mirrors/pferd
1
0
Fork 0
mirror of https://github.com/Garmelon/PFERD.git synced 2025-07-12 14:12:30 +02:00
Code Issues Packages Projects Releases Wiki Activity

Fix crawling of empty forum threads

Browse Source
This commit is contained in:
I-Al-Istannen
2025-03-09 23:44:25 +01:00
parent c8eff04ae0
commit 63f25277b0
1 changed files with 8 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
PFERD/crawl/ilias/kit_ilias_html.py
View File

@ -1387,16 +1387,18 @@ def parse_ilias_forum_export(forum_export: BeautifulSoup) -> list[IliasForumThre
title_tag = p title_tag = p
content_tag = cast(Optional[Tag], p.find_next_sibling("ul")) content_tag = cast(Optional[Tag], p.find_next_sibling("ul"))
if not content_tag:
# ILIAS allows users to delete the initial post while keeping the thread open
# This produces empty threads without *any* content.
# I am not sure why you would want this, but ILIAS makes it easy to do.
continue
title = cast(Tag, p.find("b")).text title = cast(Tag, p.find("b")).text
if ":" in title: if ":" in title:
title = title[title.find(":") + 1:] title = title[title.find(":") + 1:]
title = title.strip() title = title.strip()
if not content_tag or content_tag.find_previous_sibling("p") != title_tag:
# ILIAS allows users to delete the initial post while keeping the thread open
# This produces empty threads without *any* content.
# I am not sure why you would want this, but ILIAS makes it easy to do.
elements.append(IliasForumThread(title, title_tag, forum_export.new_tag("ul"), None))
continue
mtime = _guess_timestamp_from_forum_post_content(content_tag) mtime = _guess_timestamp_from_forum_post_content(content_tag)
elements.append(IliasForumThread(title, title_tag, content_tag, mtime)) elements.append(IliasForumThread(title, title_tag, content_tag, mtime))