Update The Straits Times

recipes/straitstimes.recipe

@@ -5,10 +5,15 @@ __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
 www.straitstimes.com
 '''
 
-import re
 from calibre.web.feeds.recipes import BasicNewsRecipe
 
 
+def classes(classes):
+    q = frozenset(classes.split(' '))
+    return dict(attrs={
+        'class': lambda x: x and frozenset(x.split()).intersection(q)})
+
+
 class StraitsTimes(BasicNewsRecipe):
     title = 'The Straits Times'
     __author__ = 'Darko Miletic'
@@ -25,23 +30,14 @@ class StraitsTimes(BasicNewsRecipe):
     conversion_options = {
         'comments': description, 'tags': category, 'language': language, 'publisher': publisher
     }
-
+    keep_only_tags = [
-    preprocess_regexps = [
+        classes('node-header node-subheadline group-byline-info group-updated-timestamp group-image-frame field-name-body')
-        (re.compile(
-            r'<meta name="description" content="[^"]+"\s*/?>',
-            re.IGNORECASE | re.DOTALL),
-         lambda m:''),
-        (re.compile(r'<!--.+?-->', re.IGNORECASE | re.DOTALL),
-         lambda m: ''),
     ]
     remove_tags = [
-        dict(name=['object', 'link', 'map', 'style']),
+        classes('st_telegram_boilerplate'),
-        dict(attrs={'class': 'st2014-realted-links'}),
+        dict(name='source'),
     ]
 
-    keep_only_tags = [dict(name='div', attrs={'class': 'story'})]
-    remove_tags_after = dict(name='div', attrs={'class': 'hr_thin'})
-
     feeds = [
               (u'Top of the News' , u'http://www.straitstimes.com/print/top-of-the-news/rss.xml')
               ,(u'World'           , u'http://www.straitstimes.com/print/world/rss.xml')