Garmelon/PFERD
1
0
Fork 0
mirror of https://github.com/Garmelon/PFERD.git synced 2026-04-12 15:35:05 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Remove size suffix for content pages

Browse source
This commit is contained in:
I-Al-Istannen 2023-08-27 11:42:25 +02:00
parent 2184ac8040
commit b54b3b979c
2 changed files with 3 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
PFERD/crawl/ilias/kit_ilias_html.py
View file

@ -377,7 +377,8 @@ class IliasPage:
for link in links:
url = self._abs_url_from_link(link)
name = _sanitize_path_name(link.getText().strip().replace("\t", ""))
name = re.sub(r"\([\d,.]+ [MK]B\)", "", link.getText()).strip().replace("\t", "")
name = _sanitize_path_name(name)
if "file_id" not in url:
_unexpected_html_warning()