artem/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2026-08-28 14:53:40 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' of https://github.com/yt-dlp/yt-dlp into jsi

Browse Source
This commit is contained in:
c-basalt
2025-03-01 16:19:20 -05:00
parent 98ae72ff50 79ec2fdff7
commit d0956644d8
58 changed files with 1648 additions and 647 deletions
Download Patch File Download Diff File Expand all files Collapse all files
yt_dlp/extractor/__init__.py
+17 -5
View File
@@ -1,16 +1,25 @@
from ..compat.compat_utils import passthrough_module
from ..globals import extractors as _extractors_context
from ..globals import plugin_ies as _plugin_ies_context
from ..plugins import PluginSpec, register_plugin_spec
passthrough_module(__name__, '.extractors')
del passthrough_module
register_plugin_spec(PluginSpec(
module_name='extractor',
suffix='IE',
destination=_extractors_context,
plugin_destination=_plugin_ies_context,
))
def gen_extractor_classes():
""" Return a list of supported extractors.
The order does matter; the first extractor matched is the one handling the URL.
"""
from .extractors import _ALL_CLASSES
return _ALL_CLASSES
import_extractors()
return list(_extractors_context.value.values())
def gen_extractors():
@@ -37,6 +46,9 @@ def list_extractors(age_limit=None):
def get_info_extractor(ie_name):
"""Returns the info extractor class with the given ie_name"""
from . import extractors
import_extractors()
return _extractors_context.value[f'{ie_name}IE']
return getattr(extractors, f'{ie_name}IE')
def import_extractors():
from . import extractors # noqa: F401
yt_dlp/extractor/_extractors.py
+2
View File
@@ -312,6 +312,7 @@ from .brilliantpala import (
)
from .bundesliga import BundesligaIE
from .bundestag import BundestagIE
from .bunnycdn import BunnyCdnIE
from .businessinsider import BusinessInsiderIE
from .buzzfeed import BuzzFeedIE
from .byutv import BYUtvIE
@@ -1894,6 +1895,7 @@ from .slutload import SlutloadIE
from .smotrim import SmotrimIE
from .snapchat import SnapchatSpotlightIE
from .snotr import SnotrIE
from .softwhiteunderbelly import SoftWhiteUnderbellyIE
from .sohu import (
SohuIE,
SohuVIE,
yt_dlp/extractor/azmedien.py
+10 -13
View File
@@ -1,7 +1,6 @@
import json
from .common import InfoExtractor
from .kaltura import KalturaIE
from ..utils.traversal import require, traverse_obj
class AZMedienIE(InfoExtractor):
@@ -9,15 +8,15 @@ class AZMedienIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:www\.|tv\.)?
(?P<host>
(?:
telezueri\.ch|
telebaern\.tv|
telem1\.ch|
tvo-online\.ch
)/
[^/]+/
[^/?#]+/
(?P<id>
[^/]+-(?P<article_id>\d+)
[^/?#]+-\d+
)
(?:
\#video=
@@ -47,19 +46,17 @@ class AZMedienIE(InfoExtractor):
'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1',
'only_matching': True,
}]
_API_TEMPL = 'https://www.%s/api/pub/gql/%s/NewsArticleTeaser/a4016f65fe62b81dc6664dd9f4910e4ab40383be'
_PARTNER_ID = '1719221'
def _real_extract(self, url):
host, display_id, article_id, entry_id = self._match_valid_url(url).groups()
display_id, entry_id = self._match_valid_url(url).groups()
if not entry_id:
entry_id = self._download_json(
self._API_TEMPL % (host, host.split('.')[0]), display_id, query={
'variables': json.dumps({
'contextId': 'NewsArticle:' + article_id,
}),
})['data']['context']['mainAsset']['video']['kaltura']['kalturaId']
webpage = self._download_webpage(url, display_id)
data = self._search_json(
r'window\.__APOLLO_STATE__\s*=', webpage, 'video data', display_id)
entry_id = traverse_obj(data, (
lambda _, v: v['__typename'] == 'KalturaData', 'kalturaId', any, {require('kaltura id')}))
return self.url_result(
f'kaltura:{self._PARTNER_ID}:{entry_id}',
yt_dlp/extractor/bunnycdn.py
+178
View File
@@ -0,0 +1,178 @@
import json
from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import (
ExtractorError,
extract_attributes,
int_or_none,
parse_qs,
smuggle_url,
unsmuggle_url,
url_or_none,
urlhandle_detect_ext,
)
from ..utils.traversal import find_element, traverse_obj
class BunnyCdnIE(InfoExtractor):
_VALID_URL = r'https?://(?:iframe\.mediadelivery\.net|video\.bunnycdn\.com)/(?:embed|play)/(?P<library_id>\d+)/(?P<id>[\da-f-]+)'
_EMBED_REGEX = [rf'<iframe[^>]+src=[\'"](?P<url>{_VALID_URL}[^\'"]*)[\'"]']
_TESTS = [{
'url': 'https://iframe.mediadelivery.net/embed/113933/e73edec1-e381-4c8b-ae73-717a140e0924',
'info_dict': {
'id': 'e73edec1-e381-4c8b-ae73-717a140e0924',
'ext': 'mp4',
'title': 'mistress morgana (3).mp4',
'description': '',
'timestamp': 1693251673,
'thumbnail': r're:^https?://.*\.b-cdn\.net/e73edec1-e381-4c8b-ae73-717a140e0924/thumbnail\.jpg',
'duration': 7.0,
'upload_date': '20230828',
},
'params': {'skip_download': True},
}, {
'url': 'https://iframe.mediadelivery.net/play/136145/32e34c4b-0d72-437c-9abb-05e67657da34',
'info_dict': {
'id': '32e34c4b-0d72-437c-9abb-05e67657da34',
'ext': 'mp4',
'timestamp': 1691145748,
'thumbnail': r're:^https?://.*\.b-cdn\.net/32e34c4b-0d72-437c-9abb-05e67657da34/thumbnail_9172dc16\.jpg',
'duration': 106.0,
'description': 'md5:981a3e899a5c78352b21ed8b2f1efd81',
'upload_date': '20230804',
'title': 'Sanela ist Teil der #arbeitsmarktkraft',
},
'params': {'skip_download': True},
}, {
# Stream requires activation and pings
'url': 'https://iframe.mediadelivery.net/embed/200867/2e8545ec-509d-4571-b855-4cf0235ccd75',
'info_dict': {
'id': '2e8545ec-509d-4571-b855-4cf0235ccd75',
'ext': 'mp4',
'timestamp': 1708497752,
'title': 'netflix part 1',
'duration': 3959.0,
'description': '',
'upload_date': '20240221',
'thumbnail': r're:^https?://.*\.b-cdn\.net/2e8545ec-509d-4571-b855-4cf0235ccd75/thumbnail\.jpg',
},
'params': {'skip_download': True},
}]
_WEBPAGE_TESTS = [{
# Stream requires Referer
'url': 'https://conword.io/',
'info_dict': {
'id': '3a5d863e-9cd6-447e-b6ef-e289af50b349',
'ext': 'mp4',
'title': 'Conword bei der Stadt Köln und Stadt Dortmund',
'description': '',
'upload_date': '20231031',
'duration': 31.0,
'thumbnail': 'https://video.watchuh.com/3a5d863e-9cd6-447e-b6ef-e289af50b349/thumbnail.jpg',
'timestamp': 1698783879,
},
'params': {'skip_download': True},
}, {
# URL requires token and expires
'url': 'https://www.stockphotos.com/video/moscow-subway-the-train-is-arriving-at-the-park-kultury-station-10017830',
'info_dict': {
'id': '0b02fa20-4e8c-4140-8f87-f64d820a3386',
'ext': 'mp4',
'thumbnail': r're:^https?://.*\.b-cdn\.net/0b02fa20-4e8c-4140-8f87-f64d820a3386/thumbnail\.jpg',
'title': 'Moscow subway. The train is arriving at the Park Kultury station.',
'upload_date': '20240531',
'duration': 18.0,
'timestamp': 1717152269,
'description': '',
},
'params': {'skip_download': True},
}]
@classmethod
def _extract_embed_urls(cls, url, webpage):
for embed_url in super()._extract_embed_urls(url, webpage):
yield smuggle_url(embed_url, {'Referer': url})
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
video_id, library_id = self._match_valid_url(url).group('id', 'library_id')
webpage = self._download_webpage(
f'https://iframe.mediadelivery.net/embed/{library_id}/{video_id}', video_id,
headers=traverse_obj(smuggled_data, {'Referer': 'Referer'}),
query=traverse_obj(parse_qs(url), {'token': 'token', 'expires': 'expires'}))
if html_title := self._html_extract_title(webpage, default=None) == '403':
raise ExtractorError(
'This video is inaccessible. Setting a Referer header '
'might be required to access the video', expected=True)
elif html_title == '404':
raise ExtractorError('This video does not exist', expected=True)
headers = {'Referer': url}
info = traverse_obj(self._parse_html5_media_entries(url, webpage, video_id, _headers=headers), 0) or {}
formats = info.get('formats') or []
subtitles = info.get('subtitles') or {}
original_url = self._search_regex(
r'(?:var|const|let)\s+originalUrl\s*=\s*["\']([^"\']+)["\']', webpage, 'original url', default=None)
if url_or_none(original_url):
urlh = self._request_webpage(
HEADRequest(original_url), video_id=video_id, note='Checking original',
headers=headers, fatal=False, expected_status=(403, 404))
if urlh and urlh.status == 200:
formats.append({
'url': original_url,
'format_id': 'source',
'quality': 1,
'http_headers': headers,
'ext': urlhandle_detect_ext(urlh, default='mp4'),
'filesize': int_or_none(urlh.get_header('Content-Length')),
})
# MediaCage Streams require activation and pings
src_url = self._search_regex(
r'\.setAttribute\([\'"]src[\'"],\s*[\'"]([^\'"]+)[\'"]\)', webpage, 'src url', default=None)
activation_url = self._search_regex(
r'loadUrl\([\'"]([^\'"]+/activate)[\'"]', webpage, 'activation url', default=None)
ping_url = self._search_regex(
r'loadUrl\([\'"]([^\'"]+/ping)[\'"]', webpage, 'ping url', default=None)
secret = traverse_obj(parse_qs(src_url), ('secret', 0))
context_id = traverse_obj(parse_qs(src_url), ('contextId', 0))
ping_data = {}
if src_url and activation_url and ping_url and secret and context_id:
self._download_webpage(
activation_url, video_id, headers=headers, note='Downloading activation data')
fmts, subs = self._extract_m3u8_formats_and_subtitles(
src_url, video_id, 'mp4', headers=headers, m3u8_id='hls', fatal=False)
for fmt in fmts:
