mirror of
https://github.com/searxng/searxng.git
synced 2024-11-27 05:11:03 +00:00
[fix] indexing ++ url extraction
This commit is contained in:
parent
3854703d95
commit
01c2eeb8ff
1 changed files with 5 additions and 2 deletions
|
@ -47,8 +47,11 @@ def response(resp):
|
|||
dom = html.fromstring(resp.text)
|
||||
|
||||
for result in dom.xpath(results_xpath):
|
||||
url = parse_url(extract_url(result.xpath(url_xpath), search_url))
|
||||
title = extract_text(result.xpath(title_xpath)[0])
|
||||
try:
|
||||
url = parse_url(extract_url(result.xpath(url_xpath), search_url))
|
||||
title = extract_text(result.xpath(title_xpath)[0])
|
||||
except:
|
||||
continue
|
||||
content = extract_text(result.xpath(content_xpath)[0])
|
||||
results.append({'url': url, 'title': title, 'content': content})
|
||||
|
||||
|
|
Loading…
Reference in a new issue