administration/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-17 14:41:44 +00:00
Code Issues Projects Releases Wiki Activity

[cleanup] Mark broken and remove dead extractors (#9238)

Browse Source 
Authored by: seproDev
This commit is contained in:
sepro 2024-03-09 01:02:45 +01:00 committed by GitHub
parent f4f9f6d00e
commit df773c3d5d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
112 changed files with 113 additions and 1692 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
yt_dlp/extractor/_extractors.py
View File

@ -320,7 +320,6 @@ from .cbs import (
CBSIE,
ParamountPressExpressIE,
)
from .cbsinteractive import CBSInteractiveIE
from .cbsnews import (
CBSNewsEmbedIE,
CBSNewsIE,
@ -348,10 +347,6 @@ from .cgtn import CGTNIE
from .charlierose import CharlieRoseIE
from .chaturbate import ChaturbateIE
from .chilloutzone import ChilloutzoneIE
from .chingari import (
ChingariIE,
ChingariUserIE,
)
from .chzzk import (
CHZZKLiveIE,
CHZZKVideoIE,
@ -369,7 +364,6 @@ from .ciscolive import (
from .ciscowebex import CiscoWebexIE
from .cjsw import CJSWIE
from .clipchamp import ClipchampIE
from .cliphunter import CliphunterIE
from .clippit import ClippitIE
from .cliprs import ClipRsIE
from .closertotruth import CloserToTruthIE
@ -476,7 +470,6 @@ from .dlf import (
)
from .dfb import DFBIE
from .dhm import DHMIE
from .digg import DiggIE
from .douyutv import (
DouyuShowIE,
DouyuTVIE,
@ -610,7 +603,6 @@ from .fc2 import (
)
from .fczenit import FczenitIE
from .fifa import FifaIE
from .filmmodu import FilmmoduIE
from .filmon import (
FilmOnIE,
FilmOnChannelIE,
@ -676,7 +668,6 @@ from .gab import (
GabIE,
)
from .gaia import GaiaIE
from .gameinformer import GameInformerIE
from .gamejolt import (
GameJoltIE,
GameJoltUserIE,
@ -705,7 +696,6 @@ from .gettr import (
GettrStreamingIE,
)
from .giantbomb import GiantBombIE
from .giga import GigaIE
from .glide import GlideIE
from .globalplayer import (
GlobalPlayerLiveIE,
@ -896,10 +886,8 @@ from .jtbc import (
from .jwplatform import JWPlatformIE
from .kakao import KakaoIE
from .kaltura import KalturaIE
from .kanal2 import Kanal2IE
from .kankanews import KankaNewsIE
from .karaoketv import KaraoketvIE
from .karrierevideos import KarriereVideosIE
from .kelbyone import KelbyOneIE
from .khanacademy import (
KhanAcademyIE,
@ -915,13 +903,11 @@ from .kinja import KinjaEmbedIE
from .kinopoisk import KinoPoiskIE
from .kommunetv import KommunetvIE
from .kompas import KompasVideoIE
from .konserthusetplay import KonserthusetPlayIE
from .koo import KooIE
from .kth import KTHIE
from .krasview import KrasViewIE
from .ku6 import Ku6IE
from .kukululive import KukuluLiveIE
from .kusi import KUSIIE
from .kuwo import (
KuwoIE,
KuwoAlbumIE,
@ -1003,7 +989,6 @@ from .lnkgo import (
LnkGoIE,
LnkIE,
)
from .localnews8 import LocalNews8IE
from .lovehomeporn import LoveHomePornIE
from .lrt import (
LRTVODIE,
@ -1030,7 +1015,6 @@ from .mailru import (
MailRuMusicSearchIE,
)
from .mainstreaming import MainStreamingIE
from .malltv import MallTVIE
from .mangomolo import (
MangomoloVideoIE,
MangomoloLiveIE,
@ -1074,7 +1058,6 @@ from .meipai import MeipaiIE
from .melonvod import MelonVODIE
from .metacritic import MetacriticIE
from .mgtv import MGTVIE
from .miaopai import MiaoPaiIE
from .microsoftstream import MicrosoftStreamIE
from .microsoftvirtualacademy import (
MicrosoftVirtualAcademyIE,
@ -1092,7 +1075,6 @@ from .minds import (
MindsChannelIE,
MindsGroupIE,
)
from .ministrygrid import MinistryGridIE
from .minoto import MinotoIE
from .mirrativ import (
MirrativIE,
@ -1120,7 +1102,6 @@ from .mlssoccer import MLSSoccerIE
from .mocha import MochaVideoIE
from .mojvideo import MojvideoIE
from .monstercat import MonstercatIE
from .morningstar import MorningstarIE
from .motherless import (
MotherlessIE,
MotherlessGroupIE,
@ -1365,7 +1346,6 @@ from .nuvid import NuvidIE
from .nzherald import NZHeraldIE
from .nzonscreen import NZOnScreenIE
from .nzz import NZZIE
from .odatv import OdaTVIE
from .odkmedia import OnDemandChinaEpisodeIE
from .odnoklassniki import OdnoklassnikiIE
from .oftv import (
@ -1477,7 +1457,6 @@ from .platzi import (
PlatziCourseIE,
)
from .playplustv import PlayPlusTVIE
from .playstuff import PlayStuffIE
from .playsuisse import PlaySuisseIE
from .playtvak import PlaytvakIE
from .playwire import PlaywireIE
@ -1599,7 +1578,6 @@ from .raywenderlich import (
RayWenderlichIE,
RayWenderlichCourseIE,
)
from .rbmaradio import RBMARadioIE
from .rbgtum import (
RbgTumIE,
RbgTumCourseIE,
@ -1631,7 +1609,6 @@ from .redgifs import (
RedGifsUserIE,
)
from .redtube import RedTubeIE
from .regiotv import RegioTVIE
from .rentv import (
RENTVIE,
RENTVArticleIE,
@ -1739,7 +1716,6 @@ from .safari import (
from .saitosan import SaitosanIE
from .samplefocus import SampleFocusIE
from .sapo import SapoIE
from .savefrom import SaveFromIE
from .sbs import SBSIE
from .sbscokr import (
SBSCoKrIE,
@ -1759,7 +1735,6 @@ from .scte import (
SCTECourseIE,
)
from .scrolller import ScrolllerIE
from .seeker import SeekerIE
from .sejmpl import SejmIE
from .senalcolombia import SenalColombiaLiveIE
from .senategov import SenateISVPIE, SenateGovIE
@ -1902,7 +1877,6 @@ from .storyfire import (
)
from .streamable import StreamableIE
from .streamcz import StreamCZIE
from .streamff import StreamFFIE
from .streetvoice import StreetVoiceIE
from .stretchinternet import StretchInternetIE
from .stripchat import StripchatIE
@ -1931,7 +1905,6 @@ from .tbsjp import (
TBSJPProgramIE,
TBSJPPlaylistIE,
)
from .tdslifeway import TDSLifewayIE
from .teachable import (
TeachableIE,
TeachableCourseIE,

2
yt_dlp/extractor/bleacherreport.py
View File

@ -9,6 +9,7 @@ from ..utils import (
class BleacherReportIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/articles/(?P<id>\d+)'
_TESTS = [{
'url': 'http://bleacherreport.com/articles/2496438-fsu-stat-projections-is-jalen-ramsey-best-defensive-player-in-college-football',
@ -83,6 +84,7 @@ class BleacherReportIE(InfoExtractor):
class BleacherReportCMSIE(AMPIE):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36}|\d{5})'
_TESTS = [{
'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1&library=video-cms',

1
yt_dlp/extractor/cbs.py
View File

@ -76,6 +76,7 @@ class CBSBaseIE(ThePlatformFeedIE): # XXX: Do not subclass from concrete IE
class CBSIE(CBSBaseIE):
_WORKING = False
_VALID_URL = r'''(?x)
(?:
cbs:|

98
yt_dlp/extractor/cbsinteractive.py
View File

@ -1,98 +0,0 @@
from .cbs import CBSIE
from ..utils import int_or_none
class CBSInteractiveIE(CBSIE): # XXX: Do not subclass from concrete IE
_VALID_URL = r'https?://(?:www\.)?(?P<site>cnet|zdnet)\.com/(?:videos|video(?:/share)?)/(?P<id>[^/?]+)'
_TESTS = [{
'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
'info_dict': {
'id': 'R49SYt__yAfmlXR85z4f7gNmCBDcN_00',
'display_id': 'hands-on-with-microsofts-windows-8-1-update',
'ext': 'mp4',
'title': 'Hands-on with Microsoft Windows 8.1 Update',
'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861',
'uploader': 'Sarah Mitroff',
'duration': 70,
'timestamp': 1396479627,
'upload_date': '20140402',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/',
'md5': 'f11d27b2fa18597fbf92444d2a9ed386',
'info_dict': {
'id': 'kjOJd_OoVJqbg_ZD8MZCOk8Wekb9QccK',
'display_id': 'whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187',
'ext': 'mp4',
'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)',
'description': 'md5:d2b9a95a5ffe978ae6fbd4cf944d618f',
'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40',
'uploader': 'Ashley Esqueda',
'duration': 1482,
'timestamp': 1433289889,
'upload_date': '20150603',
},
}, {
'url': 'http://www.zdnet.com/video/share/video-keeping-android-smartphones-and-tablets-secure/',
'info_dict': {
'id': 'k0r4T_ehht4xW_hAOqiVQPuBDPZ8SRjt',
'display_id': 'video-keeping-android-smartphones-and-tablets-secure',
'ext': 'mp4',
'title': 'Video: Keeping Android smartphones and tablets secure',
'description': 'Here\'s the best way to keep Android devices secure, and what you do when they\'ve come to the end of their lives.',
'uploader_id': 'f2d97ea2-8175-11e2-9d12-0018fe8a00b0',
'uploader': 'Adrian Kingsley-Hughes',
'duration': 731,
'timestamp': 1449129925,
'upload_date': '20151203',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://www.zdnet.com/video/huawei-matebook-x-video/',
'only_matching': True,
}]
MPX_ACCOUNTS = {
'cnet': 2198311517,
'zdnet': 2387448114,
}
def _real_extract(self, url):
site, display_id = self._match_valid_url(url).groups()
webpage = self._download_webpage(url, display_id)
data_json = self._html_search_regex(
r"data(?:-(?:cnet|zdnet))?-video(?:-(?:uvp(?:js)?|player))?-options='([^']+)'",
webpage, 'data json')
data = self._parse_json(data_json, display_id)
vdata = data.get('video') or (data.get('videos') or data.get('playlist'))[0]
video_id = vdata['mpxRefId']
title = vdata['title']
author = vdata.get('author')
if author:
uploader = '%s %s' % (author['firstName'], author['lastName'])
uploader_id = author.get('id')
else:
uploader = None
uploader_id = None
info = self._extract_video_info(video_id, site, self.MPX_ACCOUNTS[site])
info.update({
'id': video_id,
'display_id': display_id,
'title': title,
'duration': int_or_none(vdata.get('duration')),
'uploader': uploader,
'uploader_id': uploader_id,
})
return info

3
yt_dlp/extractor/cbssports.py
View File

@ -8,6 +8,7 @@ from ..utils import (
# class CBSSportsEmbedIE(CBSBaseIE):
class CBSSportsEmbedIE(InfoExtractor):
_WORKING = False
IE_NAME = 'cbssports:embed'
_VALID_URL = r'''(?ix)https?://(?:(?:www\.)?cbs|embed\.247)sports\.com/player/embed.+?
(?:
@ -75,6 +76,7 @@ class CBSSportsBaseIE(InfoExtractor):
class CBSSportsIE(CBSSportsBaseIE):
_WORKING = False
IE_NAME = 'cbssports'
_VALID_URL = r'https?://(?:www\.)?cbssports\.com/[^/]+/video/(?P<id>[^/?#&]+)'
_TESTS = [{
@ -92,6 +94,7 @@ class CBSSportsIE(CBSSportsBaseIE):
class TwentyFourSevenSportsIE(CBSSportsBaseIE):
_WORKING = False
IE_NAME = '247sports'
_VALID_URL = r'https?://(?:www\.)?247sports\.com/Video/(?:[^/?#&]+-)?(?P<id>\d+)'
_TESTS = [{

199
yt_dlp/extractor/chingari.py
View File

@ -1,199 +0,0 @@
import itertools
import json
import urllib.parse
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
int_or_none,
str_to_int,
url_or_none,
)
class ChingariBaseIE(InfoExtractor):
def _get_post(self, id, post_data):
media_data = post_data['mediaLocation']
base_url = media_data['base']
author_data = post_data.get('authorData', {})
song_data = post_data.get('song', {}) # revist this in future for differentiating b/w 'art' and 'author'
formats = [{
'format_id': frmt,
'width': str_to_int(frmt[1:]),
'url': base_url + frmt_path,
} for frmt, frmt_path in media_data.get('transcoded', {}).items()]
if media_data.get('path'):
formats.append({
'format_id': 'original',
'format_note': 'Direct video.',
'url': base_url + '/apipublic' + media_data['path'],
'quality': 10,
})
timestamp = str_to_int(post_data.get('created_at'))
if timestamp:
timestamp = int_or_none(timestamp, 1000)
thumbnail, uploader_url = None, None
if media_data.get('thumbnail'):
thumbnail = base_url + media_data.get('thumbnail')
if author_data.get('username'):
uploader_url = 'https://chingari.io/' + author_data.get('username')
return {
'id': id,
'extractor_key': ChingariIE.ie_key(),
'extractor': 'Chingari',
'title': urllib.parse.unquote_plus(clean_html(post_data.get('caption'))),
'description': urllib.parse.unquote_plus(clean_html(post_data.get('caption'))),
'duration': media_data.get('duration'),
'thumbnail': url_or_none(thumbnail),
'like_count': post_data.get('likeCount'),
'view_count': post_data.get('viewsCount'),
'comment_count': post_data.get('commentCount'),
'repost_count': post_data.get('shareCount'),
'timestamp': timestamp,
'uploader_id': post_data.get('userId') or author_data.get('_id'),
'uploader': author_data.get('name'),
'uploader_url': url_or_none(uploader_url),
'track': song_data.get('title'),
'artist': song_data.get('author'),
'formats': formats,
}
class ChingariIE(ChingariBaseIE):
_VALID_URL = r'https?://(?:www\.)?chingari\.io/share/post\?id=(?P<id>[^&/#?]+)'
_TESTS = [{
'url': 'https://chingari.io/share/post?id=612f8f4ce1dc57090e8a7beb',
'info_dict': {
'id': '612f8f4ce1dc57090e8a7beb',
'ext': 'mp4',
'title': 'Happy birthday Srila Prabhupada',
'description': 'md5:c7080ebfdfeb06016e638c286d6bc3fa',
'duration': 0,
'thumbnail': 'https://media.chingari.io/uploads/c41d30e2-06b6-4e3b-9b4b-edbb929cec06-1630506826911/thumbnail/198f993f-ce87-4623-82c6-cd071bd6d4f4-1630506828016.jpg',
'like_count': int,
'view_count': int,
'comment_count': int,
'repost_count': int,
'timestamp': 1630506828,
'upload_date': '20210901',
'uploader_id': '5f0403982c8bd344f4813f8c',
'uploader': 'ISKCON,Inc.',
'uploader_url': 'https://chingari.io/iskcon,inc',
},
'params': {'skip_download': True}
}]
def _real_extract(self, url):
id = self._match_id(url)
post_json = self._download_json(f'https://api.chingari.io/post/post_details/{id}', id)
if post_json['code'] != 200:
raise ExtractorError(post_json['message'], expected=True)
post_data = post_json['data']
return self._get_post(id, post_data)
class ChingariUserIE(ChingariBaseIE):
_VALID_URL = r'https?://(?:www\.)?chingari\.io/(?!share/post)(?P<id>[^/?]+)'
_TESTS = [{
'url': 'https://chingari.io/dada1023',
'info_dict': {
'id': 'dada1023',
},
'params': {'playlistend': 3},
'playlist': [{
'url': 'https://chingari.io/share/post?id=614781f3ade60b3a0bfff42a',
'info_dict': {
'id': '614781f3ade60b3a0bfff42a',
'ext': 'mp4',
'title': '#chingaribappa ',
'description': 'md5:d1df21d84088770468fa63afe3b17857',
'duration': 7,
'thumbnail': 'https://media.chingari.io/uploads/346d86d4-abb2-474e-a164-ffccf2bbcb72-1632076273717/thumbnail/b0b3aac2-2b86-4dd1-909d-9ed6e57cf77c-1632076275552.jpg',
'like_count': int,
'view_count': int,
'comment_count': int,
'repost_count': int,
'timestamp': 1632076275,
'upload_date': '20210919',
'uploader_id': '5efc4b12cca35c3d1794c2d3',
'uploader': 'dada (girish) dhawale',
'uploader_url': 'https://chingari.io/dada1023',
},
'params': {'skip_download': True}
}, {
'url': 'https://chingari.io/share/post?id=6146b132bcbf860959e12cba',
'info_dict': {
'id': '6146b132bcbf860959e12cba',
'ext': 'mp4',
'title': 'Tactor harvesting',
'description': 'md5:8403f12dce68828b77ecee7eb7e887b7',
'duration': 59.3,
'thumbnail': 'https://media.chingari.io/uploads/b353ca70-7a87-400d-93a6-fa561afaec86-1632022814584/thumbnail/c09302e3-2043-41b1-a2fe-77d97e5bd676-1632022834260.jpg',
'like_count': int,
'view_count': int,
'comment_count': int,
'repost_count': int,
'timestamp': 1632022834,
'upload_date': '20210919',
'uploader_id': '5efc4b12cca35c3d1794c2d3',
'uploader': 'dada (girish) dhawale',
'uploader_url': 'https://chingari.io/dada1023',
},
'params': {'skip_download': True}
}, {
'url': 'https://chingari.io/share/post?id=6145651b74cb030a64c40b82',
'info_dict': {
'id': '6145651b74cb030a64c40b82',
'ext': 'mp4',
'title': '#odiabhajan ',
'description': 'md5:687ea36835b9276cf2af90f25e7654cb',
'duration': 56.67,
'thumbnail': 'https://media.chingari.io/uploads/6cbf216b-babc-4cce-87fe-ceaac8d706ac-1631937782708/thumbnail/8855754f-6669-48ce-b269-8cc0699ed6da-1631937819522.jpg',
'like_count': int,
'view_count': int,
'comment_count': int,
'repost_count': int,
'timestamp': 1631937819,
'upload_date': '20210918',
'uploader_id': '5efc4b12cca35c3d1794c2d3',
'uploader': 'dada (girish) dhawale',
'uploader_url': 'https://chingari.io/dada1023',
},
'params': {'skip_download': True}
}],
}, {
'url': 'https://chingari.io/iskcon%2Cinc',
'playlist_mincount': 1025,
'info_dict': {
'id': 'iskcon%2Cinc',
},
}]
def _entries(self, id):
skip = 0
has_more = True
for page in itertools.count():
posts = self._download_json('https://api.chingari.io/users/getPosts', id,
data=json.dumps({'userId': id, 'ownerId': id, 'skip': skip, 'limit': 20}).encode(),
headers={'content-type': 'application/json;charset=UTF-8'},
note='Downloading page %s' % page)
for post in posts.get('data', []):
post_data = post['post']
yield self._get_post(post_data['_id'], post_data)
skip += 20
has_more = posts['hasMoreData']
if not has_more:
break
def _real_extract(self, url):
alt_id = self._match_id(url)
post_json = self._download_json(f'https://api.chingari.io/user/{alt_id}', alt_id)
if post_json['code'] != 200:
raise ExtractorError(post_json['message'], expected=True)
id = post_json['data']['_id']
return self.playlist_result(self._entries(id), playlist_id=alt_id)

1
yt_dlp/extractor/cinemax.py
View File

@ -2,6 +2,7 @@ from .hbo import HBOBaseIE
class CinemaxIE(HBOBaseIE):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?cinemax\.com/(?P<path>[^/]+/video/[0-9a-z-]+-(?P<id>\d+))'
_TESTS = [{
'url': 'https://www.cinemax.com/warrior/video/s1-ep-1-recap-20126903',

76
yt_dlp/extractor/cliphunter.py
View File

@ -1,76 +0,0 @@
from .common import InfoExtractor
from ..utils import (
int_or_none,
url_or_none,
)
class CliphunterIE(InfoExtractor):
IE_NAME = 'cliphunter'
_VALID_URL = r'''(?x)https?://(?:www\.)?cliphunter\.com/w/
(?P<id>[0-9]+)/
(?P<seo>.+?)(?:$|[#\?])
'''
_TESTS = [{
'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
'md5': 'b7c9bbd4eb3a226ab91093714dcaa480',
'info_dict': {
'id': '1012420',
'ext': 'flv',
'title': 'Fun Jynx Maze solo',
'thumbnail': r're:^https?://.*\.jpg$',
'age_limit': 18,
},
'skip': 'Video gone',
}, {
'url': 'http://www.cliphunter.com/w/2019449/ShesNew__My_booty_girlfriend_Victoria_Paradices_pussy_filled_with_jizz',
'md5': '55a723c67bfc6da6b0cfa00d55da8a27',
'info_dict': {
'id': '2019449',
'ext': 'mp4',
'title': 'ShesNew - My booty girlfriend, Victoria Paradice\'s pussy filled with jizz',
'thumbnail': r're:^https?://.*\.jpg$',
'age_limit': 18,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_title = self._search_regex(
r'mediaTitle = "([^"]+)"', webpage, 'title')
gexo_files = self._parse_json(
self._search_regex(
r'var\s+gexoFiles\s*=\s*({.+?});', webpage, 'gexo files'),
video_id)
formats = []
for format_id, f in gexo_files.items():
video_url = url_or_none(f.get('url'))
if not video_url:
continue
fmt = f.get('fmt')
height = f.get('h')
format_id = '%s_%sp' % (fmt, height) if fmt and height else format_id
formats.append({
'url': video_url,
'format_id': format_id,
'width': int_or_none(f.get('w')),
'height': int_or_none(height),
'tbr': int_or_none(f.get('br')),
})
thumbnail = self._search_regex(
r"var\s+mov_thumb\s*=\s*'([^']+)';",
webpage, 'thumbnail', fatal=False)
return {
'id': video_id,
'title': video_title,
'formats': formats,
'age_limit': self._rta_search(webpage),
'thumbnail': thumbnail,
}

1
yt_dlp/extractor/cliprs.py
View File

@ -2,6 +2,7 @@ from .onet import OnetBaseIE
class ClipRsIE(OnetBaseIE):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?clip\.rs/(?P<id>[^/]+)/\d+'
_TEST = {
'url': 'http://www.clip.rs/premijera-frajle-predstavljaju-novi-spot-za-pesmu-moli-me-moli/3732',

1
yt_dlp/extractor/closertotruth.py
View File

@ -4,6 +4,7 @@ from .common import InfoExtractor
class CloserToTruthIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?closertotruth\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://closertotruth.com/series/solutions-the-mind-body-problem#video-3688',

