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

feat: general link handling

Browse source
This commit is contained in:
草师傅 2025-07-31 13:48:31 +08:00
parent e4f70dd729
commit 1fd6d348c3
2 changed files with 29 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

2
assets/LegitimateURLShortener.txt
View file

@ -5164,3 +5164,5 @@ buffalonews.com##+js(set, lee_trkLinkSrc, noopFunc)
!#if !ext_ublock !#if !ext_ublock
!#include uBO%20list%20extensions/LegitimateURLShortener%20—%20AdGuardOnlyEntries.txt !#include uBO%20list%20extensions/LegitimateURLShortener%20—%20AdGuardOnlyEntries.txt
!#endif !#endif
$removeparam=utm_from

40
core/link.py
View file

@ -39,16 +39,14 @@ def should_remove_param(url, filter_rule):
def extend_short_urls(url): def extend_short_urls(url):
""" 扩展短链接 """ """ 扩展短链接 """
r = requests.get(url) r = requests.get(url, allow_redirects=False)
if 'tb.cn' in urlparse(url).hostname: if 'tb.cn' in urlparse(url).hostname:
# 淘宝短链接特殊处理 # 淘宝短链接特殊处理
html_content = r.text html_content = r.text
url = extract_tb_url_from_html(html_content) url = extract_tb_url_from_html(html_content)
if not url: if not url:
return url return url
if r.status_code != 200: if r.status_code in [301,302,304,307,308] and 'Location' in r.headers:
return url
elif r.status_code in [301,302,304,307,308]:
return r.headers['Location'] return r.headers['Location']
return url return url
@ -124,8 +122,8 @@ 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 ['mall.bilibili.com','space.bilibili.com','live.bilibili.com']: elif parsed_url.hostname in ['www.bilibili.com','m.bilibili.com','bilibili.com','mall.bilibili.com','space.bilibili.com','live.bilibili.com']:
# 只保留spm_id_from参数，创建新的query_params # 不保留任何参数
new_query_params = {} new_query_params = {}
# 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)
@ -139,6 +137,9 @@ def transform_into_fixed_url(url):
if parsed_url.hostname in ['x.com', 'twitter.com']: if parsed_url.hostname in ['x.com', 'twitter.com']:
# 把 twitter 的链接转换为 fixupx.com # 把 twitter 的链接转换为 fixupx.com
return urlunparse(parsed_url._replace(netloc='i.fixupx.com')) return urlunparse(parsed_url._replace(netloc='i.fixupx.com'))
if parsed_url.hostname in ['bilibili.com', 'm.bilibili.com']:
# 把 bilibili 的链接转换为桌面端的 www.bilibili.com
return urlunparse(parsed_url._replace(netloc='www.bilibili.com'))
return url return url
@ -151,13 +152,26 @@ async def handle_links(message: Message):
# Extract URLs from message text # Extract URLs from message text
if message.text: if message.text:
urls = re.findall(url_pattern, message.text) urls = re.findall(url_pattern, message.text)
final_urls = []
for url in urls: for url in urls:
# Process each URL with your functions # 首先清理跟踪参数
cleaned_url = remove_tracking_params(url) cleaned_url = remove_tracking_params(url)
# 扩展短链接
extended_url = extend_short_urls(cleaned_url) extended_url = extend_short_urls(cleaned_url)
only_wl_params_url = reserve_whitelisted_params(extended_url) # 对于一些网站，只保留白名单中的参数
#untracked_url = remove_tracking_params(only_wl_params_url) if urlparse(extended_url).hostname in ['item.taobao.com','detail.tmall.com','h5.m.goofish.com','music.163.com','www.bilibili.com','m.bilibili.com','bilibili.com','mall.bilibili.com','space.bilibili.com','live.bilibili.com']:
# TODO: fix final_url = reserve_whitelisted_params(extended_url)
fixed_url = transform_into_fixed_url(only_wl_params_url) if urlparse(extended_url).hostname in ['bilibili.com', 'm.bilibili.com']:
# Do something with the processed URL final_url = transform_into_fixed_url(final_url)
await message.reply(f"清理完成：\n{fixed_url}") elif urlparse(extended_url).hostname in ['x.com', 'twitter.com']:
# 对于 Twitter 链接，转换为 fixupx.com
removed_tracking_url = remove_tracking_params(extended_url)
final_url = transform_into_fixed_url(removed_tracking_url)
else:
# 对于其他链接，直接对其进行跟踪参数清理
final_url = remove_tracking_params(extended_url)
final_urls.append(final_url)
# 回复处理后的链接
if final_urls:
await message.reply(f"{"\n".join(final_urls)}\n消息里有包含跟踪参数的链接，已经帮你转换了哦")