use id2url closes #480

weboob/backends/minutes20/backend.py

@@ -14,7 +14,7 @@
 # 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.
-
+"backend for http://20minutes.fr"
 
 # python2.5 compatibility
 from __future__ import with_statement
@@ -24,11 +24,13 @@ from weboob.tools.backend import BaseBackend
 
 from .browser import Newspaper20minutesBrowser
 from weboob.tools.newsfeed import Newsfeed
-
+from .tools import url2id
 
 __all__ = ['Newspaper20minutesBackend']
 
 
+
+
 class Newspaper20minutesBackend(BaseBackend, ICapMessages):
     NAME = 'minutes20'
     MAINTAINER = 'Julien Hebert'
@@ -40,18 +42,18 @@ class Newspaper20minutesBackend(BaseBackend, ICapMessages):
     #                    Value('password',   label='Password', masked=True))
     BROWSER = Newspaper20minutesBrowser
 
-    def get_thread(self, id):
+    def get_thread(self, _id):
-        if isinstance(id, Thread):
+        if isinstance(_id, Thread):
-            thread = id
+            thread = _id
-            id = thread.id
+            _id = thread.id
         else:
             thread = None
 
         with self.browser:
-            content = self.browser.get_content(id)
+            content = self.browser.get_content(_id)
 
         if not thread:
-            thread = Thread(id)
+            thread = Thread(_id)
 
 
         flags = Message.IS_HTML
@@ -75,7 +77,8 @@ class Newspaper20minutesBackend(BaseBackend, ICapMessages):
         return thread
 
     def iter_threads(self):
-        for article in Newsfeed('http://www.20minutes.fr/rss/20minutes.xml').iter_entries():
+        for article in Newsfeed('http://www.20minutes.fr/rss/20minutes.xml', 
+            url2id).iter_entries():
             thread = Thread(article.id)
             thread.title =  article.title
             thread.date = article.datetime

weboob/backends/minutes20/browser.py

@@ -18,10 +18,9 @@
 from .pages.article import ArticlePage
 from .pages.minutes20 import Minutes20Page
 from weboob.tools.browser import BaseBrowser
-
+from .tools import id2url
 __all__ = ['Newspaper20minutesBrowser']
 
-
 class Newspaper20minutesBrowser(BaseBrowser):
     PAGES = {
              'http://www.20minutes.fr/article/?.*': ArticlePage,
@@ -33,6 +32,6 @@ class Newspaper20minutesBrowser(BaseBrowser):
     def is_logged(self):
         return False
 
-    def get_content(self, url):
+    def get_content(self, _id):
-        self.location(url)
+        self.location(id2url(_id))
         return self.page.article

weboob/backends/minutes20/pages/minutes20.py

@@ -14,26 +14,28 @@
 # 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.browser import BasePage
 from weboob.tools.parsers.lxmlparser import select, SelectElementException
-
+from weboob.backends.minutes20.tools import url2id
 __all__ = ['Minutes20Page', 'Article', 'NoAuthorElement']
 
 class NoAuthorElement(Exception):
     pass
 
 class Article(object):
-    def __init__(self):
+    def __init__(self, browser, _id):
+        self.browser = browser
+        self.id = _id
         self.title = u''
         self.body = u''
+        self.url = u''
         self.author = None 
         self.date = None
 
 class Minutes20Page(BasePage):
     main_div = NotImplementedError
     element_body = NotImplementedError
-    article = Article()
+    article = Article
     
     def set_author(self):
         self.article.author = self.get_element_author().text_content().strip()
@@ -45,13 +47,16 @@ class Minutes20Page(BasePage):
             raise NoAuthorElement()
 
     def set_body(self):
-        self.article.body = self.browser.parser.tostring(select(self.main_div, "div.mna-body", 1))
+        self.article.body = self.browser.parser.tostring(select(self.main_div, 
+                                                                "div.mna-body", 
+                                                                1))
 
 
     def on_loaded(self):
-        self.article = Article()
+        self.article = Article(self.browser, url2id(self.url) )
         self.main_div = self.document.getroot()
         self.article.title = select(self.main_div, "h1", 1).text_content()
+        self.article.url = self.url
         try :
             self.set_author()
         except NoAuthorElement:

weboob/backends/minutes20/tools.py

@@ -0,0 +1,29 @@
+# -*- 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.
+
+
+import re
+def id2url(_id):
+    regexp2 = re.compile("(\w+).(\w+).(.*$)")
+    match = regexp2.match(_id)
+    return 'http://www.20minutes.fr/%s/%s/%s' % (   match.group(1), 
+                                                    match.group(2), 
+                                                    match.group(3))
+def url2id(url):
+    regexp = re.compile("http://www.20minutes.fr/(\w+)/([0-9]+)/(.*$)")
+    match = regexp.match(url)
+    return '%s.%d.%s' % (match.group(1), int(match.group(2)), match.group(3))