fmt.update({
'protocol': 'bunnycdn',
'http_headers': headers,
})
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
ping_data = {
'_bunnycdn_ping_data': {
'url': ping_url,
'headers': headers,
'secret': secret,
'context_id': context_id,
},
}
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
**traverse_obj(webpage, ({find_element(id='main-video', html=True)}, {extract_attributes}, {
'title': ('data-plyr-config', {json.loads}, 'title', {str}),
'thumbnail': ('data-poster', {url_or_none}),
})),
**ping_data,
**self._search_json_ld(webpage, video_id, fatal=False),
}
yt_dlp/extractor/cbc.py
+165 -142
View File
@@ -1,29 +1,32 @@
import base64
import functools
import json
import re
import time
import urllib.parse
from .common import InfoExtractor
from ..networking import HEADRequest
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
js_to_json,
jwt_decode_hs256,
mimetype2ext,
orderedSet,
parse_age_limit,
parse_iso8601,
replace_extension,
smuggle_url,
strip_or_none,
traverse_obj,
try_get,
unified_timestamp,
update_url,
url_basename,
url_or_none,
urlencode_postdata,
)
from ..utils.traversal import require, traverse_obj, trim_str
class CBCIE(InfoExtractor):
@@ -516,9 +519,43 @@ class CBCPlayerPlaylistIE(InfoExtractor):
return self.playlist_result(entries(), playlist_id)
class CBCGemIE(InfoExtractor):
class CBCGemBaseIE(InfoExtractor):
_NETRC_MACHINE = 'cbcgem'
_GEO_COUNTRIES = ['CA']
def _call_show_api(self, item_id, display_id=None):
return self._download_json(
f'https://services.radio-canada.ca/ott/catalog/v2/gem/show/{item_id}',
display_id or item_id, query={'device': 'web'})
def _extract_item_info(self, item_info):
episode_number = None
title = traverse_obj(item_info, ('title', {str}))
if title and (mobj := re.match(r'(?P<episode>\d+)\. (?P<title>.+)', title)):
episode_number = int_or_none(mobj.group('episode'))
title = mobj.group('title')
return {
'episode_number': episode_number,
**traverse_obj(item_info, {
'id': ('url', {str}),
'episode_id': ('url', {str}),
'description': ('description', {str}),
'thumbnail': ('images', 'card', 'url', {url_or_none}, {update_url(query=None)}),
'episode_number': ('episodeNumber', {int_or_none}),
'duration': ('metadata', 'duration', {int_or_none}),
'release_timestamp': ('metadata', 'airDate', {unified_timestamp}),
'timestamp': ('metadata', 'availabilityDate', {unified_timestamp}),
'age_limit': ('metadata', 'rating', {trim_str(start='C')}, {parse_age_limit}),
}),
'episode': title,
'title': title,
}
class CBCGemIE(CBCGemBaseIE):
IE_NAME = 'gem.cbc.ca'
_VALID_URL = r'https?://gem\.cbc\.ca/(?:media/)?(?P<id>[0-9a-z-]+/s[0-9]+[a-z][0-9]+)'
_VALID_URL = r'https?://gem\.cbc\.ca/(?:media/)?(?P<id>[0-9a-z-]+/s(?P<season>[0-9]+)[a-z][0-9]+)'
_TESTS = [{
# This is a normal, public, TV show video
'url': 'https://gem.cbc.ca/media/schitts-creek/s06e01',
@@ -529,7 +566,7 @@ class CBCGemIE(InfoExtractor):
'description': 'md5:929868d20021c924020641769eb3e7f1',
'thumbnail': r're:https://images\.radio-canada\.ca/[^#?]+/cbc_schitts_creek_season_06e01_thumbnail_v01\.jpg',
'duration': 1324,
'categories': ['comedy'],
'genres': ['Comédie et humour'],
'series': 'Schitt\'s Creek',
'season': 'Season 6',
'season_number': 6,
@@ -537,9 +574,10 @@ class CBCGemIE(InfoExtractor):
'episode_number': 1,
'episode_id': 'schitts-creek/s06e01',
'upload_date': '20210618',
'timestamp': 1623988800,
'timestamp': 1623974400,
'release_date': '20200107',
'release_timestamp': 1578427200,
'release_timestamp': 1578355200,
'age_limit': 14,
},
'params': {'format': 'bv'},
}, {
@@ -557,12 +595,13 @@ class CBCGemIE(InfoExtractor):
'episode_number': 1,
'episode': 'The Cup Runneth Over',
'episode_id': 'schitts-creek/s01e01',
'duration': 1309,
'categories': ['comedy'],
'duration': 1308,
'genres': ['Comédie et humour'],
'upload_date': '20210617',
'timestamp': 1623902400,
'release_date': '20151124',
'release_timestamp': 1448323200,
'timestamp': 1623888000,
'release_date': '20151123',
'release_timestamp': 1448236800,
'age_limit': 14,
},
'params': {'format': 'bv'},
}, {
@@ -570,82 +609,107 @@ class CBCGemIE(InfoExtractor):
'only_matching': True,
}]
_GEO_COUNTRIES = ['CA']
_TOKEN_API_KEY = '3f4beddd-2061-49b0-ae80-6f1f2ed65b37'
_NETRC_MACHINE = 'cbcgem'
_CLIENT_ID = 'fc05b0ee-3865-4400-a3cc-3da82c330c23'
_refresh_token = None
_access_token = None
_claims_token = None
def _new_claims_token(self, email, password):
data = json.dumps({
'email': email,
'password': password,
}).encode()
headers = {'content-type': 'application/json'}
query = {'apikey': self._TOKEN_API_KEY}
resp = self._download_json('https://api.loginradius.com/identity/v2/auth/login',
None, data=data, headers=headers, query=query)
access_token = resp['access_token']
@functools.cached_property
def _ropc_settings(self):
return self._download_json(
'https://services.radio-canada.ca/ott/catalog/v1/gem/settings', None,
'Downloading site settings', query={'device': 'web'})['identityManagement']['ropc']
query = {
'access_token': access_token,
'apikey': self._TOKEN_API_KEY,
'jwtapp': 'jwt',
}
resp = self._download_json('https://cloud-api.loginradius.com/sso/jwt/api/token',
None, headers=headers, query=query)
sig = resp['signature']
def _is_jwt_expired(self, token):
return jwt_decode_hs256(token)['exp'] - time.time() < 300
data = json.dumps({'jwt': sig}).encode()
headers = {'content-type': 'application/json', 'ott-device-type': 'web'}
resp = self._download_json('https://services.radio-canada.ca/ott/cbc-api/v2/token',
None, data=data, headers=headers, expected_status=426)
cbc_access_token = resp['accessToken']
def _call_oauth_api(self, oauth_data, note='Refreshing access token'):
response = self._download_json(
self._ropc_settings['url'], None, note, data=urlencode_postdata({
'client_id': self._CLIENT_ID,
**oauth_data,
'scope': self._ropc_settings['scopes'],
}))
self._refresh_token = response['refresh_token']
self._access_token = response['access_token']
self.cache.store(self._NETRC_MACHINE, 'token_data', [self._refresh_token, self._access_token])
headers = {'content-type': 'application/json', 'ott-device-type': 'web', 'ott-access-token': cbc_access_token}
resp = self._download_json('https://services.radio-canada.ca/ott/cbc-api/v2/profile',
None, headers=headers, expected_status=426)
return resp['claimsToken']
def _perform_login(self, username, password):
if not self._refresh_token:
self._refresh_token, self._access_token = self.cache.load(
self._NETRC_MACHINE, 'token_data', default=[None, None])
def _get_claims_token_expiry(self):
# Token is a JWT
# JWT is decoded here and 'exp' field is extracted
# It is a Unix timestamp for when the token expires
b64_data = self._claims_token.split('.')[1]
data = base64.urlsafe_b64decode(b64_data + '==')
return json.loads(data)['exp']
if self._refresh_token and self._access_token:
self.write_debug('Using cached refresh token')
if not self._claims_token:
self._claims_token = self.cache.load(self._NETRC_MACHINE, 'claims_token')
return
def claims_token_expired(self):
exp = self._get_claims_token_expiry()
# It will expire in less than 10 seconds, or has already expired
return exp - time.time() < 10
try:
self._call_oauth_api({
'grant_type': 'password',
'username': username,
'password': password,
}, note='Logging in')
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 400:
raise ExtractorError('Invalid username and/or password', expected=True)
raise
def claims_token_valid(self):
return self._claims_token is not None and not self.claims_token_expired()
def _fetch_access_token(self):
if self._is_jwt_expired(self._access_token):
try:
self._call_oauth_api({
'grant_type': 'refresh_token',
'refresh_token': self._refresh_token,
})
except ExtractorError:
self._refresh_token, self._access_token = None, None
self.cache.store(self._NETRC_MACHINE, 'token_data', [None, None])
self.report_warning('Refresh token has been invalidated; retrying with credentials')
self._perform_login(*self._get_login_info())
def _get_claims_token(self, email, password):
if not self.claims_token_valid():
self._claims_token = self._new_claims_token(email, password)
return self._access_token
def _fetch_claims_token(self):
if not self._get_login_info()[0]:
return None
if not self._claims_token or self._is_jwt_expired(self._claims_token):
self._claims_token = self._download_json(
'https://services.radio-canada.ca/ott/subscription/v2/gem/Subscriber/profile',
None, 'Downloading claims token', query={'device': 'web'},
headers={'Authorization': f'Bearer {self._fetch_access_token()}'})['claimsToken']
self.cache.store(self._NETRC_MACHINE, 'claims_token', self._claims_token)
else:
self.write_debug('Using cached claims token')
return self._claims_token
def _real_initialize(self):
if self.claims_token_valid():
return
self._claims_token = self.cache.load(self._NETRC_MACHINE, 'claims_token')
def _real_extract(self, url):
video_id = self._match_id(url)
video_info = self._download_json(
f'https://services.radio-canada.ca/ott/cbc-api/v2/assets/{video_id}',
video_id, expected_status=426)
video_id, season_number = self._match_valid_url(url).group('id', 'season')
video_info = self._call_show_api(video_id)
item_info = traverse_obj(video_info, (
'content', ..., 'lineups', ..., 'items',
lambda _, v: v['url'] == video_id, any, {require('item info')}))
email, password = self._get_login_info()
if email and password:
claims_token = self._get_claims_token(email, password)
headers = {'x-claims-token': claims_token}
else:
headers = {}
m3u8_info = self._download_json(video_info['playSession']['url'], video_id, headers=headers)
headers = {}
if claims_token := self._fetch_claims_token():
headers['x-claims-token'] = claims_token
m3u8_info = self._download_json(
'https://services.radio-canada.ca/media/validation/v2/',
video_id, headers=headers, query={
'appCode': 'gem',
'connectionType': 'hd',
'deviceType': 'ipad',
'multibitrate': 'true',
'output': 'json',
'tech': 'hls',
'manifestVersion': '2',
'manifestType': 'desktop',
'idMedia': item_info['idMedia'],
})
if m3u8_info.get('errorCode') == 1:
self.raise_geo_restricted(countries=['CA'])
@@ -671,26 +735,20 @@ class CBCGemIE(InfoExtractor):
fmt['preference'] = -2
return {
'season_number': int_or_none(season_number),
**traverse_obj(video_info, {
'series': ('title', {str}),
'season_number': ('structuredMetadata', 'partofSeason', 'seasonNumber', {int_or_none}),
'genres': ('structuredMetadata', 'genre', ..., {str}),
}),
**self._extract_item_info(item_info),
'id': video_id,
'episode_id': video_id,
'formats': formats,
**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)}),
}),
}
class CBCGemPlaylistIE(InfoExtractor):
class CBCGemPlaylistIE(CBCGemBaseIE):
IE_NAME = 'gem.cbc.ca:playlist'
_VALID_URL = r'https?://gem\.cbc\.ca/(?:media/)?(?P<id>(?P<show>[0-9a-z-]+)/s(?P<season>[0-9]+))/?(?:[?#]|$)'
_TESTS = [{
@@ -700,70 +758,35 @@ class CBCGemPlaylistIE(InfoExtractor):
'info_dict': {
'id': 'schitts-creek/s06',
'title': 'Season 6',
'description': 'md5:6a92104a56cbeb5818cc47884d4326a2',
'series': 'Schitt\'s Creek',
'season_number': 6,
'season': 'Season 6',
'thumbnail': 'https://images.radio-canada.ca/v1/synps-cbc/season/perso/cbc_schitts_creek_season_06_carousel_v03.jpg?impolicy=ott&im=Resize=(_Size_)&quality=75',
},
}, {
'url': 'https://gem.cbc.ca/schitts-creek/s06',
'only_matching': True,
}]
_API_BASE = 'https://services.radio-canada.ca/ott/cbc-api/v2/shows/'
def _entries(self, season_info):
for episode in traverse_obj(season_info, ('items', lambda _, v: v['url'])):
yield self.url_result(
f'https://gem.cbc.ca/media/{episode["url"]}', CBCGemIE,
**self._extract_item_info(episode))
def _real_extract(self, url):
match = self._match_valid_url(url)
season_id = match.group('id')
show = match.group('show')
show_info = self._download_json(self._API_BASE + show, season_id, expected_status=426)
season = int(match.group('season'))
season_id, show, season = self._match_valid_url(url).group('id', 'show', 'season')
show_info = self._call_show_api(show, display_id=season_id)
season_info = traverse_obj(show_info, (
'content', ..., 'lineups',
lambda _, v: v['seasonNumber'] == int(season), any, {require('season info')}))
season_info = next((s for s in show_info['seasons'] if s.get('season') == season), None)
if season_info is None:
raise ExtractorError(f'Couldn\'t find season {season} of {show}')
episodes = []
for episode in season_info['assets']:
episodes.append({
'_type': 'url_transparent',
'ie_key': 'CBCGem',
'url': 'https://gem.cbc.ca/media/' + episode['id'],
'id': episode['id'],
'title': episode.get('title'),
'description': episode.get('description'),
'thumbnail': episode.get('image'),
'series': episode.get('series'),
'season_number': episode.get('season'),
'season': season_info['title'],
'season_id': season_info.get('id'),
'episode_number': episode.get('episode'),
'episode': episode.get('title'),
'episode_id': episode['id'],
'duration': episode.get('duration'),
'categories': [episode.get('category')],
})
thumbnail = None
tn_uri = season_info.get('image')
# the-national was observed to use a "data:image/png;base64"
# URI for their 'image' value. The image was 1x1, and is
# probably just a placeholder, so it is ignored.
if tn_uri is not None and not tn_uri.startswith('data:'):
thumbnail = tn_uri
return {
'_type': 'playlist',
'entries': episodes,
'id': season_id,
'title': season_info['title'],
'description': season_info.get('description'),
'thumbnail': thumbnail,
'series': show_info.get('title'),
'season_number': season_info.get('season'),
'season': season_info['title'],
}
return self.playlist_result(
self._entries(season_info), season_id,
**traverse_obj(season_info, {
'title': ('title', {str}),
'season': ('title', {str}),
'season_number': ('seasonNumber', {int_or_none}),
}), series=traverse_obj(show_info, ('title', {str})))
class CBCGemLiveIE(InfoExtractor):
yt_dlp/extractor/common.py
+17 -29
View File
@@ -2,7 +2,6 @@ import base64
import collections
import functools
import getpass
import hashlib
import http.client
import http.cookiejar
import http.cookies
@@ -30,6 +29,7 @@ from ..compat import (
from ..cookies import LenientSimpleCookie
from ..downloader.f4m import get_base_url, remove_encrypted_media
from ..downloader.hls import HlsFD
from ..globals import plugin_ies_overrides
from ..networking import HEADRequest, Request
from ..networking.exceptions import (
HTTPError,
@@ -78,7 +78,6 @@ from ..utils import (
parse_iso8601,
parse_m3u8_attributes,
parse_resolution,
sanitize_filename,
sanitize_url,
smuggle_url,
str_or_none,
@@ -100,6 +99,7 @@ from ..utils import (
xpath_text,
xpath_with_ns,
)
from ..utils._utils import _request_dump_filename
class InfoExtractor:
@@ -1022,23 +1022,6 @@ class InfoExtractor:
'Visit http://blocklist.rkn.gov.ru/ for a block reason.',
expected=True)
def _request_dump_filename(self, url, video_id, data=None):
if data is not None:
data = hashlib.md5(data).hexdigest()
basen = join_nonempty(video_id, data, url, delim='_')
trim_length = self.get_param('trim_file_name') or 240
if len(basen) > trim_length:
h = '___' + hashlib.md5(basen.encode()).hexdigest()
basen = basen[:trim_length - len(h)] + h
filename = sanitize_filename(f'{basen}.dump', restricted=True)
# Working around MAX_PATH limitation on Windows (see
# http://msdn.microsoft.com/en-us/library/windows/desktop/aa365247(v=vs.85).aspx)
if os.name == 'nt':
absfilepath = os.path.abspath(filename)
if len(absfilepath) > 259:
filename = fR'\\?\{absfilepath}'
return filename
def __decode_webpage(self, webpage_bytes, encoding, headers):
if not encoding:
encoding = self._guess_encoding_from_content(headers.get('Content-Type', ''), webpage_bytes)
@@ -1067,7 +1050,9 @@ class InfoExtractor:
if self.get_param('write_pages'):
if isinstance(url_or_request, Request):
data = self._create_request(url_or_request, data).data
filename = self._request_dump_filename(urlh.url, video_id, data)
filename = _request_dump_filename(
urlh.url, video_id, data,
trim_length=self.get_param('trim_file_name'))
self.to_screen(f'Saving request to {filename}')
with open(filename, 'wb') as outf:
outf.write(webpage_bytes)
@@ -1128,7 +1113,9 @@ class InfoExtractor:
impersonate=None, require_impersonation=False):
if self.get_param('load_pages'):
url_or_request = self._create_request(url_or_request, data, headers, query)
filename = self._request_dump_filename(url_or_request.url, video_id, url_or_request.data)
filename = _request_dump_filename(
url_or_request.url, video_id, url_or_request.data,
trim_length=self.get_param('trim_file_name'))
self.to_screen(f'Loading request from {filename}')
try:
with open(filename, 'rb') as dumpf:
@@ -3968,14 +3955,18 @@ class InfoExtractor:
def __init_subclass__(cls, *, plugin_name=None, **kwargs):
if plugin_name:
mro = inspect.getmro(cls)
super_class = cls.__wrapped__ = mro[mro.index(cls) + 1]
cls.PLUGIN_NAME, cls.ie_key = plugin_name, super_class.ie_key
cls.IE_NAME = f'{super_class.IE_NAME}+{plugin_name}'
next_mro_class = super_class = mro[mro.index(cls) + 1]
while getattr(super_class, '__wrapped__', None):
super_class = super_class.__wrapped__
setattr(sys.modules[super_class.__module__], super_class.__name__, cls)
_PLUGIN_OVERRIDES[super_class].append(cls)
if not any(override.PLUGIN_NAME == plugin_name for override in plugin_ies_overrides.value[super_class]):
cls.__wrapped__ = next_mro_class
cls.PLUGIN_NAME, cls.ie_key = plugin_name, next_mro_class.ie_key
cls.IE_NAME = f'{next_mro_class.IE_NAME}+{plugin_name}'
setattr(sys.modules[super_class.__module__], super_class.__name__, cls)
plugin_ies_overrides.value[super_class].append(cls)
return super().__init_subclass__(**kwargs)
@@ -4031,6 +4022,3 @@ class UnsupportedURLIE(InfoExtractor):
def _real_extract(self, url):
raise UnsupportedError(url)
_PLUGIN_OVERRIDES = collections.defaultdict(list)
yt_dlp/extractor/cultureunplugged.py
+16 -3
View File
@@ -3,7 +3,7 @@ from ..utils import int_or_none
class CultureUnpluggedIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cultureunplugged\.com/documentary/watch-online/play/(?P<id>\d+)(?:/(?P<display_id>[^/]+))?'
_VALID_URL = r'https?://(?:www\.)?cultureunplugged\.com/(?:documentary/watch-online/)?play/(?P<id>\d+)(?:/(?P<display_id>[^/#?]+))?'
