blob: 1ce2aa1ffede1cf10bdb7f72f3b7351e3c7393cd (
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
|
# WolframAlpha (Maths)
#
# @website http://www.wolframalpha.com/
#
# @using-api no
# @results HTML, JS
# @stable no
# @parse answer
import re
import json
from urllib import urlencode
from lxml import html
from searx.engines.xpath import extract_text
# search-url
url = 'http://www.wolframalpha.com/'
search_url = url+'input/?{query}'
# do search-request
def request(query, params):
params['url'] = search_url.format(query=urlencode({'i': query}))
return params
# tries to find answer under the pattern given
def extract_answer(script_list, pattern):
answer = None
# get line that matches the pattern
for script in script_list:
try:
line = re.search(pattern, script.text_content()).group(1)
except AttributeError:
continue
# extract answer from json
answer = line[line.find('{') : line.rfind('}')+1]
answer = json.loads(answer.encode('unicode-escape'))
answer = answer['stringified'].decode('unicode-escape')
return answer
# get response from search-request
def response(resp):
dom = html.fromstring(resp.text)
# the answer is inside a js script
scripts = dom.xpath('//script')
results = []
# answer can be located in different 'pods', although by default it should be in pod_0200
answer = extract_answer(scripts, 'pod_0200\.push(.*)\n')
if not answer:
answer = extract_answer(scripts, 'pod_0100\.push(.*)\n')
if answer:
results.append({'answer': answer})
else:
results.append({'answer': answer})
return results
|
