blob: 602678e4119089a6ae4db389430e98dd2e270e97 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
|
from urllib import urlencode
from lxml import html
from urlparse import urljoin
categories = ['images']
base_url = 'https://www.deviantart.com/'
search_url = base_url+'search?offset={offset}&{query}'
paging = True
def request(query, params):
offset = (params['pageno'] - 1) * 24
params['url'] = search_url.format(offset=offset,
query=urlencode({'q': query}))
return params
def response(resp):
global base_url
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'))
title_links = result.xpath('.//span[@class="details"]//a[contains(@class, "t")]') # noqa
title = ''.join(title_links[0].xpath('.//text()'))
img_src = link.xpath('.//img')[0].attrib['src']
results.append({'url': url,
'title': title,
'img_src': img_src,
'template': 'images.html'})
return results
|
