From 0cc2458513709cfa81faa1c280cee28853836bb9 Mon Sep 17 00:00:00 2001
From: Julien Veyssier <julien.veyssier@aiur.fr>
Date: Fri, 26 Nov 2010 17:15:13 +0100
Subject: [PATCH] iter_torrent wokay, unit fail

---
 weboob/backends/piratebay/browser.py        |  6 ++-
 weboob/backends/piratebay/pages/torrents.py | 45 +++++++++++----------
 2 files changed, 28 insertions(+), 23 deletions(-)

diff --git a/weboob/backends/piratebay/browser.py b/weboob/backends/piratebay/browser.py
index 52105b3f..839a287f 100644
--- a/weboob/backends/piratebay/browser.py
+++ b/weboob/backends/piratebay/browser.py
@@ -26,6 +26,8 @@ __all__ = ['PiratebayBrowser']
 
 
 class PiratebayBrowser(BaseBrowser):
+    PROTOCOL = 'https'
+    USER_AGENT = BaseBrowser.USER_AGENTS['wget']
     PAGES = {'https://thepiratebay.org' : IndexPage,
              'https://thepiratebay.org/search/.*/0/7/0' : TorrentsPage,
              #'https://thepiratebay.org/torrent/.*' : TorrentPage
@@ -34,7 +36,7 @@ class PiratebayBrowser(BaseBrowser):
     def __init__(self, *args, **kwargs):
         #self.DOMAIN = domain
         #self.PROTOCOL = protocol
-        self.PAGES = {}
+        #self.PAGES = {}
         #for key, value in PiratebayBrowser.PAGES.iteritems():
         #    self.PAGES[key % domain] = value
 
@@ -57,7 +59,7 @@ class PiratebayBrowser(BaseBrowser):
 
     def iter_torrents(self, pattern):
         #self.location(self.buildurl('/torrents.php', searchstr=pattern))
-        self.location('https://thepiratebay.org/search/%s/0/7/0' % pattern)
+        self.location('https://thepiratebay.org/search/%s/0/7/0' % pattern, '')
 
         assert self.is_on_page(TorrentsPage)
         return self.page.iter_torrents()
diff --git a/weboob/backends/piratebay/pages/torrents.py b/weboob/backends/piratebay/pages/torrents.py
index f52e227e..99cffcc0 100644
--- a/weboob/backends/piratebay/pages/torrents.py
+++ b/weboob/backends/piratebay/pages/torrents.py
@@ -50,30 +50,33 @@ class TorrentsPage(BasePage):
                 raise Exception('You''re in serious troubles!')
             else:
                 for tr in table.getiterator('tr'):
-                    td = tr.getchildren()[1]
-                    div = td.getchildren()[0]
-                    link = div.find('a').attrib('href')
-                    title = div.find('a').text
-                    idt = link.split('/')[2]
+                    if tr.get('class','') != "header":
+                        td = tr.getchildren()[1]
+                        div = td.getchildren()[0]
+                        link = div.find('a').attrib['href']
+                        title = div.find('a').text
+                        idt = link.split('/')[2]
 
-                    a = td.getchildren()[1]
-                    url = a.attrib('href')
+                        a = td.getchildren()[1]
+                        url = a.attrib['href']
 
-                    size = td.find('font').text.split(',')[1]
-                    size = size.split(' ')[2]
-                    u = size[-3:].replace('i','')
-                    size = size[:-3]
-                    
-                    seed = tr.getchildren()[2].text
-                    leech = tr.getchildren()[3].text
+                        size = td.find('font').text.split(',')[1]
+                        size = size.split(' ')[2]
+                        u = size[-3:].replace('i','')
+                        print "u:"+u
+                        size = size[:-3]
+                        print 'size:'+size
+                        
+                        seed = tr.getchildren()[2].text
+                        leech = tr.getchildren()[3].text
 
-                    torrent = Torrent(idt,
-                                      title,
-                                      url=url,
-                                      size=size,
-                                      seeders=seeders,
-                                      leechers=leechers)
-                    yield torrent
+                        torrent = Torrent(idt,
+                                          title,
+                                          url=url,
+                                          size=self.unit(size.replace('.',','),u),
+                                          seeders=int(seed),
+                                          leechers=int(leech))
+                        yield torrent
 
     def get_torrent(self, id):
         table = self.document.getroot().cssselect('div.thin')