From 32a66a5e2899dffd65b1cda2be4938c22e0711f8 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Sat, 7 Mar 2009 09:30:14 -0800
Subject: [PATCH] New recipe for Mediapart.fr by Mathieu Godlewski

---
 src/calibre/web/feeds/recipes/__init__.py     |  2 +-
 .../web/feeds/recipes/recipe_mediapart.py     | 53 +++++++++++++++++++
 2 files changed, 54 insertions(+), 1 deletion(-)
 create mode 100644 src/calibre/web/feeds/recipes/recipe_mediapart.py

diff --git a/src/calibre/web/feeds/recipes/__init__.py b/src/calibre/web/feeds/recipes/__init__.py
index 6eb24e162b..a513f34728 100644
--- a/src/calibre/web/feeds/recipes/__init__.py
+++ b/src/calibre/web/feeds/recipes/__init__.py
@@ -33,7 +33,7 @@ recipe_modules = ['recipe_' + r for r in (
            'la_republica', 'physics_today', 'chicago_tribune', 'e_novine',
            'al_jazeera', 'winsupersite', 'borba', 'courrierinternational',
            'lamujerdemivida', 'soldiers', 'theonion', 'news_times',
-           'el_universal',
+           'el_universal', 'mediapart',
           )]
 
 import re, imp, inspect, time, os
diff --git a/src/calibre/web/feeds/recipes/recipe_mediapart.py b/src/calibre/web/feeds/recipes/recipe_mediapart.py
new file mode 100644
index 0000000000..60dc893834
--- /dev/null
+++ b/src/calibre/web/feeds/recipes/recipe_mediapart.py
@@ -0,0 +1,53 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>'
+'''
+Mediapart
+'''
+
+import re, string
+from datetime import date
+from calibre.ebooks.BeautifulSoup import BeautifulSoup
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Mediapart(BasicNewsRecipe):
+    title          = 'Mediapart'
+    __author__ = 'Mathieu Godlewski <mathieu at godlewski.fr>'
+    description = 'Global news in french from online newspapers'
+    oldest_article = 7
+    language = _('French')
+    max_articles_per_feed = 50
+    no_stylesheets = True
+
+    html2lrf_options = ['--base-font-size', '10']
+    
+    feeds =  [
+        ('Les articles', 'http://www.mediapart.fr/articles/feed'),
+    ]
+             
+    preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE|re.DOTALL), i[1]) for i in
+        [
+            (r'<div class="print-title">([^>]+)</div>', lambda match : '<h2>'+match.group(1)+'</h2>'),
+            (r'<p>Mediapart\.fr</p>', lambda match : ''),
+            (r'<p[^>]*>[\s]*</p>', lambda match : ''),
+            (r'<p><a href="[^\.]+\.pdf">[^>]*</a></p>', lambda match : ''),
+        ]
+    ]
+    
+    remove_tags    = [ dict(name='div', attrs={'class':'print-source_url'}),
+                                  dict(name='div', attrs={'class':'print-links'}),
+                                  dict(name='img', attrs={'src':'entete_article.png'}),
+    ]
+    
+    
+    def print_version(self, url):
+        raw = self.browser.open(url).read()
+        soup = BeautifulSoup(raw.decode('utf8', 'replace'))
+        div = soup.find('div', {'class':'node node-type-article'})
+        if div is None:
+            return None
+        article_id = string.replace(div['id'], 'node-', '')
+        if article_id is None:
+            return None
+        return 'http://www.mediapart.fr/print/'+article_id