blob: e84f153bd69e7bcef5327ddeab902ac553648226 (
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
|
"""
not Evil (Onions)
@website http://hss3uro2hsxfogfq.onion
@provide-api yes (http://hss3uro2hsxfogfq.onion/api.htm)
@using-api no
@results HTML
@stable no
@parse url, title, content
"""
from urllib.parse import urlencode
from lxml import html
from searx.engines.xpath import extract_text
# engine dependent config
categories = ['onions']
paging = True
page_size = 20
# search-url
base_url = 'http://hss3uro2hsxfogfq.onion/'
search_url = 'index.php?{query}&hostLimit=20&start={pageno}&numRows={page_size}'
# specific xpath variables
results_xpath = '//*[@id="content"]/div/p'
url_xpath = './span[1]'
title_xpath = './a[1]'
content_xpath = './text()'
# do search-request
def request(query, params):
offset = (params['pageno'] - 1) * page_size
params['url'] = base_url + search_url.format(pageno=offset,
query=urlencode({'q': query}),
page_size=page_size)
return params
# get response from search-request
def response(resp):
results = []
# needed because otherwise requests guesses wrong encoding
resp.encoding = 'utf8'
dom = html.fromstring(resp.text)
# parse results
for result in dom.xpath(results_xpath):
url = extract_text(result.xpath(url_xpath)[0])
title = extract_text(result.xpath(title_xpath)[0])
content = extract_text(result.xpath(content_xpath))
# append result
results.append({'url': url,
'title': title,
'content': content,
'is_onion': True})
return results
|
