kamp/searxng
1
0
Fork 0
mirror of https://github.com/searxng/searxng.git synced 2024-11-19 19:00:10 +01:00
Code

[fix] startpage engine : characters with diacritic were preceded by whitespace, and cleaner way to parse the result.

Browse Source
This commit is contained in:
Dalf 2014-01-05 14:00:10 +01:00
parent bf56ec4fb1
commit a2928e8d83
1 changed files with 5 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
searx/engines/startpage.py
View File

@ -19,14 +19,13 @@ def response(resp):
global base_url global base_url
results = [] results = []
dom = html.fromstring(resp.content) dom = html.fromstring(resp.content)
for result in dom.xpath('//div[@class="result"]'): # ads xpath //div[@id="results"]/div[@id="sponsored"]//div[@class="result"]
# not ads : div[@class="result"] are the direct childs of div[@id="results"]
for result in dom.xpath('//div[@id="results"]/div[@class="result"]'):
link = result.xpath('.//h3/a')[0] link = result.xpath('.//h3/a')[0]
url = link.attrib.get('href') url = link.attrib.get('href')
parsed_url = urlparse(url) parsed_url = urlparse(url)
# TODO better google link detection title = link.text_content()
if parsed_url.netloc.find('www.google.com') >= 0: content = result.xpath('./p[@class="desc"]')[0].text_content()
continue
title = ' '.join(link.xpath('.//text()'))
content = escape(' '.join(result.xpath('.//p[@class="desc"]//text()')))
results.append({'url': url, 'title': title, 'content': content}) results.append({'url': url, 'title': title, 'content': content})
return results return results