@@ -1,6 +1,6 @@
1from urllib import quote
1from urllib import quote
2from lxml import html
2from lxml import html
3−from urlparse import urljoin
3+from urlparse import urljoin, urlparse
4from cgi import escape
4from cgi import escape
6base_url = 'https://startpage.com/'
6base_url = 'https://startpage.com/'
@@ -22,6 +22,10 @@ def response(resp):
22 for result in dom.xpath('//div[@class="result"]'):
22 for result in dom.xpath('//div[@class="result"]'):
23 link = result.xpath('.//h3/a')[0]
23 link = result.xpath('.//h3/a')[0]
24 url = urljoin(base_url, link.attrib.get('href'))
24 url = urljoin(base_url, link.attrib.get('href'))
25+ parsed_url = urlparse(url)
26+ # TODO better google link detection
27+ if parsed_url.netloc.find('google.com') >= 0:
25 title = ' '.join(link.xpath('.//text()'))
29 title = ' '.join(link.xpath('.//text()'))
26 content = escape(' '.join(result.xpath('.//p[@class="desc"]//text()')))
30 content = escape(' '.join(result.xpath('.//p[@class="desc"]//text()')))
27 results.append({'url': url, 'title': title, 'content': content})
31 results.append({'url': url, 'title': title, 'content': content})