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

Mention href for users of link_regex option

Browse Source
This commit is contained in:
Joscha 2022-05-05 14:23:19 +02:00
parent bc3fa36637
commit af2cc1169a
2 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
CHANGELOG.md
View File

@ -24,6 +24,7 @@ ambiguous situations.
### Changed ### Changed
- Add `cpp` extension to default `link_regex` of IPD crawler - Add `cpp` extension to default `link_regex` of IPD crawler
- Mention hrefs in IPD crawler for users of `link_regex` option
### Fixed ### Fixed
- IPD crawler crashes on some sites - IPD crawler crashes on some sites

4
PFERD/crawl/kit_ipd_crawler.py
View File

@ -45,7 +45,7 @@ class KitIpdFolder:
def explain(self) -> None: def explain(self) -> None:
log.explain_topic(f"Folder {self.name!r}") log.explain_topic(f"Folder {self.name!r}")
for file in self.files: for file in self.files:
log.explain(f"File {file.name!r}") log.explain(f"File {file.name!r} (href={file.url!r})")
def __hash__(self) -> int: def __hash__(self) -> int:
return self.name.__hash__() return self.name.__hash__()
@ -113,7 +113,7 @@ class KitIpdCrawler(HttpCrawler):
else: else:
file = self._extract_file(element) file = self._extract_file(element)
items.add(file) items.add(file)
log.explain_topic(f"Orphan file {file.name!r}") log.explain_topic(f"Orphan file {file.name!r} (href={file.url!r})")
log.explain("Attributing it to root folder") log.explain("Attributing it to root folder")
return items return items