mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2025-05-01 00:08:47 +02:00
Compare commits
3 Commits
b872ffec50
...
9bf23902ce
Author | SHA1 | Date | |
---|---|---|---|
|
9bf23902ce | ||
|
be5af3f9e9 | ||
|
fe4f14b836 |
@ -55,8 +55,7 @@ default = [
|
||||
"websockets>=13.0",
|
||||
]
|
||||
curl-cffi = [
|
||||
"curl-cffi==0.5.10; os_name=='nt' and implementation_name=='cpython'",
|
||||
"curl-cffi>=0.5.10,!=0.6.*,<0.7.2; os_name!='nt' and implementation_name=='cpython'",
|
||||
"curl-cffi>=0.5.10,!=0.6.*,!=0.7.*,!=0.8.*,!=0.9.*,<0.11; implementation_name=='cpython'",
|
||||
]
|
||||
secretstorage = [
|
||||
"cffi",
|
||||
|
@ -614,7 +614,6 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
|
||||
rh, Request(f'http://127.0.0.1:{self.http_port}/source_address')).read().decode()
|
||||
assert source_address == data
|
||||
|
||||
# Not supported by CurlCFFI
|
||||
@pytest.mark.skip_handler('CurlCFFI', 'not supported by curl-cffi')
|
||||
def test_gzip_trailing_garbage(self, handler):
|
||||
with handler() as rh:
|
||||
|
@ -23,7 +23,6 @@ from yt_dlp.extractor import (
|
||||
TedTalkIE,
|
||||
ThePlatformFeedIE,
|
||||
ThePlatformIE,
|
||||
VikiIE,
|
||||
VimeoIE,
|
||||
WallaIE,
|
||||
YoutubeIE,
|
||||
@ -331,20 +330,6 @@ class TestRaiPlaySubtitles(BaseTestSubtitles):
|
||||
self.assertEqual(md5(subtitles['it']), '4b3264186fbb103508abe5311cfcb9cd')
|
||||
|
||||
|
||||
@is_download_test
|
||||
@unittest.skip('IE broken - DRM only')
|
||||
class TestVikiSubtitles(BaseTestSubtitles):
|
||||
url = 'http://www.viki.com/videos/1060846v-punch-episode-18'
|
||||
IE = VikiIE
|
||||
|
||||
def test_allsubtitles(self):
|
||||
self.DL.params['writesubtitles'] = True
|
||||
self.DL.params['allsubtitles'] = True
|
||||
subtitles = self.getSubtitles()
|
||||
self.assertEqual(set(subtitles.keys()), {'en'})
|
||||
self.assertEqual(md5(subtitles['en']), '53cb083a5914b2d84ef1ab67b880d18a')
|
||||
|
||||
|
||||
@is_download_test
|
||||
class TestThePlatformSubtitles(BaseTestSubtitles):
|
||||
# from http://www.3playmedia.com/services-features/tools/integrations/theplatform/
|
||||
|
@ -4152,7 +4152,7 @@ class YoutubeDL:
|
||||
(target, rh.RH_NAME)
|
||||
for rh in self._request_director.handlers.values()
|
||||
if isinstance(rh, ImpersonateRequestHandler)
|
||||
for target in rh.supported_targets
|
||||
for target in reversed(rh.supported_targets)
|
||||
]
|
||||
|
||||
def _impersonate_target_available(self, target):
|
||||
|
@ -1021,8 +1021,9 @@ def _real_main(argv=None):
