if not mobj :
mobj = re . search (
r ' data-video-link=[ " \' ](?P<url>http://m.mlb.com/video/[^ " \' ]+) ' ,
webpage )
2014-09-02 20:19:28 +07:00
if mobj is not None :
return self . url_result ( mobj . group ( ' url ' ) , ' MLB ' )
2014-10-13 19:59:35 +07:00
mobj = re . search (
2015-09-27 05:55:48 +06:00
r ' <(?:iframe|script)[^>]+?src=([ " \' ])(?P<url> %s ) \ 1 ' % CondeNastIE . EMBED_URL ,
2014-10-13 19:59:35 +07:00
webpage )
if mobj is not None :
return self . url_result ( self . _proto_relative_url ( mobj . group ( ' url ' ) , scheme = ' http: ' ) , ' CondeNast ' )
2014-11-13 16:12:51 +01:00
mobj = re . search (
2016-05-23 01:39:09 +08:00
r ' <iframe[^>]+src= " (?P<url>https?://(?:new \ .)?livestream \ .com/[^ " ]+/player[^ " ]+) " ' ,
2014-11-13 16:12:51 +01:00
webpage )
if mobj is not None :
return self . url_result ( mobj . group ( ' url ' ) , ' Livestream ' )
2015-02-22 01:39:26 +06:00
# 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 ' )
2015-02-27 00:34:19 +02:00
# Look for Kaltura embeds
2016-06-27 22:45:26 +07:00
kaltura_url = KalturaIE . _extract_url ( webpage )
if kaltura_url :
return self . url_result ( smuggle_url ( kaltura_url , { ' source_url ' : url } ) , KalturaIE . ie_key ( ) )
2015-02-27 00:34:19 +02:00
2017-07-09 15:57:33 +07:00
# Look for EaglePlatform embeds
2016-06-29 23:01:34 +07:00
eagleplatform_url = EaglePlatformIE . _extract_url ( webpage )
if eagleplatform_url :
2017-07-09 15:57:33 +07:00
return self . url_result ( smuggle_url ( eagleplatform_url , { ' referrer ' : url } ) , EaglePlatformIE . ie_key ( ) )
2015-03-07 22:22:57 +06:00
2017-07-09 15:57:33 +07:00
# Look for ClipYou (uses EaglePlatform) embeds
2015-03-07 22:34:44 +06:00
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 ' )
2015-03-08 18:07:10 +06:00
# Look for Pladform embeds
2015-12-07 22:03:21 +06:00
pladform_url = PladformIE . _extract_url ( webpage )
if pladform_url :
return self . url_result ( pladform_url )
2015-03-08 18:07:10 +06:00
2015-12-29 23:58:23 +06:00
# Look for Videomore embeds
videomore_url = VideomoreIE . _extract_url ( webpage )
if videomore_url :
return self . url_result ( videomore_url )
2016-11-27 19:56:32 +07:00
# Look for Webcaster embeds
webcaster_url = WebcasterFeedIE . _extract_url ( self , webpage )
if webcaster_url :
return self . url_result ( webcaster_url , ie = WebcasterFeedIE . ie_key ( ) )
2015-04-15 22:10:08 +06:00
# 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 ' ) )
2015-03-29 04:57:37 +03:00
# 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 ' )
2015-04-11 20:20:20 +06:00
# 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 ' ) )
2015-03-31 03:36:09 +08:00
# 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 ' )
2016-06-10 13:32:59 +08:00
# 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 ' )
2015-06-29 08:01:30 +01:00
# Look for Google Drive embeds
2015-12-21 03:05:34 +01:00
google_drive_url = GoogleDriveIE . _extract_url ( webpage )
2015-06-29 08:01:30 +01:00
if google_drive_url :
return self . url_result ( google_drive_url , ' GoogleDrive ' )
2015-04-08 17:26:51 +08:00
# Look for UDN embeds
mobj = re . search (
2017-10-12 16:14:43 +00:00
