mirrors/pferd
1
0
Fork 0
mirror of https://github.com/Garmelon/PFERD.git synced 2023-12-21 10:23:01 +01:00
Code Issues Packages Projects Releases Wiki Activity

Expand "is course" check to not download magazines or other weird things

Browse Source
This commit is contained in:
I-Al-Istannen 2020-09-28 16:36:03 +02:00
parent 8e8c1c031a
commit 3f0ae729d6
1 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
PFERD/ilias/crawler.py
View File

@ -134,7 +134,7 @@ class IliasCrawler:
if not self._is_course_id_valid(root_url, course_id): if not self._is_course_id_valid(root_url, course_id):
raise FatalException( raise FatalException(
"Invalid course id? The URL the server returned did not contain my id." "Invalid course id? I didn't find anything looking like a course!"
) )
# And treat it as a folder # And treat it as a folder
@ -143,7 +143,15 @@ class IliasCrawler:
def _is_course_id_valid(self, root_url: str, course_id: str) -> bool: def _is_course_id_valid(self, root_url: str, course_id: str) -> bool:
response: requests.Response = self._session.get(root_url) response: requests.Response = self._session.get(root_url)
return course_id in response.url # We were redirected ==> Non-existant ID
if course_id not in response.url:
return False
link_element: bs4.Tag = self._get_page(root_url, {}).find(id="current_perma_link")
if not link_element:
return False
# It wasn't a course but a category list, forum, etc.
return "crs_" in link_element.get("value")
def crawl_personal_desktop(self) -> List[IliasDownloadInfo]: def crawl_personal_desktop(self) -> List[IliasDownloadInfo]:
""" """