mirrors/pferd
1
0
Fork 0
mirror of https://github.com/Garmelon/PFERD.git synced 2025-07-12 22:22:30 +02:00
Code Issues Packages Projects Releases Wiki Activity

Support finding entries for course overview page

Browse Source 
Related to issue #93
This commit is contained in:
I-Al-Istannen
2024-06-26 16:39:24 +02:00
parent 21a266e302
commit c897d9e2f5
2 changed files with 11 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
CHANGELOG.md
View File

@ -24,6 +24,8 @@ ambiguous situations.
### Added ### Added
- Generic `ilias-web` crawler and `ilias-web` CLI command - Generic `ilias-web` crawler and `ilias-web` CLI command
- Support for the course overview page. Using this URL as a target might cause
duplication warnings, as subgroups are listed separately.
### Fixed ### Fixed
- Normalization of meeting names in cards - Normalization of meeting names in cards

10
PFERD/crawl/ilias/kit_ilias_html.py
View File

@ -349,6 +349,9 @@ class IliasPage:
might_be_info = self._soup.find("form", attrs={"name": lambda x: x == "formInfoScreen"}) is not None might_be_info = self._soup.find("form", attrs={"name": lambda x: x == "formInfoScreen"}) is not None
return self._page_type == IliasElementType.INFO_TAB and might_be_info return self._page_type == IliasElementType.INFO_TAB and might_be_info
def _is_course_overview_page(self) -> bool:
return "baseClass=ilmembershipoverviewgui" in self._page_url
def _select_content_page_url(self) -> Optional[IliasPageElement]: def _select_content_page_url(self) -> Optional[IliasPageElement]:
tab = self._soup.find( tab = self._soup.find(
id="tab_view_content", id="tab_view_content",
@ -686,8 +689,13 @@ class IliasPage:
def _find_normal_entries(self) -> List[IliasPageElement]: def _find_normal_entries(self) -> List[IliasPageElement]:
result: List[IliasPageElement] = [] result: List[IliasPageElement] = []
links: List[Tag] = []
# Fetch all links and throw them to the general interpreter # Fetch all links and throw them to the general interpreter
links: List[Tag] = self._soup.select("a.il_ContainerItemTitle") if self._is_course_overview_page():
log.explain("Page is a course overview page, adjusting link selector")
links.extend(self._soup.select(".il-item-title > a"))
else:
links.extend(self._soup.select("a.il_ContainerItemTitle"))
for link in links: for link in links:
abs_url = self._abs_url_from_link(link) abs_url = self._abs_url_from_link(link)