mirrors/searxng
1
0
Fork 0
mirror of https://github.com/searxng/searxng.git synced 2025-03-13 07:52:40 +00:00
Code Issues Projects Releases Wiki Activity

[fix] google engine: remove <script> tags from result items

Browse source 
In some results, Google returns a <script> tag that must be removed before
extracting the content.

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
This commit is contained in:
Markus Heiser 2024-11-27 13:35:21 +01:00 committed by Markus Heiser
parent 55481a6377
commit 342d321196
1 changed files with 9 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
searx/engines/google.py
View file

@ -59,11 +59,6 @@ filter_mapping = {0: 'off', 1: 'medium', 2: 'high'}
# specific xpath variables
# ------------------------
results_xpath = './/div[contains(@jscontroller, "SC7lYd")]'
title_xpath = './/a/h3[1]'
href_xpath = './/a[h3]/@href'
content_xpath = './/div[contains(@data-sncf, "1")]'
# Suggestions are links placed in a *card-section*, we extract only the text
# from the links not the links itself.
suggestion_xpath = '//div[contains(@class, "EIaa9b")]//a'
@ -345,22 +340,27 @@ def response(resp):
# parse results
for result in eval_xpath_list(dom, results_xpath): # pylint: disable=too-many-nested-blocks
for result in eval_xpath_list(dom, './/div[contains(@jscontroller, "SC7lYd")]'):
# pylint: disable=too-many-nested-blocks
try:
title_tag = eval_xpath_getindex(result, title_xpath, 0, default=None)
title_tag = eval_xpath_getindex(result, './/a/h3[1]', 0, default=None)
if title_tag is None:
# this not one of the common google results *section*
logger.debug('ignoring item from the result_xpath list: missing title')
continue
title = extract_text(title_tag)
url = eval_xpath_getindex(result, href_xpath, 0, None)
url = eval_xpath_getindex(result, './/a[h3]/@href', 0, None)
if url is None:
logger.debug('ignoring item from the result_xpath list: missing url of title "%s"', title)
continue
content_nodes = eval_xpath(result, content_xpath)
content_nodes = eval_xpath(result, './/div[contains(@data-sncf, "1")]')
for item in content_nodes:
for script in item.xpath(".//script"):
script.getparent().remove(script)
content = extract_text(content_nodes)
if not content: