Update Mediapart and rue89

recipes/mediapart.recipe

@@ -1,11 +1,13 @@
 __license__   = 'GPL v3'
-__copyright__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>; 2010, 2011, Louis Gesbert <meta at antislash dot info>'
+__copyright__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>; 2010-2012, Louis Gesbert <meta at antislash dot info>'
 '''
 Mediapart
 '''
 
+__author__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>; 2010-2012, Louis Gesbert <meta at antislash dot info>'
+
 import re
-from calibre.ebooks.BeautifulSoup import BeautifulSoup
+from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Mediapart(BasicNewsRecipe):
@@ -15,8 +17,9 @@ class Mediapart(BasicNewsRecipe):
     oldest_article = 7
     language = 'fr'
     needs_subscription = True
-
     max_articles_per_feed = 50
+
+    use_embedded_content = False
     no_stylesheets = True
 
     cover_url = 'http://static.mediapart.fr/files/pave_mediapart.jpg'
@@ -27,14 +30,9 @@ class Mediapart(BasicNewsRecipe):
 
 # -- print-version
 
-    preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE|re.DOTALL), i[1]) for i in
+    conversion_options = { 'smarten_punctuation' : True }
-        [
-            (r'<div class="print-title">([^>]+)</div>', lambda match : '<h2>'+match.group(1)+'</h2>'),
-            (r'\'', lambda match: '&rsquo;')
-        ]
-    ]
 
-    remove_tags    = [ dict(name='div', attrs={'class':'print-source_url'}) ]
+    remove_tags = [ dict(name='div', attrs={'class':'print-source_url'}) ]
 
     def print_version(self, url):
         raw = self.browser.open(url).read()
@@ -55,3 +53,11 @@ class Mediapart(BasicNewsRecipe):
             br['pass'] = self.password
             br.submit()
         return br
+
+    def preprocess_html(self, soup):
+        for title in soup.findAll('p', {'class':'titre_page'}):
+            title.name = 'h3'
+        for legend in soup.findAll('span', {'class':'legend'}):
+            legend.insert(0, Tag(soup, 'br', []))
+            legend.name = 'small'
+        return soup

recipes/rue89.recipe

@@ -1,10 +1,10 @@
 __license__   = 'GPL v3'
-__copyright__ = '2010, Louis Gesbert <meta at antislash dot info>'
+__copyright__ = '2010-2012, Louis Gesbert <meta at antislash dot info>'
 '''
 Rue89
 '''
 
-__author__ = '2010, Louis Gesbert <meta at antislash dot info>'
+__author__ = '2010-2012, Louis Gesbert <meta at antislash dot info>'
 
 import re
 from calibre.ebooks.BeautifulSoup import Tag
@@ -17,37 +17,45 @@ class Rue89(BasicNewsRecipe):
     title = u'Rue89'
     language = 'fr'
     oldest_article = 7
-    max_articles_per_feed = 50
+    max_articles_per_feed = 12
 
-    feeds = [(u'La Une', u'http://www.rue89.com/homepage/feed')]
+    use_embedded_content = False
+
+    # From http://www.rue89.com/les-flux-rss-de-rue89
+    feeds = [
+        (u'La Une',    u'http://www.rue89.com/feed'),
+        (u'Rue69',     u'http://www.rue89.com/rue69/feed'),
+        (u'Eco',       u'http://www.rue89.com/rue89-eco/feed'),
+        (u'Planète',   u'http://www.rue89.com/rue89-planete/feed'),
+        (u'Sport',     u'http://www.rue89.com/rue89-sport/feed'),
+        (u'Culture',   u'http://www.rue89.com/culture/feed'),
+        (u'Hi-tech',   u'http://www.rue89.com/hi-tech/feed'),
+        (u'Media',     u'http://www.rue89.com/medias/feed'),
+        (u'Monde',     u'http://www.rue89.com/monde/feed'),
+        (u'Politique', u'http://www.rue89.com/politique/feed'),
+        (u'Societe',   u'http://www.rue89.com/societe/feed'),
+    ]
+
+    # Follow redirection from feedsportal.com
+    def get_article_url(self,article):
+        return self.browser.open_novisit(article.link).geturl()
+
+    def print_version(self, url):
+        return url + '?imprimer=1'
 
     no_stylesheets = True
 
-    preprocess_regexps = [
+    conversion_options = { 'smarten_punctuation' : True }
-        (re.compile(r'<(/?)h2>', re.IGNORECASE|re.DOTALL),
-         lambda match : '<'+match.group(1)+'h3>'),
-        (re.compile(r'<div class="print-title">([^>]+)</div>', re.IGNORECASE|re.DOTALL),
-         lambda match : '<h2>'+match.group(1)+'</h2>'),
-        (re.compile(r'<img[^>]+src="[^"]*/numeros/(\d+)[^0-9.">]*.gif"[^>]*/>', re.IGNORECASE|re.DOTALL),
-         lambda match : '<span style="font-family: Sans-serif; color: red; font-size:24pt; padding=2pt;">'+match.group(1)+'</span>'),
-        (re.compile(r'\''), lambda match: '&rsquo;'),
-        ]
 
-    def preprocess_html(self,soup):
+    keep_only_tags = [
-        body = Tag(soup, 'body')
+        dict(name='div', attrs={'id':'article'}),
-        title = soup.find('h1', {'class':'title'})
+    ]
-        content = soup.find('div', {'class':'content'})
-        soup.body.replaceWith(body)
-        body.insert(0, title)
-        body.insert(1, content)
-        return soup
 
-    remove_tags = [ #dict(name='div', attrs={'class':'print-source_url'}),
+    remove_tags_after = [
-                    #dict(name='div', attrs={'class':'print-links'}),
+        dict(name='div', attrs={'id':'plus_loin'}),
-                    #dict(name='img', attrs={'class':'print-logo'}),
+    ]
-                    dict(name='div', attrs={'class':'content_top'}),
-                    dict(name='div', attrs={'id':'sidebar-left'}), ]
 
-# -- print-version has poor quality on this website, better do the conversion ourselves
+    remove_tags = [
-#    def print_version(self, url):
+        dict(name='div', attrs={'id':'article_tools'}),
-#        return re.sub('^.*-([0-9]+)$', 'http://www.rue89.com/print/\\1',url)
+        dict(name='div', attrs={'id':'plus_loin'}),
+    ]