From 8162d7aff4a61801615d8044b71c7c477b2b2816 Mon Sep 17 00:00:00 2001 From: Markus Heiser Date: Thu, 1 Oct 2020 09:44:29 +0200 Subject: [PATCH] [fix] google engine - div classes has been renamed in HTML reult Since 1. October 2020 google has changed the 'class' attribute of the HTML result page. Fix the xpath expressions and ignore
sections which do not match to title's xpath expression. Signed-off-by: Markus Heiser --- searx/engines/google.py | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/searx/engines/google.py b/searx/engines/google.py index 7dc6b44ac..c9faadb6e 100644 --- a/searx/engines/google.py +++ b/searx/engines/google.py @@ -116,12 +116,12 @@ 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
it's first child is a (on some results, the is the first "descendant", not ""child") -href_xpath = './/div[@class="r"]//a/@href' +# in the result group there is
it's first child is a +href_xpath = './/div[@class="yuRUbf"]//a/@href' -# in the result group there is
containing he *content* -content_xpath = './/div[@class="s"]' +# in the result group there is
containing he *content* +content_xpath = './/div[@class="IsZvec"]' # Suggestions are links placed in a *card-section*, we extract only the text # from the links not the links itself. @@ -249,7 +249,12 @@ def response(resp): continue 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
section: missing title') + continue + title = extract_text(title_tag[0]) url = eval_xpath(result, href_xpath)[0] content = extract_text_from_dom(result, content_xpath) results.append({