blob: 95d15cfb997e0b2f1d9d877d90b7df92639f30a9 (
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
|
"""
Google (News)
@website https://www.google.com
@provide-api yes (https://developers.google.com/web-search/docs/),
deprecated!
@using-api yes
@results JSON
@stable yes (but deprecated)
@parse url, title, content, publishedDate
"""
from urllib import urlencode
from json import loads
from dateutil import parser
# search-url
categories = ['news']
paging = True
language_support = True
# engine dependent config
url = 'https://ajax.googleapis.com/'
search_url = url + 'ajax/services/search/news?v=2.0&start={offset}&rsz=large&safe=off&filter=off&{query}&hl={lang}'
# do search-request
def request(query, params):
offset = (params['pageno'] - 1) * 8
language = 'en-US'
if params['language'] != 'all':
language = params['language'].replace('_', '-')
params['url'] = search_url.format(offset=offset,
query=urlencode({'q': query}),
lang=language)
return params
# get response from search-request
def response(resp):
results = []
search_res = loads(resp.text)
# return empty array if there are no results
if not search_res.get('responseData', {}).get('results'):
return []
# parse results
for result in search_res['responseData']['results']:
# parse publishedDate
publishedDate = parser.parse(result['publishedDate'])
if 'url' not in result:
continue
# append result
results.append({'url': result['unescapedUrl'],
'title': result['titleNoFormatting'],
'publishedDate': publishedDate,
'content': result['content']})
# return results
return results
|
