|  | @@ -0,0 +1,115 @@
 | 
	
		
			
			|  | 1 | +"""
 | 
	
		
			
			|  | 2 | + Nyaa.se (Anime Bittorrent tracker)
 | 
	
		
			
			|  | 3 | +
 | 
	
		
			
			|  | 4 | + @website      http://www.nyaa.se/
 | 
	
		
			
			|  | 5 | + @provide-api  no
 | 
	
		
			
			|  | 6 | + @using-api    no
 | 
	
		
			
			|  | 7 | + @results      HTML
 | 
	
		
			
			|  | 8 | + @stable       no (HTML can change)
 | 
	
		
			
			|  | 9 | + @parse        url, title, content, seed, leech, torrentfile
 | 
	
		
			
			|  | 10 | +"""
 | 
	
		
			
			|  | 11 | +
 | 
	
		
			
			|  | 12 | +from cgi import escape
 | 
	
		
			
			|  | 13 | +from urllib import urlencode
 | 
	
		
			
			|  | 14 | +from lxml import html
 | 
	
		
			
			|  | 15 | +from searx.engines.xpath import extract_text
 | 
	
		
			
			|  | 16 | +
 | 
	
		
			
			|  | 17 | +# engine dependent config
 | 
	
		
			
			|  | 18 | +categories = ['files', 'images', 'videos', 'music']
 | 
	
		
			
			|  | 19 | +paging = True
 | 
	
		
			
			|  | 20 | +
 | 
	
		
			
			|  | 21 | +# search-url
 | 
	
		
			
			|  | 22 | +base_url = 'http://www.nyaa.se/'
 | 
	
		
			
			|  | 23 | +search_url = base_url + '?page=search&{query}&offset={offset}'
 | 
	
		
			
			|  | 24 | +
 | 
	
		
			
			|  | 25 | +# xpath queries
 | 
	
		
			
			|  | 26 | +xpath_results = '//table[@class="tlist"]//tr[contains(@class, "tlistrow")]'
 | 
	
		
			
			|  | 27 | +xpath_category = './/td[@class="tlisticon"]/a'
 | 
	
		
			
			|  | 28 | +xpath_title = './/td[@class="tlistname"]/a'
 | 
	
		
			
			|  | 29 | +xpath_torrent_file = './/td[@class="tlistdownload"]/a'
 | 
	
		
			
			|  | 30 | +xpath_filesize = './/td[@class="tlistsize"]/text()'
 | 
	
		
			
			|  | 31 | +xpath_seeds = './/td[@class="tlistsn"]/text()'
 | 
	
		
			
			|  | 32 | +xpath_leeches = './/td[@class="tlistln"]/text()'
 | 
	
		
			
			|  | 33 | +xpath_downloads = './/td[@class="tlistdn"]/text()'
 | 
	
		
			
			|  | 34 | +
 | 
	
		
			
			|  | 35 | +
 | 
	
		
			
			|  | 36 | +# convert a variable to integer or return 0 if it's not a number
 | 
	
		
			
			|  | 37 | +def int_or_zero(num):
 | 
	
		
			
			|  | 38 | +    if isinstance(num, list):
 | 
	
		
			
			|  | 39 | +        if len(num) < 1:
 | 
	
		
			
			|  | 40 | +            return 0
 | 
	
		
			
			|  | 41 | +        num = num[0]
 | 
	
		
			
			|  | 42 | +    if num.isdigit():
 | 
	
		
			
			|  | 43 | +        return int(num)
 | 
	
		
			
			|  | 44 | +    return 0
 | 
	
		
			
			|  | 45 | +
 | 
	
		
			
			|  | 46 | +
 | 
	
		
			
			|  | 47 | +# do search-request
 | 
	
		
			
			|  | 48 | +def request(query, params):
 | 
	
		
			
			|  | 49 | +    query = urlencode({'term': query})
 | 
	
		
			
			|  | 50 | +    params['url'] = search_url.format(query=query, offset=params['pageno'])
 | 
	
		
			
			|  | 51 | +    return params
 | 
	
		
			
			|  | 52 | +
 | 
	
		
			
			|  | 53 | +
 | 
	
		
			
			|  | 54 | +# get response from search-request
 | 
	
		
			
			|  | 55 | +def response(resp):
 | 
	
		
			
			|  | 56 | +    results = []
 | 
	
		
			
			|  | 57 | +
 | 
	
		
			
			|  | 58 | +    dom = html.fromstring(resp.text)
 | 
	
		
			
			|  | 59 | +
 | 
	
		
			
			|  | 60 | +    for result in dom.xpath(xpath_results):
 | 
	
		
			
			|  | 61 | +        # category in which our torrent belongs
 | 
	
		
			
			|  | 62 | +        category = result.xpath(xpath_category)[0].attrib.get('title')
 | 
	
