From 913d89192e123aa31642a045e7651947c0f30173 Mon Sep 17 00:00:00 2001
From: Romain Bignon <romain@peerfuse.org>
Date: Sat, 3 Apr 2010 18:01:52 +0200
Subject: [PATCH] [dlfp] url2id and id2url functions

---
 weboob/backends/dlfp/feeds.py |  9 +++----
 weboob/backends/dlfp/tools.py | 44 +++++++++++++++++++++++++++++++++++
 2 files changed, 47 insertions(+), 6 deletions(-)
 create mode 100644 weboob/backends/dlfp/tools.py

diff --git a/weboob/backends/dlfp/feeds.py b/weboob/backends/dlfp/feeds.py
index b602e3ba..00123327 100644
--- a/weboob/backends/dlfp/feeds.py
+++ b/weboob/backends/dlfp/feeds.py
@@ -23,6 +23,8 @@ import feedparser
 import re
 from datetime import datetime
 
+from .tools import url2id
+
 class Article:
     RSS = None
 
@@ -56,10 +58,5 @@ class ArticlesList:
             url = klass.RSS
             feed = feedparser.parse(url)
             for item in feed['items']:
-                m = re.match('.*/([0-9]+).html', item['link'])
-                if not m:
-                    warning('Unable to parse ID from link \'%s\'' % item['link'])
-                    continue
-                _id = m.group(1)
-                article = klass(_id, item['link'], item['title'], item['author'], datetime(*item['date_parsed'][:7]))
+                article = klass(url2id(item['link']), item['link'], item['title'], item['author'], datetime(*item['date_parsed'][:7]))
                 yield article
diff --git a/weboob/backends/dlfp/tools.py b/weboob/backends/dlfp/tools.py
new file mode 100644
index 00000000..55fb67e0
--- /dev/null
+++ b/weboob/backends/dlfp/tools.py
@@ -0,0 +1,44 @@
+# -*- 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
+
+ID2URL_NEWSPAPER = re.compile('.*/(\d{4})/(\d{2})/(\d{2})/(\d+)\.html$')
+ID2URL_TELEGRAM  = re.compile('.*/~([A-Za-z0-9_]+)/(\d+)\.html$')
+URL2ID_NEWSPAPER = re.compile('^N(\d{4})(\d{2})(\d{2}).(\d+)$')
+URL2ID_TELEGRAM  = re.compile('^T([A-Za-z0-9_]+).(\d+)$')
+
+def url2id(url):
+    m = ID2URL_NEWSPAPER.match(url)
+    if m:
+        return 'N%04d%02d%02d.%d' % (int(m.group(1)), int(m.group(2)), int(m.group(3)), int(m.group(4)))
+    m = ID2URL_TELEGRAM.match(url)
+    if m:
+        return 'T%s.%d' % (m.group(1), int(m.group(2)))
+    return None
+
+def id2url(_id):
+    m = URL2ID_NEWSPAPER.match(_id)
+    if m:
+        return '/%04d/%02d/%02d/%d.html' % (int(m.group(1)), int(m.group(2)), int(m.group(3)), int(m.group(4)))
+    m = URL2ID_TELEGRAM.match(_id)
+    if m:
+        return '/~%s/%d.html' % (m.group(1), int(m.group(2)))
+    return None