searxng/searx/engines/kickass.py

93 lines
2.9 KiB
Python
Raw Normal View History

"""
Kickass Torrent (Videos, Music, Files)
@website https://kickass.so
@provide-api no (nothing found)
@using-api no
@results HTML (using search portal)
@stable yes (HTML can change)
@parse url, title, content, seed, leech, magnetlink
"""
from lxml import html
from operator import itemgetter
2015-01-30 20:02:17 +00:00
from searx.engines.xpath import extract_text
2016-10-11 17:31:42 +00:00
from searx.utils import get_torrent_size, convert_str_to_int
2016-11-30 17:43:03 +00:00
from searx.url_utils import quote, urljoin
# engine dependent config
categories = ['videos', 'music', 'files']
paging = True
# search-url
2016-10-11 17:31:42 +00:00
url = 'https://kickass.cd/'
search_url = url + 'search/{search_term}/{pageno}/'
# specific xpath variables
magnet_xpath = './/a[@title="Torrent magnet link"]'
2015-01-10 18:40:27 +00:00
torrent_xpath = './/a[@title="Download torrent file"]'
content_xpath = './/span[@class="font11px lightgrey block"]'
# do search-request
def request(query, params):
params['url'] = search_url.format(search_term=quote(query),
pageno=params['pageno'])
return params
# get response from search-request
def response(resp):
results = []
dom = html.fromstring(resp.text)
search_res = dom.xpath('//table[@class="data"]//tr')
# return empty array if nothing is found
if not search_res:
return []
# parse results
for result in search_res[1:]:
link = result.xpath('.//a[@class="cellMainLink"]')[0]
href = urljoin(url, link.attrib['href'])
2015-01-30 20:02:17 +00:00
title = extract_text(link)
content = extract_text(result.xpath(content_xpath))
2016-10-11 17:31:42 +00:00
seed = extract_text(result.xpath('.//td[contains(@class, "green")]'))
leech = extract_text(result.xpath('.//td[contains(@class, "red")]'))
filesize_info = extract_text(result.xpath('.//td[contains(@class, "nobr")]'))
files = extract_text(result.xpath('.//td[contains(@class, "center")][2]'))
2016-10-11 17:31:42 +00:00
seed = convert_str_to_int(seed)
leech = convert_str_to_int(leech)
filesize, filesize_multiplier = filesize_info.split()
filesize = get_torrent_size(filesize, filesize_multiplier)
2015-01-10 18:40:27 +00:00
if files.isdigit():
files = int(files)
else:
files = None
magnetlink = result.xpath(magnet_xpath)[0].attrib['href']
2015-01-10 19:01:36 +00:00
2015-01-10 18:40:27 +00:00
torrentfile = result.xpath(torrent_xpath)[0].attrib['href']
torrentfileurl = quote(torrentfile, safe="%/:=&?~#+!$,;'@()*")
# append result
results.append({'url': href,
'title': title,
'content': content,
'seed': seed,
'leech': leech,
2015-01-10 18:40:27 +00:00
'filesize': filesize,
'files': files,
'magnetlink': magnetlink,
'torrentfile': torrentfileurl,
'template': 'torrent.html'})
# return results sorted by seeder
return sorted(results, key=itemgetter('seed'), reverse=True)