		
			
			|  | 63 | +
 | 
	
		
			
			|  | 64 | +        # torrent title
 | 
	
		
			
			|  | 65 | +        page_a = result.xpath(xpath_title)[0]
 | 
	
		
			
			|  | 66 | +        title = escape(extract_text(page_a))
 | 
	
		
			
			|  | 67 | +
 | 
	
		
			
			|  | 68 | +        # link to the page
 | 
	
		
			
			|  | 69 | +        href = page_a.attrib.get('href')
 | 
	
		
			
			|  | 70 | +
 | 
	
		
			
			|  | 71 | +        # link to the torrent file
 | 
	
		
			
			|  | 72 | +        torrent_link = result.xpath(xpath_torrent_file)[0].attrib.get('href')
 | 
	
		
			
			|  | 73 | +
 | 
	
		
			
			|  | 74 | +        # torrent size
 | 
	
		
			
			|  | 75 | +        try:
 | 
	
		
			
			|  | 76 | +            file_size, suffix = result.xpath(xpath_filesize)[0].split(' ')
 | 
	
		
			
			|  | 77 | +
 | 
	
		
			
			|  | 78 | +            # convert torrent size to bytes.
 | 
	
		
			
			|  | 79 | +            # if there is no correct index in this dictionary,
 | 
	
		
			
			|  | 80 | +            # the try block fails as it should
 | 
	
		
			
			|  | 81 | +            multiplier = {
 | 
	
		
			
			|  | 82 | +                'KIB': 1024,
 | 
	
		
			
			|  | 83 | +                'MIB': 1024 ** 2,
 | 
	
		
			
			|  | 84 | +                'GIB': 1024 ** 3,
 | 
	
		
			
			|  | 85 | +                'TIB': 1024 ** 4
 | 
	
		
			
			|  | 86 | +            }[suffix.upper()]
 | 
	
		
			
			|  | 87 | +
 | 
	
		
			
			|  | 88 | +            file_size = int(float(file_size) * multiplier)
 | 
	
		
			
			|  | 89 | +        except Exception as e:
 | 
	
		
			
			|  | 90 | +            file_size = None
 | 
	
		
			
			|  | 91 | +
 | 
	
		
			
			|  | 92 | +        # seed count
 | 
	
		
			
			|  | 93 | +        seed = int_or_zero(result.xpath(xpath_seeds))
 | 
	
		
			
			|  | 94 | +
 | 
	
		
			
			|  | 95 | +        # leech count
 | 
	
		
			
			|  | 96 | +        leech = int_or_zero(result.xpath(xpath_leeches))
 | 
	
		
			
			|  | 97 | +
 | 
	
		
			
			|  | 98 | +        # torrent downloads count
 | 
	
		
			
			|  | 99 | +        downloads = int_or_zero(result.xpath(xpath_downloads))
 | 
	
		
			
			|  | 100 | +
 | 
	
		
			
			|  | 101 | +        # content string contains all information not included into template
 | 
	
		
			
			|  | 102 | +        content = 'Category: "{category}". Downloaded {downloads} times.'
 | 
	
		
			
			|  | 103 | +        content = content.format(category=category, downloads=downloads)
 | 
	
		
			
			|  | 104 | +        content = escape(content)
 | 
	
		
			
			|  | 105 | +
 | 
	
		
			
			|  | 106 | +        results.append({'url': href,
 | 
	
		
			
			|  | 107 | +                        'title': title,
 | 
	
		
			
			|  | 108 | +                        'content': content,
 | 
	
		
			
			|  | 109 | +                        'seed': seed,
 | 
	
		
			
			|  | 110 | +                        'leech': leech,
 | 
	
		
			
			|  | 111 | +                        'filesize': file_size,
 | 
	
		
			
			|  | 112 | +                        'torrentfile': torrent_link,
 | 
	
		
			
			|  | 113 | +                        'template': 'torrent.html'})
 | 
	
		
			
			|  | 114 | +
 | 
	
		
			
			|  | 115 | +    return results
 |