Miroirs/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-28 22:24:34 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

generic extraction

Browse source
This commit is contained in:
c-basalt 2024-12-10 22:49:35 -05:00
parent 29a955d63d
commit 941c50b699
2 changed files with 23 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
yt_dlp/extractor/generic.py
View file

@ -2393,7 +2393,7 @@ class GenericIE(InfoExtractor):
full_response = self._request_webpage(url, video_id, headers=filter_dict({ full_response = self._request_webpage(url, video_id, headers=filter_dict({
'Accept-Encoding': 'identity', 'Accept-Encoding': 'identity',
'Referer': smuggled_data.get('referer'), 'Referer': smuggled_data.get('referer'),
}), impersonate=impersonate) }), impersonate=impersonate, expected_status=404)
except ExtractorError as e: except ExtractorError as e:
if not (isinstance(e.cause, HTTPError) and e.cause.status == 403 if not (isinstance(e.cause, HTTPError) and e.cause.status == 403
and e.cause.response.get_header('cf-mitigated') == 'challenge' and e.cause.response.get_header('cf-mitigated') == 'challenge'

31
yt_dlp/extractor/niconicochannelplus.py
View file

@ -93,6 +93,9 @@ class NiconicoChannelPlusBaseIE(InfoExtractor):
), ('data', 'fanclub_site', 'content_provider', 'age_limit', {int})) ), ('data', 'fanclub_site', 'content_provider', 'age_limit', {int}))
return self._CHANNEL_AGE_LIMIT[fanclub_site_id] return self._CHANNEL_AGE_LIMIT[fanclub_site_id]
def _is_channel_plus_webpage(self, webpage):
return 'GTM-KXT7G5G' in webpage or 'NicoGoogleTagManagerDataLayer' in webpage
class NiconicoChannelPlusIE(NiconicoChannelPlusBaseIE): class NiconicoChannelPlusIE(NiconicoChannelPlusBaseIE):
IE_NAME = 'NiconicoChannelPlus' IE_NAME = 'NiconicoChannelPlus'
@ -159,22 +162,25 @@ class NiconicoChannelPlusIE(NiconicoChannelPlusBaseIE):
'skip': 'subscriber only', 'skip': 'subscriber only',
}] }]
def _parse_video_id(self, url): def _extract_from_webpage(self, url, webpage):
parsed = urllib.parse.urlparse(url) if self._match_video_id(url) and self._is_channel_plus_webpage(webpage):
return re.search(r'/(?:video|live)/(?P<id>\w+)', parsed.path)[1] yield self._real_extract(url)
def _match_video_id(self, url):
return re.search(r'/(?:video|audio|live)/(?P<id>sm\w+)', urllib.parse.urlparse(url).path)
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._parse_video_id(url) video_id = self._match_video_id(url).group('id')
video_info = self._download_api_json(url, f'/video_pages/{video_id}', video_id, video_info = self._download_api_json(url, f'/video_pages/{video_id}', video_id,
note='Downloading video info')['data']['video_page'] note='Downloading video info')['data']['video_page']
live_status, session_payload, timestamp = self._parse_live_status(video_id, video_info) live_status, session_payload, timestamp = self._parse_live_status(video_id, video_info)
session_info = self._download_api_json( session_id = self._download_api_json(
url, f'/video_pages/{video_id}/session_ids', video_id, data=json.dumps(session_payload).encode(), url, f'/video_pages/{video_id}/session_ids', video_id, data=json.dumps(session_payload).encode(),
headers={'content-type': 'application/json'}, note='Downloading video session')['data'] headers={'content-type': 'application/json'}, note='Downloading video session')['data']['session_id']
formats = self._extract_m3u8_formats( formats = self._extract_m3u8_formats(
video_info['video_stream']['authenticated_url'].format(**session_info), video_id) video_info['video_stream']['authenticated_url'].format(session_id=session_id), video_id)
return { return {
'id': video_id, 'id': video_id,
@ -291,8 +297,7 @@ class NiconicoChannelPlusChannelBaseIE(NiconicoChannelPlusBaseIE):
for content_code in traverse_obj(response, ('data', 'video_pages', 'list', ..., 'content_code')): for content_code in traverse_obj(response, ('data', 'video_pages', 'list', ..., 'content_code')):
# "video/{content_code}" works for both VOD and live, but "live/{content_code}" doesn't work for VOD # "video/{content_code}" works for both VOD and live, but "live/{content_code}" doesn't work for VOD
yield self.url_result( yield self.url_result(f'{self._get_channel_url(site_url)}/video/{content_code}')
f'{self._get_channel_url(site_url)}/video/{content_code}', NiconicoChannelPlusIE)
class NiconicoChannelPlusChannelVideosIE(NiconicoChannelPlusChannelBaseIE): class NiconicoChannelPlusChannelVideosIE(NiconicoChannelPlusChannelBaseIE):
@ -381,6 +386,10 @@ class NiconicoChannelPlusChannelVideosIE(NiconicoChannelPlusChannelBaseIE):
'playlist_mincount': 6, 'playlist_mincount': 6,
}] }]
def _extract_from_webpage(self, url, webpage):
if re.search(r'/videos/?(?:[\?#]|$)', url) and self._is_channel_plus_webpage(webpage):
yield self._real_extract(url)
def _real_extract(self, url): def _real_extract(self, url):
""" """
API parameters: API parameters:
@ -444,6 +453,10 @@ class NiconicoChannelPlusChannelLivesIE(NiconicoChannelPlusChannelBaseIE):
'playlist_mincount': 6, 'playlist_mincount': 6,
}] }]
def _extract_from_webpage(self, url, webpage):
if re.search(r'/lives/?(?:[\?#]|$)', url) and self._is_channel_plus_webpage(webpage):
yield self._real_extract(url)
def _real_extract(self, url): def _real_extract(self, url):
""" """
API parameters: API parameters: