bellingcat/auto-archiver
1
0
Fork 0
mirror of https://github.com/bellingcat/auto-archiver.git synced 2026-06-12 13:18:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Improved docstrings for base modules

Browse Source
This commit is contained in:
Patrick Robertson
2025-02-12 11:32:13 +00:00
parent 8054ea96b3
commit a0c4a82825
6 changed files with 87 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
src/auto_archiver/core/extractor.py
View File

@@ -29,14 +29,24 @@ class Extractor(BaseModule):
valid_url: re.Pattern = None
def cleanup(self) -> None:
# called when extractors are done, or upon errors, cleanup any resources
"""
Called when extractors are done, or upon errors, cleanup any resources
"""
pass
def sanitize_url(self, url: str) -> str:
# used to clean unnecessary URL parameters OR unfurl redirect links
"""
Used to clean unnecessary URL parameters OR unfurl redirect links
"""
return url
def match_link(self, url: str) -> re.Match:
"""
Returns a match object if the given URL matches the valid_url pattern or False/None if not.
Normally used in the `suitable` method to check if the URL is supported by this extractor.
"""
return self.valid_url.match(url)
def suitable(self, url: str) -> bool: