[fix] sanitize results II.

This commit is contained in:
asciimoo 2013-10-19 20:13:48 +02:00
parent d2da51179a
commit 1e5cbc5f9e

View file

@ -24,7 +24,7 @@ def response(resp):
url = urljoin(base_url, link.attrib.get('href'))
parsed_url = urlparse(url)
# TODO better google link detection
if parsed_url.netloc.find('google.com') >= 0:
if parsed_url.netloc.find('www.google.com') >= 0:
continue
title = ' '.join(link.xpath('.//text()'))
content = escape(' '.join(result.xpath('.//p[@class="desc"]//text()')))