jandieman/searxng
2
0
Fork 0
mirror of https://github.com/searxng/searxng.git synced 2025-12-23 04:00:02 +00:00
Code Issues Projects Releases Wiki Activity

[fix] indexing ++ url extraction

Browse Source
This commit is contained in:
Adam Tauber
2014-03-21 16:36:13 +01:00
parent 3854703d95
commit 01c2eeb8ff
1 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
searx/engines/yahoo.py
View File

@@ -47,8 +47,11 @@ def response(resp):
dom = html.fromstring(resp.text) dom = html.fromstring(resp.text)
for result in dom.xpath(results_xpath): for result in dom.xpath(results_xpath):
try:
url = parse_url(extract_url(result.xpath(url_xpath), search_url)) url = parse_url(extract_url(result.xpath(url_xpath), search_url))
title = extract_text(result.xpath(title_xpath)[0]) title = extract_text(result.xpath(title_xpath)[0])
except:
continue
content = extract_text(result.xpath(content_xpath)[0]) content = extract_text(result.xpath(content_xpath)[0])
results.append({'url': url, 'title': title, 'content': content}) results.append({'url': url, 'title': title, 'content': content})