1
0
mirror of https://github.com/searxng/searxng.git synced 2024-11-16 17:40:11 +01:00
searxng/searx/engines/deviantart.py

36 lines
1.1 KiB
Python
Raw Normal View History

2013-10-20 11:12:10 +02:00
from urllib import urlencode
from urlparse import urljoin
2014-02-05 20:24:31 +01:00
from lxml import html
2013-10-20 11:12:10 +02:00
categories = ['images']
base_url = 'https://www.deviantart.com/'
2014-01-30 00:09:47 +01:00
search_url = base_url+'search?offset={offset}&{query}'
paging = True
2013-10-20 11:12:10 +02:00
2014-01-20 02:31:20 +01:00
2013-10-20 11:12:10 +02:00
def request(query, params):
2014-01-30 00:09:47 +01:00
offset = (params['pageno'] - 1) * 24
params['url'] = search_url.format(offset=offset,
query=urlencode({'q': query}))
2013-10-20 11:12:10 +02:00
return params
def response(resp):
results = []
if resp.status_code == 302:
return results
dom = html.fromstring(resp.text)
for result in dom.xpath('//div[contains(@class, "tt-a tt-fh")]'):
link = result.xpath('.//a[contains(@class, "thumb")]')[0]
url = urljoin(base_url, link.attrib.get('href'))
2014-01-20 02:31:20 +01:00
title_links = result.xpath('.//span[@class="details"]//a[contains(@class, "t")]') # noqa
2013-10-20 11:12:10 +02:00
title = ''.join(title_links[0].xpath('.//text()'))
img_src = link.xpath('.//img')[0].attrib['src']
2014-01-20 02:31:20 +01:00
results.append({'url': url,
'title': title,
'img_src': img_src,
'template': 'images.html'})
2013-10-20 11:12:10 +02:00
return results