|
||||
# List of simplified targets we know are supported,
|
||||
# to help users know what dependencies may be required.
|
||||
(ImpersonateTarget('chrome'), 'curl_cffi'),
|
||||
(ImpersonateTarget('edge'), 'curl_cffi'),
|
||||
(ImpersonateTarget('safari'), 'curl_cffi'),
|
||||
(ImpersonateTarget('firefox'), 'curl_cffi>=0.10'),
|
||||
(ImpersonateTarget('edge'), 'curl_cffi'),
|
||||
]
|
||||
|
||||
available_targets = ydl._get_available_impersonate_targets()
|
||||
@ -1038,12 +1039,12 @@ def _real_main(argv=None):
|
||||
|
||||
for known_target, known_handler in known_targets:
|
||||
if not any(
|
||||
known_target in target and handler == known_handler
|
||||
known_target in target and known_handler.startswith(handler)
|
||||
for target, handler in available_targets
|
||||
):
|
||||
rows.append([
|
||||
rows.insert(0, [
|
||||
ydl._format_out(text, ydl.Styles.SUPPRESS)
|
||||
for text in make_row(known_target, f'{known_handler} (not available)')
|
||||
for text in make_row(known_target, f'{known_handler} (unavailable)')
|
||||
])
|
||||
|
||||
ydl.to_screen('[info] Available impersonate targets')
|
||||
|
@ -496,10 +496,6 @@ from .daum import (
|
||||
from .daystar import DaystarClipIE
|
||||
from .dbtv import DBTVIE
|
||||
from .dctp import DctpTvIE
|
||||
from .deezer import (
|
||||
DeezerAlbumIE,
|
||||
DeezerPlaylistIE,
|
||||
)
|
||||
from .democracynow import DemocracynowIE
|
||||
from .detik import DetikEmbedIE
|
||||
from .deuxm import (
|
||||
@ -2352,10 +2348,6 @@ from .viewlift import (
|
||||
ViewLiftIE,
|
||||
)
|
||||
from .viidea import ViideaIE
|
||||
from .viki import (
|
||||
VikiChannelIE,
|
||||
VikiIE,
|
||||
)
|
||||
from .vimeo import (
|
||||
VHXEmbedIE,
|
||||
VimeoAlbumIE,
|
||||
|
@ -1,142 +0,0 @@
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
orderedSet,
|
||||
)
|
||||
|
||||
|
||||
class DeezerBaseInfoExtractor(InfoExtractor):
|
||||
def get_data(self, url):
|
||||
if not self.get_param('test'):
|
||||
self.report_warning('For now, this extractor only supports the 30 second previews. Patches welcome!')
|
||||
|
||||
mobj = self._match_valid_url(url)
|
||||
data_id = mobj.group('id')
|
||||
|
||||
webpage = self._download_webpage(url, data_id)
|
||||
geoblocking_msg = self._html_search_regex(
|
||||
r'<p class="soon-txt">(.*?)</p>', webpage, 'geoblocking message',
|
||||
default=None)
|
||||
if geoblocking_msg is not None:
|
||||
raise ExtractorError(
|
||||
f'Deezer said: {geoblocking_msg}', expected=True)
|
||||
|
||||
data_json = self._search_regex(
|
||||
(r'__DZR_APP_STATE__\s*=\s*({.+?})\s*</script>',
|
||||
r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n'),
|
||||
webpage, 'data JSON')
|
||||
data = json.loads(data_json)
|
||||
return data_id, webpage, data
|
||||
|
||||
|
||||
class DeezerPlaylistIE(DeezerBaseInfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?playlist/(?P<id>[0-9]+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.deezer.com/playlist/176747451',
|
||||
'info_dict': {
|
||||
'id': '176747451',
|
||||
'title': 'Best!',
|
||||
'uploader': 'anonymous',
|
||||
'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
|
||||
},
|
||||
'playlist_count': 29,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
playlist_id, webpage, data = self.get_data(url)
|
||||
|
||||
playlist_title = data.get('DATA', {}).get('TITLE')
|
||||
playlist_uploader = data.get('DATA', {}).get('PARENT_USERNAME')
|
||||
playlist_thumbnail = self._search_regex(
|
||||
r'<img id="naboo_playlist_image".*?src="([^"]+)"', webpage,
|
||||
'playlist thumbnail')
|
||||
|
||||
entries = []
|
||||
for s in data.get('SONGS', {}).get('data'):
|
||||
formats = [{
|
||||
'format_id': 'preview',
|
||||
'url': s.get('MEDIA', [{}])[0].get('HREF'),
|
||||
'preference': -100, # Only the first 30 seconds
|
||||
'ext': 'mp3',
|
||||
}]
|
||||
artists = ', '.join(
|
||||
orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
|
||||
entries.append({
|
||||
'id': s.get('SNG_ID'),
|
||||
'duration': int_or_none(s.get('DURATION')),
|
||||
'title': '{} - {}'.format(artists, s.get('SNG_TITLE')),
|
||||
'uploader': s.get('ART_NAME'),
|
||||
'uploader_id': s.get('ART_ID'),
|
||||
'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
|
||||
'formats': formats,
|
||||
})
|
||||
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'id': playlist_id,
|
||||
'title': playlist_title,
|
||||
'uploader': playlist_uploader,
|
||||
'thumbnail': playlist_thumbnail,
|
||||
'entries': entries,
|
||||
}
|
||||
|
||||
|
||||
class DeezerAlbumIE(DeezerBaseInfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?album/(?P<id>[0-9]+)'
|
||||
_TEST = {
|
||||
'url': 'https://www.deezer.com/fr/album/67505622',
|
||||
'info_dict': {
|
||||
'id': '67505622',
|
||||
'title': 'Last Week',
|
||||
'uploader': 'Home Brew',
|
||||
'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
|
||||
},
|
||||
'playlist_count': 7,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
album_id, webpage, data = self.get_data(url)
|
||||
|
||||
album_title = data.get('DATA', {}).get('ALB_TITLE')
|
||||
album_uploader = data.get('DATA', {}).get('ART_NAME')
|
||||
album_thumbnail = self._search_regex(
|
||||
r'<img id="naboo_album_image".*?src="([^"]+)"', webpage,
|
||||
'album thumbnail')
|
||||
|
||||
entries = []
|
||||
for s in data.get('SONGS', {}).get('data'):
|
||||
formats = [{
|
||||
'format_id': 'preview',
|
||||
'url': s.get('MEDIA', [{}])[0].get('HREF'),
|
||||
'preference': -100, # Only the first 30 seconds
|
||||
'ext': 'mp3',
|
||||
}]
|
||||
artists = ', '.join(
|
||||
orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
|
||||
entries.append({
|
||||
'id': s.get('SNG_ID'),
|
||||
'duration': int_or_none(s.get('DURATION')),
|
||||
'title': '{} - {}'.format(artists, s.get('SNG_TITLE')),
|
||||
'uploader': s.get('ART_NAME'),
|
||||
'uploader_id': s.get('ART_ID'),
|
||||
'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
|
||||
'formats': formats,
|
||||
'track': s.get('SNG_TITLE'),
|
||||
'track_number': int_or_none(s.get('TRACK_NUMBER')),
|
||||
'track_id': s.get('SNG_ID'),
|
||||
'artist': album_uploader,
|
||||
'album': album_title,
|
||||
'album_artist': album_uploader,
|
||||
})
|
||||
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'id': album_id,
|
||||
'title': album_title,
|
||||
'uploader': album_uploader,
|
||||
'thumbnail': album_thumbnail,
|
||||
'entries': entries,
|
||||
}
|
@ -51,6 +51,8 @@ class KnownDRMIE(UnsupportedInfoExtractor):
|
||||
r'(?:watch|front)\.njpwworld\.com',
|
||||
r'qub\.ca/vrai',
|
||||
r'(?:beta\.)?crunchyroll\.com',
|
||||
r'viki\.com',
|
||||
r'deezer\.com',
|
||||
)
|
||||
|
||||
_TESTS = [{
|
||||
@ -160,6 +162,12 @@ class KnownDRMIE(UnsupportedInfoExtractor):
|
||||
}, {
|
||||
'url': 'https://beta.crunchyroll.com/pt-br/watch/G8WUN8VKP/the-ruler-of-conspiracy',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.viki.com/videos/1175236v-choosing-spouse-by-lottery-episode-1',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.deezer.com/playlist/176747451',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
@ -1,346 +0,0 @@
|
||||
import hashlib
|
||||
import hmac
|
||||
import json
|
||||
import time
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
parse_age_limit,
|
||||
parse_iso8601,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class VikiBaseIE(InfoExtractor):
|
||||
_VALID_URL_BASE = r'https?://(?:www\.)?viki\.(?:com|net|mx|jp|fr)/'
|
||||
_API_URL_TEMPLATE = 'https://api.viki.io%s'
|
||||
|
||||
_DEVICE_ID = '112395910d'
|
||||
_APP = '100005a'
|
||||
_APP_VERSION = '6.11.3'
|
||||
_APP_SECRET = 'd96704b180208dbb2efa30fe44c48bd8690441af9f567ba8fd710a72badc85198f7472'
|
||||
|
||||
_GEO_BYPASS = False
|
||||
_NETRC_MACHINE = 'viki'
|
||||
|
||||
_token = None
|
||||
|
