mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2026-02-05 21:46:59 +00:00
Code Issues Projects Releases Wiki Activity

Merge remote-tracking branch 'upstream/master' into boomplay

Browse Source
This commit is contained in:
grqx_wsl
2024-10-23 23:38:20 +13:00
parent aa34d34596 dd2e244469
commit 1066a94acf
41 changed files with 940 additions and 605 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
yt_dlp/extractor/_extractors.py
View File

@@ -373,7 +373,10 @@ from .ccc import (
)
from .ccma import CCMAIE
from .cctv import CCTVIE
from .cda import CDAIE
from .cda import (
CDAIE,
CDAFolderIE,
)
from .cellebrite import CellebriteIE
from .ceskatelevize import CeskaTelevizeIE
from .cgtn import CGTNIE

7
yt_dlp/extractor/adobepass.py
View File

@@ -1355,6 +1355,7 @@ MSO_INFO = {
class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
_SERVICE_PROVIDER_TEMPLATE = 'https://sp.auth.adobe.com/adobe-services/%s'
_USER_AGENT = 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0'
_MODERN_USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; rv:131.0) Gecko/20100101 Firefox/131.0'
_MVPD_CACHE = 'ap-mvpd'
_DOWNLOADING_LOGIN_PAGE = 'Downloading Provider Login Page'
@@ -1454,7 +1455,11 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
'no_iframe': 'false',
'domain_name': 'adobe.com',
'redirect_url': url,
})
}, headers={
# yt-dlp's default user-agent is usually too old for Comcast_SSO
# See: https://github.com/yt-dlp/yt-dlp/issues/10848
'User-Agent': self._MODERN_USER_AGENT,
} if mso_id == 'Comcast_SSO' else None)
elif not self._cookies_passed:
raise_mvpd_required()

