Update taz.de (RSS)

recipes/taz_rss.recipe

@@ -1,3 +1,4 @@
+
 __license__ = 'GPL v3'
 __copyright__ = '2013, Alexander Schremmer <alex@alexanderweb.de>, Robert Riemann <robert@riemann.cc>'
 
@@ -6,10 +7,15 @@ from calibre.web.feeds.news import BasicNewsRecipe
 
 class TazRSSRecipe(BasicNewsRecipe):
     title = u'Taz - die Tageszeitung'
-    description = u'Taz.de - die tageszeitung'
+    description = u'Taz.de - die tageszeitung (Anpassung von Robert)'
     __author__ = 'Alexander Schremmer, Robert Riemann'
     language = 'de'
     lang = 'de-DE'
+    category = 'news, Germany'
+    timefmt = ' [%a, %d %b %Y]'
+    publication_type = 'newspaper'
+    remove_empty_feeds = True
+    use_embedded_content = False
     oldest_article = 7
     max_articles_per_feed = 100
     publisher = 'taz Entwicklungs GmbH & Co. Medien KG'
@@ -31,6 +37,12 @@ class TazRSSRecipe(BasicNewsRecipe):
             (u'Berlin', u'http://www.taz.de/Berlin/!p14;rss/'),
             (u'Nord', u'http://www.taz.de/Nord/!p11;rss/')
             ]
+    # omit articles already linked in Schlagzeilen feed
+    ignore_duplicate_articles = {'title', 'url'}
+
+    # use the cover presented on the homepage
+    cover_url = 'http://www.taz.de/digitaz/.s1jpeg320'
+
     keep_only_tags = [dict(name='div', attrs={'class': 'sect sect_article'})]
     remove_tags = [
                   dict(name=['div'], attrs={'class': 'artikelwerbung'}),
@@ -41,3 +53,10 @@ class TazRSSRecipe(BasicNewsRecipe):
                   dict(name=['div'], attrs={'class': re.compile(r".*\bsect_seealso\b.*")}),
                   dict(name=['div'], attrs={'class': 'sectfoot'})
                   ]
+
+# with article pictures on Kindle super-slow
+#    def populate_article_metadata(self, article, soup, first):
+#        if first and hasattr(self, 'add_toc_thumbnail'):
+#            picdiv = soup.find('img')
+#            if picdiv is not None:
+#                self.add_toc_thumbnail(article,picdiv['src'])