logo

searx

My custom branche(s) on searx, a meta-search engine git clone https://hacktivis.me/git/searx.git

seedpeer.py (2995B)

    

  1. #  Seedpeer (Videos, Music, Files)

  2. #

  3. # @website     http://seedpeer.eu

  4. # @provide-api no (nothing found)

  5. #

  6. # @using-api   no

  7. # @results     HTML (using search portal)

  8. # @stable      yes (HTML can change)

  9. # @parse       url, title, content, seed, leech, magnetlink

  10. 

  11. from lxml import html

  12. from operator import itemgetter

  13. from searx.url_utils import quote, urljoin

  14. 

  15. 

  16. url = 'http://www.seedpeer.eu/'

  17. search_url = url + 'search/{search_term}/7/{page_no}.html'

  18. # specific xpath variables

  19. torrent_xpath = '//*[@id="body"]/center/center/table[2]/tr/td/a'

  20. alternative_torrent_xpath = '//*[@id="body"]/center/center/table[1]/tr/td/a'

  21. title_xpath = '//*[@id="body"]/center/center/table[2]/tr/td/a/text()'

  22. alternative_title_xpath = '//*[@id="body"]/center/center/table/tr/td/a'

  23. seeds_xpath = '//*[@id="body"]/center/center/table[2]/tr/td[4]/font/text()'

  24. alternative_seeds_xpath = '//*[@id="body"]/center/center/table/tr/td[4]/font/text()'

  25. peers_xpath = '//*[@id="body"]/center/center/table[2]/tr/td[5]/font/text()'

  26. alternative_peers_xpath = '//*[@id="body"]/center/center/table/tr/td[5]/font/text()'

  27. age_xpath = '//*[@id="body"]/center/center/table[2]/tr/td[2]/text()'

  28. alternative_age_xpath = '//*[@id="body"]/center/center/table/tr/td[2]/text()'

  29. size_xpath = '//*[@id="body"]/center/center/table[2]/tr/td[3]/text()'

  30. alternative_size_xpath = '//*[@id="body"]/center/center/table/tr/td[3]/text()'

  31. 

  32. 

  33. # do search-request

  34. def request(query, params):

  35.     params['url'] = search_url.format(search_term=quote(query),

  36.                                       page_no=params['pageno'] - 1)

  37.     return params

  38. 

  39. 

  40. # get response from search-request

  41. def response(resp):

  42.     results = []

  43.     dom = html.fromstring(resp.text)

  44.     torrent_links = dom.xpath(torrent_xpath)

  45.     if len(torrent_links) > 0:

  46.         seeds = dom.xpath(seeds_xpath)

  47.         peers = dom.xpath(peers_xpath)

  48.         titles = dom.xpath(title_xpath)

  49.         sizes = dom.xpath(size_xpath)

  50.         ages = dom.xpath(age_xpath)

  51.     else:  # under ~5 results uses a different xpath

  52.         torrent_links = dom.xpath(alternative_torrent_xpath)

  53.         seeds = dom.xpath(alternative_seeds_xpath)

  54.         peers = dom.xpath(alternative_peers_xpath)

  55.         titles = dom.xpath(alternative_title_xpath)

  56.         sizes = dom.xpath(alternative_size_xpath)

  57.         ages = dom.xpath(alternative_age_xpath)

  58.     # return empty array if nothing is found

  59.     if not torrent_links:

  60.         return []

  61. 

  62.     # parse results

  63.     for index, result in enumerate(torrent_links):

  64.         link = result.attrib.get('href')

  65.         href = urljoin(url, link)

  66.         results.append({'url': href,

  67.                         'title': titles[index].text_content(),

  68.                         'content': '{}, {}'.format(sizes[index], ages[index]),

  69.                         'seed': seeds[index],

  70.                         'leech': peers[index],

  71. 

  72.                         'template': 'torrent.html'})

  73. 

  74.     # return results sorted by seeder

  75.     return sorted(results, key=itemgetter('seed'), reverse=True)