[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 MatthieuBarbu
parent a00e5d2d75
commit 30c12a206a

View File

@ -159,9 +159,12 @@ def parse_web_lite(resp):
dom = lxml.html.fromstring(resp.text)
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(
{
'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')),
'content': extract_text(eval_xpath(item, './p')),
}