searxng/searx/engines/stackoverflow.py
2014-01-11 12:39:39 +01:00

25 lines
800 B
Python

from lxml import html
from urlparse import urljoin
from cgi import escape
from urllib import urlencode
categories = ['it']
url = 'http://stackoverflow.com/'
search_url = url+'search?'
def request(query, params):
params['url'] = search_url + urlencode({'q': query})
return params
def response(resp):
results = []
dom = html.fromstring(resp.text)
for result in dom.xpath('//div[@class="question-summary search-result"]'):
link = result.xpath('.//div[@class="result-link"]//a')[0]
href = urljoin(url, link.attrib.get('href'))
title = escape(' '.join(link.xpath('.//text()')))
content = escape(' '.join(result.xpath('.//div[@class="excerpt"]//text()')))
results.append({'url': href, 'title': title, 'content': content})
return results