185
yt_dlp/extractor/afreecatv.py
View File

@@ -33,21 +33,21 @@ class AfreecaTVBaseIE(InfoExtractor):
}
response = self._download_json(
'https://login.afreecatv.com/app/LoginAction.php', None,
'https://login.sooplive.co.kr/app/LoginAction.php', None,
'Logging in', data=urlencode_postdata(login_form))
_ERRORS = {
-4: 'Your account has been suspended due to a violation of our terms and policies.',
-5: 'https://member.afreecatv.com/app/user_delete_progress.php',
-6: 'https://login.afreecatv.com/membership/changeMember.php',
-8: "Hello! AfreecaTV here.\nThe username you have entered belongs to \n an account that requires a legal guardian's consent. \nIf you wish to use our services without restriction, \nplease make sure to go through the necessary verification process.",
-9: 'https://member.afreecatv.com/app/pop_login_block.php',
-11: 'https://login.afreecatv.com/afreeca/second_login.php',
-12: 'https://member.afreecatv.com/app/user_security.php',
-5: 'https://member.sooplive.co.kr/app/user_delete_progress.php',
-6: 'https://login.sooplive.co.kr/membership/changeMember.php',
-8: "Hello! Soop here.\nThe username you have entered belongs to \n an account that requires a legal guardian's consent. \nIf you wish to use our services without restriction, \nplease make sure to go through the necessary verification process.",
-9: 'https://member.sooplive.co.kr/app/pop_login_block.php',
-11: 'https://login.sooplive.co.kr/afreeca/second_login.php',
-12: 'https://member.sooplive.co.kr/app/user_security.php',
0: 'The username does not exist or you have entered the wrong password.',
-1: 'The username does not exist or you have entered the wrong password.',
-3: 'You have entered your username/password incorrectly.',
-7: 'You cannot use your Global AfreecaTV account to access Korean AfreecaTV.',
-7: 'You cannot use your Global Soop account to access Korean Soop.',
-10: 'Sorry for the inconvenience. \nYour account has been blocked due to an unauthorized access. \nPlease contact our Help Center for assistance.',
-32008: 'You have failed to log in. Please contact our Help Center.',
}
@@ -61,76 +61,40 @@ class AfreecaTVBaseIE(InfoExtractor):
def _call_api(self, endpoint, display_id, data=None, headers=None, query=None):
return self._download_json(Request(
f'https://api.m.afreecatv.com/{endpoint}',
f'https://api.m.sooplive.co.kr/{endpoint}',
data=data, headers=headers, query=query,
extensions={'legacy_ssl': True}), display_id,
'Downloading API JSON', 'Unable to download API JSON')
class AfreecaTVIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv'
IE_DESC = 'afreecatv.com'
_VALID_URL = r'''(?x)
https?://
(?:
(?:(?:live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
(?:
/app/(?:index|read_ucc_bbs)\.cgi|
/player/[Pp]layer\.(?:swf|html)
)\?.*?\bnTitleNo=|
vod\.afreecatv\.com/(PLAYER/STATION|player)/
)
(?P<id>\d+)/?(?:$|[?#&])
'''
IE_NAME = 'soop'
IE_DESC = 'sooplive.co.kr'
_VALID_URL = r'https?://vod\.(?:sooplive\.co\.kr|afreecatv\.com)/(?:PLAYER/STATION|player)/(?P<id>\d+)/?(?:$|[?#&])'
_TESTS = [{
'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
'url': 'https://vod.sooplive.co.kr/player/96753363',
'info_dict': {
'id': '36164052',
'id': '20230108_9FF5BEE1_244432674_1',
'ext': 'mp4',
'title': '데일리 에이프릴 요정들의 시상식!',
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
'upload_date': '20160503',
'uploader_id': 'rlantnghks',
'uploader': '페이즈으',
'duration': 10840,
'thumbnail': r're:https?://videoimg\.sooplive\.co/.kr/.+',
'upload_date': '20230108',
'timestamp': 1673218805,
'title': '젠지 페이즈',
},
'skip': 'Video is gone',
}, {
'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867',
'info_dict': {
'id': '36153164',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
'params': {
'skip_download': True,
},
'playlist_count': 2,
'playlist': [{
'md5': 'd8b7c174568da61d774ef0203159bf97',
'info_dict': {
'id': '36153164_1',
'ext': 'mp4',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'upload_date': '20160502',
},
}, {
'md5': '58f2ce7f6044e34439ab2d50612ab02b',
'info_dict': {
'id': '36153164_2',
'ext': 'mp4',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'upload_date': '20160502',
},
}],
'skip': 'Video is gone',
}, {
# non standard key
'url': 'http://vod.afreecatv.com/PLAYER/STATION/20515605',
'url': 'http://vod.sooplive.co.kr/PLAYER/STATION/20515605',
'info_dict': {
'id': '20170411_BE689A0E_190960999_1_2_h',
'ext': 'mp4',
'title': '혼자사는여자집',
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'thumbnail': r're:https?://(?:video|st)img\.sooplive\.co\.kr/.+',
'uploader': '♥이슬이',
'uploader_id': 'dasl8121',
'upload_date': '20170411',
@@ -142,12 +106,12 @@ class AfreecaTVIE(AfreecaTVBaseIE):
},
}, {
# adult content
'url': 'https://vod.afreecatv.com/player/97267690',
'url': 'https://vod.sooplive.co.kr/player/97267690',
'info_dict': {
'id': '20180327_27901457_202289533_1',
'ext': 'mp4',
'title': '[생]빨개요♥ (part 1)',
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'thumbnail': r're:https?://(?:video|st)img\.sooplive\.co\.kr/.+',
'uploader': '[SA]서아',
'uploader_id': 'bjdyrksu',
'upload_date': '20180327',
@@ -157,36 +121,17 @@ class AfreecaTVIE(AfreecaTVBaseIE):
'skip_download': True,
},
'skip': 'The VOD does not exist',
}, {
'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
'only_matching': True,
}, {
'url': 'https://vod.afreecatv.com/player/96753363',
'info_dict': {
'id': '20230108_9FF5BEE1_244432674_1',
'ext': 'mp4',
'uploader_id': 'rlantnghks',
'uploader': '페이즈으',
'duration': 10840,
'thumbnail': r're:https?://videoimg\.afreecatv\.com/.+',
'upload_date': '20230108',
'timestamp': 1673218805,
'title': '젠지 페이즈',
},
'params': {
'skip_download': True,
},
}, {
# adult content
'url': 'https://vod.afreecatv.com/player/70395877',
'url': 'https://vod.sooplive.co.kr/player/70395877',
'only_matching': True,
}, {
# subscribers only
'url': 'https://vod.afreecatv.com/player/104647403',
'url': 'https://vod.sooplive.co.kr/player/104647403',
'only_matching': True,
}, {
# private
'url': 'https://vod.afreecatv.com/player/81669846',
'url': 'https://vod.sooplive.co.kr/player/81669846',
'only_matching': True,
}]
@@ -262,11 +207,11 @@ class AfreecaTVIE(AfreecaTVBaseIE):
class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv:catchstory'
IE_DESC = 'afreecatv.com catch story'
_VALID_URL = r'https?://vod\.afreecatv\.com/player/(?P<id>\d+)/catchstory'
IE_NAME = 'soop:catchstory'
IE_DESC = 'sooplive.co.kr catch story'
_VALID_URL = r'https?://vod\.(?:sooplive\.co\.kr|afreecatv\.com)/player/(?P<id>\d+)/catchstory'
_TESTS = [{
'url': 'https://vod.afreecatv.com/player/103247/catchstory',
'url': 'https://vod.sooplive.co.kr/player/103247/catchstory',
'info_dict': {
'id': '103247',
},
@@ -299,11 +244,11 @@ class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
class AfreecaTVLiveIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv:live'
IE_DESC = 'afreecatv.com livestreams'
_VALID_URL = r'https?://play\.afreeca(?:tv)?\.com/(?P<id>[^/]+)(?:/(?P<bno>\d+))?'
IE_NAME = 'soop:live'
IE_DESC = 'sooplive.co.kr livestreams'
_VALID_URL = r'https?://play\.(?:sooplive\.co\.kr|afreecatv\.com)/(?P<id>[^/?#]+)(?:/(?P<bno>\d+))?'
_TESTS = [{
'url': 'https://play.afreecatv.com/pyh3646/237852185',
'url': 'https://play.sooplive.co.kr/pyh3646/237852185',
'info_dict': {
'id': '237852185',
'ext': 'mp4',
@@ -315,30 +260,30 @@ class AfreecaTVLiveIE(AfreecaTVBaseIE):
},
'skip': 'Livestream has ended',
}, {
'url': 'https://play.afreecatv.com/pyh3646/237852185',
'url': 'https://play.sooplive.co.kr/pyh3646/237852185',
'only_matching': True,
}, {
'url': 'https://play.afreecatv.com/pyh3646',
'url': 'https://play.sooplive.co.kr/pyh3646',
'only_matching': True,
}]
_LIVE_API_URL = 'https://live.afreecatv.com/afreeca/player_live_api.php'
_LIVE_API_URL = 'https://live.sooplive.co.kr/afreeca/player_live_api.php'
_WORKING_CDNS = [
'gcp_cdn', # live-global-cdn-v02.afreecatv.com
'gs_cdn_pc_app', # pc-app.stream.afreecatv.com
'gs_cdn_mobile_web', # mobile-web.stream.afreecatv.com
'gs_cdn_pc_web', # pc-web.stream.afreecatv.com
'gcp_cdn', # live-global-cdn-v02.sooplive.co.kr
'gs_cdn_pc_app', # pc-app.stream.sooplive.co.kr
'gs_cdn_mobile_web', # mobile-web.stream.sooplive.co.kr
'gs_cdn_pc_web', # pc-web.stream.sooplive.co.kr
]
_BAD_CDNS = [
'gs_cdn', # chromecast.afreeca.gscdn.com (cannot resolve)
'gs_cdn_chromecast', # chromecast.stream.afreecatv.com (HTTP Error 400)
'azure_cdn', # live-global-cdn-v01.afreecatv.com (cannot resolve)
'aws_cf', # live-global-cdn-v03.afreecatv.com (cannot resolve)
'kt_cdn', # kt.stream.afreecatv.com (HTTP Error 400)
'gs_cdn_chromecast', # chromecast.stream.sooplive.co.kr (HTTP Error 400)
'azure_cdn', # live-global-cdn-v01.sooplive.co.kr (cannot resolve)
'aws_cf', # live-global-cdn-v03.sooplive.co.kr (cannot resolve)
'kt_cdn', # kt.stream.sooplive.co.kr (HTTP Error 400)
]
def _extract_formats(self, channel_info, broadcast_no, aid):
stream_base_url = channel_info.get('RMD') or 'https://livestream-manager.afreecatv.com'
stream_base_url = channel_info.get('RMD') or 'https://livestream-manager.sooplive.co.kr'
# If user has not passed CDN IDs, try API-provided CDN ID followed by other working CDN IDs
default_cdn_ids = orderedSet([
@@ -358,7 +303,7 @@ class AfreecaTVLiveIE(AfreecaTVBaseIE):
try:
return self._extract_m3u8_formats(
m3u8_url, broadcast_no, 'mp4', m3u8_id='hls', query={'aid': aid},
headers={'Referer': 'https://play.afreecatv.com/'})
headers={'Referer': 'https://play.sooplive.co.kr/'})
except ExtractorError as e:
if attempt == len(cdn_ids):
raise
@@ -374,7 +319,13 @@ class AfreecaTVLiveIE(AfreecaTVBaseIE):
broadcaster_id = channel_info.get('BJID') or broadcaster_id
broadcast_no = channel_info.get('BNO') or broadcast_no
if not broadcast_no:
raise UserNotLive(video_id=broadcaster_id)
result = channel_info.get('RESULT')
if result == 0:
raise UserNotLive(video_id=broadcaster_id)
elif result == -6:
self.raise_login_required(
'This channel is streaming for subscribers only', method='password')
raise ExtractorError('Unable to extract broadcast number')
password = self.get_param('videopassword')
if channel_info.get('BPWD') == 'Y' and password is None:
@@ -403,7 +354,7 @@ class AfreecaTVLiveIE(AfreecaTVBaseIE):
formats = self._extract_formats(channel_info, broadcast_no, aid)
station_info = traverse_obj(self._download_json(
'https://st.afreecatv.com/api/get_station_status.php', broadcast_no,
'https://st.sooplive.co.kr/api/get_station_status.php', broadcast_no,
'Downloading channel metadata', 'Unable to download channel metadata',
query={'szBjId': broadcaster_id}, fatal=False), {dict}) or {}
@@ -419,11 +370,11 @@ class AfreecaTVLiveIE(AfreecaTVBaseIE):
}
class AfreecaTVUserIE(InfoExtractor):
IE_NAME = 'afreecatv:user'
_VALID_URL = r'https?://bj\.afreeca(?:tv)?\.com/(?P<id>[^/]+)/vods/?(?P<slug_type>[^/]+)?'
class AfreecaTVUserIE(AfreecaTVBaseIE):
IE_NAME = 'soop:user'
_VALID_URL = r'https?://ch\.(?:sooplive\.co\.kr|afreecatv\.com)/(?P<id>[^/?#]+)/vods/?(?P<slug_type>[^/?#]+)?'
_TESTS = [{
'url': 'https://bj.afreecatv.com/ryuryu24/vods/review',
'url': 'https://ch.sooplive.co.kr/ryuryu24/vods/review',
'info_dict': {
'_type': 'playlist',
'id': 'ryuryu24',
@@ -431,7 +382,7 @@ class AfreecaTVUserIE(InfoExtractor):
},
'playlist_count': 218,
}, {
'url': 'https://bj.afreecatv.com/parang1995/vods/highlight',
'url': 'https://ch.sooplive.co.kr/parang1995/vods/highlight',
'info_dict': {
'_type': 'playlist',
'id': 'parang1995',
@@ -439,7 +390,7 @@ class AfreecaTVUserIE(InfoExtractor):
},
'playlist_count': 997,
}, {
'url': 'https://bj.afreecatv.com/ryuryu24/vods',
'url': 'https://ch.sooplive.co.kr/ryuryu24/vods',
'info_dict': {
'_type': 'playlist',
'id': 'ryuryu24',
@@ -447,7 +398,7 @@ class AfreecaTVUserIE(InfoExtractor):
},
'playlist_count': 221,
}, {
'url': 'https://bj.afreecatv.com/ryuryu24/vods/balloonclip',
'url': 'https://ch.sooplive.co.kr/ryuryu24/vods/balloonclip',
'info_dict': {
'_type': 'playlist',
'id': 'ryuryu24',
@@ -459,12 +410,12 @@ class AfreecaTVUserIE(InfoExtractor):
def _fetch_page(self, user_id, user_type, page):
page += 1
info = self._download_json(f'https://bjapi.afreecatv.com/api/{user_id}/vods/{user_type}', user_id,
info = self._download_json(f'https://chapi.sooplive.co.kr/api/{user_id}/vods/{user_type}', user_id,
query={'page': page, 'per_page': self._PER_PAGE, 'orderby': 'reg_date'},
note=f'Downloading {user_type} video page {page}')
for item in info['data']:
yield self.url_result(
f'https://vod.afreecatv.com/player/{item["title_no"]}/', AfreecaTVIE, item['title_no'])
f'https://vod.sooplive.co.kr/player/{item["title_no"]}/', AfreecaTVIE, item['title_no'])
def _real_extract(self, url):
user_id, user_type = self._match_valid_url(url).group('id', 'slug_type')

82
yt_dlp/extractor/cbc.py
View File

@@ -4,7 +4,6 @@ import json
import re
import time
import urllib.parse
import xml.etree.ElementTree
from .common import InfoExtractor
from ..networking import HEADRequest
@@ -12,7 +11,6 @@ from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
join_nonempty,
js_to_json,
mimetype2ext,
orderedSet,
@@ -524,14 +522,13 @@ class CBCGemIE(InfoExtractor):
_TESTS = [{
# This is a normal, public, TV show video
'url': 'https://gem.cbc.ca/media/schitts-creek/s06e01',
'md5': '93dbb31c74a8e45b378cf13bd3f6f11e',
'info_dict': {
'id': 'schitts-creek/s06e01',
'ext': 'mp4',
'title': 'Smoke Signals',
'description': 'md5:929868d20021c924020641769eb3e7f1',
'thumbnail': 'https://images.radio-canada.ca/v1/synps-cbc/episode/perso/cbc_schitts_creek_season_06e01_thumbnail_v01.jpg?im=Resize=(Size)',
'duration': 1314,
'thumbnail': r're:https://images\.radio-canada\.ca/[^#?]+/cbc_schitts_creek_season_06e01_thumbnail_v01\.jpg',
'duration': 1324,
'categories': ['comedy'],
'series': 'Schitt\'s Creek',
'season': 'Season 6',
@@ -539,19 +536,21 @@ class CBCGemIE(InfoExtractor):
'episode': 'Smoke Signals',
'episode_number': 1,
'episode_id': 'schitts-creek/s06e01',
'upload_date': '20210618',
'timestamp': 1623988800,
'release_date': '20200107',
'release_timestamp': 1578427200,
},
'params': {'format': 'bv'},
'skip': 'Geo-restricted to Canada',
}, {
# This video requires an account in the browser, but works fine in yt-dlp
'url': 'https://gem.cbc.ca/media/schitts-creek/s01e01',
'md5': '297a9600f554f2258aed01514226a697',
'info_dict': {
'id': 'schitts-creek/s01e01',
'ext': 'mp4',
'title': 'The Cup Runneth Over',
'description': 'md5:9bca14ea49ab808097530eb05a29e797',
'thumbnail': 'https://images.radio-canada.ca/v1/synps-cbc/episode/perso/cbc_schitts_creek_season_01e01_thumbnail_v01.jpg?im=Resize=(Size)',
'thumbnail': r're:https://images\.radio-canada\.ca/[^#?]+/cbc_schitts_creek_season_01e01_thumbnail_v01\.jpg',
'series': 'Schitt\'s Creek',
'season_number': 1,
'season': 'Season 1',
@@ -560,9 +559,12 @@ class CBCGemIE(InfoExtractor):
'episode_id': 'schitts-creek/s01e01',
'duration': 1309,
'categories': ['comedy'],
'upload_date': '20210617',
'timestamp': 1623902400,
'release_date': '20151124',
'release_timestamp': 1448323200,
},
'params': {'format': 'bv'},
'skip': 'Geo-restricted to Canada',
}, {
'url': 'https://gem.cbc.ca/nadiyas-family-favourites/s01e01',
'only_matching': True,
@@ -631,38 +633,6 @@ class CBCGemIE(InfoExtractor):
return
self._claims_token = self.cache.load(self._NETRC_MACHINE, 'claims_token')
def _find_secret_formats(self, formats, video_id):
""" Find a valid video url and convert it to the secret variant """
base_format = next((f for f in formats if f.get('vcodec') != 'none'), None)
if not base_format:
return
base_url = re.sub(r'(Manifest\(.*?),filter=[\w-]+(.*?\))', r'\1\2', base_format['url'])
url = re.sub(r'(Manifest\(.*?),format=[\w-]+(.*?\))', r'\1\2', base_url)
secret_xml = self._download_xml(url, video_id, note='Downloading secret XML', fatal=False)
if not isinstance(secret_xml, xml.etree.ElementTree.Element):
return
for child in secret_xml:
if child.attrib.get('Type') != 'video':
continue
for video_quality in child:
bitrate = int_or_none(video_quality.attrib.get('Bitrate'))
if not bitrate or 'Index' not in video_quality.attrib:
continue
height = int_or_none(video_quality.attrib.get('MaxHeight'))
yield {
**base_format,
'format_id': join_nonempty('sec', height),
# Note: \g<1> is necessary instead of \1 since bitrate is a number
'url': re.sub(r'(QualityLevels\()\d+(\))', fr'\g<1>{bitrate}\2', base_url),
'width': int_or_none(video_quality.attrib.get('MaxWidth')),
'tbr': bitrate / 1000.0,
'height': height,
}
def _real_extract(self, url):
video_id = self._match_id(url)
video_info = self._download_json(
@@ -676,7 +646,6 @@ class CBCGemIE(InfoExtractor):
else:
headers = {}
m3u8_info = self._download_json(video_info['playSession']['url'], video_id, headers=headers)
m3u8_url = m3u8_info.get('url')
if m3u8_info.get('errorCode') == 1:
self.raise_geo_restricted(countries=['CA'])
@@ -685,9 +654,9 @@ class CBCGemIE(InfoExtractor):
elif m3u8_info.get('errorCode') != 0:
raise ExtractorError(f'{self.IE_NAME} said: {m3u8_info.get("errorCode")} - {m3u8_info.get("message")}')
formats = self._extract_m3u8_formats(m3u8_url, video_id, m3u8_id='hls')
formats = self._extract_m3u8_formats(
m3u8_info['url'], video_id, 'mp4', m3u8_id='hls', query={'manifestType': ''})
self._remove_duplicate_formats(formats)
formats.extend(self._find_secret_formats(formats, video_id))
for fmt in formats:
if fmt.get('vcodec') == 'none':
@@ -703,20 +672,21 @@ class CBCGemIE(InfoExtractor):
return {
'id': video_id,
'title': video_info['title'],
'description': video_info.get('description'),
'thumbnail': video_info.get('image'),
'series': video_info.get('series'),
'season_number': video_info.get('season'),
'season': f'Season {video_info.get("season")}',
'episode_number': video_info.get('episode'),
'episode': video_info.get('title'),
'episode_id': video_id,
'duration': video_info.get('duration'),
'categories': [video_info.get('category')],
'formats': formats,
'release_timestamp': video_info.get('airDate'),
'timestamp': video_info.get('availableDate'),
**traverse_obj(video_info, {
'title': ('title', {str}),
'episode': ('title', {str}),
'description': ('description', {str}),
'thumbnail': ('image', {url_or_none}),
'series': ('series', {str}),
'season_number': ('season', {int_or_none}),
'episode_number': ('episode', {int_or_none}),
'duration': ('duration', {int_or_none}),
'categories': ('category', {str}, all),
'release_timestamp': ('airDate', {int_or_none(scale=1000)}),
'timestamp': ('availableDate', {int_or_none(scale=1000)}),
}),
}

48
yt_dlp/extractor/cda.py
View File

@@ -12,6 +12,7 @@ from .common import InfoExtractor
from ..compat import compat_ord
from ..utils import (
ExtractorError,
OnDemandPagedList,
float_or_none,
int_or_none,
merge_dicts,
@@ -351,3 +352,50 @@ class CDAIE(InfoExtractor):
extract_format(webpage, resolution)
return merge_dicts(info_dict, info)
class CDAFolderIE(InfoExtractor):
_MAX_PAGE_SIZE = 36
_VALID_URL = r'https?://(?:www\.)?cda\.pl/(?P<channel>\w+)/folder/(?P<id>\d+)'
_TESTS = [
{
'url': 'https://www.cda.pl/domino264/folder/31188385',
'info_dict': {
'id': '31188385',
'title': 'SERIA DRUGA',
},
'playlist_mincount': 13,
},
{
'url': 'https://www.cda.pl/smiechawaTV/folder/2664592/vfilm',
'info_dict': {
'id': '2664592',
'title': 'VideoDowcipy - wszystkie odcinki',
},
'playlist_mincount': 71,
},
{
'url': 'https://www.cda.pl/DeliciousBeauty/folder/19129979/vfilm',
'info_dict': {
'id': '19129979',
'title': 'TESTY KOSMETYKÓW',
},
'playlist_mincount': 139,
}]
def _real_extract(self, url):
folder_id, channel = self._match_valid_url(url).group('id', 'channel')
webpage = self._download_webpage(url, folder_id)
def extract_page_entries(page):
webpage = self._download_webpage(
f'https://www.cda.pl/{channel}/folder/{folder_id}/vfilm/{page + 1}', folder_id,
f'Downloading page {page + 1}', expected_status=404)
items = re.findall(r'<a[^>]+href="/video/([0-9a-z]+)"', webpage)
for video_id in items:
yield self.url_result(f'https://www.cda.pl/video/{video_id}', CDAIE, video_id)
return self.playlist_result(
OnDemandPagedList(extract_page_entries, self._MAX_PAGE_SIZE),
folder_id, self._og_search_title(webpage))

4
yt_dlp/extractor/common.py
View File

@@ -333,7 +333,7 @@ class InfoExtractor:
like_count: Number of positive ratings of the video
dislike_count: Number of negative ratings of the video
repost_count: Number of reposts of the video
average_rating: Average rating give by users, the scale used depends on the webpage
average_rating: Average rating given by users, the scale used depends on the webpage
comment_count: Number of comments on the video
comments: A list of comments, each with one or more of the following
properties (all but one of text or html optional):
@@ -520,7 +520,7 @@ class InfoExtractor:
or _extract_from_webpage as necessary. While these are normally classmethods,
_extract_from_webpage is allowed to be an instance method.
_extract_from_webpage may raise self.StopExtraction() to stop further
_extract_from_webpage may raise self.StopExtraction to stop further
processing of the webpage and obtain exclusive rights to it. This is useful
when the extractor cannot reliably be matched using just the URL,
e.g. invidious/peertube instances

