|  | @@ -0,0 +1,66 @@
 | 
	
		
			
			|  | 1 | +# WolframAlpha (Maths)
 | 
	
		
			
			|  | 2 | +#
 | 
	
		
			
			|  | 3 | +# @website     http://www.wolframalpha.com/
 | 
	
		
			
			|  | 4 | +#
 | 
	
		
			
			|  | 5 | +# @using-api   no
 | 
	
		
			
			|  | 6 | +# @results     HTML, JS
 | 
	
		
			
			|  | 7 | +# @stable      no
 | 
	
		
			
			|  | 8 | +# @parse       answer
 | 
	
		
			
			|  | 9 | +
 | 
	
		
			
			|  | 10 | +import re
 | 
	
		
			
			|  | 11 | +import json
 | 
	
		
			
			|  | 12 | +from urllib import urlencode
 | 
	
		
			
			|  | 13 | +from lxml import html
 | 
	
		
			
			|  | 14 | +from searx.engines.xpath import extract_text
 | 
	
		
			
			|  | 15 | +
 | 
	
		
			
			|  | 16 | +# search-url
 | 
	
		
			
			|  | 17 | +url = 'http://www.wolframalpha.com/'
 | 
	
		
			
			|  | 18 | +search_url = url+'input/?{query}'
 | 
	
		
			
			|  | 19 | +
 | 
	
		
			
			|  | 20 | +
 | 
	
		
			
			|  | 21 | +# do search-request
 | 
	
		
			
			|  | 22 | +def request(query, params):
 | 
	
		
			
			|  | 23 | +    params['url'] = search_url.format(query=urlencode({'i': query}))
 | 
	
		
			
			|  | 24 | +
 | 
	
		
			
			|  | 25 | +    return params
 | 
	
		
			
			|  | 26 | +
 | 
	
		
			
			|  | 27 | +
 | 
	
		
			
			|  | 28 | +# tries to find answer under the pattern given
 | 
	
		
			
			|  | 29 | +def extract_answer(script_list, pattern):
 | 
	
		
			
			|  | 30 | +    answer = None
 | 
	
		
			
			|  | 31 | +
 | 
	
		
			
			|  | 32 | +    # get line that matches the pattern
 | 
	
		
			
			|  | 33 | +    for script in script_list:
 | 
	
		
			
			|  | 34 | +        try:
 | 
	
		
			
			|  | 35 | +            line = re.search(pattern, script.text_content()).group(1)
 | 
	
		
			
			|  | 36 | +        except AttributeError:
 | 
	
		
			
			|  | 37 | +            continue
 | 
	
		
			
			|  | 38 | +
 | 
	
		
			
			|  | 39 | +        # extract answer from json
 | 
	
		
			
			|  | 40 | +        answer = line[line.find('{') : line.rfind('}')+1]
 | 
	
		
			
			|  | 41 | +        answer = json.loads(answer.encode('unicode-escape'))
 | 
	
		
			
			|  | 42 | +        answer = answer['stringified'].decode('unicode-escape')
 | 
	
		
			
			|  | 43 | +
 | 
	
		
			
			|  | 44 | +    return answer
 | 
	
		
			
			|  | 45 | +
 | 
	
		
			
			|  | 46 | +
 | 
	
		
			
			|  | 47 | +# get response from search-request
 | 
	
		
			
			|  | 48 | +def response(resp):
 | 
	
		
			
			|  | 49 | +
 | 
	
		
			
			|  | 50 | +    dom = html.fromstring(resp.text)
 | 
	
		
			
			|  | 51 | +
 | 
	
		
			
			|  | 52 | +    # the answer is inside a js script
 | 
	
		
			
			|  | 53 | +    scripts = dom.xpath('//script')
 | 
	
		
			
			|  | 54 | +
 | 
	
		
			
			|  | 55 | +    results = []
 | 
	
		
			
			|  | 56 | +
 | 
	
		
			
			|  | 57 | +    # answer can be located in different 'pods', although by default it should be in pod_0200
 | 
	
		
			
			|  | 58 | +    answer = extract_answer(scripts, 'pod_0200\.push(.*)\n')
 | 
	
		
			
			|  | 59 | +    if not answer:
 | 
	
		
			
			|  | 60 | +        answer = extract_answer(scripts, 'pod_0100\.push(.*)\n')
 | 
	
		
			
			|  | 61 | +        if answer:
 | 
	
		
			
			|  | 62 | +            results.append({'answer': answer})
 | 
	
		
			
			|  | 63 | +    else:
 | 
	
		
			
			|  | 64 | +        results.append({'answer': answer})
 | 
	
		
			
			|  | 65 | +    
 | 
	
		
			
			|  | 66 | +    return results
 |