kamp/searxng
1
0
Fork 0
mirror of https://github.com/searxng/searxng.git synced 2024-11-20 03:10:10 +01:00
Code

Merge pull request #2236 from return42/fix-2234

Browse Source 
[fix] google engine - div classes has been renamed in HTML result
This commit is contained in:
Alexandre Flament 2020-10-01 10:11:19 +02:00 committed by GitHub
commit ecb9f28869
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 11 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
searx/engines/google.py
View File

@ -116,12 +116,12 @@ g_section_with_header = './g-section-with-header'
# the title is a h3 tag relative to the result group # the title is a h3 tag relative to the result group
title_xpath = './/h3[1]' title_xpath = './/h3[1]'
# in the result group there is <div class="r" ../> it's first child is a <a # in the result group there is <div class="yuRUbf" ../> it's first child is a <a
# href=...> (on some results, the <a> is the first "descendant", not ""child") # href=...>
href_xpath = './/div[@class="r"]//a/@href' href_xpath = './/div[@class="yuRUbf"]//a/@href'
# in the result group there is <div class="s" ../> containing he *content* # in the result group there is <div class="IsZvec" ../> containing he *content*
content_xpath = './/div[@class="s"]' content_xpath = './/div[@class="IsZvec"]'
# 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.
@ -249,7 +249,12 @@ def response(resp):
continue continue
try: try:
title = extract_text(eval_xpath(result, title_xpath)[0]) title_tag = eval_xpath(result, title_xpath)
if not title_tag:
# this not one of the common google results *section*
logger.debug('ingoring <div class="g" ../> section: missing title')
continue
title = extract_text(title_tag[0])
url = eval_xpath(result, href_xpath)[0] url = eval_xpath(result, href_xpath)[0]
content = extract_text_from_dom(result, content_xpath) content = extract_text_from_dom(result, content_xpath)
results.append({ results.append({