blob: e24b309c1e478b7b60652cca232555fe4b584745 (
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
|
from urlparse import urljoin
from cgi import escape
from urllib import urlencode
from lxml import html
categories = ['it']
url = 'http://stackoverflow.com/'
search_url = url+'search?{query}&page={pageno}'
result_xpath = './/div[@class="excerpt"]//text()'
paging = True
def request(query, params):
params['url'] = search_url.format(query=urlencode({'q': query}),
pageno=params['pageno'])
return params
def response(resp):
results = []
dom = html.fromstring(resp.text)
for result in dom.xpath('//div[@class="question-summary search-result"]'):
link = result.xpath('.//div[@class="result-link"]//a')[0]
href = urljoin(url, link.attrib.get('href'))
title = escape(' '.join(link.xpath('.//text()')))
content = escape(' '.join(result.xpath(result_xpath)))
results.append({'url': href, 'title': title, 'content': content})
return results
|
