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

Ilias9: Fix invalid course id

Browse source 
Ilias 9 seems to enforce a new url scheme, which brakes a lot of things
This commit is contained in:
compilebreak 2025-04-09 13:48:45 +02:00
parent 63f25277b0
commit 9bc6ab7f93
2 changed files with 9 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

2
PFERD/crawl/ilias/ilias_web_crawler.py
View file

@ -267,7 +267,7 @@ instance's greatest bottleneck.
# If we expect to find a root course, enforce it # If we expect to find a root course, enforce it
if current_parent is None and expected_course_id is not None: if current_parent is None and expected_course_id is not None:
perma_link = IliasPage.get_soup_permalink(soup) perma_link = IliasPage.get_soup_permalink(soup)
if not perma_link or "crs_" not in perma_link: if not perma_link or "crs" not in perma_link:
raise CrawlError("Invalid course id? Didn't find anything looking like a course") raise CrawlError("Invalid course id? Didn't find anything looking like a course")
if str(expected_course_id) not in perma_link: if str(expected_course_id) not in perma_link:
raise CrawlError(f"Expected course id {expected_course_id} but got {perma_link}") raise CrawlError(f"Expected course id {expected_course_id} but got {perma_link}")

12
PFERD/crawl/ilias/kit_ilias_html.py
View file

@ -1301,10 +1301,14 @@ class IliasPage:
@staticmethod @staticmethod
def get_soup_permalink(soup: BeautifulSoup) -> Optional[str]: def get_soup_permalink(soup: BeautifulSoup) -> Optional[str]:
perma_link_element = cast(Tag, soup.select_one(".il-footer-permanent-url > a")) for script in soup.find_all("script", attrs={'src': cast(str, None)}):
if not perma_link_element or not perma_link_element.get("href"): match = re.search(
return None r"((?:https?:\\\/\\\/)?(?:[^.]+\.)?ilias\.studium\.kit\.edu(\\\/.*)?)\"",
return cast(Optional[str], perma_link_element.get("href")) script.text
)
if match is not None:
return match.group(1)
return None
def _unexpected_html_warning() -> None: def _unexpected_html_warning() -> None: