diff options
| author | Adam Tauber <asciimoo@gmail.com> | 2014-03-21 16:36:13 +0100 |
|---|---|---|
| committer | Adam Tauber <asciimoo@gmail.com> | 2014-03-21 16:36:13 +0100 |
| commit | 01c2eeb8ff055cfecdb8f1b38f284e95c483d5d9 (patch) | |
| tree | 4c3bf959ce0ae87be2794de4137e460717a8bc3a /searx/engines | |
| parent | 3854703d952d22257841f4f6d85921a340c72da5 (diff) | |
| download | searxng-01c2eeb8ff055cfecdb8f1b38f284e95c483d5d9.tar.gz searxng-01c2eeb8ff055cfecdb8f1b38f284e95c483d5d9.zip | |
[fix] indexing ++ url extraction
Diffstat (limited to 'searx/engines')
| -rw-r--r-- | searx/engines/yahoo.py | 7 |
1 files changed, 5 insertions, 2 deletions
diff --git a/searx/engines/yahoo.py b/searx/engines/yahoo.py index c6cabb58a..f89741839 100644 --- a/searx/engines/yahoo.py +++ b/searx/engines/yahoo.py @@ -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}) |