[ie/Xinpianchang] Fix extractor (#10950)

Authored by: seproDev
This commit is contained in:
sepro 2024-09-14 02:15:07 +02:00 committed by GitHub
parent 300c91274f
commit 3aa0156e05
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -3,16 +3,13 @@
int_or_none, int_or_none,
str_or_none, str_or_none,
try_get, try_get,
update_url_query,
url_or_none, url_or_none,
) )
class XinpianchangIE(InfoExtractor): class XinpianchangIE(InfoExtractor):
_WORKING = False _VALID_URL = r'https?://(www\.)?xinpianchang\.com/(?P<id>a\d+)'
_VALID_URL = r'https?://www\.xinpianchang\.com/(?P<id>[^/]+?)(?:\D|$)' IE_DESC = '新片场'
IE_NAME = 'xinpianchang'
IE_DESC = 'xinpianchang.com'
_TESTS = [{ _TESTS = [{
'url': 'https://www.xinpianchang.com/a11766551', 'url': 'https://www.xinpianchang.com/a11766551',
'info_dict': { 'info_dict': {
@ -49,11 +46,11 @@ class XinpianchangIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id=video_id) webpage = self._download_webpage(url, video_id=video_id)
domain = self.find_value_with_regex(var='requireNewDomain', webpage=webpage) video_data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['detail']['video']
vid = self.find_value_with_regex(var='vid', webpage=webpage)
app_key = self.find_value_with_regex(var='modeServerAppKey', webpage=webpage) data = self._download_json(
api = update_url_query(f'{domain}/mod/api/v2/media/{vid}', {'appKey': app_key}) f'https://mod-api.xinpianchang.com/mod/api/v2/media/{video_data["vid"]}', video_id,
data = self._download_json(api, video_id=video_id)['data'] query={'appKey': video_data['appKey']})['data']
formats, subtitles = [], {} formats, subtitles = [], {}
for k, v in data.get('resource').items(): for k, v in data.get('resource').items():
if k in ('dash', 'hls'): if k in ('dash', 'hls'):
@ -72,6 +69,10 @@ def _real_extract(self, url):
'width': int_or_none(prog.get('width')), 'width': int_or_none(prog.get('width')),
'height': int_or_none(prog.get('height')), 'height': int_or_none(prog.get('height')),
'ext': 'mp4', 'ext': 'mp4',
'http_headers': {
# NB: Server returns 403 without the Range header
'Range': 'bytes=0-',
},
} for prog in v if prog.get('url') or []]) } for prog in v if prog.get('url') or []])
return { return {
@ -87,6 +88,3 @@ def _real_extract(self, url):
'formats': formats, 'formats': formats,
'subtitles': subtitles, 'subtitles': subtitles,
} }
def find_value_with_regex(self, var, webpage):
return self._search_regex(rf'var\s{var}\s=\s\"(?P<vid>[^\"]+)\"', webpage, name=var)