isohunt 50%

weboob/backends/isohunt/__init__.py

@@ -0,0 +1,3 @@
+from .backend import IsohuntBackend
+
+__all__ = ['IsohuntBackend']

weboob/backends/isohunt/backend.py

@@ -0,0 +1,54 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010  Julien Veyssier
+#
+# 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.capabilities.torrent import ICapTorrent
+from weboob.tools.backend import BaseBackend
+
+from .browser import IsohuntBrowser
+
+
+__all__ = ['IsohuntBackend']
+
+
+class IsohuntBackend(BaseBackend, ICapTorrent):
+    NAME = 'isohunt'
+    MAINTAINER = 'Julien Veyssier'
+    EMAIL = 'julien.veyssier@aiur.fr'
+    VERSION = '0.4'
+    DESCRIPTION = 'isohunt.com bittorrent tracker'
+    LICENSE = 'GPLv3'
+    #CONFIG = ValuesDict(Value('domain',   label='Domain (example "ssl.what.cd")'),
+    #                    Value('protocol', label='Protocol to use', choices=('http', 'https')),
+    #                    Value('username', label='Username'),
+    #                    Value('password', label='Password', masked=True))
+    BROWSER = IsohuntBrowser
+
+    def create_default_browser(self):
+        return self.create_browser()
+
+    def get_torrent(self, id):
+        return self.browser.get_torrent(id)
+
+    def get_torrent_file(self, id):
+        torrent = self.browser.get_torrent(id)
+        if not torrent:
+            return None
+
+        return self.browser.openurl(torrent.url.encode('utf-8')).read()
+
+    def iter_torrents(self, pattern):
+        return self.browser.iter_torrents(pattern.replace(' ','+'))

weboob/backends/isohunt/browser.py

@@ -0,0 +1,53 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010  Julien Veyssier
+#
+# 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.torrents import TorrentsPage, TorrentPage
+
+
+__all__ = ['IsohuntBrowser']
+
+
+class IsohuntBrowser(BaseBrowser):
+    DOMAIN = 'isohunt.com'
+    PROTOCOL = 'https'
+    ENCODING = 'utf-8'
+    USER_AGENT = BaseBrowser.USER_AGENTS['wget']
+    PAGES = {
+             'https://isohunt.com/torrents/.*iht=-1&ihp=1&ihs1=2&iho1=d' : TorrentsPage,
+             'http://isohunt.com/torrent_details.*tab=summary' : TorrentPage
+             }
+
+    def __init__(self, *args, **kwargs):
+        BaseBrowser.__init__(self, *args, **kwargs)
+
+    def home(self):
+        return self.location('https://isohunt.com')
+
+    def iter_torrents(self, pattern):
+        self.location('https://isohunt.com/torrents/%s?iht=-1&ihp=1&ihs1=2&iho1=d' % pattern)
+
+        assert self.is_on_page(TorrentsPage)
+        return self.page.iter_torrents()
+
+    def get_torrent(self, id):
+        self.location('https://isohunt.com/torrent_details/%s/?tab=summary' % id)
+
+        assert self.is_on_page(TorrentPage)
+        return self.page.get_torrent(id)

weboob/backends/isohunt/pages/torrents.py

@@ -0,0 +1,117 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010  Julien Veyssier
+#
+# 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
+from weboob.capabilities.torrent import Torrent
+
+
+__all__ = ['TorrentsPage']
+
+
+class TorrentsPage(BasePage):
+    def unit(self, n, u):
+        m = {'KB': 1024,
+             'MB': 1024*1024,
+             'GB': 1024*1024*1024,
+             'TB': 1024*1024*1024*1024,
+            }
+        return float(n*m[u])
+
+    def iter_torrents(self):
+
+
+
+        for tr in self.document.getiterator('tr'):
+            if tr.attrib.get('class','') == 'hlRow':
+                atitle = tr.getchildren()[2].getchildren()[1]
+                title = atitle.text
+                if not title:
+                    title = ''
+                for bold in atitle.getchildren():
+                    if bold.text:
+                        title += bold.text
+                    if bold.tail:
+                        title += bold.tail
+                idt = tr.getchildren()[2].getchildren()[0].attrib.get('href','')
+                idt = idt.split('/')[2]
+                size = tr.getchildren()[3].text
+                u = size[-2:]
+                size = float(size[:-3])
+                seed = tr.getchildren()[4].text
+                leech = tr.getchildren()[5].text
+                url = 'https://isohunt.com/download/%s/mon_joli_torrent.torrent' % idt
+
+                torrent = Torrent(idt,
+                                  title,
+                                  url=url,
+                                  size=self.unit(size,u),
+                                  seeders=int(seed),
+                                  leechers=int(leech))
+                yield torrent
+
+class TorrentPage(BasePage):
+    def unit(self, n, u):
+        m = {'KB': 1024,
+             'MB': 1024*1024,
+             'GB': 1024*1024*1024,
+             'TB': 1024*1024*1024*1024,
+            }
+        return float(n*m[u])
+
+    def get_torrent(self, id):
+        url = 'https://isohunt.com/download/%s/mon_joli_torrent.torrent' % id
+        for a in self.document.getiterator('a'):
+            if 'Search more torrents of' in a.attrib.get('title',''):
+                title = a.tail
+        #--------------------------TODO
+
+        description = "No description"
+        for div in self.document.getiterator('div'):
+            if div.attrib.get('id','') == 'desc':
+                description = div.text.strip()
+        for td in self.document.getiterator('td'):
+            if td.attrib.get('class','') == 'hreview-aggregate':
+                seed = int(td.getchildren()[2].getchildren()[0].getchildren()[0].text)
+                leech = int(td.getchildren()[2].getchildren()[1].getchildren()[0].text)
+                url = td.getchildren()[3].getchildren()[0].attrib.get('href')
+                title = td.getchildren()[1].getchildren()[0].getchildren()[0].text
+
+        size = 0
+        for span in self.document.getiterator('span'):
+            if span.attrib.get('class','') == "folder" or span.attrib.get('class','') == "folderopen":
+                size = span.getchildren()[1].tail
+                u = size.split(' ')[-1].split(')')[0]
+                size = float(size.split(': ')[1].split(' ')[0].replace(',','.'))
+
+        files = []
+        for td in self.document.getiterator('td'):
+            if td.attrib.get('class','') == 'torFileName':
+                files.append(td.text)
+
+
+        torrent = Torrent(id, title)
+        torrent = Torrent(id, title)
+        torrent.url = url
+        torrent.size = self.unit(size,u)
+        torrent.seeders = int(seed)
+        torrent.leechers = int(leech)
+        torrent.description = description
+        torrent.files = files
+                    
+        return torrent

weboob/backends/isohunt/test.py

@@ -0,0 +1,26 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010  Julien Veyssier
+#
+# 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.test import BackendTest
+
+class IsohuntTest(BackendTest):
+    BACKEND = 'isohunt'
+
+    def test_torrent(self):
+        l = list(self.backend.iter_torrents('debian'))
+        if len(l) > 0:
+            self.backend.get_torrent_file(l[0].id)