support repositories to manage backends (closes #747)

modules/minutes20/__init__.py

@@ -0,0 +1,22 @@
+"init of Newspaper20minutesBackend"
+# -*- 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 Newspaper20minutesBackend
+__all__ = ['Newspaper20minutesBackend']

modules/minutes20/backend.py

@@ -0,0 +1,38 @@
+# -*- 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://20minutes.fr"
+
+from weboob.capabilities.messages import ICapMessages
+from weboob.tools.capabilities.messages.GenericBackend import GenericNewspaperBackend
+from .browser import Newspaper20minutesBrowser
+from .tools import rssid
+
+class Newspaper20minutesBackend(GenericNewspaperBackend, ICapMessages):
+    "Newspaper20minutesBackend class"
+    MAINTAINER = 'Julien Hebert'
+    EMAIL = 'juke@free.fr'
+    VERSION = '0.a'
+    LICENSE = 'AGPLv3+'
+    STORAGE = {'seen': {}}
+    NAME = 'minutes20'
+    DESCRIPTION = u'20minutes French news  website'
+    BROWSER = Newspaper20minutesBrowser
+    RSS_FEED = 'http://www.20minutes.fr/rss/20minutes.xml'
+    RSSID = rssid
+

modules/minutes20/browser.py

@@ -0,0 +1,53 @@
+"browser for 20minutes 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.simple import SimplePage
+from weboob.tools.browser import BaseBrowser
+from .tools import id2url
+
+
+class Newspaper20minutesBrowser(BaseBrowser):
+    "Newspaper20minutesBrowser class"
+    PAGES = {
+             'http://www.20minutes.fr/article/?.*': ArticlePage,
+             'http://www.20minutes.fr/ledirect/?.*': SimplePage,
+             'http://www.20minutes.fr/preums/?.*': SimplePage
+            }
+
+    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"
+        try :
+            url = id2url(_id)
+        except ValueError:
+            url = _id
+        self.location(url)
+
+        if self.page is not None:
+            return self.page.get_article(_id)

modules/minutes20/pages/article.py

@@ -0,0 +1,45 @@
+"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 NoAuthorElement, try_remove, NoneMainDiv
+from .simple import SimplePage
+
+class ArticlePage(SimplePage):
+    "ArticlePage object for minutes20"
+    def on_loaded(self):
+        self.main_div = self.document.getroot()
+        self.element_title_selector = "h1"
+        self.element_author_selector = "div.mna-signature"
+        self.element_body_selector = "div.mna-body"
+
+    def get_body(self):
+        try:
+            element_body = self.get_element_body()
+        except NoneMainDiv:
+            return None
+        else:
+            try_remove(self.parser, element_body, "div.mna-tools")
+            try_remove(self.parser, element_body, "div.mna-comment-call")
+            try :
+                element_body.remove(self.get_element_author())
+            except NoAuthorElement:
+                pass
+            return self.parser.tostring(element_body)
+

modules/minutes20/pages/simple.py

@@ -0,0 +1,30 @@
+"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_title_selector = "h1"
+        self.element_author_selector = "div.mna-signature"
+        self.element_body_selector = "div.mna-body"
+

modules/minutes20/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__ = ['Minutes20Test']
+
+
+class Minutes20Test(BackendTest):
+    BACKEND = 'minutes20'
+
+    def test_new_messages(self):
+        for message in self.backend.iter_unread_messages():
+            pass

modules/minutes20/tools.py

@@ -0,0 +1,41 @@
+"common tools for 20minutes 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]+).(.*$)")
+    match = regexp2.match(_id)
+    if match:
+        return 'http://www.20minutes.fr/%s/%s/%s' % (   match.group(1),
+                                                        match.group(2),
+                                                        match.group(3))
+    else:
+        raise ValueError("id doesn't match")
+
+def url2id(url):
+    "return an id from an url"
+    regexp = re.compile("http://www.20minutes.fr/(\w+)/([0-9]+)/(.*$)")
+    match = regexp.match(url)
+    return '%s.%d.%s' % (match.group(1), int(match.group(2)), match.group(3))
+
+def rssid(entry):
+    return url2id(entry.id)