||||
_ERRORS = {
|
||||
'geo': 'Sorry, this content is not available in your region.',
|
||||
'upcoming': 'Sorry, this content is not yet available.',
|
||||
'paywall': 'Sorry, this content is only available to Viki Pass Plus subscribers',
|
||||
}
|
||||
|
||||
def _stream_headers(self, timestamp, sig):
|
||||
return {
|
||||
'X-Viki-manufacturer': 'vivo',
|
||||
'X-Viki-device-model': 'vivo 1606',
|
||||
'X-Viki-device-os-ver': '6.0.1',
|
||||
'X-Viki-connection-type': 'WIFI',
|
||||
'X-Viki-carrier': '',
|
||||
'X-Viki-as-id': '100005a-1625321982-3932',
|
||||
'timestamp': str(timestamp),
|
||||
'signature': str(sig),
|
||||
'x-viki-app-ver': self._APP_VERSION,
|
||||
}
|
||||
|
||||
def _api_query(self, path, version=4, **kwargs):
|
||||
path += '?' if '?' not in path else '&'
|
||||
query = f'/v{version}/{path}app={self._APP}'
|
||||
if self._token:
|
||||
query += f'&token={self._token}'
|
||||
return query + ''.join(f'&{name}={val}' for name, val in kwargs.items())
|
||||
|
||||
def _sign_query(self, path):
|
||||
timestamp = int(time.time())
|
||||
query = self._api_query(path, version=5)
|
||||
sig = hmac.new(
|
||||
self._APP_SECRET.encode('ascii'), f'{query}&t={timestamp}'.encode('ascii'), hashlib.sha1).hexdigest()
|
||||
return timestamp, sig, self._API_URL_TEMPLATE % query
|
||||
|
||||
def _call_api(
|
||||
self, path, video_id, note='Downloading JSON metadata', data=None, query=None, fatal=True):
|
||||
if query is None:
|
||||
timestamp, sig, url = self._sign_query(path)
|
||||
else:
|
||||
url = self._API_URL_TEMPLATE % self._api_query(path, version=4)
|
||||
resp = self._download_json(
|
||||
url, video_id, note, fatal=fatal, query=query,
|
||||
data=json.dumps(data).encode() if data else None,
|
||||
headers=({'x-viki-app-ver': self._APP_VERSION} if data
|
||||
else self._stream_headers(timestamp, sig) if query is None
|
||||
else None), expected_status=400) or {}
|
||||
|
||||
self._raise_error(resp.get('error'), fatal)
|
||||
return resp
|
||||
|
||||
def _raise_error(self, error, fatal=True):
|
||||
if error is None:
|
||||
return
|
||||
msg = f'{self.IE_NAME} said: {error}'
|
||||
if fatal:
|
||||
raise ExtractorError(msg, expected=True)
|
||||
else:
|
||||
self.report_warning(msg)
|
||||
|
||||
def _check_errors(self, data):
|
||||
for reason, status in (data.get('blocking') or {}).items():
|
||||
if status and reason in self._ERRORS:
|
||||
message = self._ERRORS[reason]
|
||||
if reason == 'geo':
|
||||
self.raise_geo_restricted(msg=message)
|
||||
elif reason == 'paywall':
|
||||
if try_get(data, lambda x: x['paywallable']['tvod']):
|
||||
self._raise_error('This video is for rent only or TVOD (Transactional Video On demand)')
|
||||
self.raise_login_required(message)
|
||||
self._raise_error(message)
|
||||
|
||||
def _perform_login(self, username, password):
|
||||
self._token = self._call_api(
|
||||
'sessions.json', None, 'Logging in', fatal=False,
|
||||
data={'username': username, 'password': password}).get('token')
|
||||
if not self._token:
|
||||
self.report_warning('Login Failed: Unable to get session token')
|
||||
|
||||
@staticmethod
|
||||
def dict_selection(dict_obj, preferred_key):
|
||||
if preferred_key in dict_obj:
|
||||
return dict_obj[preferred_key]
|
||||
return (list(filter(None, dict_obj.values())) or [None])[0]
|
||||
|
||||
|
||||
class VikiIE(VikiBaseIE):
|
||||
IE_NAME = 'viki'
|
||||
_VALID_URL = rf'{VikiBaseIE._VALID_URL_BASE}(?:videos|player)/(?P<id>[0-9]+v)'
|
||||
_TESTS = [{
|
||||
'note': 'Free non-DRM video with storyboards in MPD',
|
||||
'url': 'https://www.viki.com/videos/1175236v-choosing-spouse-by-lottery-episode-1',
|
||||
'info_dict': {
|
||||
'id': '1175236v',
|
||||
'ext': 'mp4',
|
||||
'title': 'Choosing Spouse by Lottery - Episode 1',
|
||||
'timestamp': 1606463239,
|
||||
'age_limit': 13,
|
||||
'uploader': 'FCC',
|
||||