5
yt_dlp/extractor/funk.py
View File

@@ -3,7 +3,7 @@ from .nexx import NexxIE
class FunkIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.|origin\.)?funk\.net/(?:channel|playlist)/[^/]+/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)'
_VALID_URL = r'https?://(?:(?:www|origin|play)\.)?funk\.net/(?:channel|playlist)/[^/?#]+/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.funk.net/channel/ba-793/die-lustigsten-instrumente-aus-dem-internet-teil-2-1155821',
'md5': '8610449476156f338761a75391b0017d',
@@ -27,6 +27,9 @@ class FunkIE(InfoExtractor):
}, {
'url': 'https://www.funk.net/playlist/neuesteVideos/kameras-auf-dem-fusion-festival-1618699',
'only_matching': True,
}, {
'url': 'https://play.funk.net/playlist/neuesteVideos/george-floyd-wenn-die-polizei-toetet-der-fall-2004391',
'only_matching': True,
}]
def _real_extract(self, url):

73
yt_dlp/extractor/imgur.py
View File

@@ -37,7 +37,7 @@ class ImgurBaseIE(InfoExtractor):
class ImgurIE(ImgurBaseIE):
_VALID_URL = r'https?://(?:i\.)?imgur\.com/(?!(?:a|gallery|t|topic|r)/)(?P<id>[a-zA-Z0-9]+)'
_VALID_URL = r'https?://(?:i\.)?imgur\.com/(?!(?:a|gallery|t|topic|r)/)(?:[^/?#]+-)?(?P<id>[a-zA-Z0-9]+)'
_TESTS = [{
'url': 'https://imgur.com/A61SaA1',
@@ -54,6 +54,22 @@ class ImgurIE(ImgurBaseIE):
'like_count': int,
'thumbnail': 'https://i.imgur.com/A61SaA1h.jpg',
},
}, {
# Test with URL slug
'url': 'https://imgur.com/mrw-gifv-is-up-running-without-any-bugs-A61SaA1',
'info_dict': {
'id': 'A61SaA1',
'ext': 'mp4',
'title': 'MRW gifv is up and running without any bugs',
'timestamp': 1416446068,
'upload_date': '20141120',
'dislike_count': int,
'comment_count': int,
'release_timestamp': 1416446068,
'release_date': '20141120',
'like_count': int,
'thumbnail': 'https://i.imgur.com/A61SaA1h.jpg',
},
}, {
'url': 'https://i.imgur.com/A61SaA1.gifv',
'only_matching': True,
@@ -92,6 +108,7 @@ class ImgurIE(ImgurBaseIE):
'comment_count': int,
'release_timestamp': 1710491255,
'release_date': '20240315',
'thumbnail': 'https://i.imgur.com/zV03bd5h.jpg',
},
}]
@@ -208,7 +225,10 @@ class ImgurIE(ImgurBaseIE):
}), get_all=False),
'id': video_id,
'formats': formats,
'thumbnail': url_or_none(search('thumbnailUrl')),
'thumbnails': [{
'url': thumbnail_url,
'http_headers': {'Accept': '*/*'},
}] if (thumbnail_url := search(['thumbnailUrl', 'twitter:image', 'og:image'])) else None,
'http_headers': {'Accept': '*/*'},
}
@@ -252,17 +272,9 @@ class ImgurGalleryBaseIE(ImgurBaseIE):
class ImgurGalleryIE(ImgurGalleryBaseIE):
IE_NAME = 'imgur:gallery'
_VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:gallery|(?:t(?:opic)?|r)/[^/?#]+)/(?P<id>[a-zA-Z0-9]+)'
_VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:gallery|(?:t(?:opic)?|r)/[^/?#]+)/(?:[^/?#]+-)?(?P<id>[a-zA-Z0-9]+)'
_TESTS = [{
'url': 'http://imgur.com/gallery/Q95ko',
'info_dict': {
'id': 'Q95ko',
'title': 'Adding faces make every GIF better',
},
'playlist_count': 25,
'skip': 'Zoinks! You\'ve taken a wrong turn.',
}, {
# TODO: static images - replace with animated/video gallery
'url': 'http://imgur.com/topic/Aww/ll5Vk',
'only_matching': True,
@@ -280,7 +292,27 @@ class ImgurGalleryIE(ImgurGalleryBaseIE):
'release_timestamp': 1358554297,
'thumbnail': 'https://i.imgur.com/YcAQlkxh.jpg',
'release_date': '20130119',
'uploader_url': 'https://i.imgur.com/u3R4I2S_d.png?maxwidth=290&fidelity=grand',
'uploader_url': 'https://i.imgur.com/N5Flb2v_d.png?maxwidth=290&fidelity=grand',
'comment_count': int,
'dislike_count': int,
'like_count': int,
},
}, {
# Test with slug
'url': 'https://imgur.com/gallery/classic-steve-carell-gif-cracks-me-up-everytime-repost-downvotes-YcAQlkx',
'add_ies': ['Imgur'],
'info_dict': {
'id': 'YcAQlkx',
'ext': 'mp4',
'title': 'Classic Steve Carell gif...cracks me up everytime....damn the repost downvotes....',
'timestamp': 1358554297,
'upload_date': '20130119',
'uploader_id': '1648642',
'uploader': 'wittyusernamehere',
'release_timestamp': 1358554297,
'release_date': '20130119',
'thumbnail': 'https://i.imgur.com/YcAQlkxh.jpg',
'uploader_url': 'https://i.imgur.com/N5Flb2v_d.png?maxwidth=290&fidelity=grand',
'comment_count': int,
'dislike_count': int,
'like_count': int,
@@ -317,6 +349,13 @@ class ImgurGalleryIE(ImgurGalleryBaseIE):
'title': 'Penguins !',
},
'playlist_count': 3,
}, {
'url': 'https://imgur.com/t/unmuted/penguins-penguins-6lAn9VQ',
'info_dict': {
'id': '6lAn9VQ',
'title': 'Penguins !',
},
'playlist_count': 3,
}, {
'url': 'https://imgur.com/t/unmuted/kx2uD3C',
'add_ies': ['Imgur'],
@@ -357,7 +396,7 @@ class ImgurGalleryIE(ImgurGalleryBaseIE):
class ImgurAlbumIE(ImgurGalleryBaseIE):
IE_NAME = 'imgur:album'
_VALID_URL = r'https?://(?:i\.)?imgur\.com/a/(?P<id>[a-zA-Z0-9]+)'
_VALID_URL = r'https?://(?:i\.)?imgur\.com/a/(?:[^/?#]+-)?(?P<id>[a-zA-Z0-9]+)'
_GALLERY = False
_TESTS = [{
# TODO: only static images - replace with animated/video gallery
@@ -372,6 +411,14 @@ class ImgurAlbumIE(ImgurGalleryBaseIE):
'title': 'enen-no-shouboutai',
},
'playlist_count': 2,
}, {
# Test with URL slug
'url': 'https://imgur.com/a/enen-no-shouboutai-iX265HX',
'info_dict': {
'id': 'iX265HX',
'title': 'enen-no-shouboutai',
},
'playlist_count': 2,
}, {
'url': 'https://imgur.com/a/8pih2Ed',
'info_dict': {

26
yt_dlp/extractor/mitele.py
View File

@@ -1,14 +1,13 @@
from .telecinco import TelecincoIE
from .telecinco import TelecincoBaseIE
from ..utils import (
int_or_none,
parse_iso8601,
)
class MiTeleIE(TelecincoIE): # XXX: Do not subclass from concrete IE
class MiTeleIE(TelecincoBaseIE):
IE_DESC = 'mitele.es'
_VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/)+(?P<id>[^/]+)/player'
_TESTS = [{
'url': 'http://www.mitele.es/programas-tv/diario-de/57b0dfb9c715da65618b4afa/player',
'info_dict': {
@@ -27,6 +26,7 @@ class MiTeleIE(TelecincoIE): # XXX: Do not subclass from concrete IE
'timestamp': 1471209401,
'upload_date': '20160814',
},
'skip': 'HTTP Error 404 Not Found',
}, {
# no explicit title
'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/57b0de3dc915da14058b4876/player',
@@ -49,6 +49,26 @@ class MiTeleIE(TelecincoIE): # XXX: Do not subclass from concrete IE
'params': {
'skip_download': True,
},
'skip': 'HTTP Error 404 Not Found',
}, {
'url': 'https://www.mitele.es/programas-tv/horizonte/temporada-5/programa-171-40_013480051/player/',
'info_dict': {
'id': '7adbe22e-cd41-4787-afa4-36f3da7c2c6f',
'ext': 'mp4',
'title': 'Horizonte Temporada 5 Programa 171',
'description': 'md5:97f1fb712c5ac27e5693a8b3c5c0c6e3',
'episode': 'Las Zonas de Bajas Emisiones, a debate',
'episode_number': 171,
'season': 'Season 5',
'season_number': 5,
'series': 'Horizonte',
'duration': 7012,
'upload_date': '20240927',
'timestamp': 1727416450,
'thumbnail': 'https://album.mediaset.es/eimg/2024/09/27/horizonte-171_9f02.jpg',
'age_limit': 12,
},
'params': {'geo_bypass_country': 'ES'},
}, {
'url': 'http://www.mitele.es/series-online/la-que-se-avecina/57aac5c1c915da951a8b45ed/player',
'only_matching': True,

2
yt_dlp/extractor/nexx.py
View File

@@ -371,7 +371,7 @@ class NexxIE(InfoExtractor):
# not all videos work via arc, e.g. nexx:741:1269984
if not video:
# Reverse engineered from JS code (see getDeviceID function)
device_id = f'{random.randint(1, 4)}:{int(time.time())}:{random.randint(1e4, 99999)}{random.randint(1, 9)}'
device_id = f'{random.randint(1, 4)}:{int(time.time())}:{random.randint(10000, 99999)}{random.randint(1, 9)}'
result = self._call_api(domain_id, 'session/init', video_id, data={
'nxp_devh': device_id,

31
yt_dlp/extractor/substack.py
View File

@@ -2,7 +2,13 @@ import re
import urllib.parse
from .common import InfoExtractor
from ..utils import js_to_json, str_or_none, traverse_obj
from ..networking import HEADRequest
from ..utils import (
determine_ext,
js_to_json,
str_or_none,
)
from ..utils.traversal import traverse_obj
class SubstackIE(InfoExtractor):
@@ -43,6 +49,19 @@ class SubstackIE(InfoExtractor):
'uploader': "Andrew Zimmern's Spilled Milk ",
'uploader_id': '577659',
},
}, {
# Podcast that needs its file extension resolved to mp3
'url': 'https://persuasion1.substack.com/p/summers',
'md5': '1456a755d46084744facdfac9edf900f',
'info_dict': {
'id': '141970405',
'ext': 'mp3',
'title': 'Larry Summers on What Went Wrong on Campus',
'description': 'Yascha Mounk and Larry Summers also discuss the promise and perils of artificial intelligence.',
'thumbnail': r're:https://substackcdn\.com/image/.+\.jpeg',
'uploader': 'Persuasion',
'uploader_id': '61579',
},
}]
@classmethod
@@ -89,7 +108,15 @@ class SubstackIE(InfoExtractor):
post_type = webpage_info['post']['type']
formats, subtitles = [], {}
if post_type == 'podcast':
formats, subtitles = [{'url': webpage_info['post']['podcast_url']}], {}
fmt = {'url': webpage_info['post']['podcast_url']}
if not determine_ext(fmt['url'], default_ext=None):
# The redirected format URL expires but the original URL doesn't,
# so we only want to extract the extension from this request
fmt['ext'] = determine_ext(self._request_webpage(
HEADRequest(fmt['url']), display_id,
'Resolving podcast file extension',
'Podcast URL is invalid').url)
formats.append(fmt)
elif post_type == 'video':
formats, subtitles = self._extract_video_formats(webpage_info['post']['videoUpload']['id'], canonical_url)
else:

140
yt_dlp/extractor/telecinco.py
View File

@@ -2,15 +2,69 @@ import json
import re
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
clean_html,
int_or_none,
join_nonempty,
str_or_none,
try_get,
traverse_obj,
update_url,
url_or_none,
)
class TelecincoIE(InfoExtractor):
class TelecincoBaseIE(InfoExtractor):
def _parse_content(self, content, url):
video_id = content['dataMediaId']
config = self._download_json(
content['dataConfig'], video_id, 'Downloading config JSON')
services = config['services']
caronte = self._download_json(services['caronte'], video_id)
if traverse_obj(caronte, ('dls', 0, 'drm', {bool})):
self.report_drm(video_id)
stream = caronte['dls'][0]['stream']
headers = {
'Referer': url,
'Origin': re.match(r'https?://[^/]+', url).group(0),
}
geo_headers = {**headers, **self.geo_verification_headers()}
try:
cdn = self._download_json(
caronte['cerbero'], video_id, data=json.dumps({
'bbx': caronte['bbx'],
'gbx': self._download_json(services['gbx'], video_id)['gbx'],
}).encode(), headers={
'Content-Type': 'application/json',
**geo_headers,
})['tokens']['1']['cdn']
except ExtractorError as error:
if isinstance(error.cause, HTTPError) and error.cause.status == 403:
error_code = traverse_obj(
self._webpage_read_content(error.cause.response, caronte['cerbero'], video_id, fatal=False),
({json.loads}, 'code', {int}))
if error_code == 4038:
self.raise_geo_restricted(countries=['ES'])
raise
formats = self._extract_m3u8_formats(
update_url(stream, query=cdn), video_id, 'mp4', m3u8_id='hls', headers=geo_headers)
return {
'id': video_id,
'title': traverse_obj(config, ('info', 'title', {str})),
'formats': formats,
'thumbnail': (traverse_obj(content, ('dataPoster', {url_or_none}))
or traverse_obj(config, 'poster', 'imageUrl', expected_type=url_or_none)),
'duration': traverse_obj(content, ('dataDuration', {int_or_none})),
'http_headers': headers,
}
class TelecincoIE(TelecincoBaseIE):
IE_DESC = 'telecinco.es, cuatro.com and mediaset.es'
_VALID_URL = r'https?://(?:www\.)?(?:telecinco\.es|cuatro\.com|mediaset\.es)/(?:[^/]+/)+(?P<id>.+?)\.html'
@@ -30,6 +84,7 @@ class TelecincoIE(InfoExtractor):
'duration': 662,
},
}],
'skip': 'HTTP Error 410 Gone',
}, {
'url': 'http://www.cuatro.com/deportes/futbol/barcelona/Leo_Messi-Champions-Roma_2_2052780128.html',
'md5': 'c86fe0d99e3bdb46b7950d38bf6ef12a',
@@ -40,23 +95,24 @@ class TelecincoIE(InfoExtractor):
'description': 'md5:a62ecb5f1934fc787107d7b9a2262805',
'duration': 79,
},
'skip': 'Redirects to main page',
}, {
'url': 'http://www.mediaset.es/12meses/campanas/doylacara/conlatratanohaytrato/Ayudame-dar-cara-trata-trato_2_1986630220.html',
'md5': 'eddb50291df704ce23c74821b995bcac',
'md5': '5ce057f43f30b634fbaf0f18c71a140a',
'info_dict': {
'id': 'aywerkD2Sv1vGNqq9b85Q2',
'ext': 'mp4',
'title': '#DOYLACARA. Con la trata no hay trato',
'description': 'md5:2771356ff7bfad9179c5f5cd954f1477',
'duration': 50,
'thumbnail': 'https://album.mediaset.es/eimg/2017/11/02/1tlQLO5Q3mtKT24f3EaC24.jpg',
},
}, {
# video in opening's content
'url': 'https://www.telecinco.es/vivalavida/fiorella-sobrina-edmundo-arrocet-entrevista_18_2907195140.html',
'info_dict': {
'id': '2907195140',
'id': '1691427',
'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"',
'description': 'md5:73f340a7320143d37ab895375b2bf13a',
'description': r're:Fiorella, la sobrina de Edmundo Arrocet, concedió .{727}',
},
'playlist': [{
'md5': 'adb28c37238b675dad0f042292f209a7',
@@ -65,6 +121,7 @@ class TelecincoIE(InfoExtractor):
'ext': 'mp4',
'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"',
'duration': 1015,
'thumbnail': 'https://album.mediaset.es/eimg/2020/02/29/5opaC37lUhKlZ7FoDhiVC.jpg',
},
}],
'params': {
@@ -81,66 +138,29 @@ class TelecincoIE(InfoExtractor):
'only_matching': True,
}]
def _parse_content(self, content, url):
video_id = content['dataMediaId']
config = self._download_json(
content['dataConfig'], video_id, 'Downloading config JSON')
title = config['info']['title']
services = config['services']
caronte = self._download_json(services['caronte'], video_id)
stream = caronte['dls'][0]['stream']
headers = self.geo_verification_headers()
headers.update({
'Content-Type': 'application/json;charset=UTF-8',
'Origin': re.match(r'https?://[^/]+', url).group(0),
})
cdn = self._download_json(
caronte['cerbero'], video_id, data=json.dumps({
'bbx': caronte['bbx'],
'gbx': self._download_json(services['gbx'], video_id)['gbx'],
}).encode(), headers=headers)['tokens']['1']['cdn']
formats = self._extract_m3u8_formats(
stream + '?' + cdn, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': content.get('dataPoster') or config.get('poster', {}).get('imageUrl'),
'duration': int_or_none(content.get('dataDuration')),
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
article = self._parse_json(self._search_regex(
r'window\.\$REACTBASE_STATE\.article(?:_multisite)?\s*=\s*({.+})',
webpage, 'article'), display_id)['article']
title = article.get('title')
description = clean_html(article.get('leadParagraph')) or ''
article = self._search_json(
r'window\.\$REACTBASE_STATE\.article(?:_multisite)?\s*=',
webpage, 'article', display_id)['article']
description = traverse_obj(article, ('leadParagraph', {clean_html}, filter))
if article.get('editorialType') != 'VID':
entries = []
body = [article.get('opening')]
body.extend(try_get(article, lambda x: x['body'], list) or [])
for p in body:
if not isinstance(p, dict):
continue
content = p.get('content')
if not content:
continue
for p in traverse_obj(article, ((('opening', all), 'body'), lambda _, v: v['content'])):
content = p['content']
type_ = p.get('type')
if type_ == 'paragraph':
content_str = str_or_none(content)
if content_str:
description += content_str
continue
if type_ == 'video' and isinstance(content, dict):
if type_ == 'paragraph' and isinstance(content, str):
description = join_nonempty(description, content, delim='')
elif type_ == 'video' and isinstance(content, dict):
entries.append(self._parse_content(content, url))
return self.playlist_result(
entries, str_or_none(article.get('id')), title, description)
content = article['opening']['content']
info = self._parse_content(content, url)
info.update({
'description': description,
})
entries, str_or_none(article.get('id')),
traverse_obj(article, ('title', {str})), clean_html(description))
info = self._parse_content(article['opening']['content'], url)
info['description'] = description
return info