r ' <iframe[^>]+src= " (?:https?:)?(?P<url> %s ) " ' % UDNEmbedIE . _PROTOCOL_RELATIVE_VALID_URL , webpage )
2015-04-08 17:26:51 +08:00
if mobj is not None :
return self . url_result (
2015-04-08 21:39:34 +08:00
compat_urlparse . urljoin ( url , mobj . group ( ' url ' ) ) , ' UDNEmbed ' )
2015-04-08 17:26:51 +08:00
2015-04-21 03:18:38 +08:00
# Look for Senate ISVP iframe
senate_isvp_url = SenateISVPIE . _search_iframe_url ( webpage )
if senate_isvp_url :
2015-05-15 23:23:51 +06:00
return self . url_result ( senate_isvp_url , ' SenateISVP ' )
2015-04-21 03:18:38 +08:00
2015-06-24 23:19:50 +06:00
# Look for OnionStudios embeds
onionstudios_url = OnionStudiosIE . _extract_url ( webpage )
if onionstudios_url :
return self . url_result ( onionstudios_url )
2016-04-29 11:14:42 +01:00
# Look for ViewLift embeds
viewlift_url = ViewLiftEmbedIE . _extract_url ( webpage )
if viewlift_url :
return self . url_result ( viewlift_url )
2015-06-27 18:26:14 +06:00
2015-12-21 04:24:58 +01:00
# Look for JWPlatform embeds
2018-01-07 21:49:23 +07:00
jwplatform_urls = JWPlatformIE . _extract_urls ( webpage )
if jwplatform_urls :
return self . playlist_from_matches ( jwplatform_urls , video_id , video_title , ie = JWPlatformIE . ie_key ( ) )
2015-12-21 04:24:58 +01:00
2016-01-19 21:51:46 +06:00
# 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 ( ) )
2015-09-25 10:52:48 +01:00
2016-07-23 17:56:48 +07:00
# Look for Arkena embeds
arkena_url = ArkenaIE . _extract_url ( webpage )
if arkena_url :
return self . url_result ( arkena_url , ArkenaIE . ie_key ( ) )
2016-12-20 12:34:46 +01:00
# Look for Piksel embeds
piksel_url = PikselIE . _extract_url ( webpage )
if piksel_url :
return self . url_result ( piksel_url , PikselIE . ie_key ( ) )
2016-01-30 20:45:56 +01:00
# Look for Limelight embeds
2017-04-17 00:23:16 +07:00
limelight_urls = LimelightBaseIE . _extract_urls ( webpage , url )
if limelight_urls :
return self . playlist_result (
limelight_urls , video_id , video_title , video_description )
2017-04-29 19:49:04 +07:00
# Look for Anvato embeds
anvato_urls = AnvatoIE . _extract_urls ( self , webpage , video_id )
if anvato_urls :
return self . playlist_result (
anvato_urls , video_id , video_title , video_description )
2015-06-22 15:02:53 +08:00
# 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 ' )
2016-03-23 23:55:08 +08:00
# 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 ' )
2016-08-04 09:37:27 +01:00
# Look for VODPlatform embeds
mobj = re . search (
2016-08-29 07:56:54 +01:00
r ' <iframe[^>]+src=([ " \' ])(?P<url>(?:https?:)?//(?:www \ .)?vod-platform \ .net/[eE]mbed/.+?) \ 1 ' ,
2016-08-04 09:37:27 +01:00
webpage )
if mobj is not None :
return self . url_result (
2016-08-29 07:56:54 +01:00
self . _proto_relative_url ( unescapeHTML ( mobj . group ( ' url ' ) ) ) , ' VODPlatform ' )
2016-08-04 09:37:27 +01:00
2016-09-16 19:31:39 +01:00
# Look for Mangomolo embeds
mobj = re . search (
2016-09-17 08:11:01 +01:00
r ''' (?x)<iframe[^>]+src=([ " \ ' ])(?P<url>(?:https?:)?//(?:www \ .)?admin \ .mangomolo \ .com/analytics/index \ .php/customers/embed/
2016-09-16 19:31:39 +01:00
( ? :
video \? . * ? \bid = ( ? P < video_id > \d + ) |
