Rusia Hoy by DM

resources/recipes/rusiahoy.recipe

@@ -0,0 +1,47 @@
+__license__   = 'GPL v3'
+__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
+'''
+rusiahoy.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class RusiaHoy(BasicNewsRecipe):
+    title                 = 'Rusia Hoy'
+    __author__            = 'Darko Miletic'
+    description           = 'Noticias de Russia en castellano'
+    publisher             = 'rusiahoy.com'
+    category              = 'news, politics, Russia'
+    oldest_article        = 7
+    max_articles_per_feed = 200
+    no_stylesheets        = True
+    encoding              = 'utf8'
+    use_embedded_content  = False
+    language              = 'es'
+    remove_empty_feeds    = True
+    extra_css             = """ 
+                                body{font-family: Arial,sans-serif }
+                                .article_article_title{font-size: xx-large; font-weight: bold}
+                                .article_date{color: black; font-size: small}
+                            """
+
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    remove_tags = [dict(name=['meta','link','iframe','base','object','embed'])]
+    keep_only_tags=[  dict(attrs={'class':['article_rubric_title','article_date','article_article_title','article_article_lead']})
+                     ,dict(attrs={'class':'article_article_text'})
+                   ]
+    remove_attributes=['align','width','height']
+
+    feeds = [(u'Articulos', u'http://rusiahoy.com/xml/index.xml')]
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
+