'upload_date': '20201127',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.viki.com/videos/1023585v-heirs-episode-14',
|
||||
'info_dict': {
|
||||
'id': '1023585v',
|
||||
'ext': 'mp4',
|
||||
'title': 'Heirs - Episode 14',
|
||||
'uploader': 'SBS Contents Hub',
|
||||
'timestamp': 1385047627,
|
||||
'upload_date': '20131121',
|
||||
'age_limit': 13,
|
||||
'duration': 3570,
|
||||
'episode_number': 14,
|
||||
},
|
||||
'skip': 'Blocked in the US',
|
||||
}, {
|
||||
# clip
|
||||
'url': 'http://www.viki.com/videos/1067139v-the-avengers-age-of-ultron-press-conference',
|
||||
'md5': '86c0b5dbd4d83a6611a79987cc7a1989',
|
||||
'info_dict': {
|
||||
'id': '1067139v',
|
||||
'ext': 'mp4',
|
||||
'title': "'The Avengers: Age of Ultron' Press Conference",
|
||||
'description': 'md5:d70b2f9428f5488321bfe1db10d612ea',
|
||||
'duration': 352,
|
||||
'timestamp': 1430380829,
|
||||
'upload_date': '20150430',
|
||||
'uploader': 'Arirang TV',
|
||||
'like_count': int,
|
||||
'age_limit': 0,
|
||||
},
|
||||
'skip': 'Sorry. There was an error loading this video',
|
||||
}, {
|
||||
'url': 'http://www.viki.com/videos/1048879v-ankhon-dekhi',
|
||||
'info_dict': {
|
||||
'id': '1048879v',
|
||||
'ext': 'mp4',
|
||||
'title': 'Ankhon Dekhi',
|
||||
'duration': 6512,
|
||||
'timestamp': 1408532356,
|
||||
'upload_date': '20140820',
|
||||
'uploader': 'Spuul',
|
||||
'like_count': int,
|
||||
'age_limit': 13,
|
||||
},
|
||||
'skip': 'Blocked in the US',
|
||||
}, {
|
||||
# episode
|
||||
'url': 'http://www.viki.com/videos/44699v-boys-over-flowers-episode-1',
|
||||
'md5': '0a53dc252e6e690feccd756861495a8c',
|
||||
'info_dict': {
|
||||
'id': '44699v',
|
||||
'ext': 'mp4',
|
||||
'title': 'Boys Over Flowers - Episode 1',
|
||||
'description': 'md5:b89cf50038b480b88b5b3c93589a9076',
|
||||
'duration': 4172,
|
||||
'timestamp': 1270496524,
|
||||
'upload_date': '20100405',
|
||||
'uploader': 'group8',
|
||||
'like_count': int,
|
||||
'age_limit': 13,
|
||||
'episode_number': 1,
|
||||
},
|
||||
}, {
|
||||
# youtube external
|
||||
'url': 'http://www.viki.com/videos/50562v-poor-nastya-complete-episode-1',
|
||||
'md5': '63f8600c1da6f01b7640eee7eca4f1da',
|
||||
'info_dict': {
|
||||
'id': '50562v',
|
||||
'ext': 'webm',
|
||||
'title': 'Poor Nastya [COMPLETE] - Episode 1',
|
||||
'description': '',
|
||||
'duration': 606,
|
||||
'timestamp': 1274949505,
|
||||
'upload_date': '20101213',
|
||||
'uploader': 'ad14065n',
|
||||
'uploader_id': 'ad14065n',
|
||||
'like_count': int,
|
||||
'age_limit': 13,
|
||||
},
|
||||
'skip': 'Page not found!',
|
||||
}, {
|
||||
'url': 'http://www.viki.com/player/44699v',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# non-English description
|
||||
'url': 'http://www.viki.com/videos/158036v-love-in-magic',
|
||||
'md5': '41faaba0de90483fb4848952af7c7d0d',
|
||||
'info_dict': {
|
||||
'id': '158036v',
|
||||
'ext': 'mp4',
|
||||
'uploader': 'I Planet Entertainment',
|
||||
'upload_date': '20111122',
|
||||
'timestamp': 1321985454,
|
||||
'description': 'md5:44b1e46619df3a072294645c770cef36',
|
||||
'title': 'Love In Magic',
|
||||
'age_limit': 13,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
video = self._call_api(f'videos/{video_id}.json', video_id, 'Downloading video JSON', query={})
|
||||
self._check_errors(video)
|
||||
|
||||
title = try_get(video, lambda x: x['titles']['en'], str)
|
||||
episode_number = int_or_none(video.get('number'))
|
||||
if not title:
|
||||
title = f'Episode {episode_number}' if video.get('type') == 'episode' else video.get('id') or video_id
|
||||
container_titles = try_get(video, lambda x: x['container']['titles'], dict) or {}
|
||||
container_title = self.dict_selection(container_titles, 'en')
|
||||
title = f'{container_title} - {title}'
|
||||
|
||||
thumbnails = [{
|
||||
'id': thumbnail_id,
|
||||
'url': thumbnail['url'],
|
||||
} for thumbnail_id, thumbnail in (video.get('images') or {}).items() if thumbnail.get('url')]
|
||||
|
||||
resp = self._call_api(
|
||||
f'playback_streams/{video_id}.json?drms=dt3&device_id={self._DEVICE_ID}',
|
||||
video_id, 'Downloading video streams JSON')['main'][0]
|
||||
|
||||
stream_id = try_get(resp, lambda x: x['properties']['track']['stream_id'])
|
||||
subtitles = dict((lang, [{
|
||||
'ext': ext,
|
||||
'url': self._API_URL_TEMPLATE % self._api_query(
|
||||
f'videos/{video_id}/auth_subtitles/{lang}.{ext}', stream_id=stream_id),
|
||||
} for ext in ('srt', 'vtt')]) for lang in (video.get('subtitle_completions') or {}))
|
||||
|
||||
mpd_url = resp['url']
|
||||
# 720p is hidden in another MPD which can be found in the current manifest content
|
||||
mpd_content = self._download_webpage(mpd_url, video_id, note='Downloading initial MPD manifest')
|
||||
mpd_url = self._search_regex(
|
||||
r'(?mi)<BaseURL>(http.+.mpd)', mpd_content, 'new manifest', default=mpd_url)
|
||||
if 'mpdhd_high' not in mpd_url and 'sig=' not in mpd_url:
|
||||
# Modify the URL to get 1080p
|
||||
mpd_url = mpd_url.replace('mpdhd', 'mpdhd_high')
|
||||
formats = self._extract_mpd_formats(mpd_url, video_id)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'title': title,
|
||||
'description': self.dict_selection(video.get('descriptions', {}), 'en'),
|
||||
'duration': int_or_none(video.get('duration')),
|
||||
'timestamp': parse_iso8601(video.get('created_at')),
|
||||
'uploader': video.get('author'),
|
||||
'uploader_url': video.get('author_url'),
|
||||
'like_count': int_or_none(try_get(video, lambda x: x['likes']['count'])),
|
||||
'age_limit': parse_age_limit(video.get('rating')),
|
||||
'thumbnails': thumbnails,
|
||||
'subtitles': subtitles,
|
||||
'episode_number': episode_number,
|
||||
}
|
||||
|
||||
|
||||
class VikiChannelIE(VikiBaseIE):
|
||||
IE_NAME = 'viki:channel'
|
||||
_VALID_URL = rf'{VikiBaseIE._VALID_URL_BASE}(?:tv|news|movies|artists)/(?P<id>[0-9]+c)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.viki.com/tv/50c-boys-over-flowers',
|
||||
'info_dict': {
|
||||
'id': '50c',
|
||||
'title': 'Boys Over Flowers',
|
||||
'description': 'md5:804ce6e7837e1fd527ad2f25420f4d59',
|
||||
},
|
||||
'playlist_mincount': 51,
|
||||
}, {
|
||||
'url': 'http://www.viki.com/tv/1354c-poor-nastya-complete',
|
||||
'info_dict': {
|
||||
'id': '1354c',
|
||||
'title': 'Poor Nastya [COMPLETE]',
|
||||
'description': 'md5:05bf5471385aa8b21c18ad450e350525',
|
||||
},
|
||||
'playlist_count': 127,
|
||||
'skip': 'Page not found',
|
||||
}, {
|
||||
'url': 'http://www.viki.com/news/24569c-showbiz-korea',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.viki.com/movies/22047c-pride-and-prejudice-2005',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.viki.com/artists/2141c-shinee',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
_video_types = ('episodes', 'movies', 'clips', 'trailers')
|
||||
|
||||
def _entries(self, channel_id):
|
||||
params = {
|
||||
'app': self._APP, 'token': self._token, 'only_ids': 'true',
|
||||
'direction': 'asc', 'sort': 'number', 'per_page': 30,
|
||||
}
|
||||
video_types = self._configuration_arg('video_types') or self._video_types
|
||||
for video_type in video_types:
|
||||
if video_type not in self._video_types:
|
||||
self.report_warning(f'Unknown video_type: {video_type}')
|
||||
page_num = 0
|
||||
while True:
|
||||
page_num += 1
|
||||
params['page'] = page_num
|
||||
res = self._call_api(
|
||||
f'containers/{channel_id}/{video_type}.json', channel_id, query=params, fatal=False,
|
||||
note=f'Downloading {video_type.title()} JSON page {page_num}')
|
||||
|
||||
for video_id in res.get('response') or []:
|
||||
yield self.url_result(f'https://www.viki.com/videos/{video_id}', VikiIE.ie_key(), video_id)
|
||||
if not res.get('more'):
|
||||
break
|
||||
|
||||
def _real_extract(self, url):
|
||||
channel_id = self._match_id(url)
