summaryrefslogtreecommitdiff
path: root/searx/engines/bing.py
blob: 6b0bf5a3f89f8d4a7abfb13cd64ff632917dffee (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
37
38
from lxml import html
from urllib import urlencode
from cgi import escape

base_url = 'http://www.bing.com/'
search_string = 'search?{query}'
locale = 'en-US' # see http://msdn.microsoft.com/en-us/library/dd251064.aspx


def request(query, params):
    search_path = search_string.format(query=urlencode({'q': query, 'setmkt': locale}))
    #if params['category'] == 'images':
    #    params['url'] = base_url + 'images/' + search_path
    params['url'] = base_url + search_path
    return params


def response(resp):
    global base_url
    results = []
    dom = html.fromstring(resp.content)
    for result in dom.xpath('//div[@class="sa_cc"]'):
        link = result.xpath('.//h3/a')[0]
        url = link.attrib.get('href')
        title = ' '.join(link.xpath('.//text()'))
        content = escape(' '.join(result.xpath('.//p//text()')))
        results.append({'url': url, 'title': title, 'content': content})

    if results:
        return results

    for result in dom.xpath('//li[@class="b_algo"]'):
        link = result.xpath('.//h2/a')[0]
        url = link.attrib.get('href')
        title = ' '.join(link.xpath('.//text()'))
        content = escape(' '.join(result.xpath('.//p//text()')))
        results.append({'url': url, 'title': title, 'content': content})
    return results