Update On Fri Dec 19 19:41:39 CET 2025

This commit is contained in:
github-action[bot]
2025-12-19 19:41:40 +01:00
parent f649634e7c
commit 095f4a24d3
406 changed files with 14464 additions and 10964 deletions

View File

@@ -638,6 +638,7 @@ from .fc2 import (
)
from .fczenit import FczenitIE
from .fifa import FifaIE
from .filmarchiv import FilmArchivIE
from .filmon import (
FilmOnChannelIE,
FilmOnIE,
@@ -1312,12 +1313,6 @@ from .newgrounds import (
)
from .newspicks import NewsPicksIE
from .newsy import NewsyIE
from .nextmedia import (
AppleDailyIE,
NextMediaActionNewsIE,
NextMediaIE,
NextTVIE,
)
from .nexx import (
NexxEmbedIE,
NexxIE,

View File

@@ -14,7 +14,7 @@ from ..utils import (
class DropboxIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dropbox\.com/(?:(?:e/)?scl/fi|sh?)/(?P<id>\w+)'
_VALID_URL = r'https?://(?:www\.)?dropbox\.com/(?:(?:e/)?scl/f[io]|sh?)/(?P<id>\w+)'
_TESTS = [
{
'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4?dl=0',
@@ -35,6 +35,9 @@ class DropboxIE(InfoExtractor):
}, {
'url': 'https://www.dropbox.com/e/scl/fi/r2kd2skcy5ylbbta5y1pz/DJI_0003.MP4?dl=0&rlkey=wcdgqangn7t3lnmmv6li9mu9h',
'only_matching': True,
}, {
'url': 'https://www.dropbox.com/scl/fo/zjfqse5txqfd7twa8iewj/AOfZzSYWUSKle2HD7XF7kzQ/A-BEAT%20C.mp4?rlkey=6tg3jkp4tv6a5vt58a6dag0mm&dl=0',
'only_matching': True,
},
]

View File

@@ -0,0 +1,52 @@
from .common import InfoExtractor
from ..utils import clean_html
from ..utils.traversal import (
find_element,
find_elements,
traverse_obj,
)
class FilmArchivIE(InfoExtractor):
IE_DESC = 'FILMARCHIV ON'
_VALID_URL = r'https?://(?:www\.)?filmarchiv\.at/de/filmarchiv-on/video/(?P<id>f_[0-9a-zA-Z]{5,})'
_TESTS = [{
'url': 'https://www.filmarchiv.at/de/filmarchiv-on/video/f_0305p7xKrXUPBwoNE9x6mh',
'md5': '54a6596f6a84624531866008a77fa27a',
'info_dict': {
'id': 'f_0305p7xKrXUPBwoNE9x6mh',
'ext': 'mp4',
'title': 'Der Wurstelprater zur Kaiserzeit',
'description': 'md5:9843f92df5cc9a4975cee7aabcf6e3b2',
'thumbnail': r're:https://cdn\.filmarchiv\.at/f_0305/p7xKrXUPBwoNE9x6mh_v1/poster\.jpg',
},
}, {
'url': 'https://www.filmarchiv.at/de/filmarchiv-on/video/f_0306vI3wO0tJIsfrqYFQXF',
'md5': '595385d7f54cb6529140ee8de7d1c3c7',
'info_dict': {
'id': 'f_0306vI3wO0tJIsfrqYFQXF',
'ext': 'mp4',
'title': 'Vor 70 Jahren: Wettgehen der Briefträger in Wien',
'description': 'md5:b2a2e4230923cd1969d471c552e62811',
'thumbnail': r're:https://cdn\.filmarchiv\.at/f_0306/vI3wO0tJIsfrqYFQXF_v1/poster\.jpg',
},
}]
def _real_extract(self, url):
media_id = self._match_id(url)
webpage = self._download_webpage(url, media_id)
path = '/'.join((media_id[:6], media_id[6:]))
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
f'https://cdn.filmarchiv.at/{path}_v1_sv1/playlist.m3u8', media_id)
return {
'id': media_id,
'title': traverse_obj(webpage, ({find_element(tag='title-div')}, {clean_html})),
'description': traverse_obj(webpage, (
{find_elements(tag='div', attr='class', value=r'.*\bborder-base-content\b', regex=True)}, ...,
{find_elements(tag='div', attr='class', value=r'.*\bprose\b', html=False, regex=True)}, ...,
{clean_html}, any)),
'thumbnail': f'https://cdn.filmarchiv.at/{path}_v1/poster.jpg',
'formats': formats,
'subtitles': subtitles,
}