_TESTS = [{
'url': 'http://www.cultureunplugged.com/documentary/watch-online/play/53662/The-Next--Best-West',
'md5': 'ac6c093b089f7d05e79934dcb3d228fc',
@@ -12,12 +12,25 @@ class CultureUnpluggedIE(InfoExtractor):
'display_id': 'The-Next--Best-West',
'ext': 'mp4',
'title': 'The Next, Best West',
'description': 'md5:0423cd00833dea1519cf014e9d0903b1',
'description': 'md5:770033a3b7c2946a3bcfb7f1c6fb7045',
'thumbnail': r're:^https?://.*\.jpg$',
'creator': 'Coldstream Creative',
'creators': ['Coldstream Creative'],
'duration': 2203,
'view_count': int,
},
}, {
'url': 'https://www.cultureunplugged.com/play/2833/Koi-Sunta-Hai--Journeys-with-Kumar---Kabir--Someone-is-Listening-',
'md5': 'dc2014bc470dfccba389a1c934fa29fa',
'info_dict': {
'id': '2833',
'display_id': 'Koi-Sunta-Hai--Journeys-with-Kumar---Kabir--Someone-is-Listening-',
'ext': 'mp4',
'title': 'Koi Sunta Hai: Journeys with Kumar & Kabir (Someone is Listening)',
'description': 'md5:fa94ac934927c98660362b8285b2cda5',
'view_count': int,
'thumbnail': 'https://s3.amazonaws.com/cdn.cultureunplugged.com/thumbnails_16_9/lg/2833.jpg',
'creators': ['Srishti'],
},
}, {
'url': 'http://www.cultureunplugged.com/documentary/watch-online/play/53662',
'only_matching': True,
yt_dlp/extractor/dailymotion.py
+21 -2
View File
@@ -100,7 +100,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
class DailymotionIE(DailymotionBaseInfoExtractor):
_VALID_URL = r'''(?ix)
https?://
(?:https?:)?//
(?:
dai\.ly/|
(?:
@@ -116,7 +116,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
(?P<id>[^/?_&#]+)(?:[\w-]*\?playlist=(?P<playlist_id>x[0-9a-z]+))?
'''
IE_NAME = 'dailymotion'
_EMBED_REGEX = [r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1']
_EMBED_REGEX = [rf'(?ix)<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)["\'](?P<url>{_VALID_URL[5:]})']
_TESTS = [{
'url': 'http://www.dailymotion.com/video/x5kesuj_office-christmas-party-review-jason-bateman-olivia-munn-t-j-miller_news',
'md5': '074b95bdee76b9e3654137aee9c79dfe',
@@ -308,6 +308,25 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'description': 'Que lindura',
'tags': [],
},
}, {
# //geo.dailymotion.com/player/xysxq.html?video=k2Y4Mjp7krAF9iCuINM
'url': 'https://lcp.fr/programmes/avant-la-catastrophe-la-naissance-de-la-dictature-nazie-1933-1936-346819',
'info_dict': {
'id': 'k2Y4Mjp7krAF9iCuINM',
'ext': 'mp4',
'title': 'Avant la catastrophe la naissance de la dictature nazie 1933 -1936',
'description': 'md5:7b620d5e26edbe45f27bbddc1c0257c1',
'uploader': 'LCP Assemblée nationale',
'uploader_id': 'xbz33d',
'view_count': int,
'like_count': int,
'age_limit': 0,
'duration': 3220,
'thumbnail': 'https://s1.dmcdn.net/v/Xvumk1djJBUZfjj2a/x1080',
'tags': [],
'timestamp': 1739919947,
'upload_date': '20250218',
},
}]
_GEO_BYPASS = False
_COMMON_MEDIA_FIELDS = '''description
yt_dlp/extractor/extractors.py
+29 -20
View File
@@ -1,28 +1,37 @@
import contextlib
import inspect
import os
from ..plugins import load_plugins
from ..globals import LAZY_EXTRACTORS
from ..globals import extractors as _extractors_context
# NB: Must be before other imports so that plugins can be correctly injected
_PLUGIN_CLASSES = load_plugins('extractor', 'IE')
_CLASS_LOOKUP = None
if os.environ.get('YTDLP_NO_LAZY_EXTRACTORS'):
LAZY_EXTRACTORS.value = False
else:
try:
from .lazy_extractors import _CLASS_LOOKUP
LAZY_EXTRACTORS.value = True
except ImportError:
LAZY_EXTRACTORS.value = None
_LAZY_LOADER = False
if not os.environ.get('YTDLP_NO_LAZY_EXTRACTORS'):
with contextlib.suppress(ImportError):
from .lazy_extractors import * # noqa: F403
from .lazy_extractors import _ALL_CLASSES
_LAZY_LOADER = True
if not _CLASS_LOOKUP:
from . import _extractors
if not _LAZY_LOADER:
from ._extractors import * # noqa: F403
_ALL_CLASSES = [ # noqa: F811
klass
for name, klass in globals().items()
_CLASS_LOOKUP = {
name: value
for name, value in inspect.getmembers(_extractors)
if name.endswith('IE') and name != 'GenericIE'
]
_ALL_CLASSES.append(GenericIE) # noqa: F405
}
_CLASS_LOOKUP['GenericIE'] = _extractors.GenericIE
globals().update(_PLUGIN_CLASSES)
_ALL_CLASSES[:0] = _PLUGIN_CLASSES.values()
# We want to append to the main lookup
_current = _extractors_context.value
for name, ie in _CLASS_LOOKUP.items():
_current.setdefault(name, ie)
from .common import _PLUGIN_OVERRIDES # noqa: F401
def __getattr__(name):
value = _CLASS_LOOKUP.get(name)
if not value:
raise AttributeError(f'module {__name__} has no attribute {name}')
return value
yt_dlp/extractor/globo.py
+15 -4
View File
@@ -69,8 +69,13 @@ class GloboIE(InfoExtractor):
'info_dict': {
'id': '8013907',
'ext': 'mp4',
'title': 'Capítulo de 14⧸08⧸1989',
'title': 'Capítulo de 14/08/1989',
'episode': 'Episode 1',
'episode_number': 1,
'uploader': 'Tieta',
'uploader_id': '11895',
'duration': 2858.389,
'subtitles': 'count:1',
},
'params': {
'skip_download': True,
@@ -82,7 +87,12 @@ class GloboIE(InfoExtractor):
'id': '12824146',
'ext': 'mp4',
'title': 'Acordo de damas',
'episode': 'Episode 1',
'episode_number': 1,
'uploader': 'Rensga Hits!',
'uploader_id': '20481',
'duration': 1953.994,
'season': 'Season 2',
'season_number': 2,
},
'params': {
@@ -136,9 +146,10 @@ class GloboIE(InfoExtractor):
else:
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
main_source['url'], video_id, 'mp4', m3u8_id='hls')
self._merge_subtitles(traverse_obj(main_source, ('text', ..., {
'url': ('subtitle', 'srt', 'url', {url_or_none}),
}, all, {subs_list_to_dict(lang='en')})), target=subtitles)
self._merge_subtitles(traverse_obj(main_source, ('text', ..., ('caption', 'subtitle'), {
'url': ('srt', 'url', {url_or_none}),
}, all, {subs_list_to_dict(lang='pt-BR')})), target=subtitles)
return {
'id': video_id,
yt_dlp/extractor/instagram.py
+67 -65
View File
@@ -2,12 +2,12 @@ import hashlib
import itertools
import json
import re
import time
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
bug_reports_message,
decode_base_n,
encode_base_n,
filter_dict,
@@ -15,12 +15,12 @@ from ..utils import (
format_field,
get_element_by_attribute,
int_or_none,
join_nonempty,
lowercase_escape,
str_or_none,
str_to_int,
traverse_obj,
url_or_none,
urlencode_postdata,
)
_ENCODING_CHARS = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_'
@@ -28,63 +28,30 @@ _ENCODING_CHARS = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz012345678
def _pk_to_id(media_id):
"""Source: https://stackoverflow.com/questions/24437823/getting-instagram-post-url-from-media-id"""
return encode_base_n(int(media_id.split('_')[0]), table=_ENCODING_CHARS)
pk = int(str(media_id).split('_')[0])
return encode_base_n(pk, table=_ENCODING_CHARS)
def _id_to_pk(shortcode):
"""Covert a shortcode to a numeric value"""
return decode_base_n(shortcode[:11], table=_ENCODING_CHARS)
"""Convert a shortcode to a numeric value"""
if len(shortcode) > 28:
shortcode = shortcode[:-28]
return decode_base_n(shortcode, table=_ENCODING_CHARS)
class InstagramBaseIE(InfoExtractor):
_NETRC_MACHINE = 'instagram'
_IS_LOGGED_IN = False
_API_BASE_URL = 'https://i.instagram.com/api/v1'
_LOGIN_URL = 'https://www.instagram.com/accounts/login'
_API_HEADERS = {
'X-IG-App-ID': '936619743392459',
'X-ASBD-ID': '198387',
'X-IG-WWW-Claim': '0',
'Origin': 'https://www.instagram.com',
'Accept': '*/*',
}
def _perform_login(self, username, password):
if self._IS_LOGGED_IN:
return
login_webpage = self._download_webpage(
self._LOGIN_URL, None, note='Downloading login webpage', errnote='Failed to download login webpage')
shared_data = self._parse_json(self._search_regex(
r'window\._sharedData\s*=\s*({.+?});', login_webpage, 'shared data', default='{}'), None)
login = self._download_json(
f'{self._LOGIN_URL}/ajax/', None, note='Logging in', headers={
**self._API_HEADERS,
'X-Requested-With': 'XMLHttpRequest',
'X-CSRFToken': shared_data['config']['csrf_token'],
'X-Instagram-AJAX': shared_data['rollout_hash'],
'Referer': 'https://www.instagram.com/',
}, data=urlencode_postdata({
'enc_password': f'#PWD_INSTAGRAM_BROWSER:0:{int(time.time())}:{password}',
'username': username,
'queryParams': '{}',
'optIntoOneTap': 'false',
'stopDeletionNonce': '',
'trustedDeviceRecords': '{}',
}))
if not login.get('authenticated'):
if login.get('message'):
raise ExtractorError(f'Unable to login: {login["message"]}')
elif login.get('user'):
raise ExtractorError('Unable to login: Sorry, your password was incorrect. Please double-check your password.', expected=True)
elif login.get('user') is False:
raise ExtractorError('Unable to login: The username you entered doesn\'t belong to an account. Please check your username and try again.', expected=True)
raise ExtractorError('Unable to login')
InstagramBaseIE._IS_LOGGED_IN = True
@property
def _api_headers(self):
return {
'X-IG-App-ID': self._configuration_arg('app_id', ['936619743392459'], ie_key=InstagramIE)[0],
'X-ASBD-ID': '198387',
'X-IG-WWW-Claim': '0',
'Origin': 'https://www.instagram.com',
'Accept': '*/*',
}
def _get_count(self, media, kind, *keys):
return traverse_obj(
@@ -209,7 +176,7 @@ class InstagramBaseIE(InfoExtractor):
def _get_comments(self, video_id):
comments_info = self._download_json(
f'{self._API_BASE_URL}/media/{_id_to_pk(video_id)}/comments/?can_support_threading=true&permalink_enabled=false', video_id,
fatal=False, errnote='Comments extraction failed', note='Downloading comments info', headers=self._API_HEADERS) or {}
fatal=False, errnote='Comments extraction failed', note='Downloading comments info', headers=self._api_headers) or {}
comment_data = traverse_obj(comments_info, ('edge_media_to_parent_comment', 'edges'), 'comments')
for comment_dict in comment_data or []:
@@ -402,14 +369,14 @@ class InstagramIE(InstagramBaseIE):
info = traverse_obj(self._download_json(
f'{self._API_BASE_URL}/media/{_id_to_pk(video_id)}/info/', video_id,
fatal=False, errnote='Video info extraction failed',
note='Downloading video info', headers=self._API_HEADERS), ('items', 0))
note='Downloading video info', headers=self._api_headers), ('items', 0))
if info:
media.update(info)
return self._extract_product(media)
api_check = self._download_json(
f'{self._API_BASE_URL}/web/get_ruling_for_content/?content_type=MEDIA&target_id={_id_to_pk(video_id)}',
video_id, headers=self._API_HEADERS, fatal=False, note='Setting up session', errnote=False) or {}
video_id, headers=self._api_headers, fatal=False, note='Setting up session', errnote=False) or {}
csrf_token = self._get_cookies('https://www.instagram.com').get('csrftoken')
if not csrf_token:
@@ -429,7 +396,7 @@ class InstagramIE(InstagramBaseIE):
general_info = self._download_json(
'https://www.instagram.com/graphql/query/', video_id, fatal=False, errnote=False,
headers={
**self._API_HEADERS,
**self._api_headers,
'X-CSRFToken': csrf_token or '',
'X-Requested-With': 'XMLHttpRequest',
'Referer': url,
@@ -437,7 +404,6 @@ class InstagramIE(InstagramBaseIE):
'doc_id': '8845758582119845',
'variables': json.dumps(variables, separators=(',', ':')),
})
media.update(traverse_obj(general_info, ('data', 'xdt_shortcode_media')) or {})
if not general_info:
self.report_warning('General metadata extraction failed (some metadata might be missing).', video_id)
@@ -466,6 +432,26 @@ class InstagramIE(InstagramBaseIE):
media.update(traverse_obj(
additional_data, ('graphql', 'shortcode_media'), 'shortcode_media', expected_type=dict) or {})
else:
xdt_shortcode_media = traverse_obj(general_info, ('data', 'xdt_shortcode_media', {dict})) or {}
if not xdt_shortcode_media:
error = join_nonempty('title', 'description', delim=': ', from_dict=api_check)
if 'Restricted Video' in error:
self.raise_login_required(error)
elif error:
raise ExtractorError(error, expected=True)
elif len(video_id) > 28:
# It's a private post (video_id == shortcode + 28 extra characters)
# Only raise after getting empty response; sometimes "long"-shortcode posts are public
self.raise_login_required(
'This content is only available for registered users who follow this account')
raise ExtractorError(
'Instagram sent an empty media response. Check if this post is accessible in your '
f'browser without being logged-in. If it is not, then u{self._login_hint()[1:]}. '
'Otherwise, if the post is accessible in browser without being logged-in'
f'{bug_reports_message(before=",")}', expected=True)
media.update(xdt_shortcode_media)
username = traverse_obj(media, ('owner', 'username')) or self._search_regex(
r'"owner"\s*:\s*{\s*"username"\s*:\s*"(.+?)"', webpage, 'username', fatal=False)
@@ -485,8 +471,7 @@ class InstagramIE(InstagramBaseIE):
return self.playlist_result(
self._extract_nodes(nodes, True), video_id,
format_field(username, None, 'Post by %s'), description)
video_url = self._og_search_video_url(webpage, secure=False)
raise ExtractorError('There is no video in this post', expected=True)
formats = [{
'url': video_url,
@@ -689,7 +674,7 @@ class InstagramTagIE(InstagramPlaylistBaseIE):
class InstagramStoryIE(InstagramBaseIE):
_VALID_URL = r'https?://(?:www\.)?instagram\.com/stories/(?P<user>[^/]+)/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?instagram\.com/stories/(?P<user>[^/?#]+)(?:/(?P<id>\d+))?'
IE_NAME = 'instagram:story'
_TESTS = [{
@@ -699,25 +684,38 @@ class InstagramStoryIE(InstagramBaseIE):
'title': 'Rare',
},
'playlist_mincount': 50,
}, {
'url': 'https://www.instagram.com/stories/fruits_zipper/3570766765028588805/',
'only_matching': True,
}, {
'url': 'https://www.instagram.com/stories/fruits_zipper',
'only_matching': True,
}]
def _real_extract(self, url):
username, story_id = self._match_valid_url(url).groups()
story_info = self._download_webpage(url, story_id)
user_info = self._search_json(r'"user":', story_info, 'user info', story_id, fatal=False)
username, story_id = self._match_valid_url(url).group('user', 'id')
if username == 'highlights' and not story_id: # story id is only mandatory for highlights
raise ExtractorError('Input URL is missing a highlight ID', expected=True)
display_id = story_id or username
story_info = self._download_webpage(url, display_id)
user_info = self._search_json(r'"user":', story_info, 'user info', display_id, fatal=False)
if not user_info:
self.raise_login_required('This content is unreachable')
user_id = traverse_obj(user_info, 'pk', 'id', expected_type=str)
story_info_url = user_id if username != 'highlights' else f'highlight:{story_id}'
if not story_info_url: # user id is only mandatory for non-highlights
raise ExtractorError('Unable to extract user id')
if username == 'highlights':
story_info_url = f'highlight:{story_id}'
else:
if not user_id: # user id is only mandatory for non-highlights
raise ExtractorError('Unable to extract user id')
story_info_url = user_id
videos = traverse_obj(self._download_json(
f'{self._API_BASE_URL}/feed/reels_media/?reel_ids={story_info_url}',
story_id, errnote=False, fatal=False, headers=self._API_HEADERS), 'reels')
display_id, errnote=False, fatal=False, headers=self._api_headers), 'reels')
if not videos:
self.raise_login_required('You need to log in to access this content')
user_info = traverse_obj(videos, (user_id, 'user', {dict})) or {}
full_name = traverse_obj(videos, (f'highlight:{story_id}', 'user', 'full_name'), (user_id, 'user', 'full_name'))
story_title = traverse_obj(videos, (f'highlight:{story_id}', 'title'))
@@ -727,6 +725,7 @@ class InstagramStoryIE(InstagramBaseIE):
highlights = traverse_obj(videos, (f'highlight:{story_id}', 'items'), (user_id, 'items'))
info_data = []
for highlight in highlights:
highlight.setdefault('user', {}).update(user_info)
highlight_data = self._extract_product(highlight)
if highlight_data.get('formats'):
info_data.append({
@@ -734,4 +733,7 @@ class InstagramStoryIE(InstagramBaseIE):
'uploader_id': user_id,
**filter_dict(highlight_data),
})
if username != 'highlights' and story_id and not self._yes_playlist(username, story_id):
return traverse_obj(info_data, (lambda _, v: v['id'] == _pk_to_id(story_id), any))
return self.playlist_result(info_data, playlist_id=story_id, playlist_title=story_title)
yt_dlp/extractor/lbry.py
+7 -3
View File
@@ -26,6 +26,7 @@ class LBRYBaseIE(InfoExtractor):
_CLAIM_ID_REGEX = r'[0-9a-f]{1,40}'
_OPT_CLAIM_ID = f'[^$@:/?#&]+(?:[:#]{_CLAIM_ID_REGEX})?'
_SUPPORTED_STREAM_TYPES = ['video', 'audio']
_UNSUPPORTED_STREAM_TYPES = ['binary']
_PAGE_SIZE = 50
def _call_api_proxy(self, method, display_id, params, resource):
@@ -336,12 +337,15 @@ class LBRYIE(LBRYBaseIE):
'vcodec': 'none' if stream_type == 'audio' else None,
})
final_url = None
# HEAD request returns redirect response to m3u8 URL if available
final_url = self._request_webpage(
urlh = self._request_webpage(
HEADRequest(streaming_url), display_id, headers=headers,
note='Downloading streaming redirect url info').url
note='Downloading streaming redirect url info', fatal=False)
if urlh:
final_url = urlh.url
elif result.get('value_type') == 'stream':
elif result.get('value_type') == 'stream' and stream_type not in self._UNSUPPORTED_STREAM_TYPES:
claim_id, is_live = result['signing_channel']['claim_id'], True
live_data = self._download_json(
'https://api.odysee.live/livestream/is_live', claim_id,
yt_dlp/extractor/niconico.py
+8 -1
View File
@@ -13,11 +13,13 @@ from ..utils import (
ExtractorError,
OnDemandPagedList,
clean_html,
determine_ext,
float_or_none,
int_or_none,
join_nonempty,
parse_duration,
parse_iso8601,
parse_qs,
parse_resolution,
qualities,
remove_start,
@@ -26,6 +28,7 @@ from ..utils import (
try_get,
unescapeHTML,
update_url_query,
url_basename,
url_or_none,
urlencode_postdata,
urljoin,
@@ -430,6 +433,7 @@ class NiconicoIE(InfoExtractor):
'format_id': ('id', {str}),
'abr': ('bitRate', {float_or_none(scale=1000)}),
'asr': ('samplingRate', {int_or_none}),
'quality': ('qualityLevel', {int_or_none}),
}), get_all=False),
'acodec': 'aac',
}
@@ -441,7 +445,9 @@ class NiconicoIE(InfoExtractor):
min_abr = min(traverse_obj(audios, (..., 'bitRate', {float_or_none})), default=0) / 1000
for video_fmt in video_fmts:
video_fmt['tbr'] -= min_abr
video_fmt['format_id'] = f'video-{video_fmt["tbr"]:.0f}'
video_fmt['format_id'] = url_basename(video_fmt['url']).rpartition('.')[0]
video_fmt['quality'] = traverse_obj(videos, (
lambda _, v: v['id'] == video_fmt['format_id'], 'qualityLevel', {int_or_none}, any)) or -1
yield video_fmt
def _real_extract(self, url):
@@ -1033,6 +1039,7 @@ class NiconicoLiveIE(InfoExtractor):
thumbnails.append({
'id': f'{name}_{width}x{height}',
'url': img_url,
'ext': traverse_obj(parse_qs(img_url), ('image', 0, {determine_ext(default_ext='jpg')})),
**res,
})
yt_dlp/extractor/pbs.py
+1 -1
View File
@@ -501,7 +501,7 @@ class PBSIE(InfoExtractor):
r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed
r'class="coveplayerid">([^<]+)<', # coveplayer
r'<section[^>]+data-coveid="(\d+)"', # coveplayer from http://www.pbs.org/wgbh/frontline/film/real-csi/
r'\bclass="passportcoveplayer"[^>]+\bdata-media="(\d+)', # https://www.thirteen.org/programs/the-woodwrights-shop/who-wrote-the-book-of-sloyd-fggvvq/
r'\sclass="passportcoveplayer"[^>]*\sdata-media="(\d+)', # https://www.thirteen.org/programs/the-woodwrights-shop/who-wrote-the-book-of-sloyd-fggvvq/
r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>', # jwplayer
r"(?s)window\.PBS\.playerConfig\s*=\s*{.*?id\s*:\s*'([0-9]+)',",
r'<div[^>]+\bdata-cove-id=["\'](\d+)"', # http://www.pbs.org/wgbh/roadshow/watch/episode/2105-indianapolis-hour-2/
yt_dlp/extractor/playsuisse.py
+63 -26
View File
@@ -1,4 +1,7 @@
import base64
import hashlib
import json
import uuid
from .common import InfoExtractor
from ..utils import (
@@ -142,39 +145,73 @@ class PlaySuisseIE(InfoExtractor):
id
url
}'''
_LOGIN_BASE_URL = 'https://login.srgssr.ch/srgssrlogin.onmicrosoft.com'
_LOGIN_PATH = 'B2C_1A__SignInV2'
_CLIENT_ID = '1e33f1bf-8bf3-45e4-bbd9-c9ad934b5fca'
_LOGIN_BASE = 'https://account.srgssr.ch'
_ID_TOKEN = None
def _perform_login(self, username, password):
login_page = self._download_webpage(
'https://www.playsuisse.ch/api/sso/login', None, note='Downloading login page',
query={'x': 'x', 'locale': 'de', 'redirectUrl': 'https://www.playsuisse.ch/'})
settings = self._search_json(r'var\s+SETTINGS\s*=', login_page, 'settings', None)
code_verifier = uuid.uuid4().hex + uuid.uuid4().hex + uuid.uuid4().hex
code_challenge = base64.urlsafe_b64encode(
hashlib.sha256(code_verifier.encode()).digest()).decode().rstrip('=')
csrf_token = settings['csrf']
query = {'tx': settings['transId'], 'p': self._LOGIN_PATH}
request_id = parse_qs(self._request_webpage(
f'{self._LOGIN_BASE}/authz-srv/authz', None, 'Requesting session ID', query={
'client_id': self._CLIENT_ID,
'redirect_uri': 'https://www.playsuisse.ch/auth',
'scope': 'email profile openid offline_access',
'response_type': 'code',
'code_challenge': code_challenge,
'code_challenge_method': 'S256',
'view_type': 'login',
}).url)['requestId'][0]
status = traverse_obj(self._download_json(
f'{self._LOGIN_BASE_URL}/{self._LOGIN_PATH}/SelfAsserted', None, 'Logging in',
query=query, headers={'X-CSRF-TOKEN': csrf_token}, data=urlencode_postdata({
'request_type': 'RESPONSE',
'signInName': username,
'password': password,
}), expected_status=400), ('status', {int_or_none}))
if status == 400:
raise ExtractorError('Invalid username or password', expected=True)
try:
exchange_id = self._download_json(
f'{self._LOGIN_BASE}/verification-srv/v2/authenticate/initiate/password', None,
'Submitting username', headers={'content-type': 'application/json'}, data=json.dumps({
'usage_type': 'INITIAL_AUTHENTICATION',
'request_id': request_id,
'medium_id': 'PASSWORD',
'type': 'password',
'identifier': username,
}).encode())['data']['exchange_id']['exchange_id']
except ExtractorError:
raise ExtractorError('Invalid username', expected=True)
urlh = self._request_webpage(
f'{self._LOGIN_BASE_URL}/{self._LOGIN_PATH}/api/CombinedSigninAndSignup/confirmed',
None, 'Downloading ID token', query={
'rememberMe': 'false',
'csrf_token': csrf_token,
**query,
'diags': '',
})
try:
login_data = self._download_json(
f'{self._LOGIN_BASE}/verification-srv/v2/authenticate/authenticate/password', None,
'Submitting password', headers={'content-type': 'application/json'}, data=json.dumps({
'requestId': request_id,
'exchange_id': exchange_id,
'type': 'password',
'password': password,
}).encode())['data']
except ExtractorError:
raise ExtractorError('Invalid password', expected=True)
authorization_code = parse_qs(self._request_webpage(
f'{self._LOGIN_BASE}/login-srv/verification/login', None, 'Logging in',
data=urlencode_postdata({
'requestId': request_id,
'exchange_id': login_data['exchange_id']['exchange_id'],
'verificationType': 'password',
'sub': login_data['sub'],
'status_id': login_data['status_id'],
'rememberMe': True,
'lat': '',
'lon': '',
})).url)['code'][0]
self._ID_TOKEN = self._download_json(
f'{self._LOGIN_BASE}/proxy/token', None, 'Downloading token', data=b'', query={
'client_id': self._CLIENT_ID,
'redirect_uri': 'https://www.playsuisse.ch/auth',
'code': authorization_code,
'code_verifier': code_verifier,
'grant_type': 'authorization_code',
})['id_token']
self._ID_TOKEN = traverse_obj(parse_qs(urlh.url), ('id_token', 0))
if not self._ID_TOKEN:
raise ExtractorError('Login failed')
yt_dlp/extractor/softwhiteunderbelly.py
+87
View File
@@ -0,0 +1,87 @@
from .common import InfoExtractor
from .vimeo import VHXEmbedIE
from ..utils import (
ExtractorError,
clean_html,
update_url,
urlencode_postdata,
)
from ..utils.traversal import find_element, traverse_obj
class SoftWhiteUnderbellyIE(InfoExtractor):
_LOGIN_URL = 'https://www.softwhiteunderbelly.com/login'
_NETRC_MACHINE = 'softwhiteunderbelly'
_VALID_URL = r'https?://(?:www\.)?softwhiteunderbelly\.com/videos/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://www.softwhiteunderbelly.com/videos/kenneth-final1',
'note': 'A single Soft White Underbelly Episode',
'md5': '8e79f29ec1f1bda6da2e0b998fcbebb8',
'info_dict': {
'id': '3201266',
'ext': 'mp4',
'display_id': 'kenneth-final1',
'title': 'Appalachian Man interview-Kenneth',
'description': 'Soft White Underbelly interview and portrait of Kenneth, an Appalachian man in Clay County, Kentucky.',
'thumbnail': 'https://vhx.imgix.net/softwhiteunderbelly/assets/249f6db0-2b39-49a4-979b-f8dad4681825.jpg',
'uploader_url': 'https://vimeo.com/user80538407',
'uploader': 'OTT Videos',
'uploader_id': 'user80538407',
'duration': 512,
},
'expected_warnings': ['Failed to parse XML: not well-formed'],
}, {
'url': 'https://www.softwhiteunderbelly.com/videos/tj-2-final-2160p',
'note': 'A single Soft White Underbelly Episode',
'md5': '286bd8851b4824c62afb369e6f307036',
'info_dict': {
'id': '3506029',
'ext': 'mp4',
'display_id': 'tj-2-final-2160p',
'title': 'Fentanyl Addict interview-TJ (follow up)',
'description': 'Soft White Underbelly follow up interview and portrait of TJ, a fentanyl addict on Skid Row.',
'thumbnail': 'https://vhx.imgix.net/softwhiteunderbelly/assets/c883d531-5da0-4faf-a2e2-8eba97e5adfc.jpg',
'duration': 817,
'uploader': 'OTT Videos',
'uploader_url': 'https://vimeo.com/user80538407',
'uploader_id': 'user80538407',
},
'expected_warnings': ['Failed to parse XML: not well-formed'],
}]
def _perform_login(self, username, password):
signin_page = self._download_webpage(self._LOGIN_URL, None, 'Fetching authenticity token')
self._download_webpage(
self._LOGIN_URL, None, 'Logging in',
data=urlencode_postdata({
