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
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
|
# SPDX-License-Identifier: AGPL-3.0-or-later
"""
Wolfram|Alpha (Science)
"""
from json import loads
from time import time
from urllib.parse import urlencode
from searx.network import get as http_get
# about
about = {
"website": 'https://www.wolframalpha.com/',
"wikidata_id": 'Q207006',
"official_api_documentation": 'https://products.wolframalpha.com/api/',
"use_official_api": False,
"require_api_key": False,
"results": 'JSON',
}
# search-url
url = 'https://www.wolframalpha.com/'
search_url = (
url + 'input/json.jsp'
'?async=false'
'&banners=raw'
'&debuggingdata=false'
'&format=image,plaintext,imagemap,minput,moutput'
'&formattimeout=2'
'&{query}'
'&output=JSON'
'&parsetimeout=2'
'&proxycode={token}'
'&scantimeout=0.5'
'&sponsorcategories=true'
'&statemethod=deploybutton'
)
referer_url = url + 'input/?{query}'
token = {'value': '', 'last_updated': None}
# pods to display as image in infobox
# this pods do return a plaintext, but they look better and are more useful as images
image_pods = {'VisualRepresentation', 'Illustration', 'Symbol'}
# seems, wolframalpha resets its token in every hour
def obtain_token():
update_time = time() - (time() % 3600)
try:
token_response = http_get('https://www.wolframalpha.com/input/api/v1/code?ts=9999999999999999999', timeout=2.0)
token['value'] = loads(token_response.text)['code']
token['last_updated'] = update_time
except: # pylint: disable=bare-except
pass
return token
def init(engine_settings=None): # pylint: disable=unused-argument
obtain_token()
# do search-request
def request(query, params):
# obtain token if last update was more than an hour
if time() - (token['last_updated'] or 0) > 3600:
obtain_token()
params['url'] = search_url.format(query=urlencode({'input': query}), token=token['value'])
params['headers']['Referer'] = referer_url.format(query=urlencode({'i': query}))
return params
# get response from search-request
def response(resp):
results = []
resp_json = loads(resp.text)
if not resp_json['queryresult']['success']:
return []
# handle resp_json['queryresult']['assumptions']?
result_chunks = []
infobox_title = ""
result_content = ""
for pod in resp_json['queryresult']['pods']:
pod_id = pod.get('id', '')
pod_title = pod.get('title', '')
pod_is_result = pod.get('primary', None)
if 'subpods' not in pod:
continue
if pod_id == 'Input' or not infobox_title:
infobox_title = pod['subpods'][0]['plaintext']
for subpod in pod['subpods']:
if subpod['plaintext'] != '' and pod_id not in image_pods:
# append unless it's not an actual answer
if subpod['plaintext'] != '(requires interactivity)':
result_chunks.append({'label': pod_title, 'value': subpod['plaintext']})
if pod_is_result or not result_content:
if pod_id != "Input":
result_content = pod_title + ': ' + subpod['plaintext']
elif 'img' in subpod:
result_chunks.append({'label': pod_title, 'image': subpod['img']})
if not result_chunks:
return []
results.append(
{
'infobox': infobox_title,
'attributes': result_chunks,
'urls': [{'title': 'Wolfram|Alpha', 'url': resp.request.headers['Referer']}],
}
)
results.append(
{
'url': resp.request.headers['Referer'],
'title': 'Wolfram|Alpha (' + infobox_title + ')',
'content': result_content,
}
)
return results
|
