SickGear/sickgear/providers/nyaa.py

#
# 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

from . import generic
from .. import logger
from ..helpers import try_int
from bs4_parser import BS4Parser

from six import iteritems


class NyaaProvider(generic.TorrentProvider):

    def __init__(self):
        generic.TorrentProvider.__init__(self, 'Nyaa', anime_only=True)

        self.url_base = 'https://www.nyaa.si/'
        self.urls = {'config_provider_home_uri': self.url_base, 'search': self.url_base + '?f=%s&c=1_0&q=%s'}

        self.url = self.urls['config_provider_home_uri']

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

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

        results = []

        if self.show_obj and not self.show_obj.is_anime:
            return results

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

        rc = dict([(k, re.compile('(?i)' + v)) for (k, v) in iteritems({'info': 'view', 'get': '(?:torrent|magnet:)'})])
        for mode in search_params:
            for search_string in search_params[mode]:
                search_url = self.urls['search'] % ((0, 2)[self.confirmed], search_string.replace('.', ' '))

                html = self.get_url(search_url)
                if self.should_skip():
                    return results

                cnt = len(items[mode])
                try:
                    if not html or self._has_no_results(html):
                        raise generic.HaltParseException

                    parse_only = dict(table={'class': (lambda at: at and 'torrent-list' in at)})
                    with BS4Parser(html, parse_only=parse_only) as tbl:
                        tbl_rows = [] if not tbl else tbl.find_all('tr')

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

                        head = None
                        for tr in tbl_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 = [try_int(n, n) for n in [
                                    cells[head[x]].get_text().strip() for x in ('seed', 'leech', 'size')]]
                                if self._reject_item(seeders, leechers):
                                    continue

                                title = tr.find('a', href=rc['info']).get_text().strip()
                                download_url = self._link(tr.find('a', href=rc['get'])['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 (BaseException, Exception):
                    logger.error(f'Failed to parse. Traceback: {traceback.format_exc()}')

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

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

        return results


provider = NyaaProvider()