2013-10-24 23:52:57 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								from lxml import html
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								from urllib import urlencode
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								from cgi import escape
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								base_url = 'http://www.bing.com/'
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								search_string = 'search?{query}'
							 | 
						
					
						
							
								
									
										
										
										
											2013-10-25 01:37:48 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								language = 'en-us' # see http://msdn.microsoft.com/en-us/library/dd251064.aspx
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2013-10-24 23:52:57 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								def request(query, params):
							 | 
						
					
						
							
								
									
										
										
										
											2013-10-25 01:37:48 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								    search_path = search_string.format(query=urlencode({'q': query, 'setmkt': language}))
							 | 
						
					
						
							
								
									
										
										
										
											2013-10-24 23:52:57 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    #if params['category'] == 'images':
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    #    params['url'] = base_url + 'images/' + search_path
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    params['url'] = base_url + search_path
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    return params
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								def response(resp):
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    global base_url
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    results = []
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    dom = html.fromstring(resp.content)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    for result in dom.xpath('//div[@class="sa_cc"]'):
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        link = result.xpath('.//h3/a')[0]
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        url = link.attrib.get('href')
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        title = ' '.join(link.xpath('.//text()'))
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        content = escape(' '.join(result.xpath('.//p//text()')))
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        results.append({'url': url, 'title': title, 'content': content})
							 | 
						
					
						
							
								
									
										
										
										
											2013-10-25 01:37:48 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    if results:
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        return results
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    for result in dom.xpath('//li[@class="b_algo"]'):
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        link = result.xpath('.//h2/a')[0]
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        url = link.attrib.get('href')
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        title = ' '.join(link.xpath('.//text()'))
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        content = escape(' '.join(result.xpath('.//p//text()')))
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        results.append({'url': url, 'title': title, 'content': content})
							 | 
						
					
						
							
								
									
										
										
										
											2013-10-24 23:52:57 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    return results
							 |