mirrors/searxng
1
0
Fork 0
mirror of https://github.com/searxng/searxng.git synced 2024-07-03 04:15:50 +00:00
Code Issues Projects Releases Wiki Activity

Merge pull request #2303 from Venca24/devel_seznam

Browse source 
[fix] engine seznam
This commit is contained in:
Markus Heiser 2023-03-31 17:33:09 +02:00 committed by GitHub
parent 27611470bf 509afbbb84
commit 901ccce664
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 10 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
searx/engines/seznam.py
View file

@ -1,6 +1,7 @@
# SPDX-License-Identifier: AGPL-3.0-or-later # SPDX-License-Identifier: AGPL-3.0-or-later
""" # lint: pylint
Seznam """Seznam
""" """
from urllib.parse import urlencode from urllib.parse import urlencode
@ -11,7 +12,6 @@ from searx.utils import (
extract_text, extract_text,
eval_xpath_list, eval_xpath_list,
eval_xpath_getindex, eval_xpath_getindex,
eval_xpath,
) )
# about # about
@ -54,8 +54,12 @@ def response(resp):
results = [] results = []
dom = html.fromstring(resp.content.decode()) dom = html.fromstring(resp.content.decode())
for result_element in eval_xpath_list(dom, '//div[@data-dot="results"]/div'): for result_element in eval_xpath_list(
result_data = eval_xpath_getindex(result_element, './/div[contains(@class, "bec586")]', 0, default=None) dom, '//div[@id="searchpage-root"]//div[@class="Layout--left"]/div[@class="f2c528"]'
):
result_data = eval_xpath_getindex(
result_element, './/div[@class="c8774a" or @class="e69e8d a11657"]', 0, default=None
)
if result_data is None: if result_data is None:
continue continue
title_element = eval_xpath_getindex(result_element, './/h3/a', 0) title_element = eval_xpath_getindex(result_element, './/h3/a', 0)
@ -63,7 +67,7 @@ def response(resp):
{ {
'url': title_element.get('href'), 'url': title_element.get('href'),
'title': extract_text(title_element), 'title': extract_text(title_element),
'content': extract_text(eval_xpath(result_data, './/div[@class="_3eded7"]')), 'content': extract_text(result_data),
} }
) )