54
yt_dlp/extractor/digg.py
View File

@ -1,54 +0,0 @@
from .common import InfoExtractor
from ..utils import js_to_json
class DiggIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?digg\.com/video/(?P<id>[^/?#&]+)'
_TESTS = [{
# JWPlatform via provider
'url': 'http://digg.com/video/sci-fi-short-jonah-daniel-kaluuya-get-out',
'info_dict': {
'id': 'LcqvmS0b',
'ext': 'mp4',
'title': "'Get Out' Star Daniel Kaluuya Goes On 'Moby Dick'-Like Journey In Sci-Fi Short 'Jonah'",
'description': 'md5:541bb847648b6ee3d6514bc84b82efda',
'upload_date': '20180109',
'timestamp': 1515530551,
},
'params': {
'skip_download': True,
},
}, {
# Youtube via provider
'url': 'http://digg.com/video/dog-boat-seal-play',
'only_matching': True,
}, {
# vimeo as regular embed
'url': 'http://digg.com/video/dream-girl-short-film',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
info = self._parse_json(
self._search_regex(
r'(?s)video_info\s*=\s*({.+?});\n', webpage, 'video info',
default='{}'), display_id, transform_source=js_to_json,
fatal=False)
video_id = info.get('video_id')
if video_id:
provider = info.get('provider_name')
if provider == 'youtube':
return self.url_result(
video_id, ie='Youtube', video_id=video_id)
elif provider == 'jwplayer':
return self.url_result(
'jwplatform:%s' % video_id, ie='JWPlatform',
video_id=video_id)
return self.url_result(url, 'Generic')

1
yt_dlp/extractor/dtube.py
View File

@ -9,6 +9,7 @@ from ..utils import (
class DTubeIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?d\.tube/(?:#!/)?v/(?P<uploader_id>[0-9a-z.-]+)/(?P<id>[0-9a-z]{8})'
_TEST = {
'url': 'https://d.tube/#!/v/broncnutz/x380jtr1',

4
yt_dlp/extractor/dw.py
View File

@ -8,6 +8,8 @@ from ..compat import compat_urlparse
class DWIE(InfoExtractor):
_WORKING = False
_ENABLED = None # XXX: pass through to GenericIE
IE_NAME = 'dw'
_VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+(?:av|e)-(?P<id>\d+)'
_TESTS = [{
@ -82,6 +84,8 @@ class DWIE(InfoExtractor):
class DWArticleIE(InfoExtractor):
_WORKING = False
_ENABLED = None # XXX: pass through to GenericIE
IE_NAME = 'dw:article'
_VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+a-(?P<id>\d+)'
_TEST = {

1
yt_dlp/extractor/europa.py
View File

@ -13,6 +13,7 @@ from ..utils import (
class EuropaIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://ec\.europa\.eu/avservices/(?:video/player|audio/audioDetails)\.cfm\?.*?\bref=(?P<id>[A-Za-z0-9-]+)'
_TESTS = [{
'url': 'http://ec.europa.eu/avservices/video/player.cfm?ref=I107758',

2
yt_dlp/extractor/fancode.py
View File

@ -10,6 +10,7 @@ from ..utils import (
class FancodeVodIE(InfoExtractor):
_WORKING = False
IE_NAME = 'fancode:vod'
_VALID_URL = r'https?://(?:www\.)?fancode\.com/video/(?P<id>[0-9]+)\b'
@ -126,6 +127,7 @@ class FancodeVodIE(InfoExtractor):
class FancodeLiveIE(FancodeVodIE): # XXX: Do not subclass from concrete IE
_WORKING = False
IE_NAME = 'fancode:live'
_VALID_URL = r'https?://(www\.)?fancode\.com/match/(?P<id>[0-9]+).+'

69
yt_dlp/extractor/filmmodu.py
View File

@ -1,69 +0,0 @@
from .common import InfoExtractor
from ..utils import int_or_none
class FilmmoduIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?filmmodu\.org/(?P<id>[^/]+-(?:turkce-dublaj-izle|altyazili-izle))'
_TESTS = [{
'url': 'https://www.filmmodu.org/f9-altyazili-izle',
'md5': 'aeefd955c2a508a5bdaa3bcec8eeb0d4',
'info_dict': {
'id': '10804',
'ext': 'mp4',
'title': 'F9',
'description': 'md5:2713f584a4d65afa2611e2948d0b953c',
'subtitles': {
'tr': [{
'ext': 'vtt',
}],
},
'thumbnail': r're:https://s[0-9]+.filmmodu.org/uploads/movie/cover/10804/xXHZeb1yhJvnSHPzZDqee0zfMb6.jpg',
},
}, {
'url': 'https://www.filmmodu.org/the-godfather-turkce-dublaj-izle',
'md5': '109f2fcb9c941330eed133971c035c00',
'info_dict': {
'id': '3646',
'ext': 'mp4',
'title': 'Baba',
'description': 'md5:d43fd651937cd75cc650883ebd8d8461',
'thumbnail': r're:https://s[0-9]+.filmmodu.org/uploads/movie/cover/3646/6xKCYgH16UuwEGAyroLU6p8HLIn.jpg',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._og_search_title(webpage, fatal=True)
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
real_video_id = self._search_regex(r'var\s*videoId\s*=\s*\'([0-9]+)\'', webpage, 'video_id')
video_type = self._search_regex(r'var\s*videoType\s*=\s*\'([a-z]+)\'', webpage, 'video_type')
data = self._download_json('https://www.filmmodu.org/get-source', real_video_id, query={
'movie_id': real_video_id,
'type': video_type,
})
formats = [{
'url': source['src'],
'ext': 'mp4',
'format_id': source['label'],
'height': int_or_none(source.get('res')),
'protocol': 'm3u8_native',
} for source in data['sources']]
subtitles = {}
if data.get('subtitle'):
subtitles['tr'] = [{
'url': data['subtitle'],
}]
return {
'id': real_video_id,
'display_id': video_id,
'title': title,
'description': description,
'formats': formats,
'subtitles': subtitles,
'thumbnail': thumbnail,
}

46
yt_dlp/extractor/gameinformer.py
View File

@ -1,46 +0,0 @@
from .brightcove import BrightcoveNewIE
from .common import InfoExtractor
from ..utils import (
clean_html,
get_element_by_class,
get_element_by_id,
)
class GameInformerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gameinformer\.com/(?:[^/]+/)*(?P<id>[^.?&#]+)'
_TESTS = [{
# normal Brightcove embed code extracted with BrightcoveNewIE._extract_url
'url': 'http://www.gameinformer.com/b/features/archive/2015/09/26/replay-animal-crossing.aspx',
'md5': '292f26da1ab4beb4c9099f1304d2b071',
'info_dict': {
'id': '4515472681001',
'ext': 'mp4',
'title': 'Replay - Animal Crossing',
'description': 'md5:2e211891b215c85d061adc7a4dd2d930',
'timestamp': 1443457610,
'upload_date': '20150928',
'uploader_id': '694940074001',
},
}, {
# Brightcove id inside unique element with field--name-field-brightcove-video-id class
'url': 'https://www.gameinformer.com/video-feature/new-gameplay-today/2019/07/09/new-gameplay-today-streets-of-rogue',
'info_dict': {
'id': '6057111913001',
'ext': 'mp4',
'title': 'New Gameplay Today – Streets Of Rogue',
'timestamp': 1562699001,
'upload_date': '20190709',
'uploader_id': '694940074001',
},
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/694940074001/default_default/index.html?videoId=%s'
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(
url, display_id, headers=self.geo_verification_headers())
brightcove_id = clean_html(get_element_by_class('field--name-field-brightcove-video-id', webpage) or get_element_by_id('video-source-content', webpage))
brightcove_url = self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id if brightcove_id else BrightcoveNewIE._extract_url(self, webpage)
return self.url_result(brightcove_url, 'BrightcoveNew', brightcove_id)

1
yt_dlp/extractor/gazeta.py
View File

@ -2,6 +2,7 @@ from .common import InfoExtractor
class GazetaIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'(?P<url>https?://(?:www\.)?gazeta\.ru/(?:[^/]+/)?video/(?:main/)*(?:\d{4}/\d{2}/\d{2}/)?(?P<id>[A-Za-z0-9-_.]+)\.s?html)'
_TESTS = [{
'url': 'http://www.gazeta.ru/video/main/zadaite_vopros_vladislavu_yurevichu.shtml',

1
yt_dlp/extractor/gdcvault.py
View File

@ -7,6 +7,7 @@ from ..utils import remove_start, smuggle_url, urlencode_postdata
class GDCVaultIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)(?:/(?P<name>[\w-]+))?'
_NETRC_MACHINE = 'gdcvault'
_TESTS = [

93
yt_dlp/extractor/giga.py
View File

@ -1,93 +0,0 @@
import itertools
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import parse_duration, parse_iso8601, qualities, str_to_int
class GigaIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?giga\.de/(?:[^/]+/)*(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://www.giga.de/filme/anime-awesome/trailer/anime-awesome-chihiros-reise-ins-zauberland-das-beste-kommt-zum-schluss/',
'md5': '6bc5535e945e724640664632055a584f',
'info_dict': {
'id': '2622086',
'display_id': 'anime-awesome-chihiros-reise-ins-zauberland-das-beste-kommt-zum-schluss',
'ext': 'mp4',
'title': 'Anime Awesome: Chihiros Reise ins Zauberland – Das Beste kommt zum Schluss',
'description': 'md5:afdf5862241aded4718a30dff6a57baf',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 578,
'timestamp': 1414749706,
'upload_date': '20141031',
'uploader': 'Robin Schweiger',
'view_count': int,
},
}, {
'url': 'http://www.giga.de/games/channel/giga-top-montag/giga-topmontag-die-besten-serien-2014/',
'only_matching': True,
}, {
'url': 'http://www.giga.de/extra/netzkultur/videos/giga-games-tom-mats-robin-werden-eigene-wege-gehen-eine-ankuendigung/',
'only_matching': True,
}, {
'url': 'http://www.giga.de/tv/jonas-liest-spieletitel-eingedeutscht-episode-2/',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
[r'data-video-id="(\d+)"', r'/api/video/jwplayer/#v=(\d+)'],
webpage, 'video id')
playlist = self._download_json(
'http://www.giga.de/api/syndication/video/video_id/%s/playlist.json?content=syndication/key/368b5f151da4ae05ced7fa296bdff65a/'
% video_id, video_id)[0]
quality = qualities(['normal', 'hd720'])
formats = []
for format_id in itertools.count(0):
fmt = playlist.get(compat_str(format_id))
if not fmt:
break
formats.append({
'url': fmt['src'],
'format_id': '%s-%s' % (fmt['quality'], fmt['type'].split('/')[-1]),
'quality': quality(fmt['quality']),
})
title = self._html_search_meta(
'title', webpage, 'title', fatal=True)
description = self._html_search_meta(
'description', webpage, 'description')
thumbnail = self._og_search_thumbnail(webpage)
duration = parse_duration(self._search_regex(
r'(?s)(?:data-video-id="{0}"|data-video="[^"]*/api/video/jwplayer/#v={0}[^"]*")[^>]*>.+?<span class="duration">([^<]+)</span>'.format(video_id),
webpage, 'duration', fatal=False))
timestamp = parse_iso8601(self._search_regex(
r'datetime="([^"]+)"', webpage, 'upload date', fatal=False))
uploader = self._search_regex(
r'class="author">([^<]+)</a>', webpage, 'uploader', fatal=False)
view_count = str_to_int(self._search_regex(
r'<span class="views"><strong>([\d.,]+)</strong>',
webpage, 'view count', fatal=False))
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'timestamp': timestamp,
'uploader': uploader,
'view_count': view_count,
'formats': formats,
}

1
yt_dlp/extractor/godtube.py
View File

@ -6,6 +6,7 @@ from ..utils import (
class GodTubeIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?godtube\.com/watch/\?v=(?P<id>[\da-zA-Z]+)'
_TESTS = [
{

1
yt_dlp/extractor/hotnewhiphop.py
View File

@ -5,6 +5,7 @@ from ..utils import ExtractorError, urlencode_postdata
class HotNewHipHopIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
_TEST = {
'url': 'http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html',

