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
|
# SPDX-License-Identifier: AGPL-3.0-or-later
"""
Microsoft Academic (Science)
"""
from json import dumps, loads
from searx.utils import html_to_text
# about
about = {
"website": 'https://academic.microsoft.com',
"wikidata_id": 'Q28136779',
"official_api_documentation": 'http://ma-graph.org/',
"use_official_api": False,
"require_api_key": False,
"results": 'JSON',
}
categories = ['images']
paging = True
search_url = 'https://academic.microsoft.com/api/search'
_paper_url = 'https://academic.microsoft.com/paper/{id}/reference'
def request(query, params):
params['url'] = search_url
params['method'] = 'POST'
params['headers']['content-type'] = 'application/json; charset=utf-8'
params['data'] = dumps(
{
'query': query,
'queryExpression': '',
'filters': [],
'orderBy': 0,
'skip': (params['pageno'] - 1) * 10,
'sortAscending': True,
'take': 10,
'includeCitationContexts': False,
'profileId': '',
}
)
return params
def response(resp):
results = []
response_data = loads(resp.text)
if not response_data:
return results
for result in response_data.get('pr', {}):
if 'dn' not in result['paper']:
continue
title = result['paper']['dn']
content = _get_content(result['paper'])
url = _paper_url.format(id=result['paper']['id'])
results.append(
{
'url': url,
'title': html_to_text(title),
'content': html_to_text(content),
}
)
return results
def _get_content(result):
if 'd' in result:
content = result['d']
if len(content) > 300:
return content[:300] + '...'
return content
return ''
|
