new 'gazelle' backend (bittorrent trackers), implementing ICapTorrent

weboob/backends/gazelle/__init__.py

@@ -0,0 +1 @@
+from .backend import GazelleBackend

weboob/backends/gazelle/backend.py

@@ -0,0 +1,57 @@
+# -*- coding: utf-8 -*-
+
+"""
+Copyright(C) 2010  Romain Bignon
+
+This program 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, version 3 of the License.
+
+This program 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 this program; if not, write to the Free Software
+Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+
+"""
+
+from weboob.backend import BaseBackend
+from weboob.capabilities.torrent import ICapTorrent
+
+from .browser import GazelleBrowser
+
+
+__all__ = ['GazelleBackend']
+
+
+class GazelleBackend(BaseBackend, ICapTorrent):
+    NAME = 'gazelle'
+    MAINTAINER = 'Romain Bignon'
+    EMAIL = 'romain@peerfuse.org'
+    VERSION = '0.1'
+    DESCRIPTION = 'gazelle bittorrent tracker'
+    LICENSE = 'GPLv3'
+
+    CONFIG = {'username':      BaseBackend.ConfigField(description='Username on website'),
+              'password':      BaseBackend.ConfigField(description='Password of account', is_masked=True),
+              'protocol':      BaseBackend.ConfigField(description='Protocol to use', default='https'),
+              'domain':        BaseBackend.ConfigField(description='Domain', default='ssl.what.cd'),
+             }
+    _browser = None
+
+    def __getattr__(self, name):
+        if name == 'browser':
+            if not self._browser:
+                self._browser = GazelleBrowser(self.config['protocol'], self.config['domain'],
+                                               self.config['username'], self.config['password'])
+            return self._browser
+        raise AttributeError, name
+
+    def get_torrent(self, id):
+        return self.browser.get_torrent(id)
+
+    def iter_torrents(self, pattern):
+        return self.browser.iter_torrents(pattern)

weboob/backends/gazelle/browser.py

@@ -0,0 +1,69 @@
+# -*- coding: utf-8 -*-
+
+"""
+Copyright(C) 2010  Romain Bignon
+
+This program 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, version 3 of the License.
+
+This program 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 this program; if not, write to the Free Software
+Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+
+"""
+
+from weboob.tools.browser import BaseBrowser
+
+from .pages.index import IndexPage, LoginPage
+from .pages.torrents import TorrentsPage
+
+
+__all__ = ['GazelleBrowser']
+
+
+class GazelleBrowser(BaseBrowser):
+    DOMAIN = 'ssl.what.cd'
+    PROTOCOL = 'https'
+    PAGES = {'https?://%s/?(index.php)?':  IndexPage,
+             'https?://%s/login.php':      LoginPage,
+             'https?://%s/torrents.php.*': TorrentsPage,
+            }
+
+    def __init__(self, protocol, domain, *args, **kwargs):
+        self.DOMAIN = domain
+        self.PROTOCOL = protocol
+        self.PAGES = {}
+        for key, value in GazelleBrowser.PAGES.iteritems():
+            self.PAGES[key % domain] = value
+
+        BaseBrowser.__init__(self, *args, **kwargs)
+
+    def login(self):
+        if not self.is_on_page(LoginPage):
+            self.home()
+        self.page.login(self.username, self.password)
+
+    def is_logged(self):
+        if not self.page or self.is_on_page(LoginPage):
+            return False
+        if self.is_on_page(IndexPage):
+            return self.page.is_logged()
+        return True
+
+    def home(self):
+        return self.location('%s://%s/login.php' % (self.PROTOCOL, self.DOMAIN))
+
+    def iter_torrents(self, pattern):
+        self.location('/torrents.php?searchstr=%s' % pattern)
+
+        assert self.is_on_page(TorrentsPage)
+        return self.page.iter_torrents()
+
+    def get_torrent(self, id):
+        pass

weboob/backends/gazelle/pages/index.py

@@ -0,0 +1,36 @@
+# -*- coding: utf-8 -*-
+
+"""
+Copyright(C) 2010  Romain Bignon
+
+This program 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, version 3 of the License.
+
+This program 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 this program; if not, write to the Free Software
+Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+
+"""
+
+from weboob.tools.browser import BasePage
+
+
+__all__ = ['IndexPage', 'LoginPage']
+
+
+class IndexPage(BasePage):
+    def is_logged(self):
+        return 'id' in self.document.find('body').attrib
+
+class LoginPage(BasePage):
+    def login(self, login, password):
+        self.browser.select_form(nr=0)
+        self.browser['username'] = login
+        self.browser['password'] = password
+        self.browser.submit()

weboob/backends/gazelle/pages/torrents.py

@@ -0,0 +1,94 @@
+# -*- coding: utf-8 -*-
+
+"""
+Copyright(C) 2010  Romain Bignon
+
+This program 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, version 3 of the License.
+
+This program 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 this program; if not, write to the Free Software
+Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+
+"""
+
+import re
+
+from weboob.tools.browser import BasePage
+from weboob.capabilities.torrent import Torrent
+
+
+__all__ = ['TorrentsPage']
+
+
+class TorrentsPage(BasePage):
+    TORRENTID_REGEXP = re.compile('torrents\.php\?action=download&id=(\d+)')
+    def unit(self, n, u):
+        m = {'KB': 1024,
+             'MB': 1024*1024,
+             'GB': 1024*1024*1024,
+             'TB': 1024*1024*1024*1024,
+            }
+        return float(n.replace(',', '')) * m.get(u, 1)
+
+    def iter_torrents(self):
+        table = self.document.getroot().cssselect('table#torrent_table')
+        if not table:
+            table = self.document.getroot().cssselect('table#browse_torrent_table')
+        if table:
+            table = table[0]
+            current_group = None
+            for tr in table.findall('tr'):
+                if tr.attrib.get('class', '') == 'group':
+                    tds = tr.findall('td')
+                    current_group = u''
+                    div = tds[-6]
+                    if div.getchildren()[0].tag == 'div':
+                        div = div.getchildren()[0]
+                    for a in div.findall('a'):
+                        if not a.text:
+                            continue
+                        if current_group:
+                            current_group += ' - '
+                        current_group += a.text
+                elif tr.attrib.get('class', '').startswith('group_torrent ') or \
+                     tr.attrib.get('class', '').startswith('torrent'):
+                    tds = tr.findall('td')
+
+                    title = current_group
+                    if len(tds) == 7:
+                        # Under a group
+                        i = 0
+                    elif len(tds) in (8,9):
+                        # An alone torrent
+                        i = len(tds) - 7
+                    else:
+                        # Useless title
+                        continue
+
+                    if title:
+                        title += u' (%s)' % tds[i].find('a').text
+                    else:
+                        title = tds[i].find('a').text
+                    url = tds[i].find('span').find('a').attrib['href']
+                    id = self.TORRENTID_REGEXP.match(url)
+                    if not id:
+                        continue
+                    id = id.group(1)
+                    size = self.unit(*tds[i+3].text.split())
+                    seeders = int(tds[i+5].text)
+                    leechers = int(tds[i+6].text)
+
+                    torrent = Torrent(id,
+                                      title,
+                                      url=url,
+                                      size=size,
+                                      seeders=seeders,
+                                      leechers=leechers)
+                    yield torrent

weboob/capabilities/torrent.py

@@ -24,7 +24,7 @@ from .cap import ICap
 __all__ = ['ICapTorrent']
 
 class Torrent(object):
-    def __init__(self, id, name, date=None, size=0.0, url=u'', seeders=0, leechers=0, files=[])
+    def __init__(self, id, name, date=None, size=0.0, url=u'', seeders=0, leechers=0, files=[]):
         self.id = id
         self.name = name
         self.date = date