zaclys
/
searxng
mirror of https://github.com/searxng/searxng.git
1
0
Fork 1
Code Issues Packages Projects Releases Wiki Activity

[fix] engine qwant (web-lite) - ignore advertising adds 

Closes: https://github.com/searxng/searxng/issues/2812
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
This commit is contained in:
Markus Heiser 2023-09-19 12:55:21 +02:00 committed by Markus Heiser
parent 3ac7c40b6a
commit 043dcbf7c5
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
searx/engines/qwant.py
View File

@ -159,9 +159,12 @@ def parse_web_lite(resp):
dom = lxml.html.fromstring(resp.text) dom = lxml.html.fromstring(resp.text)
for item in eval_xpath_list(dom, '//section/article'): for item in eval_xpath_list(dom, '//section/article'):
if eval_xpath(item, "./span[contains(@class, 'tooltip')]"):
# ignore randomly interspersed advertising adds
continue
results.append( results.append(
{ {
'url': extract_text(eval_xpath(item, './span')), 'url': extract_text(eval_xpath(item, "./span[contains(@class, 'url partner')]")),
'title': extract_text(eval_xpath(item, './h2/a')), 'title': extract_text(eval_xpath(item, './h2/a')),
'content': extract_text(eval_xpath(item, './p')), 'content': extract_text(eval_xpath(item, './p')),
} }