nakidai
/
whoogle-search
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fix bug in title/url blocking regex (#969) 

Fix the exception `AttributeError: 'Filter' object has no attribute 'block_url'`
introduced in this commit [1].

`self.block_title` and `self.block_url` were members of the Filter
object[2], but not anymore after commit [1].

This bug can be reproduced with setting WHOOGLE_CONFIG_BLOCK_URL to a
non-empty string.

[1] 10a15e06e1
[2] 284a8102c8
main
xatier 2023-03-14 10:22:53 -07:00 committed by GitHub
parent 8c426ab180
commit b1e468ff01
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
app/filter.py
View File

@ -225,7 +225,7 @@ class Filter:
def remove_block_titles(self) -> None: def remove_block_titles(self) -> None:
if not self.main_divs or not self.config.block_title: if not self.main_divs or not self.config.block_title:
return return
block_title = re.compile(self.block_title) block_title = re.compile(self.config.block_title)
for div in [_ for _ in self.main_divs.find_all('div', recursive=True)]: for div in [_ for _ in self.main_divs.find_all('div', recursive=True)]:
block_divs = [_ for _ in div.find_all('h3', recursive=True) block_divs = [_ for _ in div.find_all('h3', recursive=True)
if block_title.search(_.text) is not None] if block_title.search(_.text) is not None]
@ -234,7 +234,7 @@ class Filter:
def remove_block_url(self) -> None: def remove_block_url(self) -> None:
if not self.main_divs or not self.config.block_url: if not self.main_divs or not self.config.block_url:
return return
block_url = re.compile(self.block_url) block_url = re.compile(self.config.block_url)
for div in [_ for _ in self.main_divs.find_all('div', recursive=True)]: for div in [_ for _ in self.main_divs.find_all('div', recursive=True)]:
block_divs = [_ for _ in div.find_all('a', recursive=True) block_divs = [_ for _ in div.find_all('a', recursive=True)
if block_url.search(_.attrs['href']) is not None] if block_url.search(_.attrs['href']) is not None]