fix broken backend

This commit is contained in:
Romain Bignon 2011-10-25 14:24:08 +02:00
commit 6444ee9146
2 changed files with 42 additions and 4 deletions

View file

@ -20,6 +20,7 @@
from .pages.article import ArticlePage
from .pages.flashactu import FlashActuPage
from .pages.special import SpecialPage
from weboob.tools.browser import BaseBrowser, BasePage
class IndexPage(BasePage):
@ -29,10 +30,12 @@ class IndexPage(BasePage):
class NewspaperFigaroBrowser(BaseBrowser):
"NewspaperFigaroBrowser class"
PAGES = {
"http://www.lefigaro.fr/flash-.*/(\d{4})/(\d{2})/(\d{2})/(.*$)": FlashActuPage,
"http://www.lefigaro.fr/bd/(\d{4})/(\d{2})/(\d{2})/(.*$)": FlashActuPage,
"http://www.lefigaro.fr/(?!flash-|bd).+/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
"http://www.lefigaro.fr/": IndexPage,
"http://\w+.lefigaro.fr/flash-.*/(\d{4})/(\d{2})/(\d{2})/(.*$)": FlashActuPage,
"http://\w+.lefigaro.fr/bd/(\d{4})/(\d{2})/(\d{2})/(.*$)": FlashActuPage,
"http://\w+.lefigaro.fr/actualite/(\d{4})/(\d{2})/(\d{2})/(.*$)": SpecialPage,
"http://\w+.lefigaro.fr/(?!flash-|bd|actualite).+/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
"http://\w+.lefigaro.fr/actualite-.*/(\d{4})/(\d{2})/(\d{2})/(.*$)": ArticlePage,
"http://\w+.lefigaro.fr/": IndexPage,
}
def is_logged(self):

View file

@ -0,0 +1,35 @@
# -*- coding: utf-8 -*-
# Copyright(C) 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.capabilities.messages.genericArticle import GenericNewsPage, try_remove_from_selector_list
class SpecialPage(GenericNewsPage):
"ArticlePage object for inrocks"
def on_loaded(self):
self.main_div = self.document.getroot()
self.element_title_selector = "h2"
self.element_author_selector = "div.name>span"
self.element_body_selector = ".block-text"
def get_body(self):
element_body = self.get_element_body()
try_remove_from_selector_list(self.parser, element_body, ['div'])
element_body.tag = "div"
return self.parser.tostring(element_body)