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

Update minimal mode for new Google formatting (#637) 

Google's latest formatting changes broke the modifications made when enabling
`WHOOGLE_MINIMAL`. This updates the result filtering to work with the new
changes.

Fixes #634
main
DUO Labs 2022-02-02 14:57:05 -05:00 committed by GitHub
parent b393e68d1d
commit 500942cb99
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
app/filter.py
View File

@ -12,6 +12,8 @@ import urllib.parse as urlparse
from urllib.parse import parse_qs from urllib.parse import parse_qs
import os import os
minimal_mode_sections = ['Top stories', 'Images', 'People also ask']
def extract_q(q_str: str, href: str) -> str: def extract_q(q_str: str, href: str) -> str:
"""Extracts the 'q' element from a result link. This is typically """Extracts the 'q' element from a result link. This is typically
@ -169,7 +171,11 @@ class Filter:
for result in self.main_divs: for result in self.main_divs:
result_children = pull_child_divs(result) result_children = pull_child_divs(result)
if minimal_mode: if minimal_mode:
if len(result_children) in (1, 3): if any(f">{x}</span" in str(s) for s in result_children
for x in minimal_mode_sections):
result.decompose()
continue
if len(result_children) < self.RESULT_CHILD_LIMIT:
continue continue
else: else:
if len(result_children) < self.RESULT_CHILD_LIMIT: if len(result_children) < self.RESULT_CHILD_LIMIT: