Fix wrong base URL for multi-stage pages

CHANGELOG.md

@@ -38,6 +38,9 @@ path separators to `/` in your regex rules.
 - Use the label to the left for exercises instead of the button name to
   determine the folder name
 
+### Fixed
+- Video pagination handling in ILIAS crawler
+
 ## 3.0.1 - 2021-06-01
 
 ### Added

PFERD/crawl/ilias/kit_ilias_html.py

@@ -480,7 +480,7 @@ class IliasPage:
             return None
 
         if "opencast" in str(img_tag["alt"]).lower():
-            return IliasElementType.VIDEO_FOLDER
+            return IliasElementType.VIDEO_FOLDER_MAYBE_PAGINATED
 
         if str(img_tag["src"]).endswith("icon_exc.svg"):
             return IliasElementType.EXERCISE

PFERD/crawl/ilias/kit_ilias_web_crawler.py

@@ -253,7 +253,7 @@ instance's greatest bottleneck.
                     soup = await self._get_page(next_stage_url)
                     log.explain_topic(f"Parsing HTML page for {fmt_path(path)}")
                     log.explain(f"URL: {next_stage_url}")
-                    page = IliasPage(soup, url, parent)
+                    page = IliasPage(soup, next_stage_url, parent)
                     next_stage_url = page.get_next_stage_url()
 
                 elements.extend(page.get_child_elements())