1
0
mirror of https://github.com/searxng/searxng.git synced 2024-11-22 12:10:11 +01:00

[fix] proper html escaping

This commit is contained in:
asciimoo 2013-10-17 20:43:05 +02:00
parent 48839295d3
commit e47258ce38

View File

@ -1,6 +1,7 @@
from urllib import quote from urllib import quote
from lxml import html from lxml import html
from urlparse import urljoin from urlparse import urljoin
from cgi import escape
base_url = 'http://stackoverflow.com/' base_url = 'http://stackoverflow.com/'
search_url = base_url+'search?q=' search_url = base_url+'search?q='
@ -20,6 +21,6 @@ def response(resp):
link = result.xpath('.//div[@class="result-link"]//a')[0] link = result.xpath('.//div[@class="result-link"]//a')[0]
url = urljoin(base_url, link.attrib.get('href')) url = urljoin(base_url, link.attrib.get('href'))
title = ' '.join(link.xpath('.//text()')) title = ' '.join(link.xpath('.//text()'))
content = ' '.join(result.xpath('.//div[@class="excerpt"]//text()')) content = escape(' '.join(result.xpath('.//div[@class="excerpt"]//text()')))
results.append({'url': url, 'title': title, 'content': content}) results.append({'url': url, 'title': title, 'content': content})
return results return results