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
|
# SPDX-License-Identifier: AGPL-3.0-or-later
"""
Seznam
"""
from urllib.parse import urlencode, urlparse
from lxml import html
from searx.poolrequests import get
from searx.exceptions import SearxEngineAccessDeniedException
from searx.utils import (
extract_text,
eval_xpath_list,
eval_xpath_getindex,
eval_xpath,
)
# about
about = {
"website": "https://www.seznam.cz/",
"wikidata_id": "Q3490485",
"official_api_documentation": "https://api.sklik.cz/",
"use_official_api": False,
"require_api_key": False,
"results": "HTML",
}
base_url = 'https://search.seznam.cz/'
def request(query, params):
response_index = get(base_url, headers=params['headers'], raise_for_httperror=True)
dom = html.fromstring(response_index.text)
url_params = {
'q': query,
'oq': query,
}
for e in eval_xpath_list(dom, '//input[@type="hidden"]'):
name = e.get('name')
value = e.get('value')
url_params[name] = value
params['url'] = base_url + '?' + urlencode(url_params)
params['cookies'] = response_index.cookies
return params
def response(resp):
resp_url = urlparse(resp.url)
if resp_url.path.startswith('/verify'):
raise SearxEngineAccessDeniedException()
results = []
dom = html.fromstring(resp.content.decode())
for result_element in eval_xpath_list(dom, '//div[@data-dot="results"]/div'):
result_data = eval_xpath_getindex(result_element, './/div[contains(@class, "Result")]', 0, default=None)
if result_data is None:
continue
title_element = eval_xpath_getindex(result_element, './/h3/a', 0)
results.append({
'url': title_element.get('href'),
'title': extract_text(title_element),
'content': extract_text(eval_xpath(result_data, './/p[@class="Result-description"]')),
})
return results
|
