diff --git a/recipes/foxnews.recipe b/recipes/foxnews.recipe index 386a0e17c6..00044ef87e 100644 --- a/recipes/foxnews.recipe +++ b/recipes/foxnews.recipe @@ -35,13 +35,9 @@ class FoxNews(BasicNewsRecipe): remove_attributes = ['xmlns','lang'] - remove_tags=[ - dict(attrs={'class':['user-control','logo','ad-300x250','url-description']}) - ,dict(name=['meta','base','link','iframe','object','embed']) - ] - - keep_only_tags=[dict(attrs={'id':'article-print'})] - remove_tags_after =dict(attrs={'class':'url-description'}) + keep_only_tags = [ + dict(itemprop=['headline', 'articleBody']), + ] feeds = [ (u'Latest Headlines', u'http://feeds.foxnews.com/foxnews/latest' ) @@ -54,26 +50,3 @@ class FoxNews(BasicNewsRecipe): ,(u'Entertainment' , u'http://feeds.foxnews.com/foxnews/entertainment' ) ] - def print_version(self, url): - return url + 'print' - - def preprocess_html(self, soup): - for item in soup.findAll(style=True): - del item['style'] - for item in soup.findAll('a'): - limg = item.find('img') - if item.string is not None: - str = item.string - item.replaceWith(str) - else: - if limg: - item.name = 'div' - item.attrs = [] - else: - str = self.tag_to_string(item) - item.replaceWith(str) - for item in soup.findAll('img'): - if not item.has_key('alt'): - item['alt'] = 'image' - return soup - \ No newline at end of file