Update FOX News

recipes/foxnews.recipe

@@ -1,12 +1,15 @@
-__license__ = 'GPL v3'
-__copyright__ = '2010-2011, Darko Miletic <darko.miletic at gmail.com>'
-'''
-foxnews.com
-'''
-
+#!/usr/bin/env python2
+# vim:fileencoding=utf-8
+from __future__ import unicode_literals, division, absolute_import, print_function
 from calibre.web.feeds.news import BasicNewsRecipe
 
 
+def classes(classes):
+    q = frozenset(classes.split(' '))
+    return dict(
+        attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
+
+
 class FoxNews(BasicNewsRecipe):
     title = 'FOX News'
     __author__ = 'Darko Miletic'
@@ -18,34 +21,36 @@ class FoxNews(BasicNewsRecipe):
     no_stylesheets = True
     encoding = 'utf8'
     use_embedded_content = False
+
     language = 'en'
-    publication_type = 'newsportal'
     remove_empty_feeds = True
-    extra_css             = """
-                                body{font-family: Arial,sans-serif }
-                                .caption{font-size: x-small}
-                                .author,.dateline{font-size: small}
-                            """
+    extra_css = """
+        body{font-family: Arial,sans-serif }
+        .caption{font-size: x-small}
+        .author,.dateline{font-size: small}
+    """
 
     conversion_options = {
-        'comment': description, 'tags': category, 'publisher': publisher, 'language': language
-    }
+        'comment': description,
+        'tags': category,
+        'publisher': publisher,
+        'language': language}
 
     remove_attributes = ['xmlns', 'lang']
-
+    ignore_duplicate_articles = {'title', 'url'}
     keep_only_tags = [
+        dict(itemprop=['headline', 'articleBody']),
         dict(name='h1'),
-        dict(attrs={'class':'article-info article-body'.split()}),
+        classes('byline author date source article-info article-body featured-image'),
     ]
 
-    feeds = [
-
-    (u'Latest Headlines', u'http://feeds.foxnews.com/foxnews/latest'),
-    (u'National', u'http://feeds.foxnews.com/foxnews/national'),
-    (u'World', u'http://feeds.foxnews.com/foxnews/world'),
-    (u'Politics', u'http://feeds.foxnews.com/foxnews/politics'),
-    (u'Business', u'http://feeds.foxnews.com/foxnews/business'),
-    (u'SciTech', u'http://feeds.foxnews.com/foxnews/scitech'),
-    (u'Health', u'http://feeds.foxnews.com/foxnews/health'),
-    (u'Entertainment', u'http://feeds.foxnews.com/foxnews/entertainment')
-    ]
+    feeds = [(u'Latest Headlines', u'http://feeds.foxnews.com/foxnews/latest'),
+             (u'National', u'http://feeds.foxnews.com/foxnews/national'),
+             (u'World', u'http://feeds.foxnews.com/foxnews/world'),
+             (u'Politics', u'http://feeds.foxnews.com/foxnews/politics'),
+             (u'Opinion', u'http://feeds.foxnews.com/foxnews/opinion'),
+             (u'Science', u'http://feeds.foxnews.com/foxnews/science'),
+             (u'Technology', u'http://feeds.foxnews.com/foxnews/tech'),
+             (u'Health', u'http://feeds.foxnews.com/foxnews/health'),
+             (u'Lifestyle', u'http://feeds.foxnews.com/foxnews/section/lifestyle'),
+             (u'Travel', u'http://feeds.foxnews.com/foxnews/internal/travel/mixed')]