2
yt_dlp/extractor/tubetugraz.py
View File

@@ -236,7 +236,7 @@ class TubeTuGrazSeriesIE(TubeTuGrazBaseIE):
},
},
],
'min_playlist_count': 4,
'playlist_mincount': 4,
}]
def _real_extract(self, url):

5
yt_dlp/extractor/tubitv.py
View File

@@ -6,6 +6,7 @@ from ..utils import (
ExtractorError,
int_or_none,
js_to_json,
strip_or_none,
traverse_obj,
url_or_none,
urlencode_postdata,
@@ -132,12 +133,12 @@ class TubiTvIE(InfoExtractor):
return {
'id': video_id,
'title': title,
'title': strip_or_none(title),
'formats': formats,
'subtitles': subtitles,
'season_number': int_or_none(season_number),
'episode_number': int_or_none(episode_number),
'episode': episode_title,
'episode': strip_or_none(episode_title),
**traverse_obj(video_data, {
'description': ('description', {str}),
'duration': ('duration', {int_or_none}),

5
yt_dlp/extractor/twitter.py
View File

@@ -934,14 +934,13 @@ class TwitterIE(TwitterBaseIE):
'uploader_id': 'MoniqueCamarra',
'live_status': 'was_live',
'release_timestamp': 1658417414,
'description': 'md5:acce559345fd49f129c20dbcda3f1201',
'description': r're:Twitter Space participated by Sergej Sumlenny.+',
'timestamp': 1658407771,
'release_date': '20220721',
'upload_date': '20220721',
},
'add_ie': ['TwitterSpaces'],
'params': {'skip_download': 'm3u8'},
'skip': 'Requires authentication',
}, {
# URL specifies video number but --yes-playlist
'url': 'https://twitter.com/CTVJLaidlaw/status/1600649710662213632/video/1',
@@ -1856,8 +1855,6 @@ class TwitterSpacesIE(TwitterBaseIE):
def _real_extract(self, url):
space_id = self._match_id(url)
if not self.is_logged_in:
self.raise_login_required('Twitter Spaces require authentication')
space_data = self._call_graphql_api('HPEisOmj1epUNLCWTYhUWw/AudioSpaceById', space_id)['audioSpace']
if not space_data:
raise ExtractorError('Twitter Space not found', expected=True)

2
yt_dlp/extractor/ustream.py
View File

@@ -73,7 +73,7 @@ class UstreamIE(InfoExtractor):
def num_to_hex(n):
return hex(n)[2:]
rnd = random.randrange
rnd = lambda x: random.randrange(int(x))
if not extra_note:
extra_note = ''

5
yt_dlp/extractor/veoh.py
View File

@@ -8,7 +8,8 @@ from ..utils import (
int_or_none,
parse_duration,
qualities,
try_get,
remove_start,
strip_or_none,
)
@@ -108,7 +109,7 @@ class VeohIE(InfoExtractor):
categories = metadata.get('categoryPath')
if not categories:
category = try_get(video, lambda x: x['category'].strip().removeprefix('category_'))
category = remove_start(strip_or_none(video.get('category')), 'category_')
categories = [category] if category else None
tags = video.get('tags')

