blob: 9387b08d0418cb25836c5a39d64eae02b85cda4a (
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
|
"""
Microsoft Academic (Science)
@website https://academic.microsoft.com
@provide-api yes
@using-api no
@results JSON
@stable no
@parse url, title, content
"""
from datetime import datetime
from json import loads
from uuid import uuid4
from searx.url_utils import urlencode
from searx.utils import html_to_text
categories = ['images']
paging = True
result_url = 'https://academic.microsoft.com/api/search/GetEntityResults?{query}'
def request(query, params):
correlation_id = uuid4()
msacademic = uuid4()
time_now = datetime.now()
params['url'] = result_url.format(query=urlencode({'correlationId': correlation_id}))
params['cookies']['msacademic'] = str(msacademic)
params['cookies']['ai_user'] = 'vhd0H|{now}'.format(now=str(time_now))
params['method'] = 'POST'
params['data'] = {
'Query': '@{query}@'.format(query=query),
'Limit': 10,
'Offset': params['pageno'] - 1,
'Filters': '',
'OrderBy': '',
'SortAscending': False,
}
return params
def response(resp):
results = []
response_data = loads(resp.text)
for result in response_data['results']:
url = _get_url(result)
title = result['e']['dn']
content = _get_content(result)
results.append({
'url': url,
'title': html_to_text(title),
'content': html_to_text(content),
})
return results
def _get_url(result):
if 's' in result['e']:
return result['e']['s'][0]['u']
return 'https://academic.microsoft.com/#/detail/{pid}'.format(pid=result['id'])
def _get_content(result):
if 'd' in result['e']:
content = result['e']['d']
if len(content) > 300:
return content[:300] + '...'
return content
return ''
|
