From a7b42940b0b1f59db7e84a7821b7ff0d635f9ca3 Mon Sep 17 00:00:00 2001
From: Julien Veyssier <julien.veyssier@aiur.fr>
Date: Sun, 17 Mar 2013 18:43:22 +0100
Subject: [PATCH] [piratebay] unescape title

---
 modules/imdb/browser.py             | 2 ++
 modules/piratebay/pages/torrents.py | 6 ++++--
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/modules/imdb/browser.py b/modules/imdb/browser.py
index 02905cbd9e..c3b48f2492 100644
--- a/modules/imdb/browser.py
+++ b/modules/imdb/browser.py
@@ -219,6 +219,8 @@ def get_movie_releases(self, id, country):
             '&#xC0;': u'À',
             '&#xE2;': u'â',
             '&#xC9;': u'É',
+            '&#xEB;': u'ë',
+            '&#xF4;': u'ô',
             '&#xE7;': u'ç'
             }
 
diff --git a/modules/piratebay/pages/torrents.py b/modules/piratebay/pages/torrents.py
index e43edc5a81..b09a4240ed 100644
--- a/modules/piratebay/pages/torrents.py
+++ b/modules/piratebay/pages/torrents.py
@@ -22,6 +22,8 @@
 from weboob.capabilities.torrent import Torrent
 from weboob.capabilities.base import NotAvailable, NotLoaded
 
+from html2text import unescape
+
 
 __all__ = ['TorrentsPage']
 
@@ -50,7 +52,7 @@ def iter_torrents(self):
                 td = tr.getchildren()[1]
                 div = td.getchildren()[0]
                 link = div.find('a').attrib['href']
-                title = unicode(div.find('a').text)
+                title = unicode(unescape(div.find('a').text))
                 idt = link.split('/')[2]
 
                 a = td.getchildren()[1]
@@ -80,7 +82,7 @@ def get_torrent(self, id):
         magnet = NotAvailable
         for div in self.document.getiterator('div'):
             if div.attrib.get('id', '') == 'title':
-                title = unicode(div.text.strip())
+                title = unicode(unescape(div.text.strip()))
             elif div.attrib.get('class', '') == 'download':
                 for link in self.parser.select(div, 'a'):
                     href = link.attrib.get('href', '')
-- 
GitLab