Upgrade yt_dlp and download script

This commit is contained in:
2025-05-02 16:11:08 -05:00
parent 3a2e8eeb08
commit d68d9ce4f9
1194 changed files with 60099 additions and 44436 deletions

View File

@@ -5,11 +5,12 @@ from ..utils import (
ExtractorError,
lowercase_escape,
url_or_none,
urlencode_postdata,
)
class ChaturbateIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?:fullvideo/?\?.*?\bb=)?(?P<id>[^/?&#]+)'
_VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.(?P<tld>com|eu|global)/(?:fullvideo/?\?.*?\bb=)?(?P<id>[^/?&#]+)'
_TESTS = [{
'url': 'https://www.chaturbate.com/siswet19/',
'info_dict': {
@@ -29,16 +30,58 @@ class ChaturbateIE(InfoExtractor):
}, {
'url': 'https://en.chaturbate.com/siswet19/',
'only_matching': True,
}, {
'url': 'https://chaturbate.eu/siswet19/',
'only_matching': True,
}, {
'url': 'https://chaturbate.eu/fullvideo/?b=caylin',
'only_matching': True,
}, {
'url': 'https://chaturbate.global/siswet19/',
'only_matching': True,
}]
_ROOM_OFFLINE = 'Room is currently offline'
_ERROR_MAP = {
'offline': 'Room is currently offline',
'private': 'Room is currently in a private show',
'away': 'Performer is currently away',
'password protected': 'Room is password protected',
'hidden': 'Hidden session in progress',
}
def _real_extract(self, url):
video_id = self._match_id(url)
def _extract_from_api(self, video_id, tld):
response = self._download_json(
f'https://chaturbate.{tld}/get_edge_hls_url_ajax/', video_id,
data=urlencode_postdata({'room_slug': video_id}),
headers={
**self.geo_verification_headers(),
'X-Requested-With': 'XMLHttpRequest',
'Accept': 'application/json',
}, fatal=False, impersonate=True) or {}
m3u8_url = response.get('url')
if not m3u8_url:
status = response.get('room_status')
if error := self._ERROR_MAP.get(status):
raise ExtractorError(error, expected=True)
if status == 'public':
self.raise_geo_restricted()
self.report_warning(f'Got status "{status}" from API; falling back to webpage extraction')
return None
return {
'id': video_id,
'title': video_id,
'thumbnail': f'https://roomimg.stream.highwebmedia.com/ri/{video_id}.jpg',
'is_live': True,
'age_limit': 18,
'formats': self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True),
}
def _extract_from_html(self, video_id, tld):
webpage = self._download_webpage(
'https://chaturbate.com/%s/' % video_id, video_id,
headers=self.geo_verification_headers())
f'https://chaturbate.{tld}/{video_id}/', video_id,
headers=self.geo_verification_headers(), impersonate=True)
found_m3u8_urls = []
@@ -76,8 +119,8 @@ class ChaturbateIE(InfoExtractor):
webpage, 'error', group='error', default=None)
if not error:
if any(p in webpage for p in (
self._ROOM_OFFLINE, 'offline_tipping', 'tip_offline')):
error = self._ROOM_OFFLINE
self._ERROR_MAP['offline'], 'offline_tipping', 'tip_offline')):
error = self._ERROR_MAP['offline']
if error:
raise ExtractorError(error, expected=True)
raise ExtractorError('Unable to find stream URL')
@@ -85,7 +128,7 @@ class ChaturbateIE(InfoExtractor):
formats = []
for m3u8_url in m3u8_urls:
for known_id in ('fast', 'slow'):
if '_%s' % known_id in m3u8_url:
if f'_{known_id}' in m3u8_url:
m3u8_id = known_id
break
else:
@@ -99,8 +142,12 @@ class ChaturbateIE(InfoExtractor):
return {
'id': video_id,
'title': video_id,
'thumbnail': 'https://roomimg.stream.highwebmedia.com/ri/%s.jpg' % video_id,
'thumbnail': f'https://roomimg.stream.highwebmedia.com/ri/{video_id}.jpg',
'age_limit': self._rta_search(webpage),
'is_live': True,
'formats': formats,
}
def _real_extract(self, url):
video_id, tld = self._match_valid_url(url).group('id', 'tld')
return self._extract_from_api(video_id, tld) or self._extract_from_html(video_id, tld)