359
yt_dlp/extractor/youtube.py
View File

@@ -22,7 +22,7 @@ import urllib.parse
from .common import InfoExtractor, SearchInfoExtractor
from .openload import PhantomJSwrapper
from ..jsinterp import JSInterpreter
from ..networking.exceptions import HTTPError, network_exceptions
from ..networking.exceptions import HTTPError, TransportError, network_exceptions
from ..utils import (
NO_DEFAULT,
ExtractorError,
@@ -55,6 +55,7 @@ from ..utils import (
str_or_none,
str_to_int,
strftime_or_none,
time_seconds,
traverse_obj,
try_call,
try_get,
@@ -114,6 +115,7 @@ INNERTUBE_CLIENTS = {
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
},
# This client now requires sign-in for every video
'web_creator': {
'INNERTUBE_CONTEXT': {
'client': {
@@ -153,6 +155,7 @@ INNERTUBE_CLIENTS = {
'REQUIRE_JS_PLAYER': False,
'REQUIRE_PO_TOKEN': True,
},
# This client now requires sign-in for every video
'android_creator': {
'INNERTUBE_CONTEXT': {
'client': {
@@ -200,21 +203,6 @@ INNERTUBE_CLIENTS = {
'REQUIRE_JS_PLAYER': False,
'PLAYER_PARAMS': '2AMB',
},
# This client only has legacy formats and storyboards
'android_producer': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_PRODUCER',
'clientVersion': '0.111.1',
'androidSdkVersion': 30,
'userAgent': 'com.google.android.apps.youtube.producer/0.111.1 (Linux; U; Android 11) gzip',
'osName': 'Android',
'osVersion': '11',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 91,
'REQUIRE_JS_PLAYER': False,
},
# iOS clients have HLS live streams. Setting device model to get 60fps formats.
# See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
'ios': {
@@ -247,6 +235,7 @@ INNERTUBE_CLIENTS = {
'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
'REQUIRE_JS_PLAYER': False,
},
# This client now requires sign-in for every video
'ios_creator': {
'INNERTUBE_CONTEXT': {
'client': {
@@ -282,8 +271,9 @@ INNERTUBE_CLIENTS = {
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 7,
},
# This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
# See: https://github.com/zerodytrash/YouTube-Internal-Clients
# This client now requires sign-in for every video
# It was previously an age-gate workaround for videos that were `playable_in_embed`
# It may still be useful if signed into an EU account that is not age-verified
'tv_embedded': {
'INNERTUBE_CONTEXT': {
'client': {
@@ -526,6 +516,8 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
_YT_HANDLE_RE = r'@[\w.-]{3,30}' # https://support.google.com/youtube/answer/11585688?hl=en
_YT_CHANNEL_UCID_RE = r'UC[\w-]{22}'
_NETRC_MACHINE = 'youtube'
def ucid_or_none(self, ucid):
return self._search_regex(rf'^({self._YT_CHANNEL_UCID_RE})$', ucid, 'UC-id', default=None)
@@ -584,9 +576,213 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
self._initialize_consent()
self._check_login_required()
def _perform_login(self, username, password):
auth_type, _, user = (username or '').partition('+')
if auth_type != 'oauth':
raise ExtractorError(self._youtube_login_hint, expected=True)
self._initialize_oauth(user, password)
'''
OAuth 2.0 Device Authorization Grant flow, used by the YouTube TV client (youtube.com/tv).
For more information regarding OAuth 2.0 and the Device Authorization Grant flow in general, see:
- https://developers.google.com/identity/protocols/oauth2/limited-input-device
- https://accounts.google.com/.well-known/openid-configuration
- https://www.rfc-editor.org/rfc/rfc8628
- https://www.rfc-editor.org/rfc/rfc6749
Note: The official client appears to use a proxied version of the oauth2 endpoints on youtube.com/o/oauth2,
which applies some modifications to the response (such as returning errors as 200 OK).
Since the client works with the standard API, we will use that as it is well-documented.
'''
_OAUTH_PROFILE = None
_OAUTH_ACCESS_TOKEN_CACHE = {}
_OAUTH_DISPLAY_ID = 'oauth'
# YouTube TV (TVHTML5) client. You can find these at youtube.com/tv
_OAUTH_CLIENT_ID = '861556708454-d6dlm3lh05idd8npek18k6be8ba3oc68.apps.googleusercontent.com'
_OAUTH_CLIENT_SECRET = 'SboVhoG9s0rNafixCSGGKXAT'
_OAUTH_SCOPE = 'http://gdata.youtube.com https://www.googleapis.com/auth/youtube-paid-content'
# From https://accounts.google.com/.well-known/openid-configuration
# Technically, these should be fetched dynamically and not hard-coded.
# However, as these endpoints rarely change, we can risk saving an extra request for every invocation.
_OAUTH_DEVICE_AUTHORIZATION_ENDPOINT = 'https://oauth2.googleapis.com/device/code'
_OAUTH_TOKEN_ENDPOINT = 'https://oauth2.googleapis.com/token'
@property
def _oauth_cache_key(self):
return f'oauth_refresh_token_{self._OAUTH_PROFILE}'
def _read_oauth_error_response(self, response):
return traverse_obj(
self._webpage_read_content(response, self._OAUTH_TOKEN_ENDPOINT, self._OAUTH_DISPLAY_ID, fatal=False),
({json.loads}, 'error', {str}))
def _set_oauth_info(self, token_response):
YoutubeBaseInfoExtractor._OAUTH_ACCESS_TOKEN_CACHE.setdefault(self._OAUTH_PROFILE, {}).update({
'access_token': token_response['access_token'],
'token_type': token_response['token_type'],
'expiry': time_seconds(
seconds=traverse_obj(token_response, ('expires_in', {float_or_none}), default=300) - 10),
})
refresh_token = traverse_obj(token_response, ('refresh_token', {str}))
if refresh_token:
self.cache.store(self._NETRC_MACHINE, self._oauth_cache_key, refresh_token)
YoutubeBaseInfoExtractor._OAUTH_ACCESS_TOKEN_CACHE[self._OAUTH_PROFILE]['refresh_token'] = refresh_token
def _initialize_oauth(self, user, refresh_token):
self._OAUTH_PROFILE = user or 'default'
if self._OAUTH_PROFILE in YoutubeBaseInfoExtractor._OAUTH_ACCESS_TOKEN_CACHE:
self.write_debug(f'{self._OAUTH_DISPLAY_ID}: Using cached access token for profile "{self._OAUTH_PROFILE}"')
return
YoutubeBaseInfoExtractor._OAUTH_ACCESS_TOKEN_CACHE[self._OAUTH_PROFILE] = {}
if refresh_token:
refresh_token = refresh_token.strip('\'') or None
# Allow refresh token passed to initialize cache
if refresh_token:
self.cache.store(self._NETRC_MACHINE, self._oauth_cache_key, refresh_token)
refresh_token = refresh_token or self.cache.load(self._NETRC_MACHINE, self._oauth_cache_key)
if refresh_token:
YoutubeBaseInfoExtractor._OAUTH_ACCESS_TOKEN_CACHE[self._OAUTH_PROFILE]['refresh_token'] = refresh_token
try:
token_response = self._refresh_token(refresh_token)
except ExtractorError as e:
error_msg = str(e.orig_msg).replace('Failed to refresh access token: ', '')
self.report_warning(f'{self._OAUTH_DISPLAY_ID}: Failed to refresh access token: {error_msg}')
token_response = self._oauth_authorize
else:
token_response = self._oauth_authorize
self._set_oauth_info(token_response)
self.write_debug(f'{self._OAUTH_DISPLAY_ID}: Logged in using profile "{self._OAUTH_PROFILE}"')
def _refresh_token(self, refresh_token):
try:
token_response = self._download_json(
self._OAUTH_TOKEN_ENDPOINT,
video_id=self._OAUTH_DISPLAY_ID,
note='Refreshing access token',
data=json.dumps({
'client_id': self._OAUTH_CLIENT_ID,
'client_secret': self._OAUTH_CLIENT_SECRET,
'refresh_token': refresh_token,
'grant_type': 'refresh_token',
}).encode(),
headers={'Content-Type': 'application/json'})
except ExtractorError as e:
if isinstance(e.cause, HTTPError):
error = self._read_oauth_error_response(e.cause.response)
if error == 'invalid_grant':
# RFC6749 § 5.2
raise ExtractorError(
'Failed to refresh access token: Refresh token is invalid, revoked, or expired (invalid_grant)',
expected=True, video_id=self._OAUTH_DISPLAY_ID)
raise ExtractorError(
f'Failed to refresh access token: Authorization server returned error {error}',
video_id=self._OAUTH_DISPLAY_ID)
raise
return token_response
@property
def _oauth_authorize(self):
code_response = self._download_json(
self._OAUTH_DEVICE_AUTHORIZATION_ENDPOINT,
video_id=self._OAUTH_DISPLAY_ID,
note='Initializing authorization flow',
data=json.dumps({
'client_id': self._OAUTH_CLIENT_ID,
'scope': self._OAUTH_SCOPE,
}).encode(),
headers={'Content-Type': 'application/json'})
verification_url = traverse_obj(code_response, ('verification_url', {str}))
user_code = traverse_obj(code_response, ('user_code', {str}))
if not verification_url or not user_code:
raise ExtractorError(
'Authorization server did not provide verification_url or user_code', video_id=self._OAUTH_DISPLAY_ID)
# note: The whitespace is intentional
self.to_screen(
f'{self._OAUTH_DISPLAY_ID}: To give yt-dlp access to your account, '
f'go to {verification_url} and enter code {user_code}')
# RFC8628 § 3.5: default poll interval is 5 seconds if not provided
poll_interval = traverse_obj(code_response, ('interval', {int}), default=5)
for retry in self.RetryManager():
while True:
try:
token_response = self._download_json(
self._OAUTH_TOKEN_ENDPOINT,
video_id=self._OAUTH_DISPLAY_ID,
note=False,
errnote='Failed to request access token',
data=json.dumps({
'client_id': self._OAUTH_CLIENT_ID,
'client_secret': self._OAUTH_CLIENT_SECRET,
'device_code': code_response['device_code'],
'grant_type': 'urn:ietf:params:oauth:grant-type:device_code',
}).encode(),
headers={'Content-Type': 'application/json'})
except ExtractorError as e:
if isinstance(e.cause, TransportError):
retry.error = e
break
elif isinstance(e.cause, HTTPError):
error = self._read_oauth_error_response(e.cause.response)
if not error:
retry.error = e
break
if error == 'authorization_pending':
time.sleep(poll_interval)
continue
elif error == 'expired_token':
raise ExtractorError(
'Authorization timed out', expected=True, video_id=self._OAUTH_DISPLAY_ID)
elif error == 'access_denied':
raise ExtractorError(
'You denied access to an account', expected=True, video_id=self._OAUTH_DISPLAY_ID)
elif error == 'slow_down':
# RFC8628 § 3.5: add 5 seconds to the poll interval
poll_interval += 5
time.sleep(poll_interval)
continue
else:
raise ExtractorError(
f'Authorization server returned an error when fetching access token: {error}',
video_id=self._OAUTH_DISPLAY_ID)
raise
return token_response
def _update_oauth(self):
token = YoutubeBaseInfoExtractor._OAUTH_ACCESS_TOKEN_CACHE.get(self._OAUTH_PROFILE)
if token is None or token['expiry'] > time.time():
return
self._set_oauth_info(self._refresh_token(token['refresh_token']))
@property
def _youtube_login_hint(self):
return ('Use --username=oauth[+PROFILE] --password="" to log in using oauth, '
f'or else u{self._login_hint(method="cookies")[1:]}. '
'See https://github.com/yt-dlp/yt-dlp/wiki/Extractors#logging-in-with-oauth for more on how to use oauth. '
'See https://github.com/yt-dlp/yt-dlp/wiki/Extractors#exporting-youtube-cookies for help with cookies')
def _check_login_required(self):
if self._LOGIN_REQUIRED and not self._cookies_passed:
self.raise_login_required('Login details are needed to download this content', method='cookies')
if self._LOGIN_REQUIRED and not self.is_authenticated:
self.raise_login_required(
f'Login details are needed to download this content. {self._youtube_login_hint}', method=None)
_YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
_YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
@@ -685,17 +881,6 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
if session_index is not None:
return session_index
# Deprecated?
def _extract_identity_token(self, ytcfg=None, webpage=None):
if ytcfg:
token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
if token:
return token
if webpage:
return self._search_regex(
