blob: 6b79ff5c868862e1e6bc78ef311181ba6fee7c4f (
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
80
81
82
83
84
85
|
"""
Google (News)
@website https://news.google.com
@provide-api no
@using-api no
@results HTML
@stable no
@parse url, title, content, publishedDate
"""
from lxml import html
from urllib import urlencode
from json import loads
from searx.engines.google import _fetch_supported_languages, supported_languages_url
# search-url
categories = ['news']
paging = True
language_support = True
safesearch = True
time_range_support = True
number_of_results = 10
search_url = 'https://www.google.com/search'\
'?{query}'\
'&tbm=nws'\
'&gws_rd=cr'\
'&{search_options}'
time_range_attr = "qdr:{range}"
time_range_dict = {'day': 'd',
'week': 'w',
'month': 'm',
'year': 'y'}
# do search-request
def request(query, params):
search_options = {
'start': (params['pageno'] - 1) * number_of_results
}
if params['time_range'] in time_range_dict:
search_options['tbs'] = time_range_attr.format(range=time_range_dict[params['time_range']])
if safesearch and params['safesearch']:
search_options['safe'] = 'on'
params['url'] = search_url.format(query=urlencode({'q': query}),
search_options=urlencode(search_options))
if params['language'] != 'all':
language_array = params['language'].lower().split('-')
params['url'] += '&lr=lang_' + language_array[0]
return params
# get response from search-request
def response(resp):
results = []
dom = html.fromstring(resp.text)
# parse results
for result in dom.xpath('//div[@class="g"]|//div[@class="g _cy"]'):
try:
r = {
'url': result.xpath('.//div[@class="_cnc"]//a/@href')[0],
'title': ''.join(result.xpath('.//div[@class="_cnc"]//h3//text()')),
'content': ''.join(result.xpath('.//div[@class="st"]//text()')),
}
except:
continue
imgs = result.xpath('.//img/@src')
if len(imgs) and not imgs[0].startswith('data'):
r['img_src'] = imgs[0]
results.append(r)
# return results
return results
|