1
yt_dlp/extractor/instagram.py
View File

@ -617,6 +617,7 @@ class InstagramPlaylistBaseIE(InstagramBaseIE):
class InstagramUserIE(InstagramPlaylistBaseIE):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P<id>[^/]{2,})/?(?:$|[?#])'
IE_DESC = 'Instagram user profile'
IE_NAME = 'instagram:user'

2
yt_dlp/extractor/jeuxvideo.py
View File

@ -2,6 +2,8 @@ from .common import InfoExtractor
class JeuxVideoIE(InfoExtractor):
_WORKING = False
_ENABLED = None # XXX: pass through to GenericIE
_VALID_URL = r'https?://.*?\.jeuxvideo\.com/.*/(.*?)\.htm'
_TESTS = [{

66
yt_dlp/extractor/kanal2.py
View File

@ -1,66 +0,0 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
join_nonempty,
traverse_obj,
unified_timestamp,
update_url_query,
)
class Kanal2IE(InfoExtractor):
_VALID_URL = r'https?://kanal2\.postimees\.ee/[^?#]+\?([^#]+&)?id=(?P<id>\d+)'
_TESTS = [{
'note': 'Test standard url (#5575)',
'url': 'https://kanal2.postimees.ee/pluss/video/?id=40792',
'md5': '7ea7b16266ec1798743777df241883dd',
'info_dict': {
'id': '40792',
'ext': 'mp4',
'title': 'Aedniku aabits / Osa 53 (05.08.2016 20:00)',
'thumbnail': r're:https?://.*\.jpg$',
'description': 'md5:53cabf3c5d73150d594747f727431248',
'upload_date': '20160805',
'timestamp': 1470420000,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
playlist = self._download_json(
f'https://kanal2.postimees.ee/player/playlist/{video_id}',
video_id, query={'type': 'episodes'},
headers={'X-Requested-With': 'XMLHttpRequest'})
return {
'id': video_id,
'title': join_nonempty(*traverse_obj(playlist, ('info', ('title', 'subtitle'))), delim=' / '),
'description': traverse_obj(playlist, ('info', 'description')),
'thumbnail': traverse_obj(playlist, ('data', 'image')),
'formats': self.get_formats(playlist, video_id),
'timestamp': unified_timestamp(self._search_regex(
r'\((\d{2}\.\d{2}\.\d{4}\s\d{2}:\d{2})\)$',
traverse_obj(playlist, ('info', 'subtitle')), 'timestamp', default='') + ' +0200'),
}
def get_formats(self, playlist, video_id):
path = traverse_obj(playlist, ('data', 'path'))
if not path:
raise ExtractorError('Path value not found in playlist JSON response')
session = self._download_json(
'https://sts.postimees.ee/session/register',
video_id, note='Creating session', errnote='Error creating session',
headers={
'X-Original-URI': path,
'Accept': 'application/json',
})
if session.get('reason') != 'OK' or not session.get('session'):
reason = session.get('reason', 'unknown error')
raise ExtractorError(f'Unable to obtain session: {reason}')
formats = []
for stream in traverse_obj(playlist, ('data', 'streams', ..., 'file')):
formats.extend(self._extract_m3u8_formats(
update_url_query(stream, {'s': session['session']}), video_id, 'mp4'))
return formats

1
yt_dlp/extractor/kankanews.py
View File

@ -8,6 +8,7 @@ from .common import InfoExtractor
class KankaNewsIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?kankanews\.com/a/\d+\-\d+\-\d+/(?P<id>\d+)\.shtml'
_TESTS = [{
'url': 'https://www.kankanews.com/a/2022-11-08/00310276054.shtml?appid=1088227',

96
yt_dlp/extractor/karrierevideos.py
View File

@ -1,96 +0,0 @@
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
fix_xml_ampersands,
float_or_none,
xpath_with_ns,
xpath_text,
)
class KarriereVideosIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?karrierevideos\.at(?:/[^/]+)+/(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://www.karrierevideos.at/berufsvideos/mittlere-hoehere-schulen/altenpflegerin',
'info_dict': {
'id': '32c91',
'ext': 'flv',
'title': 'AltenpflegerIn',
'description': 'md5:dbadd1259fde2159a9b28667cb664ae2',
'thumbnail': r're:^http://.*\.png',
},
'params': {
# rtmp download
'skip_download': True,
}
}, {
# broken ampersands
'url': 'http://www.karrierevideos.at/orientierung/vaeterkarenz-und-neue-chancen-fuer-muetter-baby-was-nun',
'info_dict': {
'id': '5sniu',
'ext': 'flv',
'title': 'Väterkarenz und neue Chancen für Mütter - "Baby - was nun?"',
'description': 'md5:97092c6ad1fd7d38e9d6a5fdeb2bcc33',
'thumbnail': r're:^http://.*\.png',
},
'params': {
# rtmp download
'skip_download': True,
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = (self._html_search_meta('title', webpage, default=None)
or self._search_regex(r'<h1 class="title">([^<]+)</h1>', webpage, 'video title'))
video_id = self._search_regex(
r'/config/video/(.+?)\.xml', webpage, 'video id')
# Server returns malformed headers
# Force Accept-Encoding: * to prevent gzipped results
playlist = self._download_xml(
'http://www.karrierevideos.at/player-playlist.xml.php?p=%s' % video_id,
video_id, transform_source=fix_xml_ampersands,
headers={'Accept-Encoding': '*'})
NS_MAP = {
'jwplayer': 'http://developer.longtailvideo.com/trac/wiki/FlashFormats'
}
def ns(path):
return xpath_with_ns(path, NS_MAP)
item = playlist.find('./tracklist/item')
video_file = xpath_text(
item, ns('./jwplayer:file'), 'video url', fatal=True)
streamer = xpath_text(
item, ns('./jwplayer:streamer'), 'streamer', fatal=True)
uploader = xpath_text(
item, ns('./jwplayer:author'), 'uploader')
duration = float_or_none(
xpath_text(item, ns('./jwplayer:duration'), 'duration'))
description = self._html_search_regex(
r'(?s)<div class="leadtext">(.+?)</div>',
webpage, 'description')
thumbnail = self._html_search_meta(
'thumbnail', webpage, 'thumbnail')
if thumbnail:
thumbnail = compat_urlparse.urljoin(url, thumbnail)
return {
'id': video_id,
'url': streamer.replace('rtmpt', 'rtmp'),
'play_path': 'mp4:%s' % video_file,
'ext': 'flv',
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'duration': duration,
}

1
yt_dlp/extractor/kelbyone.py
View File

@ -3,6 +3,7 @@ from ..utils import int_or_none
class KelbyOneIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://members\.kelbyone\.com/course/(?P<id>[^$&?#/]+)'
_TESTS = [{

119
yt_dlp/extractor/konserthusetplay.py
View File

@ -1,119 +0,0 @@
from .common import InfoExtractor
from ..utils import (
determine_ext,
float_or_none,
int_or_none,
url_or_none,
)
class KonserthusetPlayIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:konserthusetplay|rspoplay)\.se/\?.*\bm=(?P<id>[^&]+)'
_TESTS = [{
'url': 'http://www.konserthusetplay.se/?m=CKDDnlCY-dhWAAqiMERd-A',
'md5': 'e3fd47bf44e864bd23c08e487abe1967',
'info_dict': {
'id': 'CKDDnlCY-dhWAAqiMERd-A',
'ext': 'mp4',
'title': 'Orkesterns instrument: Valthornen',
'description': 'md5:f10e1f0030202020396a4d712d2fa827',
'thumbnail': 're:^https?://.*$',
'duration': 398.76,
},
}, {
'url': 'http://rspoplay.se/?m=elWuEH34SMKvaO4wO_cHBw',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
e = self._search_regex(
r'https?://csp\.picsearch\.com/rest\?.*\be=(.+?)[&"\']', webpage, 'e')
rest = self._download_json(
'http://csp.picsearch.com/rest?e=%s&containerId=mediaplayer&i=object' % e,
video_id, transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1])
media = rest['media']
player_config = media['playerconfig']
playlist = player_config['playlist']
source = next(f for f in playlist if f.get('bitrates') or f.get('provider'))
FORMAT_ID_REGEX = r'_([^_]+)_h264m\.mp4'
formats = []
m3u8_url = source.get('url')
if m3u8_url and determine_ext(m3u8_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
fallback_url = source.get('fallbackUrl')
fallback_format_id = None
if fallback_url:
fallback_format_id = self._search_regex(
FORMAT_ID_REGEX, fallback_url, 'format id', default=None)
connection_url = (player_config.get('rtmp', {}).get(
'netConnectionUrl') or player_config.get(
'plugins', {}).get('bwcheck', {}).get('netConnectionUrl'))
if connection_url:
for f in source['bitrates']:
video_url = f.get('url')
if not video_url:
continue
format_id = self._search_regex(
FORMAT_ID_REGEX, video_url, 'format id', default=None)
f_common = {
'vbr': int_or_none(f.get('bitrate')),
'width': int_or_none(f.get('width')),
'height': int_or_none(f.get('height')),
}
f = f_common.copy()
f.update({
'url': connection_url,
'play_path': video_url,
'format_id': 'rtmp-%s' % format_id if format_id else 'rtmp',
'ext': 'flv',
})
formats.append(f)
if format_id and format_id == fallback_format_id:
f = f_common.copy()
f.update({
'url': fallback_url,
'format_id': 'http-%s' % format_id if format_id else 'http',
})
formats.append(f)
if not formats and fallback_url:
formats.append({
'url': fallback_url,
})
title = player_config.get('title') or media['title']
description = player_config.get('mediaInfo', {}).get('description')
thumbnail = media.get('image')
duration = float_or_none(media.get('duration'), 1000)
subtitles = {}
captions = source.get('captionsAvailableLanguages')
if isinstance(captions, dict):
for lang, subtitle_url in captions.items():
subtitle_url = url_or_none(subtitle_url)
if lang != 'none' and subtitle_url:
subtitles.setdefault(lang, []).append({'url': subtitle_url})
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
'subtitles': subtitles,
}

1
yt_dlp/extractor/koo.py
View File

@ -6,6 +6,7 @@ from ..utils import (
class KooIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?kooapp\.com/koo/[^/]+/(?P<id>[^/&#$?]+)'
_TESTS = [{ # Test for video in the comments
'url': 'https://www.kooapp.com/koo/ytdlpTestAccount/946c4189-bc2d-4524-b95b-43f641e2adde',

1
yt_dlp/extractor/krasview.py
View File

@ -8,6 +8,7 @@ from ..utils import (
class KrasViewIE(InfoExtractor):
_WORKING = False
IE_DESC = 'Красвью'
_VALID_URL = r'https?://krasview\.ru/(?:video|embed)/(?P<id>\d+)'

