Add provider TorrentDB.

CHANGES.md

@@ -1,5 +1,6 @@
 ### 0.25.0 (2021-xx-xx xx:xx:xx UTC)
 
+* Add provider TorrentDB
 
 
 [develop changelog]

sickbeard/providers/__init__.py

@@ -43,7 +43,7 @@ __all__ = [
     'immortalseed', 'iptorrents', 'limetorrents', 'magnetdl', 'milkie', 'morethan', 'nebulance', 'ncore', 'nyaa',
     'pretome', 'privatehd', 'ptf',
     'rarbg', 'revtt', 'scenehd', 'scenetime', 'shazbat', 'showrss', 'snowfl', 'speedapp', 'speedcd',
-    'thepiratebay', 'torlock', 'torrentday', 'torrenting', 'torrentleech',  'tvchaosuk',
+    'thepiratebay', 'torlock', 'torrentday', 'torrentdb', 'torrenting', 'torrentleech',  'tvchaosuk',
     'xspeeds', 'zooqle',
     # anime
     'tokyotoshokan',

sickbeard/providers/torrentdb.py

@@ -0,0 +1,196 @@
+# 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 random
+import re
+import time
+import traceback
+
+from . import generic
+from .. import logger
+from ..helpers import try_int
+from bs4_parser import BS4Parser
+
+from _23 import unidecode
+from six import iteritems
+
+
+class TorrentDBProvider(generic.TorrentProvider):
+
+    def __init__(self):
+        generic.TorrentProvider.__init__(self, 'TorrentDB')
+
+        self.url_base = 'https://torrentdb.net/'
+        self.urls = {'config_provider_home_uri': self.url_base,
+                     'login_action': self.url_base + 'login',
+                     'logout': self.url_base + 'logout',
+                     'passkey': self.url_base + 'settings',
+                     'search': self.url_base + 'filter/torrents?%s' % '&'.join(
+                         ['_token=%s', '%s', 'tags=', 'sorting=created_at', 'direction=desc', 'qty=100', 'search=%s'])}
+
+        self.categories = {'Season': [21, 52, 61, 62, 63, 64, 65], 'anime': [53]}
+        self.categories['Cache'] = self.categories['Episode'] = self.categories['Season']
+
+        self.url = self.urls['config_provider_home_uri']
+
+        self.username, self.password, self._token, self._passkey, \
+            self.freeleech, self.minseed, self.minleech = 7 * [None]
+
+    def _authorised(self, **kwargs):
+
+        return super(TorrentDBProvider, self)._authorised(
+            logged_in=self.logged_in, post_params=dict(remember='on'),
+            failed_msg=(lambda y=None: u'Failed to parse (or authenticate) a response from %s'))
+
+    def logged_in(self, resp=None):
+
+        result = True
+        if not self._token:
+            try:
+                result = 'Username' not in resp and 'Logout' in resp
+                if not self.session.cookies.get('laravel_session', domain='torrentdb.net'):
+                    raise ValueError('Cookie invalid')
+                input_tag = re.findall(r'(<input[^>]+?"(?:hidden|_token)"[^>]+?"(?:hidden|_token)"[^>]+?>)', resp)[0]
+                csrf = re.findall(r'<meta[^>]+csrf-token[^>]+content[^"]+"\s*([^\s"]+)', resp)[0]
+                token = re.findall(r'value\s*=\s*["\']\s*([^"\'\s]+)', input_tag)[0]
+                self._token = csrf == token and token
+
+                html = self.get_url(self.urls['passkey'], skip_auth=True)
+                with BS4Parser(html, parse_only=dict(form={'action': (lambda at: at and 'change_pid' in at)})) as form:
+                    self._passkey = re.sub('(?mi)^.*?passkey.*?$', '', form.get_text()).strip()
+            except (BaseException, Exception):
+                result = False
+        return result
+
+    def _search_provider(self, search_params, **kwargs):
+
+        results = []
+
+        vals = [i for i in range(5, 16)]
+        random.SystemRandom().shuffle(vals)
+        attempts = None
+        action = 'Failed to authorise'
+        for attempts, s in enumerate((0, vals[0], vals[5], vals[10])):
+            time.sleep(s)
+            if self._authorised():
+                action = 'Authorised'
+                break
+        if attempts:
+            logger.log('%s after %s attempts' % (action, attempts + 1))
+        if 'Auth' not in action:
+            return results
+
+        items = {'Cache': [], 'Season': [], 'Episode': [], 'Propers': []}
+
+        rc = dict([(k, re.compile('(?i)' + v)) for (k, v) in iteritems({'info': r'/torrent/'})])
+
+        for mode in search_params:
+            for search_string in search_params[mode]:
+                search_string = unidecode(search_string)
+                search_url = self.urls['search'] % (
+                    self._token, self._categories_string(mode, 'types[]=%s'), search_string)
+
+                vals = [i for i in range(5, 16)]
+                random.SystemRandom().shuffle(vals)
+                attempts = html = soup = tbl = None
+                action = 'failed fetch'
+                for attempts, s in enumerate((0, vals[0], vals[5], vals[10])):
+                    time.sleep(s)
+                    html = self.get_url(search_url)
+                    if self.should_skip():
+                        logger.log('%s %s after %s attempts' % (mode, action, attempts + 1))
+                        return results
+                    if html:
+                        try:
+                            soup = BS4Parser(html).soup
+                            tbl = soup.find('table', class_=(lambda at: at and 'table' in at))
+                            if tbl:
+                                action = 'data fetched'
+                                break
+                        except (BaseException, Exception):
+                            pass
+                    # after auth multi-attempted, force re-auth due to strange server responses
+                    self.get_url(self.urls['logout'], skip_auth=True)
+                    self._token = None
+
+                if attempts:
+                    logger.log('%s %s after %s attempts' % (mode, action, attempts+1))
+
+                if self.should_skip():
+                    return results
+
+                cnt = len(items[mode])
+                try:
+                    if not html or self._has_no_results(html) or not tbl:
+                        raise generic.HaltParseException
+
+                    with BS4Parser(html, parse_only=dict(table={'class': (lambda at: at and 'table' in at)})) 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, {'info': r'(?:name)'})
+
+                                if self.freeleech:
+                                    marked = ','.join([x.get_text(strip=True).lower()
+                                                       for x in cells[head['info']].find_all(
+                                            'span', attrs={'class': (lambda at: at and 'align-middle' in at)})])
+                                    if 'free' not in marked:
+                                        continue
+
+                                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
+
+                                info = cells[head['info']].find('a', href=rc['info'])
+                                title = info.get_text(strip=True)
+                                download_url = '%s/%s' % (
+                                    info['href'].replace('/torrent/', '/torrent/download/irssi/', 1), self._passkey)
+                            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.log(u'Failed to parse. Traceback: %s' % traceback.format_exc(), logger.ERROR)
+
+                if soup:
+                    soup.clear(True)
+                    del soup
+
+                self._log_search(mode, len(items[mode]) - cnt, search_url)
+
+                if mode in 'Season' and len(items[mode]):
+                    break
+
+            results = self._sort_seeding(mode, results + items[mode])
+
+        return results
+
+
+provider = TorrentDBProvider()