OpenSource/telegram-crawler
OpenSource/telegram-crawler
1
0
Fork 0
mirror of https://github.com/MarshalX/telegram-crawler.git synced 2025-01-20 16:15:08 +01:00
Code Issues Projects Releases Packages Wiki Activity

fix wildcard

Browse source
This commit is contained in:
Ilya (Marshal) 2022-10-29 23:13:34 +02:00
parent 1b994f6df3
commit 621e96143f
1 changed files with 8 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
make_tracked_links_list.py
View file

@ -49,6 +49,10 @@ HIDDEN_URLS = {
'webappcontent.telegram.org/cafe', # demo 2
# 'a-webappcontent.stel.com/demo',
# 'a-webappcontent.stel.com/cafe',
# 'fragment.com/about',
# 'fragment.com/privacy',
# 'fragment.com/terms',
}
ADDITIONAL_URLS = {
'raw.githubusercontent.com/telegramdesktop/tdesktop/dev/Telegram/Resources/tl/mtproto.tl',
@ -280,6 +284,10 @@ def cleanup_links(links: set[str]) -> set[str]:
if '@' in link_parts[0]:
continue
# fix wildcard
if link.startswith('.'):
link = link[1:]
cleaned_links.add(link)
return cleaned_links