83
yt_dlp/extractor/kusi.py
View File

@ -1,83 +0,0 @@
import random
import urllib.parse
from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
timeconvert,
update_url_query,
xpath_text,
)
class KUSIIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?kusi\.com/(?P<path>story/.+|video\?clipId=(?P<clipId>\d+))'
_TESTS = [{
'url': 'http://www.kusi.com/story/32849881/turko-files-refused-to-help-it-aint-right',
'md5': '4e76ce8e53660ce9697d06c0ba6fc47d',
'info_dict': {
'id': '12689020',
'ext': 'mp4',
'title': "Turko Files: Refused to Help, It Ain't Right!",
'duration': 223.586,
'upload_date': '20160826',
'timestamp': 1472233118,
'thumbnail': r're:^https?://.*\.jpg$'
},
}, {
'url': 'http://kusi.com/video?clipId=12203019',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
clip_id = mobj.group('clipId')
video_id = clip_id or mobj.group('path')
webpage = self._download_webpage(url, video_id)
if clip_id is None:
video_id = clip_id = self._html_search_regex(
r'"clipId"\s*,\s*"(\d+)"', webpage, 'clip id')
affiliate_id = self._search_regex(
r'affiliateId\s*:\s*\'([^\']+)\'', webpage, 'affiliate id')
# See __Packages/worldnow/model/GalleryModel.as of WNGallery.swf
xml_url = update_url_query('http://www.kusi.com/build.asp', {
'buildtype': 'buildfeaturexmlrequest',
'featureType': 'Clip',
'featureid': clip_id,
'affiliateno': affiliate_id,
'clientgroupid': '1',
'rnd': int(round(random.random() * 1000000)),
})
doc = self._download_xml(xml_url, video_id)
video_title = xpath_text(doc, 'HEADLINE', fatal=True)
duration = float_or_none(xpath_text(doc, 'DURATION'), scale=1000)
description = xpath_text(doc, 'ABSTRACT')
thumbnail = xpath_text(doc, './THUMBNAILIMAGE/FILENAME')
creation_time = timeconvert(xpath_text(doc, 'rfc822creationdate'))
quality_options = doc.find('{http://search.yahoo.com/mrss/}group').findall('{http://search.yahoo.com/mrss/}content')
formats = []
for quality in quality_options:
formats.append({
'url': urllib.parse.unquote_plus(quality.attrib['url']),
'height': int_or_none(quality.attrib.get('height')),
'width': int_or_none(quality.attrib.get('width')),
'vbr': float_or_none(quality.attrib.get('bitratebits'), scale=1000),
})
return {
'id': video_id,
'title': video_title,
'description': description,
'duration': duration,
'formats': formats,
'thumbnail': thumbnail,
'timestamp': creation_time,
}

6
yt_dlp/extractor/kuwo.py
View File

@ -54,6 +54,7 @@ class KuwoBaseIE(InfoExtractor):
class KuwoIE(KuwoBaseIE):
_WORKING = False
IE_NAME = 'kuwo:song'
IE_DESC = '酷我音乐'
_VALID_URL = r'https?://(?:www\.)?kuwo\.cn/yinyue/(?P<id>\d+)'
@ -133,6 +134,7 @@ class KuwoIE(KuwoBaseIE):
class KuwoAlbumIE(InfoExtractor):
_WORKING = False
IE_NAME = 'kuwo:album'
IE_DESC = '酷我音乐 - 专辑'
_VALID_URL = r'https?://(?:www\.)?kuwo\.cn/album/(?P<id>\d+?)/'
@ -169,6 +171,7 @@ class KuwoAlbumIE(InfoExtractor):
class KuwoChartIE(InfoExtractor):
_WORKING = False
IE_NAME = 'kuwo:chart'
IE_DESC = '酷我音乐 - 排行榜'
_VALID_URL = r'https?://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm'
@ -194,6 +197,7 @@ class KuwoChartIE(InfoExtractor):
class KuwoSingerIE(InfoExtractor):
_WORKING = False
IE_NAME = 'kuwo:singer'
IE_DESC = '酷我音乐 - 歌手'
_VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mingxing/(?P<id>[^/]+)'
@ -251,6 +255,7 @@ class KuwoSingerIE(InfoExtractor):
class KuwoCategoryIE(InfoExtractor):
_WORKING = False
IE_NAME = 'kuwo:category'
IE_DESC = '酷我音乐 - 分类'
_VALID_URL = r'https?://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm'
@ -290,6 +295,7 @@ class KuwoCategoryIE(InfoExtractor):
class KuwoMvIE(KuwoBaseIE):
_WORKING = False
IE_NAME = 'kuwo:mv'
IE_DESC = '酷我音乐 - MV'
_VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mv/(?P<id>\d+?)/'

1
yt_dlp/extractor/lecture2go.py
View File

@ -10,6 +10,7 @@ from ..utils import (
class Lecture2GoIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://lecture2go\.uni-hamburg\.de/veranstaltungen/-/v/(?P<id>\d+)'
_TEST = {
'url': 'https://lecture2go.uni-hamburg.de/veranstaltungen/-/v/17473',

1
yt_dlp/extractor/lenta.py
View File

@ -2,6 +2,7 @@ from .common import InfoExtractor
class LentaIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?lenta\.ru/[^/]+/\d+/\d+/\d+/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://lenta.ru/news/2018/03/22/savshenko_go/',

42
yt_dlp/extractor/localnews8.py
View File

@ -1,42 +0,0 @@
from .common import InfoExtractor
class LocalNews8IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?localnews8\.com/(?:[^/]+/)*(?P<display_id>[^/]+)/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.localnews8.com/news/rexburg-business-turns-carbon-fiber-scraps-into-wedding-rings/35183304',
'md5': 'be4d48aea61aa2bde7be2ee47691ad20',
'info_dict': {
'id': '35183304',
'display_id': 'rexburg-business-turns-carbon-fiber-scraps-into-wedding-rings',
'ext': 'mp4',
'title': 'Rexburg business turns carbon fiber scraps into wedding ring',
'description': 'The process was first invented by Lamborghini and less than a dozen companies around the world use it.',
'duration': 153,
'timestamp': 1441844822,
'upload_date': '20150910',
'uploader_id': 'api',
}
}
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
partner_id = self._search_regex(
r'partnerId\s*[:=]\s*(["\'])(?P<id>\d+)\1',
webpage, 'partner id', group='id')
kaltura_id = self._search_regex(
r'videoIdString\s*[:=]\s*(["\'])kaltura:(?P<id>[0-9a-z_]+)\1',
webpage, 'videl id', group='id')
return {
'_type': 'url_transparent',
'url': 'kaltura:%s:%s' % (partner_id, kaltura_id),
'ie_key': 'Kaltura',
'id': video_id,
'display_id': display_id,
}

107
yt_dlp/extractor/malltv.py
View File

@ -1,107 +0,0 @@
from .common import InfoExtractor
from ..utils import (
clean_html,
dict_get,
float_or_none,
int_or_none,
merge_dicts,
parse_duration,
try_get,
)
class MallTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|sk)\.)?mall\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
'md5': 'cd69ce29176f6533b65bff69ed9a5f2a',
'info_dict': {
'id': 't0zzt0',
'display_id': '18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
'ext': 'mp4',
'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?',
'description': 'md5:db7d5744a4bd4043d9d98324aa72ab35',
'duration': 216,
'timestamp': 1538870400,
'upload_date': '20181007',
'view_count': int,
'comment_count': int,
'thumbnail': 'https://cdn.vpplayer.tech/agmipnzv/encode/vjsnigfq/thumbnails/retina.jpg',
'average_rating': 9.060869565217391,
'dislike_count': int,
'like_count': int,
}
}, {
'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
'only_matching': True,
}, {
'url': 'https://sk.mall.tv/gejmhaus/reklamacia-nehreje-vyrobnik-tepla-alebo-spekacka',
'only_matching': True,
}, {
'url': 'https://www.mall.tv/zivoty-slavnych/nadeje-vychodu-i-zapadu-jak-michail-gorbacov-zmenil-politickou-mapu-sveta-a-ziskal-za-to-nobelovu-cenu-miru',
'info_dict': {
'id': 'yx010y',
'ext': 'mp4',
'dislike_count': int,
'description': 'md5:aee02bee5a8d072c6a8207b91d1905a9',
'thumbnail': 'https://cdn.vpplayer.tech/agmipnzv/encode/vjsnjdeu/thumbnails/retina.jpg',
'comment_count': int,
'display_id': 'md5:0ec2afa94d2e2b7091c019cef2a43a9b',
'like_count': int,
'duration': 752,
'timestamp': 1646956800,
'title': 'md5:fe79385daaf16d74c12c1ec4a26687af',
'view_count': int,
'upload_date': '20220311',
'average_rating': 9.685714285714285,
}
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(
url, display_id, headers=self.geo_verification_headers())
video = self._parse_json(self._search_regex(
r'videoObject\s*=\s*JSON\.parse\(JSON\.stringify\(({.+?})\)\);',
webpage, 'video object'), display_id)
video_id = self._search_regex(
r'<input\s*id\s*=\s*player-id-name\s*[^>]+value\s*=\s*(\w+)', webpage, 'video id')
formats = self._extract_m3u8_formats(
video['VideoSource'], video_id, 'mp4', 'm3u8_native')
subtitles = {}
for s in (video.get('Subtitles') or {}):
s_url = s.get('Url')
if not s_url:
continue
subtitles.setdefault(s.get('Language') or 'cz', []).append({
'url': s_url,
})
entity_counts = video.get('EntityCounts') or {}
def get_count(k):
v = entity_counts.get(k + 's') or {}
return int_or_none(dict_get(v, ('Count', 'StrCount')))
info = self._search_json_ld(webpage, video_id, default={})
return merge_dicts({
'id': str(video_id),
'display_id': display_id,
'title': video.get('Title'),
'description': clean_html(video.get('Description')),
'thumbnail': video.get('ThumbnailUrl'),
'formats': formats,
'subtitles': subtitles,
'duration': int_or_none(video.get('DurationSeconds')) or parse_duration(video.get('Duration')),
'view_count': get_count('View'),
'like_count': get_count('Like'),
'dislike_count': get_count('Dislike'),
'average_rating': float_or_none(try_get(video, lambda x: x['EntityRating']['AvarageRate'])),
'comment_count': get_count('Comment'),
}, info)

1
yt_dlp/extractor/manyvids.py
View File

@ -12,6 +12,7 @@ from ..utils import (
class ManyVidsIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'(?i)https?://(?:www\.)?manyvids\.com/video/(?P<id>\d+)'
_TESTS = [{
# preview video

2
yt_dlp/extractor/markiza.py
View File

@ -10,6 +10,7 @@ from ..utils import (
class MarkizaIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?videoarchiv\.markiza\.sk/(?:video/(?:[^/]+/)*|embed/)(?P<id>\d+)(?:[_/]|$)'
_TESTS = [{
'url': 'http://videoarchiv.markiza.sk/video/oteckovia/84723_oteckovia-109',
@ -68,6 +69,7 @@ class MarkizaIE(InfoExtractor):
class MarkizaPageIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?(?:(?:[^/]+\.)?markiza|tvnoviny)\.sk/(?:[^/]+/)*(?P<id>\d+)_'
_TESTS = [{
'url': 'http://www.markiza.sk/soubiz/zahranicny/1923705_oteckovia-maju-svoj-den-ti-slavni-nie-su-o-nic-menej-rozkosni',

36
yt_dlp/extractor/miaopai.py
View File

@ -1,36 +0,0 @@
from .common import InfoExtractor
class MiaoPaiIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?miaopai\.com/show/(?P<id>[-A-Za-z0-9~_]+)'
_TEST = {
'url': 'http://www.miaopai.com/show/n~0hO7sfV1nBEw4Y29-Hqg__.htm',
'md5': '095ed3f1cd96b821add957bdc29f845b',
'info_dict': {
'id': 'n~0hO7sfV1nBEw4Y29-Hqg__',
'ext': 'mp4',
'title': '西游记音乐会的秒拍视频',
'thumbnail': 're:^https?://.*/n~0hO7sfV1nBEw4Y29-Hqg___m.jpg',
}
}
_USER_AGENT_IPAD = 'Mozilla/5.0 (iPad; CPU OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1'
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
url, video_id, headers={'User-Agent': self._USER_AGENT_IPAD})
title = self._html_extract_title(webpage)
thumbnail = self._html_search_regex(
r'<div[^>]+class=(?P<q1>[\'"]).*\bvideo_img\b.*(?P=q1)[^>]+data-url=(?P<q2>[\'"])(?P<url>[^\'"]+)(?P=q2)',
webpage, 'thumbnail', fatal=False, group='url')
videos = self._parse_html5_media_entries(url, webpage, video_id)
info = videos[0]
info.update({
'id': video_id,
'title': title,
'thumbnail': thumbnail,
})
return info

55
yt_dlp/extractor/ministrygrid.py
View File

@ -1,55 +0,0 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
smuggle_url,
)
class MinistryGridIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ministrygrid\.com/([^/?#]*/)*(?P<id>[^/#?]+)/?(?:$|[?#])'
_TEST = {
'url': 'http://www.ministrygrid.com/training-viewer/-/training/t4g-2014-conference/the-gospel-by-numbers-4/the-gospel-by-numbers',
'md5': '844be0d2a1340422759c2a9101bab017',
'info_dict': {
'id': '3453494717001',
'ext': 'mp4',
'title': 'The Gospel by Numbers',
'thumbnail': r're:^https?://.*\.jpg',
'upload_date': '20140410',
'description': 'Coming soon from T4G 2014!',
'uploader_id': '2034960640001',
'timestamp': 1397145591,
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['TDSLifeway'],
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
portlets = self._parse_json(self._search_regex(
r'Liferay\.Portlet\.list=(\[.+?\])', webpage, 'portlet list'),
video_id)
pl_id = self._search_regex(
r'getPlid:function\(\){return"(\d+)"}', webpage, 'p_l_id')
for i, portlet in enumerate(portlets):
portlet_url = 'http://www.ministrygrid.com/c/portal/render_portlet?p_l_id=%s&p_p_id=%s' % (pl_id, portlet)
portlet_code = self._download_webpage(
portlet_url, video_id,
note='Looking in portlet %s (%d/%d)' % (portlet, i + 1, len(portlets)),
fatal=False)
video_iframe_url = self._search_regex(
r'<iframe.*?src="([^"]+)"', portlet_code, 'video iframe',
default=None)
if video_iframe_url:
return self.url_result(
smuggle_url(video_iframe_url, {'force_videoid': video_id}),
video_id=video_id)
raise ExtractorError('Could not find video iframe in any portlets')

45
yt_dlp/extractor/morningstar.py
View File

@ -1,45 +0,0 @@
from .common import InfoExtractor
class MorningstarIE(InfoExtractor):
IE_DESC = 'morningstar.com'
_VALID_URL = r'https?://(?:(?:www|news)\.)morningstar\.com/[cC]over/video[cC]enter\.aspx\?id=(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://www.morningstar.com/cover/videocenter.aspx?id=615869',
'md5': '6c0acface7a787aadc8391e4bbf7b0f5',
'info_dict': {
'id': '615869',
'ext': 'mp4',
'title': 'Get Ahead of the Curve on 2013 Taxes',
'description': "Vanguard's Joel Dickson on managing higher tax rates for high-income earners and fund capital-gain distributions in 2013.",
'thumbnail': r're:^https?://.*m(?:orning)?star\.com/.+thumb\.jpg$'
}
}, {
'url': 'http://news.morningstar.com/cover/videocenter.aspx?id=825556',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'<h1 id="titleLink">(.*?)</h1>', webpage, 'title')
video_url = self._html_search_regex(
r'<input type="hidden" id="hidVideoUrl" value="([^"]+)"',
webpage, 'video URL')
thumbnail = self._html_search_regex(
r'<input type="hidden" id="hidSnapshot" value="([^"]+)"',
webpage, 'thumbnail', fatal=False)
description = self._html_search_regex(
r'<div id="mstarDeck".*?>(.*?)</div>',
webpage, 'description', fatal=False)
return {
'id': video_id,
'title': title,
'url': video_url,
'thumbnail': thumbnail,
'description': description,
}

1
yt_dlp/extractor/motorsport.py
View File

@ -5,6 +5,7 @@ from ..compat import (
class MotorsportIE(InfoExtractor):
_WORKING = False
IE_DESC = 'motorsport.com'
_VALID_URL = r'https?://(?:www\.)?motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/?(?:$|[?#])'
_TEST = {

1
yt_dlp/extractor/mtv.py
View File

@ -451,6 +451,7 @@ class MTVVideoIE(MTVServicesInfoExtractor):
class MTVDEIE(MTVServicesInfoExtractor):
_WORKING = False
IE_NAME = 'mtv.de'
_VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:musik/videoclips|folgen|news)/(?P<id>[0-9a-z]+)'
_TESTS = [{

1
yt_dlp/extractor/muenchentv.py
View File

@ -9,6 +9,7 @@ from ..utils import (
class MuenchenTVIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?muenchen\.tv/livestream'
IE_DESC = 'münchen.tv'
_TEST = {

2
yt_dlp/extractor/murrtube.py
View File

@ -12,6 +12,7 @@ from ..utils import (
class MurrtubeIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'''(?x)
(?:
murrtube:|
@ -100,6 +101,7 @@ query Medium($id: ID!) {
class MurrtubeUserIE(MurrtubeIE): # XXX: Do not subclass from concrete IE
_WORKING = False
IE_DESC = 'Murrtube user profile'
_VALID_URL = r'https?://murrtube\.net/(?P<id>[^/]+)$'
_TEST = {

1
yt_dlp/extractor/ndtv.py
View File

@ -5,6 +5,7 @@ from ..utils import parse_duration, remove_end, unified_strdate, urljoin
class NDTVIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:[^/]+\.)?ndtv\.com/(?:[^/]+/)*videos?/?(?:[^/]+/)*[^/?^&]+-(?P<id>\d+)'
_TESTS = [

1
yt_dlp/extractor/netzkino.py
View File

@ -8,6 +8,7 @@ from ..utils import (
class NetzkinoIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?netzkino\.de/\#!/[^/]+/(?P<id>[^/]+)'
_TESTS = [{

2
yt_dlp/extractor/nextmedia.py
View File

@ -191,6 +191,8 @@ class AppleDailyIE(NextMediaIE): # XXX: Do not subclass from concrete IE
class NextTVIE(InfoExtractor):
_WORKING = False
_ENABLED = None # XXX: pass through to GenericIE
IE_DESC = '壹電視'
_VALID_URL = r'https?://(?:www\.)?nexttv\.com\.tw/(?:[^/]+/)+(?P<id>\d+)'

1
yt_dlp/extractor/nobelprize.py
View File

@ -10,6 +10,7 @@ from ..utils import (
class NobelPrizeIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?nobelprize\.org/mediaplayer.*?\bid=(?P<id>\d+)'
_TEST = {
'url': 'http://www.nobelprize.org/mediaplayer/?id=2636',

1
yt_dlp/extractor/noz.py
View File

@ -9,6 +9,7 @@ from ..compat import compat_urllib_parse_unquote
class NozIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?noz\.de/video/(?P<id>[0-9]+)/'
_TESTS = [{
'url': 'http://www.noz.de/video/25151/32-Deutschland-gewinnt-Badminton-Lnderspiel-in-Melle',

47
yt_dlp/extractor/odatv.py
View File

@ -1,47 +0,0 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
NO_DEFAULT,
remove_start
)
class OdaTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?odatv\.com/(?:mob|vid)_video\.php\?.*\bid=(?P<id>[^&]+)'
_TESTS = [{
'url': 'http://odatv.com/vid_video.php?id=8E388',
'md5': 'dc61d052f205c9bf2da3545691485154',
'info_dict': {
'id': '8E388',
'ext': 'mp4',
'title': 'Artık Davutoğlu ile devam edemeyiz'
}
}, {
# mobile URL
'url': 'http://odatv.com/mob_video.php?id=8E388',
'only_matching': True,
}, {
# no video
'url': 'http://odatv.com/mob_video.php?id=8E900',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
no_video = 'NO VIDEO!' in webpage
video_url = self._search_regex(
r'mp4\s*:\s*(["\'])(?P<url>http.+?)\1', webpage, 'video url',
default=None if no_video else NO_DEFAULT, group='url')
if no_video:
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
return {
'id': video_id,
'url': video_url,
'title': remove_start(self._og_search_title(webpage), 'Video: '),
'thumbnail': self._og_search_thumbnail(webpage),
}

2
yt_dlp/extractor/parlview.py
View File

@ -8,7 +8,7 @@ from ..utils import (
class ParlviewIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?parlview\.aph\.gov\.au/(?:[^/]+)?\bvideoID=(?P<id>\d{6})'
_TESTS = [{
'url': 'https://parlview.aph.gov.au/mediaPlayer.php?videoID=542661',

63
yt_dlp/extractor/playstuff.py
View File

@ -1,63 +0,0 @@
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
smuggle_url,
try_get,
)
class PlayStuffIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?play\.stuff\.co\.nz/details/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://play.stuff.co.nz/details/608778ac1de1c4001a3fa09a',
'md5': 'c82d3669e5247c64bc382577843e5bd0',
'info_dict': {
'id': '6250584958001',
'ext': 'mp4',
'title': 'Episode 1: Rotorua/Mt Maunganui/Tauranga',
'description': 'md5:c154bafb9f0dd02d01fd4100fb1c1913',
'uploader_id': '6005208634001',
'timestamp': 1619491027,
'upload_date': '20210427',
},
'add_ie': ['BrightcoveNew'],
}, {
# geo restricted, bypassable
'url': 'https://play.stuff.co.nz/details/_6155660351001',
'only_matching': True,
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
state = self._parse_json(
self._search_regex(
r'__INITIAL_STATE__\s*=\s*({.+?})\s*;', webpage, 'state'),
video_id)
account_id = try_get(
state, lambda x: x['configurations']['accountId'],
compat_str) or '6005208634001'
player_id = try_get(
state, lambda x: x['configurations']['playerId'],
compat_str) or 'default'
entries = []
for item_id, video in state['items'].items():
if not isinstance(video, dict):
continue
asset_id = try_get(
video, lambda x: x['content']['attributes']['assetId'],
compat_str)
if not asset_id:
continue
entries.append(self.url_result(
smuggle_url(
self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, asset_id),
{'geo_countries': ['NZ']}),
'BrightcoveNew', video_id))
return self.playlist_result(entries, video_id)

1
yt_dlp/extractor/plutotv.py
View File

@ -16,6 +16,7 @@ from ..utils import (
class PlutoTVIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'''(?x)
https?://(?:www\.)?pluto\.tv(?:/[^/]+)?/on-demand
/(?P<video_type>movies|series)

1
yt_dlp/extractor/podomatic.py
View File

@ -5,6 +5,7 @@ from ..utils import int_or_none
class PodomaticIE(InfoExtractor):
_WORKING = False
IE_NAME = 'podomatic'
_VALID_URL = r'''(?x)
(?P<proto>https?)://

1
yt_dlp/extractor/pornovoisines.py
View File

@ -7,6 +7,7 @@ from ..utils import (
class PornoVoisinesIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?pornovoisines\.com/videos/show/(?P<id>\d+)/(?P<display_id>[^/.]+)'
_TEST = {

1
yt_dlp/extractor/pornoxo.py
View File

@ -5,6 +5,7 @@ from ..utils import (
class PornoXOIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?pornoxo\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)\.html'
_TEST = {
'url': 'http://www.pornoxo.com/videos/7564/striptease-from-sexy-secretary.html',

1
yt_dlp/extractor/projectveritas.py
View File

@ -7,6 +7,7 @@ from ..utils import (
class ProjectVeritasIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?projectveritas\.com/(?P<type>news|video)/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.projectveritas.com/news/exclusive-inside-the-new-york-and-new-jersey-hospitals-battling-coronavirus/',

4
yt_dlp/extractor/r7.py
View File

@ -3,6 +3,8 @@ from ..utils import int_or_none
class R7IE(InfoExtractor):
_WORKING = False
_ENABLED = None # XXX: pass through to GenericIE
_VALID_URL = r'''(?x)
https?://
(?:
@ -86,6 +88,8 @@ class R7IE(InfoExtractor):
class R7ArticleIE(InfoExtractor):
_WORKING = False
_ENABLED = None # XXX: pass through to GenericIE
_VALID_URL = r'https?://(?:[a-zA-Z]+)\.r7\.com/(?:[^/]+/)+[^/?#&]+-(?P<id>\d+)'
_TEST = {
'url': 'http://tv.r7.com/record-play/balanco-geral/videos/policiais-humilham-suspeito-a-beira-da-morte-morre-com-dignidade-16102015',

