fix simplex parsing

This commit is contained in:
cynthia 2025-04-14 23:26:46 +01:00
parent 13d39dc5c2
commit 013673fffb
2 changed files with 9 additions and 6 deletions

View file

@ -20,17 +20,18 @@ hostname_pattern = re.compile(r'^(?:[a-zA-Z0-9.-]+|[0-9]{1,3}(?:\.[0-9]{1,3}){3}
def IsSimpleXChatroomValid(url: str) -> bool:
"""Validate the SimpleX chatroom URL."""
REQUIRED_SUBSTRING = "contact#/?v=2-7&smp=smp%3A%2F"
REQUIRED_SUBSTRING2 = "contact/#/?v=2-7&smp=smp%3A%2F"
# Step 1: Check if it starts with http://, https://, or simplex:/
if url.startswith(('http://', 'https://', 'simplex:/')):
# Step 1.5: If http:// or https://, check for valid clearnet or onion domain
if url.startswith(('http://', 'https://')):
return IsUrlValid(url)
if url.startswith(('http://', 'https://')) and not IsUrlValid(url):
return False
elif not url.startswith('simplex:/'):
return False # Must start with one of the valid protocols
# Step 2: Check for the presence of the required substring
if REQUIRED_SUBSTRING not in url:
if REQUIRED_SUBSTRING not in url and REQUIRED_SUBSTRING2 not in url:
return False # Required substring not found
# Step 3: Extract the part after "smp=smp%3A%2F"