fixe regexp to match differents pages

weboob/backends/lefigaro/browser.py

@@ -16,13 +16,27 @@
 # Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 
 from .pages.article import ArticlePage
+from .pages.flashactu import FlashActuPage
 from weboob.tools.browser import BaseBrowser
 
 
 
 class NewspaperFigaroBrowser(BaseBrowser):
     PAGES = {
-             '.*': ArticlePage,
+             "http://www.lefigaro.fr/flash-actu/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": FlashActuPage,
+             "http://www.lefigaro.fr/flash-sport/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": FlashActuPage,
+             "http://www.lefigaro.fr/politique/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/football-ligue-1-et-2/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/international/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/actualite-france/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/cinema/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/conjoncture/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/automobile/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/actualites/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/matieres-premieres/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/le-talk/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": ArticlePage,
+             "http://www.lefigaro.fr/flash-eco/([0-9][0-9][0-9][0-9])/([0-9][0-9])/([0-9][0-9])/(.*$)": FlashActuPage,
+             #'.*': ArticlePage
             }
 
     def is_logged(self):
@@ -31,4 +45,5 @@ class NewspaperFigaroBrowser(BaseBrowser):
     def get_content(self, _id):
         url = _id
         self.location(url)
+        print self.page
         return self.page.get_article(_id)

weboob/backends/lefigaro/pages/flashactu.py

@@ -0,0 +1,39 @@
+"ArticlePage object for inrocks"
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2011  Julien Hebert
+#
+# 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.parsers.lxmlparser import select, SelectElementException
+from .genericArticle import GenericNewsPage
+
+def try_remove(base_element, selector):
+    try :
+        base_element.remove(select(base_element, selector, 1 ))
+    except (SelectElementException, ValueError):
+        pass
+
+class FlashActuPage(GenericNewsPage):
+    "ArticlePage object for inrocks"
+    def on_loaded(self):
+        self.main_div = self.document.getroot()
+        self.element_author_selector    = "div.name>span"
+        self.element_body_selector      = "h2"
+
+    def get_body(self):
+        element_body = self.get_element_body()
+        element_body.tag = "div"
+        return self.browser.parser.tostring(element_body)
+