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

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

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
This commit is contained in:
Markus Heiser 2022-08-10 18:55:31 +02:00
parent b9f16a77db
commit eb02cc77c5
1 changed files with 4 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
searx/engines/google.py
View File

@ -112,21 +112,14 @@ filter_mapping = {0: 'off', 1: 'medium', 2: 'high'}
# specific xpath variables # specific xpath variables
# ------------------------ # ------------------------
# google results are grouped into <div class="jtfYYd ..." ../> results_xpath = '//div[contains(@class, "MjjYud")]'
results_xpath = '//div[contains(@class, "jtfYYd")]' title_xpath = './/h3[1]'
href_xpath = './/a/@href'
content_xpath = './/div[@data-content-feature=1]'
# google *sections* are no usual *results*, we ignore them # google *sections* are no usual *results*, we ignore them
g_section_with_header = './g-section-with-header' 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 # Suggestions are links placed in a *card-section*, we extract only the text
# from the links not the links itself. # from the links not the links itself.