SickGear/sickbeard/providers/extratorrent.py

# coding=utf-8
#
# This file is part of SickGear.
#
# SickGear is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# SickGear is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with SickGear.  If not, see <http://www.gnu.org/licenses/>.

import re
import traceback
import urllib

from . import generic
from sickbeard import logger
from sickbeard.bs4_parser import BS4Parser
from sickbeard.helpers import tryInt
from lib.unidecode import unidecode


class ExtraTorrentProvider(generic.TorrentProvider):

    def __init__(self):
        generic.TorrentProvider.__init__(self, 'ExtraTorrent')

        self.url_home = ['https://www.extratorrent%s/' % u for u in '.life', 'live.com', 'online.com', '.one'] + \
                        ['https://extra.to/'] + \
                        ['https://etmirror.com/', 'https://etproxy.com/', 'https://extratorrent.usbypass.xyz/']

        self.url_vars = {'search': 'search/?new=1&search=%s&s_cat=8', 'browse': 'view/today/TV.html',
                         'get': '%s'}
        self.url_tmpl = {'config_provider_home_uri': '%(home)s', 'search': '%(home)s%(vars)s',
                         'browse': '%(home)s%(vars)s', 'get': '%(home)s%(vars)s'}

        self.minseed, self.minleech = 2 * [None]

    @staticmethod
    def _has_signature(data=None):
        return data and re.search(r'(?i)ExtraTorrent', data[33:1024:])

    def _search_provider(self, search_params, **kwargs):

        results = []
        if not self.url:
            return results

        items = {'Cache': [], 'Season': [], 'Episode': [], 'Propers': []}

        rc = dict((k, re.compile('(?i)' + v)) for (k, v) in {
            'get': 'download', 'title': '(?:^download|torrent$)', 'get_url': '^/(torrent_)?'}.iteritems())

        for mode in search_params.keys():
            for search_string in search_params[mode]:

                search_string = isinstance(search_string, unicode) and unidecode(search_string) or search_string

                search_url = self.urls['browse'] if 'Cache' == mode \
                    else self.urls['search'] % (urllib.quote_plus(search_string))

                html = self.get_url(search_url)

                cnt = len(items[mode])
                try:
                    if not html or self._has_no_results(html):
                        raise generic.HaltParseException
                    with BS4Parser(html, features=['html5lib', 'permissive']) as soup:
                        torrent_table = soup.find('table', class_='tl')
                        torrent_rows = [] if not torrent_table else torrent_table.find_all('tr')

                        if 2 > len(torrent_rows):
                            raise generic.HaltParseException

                        head = None
                        for tr in torrent_rows[1:]:
                            cells = tr.find_all('td')
                            if 5 > len(cells):
                                continue
                            try:
                                head = head if None is not head else self._header_row(tr)
                                seeders, leechers, size = [tryInt(n.replace('---', '0'), n) for n in [
                                    cells[head[x]].get_text().strip() for x in 'seed', 'leech', 'size']]
                                if self._peers_fail(mode, seeders, leechers):
                                    continue

                                info = tr.find('a', title=rc['get']) or {}
                                title = rc['title'].sub('', info.get('title') or '').strip()
                                download_url = self._link(rc['get_url'].sub('', info['href']))
                            except (AttributeError, TypeError, ValueError, IndexError):
                                continue

                            if title and download_url:
                                items[mode].append((title, download_url, seeders, self._bytesizer(size)))

                except generic.HaltParseException:
                    pass
                except (StandardError, Exception):
                    logger.log(u'Failed to parse. Traceback: %s' % traceback.format_exc(), logger.ERROR)

                self._log_search(mode, len(items[mode]) - cnt, search_url)

            results = self._sort_seeding(mode, results + items[mode])

        return results


provider = ExtraTorrentProvider()