'email': username,
'password': password,
'authenticity_token': self._html_search_regex(
r'name=["\']authenticity_token["\']\s+value=["\']([^"\']+)', signin_page, 'authenticity_token'),
'utf8': True,
}),
)
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
if '<div id="watch-unauthorized"' in webpage:
if self._get_cookies('https://www.softwhiteunderbelly.com').get('_session'):
raise ExtractorError('This account is not subscribed to this content', expected=True)
self.raise_login_required()
embed_url, embed_id = self._html_search_regex(
r'embed_url:\s*["\'](?P<url>https?://embed\.vhx\.tv/videos/(?P<id>\d+)[^"\']*)',
webpage, 'embed url', group=('url', 'id'))
return {
'_type': 'url_transparent',
'ie_key': VHXEmbedIE.ie_key(),
'url': VHXEmbedIE._smuggle_referrer(embed_url, 'https://www.softwhiteunderbelly.com'),
'id': embed_id,
'display_id': display_id,
'title': traverse_obj(webpage, ({find_element(id='watch-info')}, {find_element(cls='video-title')}, {clean_html})),
'description': self._html_search_meta('description', webpage, default=None),
'thumbnail': update_url(self._og_search_thumbnail(webpage) or '', query=None) or None,
}
yt_dlp/extractor/soundcloud.py
+62 -9
View File
@@ -52,7 +52,8 @@ class SoundcloudBaseIE(InfoExtractor):
_API_VERIFY_AUTH_TOKEN = 'https://api-auth.soundcloud.com/connect/session%s'
_HEADERS = {}
_IMAGE_REPL_RE = r'-([0-9a-z]+)\.jpg'
_IMAGE_REPL_RE = r'-[0-9a-z]+\.(?P<ext>jpg|png)'
_TAGS_RE = re.compile(r'"([^"]+)"|([^ ]+)')
_ARTWORK_MAP = {
'mini': 16,
@@ -331,12 +332,14 @@ class SoundcloudBaseIE(InfoExtractor):
thumbnails = []
artwork_url = info.get('artwork_url')
thumbnail = artwork_url or user.get('avatar_url')
if isinstance(thumbnail, str):
if re.search(self._IMAGE_REPL_RE, thumbnail):
if url_or_none(thumbnail):
if mobj := re.search(self._IMAGE_REPL_RE, thumbnail):
for image_id, size in self._ARTWORK_MAP.items():
# Soundcloud serves JPEG regardless of URL's ext *except* for "original" thumb
ext = mobj.group('ext') if image_id == 'original' else 'jpg'
i = {
'id': image_id,
'url': re.sub(self._IMAGE_REPL_RE, f'-{image_id}.jpg', thumbnail),
'url': re.sub(self._IMAGE_REPL_RE, f'-{image_id}.{ext}', thumbnail),
}
if image_id == 'tiny' and not artwork_url:
size = 18
@@ -372,6 +375,7 @@ class SoundcloudBaseIE(InfoExtractor):
'comment_count': extract_count('comment'),
'repost_count': extract_count('reposts'),
'genres': traverse_obj(info, ('genre', {str}, filter, all, filter)),
'tags': traverse_obj(info, ('tag_list', {self._TAGS_RE.findall}, ..., ..., filter)),
'artists': traverse_obj(info, ('publisher_metadata', 'artist', {str}, filter, all, filter)),
'formats': formats if not extract_flat else None,
}
@@ -425,6 +429,7 @@ class SoundcloudIE(SoundcloudBaseIE):
'repost_count': int,
'thumbnail': 'https://i1.sndcdn.com/artworks-000031955188-rwb18x-original.jpg',
'uploader_url': 'https://soundcloud.com/ethmusic',
'tags': 'count:14',
},
},
# geo-restricted
@@ -440,7 +445,7 @@ class SoundcloudIE(SoundcloudBaseIE):
'uploader_id': '9615865',
'timestamp': 1337635207,
'upload_date': '20120521',
'duration': 227.155,
'duration': 227.103,
'license': 'all-rights-reserved',
'view_count': int,
'like_count': int,
@@ -450,6 +455,7 @@ class SoundcloudIE(SoundcloudBaseIE):
'thumbnail': 'https://i1.sndcdn.com/artworks-v8bFHhXm7Au6-0-original.jpg',
'genres': ['Alternative'],
'artists': ['The Royal Concept'],
'tags': [],
},
},
# private link
@@ -475,6 +481,7 @@ class SoundcloudIE(SoundcloudBaseIE):
'uploader_url': 'https://soundcloud.com/jaimemf',
'thumbnail': 'https://a1.sndcdn.com/images/default_avatar_large.png',
'genres': ['youtubedl'],
'tags': [],
},
},
# private link (alt format)
@@ -500,15 +507,16 @@ class SoundcloudIE(SoundcloudBaseIE):
'uploader_url': 'https://soundcloud.com/jaimemf',
'thumbnail': 'https://a1.sndcdn.com/images/default_avatar_large.png',
'genres': ['youtubedl'],
'tags': [],
},
},
# downloadable song
{
'url': 'https://soundcloud.com/the80m/the-following',
'md5': '9ffcddb08c87d74fb5808a3c183a1d04',
'md5': 'ecb87d7705d5f53e6c02a63760573c75', # wav: '9ffcddb08c87d74fb5808a3c183a1d04'
'info_dict': {
'id': '343609555',
'ext': 'wav',
'ext': 'opus', # wav original available with auth
'title': 'The Following',
'track': 'The Following',
'description': '',
@@ -526,15 +534,18 @@ class SoundcloudIE(SoundcloudBaseIE):
'view_count': int,
'genres': ['Dance & EDM'],
'artists': ['80M'],
'tags': ['80M', 'EDM', 'Dance', 'Music'],
},
'expected_warnings': ['Original download format is only available for registered users'],
},
# private link, downloadable format
# tags with spaces (e.g. "Uplifting Trance", "Ori Uplift")
{
'url': 'https://soundcloud.com/oriuplift/uponly-238-no-talking-wav/s-AyZUd',
'md5': '64a60b16e617d41d0bef032b7f55441e',
'md5': '2e1530d0e9986a833a67cb34fc90ece0', # wav: '64a60b16e617d41d0bef032b7f55441e'
'info_dict': {
'id': '340344461',
'ext': 'wav',
'ext': 'opus', # wav original available with auth
'title': 'Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav]',
'track': 'Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav]',
'description': 'md5:fa20ee0fca76a3d6df8c7e57f3715366',
@@ -552,7 +563,9 @@ class SoundcloudIE(SoundcloudBaseIE):
'uploader_url': 'https://soundcloud.com/oriuplift',
'genres': ['Trance'],
'artists': ['Ori Uplift'],
'tags': ['Orchestral', 'Emotional', 'Uplifting Trance', 'Trance', 'Ori Uplift', 'UpOnly'],
},
'expected_warnings': ['Original download format is only available for registered users'],
},
# no album art, use avatar pic for thumbnail
{
@@ -577,6 +590,7 @@ class SoundcloudIE(SoundcloudBaseIE):
'repost_count': int,
'uploader_url': 'https://soundcloud.com/garyvee',
'artists': ['MadReal'],
'tags': [],
},
'params': {
'skip_download': True,
@@ -604,8 +618,47 @@ class SoundcloudIE(SoundcloudBaseIE):
'repost_count': int,
'genres': ['Piano'],
'uploader_url': 'https://soundcloud.com/giovannisarani',
'tags': 'count:10',
},
},
# .png "original" artwork, 160kbps m4a HLS format
{
'url': 'https://soundcloud.com/skorxh/audio-dealer',
'info_dict': {
'id': '2011421339',
'ext': 'm4a',
'title': 'audio dealer',
'description': '',
'uploader': '$KORCH',
'uploader_id': '150292288',
'uploader_url': 'https://soundcloud.com/skorxh',
'comment_count': int,
'view_count': int,
'like_count': int,
'repost_count': int,
'duration': 213.469,
'tags': [],
'artists': ['$KORXH'],
'track': 'audio dealer',
'timestamp': 1737143201,
'upload_date': '20250117',
'license': 'all-rights-reserved',
'thumbnail': 'https://i1.sndcdn.com/artworks-a1wKGMYNreDLTMrT-fGjRiw-original.png',
'thumbnails': [
{'id': 'mini', 'url': 'https://i1.sndcdn.com/artworks-a1wKGMYNreDLTMrT-fGjRiw-mini.jpg'},
{'id': 'tiny', 'url': 'https://i1.sndcdn.com/artworks-a1wKGMYNreDLTMrT-fGjRiw-tiny.jpg'},
{'id': 'small', 'url': 'https://i1.sndcdn.com/artworks-a1wKGMYNreDLTMrT-fGjRiw-small.jpg'},
{'id': 'badge', 'url': 'https://i1.sndcdn.com/artworks-a1wKGMYNreDLTMrT-fGjRiw-badge.jpg'},
{'id': 't67x67', 'url': 'https://i1.sndcdn.com/artworks-a1wKGMYNreDLTMrT-fGjRiw-t67x67.jpg'},
{'id': 'large', 'url': 'https://i1.sndcdn.com/artworks-a1wKGMYNreDLTMrT-fGjRiw-large.jpg'},
{'id': 't300x300', 'url': 'https://i1.sndcdn.com/artworks-a1wKGMYNreDLTMrT-fGjRiw-t300x300.jpg'},
{'id': 'crop', 'url': 'https://i1.sndcdn.com/artworks-a1wKGMYNreDLTMrT-fGjRiw-crop.jpg'},
{'id': 't500x500', 'url': 'https://i1.sndcdn.com/artworks-a1wKGMYNreDLTMrT-fGjRiw-t500x500.jpg'},
{'id': 'original', 'url': 'https://i1.sndcdn.com/artworks-a1wKGMYNreDLTMrT-fGjRiw-original.png'},
],
},
'params': {'skip_download': 'm3u8', 'format': 'hls_aac_160k'},
},
{
# AAC HQ format available (account with active subscription needed)
'url': 'https://soundcloud.com/wandw/the-chainsmokers-ft-daya-dont-let-me-down-ww-remix-1',
yt_dlp/extractor/sovietscloset.py
+15 -30
View File
@@ -1,5 +1,6 @@
from .bunnycdn import BunnyCdnIE
from .common import InfoExtractor
from ..utils import try_get, unified_timestamp
from ..utils import make_archive_id, try_get, unified_timestamp
class SovietsClosetBaseIE(InfoExtractor):
@@ -43,7 +44,7 @@ class SovietsClosetIE(SovietsClosetBaseIE):
'url': 'https://sovietscloset.com/video/1337',
'md5': 'bd012b04b261725510ca5383074cdd55',
'info_dict': {
'id': '1337',
'id': '2f0cfbf4-3588-43a9-a7d6-7c9ea3755e67',
'ext': 'mp4',
'title': 'The Witcher #13',
'thumbnail': r're:^https?://.*\.b-cdn\.net/2f0cfbf4-3588-43a9-a7d6-7c9ea3755e67/thumbnail\.jpg$',
@@ -55,20 +56,23 @@ class SovietsClosetIE(SovietsClosetBaseIE):
'upload_date': '20170413',
'uploader_id': 'SovietWomble',
'uploader_url': 'https://www.twitch.tv/SovietWomble',
'duration': 7007,
'duration': 7008,
'was_live': True,
'availability': 'public',
'series': 'The Witcher',
'season': 'Misc',
'episode_number': 13,
'episode': 'Episode 13',
'creators': ['SovietWomble'],
'description': '',
'_old_archive_ids': ['sovietscloset 1337'],
},
},
{
'url': 'https://sovietscloset.com/video/1105',
'md5': '89fa928f183893cb65a0b7be846d8a90',
'info_dict': {
'id': '1105',
'id': 'c0e5e76f-3a93-40b4-bf01-12343c2eec5d',
'ext': 'mp4',
'title': 'Arma 3 - Zeus Games #5',
'uploader': 'SovietWomble',
@@ -80,39 +84,20 @@ class SovietsClosetIE(SovietsClosetBaseIE):
'upload_date': '20160420',
'uploader_id': 'SovietWomble',
'uploader_url': 'https://www.twitch.tv/SovietWomble',
'duration': 8804,
'duration': 8805,
'was_live': True,
'availability': 'public',
'series': 'Arma 3',
'season': 'Zeus Games',
'episode_number': 5,
'episode': 'Episode 5',
'creators': ['SovietWomble'],
'description': '',
'_old_archive_ids': ['sovietscloset 1105'],
},
},
]
def _extract_bunnycdn_iframe(self, video_id, bunnycdn_id):
iframe = self._download_webpage(
f'https://iframe.mediadelivery.net/embed/5105/{bunnycdn_id}',
video_id, note='Downloading BunnyCDN iframe', headers=self.MEDIADELIVERY_REFERER)
m3u8_url = self._search_regex(r'(https?://.*?\.m3u8)', iframe, 'm3u8 url')
thumbnail_url = self._search_regex(r'(https?://.*?thumbnail\.jpg)', iframe, 'thumbnail url')
m3u8_formats = self._extract_m3u8_formats(m3u8_url, video_id, headers=self.MEDIADELIVERY_REFERER)
if not m3u8_formats:
duration = None
else:
duration = self._extract_m3u8_vod_duration(
m3u8_formats[0]['url'], video_id, headers=self.MEDIADELIVERY_REFERER)
return {
'formats': m3u8_formats,
'thumbnail': thumbnail_url,
'duration': duration,
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
@@ -122,13 +107,13 @@ class SovietsClosetIE(SovietsClosetBaseIE):
stream = self.parse_nuxt_jsonp(f'{static_assets_base}/video/{video_id}/payload.js', video_id, 'video')['stream']
return {
return self.url_result(
f'https://iframe.mediadelivery.net/embed/5105/{stream["bunnyId"]}', ie=BunnyCdnIE, url_transparent=True,
**self.video_meta(
video_id=video_id, game_name=stream['game']['name'],
category_name=try_get(stream, lambda x: x['subcategory']['name'], str),
episode_number=stream.get('number'), stream_date=stream.get('date')),
**self._extract_bunnycdn_iframe(video_id, stream['bunnyId']),
}
_old_archive_ids=[make_archive_id(self, video_id)])
class SovietsClosetPlaylistIE(SovietsClosetBaseIE):
yt_dlp/extractor/tiktok.py
+12 -2
View File
@@ -249,6 +249,12 @@ class TikTokBaseIE(InfoExtractor):
elif fatal:
raise ExtractorError('Unable to extract webpage video data')
if not traverse_obj(video_data, ('video', {dict})) and traverse_obj(video_data, ('isContentClassified', {bool})):
message = 'This post may not be comfortable for some audiences. Log in for access'
if fatal:
self.raise_login_required(message)
self.report_warning(f'{message}. {self._login_hint()}', video_id=video_id)
return video_data, status
def _get_subtitles(self, aweme_detail, aweme_id, user_name):
@@ -895,8 +901,12 @@ class TikTokIE(TikTokBaseIE):
if video_data and status == 0:
return self._parse_aweme_video_web(video_data, url, video_id)
elif status == 10216:
raise ExtractorError('This video is private', expected=True)
elif status in (10216, 10222):
# 10216: private post; 10222: private account
self.raise_login_required(
'You do not have permission to view this post. Log into an account that has access')
elif status == 10204:
raise ExtractorError('Your IP address is blocked from accessing this post', expected=True)
raise ExtractorError(f'Video not available, status code {status}', video_id=video_id)
yt_dlp/extractor/weibo.py
+30 -22
View File
@@ -12,6 +12,7 @@ from ..utils import (
str_or_none,
strip_jsonp,
traverse_obj,
truncate_string,
url_or_none,
urlencode_postdata,
urljoin,
@@ -96,7 +97,8 @@ class WeiboBaseIE(InfoExtractor):
})
return formats
def _parse_video_info(self, video_info, video_id=None):
def _parse_video_info(self, video_info):
video_id = traverse_obj(video_info, (('id', 'id_str', 'mid'), {str_or_none}, any))
return {
'id': video_id,
'extractor_key': WeiboIE.ie_key(),
@@ -105,9 +107,10 @@ class WeiboBaseIE(InfoExtractor):
'http_headers': {'Referer': 'https://weibo.com/'},
'_old_archive_ids': [make_archive_id('WeiboMobile', video_id)],
**traverse_obj(video_info, {
'id': (('id', 'id_str', 'mid'), {str_or_none}),
'display_id': ('mblogid', {str_or_none}),
'title': ('page_info', 'media_info', ('video_title', 'kol_title', 'name'), {str}, filter),
'title': ('page_info', 'media_info', ('video_title', 'kol_title', 'name'),
{lambda x: x.replace('\n', ' ')}, {truncate_string(left=50)}, filter),
'alt_title': ('page_info', 'media_info', ('video_title', 'kol_title', 'name'), {str}, filter),
'description': ('text_raw', {str}),
'duration': ('page_info', 'media_info', 'duration', {int_or_none}),
'timestamp': ('page_info', 'media_info', 'video_publish_time', {int_or_none}),
@@ -129,9 +132,11 @@ class WeiboIE(WeiboBaseIE):
'url': 'https://weibo.com/7827771738/N4xlMvjhI',
'info_dict': {
'id': '4910815147462302',
'_old_archive_ids': ['weibomobile 4910815147462302'],
'ext': 'mp4',
'display_id': 'N4xlMvjhI',
'title': '【睡前消息暑假版第一期：拉泰国一把 对中国有好处】',
'alt_title': '【睡前消息暑假版第一期：拉泰国一把 对中国有好处】',
'description': 'md5:e2637a7673980d68694ea7c43cf12a5f',
'duration': 918,
'timestamp': 1686312819,
@@ -149,9 +154,11 @@ class WeiboIE(WeiboBaseIE):
'url': 'https://m.weibo.cn/status/4189191225395228',
'info_dict': {
'id': '4189191225395228',
'_old_archive_ids': ['weibomobile 4189191225395228'],
'ext': 'mp4',
'display_id': 'FBqgOmDxO',
'title': '柴犬柴犬的秒拍视频',
'alt_title': '柴犬柴犬的秒拍视频',
'description': 'md5:80f461ab5cdae6bbdb70efbf5a1db24f',
'duration': 53,
'timestamp': 1514264429,
@@ -166,34 +173,35 @@ class WeiboIE(WeiboBaseIE):
},
}, {
'url': 'https://m.weibo.cn/detail/4189191225395228',
'info_dict': {
'id': '4189191225395228',
'ext': 'mp4',
'display_id': 'FBqgOmDxO',
'title': '柴犬柴犬的秒拍视频',
'description': '午睡当然是要甜甜蜜蜜的啦！[坏笑] Instagram：shibainu.gaku http://t.cn/RHbmjzW ',
'duration': 53,
'timestamp': 1514264429,
'upload_date': '20171226',
'thumbnail': r're:https://.*\.jpg',
'uploader': '柴犬柴犬',
'uploader_id': '5926682210',
'uploader_url': 'https://weibo.com/u/5926682210',
'view_count': int,
'like_count': int,
'repost_count': int,
},
'only_matching': True,
}, {
'url': 'https://weibo.com/0/4224132150961381',
'note': 'no playback_list example',
'only_matching': True,
}, {
'url': 'https://m.weibo.cn/detail/5120561132606436',
'info_dict': {
'id': '5120561132606436',
},
'playlist_count': 9,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
return self._parse_video_info(self._weibo_download_json(
f'https://weibo.com/ajax/statuses/show?id={video_id}', video_id))
meta = self._weibo_download_json(f'https://weibo.com/ajax/statuses/show?id={video_id}', video_id)
mix_media_info = traverse_obj(meta, ('mix_media_info', 'items', ...))
if not mix_media_info:
return self._parse_video_info(meta)
return self.playlist_result(self._entries(mix_media_info), video_id)
def _entries(self, mix_media_info):
for media_info in traverse_obj(mix_media_info, lambda _, v: v['type'] != 'pic'):
yield self._parse_video_info(traverse_obj(media_info, {
'id': ('data', 'object_id'),
'page_info': {'media_info': ('data', 'media_info', {dict})},
}))
class WeiboVideoIE(WeiboBaseIE):
yt_dlp/extractor/wsj.py
+13 -4
View File
@@ -100,8 +100,8 @@ class WSJIE(InfoExtractor):
class WSJArticleIE(InfoExtractor):
_VALID_URL = r'(?i)https?://(?:www\.)?wsj\.com/articles/(?P<id>[^/?#&]+)'
_TEST = {
_VALID_URL = r'(?i)https?://(?:www\.)?wsj\.com/(?:articles|opinion)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.wsj.com/articles/dont-like-china-no-pandas-for-you-1490366939?',
'info_dict': {
'id': '4B13FA62-1D8C-45DB-8EA1-4105CB20B362',
@@ -110,11 +110,20 @@ class WSJArticleIE(InfoExtractor):
'uploader_id': 'ralcaraz',
'title': 'Bao Bao the Panda Leaves for China',
},
}
}, {
'url': 'https://www.wsj.com/opinion/hamas-hostages-caskets-bibas-family-israel-gaza-29da083b',
'info_dict': {
'id': 'CE68D629-8DB8-4CD3-B30A-92112C102054',
'ext': 'mp4',
'upload_date': '20241007',
'uploader_id': 'Tinnes, David',
'title': 'WSJ Opinion: "Get the Jew": The Crown Heights Riot Revisited',
},
}]
def _real_extract(self, url):
article_id = self._match_id(url)
webpage = self._download_webpage(url, article_id)
webpage = self._download_webpage(url, article_id, impersonate=True)
video_id = self._search_regex(
r'(?:id=["\']video|video-|iframe\.html\?guid=|data-src=["\'])([a-fA-F0-9-]{36})',
webpage, 'video id')
yt_dlp/extractor/youtube.py
+7 -1
View File
@@ -4265,6 +4265,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
} for range_start in range(0, f['filesize'], CHUNK_SIZE))
for fmt in streaming_formats:
client_name = fmt[STREAMING_DATA_CLIENT_NAME]
if fmt.get('targetDurationSec'):
continue
@@ -4309,6 +4310,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
encrypted_sig = try_get(sc, lambda x: x['s'][0])
if not all((sc, fmt_url, player_url, encrypted_sig)):
self.report_warning(
f'Some {client_name} client formats have been skipped as they are missing a url. '
f'{"Your account" if self.is_authenticated else "The current session"} may have '
f'the SSAP (server-side ads) experiment which may be interfering with yt-dlp. '
f'Please see https://github.com/yt-dlp/yt-dlp/issues/12482 for more details.',
only_once=True)
continue
try:
fmt_url += '&{}={}'.format(
@@ -4355,7 +4362,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
self.report_warning(
f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
client_name = fmt[STREAMING_DATA_CLIENT_NAME]
po_token = fmt.get(STREAMING_DATA_INITIAL_PO_TOKEN)
if po_token: