From 4b10f6705825d10187e68341c2cbd5155069d837 Mon Sep 17 00:00:00 2001
From: juke <juke@jhebert.priv.staff.proxad.net>
Date: Wed, 2 Mar 2011 20:26:29 +0100
Subject: [PATCH] add new categories

---
 weboob/backends/lefigaro/browser.py       | 10 ++++++++++
 weboob/backends/minutes20/pages/simple.py |  2 +-
 weboob/tools/genericArticle.py            | 14 ++++++++++----
 3 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/weboob/backends/lefigaro/browser.py b/weboob/backends/lefigaro/browser.py
index 566a7e9f..ecc7923f 100644
--- a/weboob/backends/lefigaro/browser.py
+++ b/weboob/backends/lefigaro/browser.py
@@ -29,6 +29,8 @@ class NewspaperFigaroBrowser(BaseBrowser):
              "http://www.lefigaro.fr/flash-sport/(\d{4})/(\d{2})/(\d{2})/(.*$)": FlashActuPage,
              "http://www.lefigaro.fr/politique/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
              "http://www.lefigaro.fr/sciences/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/sport/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/sport-business/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
              "http://www.lefigaro.fr/football-ligue-1-et-2/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
              "http://www.lefigaro.fr/international/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
              "http://www.lefigaro.fr/livres/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
@@ -59,6 +61,14 @@ class NewspaperFigaroBrowser(BaseBrowser):
              "http://www.lefigaro.fr/sciences/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
              "http://www.lefigaro.fr/assurance/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
              "http://www.lefigaro.fr/retraite/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/tennis/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/emploi/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/impots/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/culture/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/musique/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/photos/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/formation/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/lefigaromagazine/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
              "http://www.lefigaro.fr/creation-gestion-entreprise/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
              "http://www.lefigaro.fr/flash-eco/(\d{4})/(\d{2})/(\d{2})/(.*$)": FlashActuPage,
             }
diff --git a/weboob/backends/minutes20/pages/simple.py b/weboob/backends/minutes20/pages/simple.py
index 2ba4bc65..43b58cb3 100644
--- a/weboob/backends/minutes20/pages/simple.py
+++ b/weboob/backends/minutes20/pages/simple.py
@@ -25,6 +25,6 @@ class SimplePage(GenericNewsPage):
         self.main_div = self.document.getroot()
         self.element_author_selector = "div.mna-signature"
         self.element_body_selector = "div.mna-body"
-        self.element_title_selector = "div.mn-left>h1"
+        self.element_title_selector = "h1"
 
     
diff --git a/weboob/tools/genericArticle.py b/weboob/tools/genericArticle.py
index 36b42348..ae4ead8b 100644
--- a/weboob/tools/genericArticle.py
+++ b/weboob/tools/genericArticle.py
@@ -27,6 +27,9 @@ def try_remove(base_element, selector):
 class NoAuthorElement(SelectElementException):
     pass
 
+class NoTitleException(SelectElementException):
+    pass
+
 class NoneMainDiv(AttributeError):
     pass
 
@@ -59,10 +62,13 @@ class GenericNewsPage(BasePage):
             return self.__article.author
 
     def get_title(self):
-        return select(
-            self.main_div,
-            self.element_title_selector,
-            1).text_content().strip()
+        try :
+            return select(
+                self.main_div,
+                self.element_title_selector,
+                1).text_content().strip()
+        except SelectElementException:
+            raise NoTitleException("no title on %s" % (self.browser)) 
 
     def get_element_body(self):
         return select(self.main_div, self.element_body_selector, 1)