try to move to ICapMessages

weboob/applications/cleanboob/cleanboob.py

@@ -18,7 +18,7 @@
 
 import sys
 
-from weboob.capabilities.content import ICapContent
+from weboob.capabilities.messages import ICapMessages, Message
 from weboob.tools.application.repl import ReplApplication
 
 
@@ -30,9 +30,9 @@ class CleanBoob(ReplApplication):
     VERSION = '0.1'
     COPYRIGHT = 'Copyright(C) 2011-2012 Julien Hébert'
     DESCRIPTION = "CleanBoob is a console application to extract article from website."
-    CAPS = ICapContent
+    CAPS = ICapMessages
 
     def main(self, argv):
-        for backend, content in self.do('get_content', argv[1]):
+        for backend, content in self.do('get_thread', argv[1]):
             self.format(content)
         return 0

weboob/backends/minutes20/backend.py

@@ -19,7 +19,7 @@
 # python2.5 compatibility
 from __future__ import with_statement
 
-from weboob.capabilities.content import ICapContent, Content
+from weboob.capabilities.messages import ICapMessages, Message, Thread
 from weboob.tools.backend import BaseBackend
 
 from .browser import Newspaper20minutesBrowser
@@ -28,7 +28,7 @@ from .browser import Newspaper20minutesBrowser
 __all__ = ['Newspaper20minutesBackend']
 
 
-class Newspaper20minutesBackend(BaseBackend, ICapContent):
+class Newspaper20minutesBackend(BaseBackend, ICapMessages):
     NAME = 'minutes20'
     MAINTAINER = 'Julien Hebert'
     EMAIL = 'juke@free.fr'
@@ -39,7 +39,7 @@ class Newspaper20minutesBackend(BaseBackend, ICapContent):
     #                    Value('password',   label='Password', masked=True))
     BROWSER = Newspaper20minutesBrowser
 
-    def get_content(self, url):
+    """def get_content(self, url):
         if isinstance(url, basestring):
             content = Content(url)
         else:
@@ -58,3 +58,32 @@ class Newspaper20minutesBackend(BaseBackend, ICapContent):
 
     def push_content(self, content, message = None):
         raise NotImplementedError()
+    """
+
+    def get_thread(self, id):
+        if isinstance(id, Thread):
+            thread = id
+            id = thread.id
+        else:
+            thread = None
+
+        with self.browser:
+            content = self.browser.get_content(id)
+
+        if not thread:
+            thread = Thread(id)
+
+        flags = Message.IS_HTML
+        if not thread.id in self.storage.get('seen', default={}):
+            flags |= Message.IS_UNREAD
+
+
+        thread.title = content.title
+        if not thread.date:
+            thread.date = content.date
+
+        #thread.root = Message(thread=thread, id=0, title=content.title, sender=content.author, receivers=None, date=thread.date, parent=None, content=content.body, signature=None, children = [], flags=flags)
+
+        thread.root = Message(thread=thread, id=0, title=content.title)
+        return thread
+

weboob/backends/minutes20/pages/article.py

@@ -19,9 +19,27 @@
 from weboob.tools.browser import BasePage
 from weboob.tools.parsers.lxmlparser import select
 
+class Article(object):
+    def __init__(self):
+        self.title = u''
+        self.body = u''
+        self.author =None 
+        self.date = None
+
 class ArticlePage(BasePage):
+    def on_loaded(self):
+        self.article = None
+        self.set_article()
+
+    def set_article(self):
+        self.article = Article()
+        #elp(self.get_title().encode('iso8859-1'))
+        self.article.title = self.get_title()
+        self.article.body = self.get_article()
+
+
     def get_title(self):
-        return select(self.document.getroot(), "h1", 1).text_content()
+        return self.browser.parser.tostring(select(self.document.getroot(), "h1", 1))
 
     def get_article(self):
         main_div = self.document.getroot()
@@ -32,6 +50,4 @@ class ArticlePage(BasePage):
         return txt_article.replace(txt_to_remove, '', 1).replace( txt_to_remove2, '', 1)
 
     def get_content(self):
-        title = self.get_title()
+        return self.article
-        content = self.get_article()
-        return [title, content]