1
yt_dlp/extractor/radiode.py
View File

@ -2,6 +2,7 @@ from .common import InfoExtractor
class RadioDeIE(InfoExtractor):
_WORKING = False
IE_NAME = 'radio.de'
_VALID_URL = r'https?://(?P<id>.+?)\.(?:radio\.(?:de|at|fr|pt|es|pl|it)|rad\.io)'
_TEST = {

1
yt_dlp/extractor/radiojavan.py
View File

@ -11,6 +11,7 @@ from ..utils import (
class RadioJavanIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?'
_TEST = {
'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam',

68
yt_dlp/extractor/rbmaradio.py
View File

@ -1,68 +0,0 @@
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
clean_html,
int_or_none,
unified_timestamp,
update_url_query,
)
class RBMARadioIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:rbmaradio|redbullradio)\.com/shows/(?P<show_id>[^/]+)/episodes/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'https://www.rbmaradio.com/shows/main-stage/episodes/ford-lopatin-live-at-primavera-sound-2011',
'md5': '6bc6f9bcb18994b4c983bc3bf4384d95',
'info_dict': {
'id': 'ford-lopatin-live-at-primavera-sound-2011',
'ext': 'mp3',
'title': 'Main Stage - Ford & Lopatin at Primavera Sound',
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 2452,
'timestamp': 1307103164,
'upload_date': '20110603',
},
}
def _real_extract(self, url):
mobj = self._match_valid_url(url)
show_id = mobj.group('show_id')
episode_id = mobj.group('id')
webpage = self._download_webpage(url, episode_id)
episode = self._parse_json(
self._search_regex(
r'__INITIAL_STATE__\s*=\s*({.+?})\s*</script>',
webpage, 'json data'),
episode_id)['episodes'][show_id][episode_id]
title = episode['title']
show_title = episode.get('showTitle')
if show_title:
title = '%s - %s' % (show_title, title)
formats = [{
'url': update_url_query(episode['audioURL'], query={'cbr': abr}),
'format_id': compat_str(abr),
'abr': abr,
'vcodec': 'none',
} for abr in (96, 128, 192, 256)]
self._check_formats(formats, episode_id)
description = clean_html(episode.get('longTeaser'))
thumbnail = self._proto_relative_url(episode.get('imageURL', {}).get('landscape'))
duration = int_or_none(episode.get('duration'))
timestamp = unified_timestamp(episode.get('publishedAt'))
return {
'id': episode_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'timestamp': timestamp,
'formats': formats,
}

1
yt_dlp/extractor/rds.py
View File

@ -8,6 +8,7 @@ from ..compat import compat_str
class RDSIE(InfoExtractor):
_WORKING = False
IE_DESC = 'RDS.ca'
_VALID_URL = r'https?://(?:www\.)?rds\.ca/vid(?:[eé]|%C3%A9)os/(?:[^/]+/)*(?P<id>[^/]+)-\d+\.\d+'

1
yt_dlp/extractor/redbee.py
View File

@ -134,6 +134,7 @@ class ParliamentLiveUKIE(RedBeeBaseIE):
class RTBFIE(RedBeeBaseIE):
_WORKING = False
_VALID_URL = r'''(?x)
https?://(?:www\.)?rtbf\.be/
(?:

55
yt_dlp/extractor/regiotv.py
View File

@ -1,55 +0,0 @@
from .common import InfoExtractor
from ..networking import Request
from ..utils import xpath_text, xpath_with_ns
class RegioTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?regio-tv\.de/video/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://www.regio-tv.de/video/395808.html',
'info_dict': {
'id': '395808',
'ext': 'mp4',
'title': 'Wir in Ludwigsburg',
'description': 'Mit unseren zuckersüßen Adventskindern, außerdem besuchen wir die Abendsterne!',
}
}, {
'url': 'http://www.regio-tv.de/video/395808',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
key = self._search_regex(
r'key\s*:\s*(["\'])(?P<key>.+?)\1', webpage, 'key', group='key')
title = self._og_search_title(webpage)
SOAP_TEMPLATE = '<?xml version="1.0" encoding="utf-8"?><soap:Envelope xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:soap="http://schemas.xmlsoap.org/soap/envelope/"><soap:Body><{0} xmlns="http://v.telvi.de/"><key xsi:type="xsd:string">{1}</key></{0}></soap:Body></soap:Envelope>'
request = Request(
'http://v.telvi.de/',
SOAP_TEMPLATE.format('GetHTML5VideoData', key).encode('utf-8'))
video_data = self._download_xml(request, video_id, 'Downloading video XML')
NS_MAP = {
'xsi': 'http://www.w3.org/2001/XMLSchema-instance',
'soap': 'http://schemas.xmlsoap.org/soap/envelope/',
}
video_url = xpath_text(
video_data, xpath_with_ns('.//video', NS_MAP), 'video url', fatal=True)
thumbnail = xpath_text(
video_data, xpath_with_ns('.//image', NS_MAP), 'thumbnail')
description = self._og_search_description(
webpage) or self._html_search_meta('description', webpage)
return {
'id': video_id,
'url': video_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
}

2
yt_dlp/extractor/rentv.py
View File

@ -8,6 +8,7 @@ from ..utils import (
class RENTVIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'(?:rentv:|https?://(?:www\.)?ren\.tv/(?:player|video/epizod)/)(?P<id>\d+)'
_TESTS = [{
'url': 'http://ren.tv/video/epizod/118577',
@ -59,6 +60,7 @@ class RENTVIE(InfoExtractor):
class RENTVArticleIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?ren\.tv/novosti/\d{4}-\d{2}-\d{2}/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'http://ren.tv/novosti/2016-10-26/video-mikroavtobus-popavshiy-v-dtp-s-gruzovikami-v-podmoskove-prevratilsya-v',

1
yt_dlp/extractor/restudy.py
View File

@ -2,6 +2,7 @@ from .common import InfoExtractor
class RestudyIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:(?:www|portal)\.)?restudy\.dk/video/[^/]+/id/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://www.restudy.dk/video/play/id/1637',

1
yt_dlp/extractor/reuters.py
View File

@ -9,6 +9,7 @@ from ..utils import (
class ReutersIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?reuters\.com/.*?\?.*?videoId=(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.reuters.com/video/2016/05/20/san-francisco-police-chief-resigns?videoId=368575562',

1
yt_dlp/extractor/rockstargames.py
View File

@ -6,6 +6,7 @@ from ..utils import (
class RockstarGamesIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?rockstargames\.com/videos(?:/video/|#?/?\?.*\bvideo=)(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.rockstargames.com/videos/video/11544/',

1
yt_dlp/extractor/rts.py
View File

@ -13,6 +13,7 @@ from ..utils import (
class RTSIE(SRGSSRIE): # XXX: Do not subclass from concrete IE
_WORKING = False
IE_DESC = 'RTS.ch'
_VALID_URL = r'rts:(?P<rts_id>\d+)|https?://(?:.+?\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html'

1
yt_dlp/extractor/saitosan.py
View File

@ -3,6 +3,7 @@ from ..utils import ExtractorError, try_get
class SaitosanIE(InfoExtractor):
_WORKING = False
IE_NAME = 'Saitosan'
_VALID_URL = r'https?://(?:www\.)?saitosan\.net/bview.html\?id=(?P<id>[0-9]+)'
_TESTS = [{

30
yt_dlp/extractor/savefrom.py
View File

@ -1,30 +0,0 @@
import os.path
from .common import InfoExtractor
class SaveFromIE(InfoExtractor):
IE_NAME = 'savefrom.net'
_VALID_URL = r'https?://[^.]+\.savefrom\.net/\#url=(?P<url>.*)$'
_TEST = {
'url': 'http://en.savefrom.net/#url=http://youtube.com/watch?v=UlVRAPW2WJY&utm_source=youtube.com&utm_medium=short_domains&utm_campaign=ssyoutube.com',
'info_dict': {
'id': 'UlVRAPW2WJY',
'ext': 'mp4',
'title': 'About Team Radical MMA | MMA Fighting',
'upload_date': '20120816',
'uploader': 'Howcast',
'uploader_id': 'Howcast',
'description': r're:(?s).* Hi, my name is Rene Dreifuss\. And I\'m here to show you some MMA.*',
},
'params': {
'skip_download': True
}
}
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id = os.path.splitext(url.split('/')[-1])[0]
return self.url_result(mobj.group('url'), video_id=video_id)

55
yt_dlp/extractor/seeker.py
View File

@ -1,55 +0,0 @@
import re
from .common import InfoExtractor
from ..utils import (
get_element_by_class,
strip_or_none,
)
class SeekerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?seeker\.com/(?P<display_id>.*)-(?P<article_id>\d+)\.html'
_TESTS = [{
'url': 'http://www.seeker.com/should-trump-be-required-to-release-his-tax-returns-1833805621.html',
'md5': '897d44bbe0d8986a2ead96de565a92db',
'info_dict': {
'id': 'Elrn3gnY',
'ext': 'mp4',
'title': 'Should Trump Be Required To Release His Tax Returns?',
'description': 'md5:41efa8cfa8d627841045eec7b018eb45',
'timestamp': 1490090165,
'upload_date': '20170321',
}
}, {
'url': 'http://www.seeker.com/changes-expected-at-zoos-following-recent-gorilla-lion-shootings-1834116536.html',
'playlist': [
{
'md5': '0497b9f20495174be73ae136949707d2',
'info_dict': {
'id': 'FihYQ8AE',
'ext': 'mp4',
'title': 'The Pros & Cons Of Zoos',
'description': 'md5:d88f99a8ea8e7d25e6ff77f271b1271c',
'timestamp': 1490039133,
'upload_date': '20170320',
},
}
],
'info_dict': {
'id': '1834116536',
'title': 'After Gorilla Killing, Changes Ahead for Zoos',
'description': 'The largest association of zoos and others are hoping to learn from recent incidents that led to the shooting deaths of a gorilla and two lions.',
},
}]
def _real_extract(self, url):
display_id, article_id = self._match_valid_url(url).groups()
webpage = self._download_webpage(url, display_id)
entries = []
for jwp_id in re.findall(r'data-video-id="([a-zA-Z0-9]{8})"', webpage):
entries.append(self.url_result(
'jwplatform:' + jwp_id, 'JWPlatform', jwp_id))
return self.playlist_result(
entries, article_id,
self._og_search_title(webpage),
strip_or_none(get_element_by_class('subtitle__text', webpage)) or self._og_search_description(webpage))

1
yt_dlp/extractor/senalcolombia.py
View File

@ -3,6 +3,7 @@ from .rtvcplay import RTVCKalturaIE
class SenalColombiaLiveIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?senalcolombia\.tv/(?P<id>senal-en-vivo)'
_TESTS = [{

1
yt_dlp/extractor/sendtonews.py
View File

@ -12,6 +12,7 @@ from ..utils import (
class SendtoNewsIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://embed\.sendtonews\.com/player2/embedplayer\.php\?.*\bSC=(?P<id>[0-9A-Za-z-]+)'
_TEST = {

1
yt_dlp/extractor/sexu.py
View File

@ -2,6 +2,7 @@ from .common import InfoExtractor
class SexuIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?sexu\.com/(?P<id>\d+)'
_TEST = {
'url': 'http://sexu.com/961791/',

1
yt_dlp/extractor/skylinewebcams.py
View File

@ -2,6 +2,7 @@ from .common import InfoExtractor
class SkylineWebcamsIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?skylinewebcams\.com/[^/]+/webcam/(?:[^/]+/)+(?P<id>[^/]+)\.html'
_TEST = {
'url': 'https://www.skylinewebcams.com/it/webcam/italia/lazio/roma/scalinata-piazza-di-spagna-barcaccia.html',