|
||||
channel = self._call_api(f'containers/{channel_id}.json', channel_id, 'Downloading channel JSON')
|
||||
self._check_errors(channel)
|
||||
return self.playlist_result(
|
||||
self._entries(channel_id), channel_id,
|
||||
self.dict_selection(channel['titles'], 'en'),
|
||||
self.dict_selection(channel['descriptions'], 'en'))
|
@ -1,6 +1,7 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import io
|
||||
import itertools
|
||||
import math
|
||||
import re
|
||||
import urllib.parse
|
||||
@ -31,9 +32,9 @@ if curl_cffi is None:
|
||||
|
||||
curl_cffi_version = tuple(map(int, re.split(r'[^\d]+', curl_cffi.__version__)[:3]))
|
||||
|
||||
if curl_cffi_version != (0, 5, 10) and not ((0, 7, 0) <= curl_cffi_version < (0, 7, 2)):
|
||||
if curl_cffi_version != (0, 5, 10) and not (0, 10) <= curl_cffi_version:
|
||||
curl_cffi._yt_dlp__version = f'{curl_cffi.__version__} (unsupported)'
|
||||
raise ImportError('Only curl_cffi versions 0.5.10, 0.7.0 and 0.7.1 are supported')
|
||||
raise ImportError('Only curl_cffi versions 0.5.10 and 0.10.x are supported')
|
||||
|
||||
import curl_cffi.requests
|
||||
from curl_cffi.const import CurlECode, CurlOpt
|
||||
@ -97,7 +98,7 @@ class CurlCFFIResponseAdapter(Response):
|
||||
return self.fp.read(amt)
|
||||
except curl_cffi.requests.errors.RequestsError as e:
|
||||
if e.code == CurlECode.PARTIAL_FILE:
|
||||
content_length = int_or_none(e.response.headers.get('Content-Length'))
|
||||
content_length = e.response and int_or_none(e.response.headers.get('Content-Length'))
|
||||
raise IncompleteRead(
|
||||
partial=self.fp.bytes_read,
|
||||
expected=content_length - self.fp.bytes_read if content_length is not None else None,
|
||||
@ -105,6 +106,51 @@ class CurlCFFIResponseAdapter(Response):
|
||||
raise TransportError(cause=e) from e
|
||||
|
||||
|
||||
# See: https://github.com/lexiforest/curl_cffi?tab=readme-ov-file#supported-impersonate-browsers
|
||||
# https://github.com/lexiforest/curl-impersonate?tab=readme-ov-file#supported-browsers
|
||||
BROWSER_TARGETS: dict[tuple[int, ...], dict[str, ImpersonateTarget]] = {
|
||||
(0, 5): {
|
||||
'chrome99': ImpersonateTarget('chrome', '99', 'windows', '10'),
|
||||
'chrome99_android': ImpersonateTarget('chrome', '99', 'android', '12'),
|
||||
'chrome100': ImpersonateTarget('chrome', '100', 'windows', '10'),
|
||||
'chrome101': ImpersonateTarget('chrome', '101', 'windows', '10'),
|
||||
'chrome104': ImpersonateTarget('chrome', '104', 'windows', '10'),
|
||||
'chrome107': ImpersonateTarget('chrome', '107', 'windows', '10'),
|
||||
'chrome110': ImpersonateTarget('chrome', '110', 'windows', '10'),
|
||||
'edge99': ImpersonateTarget('edge', '99', 'windows', '10'),
|
||||
'edge101': ImpersonateTarget('edge', '101', 'windows', '10'),
|
||||
'safari15_3': ImpersonateTarget('safari', '15.3', 'macos', '11'),
|
||||
'safari15_5': ImpersonateTarget('safari', '15.5', 'macos', '12'),
|
||||
},
|
||||
(0, 7): {
|
||||
'chrome116': ImpersonateTarget('chrome', '116', 'windows', '10'),
|
||||
'chrome119': ImpersonateTarget('chrome', '119', 'macos', '14'),
|
||||
'chrome120': ImpersonateTarget('chrome', '120', 'macos', '14'),
|
||||
'chrome123': ImpersonateTarget('chrome', '123', 'macos', '14'),
|
||||
'chrome124': ImpersonateTarget('chrome', '124', 'macos', '14'),
|
||||
'safari17_0': ImpersonateTarget('safari', '17.0', 'macos', '14'),
|
||||
'safari17_2_ios': ImpersonateTarget('safari', '17.2', 'ios', '17.2'),
|
||||
},
|
||||
(0, 9): {
|
||||
'safari15_3': ImpersonateTarget('safari', '15.3', 'macos', '14'),
|
||||
'safari15_5': ImpersonateTarget('safari', '15.5', 'macos', '14'),
|
||||
'chrome119': ImpersonateTarget('chrome', '119', 'macos', '14'),
|
||||
'chrome120': ImpersonateTarget('chrome', '120', 'macos', '14'),
|
||||
'chrome123': ImpersonateTarget('chrome', '123', 'macos', '14'),
|
||||
'chrome124': ImpersonateTarget('chrome', '124', 'macos', '14'),