View File

@@ -46,6 +46,7 @@ class GofileIE(InfoExtractor):
'videopassword': 'password',
},
}]
_STATIC_TOKEN = '4fd6sg89d7s6' # From https://gofile.io/dist/js/config.js
_TOKEN = None
def _real_initialize(self):
@@ -60,13 +61,16 @@ class GofileIE(InfoExtractor):
self._set_cookie('.gofile.io', 'accountToken', self._TOKEN)
def _entries(self, file_id):
query_params = {'wt': '4fd6sg89d7s6'} # From https://gofile.io/dist/js/alljs.js
password = self.get_param('videopassword')
if password:
query_params = {}
if password := self.get_param('videopassword'):
query_params['password'] = hashlib.sha256(password.encode()).hexdigest()
files = self._download_json(
f'https://api.gofile.io/contents/{file_id}', file_id, 'Getting filelist',
query=query_params, headers={'Authorization': f'Bearer {self._TOKEN}'})
query=query_params, headers={
'Authorization': f'Bearer {self._TOKEN}',
'X-Website-Token': self._STATIC_TOKEN,
})
status = files['status']
if status == 'error-passwordRequired':

View File

@@ -2,84 +2,59 @@ from .common import InfoExtractor
from ..utils import (
clean_html,
int_or_none,
js_to_json,
parse_iso8601,
url_or_none,
urljoin,
)
from ..utils.traversal import traverse_obj
class NetzkinoIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?netzkino\.de/\#!/[^/]+/(?P<id>[^/]+)'
_GEO_COUNTRIES = ['DE']
_VALID_URL = r'https?://(?:www\.)?netzkino\.de/details/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.netzkino.de/#!/scifikino/rakete-zum-mond',
'md5': '92a3f8b76f8d7220acce5377ea5d4873',
'url': 'https://www.netzkino.de/details/snow-beast',
'md5': '1a4c90fe40d3ccabce163287e45e56dd',
'info_dict': {
'id': 'rakete-zum-mond',
'id': 'snow-beast',
'ext': 'mp4',
'title': 'Rakete zum Mond \u2013 Jules Verne',
'description': 'md5:f0a8024479618ddbfa450ff48ffa6c60',
'upload_date': '20120813',
'thumbnail': r're:https?://.*\.jpg$',
'timestamp': 1344858571,
'title': 'Snow Beast',
'age_limit': 12,
},
'params': {
'skip_download': 'Download only works from Germany',
},
}, {
'url': 'https://www.netzkino.de/#!/filme/dr-jekyll-mrs-hyde-2',
'md5': 'c7728b2dadd04ff6727814847a51ef03',
'info_dict': {
'id': 'dr-jekyll-mrs-hyde-2',
'ext': 'mp4',
'title': 'Dr. Jekyll & Mrs. Hyde 2',
'description': 'md5:c2e9626ebd02de0a794b95407045d186',
'upload_date': '20190130',
'thumbnail': r're:https?://.*\.jpg$',
'timestamp': 1548849437,
'age_limit': 18,
},
'params': {
'skip_download': 'Download only works from Germany',
'alt_title': 'Snow Beast',
'cast': 'count:3',
'categories': 'count:7',
'creators': 'count:2',
'description': 'md5:e604a954a7f827a80e96a3a97d48b269',
'location': 'US',
'release_year': 2011,
'thumbnail': r're:https?://.+\.jpg',
},
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id = mobj.group('id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
next_js_data = self._search_nextjs_data(webpage, video_id)
api_url = f'https://api.netzkino.de.simplecache.net/capi-2.0a/movies/{video_id}.json?d=www'
info = self._download_json(api_url, video_id)
custom_fields = info['custom_fields']
production_js = self._download_webpage(
'http://www.netzkino.de/beta/dist/production.min.js', video_id,
note='Downloading player code')
avo_js = self._search_regex(
r'var urlTemplate=(\{.*?"\})',
production_js, 'URL templates')
templates = self._parse_json(
avo_js, video_id, transform_source=js_to_json)
suffix = {
'hds': '.mp4/manifest.f4m',
'hls': '.mp4/master.m3u8',
'pmd': '.mp4',
}
film_fn = custom_fields['Streaming'][0]
formats = [{
'format_id': key,
'ext': 'mp4',
'url': tpl.replace('{}', film_fn) + suffix[key],
} for key, tpl in templates.items()]
query = traverse_obj(next_js_data, (
'props', '__dehydratedState', 'queries', ..., 'state',
'data', 'data', lambda _, v: v['__typename'] == 'CmsMovie', any))
if 'DRM' in traverse_obj(query, ('licenses', 'nodes', ..., 'properties', {str})):
self.report_drm(video_id)
return {
'id': video_id,
'formats': formats,
'title': info['title'],
'age_limit': int_or_none(custom_fields.get('FSK')[0]),
'timestamp': parse_iso8601(info.get('date'), delimiter=' '),
'description': clean_html(info.get('content')),
'thumbnail': info.get('thumbnail'),
**traverse_obj(query, {
'title': ('originalTitle', {clean_html}),
'age_limit': ('fskRating', {int_or_none}),
'alt_title': ('originalTitle', {clean_html}, filter),
'cast': ('cast', 'nodes', ..., 'person', 'name', {clean_html}, filter),
'creators': (('directors', 'writers'), 'nodes', ..., 'person', 'name', {clean_html}, filter),
'categories': ('categories', 'nodes', ..., 'category', 'title', {clean_html}, filter),
'description': ('longSynopsis', {clean_html}, filter),
'duration': ('runtimeInSeconds', {int_or_none}),
'location': ('productionCountry', {clean_html}, filter),
'release_year': ('productionYear', {int_or_none}),
'thumbnail': ('coverImage', 'masterUrl', {url_or_none}),
'url': ('videoSource', 'pmdUrl', {urljoin('https://pmd.netzkino-seite.netzkino.de/')}),
}),
}

