ZaclysIndustries/searxngRebrandZaclys
2
0
Fork 0
forked from zaclys/searxng
Code Issues Pull requests Activity

500px unit test

Browse source
This commit is contained in:
Cqoicebordel 2015-02-01 13:43:10 +01:00
parent f18807955b
commit 8cf2ee5721
3 changed files with 90 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

11
searx/engines/www500px.py
View file

@ -15,6 +15,7 @@ from urllib import urlencode
from urlparse import urljoin
from lxml import html
import re
from searx.engines.xpath import extract_text
# engine dependent config
categories = ['images']
@ -22,7 +23,7 @@ paging = True
# search-url
base_url = 'https://500px.com'
search_url = base_url+'/search?search?page={pageno}&type=photos&{query}'
search_url = base_url + '/search?search?page={pageno}&type=photos&{query}'
# do search-request
@ -44,11 +45,11 @@ def response(resp):
for result in dom.xpath('//div[@class="photo"]'):
link = result.xpath('.//a')[0]
url = urljoin(base_url, link.attrib.get('href'))
title = result.xpath('.//div[@class="title"]//text()')[0]
thumbnail_src = link.xpath('.//img')[0].attrib['src']
title = extract_text(result.xpath('.//div[@class="title"]'))
thumbnail_src = link.xpath('.//img')[0].attrib.get('src')
# To have a bigger thumbnail, uncomment the next line
#thumbnail_src = regex.sub('4.jpg', thumbnail_src)
content = result.xpath('.//div[@class="info"]//text()')[0]
# thumbnail_src = regex.sub('4.jpg', thumbnail_src)
content = extract_text(result.xpath('.//div[@class="info"]'))
img_src = regex.sub('2048.jpg', thumbnail_src)
# append result