kickass ok

weboob/backends/kickass/browser.py

@@ -18,7 +18,6 @@
 
 from weboob.tools.browser import BaseBrowser
 
-from .pages.index import IndexPage
 from .pages.torrents import TorrentsPage, TorrentPage
 
 
@@ -26,6 +25,7 @@ __all__ = ['KickassBrowser']
 
 
 class KickassBrowser(BaseBrowser):
+    DOMAIN = 'kickasstorrents.com'
     PROTOCOL = 'http'
     ENCODING = 'utf-8'
     USER_AGENT = BaseBrowser.USER_AGENTS['wget']
@@ -56,7 +56,7 @@ class KickassBrowser(BaseBrowser):
     #    return True
 
     def home(self):
-        return self.location('http://fr.kickasstorrents.com/')
+        return self.location('http://kickasstorrents.com')
 
     def iter_torrents(self, pattern):
         #self.location(self.buildurl('/torrents.php', searchstr=pattern))

weboob/backends/kickass/pages/index.py

@@ -1,28 +0,0 @@
-# -*- 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
-
-
-__all__ = ['IndexPage']
-
-
-class IndexPage(BasePage):
-    def is_logged(self):
-        return 'id' in self.document.find('body').attrib
-

weboob/backends/kickass/pages/torrents.py

@@ -31,7 +31,6 @@ class TorrentsPage(BasePage):
              'GB': 1024*1024*1024,
              'TB': 1024*1024*1024*1024,
             }
-        #return float(n.replace(',', '')) * m.get(u, 1)
         return float(n*m[u])
 
     def iter_torrents(self):
@@ -39,6 +38,13 @@ class TorrentsPage(BasePage):
         for tr in self.document.getiterator('tr'):
             if tr.attrib.get('class','') == 'odd' or tr.attrib.get('class','') == ' even':
                 title = tr.getchildren()[0].getchildren()[1].getchildren()[1].text
+                if not title:
+                    title = ''
+                for red in tr.getchildren()[0].getchildren()[1].getchildren()[1].getchildren():
+                    if red.text:
+                        title += red.text
+                    if red.tail:
+                        title += red.tail
                 idt = tr.getchildren()[0].getchildren()[1].getchildren()[1].attrib.get('href','').replace('/','').replace('.html','')
                 url = tr.getchildren()[0].getchildren()[0].getchildren()[0].getchildren()[0].attrib.get('href','')
                 size = tr.getchildren()[1].text
@@ -57,29 +63,47 @@ class TorrentsPage(BasePage):
                 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):
+
+        description = "No description"
         for div in self.document.getiterator('div'):
-            if div.attrib.get('id','') == 'title':
+            if div.attrib.get('id','') == 'desc':
-                title = div.text.strip()
+                description = div.text.strip()
-            elif div.attrib.get('class','') == 'download':
+        for td in self.document.getiterator('td'):
-                url = div.getchildren()[0].attrib.get('href','')
+            if td.attrib.get('class','') == 'hreview-aggregate':
-            elif div.attrib.get('id','') == 'details':
+                seed = int(td.getchildren()[2].getchildren()[0].getchildren()[0].text)
-                size = float(div.getchildren()[0].getchildren()[5].text.split('(')[1].split('Bytes')[0])
+                leech = int(td.getchildren()[2].getchildren()[1].getchildren()[0].text)
-                if len(div.getchildren()) > 1 \
+                url = td.getchildren()[3].getchildren()[0].attrib.get('href')
-                        and div.getchildren()[1].attrib.get('class','') == 'col2' :
+                title = td.getchildren()[1].getchildren()[0].getchildren()[0].text
-                    seed = div.getchildren()[1].getchildren()[7].text
+
-                    leech = div.getchildren()[1].getchildren()[9].text
+        size = 0
-                else:
+        for span in self.document.getiterator('span'):
-                    seed = div.getchildren()[0].getchildren()[24].text
+            if span.attrib.get('class','') == "folder" or span.attrib.get('class','') == "folderopen":
-                    leech = div.getchildren()[0].getchildren()[26].text
+                size = span.getchildren()[1].tail
-            elif div.attrib.get('class','') == 'nfo':
+                u = size.split(' ')[-1].split(')')[0]
-                description = div.getchildren()[0].text
+                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 = size
+        torrent.size = self.unit(size,u)
         torrent.seeders = int(seed)
         torrent.leechers = int(leech)
         torrent.description = description
-        torrent.files = ['NYI']
+        torrent.files = files
-
+                    
         return torrent

weboob/backends/piratebay/browser.py

@@ -26,6 +26,7 @@ __all__ = ['PiratebayBrowser']
 
 
 class PiratebayBrowser(BaseBrowser):
+    DOMAIN = 'thepiratebay.org'
     PROTOCOL = 'https'
     ENCODING = 'utf-8'
     USER_AGENT = BaseBrowser.USER_AGENTS['wget']