support repositories to manage backends (closes #747)

modules/lefigaro/__init__.py

@@ -0,0 +1,24 @@
+"NewspaperFigaroBackend init"
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2011  Julien Hebert
+#
+# 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 .backend import NewspaperFigaroBackend
+
+
+__all__ = ['NewspaperFigaroBackend']

modules/lefigaro/backend.py

@@ -0,0 +1,39 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2011  Julien Hebert
+#
+# 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/>.
+"backend for http://www.lefigaro.fr"
+
+from weboob.capabilities.messages import ICapMessages
+from weboob.tools.capabilities.messages.GenericBackend import GenericNewspaperBackend
+from .browser import NewspaperFigaroBrowser
+from .tools import rssid
+
+class NewspaperFigaroBackend(GenericNewspaperBackend, ICapMessages):
+    "NewspaperFigaroBackend class"
+    MAINTAINER = 'Julien Hebert'
+    EMAIL = 'juke@free.fr'
+    VERSION = '0.a'
+    LICENSE = 'AGPLv3+'
+    STORAGE = {'seen': {}}
+    NAME = 'lefigaro'
+    DESCRIPTION = u'Lefigaro French news website'
+    BROWSER = NewspaperFigaroBrowser
+    RSS_FEED = 'http://rss.lefigaro.fr/lefigaro/laune?format=xml'
+    RSSID = rssid
+
+

modules/lefigaro/browser.py

@@ -0,0 +1,55 @@
+"browser for lefigaro website"
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2011  Julien Hebert
+#
+# 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 .pages.article import ArticlePage
+from .pages.flashactu import FlashActuPage
+from .pages.special import SpecialPage
+from weboob.tools.browser import BaseBrowser, BasePage
+
+class IndexPage(BasePage):
+    pass
+
+
+class NewspaperFigaroBrowser(BaseBrowser):
+    "NewspaperFigaroBrowser class"
+    PAGES = {
+             "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):
+        return False
+
+    def login(self):
+        pass
+
+    def fillobj(self, obj, fields):
+        pass
+
+    def get_content(self, _id):
+        "return page article content"
+        self.location(_id)
+        if self.is_on_page(IndexPage):
+            return None
+        return self.page.get_article(_id)

modules/lefigaro/pages/article.py

@@ -0,0 +1,42 @@
+"ArticlePage object for inrocks"
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2011  Julien Hebert
+#
+# 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, remove_from_selector_list, drop_comments, try_drop_tree, try_remove_from_selector_list
+
+class ArticlePage(GenericNewsPage):
+    "ArticlePage object for inrocks"
+    def on_loaded(self):
+        self.main_div = self.document.getroot()
+        self.element_title_selector = "h1"
+        self.element_author_selector    = "div.name>span"
+        self.element_body_selector      = "#article"
+
+    def get_body(self):
+        element_body = self.get_element_body()
+        remove_from_selector_list(self.parser, element_body, [self.element_title_selector])
+        drop_comments(element_body)
+        try_drop_tree(self.parser, element_body, "script")
+
+        try_remove_from_selector_list(self.parser, element_body, ["div.infos", "div.photo", "div.art_bandeau_bottom", "div.view", "span.auteur_long", "#toolsbar", 'link'])
+
+        element_body.find_class("texte")[0].drop_tag()
+        element_body.tag = "div"
+        return self.parser.tostring(element_body)
+

modules/lefigaro/pages/flashactu.py

@@ -0,0 +1,35 @@
+"ArticlePage object for inrocks"
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2011  Julien Hebert
+#
+# 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
+
+class FlashActuPage(GenericNewsPage):
+    "ArticlePage object for inrocks"
+    def on_loaded(self):
+        self.main_div = self.document.getroot()
+        self.element_title_selector = "h1"
+        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.parser.tostring(element_body)
+

modules/lefigaro/pages/simple.py

@@ -0,0 +1,29 @@
+"ArticlePage object for minutes20"
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2011  Julien Hebert
+#
+# 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
+
+class SimplePage(GenericNewsPage):
+    "ArticlePage object for minutes20"
+    def on_loaded(self):
+        self.main_div = self.document.getroot()
+        self.element_author_selector = "div.mna-signature"
+        self.element_body_selector = "#article"
+

modules/lefigaro/pages/special.py

@@ -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)
+

modules/lefigaro/test.py

@@ -0,0 +1,32 @@
+# -*- 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.test import BackendTest
+
+
+__all__ = ['LeFigaroTest']
+
+
+class LeFigaroTest(BackendTest):
+    BACKEND = 'lefigaro'
+
+    def test_new_messages(self):
+        for message in self.backend.iter_unread_messages():
+            pass

modules/lefigaro/tools.py

@@ -0,0 +1,39 @@
+"tools for lefigaro backend"
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2011  Julien Hebert
+#
+# 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/>.
+
+
+import re
+def id2url(_id):
+    "return an url from an id"
+    regexp2 = re.compile("(\w+).([0-9]+).(.*$)")
+    match = regexp2.match(_id)
+    if match:
+        return 'http://www.20minutes.fr/%s/%s/%s' % (   match.group(1),
+                                                        match.group(2),
+                                                        match.group(3))
+    else:
+        raise ValueError("id doesn't match")
+
+def url2id(url):
+    "return an id from an url"
+    return url
+
+def rssid(entry):
+    return url2id(entry.id)