summaryrefslogtreecommitdiff
path: root/searx/engines/startpage.py
blob: 2adbfb3e4b942cdffd1274570e6fdc546791c635 (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
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
## Startpage (Web)
# 
# @website     https://startpage.com
# @provide-api no (nothing found)
# 
# @using-api   no
# @results     HTML
# @stable      no (HTML can change)
# @parse       url, title, content
#
# @todo        paging

from urllib import urlencode
from lxml import html
from cgi import escape
import re

# engine dependent config
categories = ['general']
# there is a mechanism to block "bot" search (probably the parameter qid), require storing of qid's between mulitble search-calls
#paging = False 
language_support = True

# search-url
base_url = 'https://startpage.com/'
search_url = base_url + 'do/search'

# specific xpath variables
# ads xpath //div[@id="results"]/div[@id="sponsored"]//div[@class="result"]
# not ads: div[@class="result"] are the direct childs of div[@id="results"]
results_xpath = '//div[@class="result"]'
link_xpath = './/h3/a'


# do search-request
def request(query, params):
    offset = (params['pageno'] - 1) * 10
    query = urlencode({'q': query})[2:]

    params['url'] = search_url
    params['method'] = 'POST'
    params['data'] = {'query': query,
                      'startat': offset}   

    # set language if specified
    if params['language'] != 'all':
        params['data']['with_language'] = 'lang_' + params['language'].split('_')[0]

    return params


# get response from search-request
def response(resp):
    results = []

    dom = html.fromstring(resp.content)
    
    # parse results
    for result in dom.xpath(results_xpath):
        link = result.xpath(link_xpath)[0]
        url = link.attrib.get('href')
        title = escape(link.text_content())

        # block google-ad url's
        if re.match("^http(s|)://www.google.[a-z]+/aclk.*$", url):
            continue

        if result.xpath('./p[@class="desc"]'):
            content = escape(result.xpath('./p[@class="desc"]')[0].text_content())
        else:
            content = ''

        # append result
        results.append({'url': url, 
                        'title': title, 
                        'content': content})

    # return results
    return results