From 06eb33ec59533be1e68aac5c012effbe1795c0c9 Mon Sep 17 00:00:00 2001
From: Romain Bignon <romain@symlink.me>
Date: Tue, 25 Oct 2011 13:29:52 +0200
Subject: [PATCH] handle general errors when website is unavailable

---
 weboob/backends/gazelle/pages/base.py     | 34 +++++++++++++++++++++++
 weboob/backends/gazelle/pages/index.py    |  8 ++++--
 weboob/backends/gazelle/pages/torrents.py |  3 +-
 3 files changed, 41 insertions(+), 4 deletions(-)
 create mode 100644 weboob/backends/gazelle/pages/base.py

diff --git a/weboob/backends/gazelle/pages/base.py b/weboob/backends/gazelle/pages/base.py
new file mode 100644
index 00000000..1f236fa6
--- /dev/null
+++ b/weboob/backends/gazelle/pages/base.py
@@ -0,0 +1,34 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2011 Romain Bignon
+#
+# This file is part of weboob.
+#
+# weboob is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# weboob 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 Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with weboob. If not, see <http://www.gnu.org/licenses/>.
+
+
+from weboob.tools.browser import BrowserUnavailable, BasePage as _BasePage
+
+
+__all__ = ['BasePage']
+
+
+class BasePage(_BasePage):
+    def on_loaded(self):
+        errors = []
+        for div in self.parser.select(self.document.getroot(), 'div.poetry'):
+            errors.append(self.parser.tocleanstring(div))
+
+        if len(errors) > 0:
+            raise BrowserUnavailable(', '.join(errors))
diff --git a/weboob/backends/gazelle/pages/index.py b/weboob/backends/gazelle/pages/index.py
index 7eec7063..e59226f8 100644
--- a/weboob/backends/gazelle/pages/index.py
+++ b/weboob/backends/gazelle/pages/index.py
@@ -18,8 +18,8 @@
 # along with weboob. If not, see <http://www.gnu.org/licenses/>.
 
 
-from weboob.tools.browser import BasePage, BrowserIncorrectPassword, BrowserBanned
-from weboob.tools.misc import remove_html_tags
+from weboob.tools.browser import BrowserIncorrectPassword, BrowserBanned
+from .base import BasePage
 
 
 __all__ = ['IndexPage', 'LoginPage']
@@ -32,9 +32,11 @@ class IndexPage(BasePage):
 
 class LoginPage(BasePage):
     def on_loaded(self):
+        BasePage.on_loaded(self)
+
         warns = self.parser.select(self.document.getroot(), 'span.warning')
         for warn in warns:
-            text = remove_html_tags(self.parser.tostring(warn)).strip()
+            text = self.parser.tocleanstring(warn)
             if text.startswith('Your username'):
                 raise BrowserIncorrectPassword(text)
             if text.startswith('You are banned'):
diff --git a/weboob/backends/gazelle/pages/torrents.py b/weboob/backends/gazelle/pages/torrents.py
index 4c79a415..329b5c6d 100644
--- a/weboob/backends/gazelle/pages/torrents.py
+++ b/weboob/backends/gazelle/pages/torrents.py
@@ -23,10 +23,11 @@ import urlparse
 from logging import warning, debug
 
 from weboob.tools.misc import html2text, get_bytes_size
-from weboob.tools.browser import BasePage
 from weboob.capabilities.torrent import Torrent
 from weboob.capabilities.base import NotLoaded
 
+from .base import BasePage
+
 
 __all__ = ['TorrentsPage']