From 7f505bdc6fad1f744992f663a29ea57c0f8fbc40 Mon Sep 17 00:00:00 2001 From: Markus Heiser Date: Tue, 26 Jan 2021 12:51:54 +0100 Subject: [PATCH] [fix] google: avoid unnecessary SearxEngineXPathException errors Avoid SearxEngineXPathException errors when parsing non valid results:: .//div[@class="yuRUbf"]//a/@href index 0 not found Traceback (most recent call last): File "./searx/engines/google.py", line 274, in response url = eval_xpath_getindex(result, href_xpath, 0) File "./searx/searx/utils.py", line 608, in eval_xpath_getindex raise SearxEngineXPathException(xpath_spec, 'index ' + str(index) + ' not found') searx.exceptions.SearxEngineXPathException: .//div[@class="yuRUbf"]//a/@href index 0 not found Signed-off-by: Markus Heiser --- searx/engines/google.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/searx/engines/google.py b/searx/engines/google.py index 979253ec5..138c90411 100644 --- a/searx/engines/google.py +++ b/searx/engines/google.py @@ -271,7 +271,9 @@ def response(resp): logger.debug('ingoring
section: missing title') continue title = extract_text(title_tag) - url = eval_xpath_getindex(result, href_xpath, 0) + url = eval_xpath_getindex(result, href_xpath, 0, None) + if url is None: + continue content = extract_text(eval_xpath_getindex(result, content_xpath, 0, default=None), allow_none=True) results.append({ 'url': url,