github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[ie/bilibili] Fix --geo-verification-proxy support (#9817)

Browse source 
Closes #9797
Authored by: fireattack
This commit is contained in:
fireattack 2024-05-09 05:24:44 +08:00 committed by GitHub
parent 06d52c8731
commit 2338827072
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 10 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
yt_dlp/extractor/bilibili.py
View file

@ -93,11 +93,11 @@ def extract_formats(self, play_info):
return formats return formats
def _download_playinfo(self, video_id, cid): def _download_playinfo(self, video_id, cid, headers=None):
return self._download_json( return self._download_json(
'https://api.bilibili.com/x/player/playurl', video_id, 'https://api.bilibili.com/x/player/playurl', video_id,
query={'bvid': video_id, 'cid': cid, 'fnval': 4048}, query={'bvid': video_id, 'cid': cid, 'fnval': 4048},
note=f'Downloading video formats for cid {cid}')['data'] note=f'Downloading video formats for cid {cid}', headers=headers)['data']
def json2srt(self, json_data): def json2srt(self, json_data):
srt_data = '' srt_data = ''
@ -493,7 +493,8 @@ class BiliBiliIE(BilibiliBaseIE):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage, urlh = self._download_webpage_handle(url, video_id) headers = self.geo_verification_headers()
webpage, urlh = self._download_webpage_handle(url, video_id, headers=headers)
if not self._match_valid_url(urlh.url): if not self._match_valid_url(urlh.url):
return self.url_result(urlh.url) return self.url_result(urlh.url)
@ -531,7 +532,7 @@ def _real_extract(self, url):
self._download_json( self._download_json(
'https://api.bilibili.com/x/player/pagelist', video_id, 'https://api.bilibili.com/x/player/pagelist', video_id,
fatal=False, query={'bvid': video_id, 'jsonp': 'jsonp'}, fatal=False, query={'bvid': video_id, 'jsonp': 'jsonp'},
note='Extracting videos in anthology'), note='Extracting videos in anthology', headers=headers),
'data', expected_type=list) or [] 'data', expected_type=list) or []
is_anthology = len(page_list_json) > 1 is_anthology = len(page_list_json) > 1
@ -552,7 +553,7 @@ def _real_extract(self, url):
festival_info = {} festival_info = {}
if is_festival: if is_festival:
play_info = self._download_playinfo(video_id, cid) play_info = self._download_playinfo(video_id, cid, headers=headers)
festival_info = traverse_obj(initial_state, { festival_info = traverse_obj(initial_state, {
'uploader': ('videoInfo', 'upName'), 'uploader': ('videoInfo', 'upName'),
@ -666,14 +667,15 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
def _real_extract(self, url): def _real_extract(self, url):
episode_id = self._match_id(url) episode_id = self._match_id(url)
webpage = self._download_webpage(url, episode_id) headers = self.geo_verification_headers()
webpage = self._download_webpage(url, episode_id, headers=headers)
if '您所在的地区无法观看本片' in webpage: if '您所在的地区无法观看本片' in webpage:
raise GeoRestrictedError('This video is restricted') raise GeoRestrictedError('This video is restricted')
elif '正在观看预览，大会员免费看全片' in webpage: elif '正在观看预览，大会员免费看全片' in webpage:
self.raise_login_required('This video is for premium members only') self.raise_login_required('This video is for premium members only')
headers = {'Referer': url, **self.geo_verification_headers()} headers['Referer'] = url
play_info = self._download_json( play_info = self._download_json(
'https://api.bilibili.com/pgc/player/web/v2/playurl', episode_id, 'https://api.bilibili.com/pgc/player/web/v2/playurl', episode_id,
'Extracting episode', query={'fnval': '4048', 'ep_id': episode_id}, 'Extracting episode', query={'fnval': '4048', 'ep_id': episode_id},
@ -724,7 +726,7 @@ def _real_extract(self, url):
'duration': float_or_none(play_info.get('timelength'), scale=1000), 'duration': float_or_none(play_info.get('timelength'), scale=1000),
'subtitles': self.extract_subtitles(episode_id, episode_info.get('cid'), aid=aid), 'subtitles': self.extract_subtitles(episode_id, episode_info.get('cid'), aid=aid),
'__post_extractor': self.extract_comments(aid), '__post_extractor': self.extract_comments(aid),
'http_headers': headers, 'http_headers': {'Referer': url},
} }