mir/searx
2
0
Fork 0
mirror of https://github.com/searx/searx synced 2025-08-30 22:16:19 +00:00
Code Issues Releases Wiki Activity

[fix] google - simplify XPath selectors to fetch more results

Browse Source 
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
This commit is contained in:
Markus Heiser
2022-08-10 18:55:31 +02:00
committed by Noémi Ványi
parent d656b340ee
commit 1abecbc835
1 changed files with 4 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
searx/engines/google.py
View File

@@ -109,22 +109,15 @@ filter_mapping = {
# specific xpath variables
# ------------------------
# google results are grouped into <div class="jtfYYd ..." ../>
results_xpath = '//div[contains(@class, "jtfYYd")]'
results_xpath = '//div[contains(@class, "MjjYud")]'
title_xpath = './/h3[1]'
href_xpath = './/a/@href'
content_xpath = './/div[@data-content-feature=1]'
results_xpath_mobile_ui = '//div[contains(@class, "g ")]'
# google *sections* are no usual *results*, we ignore them
g_section_with_header = './g-section-with-header'
# the title is a h3 tag relative to the result group
title_xpath = './/h3[1]'
# in the result group there is <div class="yuRUbf" ../> it's first child is a <a
# href=...>
href_xpath = './/div[@class="yuRUbf"]//a/@href'
# in the result group there is <div class="VwiC3b ..." ../> containing the *content*
content_xpath = './/div[contains(@class, "VwiC3b")]'
# Suggestions are links placed in a *card-section*, we extract only the text
# from the links not the links itself.