View File

@@ -1,238 +0,0 @@
import urllib.parse
from .common import InfoExtractor
from ..utils import (
clean_html,
get_element_by_class,
int_or_none,
parse_iso8601,
remove_start,
unified_timestamp,
)
class NextMediaIE(InfoExtractor):
IE_DESC = '蘋果日報'
_VALID_URL = r'https?://hk\.apple\.nextmedia\.com/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)'
_TESTS = [{
'url': 'http://hk.apple.nextmedia.com/realtime/news/20141108/53109199',
'md5': 'dff9fad7009311c421176d1ac90bfe4f',
'info_dict': {
'id': '53109199',
'ext': 'mp4',
'title': '【佔領金鐘】50外國領事議員撐場 讚學生勇敢香港有希望',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'md5:28222b9912b6665a21011b034c70fcc7',
'timestamp': 1415456273,
'upload_date': '20141108',
},
}]
_URL_PATTERN = r'\{ url: \'(.+)\' \}'
def _real_extract(self, url):
news_id = self._match_id(url)
page = self._download_webpage(url, news_id)
return self._extract_from_nextmedia_page(news_id, url, page)
def _extract_from_nextmedia_page(self, news_id, url, page):
redirection_url = self._search_regex(
r'window\.location\.href\s*=\s*([\'"])(?P<url>(?!\1).+)\1',
page, 'redirection URL', default=None, group='url')
if redirection_url:
return self.url_result(urllib.parse.urljoin(url, redirection_url))
title = self._fetch_title(page)
video_url = self._search_regex(self._URL_PATTERN, page, 'video url')
attrs = {
'id': news_id,
'title': title,
'url': video_url, # ext can be inferred from url
'thumbnail': self._fetch_thumbnail(page),
'description': self._fetch_description(page),
}
timestamp = self._fetch_timestamp(page)
if timestamp:
attrs['timestamp'] = timestamp
else:
attrs['upload_date'] = self._fetch_upload_date(url)
return attrs
def _fetch_title(self, page):
return self._og_search_title(page)
def _fetch_thumbnail(self, page):
return self._og_search_thumbnail(page)
def _fetch_timestamp(self, page):
date_created = self._search_regex('"dateCreated":"([^"]+)"', page, 'created time')
return parse_iso8601(date_created)
def _fetch_upload_date(self, url):
return self._search_regex(self._VALID_URL, url, 'upload date', group='date')
def _fetch_description(self, page):
return self._og_search_property('description', page)
class NextMediaActionNewsIE(NextMediaIE): # XXX: Do not subclass from concrete IE
IE_DESC = '蘋果日報 - 動新聞'
_VALID_URL = r'https?://hk\.dv\.nextmedia\.com/actionnews/[^/]+/(?P<date>\d+)/(?P<id>\d+)/\d+'
_TESTS = [{
'url': 'http://hk.dv.nextmedia.com/actionnews/hit/20150121/19009428/20061460',
'md5': '05fce8ffeed7a5e00665d4b7cf0f9201',
'info_dict': {
'id': '19009428',
'ext': 'mp4',
'title': '【壹週刊】細10年男友偷食 50歲邵美琪再失戀',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'md5:cd802fad1f40fd9ea178c1e2af02d659',
'timestamp': 1421791200,
'upload_date': '20150120',
},
}]
def _real_extract(self, url):
news_id = self._match_id(url)
actionnews_page = self._download_webpage(url, news_id)
article_url = self._og_search_url(actionnews_page)
article_page = self._download_webpage(article_url, news_id)
return self._extract_from_nextmedia_page(news_id, url, article_page)
class AppleDailyIE(NextMediaIE): # XXX: Do not subclass from concrete IE
IE_DESC = '臺灣蘋果日報'
_VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/[^/]+/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
_TESTS = [{
'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
'md5': 'a843ab23d150977cc55ef94f1e2c1e4d',
'info_dict': {
'id': '36354694',
'ext': 'mp4',
'title': '周亭羽走過摩鐵陰霾2男陪吃 九把刀孤寒看醫生',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'md5:2acd430e59956dc47cd7f67cb3c003f4',
