blob: b852de9ba65e6150e92f7834913f65becc6cf79b (
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
|
"""
Gigablast (Web)
@website http://gigablast.com
@provide-api yes (http://gigablast.com/api.html)
@using-api yes
@results XML
@stable yes
@parse url, title, content
"""
from urllib import urlencode
from cgi import escape
from lxml import etree
# engine dependent config
categories = ['general']
paging = True
number_of_results = 5
# search-url, invalid HTTPS certificate
base_url = 'http://gigablast.com/'
search_string = 'search?{query}&n={number_of_results}&s={offset}&xml=1&qh=0'
# specific xpath variables
results_xpath = '//response//result'
url_xpath = './/url'
title_xpath = './/title'
content_xpath = './/sum'
# do search-request
def request(query, params):
offset = (params['pageno'] - 1) * number_of_results
search_path = search_string.format(
query=urlencode({'q': query}),
offset=offset,
number_of_results=number_of_results)
params['url'] = base_url + search_path
return params
# get response from search-request
def response(resp):
results = []
dom = etree.fromstring(resp.content)
# parse results
for result in dom.xpath(results_xpath):
url = result.xpath(url_xpath)[0].text
title = result.xpath(title_xpath)[0].text
content = escape(result.xpath(content_xpath)[0].text)
# append result
results.append({'url': url,
'title': title,
'content': content})
# return results
return results
|