r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
'identity token', default=None, fatal=False)
def _data_sync_id_to_delegated_session_id(self, data_sync_id):
if not data_sync_id:
return
@@ -742,7 +927,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
@functools.cached_property
def is_authenticated(self):
return bool(self._generate_sapisidhash_header())
return self._OAUTH_PROFILE or bool(self._generate_sapisidhash_header())
def extract_ytcfg(self, video_id, webpage):
if not webpage:
@@ -752,21 +937,21 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
default='{}'), video_id, fatal=False) or {}
def generate_api_headers(
self, *, ytcfg=None, account_syncid=None, session_index=None,
visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
def _generate_oauth_headers(self):
self._update_oauth()
oauth_token = YoutubeBaseInfoExtractor._OAUTH_ACCESS_TOKEN_CACHE.get(self._OAUTH_PROFILE)
if not oauth_token:
return {}
origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
headers = {
'X-YouTube-Client-Name': str(
self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
'Origin': origin,
'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client),
return {
'Authorization': f'{oauth_token["token_type"]} {oauth_token["access_token"]}',
}
def _generate_cookie_auth_headers(self, *, ytcfg=None, account_syncid=None, session_index=None, origin=None, **kwargs):
headers = {}
account_syncid = account_syncid or self._extract_account_syncid(ytcfg)
if account_syncid:
headers['X-Goog-PageId'] = account_syncid
if session_index is None:
session_index = self._extract_session_index(ytcfg)
if account_syncid or session_index is not None:
@@ -776,8 +961,29 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
if auth is not None:
headers['Authorization'] = auth
headers['X-Origin'] = origin
return headers
def generate_api_headers(
self, *, ytcfg=None, account_syncid=None, session_index=None,
visitor_data=None, api_hostname=None, default_client='web', **kwargs):
origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
headers = {
'X-YouTube-Client-Name': str(
self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
'Origin': origin,
'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client),
**self._generate_oauth_headers(),
**self._generate_cookie_auth_headers(ytcfg=ytcfg, account_syncid=account_syncid, session_index=session_index, origin=origin),
}
return filter_dict(headers)
def _generate_webpage_headers(self):
return self._generate_oauth_headers()
def _download_ytcfg(self, client, video_id):
url = {
'web': 'https://www.youtube.com',
@@ -787,7 +993,8 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
if not url:
return {}
webpage = self._download_webpage(
url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config',
headers=self._generate_webpage_headers())
return self.extract_ytcfg(video_id, webpage) or {}
@staticmethod
@@ -1525,6 +1732,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'heatmap': 'count:100',
'timestamp': 1401991663,
},
'skip': 'Age-restricted; requires authentication',
},
{
'note': 'Age-gate video with embed allowed in public site',
@@ -1555,6 +1763,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'comment_count': int,
'channel_is_verified': True,
},
'skip': 'Age-restricted; requires authentication',
},
{
'note': 'Age-gate video embedable only with clientScreen=EMBED',
@@ -1585,6 +1794,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'uploader_id': '@ProjektMelody',
'timestamp': 1577508724,
},
'skip': 'Age-restricted; requires authentication',
},
{
'note': 'Non-Agegated non-embeddable video',
@@ -2356,6 +2566,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'channel_is_verified': True,
'timestamp': 1405513526,
},
'skip': 'Age-restricted; requires authentication',
},
{
# restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
@@ -2726,6 +2937,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'timestamp': 1577508724,
},
'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'},
'skip': 'Age-restricted; requires authentication',
},
{
'url': 'https://www.youtube.com/live/qVv6vCqciTM',
@@ -3047,7 +3259,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
code = self._download_webpage(
player_url, video_id, fatal=fatal,
note='Downloading player ' + player_id,
errnote=f'Download of {player_url} failed')
errnote=f'Download of {player_url} failed',
headers=self._generate_webpage_headers())
if code:
self._code_cache[player_id] = code
return self._code_cache.get(player_id)
@@ -3330,7 +3543,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
self._download_webpage(
url, video_id, f'Marking {label}watched',
'Unable to mark watched', fatal=False)
'Unable to mark watched', fatal=False,
headers=self._generate_webpage_headers())
@classmethod
def _extract_from_webpage(cls, url, webpage):
@@ -3953,26 +4167,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
else:
prs.append(pr)
# tv_embedded can work around age-gate and age-verification IF the video is embeddable
if self._is_agegated(pr) and variant != 'tv_embedded':
append_client(f'tv_embedded.{base_client}')
# Unauthenticated users will only get tv_embedded client formats if age-gated
if self._is_agegated(pr) and not self.is_authenticated:
self.to_screen(
f'{video_id}: This video is age-restricted; some formats may be missing '
f'without authentication. {self._login_hint()}', only_once=True)
# EU countries require age-verification for accounts to access age-restricted videos
# If account is not age-verified, _is_agegated() will be truthy for non-embedded clients
# If embedding is disabled for the video, _is_unplayable() will be truthy for tv_embedded
embedding_is_disabled = variant == 'tv_embedded' and self._is_unplayable(pr)
if self.is_authenticated and (self._is_agegated(pr) or embedding_is_disabled):
if self.is_authenticated and self._is_agegated(pr):
self.to_screen(
f'{video_id}: This video is age-restricted and YouTube is requiring '
'account age-verification; some formats may be missing', only_once=True)
# web_creator and mediaconnect can work around the age-verification requirement
# _producer, _testsuite, & _vr variants can also work around age-verification
# _testsuite & _vr variants can also work around age-verification
# tv_embedded may(?) still work around age-verification if the video is embeddable
append_client('web_creator', 'mediaconnect')
prs.extend(deprioritized_prs)
@@ -4322,7 +4525,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if pp:
query['pp'] = pp
webpage = self._download_webpage(
webpage_url, video_id, fatal=False, query=query)
webpage_url, video_id, fatal=False, query=query, headers=self._generate_webpage_headers())
master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
@@ -4701,11 +4904,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
headers=self.generate_api_headers(ytcfg=master_ytcfg),
note='Downloading initial data API JSON')
COMMENTS_SECTION_IDS = ('comment-item-section', 'engagement-panel-comments-section')
info['comment_count'] = traverse_obj(initial_data, (
'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount',
), (
'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] in COMMENTS_SECTION_IDS,
'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo',
), expected_type=self._get_count, get_all=False)
@@ -5609,7 +5813,7 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
webpage, data = None, None
for retry in self.RetryManager(fatal=fatal):
try:
webpage = self._download_webpage(url, item_id, note='Downloading webpage')
webpage = self._download_webpage(url, item_id, note='Downloading webpage', headers=self._generate_webpage_headers())
data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
except ExtractorError as e:
if isinstance(e.cause, network_exceptions):
@@ -6983,7 +7187,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
raise ExtractorError('Unable to recognize tab page')
class YoutubePlaylistIE(InfoExtractor):
class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
IE_DESC = 'YouTube playlists'
_VALID_URL = r'''(?x)(?:
(?:https?://)?
@@ -7097,7 +7301,7 @@ class YoutubePlaylistIE(InfoExtractor):
return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
class YoutubeYtBeIE(InfoExtractor):
class YoutubeYtBeIE(YoutubeBaseInfoExtractor):
IE_DESC = 'youtu.be'
_VALID_URL = rf'https?://youtu\.be/(?P<id>[0-9A-Za-z_-]{{11}})/*?.*?\blist=(?P<playlist_id>{YoutubeBaseInfoExtractor._PLAYLIST_ID_RE})'
_TESTS = [{
@@ -7148,7 +7352,7 @@ class YoutubeYtBeIE(InfoExtractor):
}), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
class YoutubeLivestreamEmbedIE(InfoExtractor):
class YoutubeLivestreamEmbedIE(YoutubeBaseInfoExtractor):
IE_DESC = 'YouTube livestream embeds'
_VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
_TESTS = [{
@@ -7163,7 +7367,7 @@ class YoutubeLivestreamEmbedIE(InfoExtractor):
ie=YoutubeTabIE.ie_key(), video_id=channel_id)
class YoutubeYtUserIE(InfoExtractor):
class YoutubeYtUserIE(YoutubeBaseInfoExtractor):
IE_DESC = 'YouTube user videos; "ytuser:" prefix'
IE_NAME = 'youtube:user'
_VALID_URL = r'ytuser:(?P<id>.+)'
@@ -7450,7 +7654,7 @@ class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
class YoutubeFeedsInfoExtractor(InfoExtractor):
class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
"""
Base class for feed extractors
Subclasses must re-define the _FEED_NAME property.
@@ -7458,9 +7662,6 @@ class YoutubeFeedsInfoExtractor(InfoExtractor):
_LOGIN_REQUIRED = True
_FEED_NAME = 'feeds'
def _real_initialize(self):
YoutubeBaseInfoExtractor._check_login_required(self)
@classproperty
def IE_NAME(cls):
return f'youtube:{cls._FEED_NAME}'
@@ -7470,7 +7671,7 @@ class YoutubeFeedsInfoExtractor(InfoExtractor):
f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
class YoutubeWatchLaterIE(InfoExtractor):
class YoutubeWatchLaterIE(YoutubeBaseInfoExtractor):
IE_NAME = 'youtube:watchlater'
IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
_VALID_URL = r':ytwatchlater'
@@ -7524,7 +7725,7 @@ class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
}]
class YoutubeShortsAudioPivotIE(InfoExtractor):
class YoutubeShortsAudioPivotIE(YoutubeBaseInfoExtractor):
IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
IE_NAME = 'youtube:shorts:pivot:audio'
_VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
@@ -7548,7 +7749,7 @@ class YoutubeShortsAudioPivotIE(InfoExtractor):
ie=YoutubeTabIE)
class YoutubeTruncatedURLIE(InfoExtractor):
class YoutubeTruncatedURLIE(YoutubeBaseInfoExtractor):
IE_NAME = 'youtube:truncated_url'
IE_DESC = False # Do not list
_VALID_URL = r'''(?x)
@@ -7591,9 +7792,9 @@ class YoutubeTruncatedURLIE(InfoExtractor):
raise ExtractorError(
'Did you forget to quote the URL? Remember that & is a meta '
'character in most shells, so you want to put the URL in quotes, '
'like youtube-dl '
'like yt-dlp '
'"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
' or simply youtube-dl BaW_jenozKc .',
' or simply yt-dlp BaW_jenozKc .',
expected=True)
@@ -7707,7 +7908,7 @@ class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor):
return self.url_result(redirect_url)
class YoutubeTruncatedIDIE(InfoExtractor):
class YoutubeTruncatedIDIE(YoutubeBaseInfoExtractor):
IE_NAME = 'youtube:truncated_id'
IE_DESC = False # Do not list
_VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'