2
yt_dlp/extractor/skynewsarabia.py
View File

@ -38,6 +38,7 @@ class SkyNewsArabiaBaseIE(InfoExtractor):
class SkyNewsArabiaIE(SkyNewsArabiaBaseIE):
_WORKING = False
IE_NAME = 'skynewsarabia:video'
_VALID_URL = r'https?://(?:www\.)?skynewsarabia\.com/web/video/(?P<id>[0-9]+)'
_TEST = {
@ -64,6 +65,7 @@ class SkyNewsArabiaIE(SkyNewsArabiaBaseIE):
class SkyNewsArabiaArticleIE(SkyNewsArabiaBaseIE):
_WORKING = False
IE_NAME = 'skynewsarabia:article'
_VALID_URL = r'https?://(?:www\.)?skynewsarabia\.com/web/article/(?P<id>[0-9]+)'
_TESTS = [{

1
yt_dlp/extractor/startrek.py
View File

@ -3,6 +3,7 @@ from ..utils import int_or_none, urljoin
class StarTrekIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'(?P<base>https?://(?:intl|www)\.startrek\.com)/videos/(?P<id>[^/]+)'
_TESTS = [{
'url': 'https://intl.startrek.com/videos/watch-welcoming-jess-bush-to-the-ready-room',

30
yt_dlp/extractor/streamff.py
View File

@ -1,30 +0,0 @@
from .common import InfoExtractor
from ..utils import int_or_none, parse_iso8601
class StreamFFIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?streamff\.com/v/(?P<id>[a-zA-Z0-9]+)'
_TESTS = [{
'url': 'https://streamff.com/v/55cc94',
'md5': '8745a67bb5e5c570738efe7983826370',
'info_dict': {
'id': '55cc94',
'ext': 'mp4',
'title': '55cc94',
'timestamp': 1634764643,
'upload_date': '20211020',
'view_count': int,
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
json_data = self._download_json(f'https://streamff.com/api/videos/{video_id}', video_id)
return {
'id': video_id,
'title': json_data.get('name') or video_id,
'url': 'https://streamff.com/%s' % json_data['videoLink'],
'view_count': int_or_none(json_data.get('views')),
'timestamp': parse_iso8601(json_data.get('date')),
}

1
yt_dlp/extractor/syfy.py
View File

@ -6,6 +6,7 @@ from ..utils import (
class SyfyIE(AdobePassIE):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?syfy\.com/(?:[^/]+/)?videos/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'http://www.syfy.com/theinternetruinedmylife/videos/the-internet-ruined-my-life-season-1-trailer',

1
yt_dlp/extractor/tagesschau.py
View File

@ -12,6 +12,7 @@ from ..utils import (
class TagesschauIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?tagesschau\.de/(?P<path>[^/]+/(?:[^/]+/)*?(?P<id>[^/#?]+?(?:-?[0-9]+)?))(?:~_?[^/#?]+?)?\.html'
_TESTS = [{

1
yt_dlp/extractor/tass.py
View File

@ -8,6 +8,7 @@ from ..utils import (
class TassIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:tass\.ru|itar-tass\.com)/[^/]+/(?P<id>\d+)'
_TESTS = [
{

31
yt_dlp/extractor/tdslifeway.py
View File

@ -1,31 +0,0 @@
from .common import InfoExtractor
class TDSLifewayIE(InfoExtractor):
_VALID_URL = r'https?://tds\.lifeway\.com/v1/trainingdeliverysystem/courses/(?P<id>\d+)/index\.html'
_TEST = {
# From http://www.ministrygrid.com/training-viewer/-/training/t4g-2014-conference/the-gospel-by-numbers-4/the-gospel-by-numbers
'url': 'http://tds.lifeway.com/v1/trainingdeliverysystem/courses/3453494717001/index.html?externalRegistration=AssetId%7C34F466F1-78F3-4619-B2AB-A8EFFA55E9E9%21InstanceId%7C0%21UserId%7Caaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa&grouping=http%3A%2F%2Flifeway.com%2Fvideo%2F3453494717001&activity_id=http%3A%2F%2Flifeway.com%2Fvideo%2F3453494717001&content_endpoint=http%3A%2F%2Ftds.lifeway.com%2Fv1%2Ftrainingdeliverysystem%2FScormEngineInterface%2FTCAPI%2Fcontent%2F&actor=%7B%22name%22%3A%5B%22Guest%20Guest%22%5D%2C%22account%22%3A%5B%7B%22accountServiceHomePage%22%3A%22http%3A%2F%2Fscorm.lifeway.com%2F%22%2C%22accountName%22%3A%22aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa%22%7D%5D%2C%22objectType%22%3A%22Agent%22%7D&content_token=462a50b2-b6f9-4970-99b1-930882c499fb&registration=93d6ec8e-7f7b-4ed3-bbc8-a857913c0b2a&externalConfiguration=access%7CFREE%21adLength%7C-1%21assignOrgId%7C4AE36F78-299A-425D-91EF-E14A899B725F%21assignOrgParentId%7C%21courseId%7C%21isAnonymous%7Cfalse%21previewAsset%7Cfalse%21previewLength%7C-1%21previewMode%7Cfalse%21royalty%7CFREE%21sessionId%7C671422F9-8E79-48D4-9C2C-4EE6111EA1CD%21trackId%7C&auth=Basic%20OjhmZjk5MDBmLTBlYTMtNDJhYS04YjFlLWE4MWQ3NGNkOGRjYw%3D%3D&endpoint=http%3A%2F%2Ftds.lifeway.com%2Fv1%2Ftrainingdeliverysystem%2FScormEngineInterface%2FTCAPI%2F',
'info_dict': {
'id': '3453494717001',
'ext': 'mp4',
'title': 'The Gospel by Numbers',
'thumbnail': r're:^https?://.*\.jpg',
'upload_date': '20140410',
'description': 'Coming soon from T4G 2014!',
'uploader_id': '2034960640001',
'timestamp': 1397145591,
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['BrightcoveNew'],
}
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/2034960640001/default_default/index.html?videoId=%s'
def _real_extract(self, url):
brightcove_id = self._match_id(url)
return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)

1
yt_dlp/extractor/teachable.py
View File

@ -99,6 +99,7 @@ class TeachableBaseIE(InfoExtractor):
class TeachableIE(TeachableBaseIE):
_WORKING = False
_VALID_URL = r'''(?x)
(?:
%shttps?://(?P<site_t>[^/]+)|

2
yt_dlp/extractor/teachertube.py
View File

@ -9,6 +9,7 @@ from ..utils import (
class TeacherTubeIE(InfoExtractor):
_WORKING = False
IE_NAME = 'teachertube'
IE_DESC = 'teachertube.com videos'
@ -87,6 +88,7 @@ class TeacherTubeIE(InfoExtractor):
class TeacherTubeUserIE(InfoExtractor):
_WORKING = False
IE_NAME = 'teachertube:user:collection'
IE_DESC = 'teachertube.com user and collection videos'

1
yt_dlp/extractor/teachingchannel.py
View File

@ -2,6 +2,7 @@ from .common import InfoExtractor
class TeachingChannelIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?teachingchannel\.org/videos?/(?P<id>[^/?&#]+)'
_TEST = {

1
yt_dlp/extractor/tele5.py
View File

@ -7,6 +7,7 @@ from ..utils import (
class Tele5IE(DPlayIE): # XXX: Do not subclass from concrete IE
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_GEO_COUNTRIES = ['DE']
_TESTS = [{

1
yt_dlp/extractor/telemb.py
View File

@ -5,6 +5,7 @@ from ..utils import remove_start
class TeleMBIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?telemb\.be/(?P<display_id>.+?)_d_(?P<id>\d+)\.html'
_TESTS = [
{

2
yt_dlp/extractor/telemundo.py
View File

@ -4,7 +4,7 @@ from ..utils import try_get, unified_timestamp
class TelemundoIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?:\/\/(?:www\.)?telemundo\.com\/.+?video\/[^\/]+(?P<id>tmvo\d{7})'
_TESTS = [{
'url': 'https://www.telemundo.com/noticias/noticias-telemundo-en-la-noche/empleo/video/esta-aplicacion-gratuita-esta-ayudando-los-latinos-encontrar-trabajo-en-estados-unidos-tmvo9829325',

1
yt_dlp/extractor/teletask.py
View File

@ -5,6 +5,7 @@ from ..utils import unified_strdate
class TeleTaskIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?tele-task\.de/archive/video/html5/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.tele-task.de/archive/video/html5/26168/',

2
yt_dlp/extractor/tonline.py
View File

@ -3,6 +3,8 @@ from ..utils import int_or_none, join_nonempty
class TOnlineIE(InfoExtractor):
_WORKING = False
_ENABLED = None # XXX: pass through to GenericIE
IE_NAME = 't-online.de'
_VALID_URL = r'https?://(?:www\.)?t-online\.de/tv/(?:[^/]+/)*id_(?P<id>\d+)'
_TEST = {

2
yt_dlp/extractor/tv2.py
View File

@ -161,6 +161,7 @@ class TV2ArticleIE(InfoExtractor):
class KatsomoIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?(?:katsomo|mtv(uutiset)?)\.fi/(?:sarja/[0-9a-z-]+-\d+/[0-9a-z-]+-|(?:#!/)?jakso/(?:\d+/[^/]+/)?|video/prog)(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.mtv.fi/sarja/mtv-uutiset-live-33001002003/lahden-pelicans-teki-kovan-ratkaisun-ville-nieminen-pihalle-1181321',
@ -279,6 +280,7 @@ class KatsomoIE(InfoExtractor):
class MTVUutisetArticleIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)mtvuutiset\.fi/artikkeli/[^/]+/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.mtvuutiset.fi/artikkeli/tallaisia-vaurioita-viking-amorellassa-on-useamman-osaston-alla-vetta/7931384',

1
yt_dlp/extractor/tvn24.py
View File

@ -7,6 +7,7 @@ from ..utils import (
class TVN24IE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:(?:[^/]+)\.)?tvn24(?:bis)?\.pl/(?:[^/]+/)*(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://www.tvn24.pl/wiadomosci-z-kraju,3/oredzie-artura-andrusa,702428.html',

1
yt_dlp/extractor/tvnoe.py
View File

@ -7,6 +7,7 @@ from ..utils import (
class TVNoeIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?tvnoe\.cz/video/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.tvnoe.cz/video/10362',

1
yt_dlp/extractor/ukcolumn.py
View File

@ -9,6 +9,7 @@ from .youtube import YoutubeIE
class UkColumnIE(InfoExtractor):
_WORKING = False
IE_NAME = 'ukcolumn'
_VALID_URL = r'(?i)https?://(?:www\.)?ukcolumn\.org(/index\.php)?/(?:video|ukcolumn-news)/(?P<id>[-a-z0-9]+)'

1
yt_dlp/extractor/umg.py
View File

@ -7,6 +7,7 @@ from ..utils import (
class UMGDeIE(InfoExtractor):
_WORKING = False
IE_NAME = 'umg:de'
IE_DESC = 'Universal Music Deutschland'
_VALID_URL = r'https?://(?:www\.)?universal-music\.de/[^/]+/videos/[^/?#]+-(?P<id>\d+)'

1
yt_dlp/extractor/unity.py
View File

@ -3,6 +3,7 @@ from .youtube import YoutubeIE
class UnityIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?unity3d\.com/learn/tutorials/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://unity3d.com/learn/tutorials/topics/animation/animate-anything-mecanim',

1
yt_dlp/extractor/urort.py
View File

@ -5,6 +5,7 @@ from ..utils import unified_strdate
class UrortIE(InfoExtractor):
_WORKING = False
IE_DESC = 'NRK P3 Urørt'
_VALID_URL = r'https?://(?:www\.)?urort\.p3\.no/#!/Band/(?P<id>[^/]+)$'

Some files were not shown because too many files have changed in this diff Show More