Remove size suffix for content pages

CHANGELOG.md

@@ -27,6 +27,7 @@ ambiguous situations.
 - Crawling of file and custom opencast cards
 - Crawling of button cards without descriptions
 - Abort crawling when encountering an unexpected ilias root page redirect
+- Remove size suffix for files in content pages
 
 ### Added
 - `no-delete-prompt-override` conflict resolution strategy

PFERD/crawl/ilias/kit_ilias_html.py

@@ -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()