searxng/searx/engines/kickass.py

126 lines
4.0 KiB
Python
Raw Normal View History

## Kickass Torrent (Videos, Music, Files)
2014-12-16 16:26:16 +00:00
#
# @website https://kickass.so
# @provide-api no (nothing found)
2014-12-16 16:26:16 +00:00
#
# @using-api no
# @results HTML (using search portal)
# @stable yes (HTML can change)
# @parse url, title, content, seed, leech, magnetlink
from urlparse import urljoin
from cgi import escape
from urllib import quote
from lxml import html
from operator import itemgetter
2015-01-30 20:02:17 +00:00
from searx.engines.xpath import extract_text
# engine dependent config
categories = ['videos', 'music', 'files']
paging = True
# search-url
url = 'https://kickass.to/'
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'])
2014-12-16 16:26:16 +00:00
# FIX: SSLError: hostname 'kickass.so'
# doesn't match either of '*.kickass.to', 'kickass.to'
params['verify'] = False
return params
# get response from search-request
def response(resp):
results = []
# check if redirect comparing to the True value,
# because resp can be a Mock object, and any attribut name returns something.
2015-02-12 13:50:41 +00:00
if resp.is_redirect is True:
return 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 = escape(extract_text(result.xpath(content_xpath)))
seed = result.xpath('.//td[contains(@class, "green")]/text()')[0]
leech = result.xpath('.//td[contains(@class, "red")]/text()')[0]
2015-01-10 18:40:27 +00:00
filesize = result.xpath('.//td[contains(@class, "nobr")]/text()')[0]
filesize_multiplier = result.xpath('.//td[contains(@class, "nobr")]//span/text()')[0]
files = result.xpath('.//td[contains(@class, "center")][2]/text()')[0]
# convert seed to int if possible
if seed.isdigit():
seed = int(seed)
else:
seed = 0
# convert leech to int if possible
if leech.isdigit():
leech = int(leech)
else:
leech = 0
2015-01-10 18:40:27 +00:00
# convert filesize to byte if possible
try:
filesize = float(filesize)
2015-01-10 19:01:36 +00:00
2015-01-10 18:40:27 +00:00
# convert filesize to byte
if filesize_multiplier == 'TB':
2015-01-10 19:01:36 +00:00
filesize = int(filesize * 1024 * 1024 * 1024 * 1024)
2015-01-10 18:40:27 +00:00
elif filesize_multiplier == 'GB':
2015-01-10 19:01:36 +00:00
filesize = int(filesize * 1024 * 1024 * 1024)
2015-01-10 18:40:27 +00:00
elif filesize_multiplier == 'MB':
2015-01-10 19:01:36 +00:00
filesize = int(filesize * 1024 * 1024)
2015-01-30 20:02:17 +00:00
elif filesize_multiplier == 'KB':
2015-01-10 19:01:36 +00:00
filesize = int(filesize * 1024)
2015-01-10 18:40:27 +00:00
except:
filesize = None
# convert files to int if possible
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)