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

Include found paths in "second path found" warning

Browse Source
This commit is contained in:
I-Al-Istannen 2022-10-29 14:08:29 +02:00
parent 259cfc20cc
commit c020cccc64
3 changed files with 9 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
CHANGELOG.md
View File

@ -22,6 +22,9 @@ ambiguous situations.
## Unreleased
### Changed
- Clear up error message shown when multiple paths are found to an element
## 3.4.2 - 2022-10-26
### Added

2
PFERD/crawl/ilias/kit_ilias_html.py
View File

@ -134,7 +134,7 @@ class IliasPage:
thread_ids = [f["value"] for f in form.find_all(attrs={"name": "thread_ids[]"})]
form_data: Dict[str, Union[str, List[ſtr]]] = {
form_data: Dict[str, Union[str, List[str]]] = {
"thread_ids[]": thread_ids,
"selected_cmd2": "html",
"select_cmd2": "Ausführen",

8
PFERD/crawl/ilias/kit_ilias_web_crawler.py
View File

@ -194,7 +194,7 @@ instance's greatest bottleneck.
self._links = section.links()
self._videos = section.videos()
self._forums = section.forums()
self._visited_urls: Set[str] = set()
self._visited_urls: Dict[str, PurePath] = dict()
async def _run(self) -> None:
if isinstance(self._target, int):
@ -348,9 +348,11 @@ instance's greatest bottleneck.
) -> Optional[Coroutine[Any, Any, None]]:
if element.url in self._visited_urls:
raise CrawlWarning(
f"Found second path to element {element.name!r} at {element.url!r}. Aborting subpath"
f"Found second path to element {element.name!r} at {element.url!r}. "
+ f"First path: {fmt_path(self._visited_urls[element.url])}. "
+ f"Second path: {fmt_path(parent_path)}."
)
self._visited_urls.add(element.url)
self._visited_urls[element.url] = parent_path
element_path = PurePath(parent_path, element.name)