Update The Sun

recipes/the_sun.recipe

@@ -1,49 +1,57 @@
 import re
-from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.web.feeds.recipes import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import Tag
 
-class AdvancedUserRecipe1268409464(BasicNewsRecipe):
+class AdvancedUserRecipe1325006965(BasicNewsRecipe):
-    title = u'The Sun'
+
-    __author__ = 'Chaz Ralph'
+    title          = u'The Sun UK'
-    description = 'News from The Sun'
+    cover_url = 'http://www.thesun.co.uk/img/global/new-masthead-logo.png'
+
+    description = 'A Recipe for The Sun tabloid UK - uses feed43'
+    __author__ = 'Dave Asbury'
+    # last updated 20/2/12
+    language = 'en_GB'
     oldest_article = 1
-    max_articles_per_feed = 100
+    max_articles_per_feed = 15
-    language = 'en'
+    remove_empty_feeds = True
     no_stylesheets = True
-    extra_css = '.headline {font-size: x-large;} \n .fact { padding-top: 10pt }'
+
-    encoding= 'iso-8859-1'
+    masthead_url = 'http://www.thesun.co.uk/sol/img/global/Sun-logo.gif'
-    remove_javascript = True
+    encoding = 'cp1251'
+
+    encoding = 'cp1252'
+    remove_empty_feeds = True
+    remove_javascript     = True
+    no_stylesheets = True
+
+    extra_css  = '''
+    body{ text-align: justify; font-family:Arial,Helvetica,sans-serif; font-size:11px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:normal;}
+                     '''
+
+    preprocess_regexps = [
+        (re.compile(r'<div class="foot-copyright".*?</div>', re.IGNORECASE | re.DOTALL), lambda match: '')]
 
     keep_only_tags = [
-            dict(id='column-print')
+                               dict(name='h1'),dict(name='h2',attrs={'class' : 'medium centered'}),
+               dict(name='div',attrs={'class' : 'text-center'}),
+               dict(name='div',attrs={'id' : 'bodyText'})
+               # dict(name='p')
+               ]
+
+    remove_tags=[
+           #dict(name='head'),
+           dict(attrs={'class' : ['mystery-meat-link','ltbx-container','ltbx-var ltbx-hbxpn','ltbx-var ltbx-nav-loop','ltbx-var ltbx-url']}),
+                           dict(name='div',attrs={'class' : 'cf'}),
+           dict(attrs={'title' : 'download flash'}),
+                           dict(attrs={'style' : 'padding: 5px'})
+
+           ]
+
+    feeds          = [
+        (u'News','http://feed43.com/2517447382644748.xml'),
+        (u'Sport', u'http://feed43.com/4283846255668687.xml'),
+        (u'Bizarre', u'http://feed43.com/0233840304242011.xml'),
+        (u'Film',u'http://feed43.com/1307545221226200.xml'),
+        (u'Music',u'http://feed43.com/1701513435064132.xml'),
+        (u'Sun Woman',u'http://feed43.com/0022626854226453.xml'),
     ]
 
-    remove_tags = [
-        dict(name='div', attrs={'class':[
-            'clear text-center small padding-left-right-5 text-999 padding-top-5 padding-bottom-10 grey-solid-line',
-            'clear width-625 bg-fff padding-top-10'
-            ]}),
-        dict(name='video'),
-    ]
-
-    def preprocess_html(self, soup):
-        h1 = soup.find('h1')
-        if h1 is not None:
-            text = self.tag_to_string(h1)
-            nh = Tag(soup, 'h1')
-            nh.insert(0, text)
-            h1.replaceWith(nh)
-
-        return soup
-
-
-    feeds = [(u'News', u'http://www.thesun.co.uk/sol/homepage/feeds/rss/article312900.ece')
-,(u'Sport', u'http://www.thesun.co.uk/sol/homepage/feeds/rss/article247732.ece')
-,(u'Football', u'http://www.thesun.co.uk/sol/homepage/feeds/rss/article247739.ece')
-,(u'Gizmo', u'http://www.thesun.co.uk/sol/homepage/feeds/rss/article247829.ece')
-,(u'Bizarre', u'http://www.thesun.co.uk/sol/homepage/feeds/rss/article247767.ece')]
-
-    def print_version(self, url):
-        return re.sub(r'\?OTC-RSS&ATTR=[-a-zA-Z]+', '?print=yes', url)
-
-