new backend 'fourchan' (implements ICapMessages)

weboob/backends/fourchan/__init__.py

@@ -0,0 +1,2 @@
+from .backend import FourChanBackend
+from .browser import FourChan

weboob/backends/fourchan/backend.py

@@ -0,0 +1,107 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010  Romain Bignon
+#
+# 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.
+
+from logging import warning
+
+from weboob.backend import BaseBackend
+from weboob.capabilities.messages import ICapMessages, Message
+
+from .browser import FourChan
+
+class FourChanBackend(BaseBackend, ICapMessages):
+    NAME = 'fourchan'
+    MAINTAINER = 'Romain Bignon'
+    EMAIL = 'romain@peerfuse.org'
+    VERSION = '1.0'
+    LICENSE = 'GPLv3'
+    DESCRIPTION = "4chan website"
+
+    CONFIG = {'boards':        BaseBackend.ConfigField(description='Boards'),
+             }
+    STORAGE = {'boards': {}}
+    BROWSER = FourChan
+
+    def iter_messages(self, thread=None):
+        return self._iter_messages(thread, False)
+
+    def iter_new_messages(self, thread=None):
+        return self._iter_messages(thread, True)
+
+    def _iter_messages(self, thread, only_new):
+        if thread:
+            if '.' in thread:
+                board, thread = thread.split('.', 2)
+                return self._iter_messages_of(board, thread, only_new)
+            else:
+                warning('"%s" is not a valid ID' % thread)
+        else:
+            for board in self.config['boards'].split(' '):
+                return self._iter_messages_of(board, None, only_new)
+
+    def _iter_messages_of(self, board, thread_wanted, only_new):
+        if not board in self.storage.get('boards', default={}):
+            self.storage.set('boards', board, {})
+
+        if thread_wanted:
+            for message in self._iter_thread_messages(board, thread_wanted, only_new):
+                yield message
+        else:
+            for thread in self.browser.get_threads(board):
+                for message in self._iter_thread_messages(board, thread.id, only_new):
+                    yield message
+
+    def _iter_thread_messages(self, board, thread, only_new):
+        thread = self.browser.get_thread(board, thread)
+
+        if thread.id in self.storage.get('boards', board, default={}):
+            self.storage.set('boards', board, thread.id, [])
+            new = True
+        else:
+            new = False
+
+        if not only_new or new:
+            yield Message('%s.%s' % (board, thread.id),
+                          0,
+                          thread.filename,
+                          thread.author,
+                          thread.datetime,
+                          content=thread.text,
+                          is_html=True,
+                          is_new=new)
+
+        for comment in thread.comments:
+            if not comment.id in self.storage.get('boards', board, thread.id, default=[]):
+                self.storage.set('boards', board, thread.id, self.storage.get('boards', board, thread.id, default=[]) + [comment.id])
+                new = True
+            else:
+                new = False
+
+            if not only_new or new:
+                yield Message('%s.%s' % (board, thread.id),
+                              comment.id,
+                              thread.filename,
+                              comment.author,
+                              comment.datetime,
+                              0,
+                              comment.text,
+                              is_html=True,
+                              is_new=new)
+
+        self.storage.save()
+
+    #def post_reply(self, thread_id, reply_id, title, message):
+    #    return self.browser.post_reply(thread_id, reply_id, title, message)

weboob/backends/fourchan/browser.py

@@ -0,0 +1,41 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010  Romain Bignon
+#
+# 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.
+
+from weboob.tools.browser import BaseBrowser
+
+from .pages.board import BoardPage
+
+class FourChan(BaseBrowser):
+    DOMAIN = 'boards.4chan.org'
+    PROTOCOL = 'http'
+    PAGES = {'http://boards.4chan.org/\w+/': BoardPage,
+             'http://boards.4chan.org/\w+/res/\d+': BoardPage,
+            }
+
+    def is_logged(self):
+        return True
+
+    def get_threads(self, board):
+        self.location('http://boards.4chan.org/%s/' % board)
+
+        return self.page.articles
+
+    def get_thread(self, board, id):
+        self.location('http://boards.4chan.org/%s/res/%d' % (board, id))
+
+        assert len(self.page.articles) == 1
+        return self.page.articles[0]

weboob/backends/fourchan/pages/board.py

@@ -0,0 +1,85 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010  Romain Bignon
+#
+# 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
+from logging import warning
+
+from weboob.tools.browser import BasePage
+
+class Message(object):
+    def __init__(self, browser, board, id, filename=u'', url=u''):
+        self.id = id
+        self.browser = browser
+        self.board = board
+        self.filename = filename
+        self.datetime = 0
+        self.url = url
+        self.author = u''
+        self.text = u''
+        self.comments = []
+
+    def add_comment(self, div):
+        comment = Message(self.browser, self.board, int(div.attrib.get('id', '')))
+        comment.author = div.cssselect('span.commentpostername')[0].text
+        comment.text = self.browser.parser.tostring(div.find('blockquote'))
+        self.comments.append(comment)
+
+    def __repr__(self):
+        return '<Message id=%s filename=%s url=%s comments=%d>' % (self.id, self.filename, self.url, len(self.comments))
+
+class BoardPage(BasePage):
+    URL_REGEXP = re.compile('http://boards.4chan.org/(\w+)/')
+
+    def on_loaded(self):
+        self.articles = []
+
+        m = self.URL_REGEXP.match(self.url)
+        if m:
+            self.board = m.group(1)
+        else:
+            warning('Unable to find board')
+            self.board = 'unknown'
+
+        forms = self.document.getroot().cssselect('form')
+        form = None
+
+        for f in forms:
+            if f.attrib.get('name', '') == 'delform':
+                form = f
+                break
+
+        if form is None:
+            warning('No delform :(')
+
+        article = None
+        for div in form.getchildren():
+            if div.tag == 'span' and div.attrib.get('class', '') == 'filesize':
+                url = div.find('a').get('href', '')
+                filename = 'unknown.jpg'
+                span = div.find('span')
+                if span is not None:
+                    filename = span.text
+                article = Message(self.browser, self.board, 0, filename, url)
+                self.articles.append(article)
+            if div.tag == 'input' and div.attrib.get('type', 'checkbox') and div.attrib.get('value', 'delete'):
+                article.id = int(div.attrib.get('name', '0'))
+            if div.tag == 'blockquote':
+                article.text = self.browser.parser.tostring(div)
+            if div.tag == 'table':
+                tags = div.cssselect('td.reply')
+                if tags:
+                    article.add_comment(tags[0])

weboob/capabilities/messages.py

@@ -73,8 +73,8 @@ class Message:
         return self.id == msg.id and self.thread_id == msg.thread_id
 
     def __repr__(self):
-        result = '<Message id="%s" title="%s" date="%s" from="%s">' % (
-            self.id, self.title, self.date, self.sender)
+        result = '<Message id="%s.%s" title="%s" date="%s" from="%s">' % (
+            self.thread_id, self.id, self.title, self.date, self.sender)
         return result.encode('utf-8')
 
 class ICapMessages(ICap):