highperfocused/danswer
1
0
Fork 0
mirror of https://github.com/danswer-ai/danswer.git synced 2025-09-28 04:49:21 +02:00
Code Issues Packages Projects Releases Wiki Activity

Address issue with links for Google Sites connector

Browse Source
This commit is contained in:
Weves
2023-11-02 21:48:55 -07:00
committed by Chris Weaver
parent b0f76b97ef
commit 329824ab22
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
backend/danswer/connectors/google_site/connector.py
View File

@@ -1,4 +1,5 @@
import os import os
import re
import urllib.parse import urllib.parse
from typing import Any from typing import Any
from typing import cast from typing import cast
@@ -29,7 +30,9 @@ def process_link(element: BeautifulSoup | Tag) -> str:
href = urllib.parse.unquote(href) href = urllib.parse.unquote(href)
href = href.rstrip(".html").lower() href = href.rstrip(".html").lower()
href = href.replace("_", "") href = href.replace("_", "")
href = href.replace(" ", "-") href = re.sub(
r"([\s-]+)", "-", href
) # replace all whitespace/'-' groups with a single '-'
return href return href