|  | @@ -0,0 +1,81 @@
 | 
	
		
			
			|  | 1 | +## Bing (Images)
 | 
	
		
			
			|  | 2 | +# 
 | 
	
		
			
			|  | 3 | +# @website     https://www.bing.com/images
 | 
	
		
			
			|  | 4 | +# @provide-api yes (http://datamarket.azure.com/dataset/bing/search), max. 5000 query/month
 | 
	
		
			
			|  | 5 | +# 
 | 
	
		
			
			|  | 6 | +# @using-api   no (because of query limit)
 | 
	
		
			
			|  | 7 | +# @results     HTML (using search portal)
 | 
	
		
			
			|  | 8 | +# @stable      no (HTML can change)
 | 
	
		
			
			|  | 9 | +# @parse       url, title, img_src
 | 
	
		
			
			|  | 10 | +#
 | 
	
		
			
			|  | 11 | +# @todo        currently there are up to 35 images receive per page, because bing does not parse count=10. limited response to 10 images
 | 
	
		
			
			|  | 12 | +
 | 
	
		
			
			|  | 13 | +from urllib import urlencode
 | 
	
		
			
			|  | 14 | +from cgi import escape
 | 
	
		
			
			|  | 15 | +from lxml import html
 | 
	
		
			
			|  | 16 | +from yaml import load
 | 
	
		
			
			|  | 17 | +import re
 | 
	
		
			
			|  | 18 | +
 | 
	
		
			
			|  | 19 | +# engine dependent config
 | 
	
		
			
			|  | 20 | +categories = ['images']
 | 
	
		
			
			|  | 21 | +paging = True
 | 
	
		
			
			|  | 22 | +
 | 
	
		
			
			|  | 23 | +# search-url
 | 
	
		
			
			|  | 24 | +base_url = 'https://www.bing.com/'
 | 
	
		
			
			|  | 25 | +search_string = 'images/search?{query}&count=10&first={offset}'
 | 
	
		
			
			|  | 26 | +
 | 
	
		
			
			|  | 27 | +# do search-request
 | 
	
		
			
			|  | 28 | +def request(query, params):
 | 
	
		
			
			|  | 29 | +    offset = (params['pageno'] - 1) * 10 + 1
 | 
	
		
			
			|  | 30 | +
 | 
	
		
			
			|  | 31 | +    # required for cookie
 | 
	
		
			
			|  | 32 | +    language = 'en-US'
 | 
	
		
			
			|  | 33 | +
 | 
	
		
			
			|  | 34 | +    search_path = search_string.format(
 | 
	
		
			
			|  | 35 | +        query=urlencode({'q': query}),
 | 
	
		
			
			|  | 36 | +        offset=offset)
 | 
	
		
			
			|  | 37 | +
 | 
	
		
			
			|  | 38 | +    params['cookies']['SRCHHPGUSR'] = \
 | 
	
		
			
			|  | 39 | +        'NEWWND=0&NRSLT=-1&SRCHLANG=' + language.split('-')[0]
 | 
	
		
			
			|  | 40 | +
 | 
	
		
			
			|  | 41 | +    params['url'] = base_url + search_path
 | 
	
		
			
			|  | 42 | +
 | 
	
		
			
			|  | 43 | +    print(params['url'])
 | 
	
		
			
			|  | 44 | +
 | 
	
		
			
			|  | 45 | +    return params
 | 
	
		
			
			|  | 46 | +
 | 
	
		
			
			|  | 47 | +
 | 
	
		
			
			|  | 48 | +# get response from search-request
 | 
	
		
			
			|  | 49 | +def response(resp):
 | 
	
		
			
			|  | 50 | +    results = []
 | 
	
		
			
			|  | 51 | +
 | 
	
		
			
			|  | 52 | +    dom = html.fromstring(resp.content)
 | 
	
		
			
			|  | 53 | +
 | 
	
		
			
			|  | 54 | +    # init regex for yaml-parsing
 | 
	
		
			
			|  | 55 | +    p = re.compile( '({|,)([a-z]+):(")')
 | 
	
		
			
			|  | 56 | +
 | 
	
		
			
			|  | 57 | +    # parse results
 | 
	
		
			
			|  | 58 | +    for result in dom.xpath('//div[@class="dg_u"]'):
 | 
	
		
			
			|  | 59 | +        link = result.xpath('./a')[0]
 | 
	
		
			
			|  | 60 | +
 | 
	
		
			
			|  | 61 | +        # parse yaml-data (it is required to add a space, to make it parsable)
 | 
	
		
			
			|  | 62 | +        yaml_data = load(p.sub( r'\1\2: \3', link.attrib.get('m')))
 | 
	
		
			
			|  | 63 | + 
 | 
	
		
			
			|  | 64 | +        title = link.attrib.get('t1')
 | 
	
		
			
			|  | 65 | +        #url = 'http://' + link.attrib.get('t3')
 | 
	
		
			
			|  | 66 | +        url = yaml_data.get('surl')
 | 
	
		
			
			|  | 67 | +        img_src = yaml_data.get('imgurl')
 | 
	
		
			
			|  | 68 | +
 | 
	
		
			
			|  | 69 | +        # append result
 | 
	
		
			
			|  | 70 | +        results.append({'template': 'images.html',
 | 
	
		
			
			|  | 71 | +                        'url': url,
 | 
	
		
			
			|  | 72 | +                        'title': title,
 | 
	
		
			
			|  | 73 | +                        'content': '',  
 | 
	
		
			
			|  | 74 | +                        'img_src': img_src})
 | 
	
		
			
			|  | 75 | +
 | 
	
		
			
			|  | 76 | +        # TODO stop parsing if 10 images are found
 | 
	
		
			
			|  | 77 | +        if len(results) >= 10:
 | 
	
		
			
			|  | 78 | +            break
 | 
	
		
			
			|  | 79 | +
 | 
	
		
			
			|  | 80 | +    # return results
 | 
	
		
			
			|  | 81 | +    return results
 |