'upload_date': '20150128',
},
}, {
'url': 'http://www.appledaily.com.tw/realtimenews/article/strange/20150128/550549/%E4%B8%8D%E6%BB%BF%E8%A2%AB%E8%B8%A9%E8%85%B3%E3%80%80%E5%B1%B1%E6%9D%B1%E5%85%A9%E5%A4%A7%E5%AA%BD%E4%B8%80%E8%B7%AF%E6%89%93%E4%B8%8B%E8%BB%8A',
'md5': '86b4e9132d158279c7883822d94ccc49',
'info_dict': {
'id': '550549',
'ext': 'mp4',
'title': '不滿被踩腳 山東兩大媽一路打下車',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'md5:175b4260c1d7c085993474217e4ab1b4',
'upload_date': '20150128',
},
}, {
'url': 'http://www.appledaily.com.tw/animation/realtimenews/new/20150128/5003671',
'md5': '03df296d95dedc2d5886debbb80cb43f',
'info_dict': {
'id': '5003671',
'ext': 'mp4',
'title': '20正妹熱舞 《刀龍傳說Online》火辣上市',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'md5:23c0aac567dc08c9c16a3161a2c2e3cd',
'upload_date': '20150128',
},
'skip': 'redirect to http://www.appledaily.com.tw/animation/',
}, {
# No thumbnail
'url': 'http://www.appledaily.com.tw/animation/realtimenews/new/20150128/5003673/',
'md5': 'b06182cd386ea7bc6115ec7ff0f72aeb',
'info_dict': {
'id': '5003673',
'ext': 'mp4',
'title': '半夜尿尿 好像會看到___',
'description': 'md5:61d2da7fe117fede148706cdb85ac066',
'upload_date': '20150128',
},
'expected_warnings': [
'video thumbnail',
],
'skip': 'redirect to http://www.appledaily.com.tw/animation/',
}, {
'url': 'http://www.appledaily.com.tw/appledaily/article/supplement/20140417/35770334/',
'md5': 'eaa20e6b9df418c912d7f5dec2ba734d',
'info_dict': {
'id': '35770334',
'ext': 'mp4',
'title': '咖啡占卜測 XU裝熟指數',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'md5:7b859991a6a4fedbdf3dd3b66545c748',
'upload_date': '20140417',
},
}, {
'url': 'http://www.appledaily.com.tw/actionnews/appledaily/7/20161003/960588/',
'only_matching': True,
}, {
# Redirected from http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694
'url': 'http://ent.appledaily.com.tw/section/article/headline/20150128/36354694',
'only_matching': True,
}]
_URL_PATTERN = r'\{url: \'(.+)\'\}'
def _fetch_title(self, page):
return (self._html_search_regex(r'<h1 id="h1">([^<>]+)</h1>', page, 'news title', default=None)
or self._html_search_meta('description', page, 'news title'))
def _fetch_thumbnail(self, page):
return self._html_search_regex(r"setInitialImage\(\'([^']+)'\)", page, 'video thumbnail', fatal=False)
def _fetch_timestamp(self, page):
return None
def _fetch_description(self, page):
return self._html_search_meta('description', page, 'news description')
class NextTVIE(InfoExtractor):
_WORKING = False
_ENABLED = None # XXX: pass through to GenericIE
IE_DESC = '壹電視'
_VALID_URL = r'https?://(?:www\.)?nexttv\.com\.tw/(?:[^/]+/)+(?P<id>\d+)'
_TEST = {
'url': 'http://www.nexttv.com.tw/news/realtime/politics/11779671',
'info_dict': {
'id': '11779671',
'ext': 'mp4',
'title': '「超收稅」近4千億 藍議員籲發消費券',
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1484825400,
'upload_date': '20170119',
'view_count': int,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'<h1[^>]*>([^<]+)</h1>', webpage, 'title')
data = self._hidden_inputs(webpage)
video_url = data['ntt-vod-src-detailview']
date_str = get_element_by_class('date', webpage)
timestamp = unified_timestamp(date_str + '+0800') if date_str else None
view_count = int_or_none(remove_start(
clean_html(get_element_by_class('click', webpage)), '點閱:'))
return {
'id': video_id,
'title': title,
'url': video_url,
'thumbnail': data.get('ntt-vod-img-src'),
'timestamp': timestamp,
'view_count': view_count,
}

View File

@@ -15,7 +15,7 @@ from ..utils import (
class TubiTvIE(InfoExtractor):
IE_NAME = 'tubitv'
_VALID_URL = r'https?://(?:www\.)?tubitv\.com/(?P<type>video|movies|tv-shows)/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?tubitv\.com/(?:[a-z]{2}-[a-z]{2}/)?(?P<type>video|movies|tv-shows)/(?P<id>\d+)'
_LOGIN_URL = 'http://tubitv.com/login'
_NETRC_MACHINE = 'tubitv'
_TESTS = [{
@@ -73,6 +73,9 @@ class TubiTvIE(InfoExtractor):
'release_year': 1979,
},
'skip': 'Content Unavailable',
}, {
'url': 'https://tubitv.com/es-mx/tv-shows/477363/s01-e03-jacob-dos-dos-y-la-tarjets-de-hockey-robada',
'only_matching': True,
}]
# DRM formats are included only to raise appropriate error

View File

@@ -1212,7 +1212,7 @@ def create_parser():
help='Maximum number of seconds to sleep. Can only be used along with --min-sleep-interval')
workarounds.add_option(
'--sleep-subtitles', metavar='SECONDS',
dest='sleep_interval_subtitles', default=0, type=int,
dest='sleep_interval_subtitles', default=0, type=float,
help='Number of seconds to sleep before each subtitle download')
verbosity = optparse.OptionGroup(parser, 'Verbosity and Simulation Options')