index \? . * ? \bchannelid = ( ? P < channel_id > ( ? : [ A - Za - z0 - 9 + / = ] | % 2 B | % 2 F | % 3 D ) + )
) . + ? ) \1 ''' , webpage)
if mobj is not None :
info = {
' _type ' : ' url_transparent ' ,
' url ' : self . _proto_relative_url ( unescapeHTML ( mobj . group ( ' url ' ) ) ) ,
' title ' : video_title ,
' description ' : video_description ,
' thumbnail ' : video_thumbnail ,
' uploader ' : video_uploader ,
}
video_id = mobj . group ( ' video_id ' )
if video_id :
info . update ( {
' ie_key ' : ' MangomoloVideo ' ,
' id ' : video_id ,
} )
else :
info . update ( {
' ie_key ' : ' MangomoloLive ' ,
' id ' : mobj . group ( ' channel_id ' ) ,
} )
return info
2016-03-24 16:32:27 +08:00
# Look for Instagram embeds
instagram_embed_url = InstagramIE . _extract_embed_url ( webpage )
if instagram_embed_url is not None :
2016-04-16 22:39:20 +06:00
return self . url_result (
self . _proto_relative_url ( instagram_embed_url ) , InstagramIE . ie_key ( ) )
2016-03-24 16:32:27 +08:00
2016-03-31 20:42:55 +02:00
# Look for LiveLeak embeds
2017-08-19 22:27:53 +08:00
liveleak_urls = LiveLeakIE . _extract_urls ( webpage )
if liveleak_urls :
return self . playlist_from_matches ( liveleak_urls , video_id , video_title )
2016-03-31 20:42:55 +02:00
2016-05-14 23:40:34 +06:00
# Look for 3Q SDN embeds
threeqsdn_url = ThreeQSDNIE . _extract_url ( webpage )
if threeqsdn_url :
2016-05-14 23:58:25 +06:00
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 ,
}
2016-05-14 23:40:34 +06:00
2016-08-17 01:02:59 +07:00
# Look for VBOX7 embeds
vbox7_url = Vbox7IE . _extract_url ( webpage )
if vbox7_url :
return self . url_result ( vbox7_url , Vbox7IE . ie_key ( ) )
2016-08-17 12:45:24 +02:00
# Look for DBTV embeds
dbtv_urls = DBTVIE . _extract_urls ( webpage )
if dbtv_urls :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches ( dbtv_urls , video_id , video_title , ie = DBTVIE . ie_key ( ) )
2016-08-17 12:45:24 +02:00
2016-12-31 22:04:29 +07:00
# Look for Videa embeds
videa_urls = VideaIE . _extract_urls ( webpage )
if videa_urls :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches ( videa_urls , video_id , video_title , ie = VideaIE . ie_key ( ) )
2016-12-31 22:04:29 +07:00
2017-01-18 22:08:31 +07:00
# Look for 20 minuten embeds
twentymin_urls = TwentyMinutenIE . _extract_urls ( webpage )
if twentymin_urls :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches (
twentymin_urls , video_id , video_title , ie = TwentyMinutenIE . ie_key ( ) )
2017-01-18 22:08:31 +07:00
2017-01-25 23:27:22 +07:00
# Look for Openload embeds
openload_urls = OpenloadIE . _extract_urls ( webpage )
if openload_urls :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches (
openload_urls , video_id , video_title , ie = OpenloadIE . ie_key ( ) )
2017-01-25 23:27:22 +07:00
2017-02-05 13:37:27 +07:00
# Look for VideoPress embeds
videopress_urls = VideoPressIE . _extract_urls ( webpage )
if videopress_urls :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches (
videopress_urls , video_id , video_title , ie = VideoPressIE . ie_key ( ) )
2017-02-05 13:37:27 +07:00
2017-03-04 00:46:33 +07:00
# Look for Rutube embeds
rutube_urls = RutubeIE . _extract_urls ( webpage )
if rutube_urls :
2017-03-08 18:13:54 -05:00
return self . playlist_from_matches (
2017-07-14 17:08:32 +01:00
rutube_urls , video_id , video_title , ie = RutubeIE . ie_key ( ) )
2017-02-05 13:37:27 +07:00
2017-04-10 01:09:10 -04:00
# Look for WashingtonPost embeds
wapo_urls = WashingtonPostIE . _extract_urls ( webpage )
if wapo_urls :
return self . playlist_from_matches (
wapo_urls , video_id , video_title , ie = WashingtonPostIE . ie_key ( ) )
2017-05-14 06:29:16 +07:00
# Look for Mediaset embeds
2018-09-26 05:38:41 +07:00
mediaset_urls = MediasetIE . _extract_urls ( self , webpage )
2017-05-14 06:29:16 +07:00
if mediaset_urls :
return self . playlist_from_matches (
mediaset_urls , video_id , video_title , ie = MediasetIE . ie_key ( ) )
2017-07-09 19:05:18 +07:00
# Look for JOJ.sk embeds
joj_urls = JojIE . _extract_urls ( webpage )
if joj_urls :
return self . playlist_from_matches (
joj_urls , video_id , video_title , ie = JojIE . ie_key ( ) )
2017-07-28 12:13:19 +02:00
# Look for megaphone.fm embeds
mpfn_urls = MegaphoneIE . _extract_urls ( webpage )
if mpfn_urls :
return self . playlist_from_matches (
mpfn_urls , video_id , video_title , ie = MegaphoneIE . ie_key ( ) )
2017-08-11 22:02:00 +07:00
# Look for vzaar embeds
vzaar_urls = VzaarIE . _extract_urls ( webpage )
if vzaar_urls :
return self . playlist_from_matches (
vzaar_urls , video_id , video_title , ie = VzaarIE . ie_key ( ) )
2017-10-11 21:59:30 +07:00
channel9_urls = Channel9IE . _extract_urls ( webpage )
if channel9_urls :
return self . playlist_from_matches (
channel9_urls , video_id , video_title , ie = Channel9IE . ie_key ( ) )
2017-11-14 16:34:45 +01:00
vshare_urls = VShareIE . _extract_urls ( webpage )
if vshare_urls :
return self . playlist_from_matches (
vshare_urls , video_id , video_title , ie = VShareIE . ie_key ( ) )
2016-11-12 21:52:02 +01:00
# Look for Mediasite embeds
2017-12-30 07:28:18 +07:00
mediasite_urls = MediasiteIE . _extract_urls ( webpage )
if mediasite_urls :
entries = [
self . url_result ( smuggle_url (
compat_urlparse . urljoin ( url , mediasite_url ) ,
{ ' UrlReferrer ' : url } ) , ie = MediasiteIE . ie_key ( ) )
for mediasite_url in mediasite_urls ]
return self . playlist_result ( entries , video_id , video_title )
2016-11-12 21:52:02 +01:00
2018-01-20 00:33:45 +07:00
springboardplatform_urls = SpringboardPlatformIE . _extract_urls ( webpage )
if springboardplatform_urls :
return self . playlist_from_matches (
springboardplatform_urls , video_id , video_title ,
ie = SpringboardPlatformIE . ie_key ( ) )
2018-03-03 01:24:36 +07:00
yapfiles_urls = YapFilesIE . _extract_urls ( webpage )
if yapfiles_urls :
return self . playlist_from_matches (
yapfiles_urls , video_id , video_title , ie = YapFilesIE . ie_key ( ) )
2018-03-03 23:07:29 +07:00
vice_urls = ViceIE . _extract_urls ( webpage )
if vice_urls :
return self . playlist_from_matches (
vice_urls , video_id , video_title , ie = ViceIE . ie_key ( ) )
2018-03-17 23:57:07 +07:00
xfileshare_urls = XFileShareIE . _extract_urls ( webpage )
if xfileshare_urls :
return self . playlist_from_matches (
xfileshare_urls , video_id , video_title , ie = XFileShareIE . ie_key ( ) )
2018-05-05 01:21:52 +07:00
cloudflarestream_urls = CloudflareStreamIE . _extract_urls ( webpage )
if cloudflarestream_urls :
return self . playlist_from_matches (
cloudflarestream_urls , video_id , video_title , ie = CloudflareStreamIE . ie_key ( ) )
2018-06-19 23:00:36 +07:00
peertube_urls = PeerTubeIE . _extract_urls ( webpage , url )
2018-05-26 00:28:30 +07:00
if peertube_urls :
return self . playlist_from_matches (
peertube_urls , video_id , video_title , ie = PeerTubeIE . ie_key ( ) )
2018-12-09 22:28:24 +07:00
teachable_url = TeachableIE . _extract_url ( webpage , url )
if teachable_url :
return self . url_result ( teachable_url )
2018-05-26 01:25:40 +07:00
indavideo_urls = IndavideoEmbedIE . _extract_urls ( webpage )
if indavideo_urls :
return self . playlist_from_matches (
indavideo_urls , video_id , video_title , ie = IndavideoEmbedIE . ie_key ( ) )
2018-05-27 18:24:37 +07:00
apa_urls = APAIE . _extract_urls ( webpage )
if apa_urls :
return self . playlist_from_matches (
apa_urls , video_id , video_title , ie = APAIE . ie_key ( ) )
2018-06-20 23:51:14 +07:00
foxnews_urls = FoxNewsIE . _extract_urls ( webpage )
if foxnews_urls :
return self . playlist_from_matches (
foxnews_urls , video_id , video_title , ie = FoxNewsIE . ie_key ( ) )
2018-09-08 17:24:59 +07:00
sharevideos_urls = [ sharevideos_mobj . group ( ' url ' ) for sharevideos_mobj in re . finditer (
2018-04-09 00:25:44 +07:00
r ' <iframe[^>]+? \ bsrc \ s*= \ s*([ " \' ])(?P<url>(?:https?:)?//embed \ .share-videos \ .se/auto/embed/ \ d+ \ ?.*? \ buid= \ d+.*?) \ 1 ' ,
webpage ) ]
if sharevideos_urls :
return self . playlist_from_matches (
sharevideos_urls , video_id , video_title )
2018-07-30 03:05:36 +07:00
viqeo_urls = ViqeoIE . _extract_urls ( webpage )
if viqeo_urls :
return self . playlist_from_matches (
viqeo_urls , video_id , video_title , ie = ViqeoIE . ie_key ( ) )
2018-08-14 22:51:44 +07:00
expressen_urls = ExpressenIE . _extract_urls ( webpage )
if expressen_urls :
return self . playlist_from_matches (
expressen_urls , video_id , video_title , ie = ExpressenIE . ie_key ( ) )
2018-07-30 03:05:36 +07:00
2018-11-11 00:44:49 +07:00
zype_urls = ZypeIE . _extract_urls ( webpage )
if zype_urls :
return self . playlist_from_matches (
zype_urls , video_id , video_title , ie = ZypeIE . ie_key ( ) )
2016-10-02 03:03:41 +08:00
# Look for HTML5 media
entries = self . _parse_html5_media_entries ( url , webpage , video_id , m3u8_id = ' hls ' )
if entries :
2017-09-22 22:49:48 +00:00
if len ( entries ) == 1 :
entries [ 0 ] . update ( {
2016-10-02 03:03:41 +08:00
' id ' : video_id ,
' title ' : video_title ,
} )
2017-09-22 22:49:48 +00:00
else :
for num , entry in enumerate ( entries , start = 1 ) :
entry . update ( {
' id ' : ' %s - %s ' % ( video_id , num ) ,
' title ' : ' %s ( %d ) ' % ( video_title , num ) ,
} )
for entry in entries :
2016-10-02 03:03:41 +08:00
self . _sort_formats ( entry [ ' formats ' ] )
2017-09-22 22:49:48 +00:00
return self . playlist_result ( entries , video_id , video_title )
2016-10-02 03:03:41 +08:00
2017-03-25 19:38:30 +01:00
jwplayer_data = self . _find_jwplayer_data (
webpage , video_id , transform_source = js_to_json )
if jwplayer_data :
2018-06-14 17:12:33 +02:00
try :
info = self . _parse_jwplayer_data (
jwplayer_data , video_id , require_title = False , base_url = url )
return merge_dicts ( info , info_dict )
except ExtractorError :
2019-03-09 19:14:41 +07:00
# See https://github.com/ytdl-org/youtube-dl/pull/16735
2018-06-14 17:12:33 +02:00
pass
2017-02-16 23:42:36 +08:00
2017-09-28 00:29:42 +07:00
# Video.js embed
mobj = re . search (
2017-10-01 07:01:21 +07:00
r ' (?s) \ bvideojs \ s* \ (.+? \ .src \ s* \ ( \ s*((?: \ [.+? \ ]| { .+?})) \ s* \ ) \ s*; ' ,
2017-09-28 00:29:42 +07:00
webpage )
if mobj is not None :
sources = self . _parse_json (
mobj . group ( 1 ) , video_id , transform_source = js_to_json ,
fatal = False ) or [ ]
2017-10-01 07:01:21 +07:00
if not isinstance ( sources , list ) :
sources = [ sources ]
2017-09-28 00:29:42 +07:00
formats = [ ]
for source in sources :
2018-08-24 23:12:53 +07:00
src = source . get ( ' src ' )
if not src or not isinstance ( src , compat_str ) :
2017-09-28 00:29:42 +07:00
continue
src = compat_urlparse . urljoin ( url , src )
src_type = source . get ( ' type ' )
if isinstance ( src_type , compat_str ) :
src_type = src_type . lower ( )
ext = determine_ext ( src ) . lower ( )
if src_type == ' video/youtube ' :
return self . url_result ( src , YoutubeIE . ie_key ( ) )
if src_type == ' application/dash+xml ' or ext == ' mpd ' :
formats . extend ( self . _extract_mpd_formats (
src , video_id , mpd_id = ' dash ' , fatal = False ) )
elif src_type == ' application/x-mpegurl ' or ext == ' m3u8 ' :
formats . extend ( self . _extract_m3u8_formats (
src , video_id , ' mp4 ' , entry_protocol = ' m3u8_native ' ,
m3u8_id = ' hls ' , fatal = False ) )
else :
formats . append ( {
' url ' : src ,
' ext ' : ( mimetype2ext ( src_type ) or
ext if ext in KNOWN_EXTENSIONS else ' mp4 ' ) ,
} )
if formats :
self . _sort_formats ( formats )
info_dict [ ' formats ' ] = formats
return info_dict
2017-08-27 03:27:20 +07:00
# Looking for http://schema.org/VideoObject
json_ld = self . _search_json_ld (
webpage , video_id , default = { } , expected_type = ' VideoObject ' )
if json_ld . get ( ' url ' ) :
return merge_dicts ( json_ld , info_dict )
2014-10-09 19:26:23 +07:00
def check_video ( vurl ) :
2015-02-09 10:42:25 +01:00
if YoutubeIE . suitable ( vurl ) :
return True
2017-02-06 23:23:40 +07:00
if RtmpIE . suitable ( vurl ) :
return True
2014-10-09 19:26:23 +07:00
vpath = compat_urlparse . urlparse ( vurl ) . path
vext = determine_ext ( vpath )
2017-04-12 16:22:08 +01:00
return ' . ' in vpath and vext not in ( ' swf ' , ' png ' , ' jpg ' , ' srt ' , ' sbv ' , ' sub ' , ' vtt ' , ' ttml ' , ' js ' , ' xml ' )
2014-10-09 19:26:23 +07:00
def filter_video ( urls ) :
return list ( filter ( check_video , urls ) )
2013-06-23 20:31:45 +02:00
# Start with something easy: JW Player in SWFObject
2014-10-09 19:26:23 +07:00
found = filter_video ( re . findall ( r ' flashvars: [ \' " ](?:.*&)?file=(http[^ \' " &]*) ' , webpage ) )
2014-04-30 02:23:51 +02:00
if not found :
2014-01-05 05:34:06 +01:00
# Look for gorilla-vid style embedding
2014-10-09 19:26:23 +07:00
found = filter_video ( re . findall ( r ''' (?sx)
2014-04-21 16:16:53 +02:00
( ? :
jw_plugins |
JWPlayerOptions |
jwplayer \s * \( \s * [ " ' ][^ ' " ] + [ " ' ] \ s* \ ) \ s* \ .setup
)
2015-02-09 10:42:25 +01:00
. * ?
[ ' " ]?file[ ' " ]? \ s*: \ s*[ " \' ](.*?)[ " \' ] ' ' ' , webpage ) )
2014-04-30 02:23:51 +02:00
if not found :
2013-06-23 20:31:45 +02:00
# Broaden the search a little bit
2014-10-09 19:26:23 +07:00
found = filter_video ( re . findall ( r ' [^A-Za-z0-9]?(?:file|source)=(http[^ \' " &]*) ' , webpage ) )
2014-04-30 02:23:51 +02:00
if not found :
# Broaden the findall a little bit: JWPlayer JS loader
2014-10-09 19:26:23 +07:00
found = filter_video ( re . findall (
2015-08-05 21:19:52 +06:00
r ' [^A-Za-z0-9]?(?:file|video_url)[ " \' ]?: \ s*[ " \' ](http(?![^ \' " ]+ \ .[0-9]+[ \' " ])[^ \' " ]+)[ " \' ] ' , webpage ) )
2014-08-24 05:31:32 +02:00
if not found :
# Flow player
2014-10-09 19:26:23 +07:00
found = filter_video ( re . findall ( r ''' (?xs)
2014-08-24 05:31:32 +02:00
flowplayer \( " [^ " ] + " , \ s*
\{ [ ^ } ] + ? \} \s * ,
2015-01-30 18:41:40 +11:00
\s * \{ [ ^ } ] + ? [ " ' ]?clip[ " ' ]? \ s*: \ s* \ { \ s*
2014-08-24 05:31:32 +02:00
[ " ' ]?url[ " ' ]? \ s*: \ s*[ " ' ] ( [ ^ " ' ]+)[ " ' ]
2014-10-09 19:26:23 +07:00
''' , webpage))
2015-01-23 12:00:25 +01:00
if not found :
# Cinerama player
found = re . findall (
r " cinerama \ .embedPlayer \ ( \ s* \ ' [^ ' ]+ \ ' , \ s* ' ([^ ' ]+) ' " , webpage )
2014-04-30 02:23:51 +02:00
if not found :
2013-06-23 20:31:45 +02:00
# Try to find twitter cards info
2016-07-16 15:59:43 +07:00
# twitter:player:stream should be checked before twitter:player since
# it is expected to contain a raw stream (see
# https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2014-10-09 19:26:23 +07:00
found = filter_video ( re . findall (
r ' <meta (?:property|name)= " twitter:player:stream " (?:content|value)= " (.+?) " ' , webpage ) )
2014-04-30 02:23:51 +02:00
if not found :
2013-06-23 20:31:45 +02:00
# We look for Open Graph info:
# We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2014-04-30 02:23:51 +02:00
m_video_type = re . findall ( r ' <meta.*?property= " og:video:type " .*?content= " video/(.*?) " ' , webpage )
2013-06-23 20:31:45 +02:00
# We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
if m_video_type is not None :
2014-10-09 19:26:23 +07:00
found = filter_video ( re . findall ( r ' <meta.*?property= " og:video " .*?content= " (.*?) " ' , webpage ) )
2014-04-30 02:23:51 +02:00
if not found :
2015-03-18 00:05:40 +06:00
REDIRECT_REGEX = r ' [0-9] { ,2}; \ s*(?:URL|url)= \' ?([^ \' " ]+) '
2014-05-16 20:32:53 +07:00
found = re . search (
2014-02-27 07:21:59 +01:00
r ' (?i)<meta \ s+(?=(?:[a-z-]+= " [^ " ]+ " \ s+)*http-equiv= " refresh " ) '
2015-03-18 00:05:40 +06:00
r ' (?:[a-z-]+= " [^ " ]+ " \ s+)*?content= " %s ' % REDIRECT_REGEX ,
2014-02-27 07:21:59 +01:00
webpage )
2015-03-17 23:51:40 +06:00
if not found :
# Look also in Refresh HTTP header
refresh_header = head_response . headers . get ( ' Refresh ' )
if refresh_header :
2015-09-20 11:16:12 +06:00
# 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 ' )
2015-03-18 00:05:40 +06:00
found = re . search ( REDIRECT_REGEX , refresh_header )
2014-04-30 02:23:51 +02:00
if found :
2015-07-22 23:33:49 +02:00
new_url = compat_urlparse . urljoin ( url , unescapeHTML ( found . group ( 1 ) ) )
2017-03-24 00:45:24 +07:00
if new_url != url :
self . report_following_redirect ( new_url )
return {
' _type ' : ' url ' ,
' url ' : new_url ,
}
else :
found = None
2016-07-16 15:59:43 +07:00
if not found :
# twitter:player is a https URL to iframe player that may or may not
# be supported by youtube-dl thus this is checked the very last (see
# https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
embed_url = self . _html_search_meta ( ' twitter:player ' , webpage , default = None )
2017-09-26 21:47:18 +07:00
if embed_url and embed_url != url :
2016-07-16 15:59:43 +07:00
return self . url_result ( embed_url )
2014-04-30 02:23:51 +02:00
if not found :
2014-12-30 19:35:35 +01:00
raise UnsupportedError ( url )
2013-06-23 20:31:45 +02:00
2014-04-30 02:23:51 +02:00
entries = [ ]
2016-05-22 22:22:27 +08:00
for video_url in orderedSet ( found ) :
2016-04-24 16:23:21 +08:00
video_url = unescapeHTML ( video_url )
2015-11-21 14:12:34 +08:00
video_url = video_url . replace ( ' \\ / ' , ' / ' )
2014-04-30 02:23:51 +02:00
video_url = compat_urlparse . urljoin ( url , video_url )
2015-07-17 23:39:32 +06:00
video_id = compat_urllib_parse_unquote ( os . path . basename ( video_url ) )
2013-06-23 20:31:45 +02:00
2014-04-30 02:23:51 +02:00
# Sometimes, jwplayer extraction will result in a YouTube URL
if YoutubeIE . suitable ( video_url ) :
entries . append ( self . url_result ( video_url , ' Youtube ' ) )
continue
2013-06-23 20:31:45 +02:00
2014-04-30 02:23:51 +02:00
# here's a fun little line of code for you:
video_id = os . path . splitext ( video_id ) [ 0 ]
2014-01-06 01:42:58 +01:00
2015-11-21 16:08:54 +08:00
entry_info_dict = {
' id ' : video_id ,
' uploader ' : video_uploader ,
' title ' : video_title ,
' age_limit ' : age_limit ,
}
2017-02-06 23:31:58 +07:00
if RtmpIE . suitable ( video_url ) :
entry_info_dict . update ( {
' _type ' : ' url_transparent ' ,
' ie_key ' : RtmpIE . ie_key ( ) ,
' url ' : video_url ,
} )
entries . append ( entry_info_dict )
continue
2015-08-09 19:43:42 +06:00
ext = determine_ext ( video_url )
if ext == ' smil ' :
2015-11-21 16:08:54 +08:00
entry_info_dict [ ' formats ' ] = self . _extract_smil_formats ( video_url , video_id )
2015-08-09 19:43:42 +06:00
elif ext == ' xspf ' :
return self . playlist_result ( self . _extract_xspf_playlist ( video_url , video_id ) , video_id )
2015-11-21 16:43:01 +08:00
elif ext == ' m3u8 ' :
entry_info_dict [ ' formats ' ] = self . _extract_m3u8_formats ( video_url , video_id , ext = ' mp4 ' )
2016-02-06 19:42:03 +06:00
elif ext == ' mpd ' :
entry_info_dict [ ' formats ' ] = self . _extract_mpd_formats ( video_url , video_id )
2016-03-13 03:38:20 +06:00
elif ext == ' f4m ' :
entry_info_dict [ ' formats ' ] = self . _extract_f4m_formats ( video_url , video_id )
2016-11-02 23:43:41 +07:00
elif re . search ( r ' (?i) \ .(?:ism|smil)/manifest ' , video_url ) and video_url != url :
2016-11-02 23:34:37 +07:00
# Just matching .ism/manifest is not enough to be reliably sure
# whether it's actually an ISM manifest or some other streaming
# manifest since there are various streaming URL formats
# possible (see [1]) as well as some other shenanigans like
# .smil/manifest URLs that actually serve an ISM (see [2]) and
# so on.
# Thus the most reasonable way to solve this is to delegate
# to generic extractor in order to look into the contents of
# the manifest itself.
# 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
# 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
entry_info_dict = self . url_result (
smuggle_url ( video_url , { ' to_generic ' : True } ) ,
GenericIE . ie_key ( ) )
2015-04-16 17:16:11 +08:00
else :
2015-11-21 16:08:54 +08:00
entry_info_dict [ ' url ' ] = video_url
2016-03-27 07:03:08 +06:00
if entry_info_dict . get ( ' formats ' ) :
self . _sort_formats ( entry_info_dict [ ' formats ' ] )
2015-11-21 16:08:54 +08:00
entries . append ( entry_info_dict )
2014-04-30 02:23:51 +02:00
if len ( entries ) == 1 :
2014-05-01 16:28:37 +07:00
return entries [ 0 ]
2014-04-30 02:23:51 +02:00
else :
for num , e in enumerate ( entries , start = 1 ) :
2015-02-25 17:56:51 +01:00
# 'url' results don't have a title
if e . get ( ' title ' ) is not None :
e [ ' title ' ] = ' %s ( %d ) ' % ( e [ ' title ' ] , num )
2014-04-30 02:23:51 +02:00
return {
' _type ' : ' playlist ' ,
' entries ' : entries ,
}
