logo

searx

My custom branche(s) on searx, a meta-search engine
commit: cf6a92a996e9b110de1d0d7272ab4a1046177352
parent: 7ddf7d43ba32aa4450cdedb09093989f441648d1
Author: asciimoo <asciimoo@gmail.com>
Date:   Thu, 24 Oct 2013 23:43:39 +0200

[fix] urljoin removed

Diffstat:

Msearx/engines/startpage.py4++--
1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/searx/engines/startpage.py b/searx/engines/startpage.py @@ -1,6 +1,6 @@ from urllib import quote from lxml import html -from urlparse import urljoin, urlparse +from urlparse import urlparse from cgi import escape base_url = 'https://startpage.com/' @@ -21,7 +21,7 @@ def response(resp): dom = html.fromstring(resp.content) for result in dom.xpath('//div[@class="result"]'): link = result.xpath('.//h3/a')[0] - url = urljoin(base_url, link.attrib.get('href')) + url = link.attrib.get('href') parsed_url = urlparse(url) # TODO better google link detection if parsed_url.netloc.find('www.google.com') >= 0: