From 3aa0156e05662923d130ddbc1c82596e38c01a00 Mon Sep 17 00:00:00 2001 From: sepro Date: Sat, 14 Sep 2024 02:15:07 +0200 Subject: [PATCH] [ie/Xinpianchang] Fix extractor (#10950) Authored by: seproDev --- yt_dlp/extractor/xinpianchang.py | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-) diff --git a/yt_dlp/extractor/xinpianchang.py b/yt_dlp/extractor/xinpianchang.py index 10849916b..23ed9270d 100644 --- a/yt_dlp/extractor/xinpianchang.py +++ b/yt_dlp/extractor/xinpianchang.py @@ -3,16 +3,13 @@ from ..utils import ( int_or_none, str_or_none, try_get, - update_url_query, url_or_none, ) class XinpianchangIE(InfoExtractor): - _WORKING = False - _VALID_URL = r'https?://www\.xinpianchang\.com/(?P[^/]+?)(?:\D|$)' - IE_NAME = 'xinpianchang' - IE_DESC = 'xinpianchang.com' + _VALID_URL = r'https?://(www\.)?xinpianchang\.com/(?Pa\d+)' + IE_DESC = '新片场' _TESTS = [{ 'url': 'https://www.xinpianchang.com/a11766551', 'info_dict': { @@ -49,11 +46,11 @@ class XinpianchangIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id=video_id) - domain = self.find_value_with_regex(var='requireNewDomain', webpage=webpage) - vid = self.find_value_with_regex(var='vid', webpage=webpage) - app_key = self.find_value_with_regex(var='modeServerAppKey', webpage=webpage) - api = update_url_query(f'{domain}/mod/api/v2/media/{vid}', {'appKey': app_key}) - data = self._download_json(api, video_id=video_id)['data'] + video_data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['detail']['video'] + + data = self._download_json( + f'https://mod-api.xinpianchang.com/mod/api/v2/media/{video_data["vid"]}', video_id, + query={'appKey': video_data['appKey']})['data'] formats, subtitles = [], {} for k, v in data.get('resource').items(): if k in ('dash', 'hls'): @@ -72,6 +69,10 @@ class XinpianchangIE(InfoExtractor): 'width': int_or_none(prog.get('width')), 'height': int_or_none(prog.get('height')), 'ext': 'mp4', + 'http_headers': { + # NB: Server returns 403 without the Range header + 'Range': 'bytes=0-', + }, } for prog in v if prog.get('url') or []]) return { @@ -87,6 +88,3 @@ class XinpianchangIE(InfoExtractor): 'formats': formats, 'subtitles': subtitles, } - - def find_value_with_regex(self, var, webpage): - return self._search_regex(rf'var\s{var}\s=\s\"(?P[^\"]+)\"', webpage, name=var)