|  | @@ -1,30 +1,58 @@
 | 
	
		
			
			|  | 1 | +## Stackoverflow (It)
 | 
	
		
			
			|  | 2 | +# 
 | 
	
		
			
			|  | 3 | +# @website     https://stackoverflow.com/
 | 
	
		
			
			|  | 4 | +# @provide-api not clear (https://api.stackexchange.com/docs/advanced-search)
 | 
	
		
			
			|  | 5 | +# 
 | 
	
		
			
			|  | 6 | +# @using-api   no
 | 
	
		
			
			|  | 7 | +# @results     HTML
 | 
	
		
			
			|  | 8 | +# @stable      no (HTML can change)
 | 
	
		
			
			|  | 9 | +# @parse       url, title, content
 | 
	
		
			
			|  | 10 | +
 | 
	
		
			
			| 1 | 11 |  from urlparse import urljoin
 | 
	
		
			
			| 2 | 12 |  from cgi import escape
 | 
	
		
			
			| 3 | 13 |  from urllib import urlencode
 | 
	
		
			
			| 4 | 14 |  from lxml import html
 | 
	
		
			
			| 5 | 15 |  
 | 
	
		
			
			|  | 16 | +# engine dependent config
 | 
	
		
			
			| 6 | 17 |  categories = ['it']
 | 
	
		
			
			|  | 18 | +paging = True
 | 
	
		
			
			| 7 | 19 |  
 | 
	
		
			
			|  | 20 | +# search-url
 | 
	
		
			
			| 8 | 21 |  url = 'http://stackoverflow.com/'
 | 
	
		
			
			| 9 | 22 |  search_url = url+'search?{query}&page={pageno}'
 | 
	
		
			
			| 10 |  | -result_xpath = './/div[@class="excerpt"]//text()'
 | 
	
		
			
			| 11 | 23 |  
 | 
	
		
			
			| 12 |  | -paging = True
 | 
	
		
			
			|  | 24 | +# specific xpath variables
 | 
	
		
			
			|  | 25 | +results_xpath = '//div[contains(@class,"question-summary")]'
 | 
	
		
			
			|  | 26 | +link_xpath = './/div[@class="result-link"]//a|.//div[@class="summary"]//h3//a'
 | 
	
		
			
			|  | 27 | +title_xpath = './/text()'
 | 
	
		
			
			|  | 28 | +content_xpath = './/div[@class="excerpt"]//text()'
 | 
	
		
			
			| 13 | 29 |  
 | 
	
		
			
			| 14 | 30 |  
 | 
	
		
			
			|  | 31 | +# do search-request
 | 
	
		
			
			| 15 | 32 |  def request(query, params):
 | 
	
		
			
			| 16 | 33 |      params['url'] = search_url.format(query=urlencode({'q': query}),
 | 
	
		
			
			| 17 | 34 |                                        pageno=params['pageno'])
 | 
	
		
			
			|  | 35 | +
 | 
	
		
			
			| 18 | 36 |      return params
 | 
	
		
			
			| 19 | 37 |  
 | 
	
		
			
			| 20 | 38 |  
 | 
	
		
			
			|  | 39 | +# get response from search-request
 | 
	
		
			
			| 21 | 40 |  def response(resp):
 | 
	
		
			
			| 22 | 41 |      results = []
 | 
	
		
			
			|  | 42 | +
 | 
	
		
			
			| 23 | 43 |      dom = html.fromstring(resp.text)
 | 
	
		
			
			| 24 |  | -    for result in dom.xpath('//div[@class="question-summary search-result"]'):
 | 
	
		
			
			| 25 |  | -        link = result.xpath('.//div[@class="result-link"]//a')[0]
 | 
	
		
			
			|  | 44 | +
 | 
	
		
			
			|  | 45 | +    # parse results
 | 
	
		
			
			|  | 46 | +    for result in dom.xpath(results_xpath):
 | 
	
		
			
			|  | 47 | +        link = result.xpath(link_xpath)[0]
 | 
	
		
			
			| 26 | 48 |          href = urljoin(url, link.attrib.get('href'))
 | 
	
		
			
			| 27 |  | -        title = escape(' '.join(link.xpath('.//text()')))
 | 
	
		
			
			| 28 |  | -        content = escape(' '.join(result.xpath(result_xpath)))
 | 
	
		
			
			| 29 |  | -        results.append({'url': href, 'title': title, 'content': content})
 | 
	
		
			
			|  | 49 | +        title = escape(' '.join(link.xpath(title_xpath)))
 | 
	
		
			
			|  | 50 | +        content = escape(' '.join(result.xpath(content_xpath)))
 | 
	
		
			
			|  | 51 | +
 | 
	
		
			
			|  | 52 | +        # append result
 | 
	
		
			
			|  | 53 | +        results.append({'url': href, 
 | 
	
		
			
			|  | 54 | +                        'title': title, 
 | 
	
		
			
			|  | 55 | +                        'content': content})
 | 
	
		
			
			|  | 56 | +
 | 
	
		
			
			|  | 57 | +    # return results
 | 
	
		
			
			| 30 | 58 |      return results
 |