|
||||
'chrome131': ImpersonateTarget('chrome', '131', 'macos', '14'),
|
||||
'chrome131_android': ImpersonateTarget('chrome', '131', 'android', '14'),
|
||||
'chrome133a': ImpersonateTarget('chrome', '133', 'macos', '15'),
|
||||
'firefox133': ImpersonateTarget('firefox', '133', 'macos', '14'),
|
||||
'safari18_0': ImpersonateTarget('safari', '18.0', 'macos', '15'),
|
||||
'safari18_0_ios': ImpersonateTarget('safari', '18.0', 'ios', '18.0'),
|
||||
},
|
||||
(0, 10): {
|
||||
'firefox135': ImpersonateTarget('firefox', '135', 'macos', '14'),
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
@register_rh
|
||||
class CurlCFFIRH(ImpersonateRequestHandler, InstanceStoreMixin):
|
||||
RH_NAME = 'curl_cffi'
|
||||
@ -112,30 +158,21 @@ class CurlCFFIRH(ImpersonateRequestHandler, InstanceStoreMixin):
|
||||
_SUPPORTED_FEATURES = (Features.NO_PROXY, Features.ALL_PROXY)
|
||||
_SUPPORTED_PROXY_SCHEMES = ('http', 'https', 'socks4', 'socks4a', 'socks5', 'socks5h')
|
||||
_SUPPORTED_IMPERSONATE_TARGET_MAP = {
|
||||
**({
|
||||
ImpersonateTarget('chrome', '124', 'macos', '14'): curl_cffi.requests.BrowserType.chrome124,
|
||||
ImpersonateTarget('chrome', '123', 'macos', '14'): curl_cffi.requests.BrowserType.chrome123,
|
||||
ImpersonateTarget('chrome', '120', 'macos', '14'): curl_cffi.requests.BrowserType.chrome120,
|
||||
ImpersonateTarget('chrome', '119', 'macos', '14'): curl_cffi.requests.BrowserType.chrome119,
|
||||
ImpersonateTarget('chrome', '116', 'windows', '10'): curl_cffi.requests.BrowserType.chrome116,
|
||||
} if curl_cffi_version >= (0, 7, 0) else {}),
|
||||
ImpersonateTarget('chrome', '110', 'windows', '10'): curl_cffi.requests.BrowserType.chrome110,
|
||||
ImpersonateTarget('chrome', '107', 'windows', '10'): curl_cffi.requests.BrowserType.chrome107,
|
||||
ImpersonateTarget('chrome', '104', 'windows', '10'): curl_cffi.requests.BrowserType.chrome104,
|
||||
ImpersonateTarget('chrome', '101', 'windows', '10'): curl_cffi.requests.BrowserType.chrome101,
|
||||
ImpersonateTarget('chrome', '100', 'windows', '10'): curl_cffi.requests.BrowserType.chrome100,
|
||||
ImpersonateTarget('chrome', '99', 'windows', '10'): curl_cffi.requests.BrowserType.chrome99,
|
||||
ImpersonateTarget('edge', '101', 'windows', '10'): curl_cffi.requests.BrowserType.edge101,
|
||||
ImpersonateTarget('edge', '99', 'windows', '10'): curl_cffi.requests.BrowserType.edge99,
|
||||
**({
|
||||
ImpersonateTarget('safari', '17.0', 'macos', '14'): curl_cffi.requests.BrowserType.safari17_0,
|
||||
} if curl_cffi_version >= (0, 7, 0) else {}),
|
||||
ImpersonateTarget('safari', '15.5', 'macos', '12'): curl_cffi.requests.BrowserType.safari15_5,
|
||||
ImpersonateTarget('safari', '15.3', 'macos', '11'): curl_cffi.requests.BrowserType.safari15_3,
|
||||
ImpersonateTarget('chrome', '99', 'android', '12'): curl_cffi.requests.BrowserType.chrome99_android,
|
||||
**({
|
||||
ImpersonateTarget('safari', '17.2', 'ios', '17.2'): curl_cffi.requests.BrowserType.safari17_2_ios,
|
||||
} if curl_cffi_version >= (0, 7, 0) else {}),
|
||||
target: name if curl_cffi_version >= (0, 9) else curl_cffi.requests.BrowserType[name]
|
||||
for name, target in dict(sorted(itertools.chain.from_iterable(
|
||||
targets.items()
|
||||
for version, targets in BROWSER_TARGETS.items()
|
||||
if curl_cffi_version >= version
|
||||
), key=lambda x: (
|
||||
# deprioritize mobile targets since they give very different behavior
|
||||
x[1].os not in ('ios', 'android'),
|
||||
# prioritize edge < firefox < safari < chrome
|
||||
('edge', 'firefox', 'safari', 'chrome').index(x[1].client),
|
||||
# prioritize newest version
|
||||
float(x[1].version) if x[1].version else 0,
|
||||
# group by os name
|
||||
x[1].os,
|
||||
), reverse=True)).items()
|
||||
}
|
||||
|
||||
def _create_instance(self, cookiejar=None):
|
||||
|
Loading…
x
Reference in New Issue
Block a user