gb/bot
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix: youtube and baidu link parsing

Browse source
This commit is contained in:
草师傅 2025-08-16 21:04:56 +08:00
parent a0016cd512
commit c4d49694a2
1 changed files with 17 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

18
core/link.py
View file

@ -14,7 +14,7 @@ from config import config
whitelist_param_links = ['www.iesdouyin.com','item.taobao.com', 'detail.tmall.com', 'h5.m.goofish.com', 'music.163.com', whitelist_param_links = ['www.iesdouyin.com','item.taobao.com', 'detail.tmall.com', 'h5.m.goofish.com', 'music.163.com',
'www.bilibili.com', 'm.bilibili.com', 'bilibili.com', 'mall.bilibili.com', 'www.bilibili.com', 'm.bilibili.com', 'bilibili.com', 'mall.bilibili.com',
'space.bilibili.com', 'live.bilibili.com','item.m.jd.com','item.jd.com', 'space.bilibili.com', 'live.bilibili.com','item.m.jd.com','item.jd.com',
'www.xiaohongshu.com','zhuanlan.zhihu.com'] 'www.xiaohongshu.com','zhuanlan.zhihu.com','www.baidu.com','www.youtube.com']
has_self_redirection_links = ['www.cnbeta.com.tw','m.cnbeta.com.tw','www.landiannews.com', 'www.bilibili.com'] has_self_redirection_links = ['www.cnbeta.com.tw','m.cnbeta.com.tw','www.landiannews.com', 'www.bilibili.com']
@ -174,6 +174,22 @@ def reserve_whitelisted_params(url):
# 重新构建URL # 重新构建URL
cleaned_query = urlencode(new_query_params, doseq=True) cleaned_query = urlencode(new_query_params, doseq=True)
return urlunparse(parsed_url._replace(query=cleaned_query)) return urlunparse(parsed_url._replace(query=cleaned_query))
elif parsed_url.hostname in ['www.baidu.com','www.youtube.com']:
new_query_params = {}
if parsed_url.hostname == 'www.baidu.com' and 'wd' in query_params:
# 百度搜索链接保留 wd 参数
new_query_params['wd'] = query_params['wd']
if parsed_url.hostname == 'www.youtube.com':
# YouTube 视频链接保留 v 参数
if 'v' in query_params:
new_query_params['v'] = query_params['v'] # 保留 v 参数
if 't' in query_params:
new_query_params['t'] = query_params['t'] # 保留 t 参数
if 'list' in query_params:
new_query_params['list'] = query_params['list'] # 保留 list 参数
# 重新构建URL
cleaned_query = urlencode(new_query_params, doseq=True)
return urlunparse(parsed_url._replace(query=cleaned_query))
elif parsed_url.hostname in ['chatglm.cn'] and query_params: elif parsed_url.hostname in ['chatglm.cn'] and query_params:
# 就你叫智谱啊 # 就你叫智谱啊
new_query_params = {'share_conversation_id': query_params['share_conversation_id']} new_query_params = {'share_conversation_id': query_params['share_conversation_id']}