Update Gazet van Antwerpen

recipes/gva_be.recipe

@@ -1,12 +1,16 @@
-#!/usr/bin/env  python2
+#!/usr/bin/env python2
+# vim:fileencoding=utf-8
+from __future__ import unicode_literals, division, absolute_import, print_function
 
 __license__   = 'GPL v3'
 __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+
 '''
 www.gva.be
 '''
+
+import re
 from calibre.web.feeds.news import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import Tag
 
 class GazetvanAntwerpen(BasicNewsRecipe):
     title                 = 'Gazet van Antwerpen'
@@ -14,50 +18,45 @@ class GazetvanAntwerpen(BasicNewsRecipe):
     description           = 'News from Belgium in Dutch'
     publisher             = 'Gazet van Antwerpen'
     category              = 'news, politics, Belgium'
+    language              = 'nl_BE'
+
     oldest_article        = 2
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False
-    encoding              = 'utf-8'
+    remove_javascript     = True
-    language = 'nl_BE'
 
-    lang                  = 'nl-BE'
+    masthead_url = 'http://2.gvacdn.be/extra/assets/img/gazet-van-antwerpen-red.svg'
-    direction             = 'ltr'
-
-    html2lrf_options = [
-                          '--comment'  , description
-                        , '--category' , category
-                        , '--publisher', publisher
-                        ]
-
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\noverride_css=" p {text-indent: 0cm; margin-top: 0em; margin-bottom: 0.5em} "'
-
-    keep_only_tags = [dict(name='div', attrs={'id':'article'})]
-    remove_tags    = [
-                         dict(name=['embed','object'])
-                       , dict (name='div',attrs={'class':['note NotePortrait','note']})
-                     ]
-    remove_tags_after  = dict(name='span', attrs={'class':'author'})
 
     feeds = [
-              (u'Binnenland'            , u'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/binnenland'    )
+        ('Stad & Regio', 'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/stadenregio'),
-             ,(u'Buitenland'            , u'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/buitenland'    )
+        ('Economie', 'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/economie'),
-             ,(u'Stad & Regio'          , u'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/stadenregio'   )
+        ('Binnenland', 'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/binnenland'),
-             ,(u'Economie'              , u'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/economie'      )
+        ('Buitenland', 'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/buitenland'),
-             ,(u'Media & Cultur'        , u'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/mediaencultuur')
+        ('Media & Cultuur', 'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/mediaencultuur'),
-             ,(u'Wetenschap'            , u'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/wetenschap'    )
+        ('Sport', 'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/sport')
-             ,(u'Sport'                 , u'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/sport'         )
+    ]
-            ]
+
+    keep_only_tags = [
+        dict(name='header', attrs={'class':'article__header'}),
+        dict(name='footer', attrs={'class':'article__meta'}),
+        dict(name='div', attrs={'class':['article', 'article__body', 'slideshow__intro']}),
+        dict(name='figure', attrs={'class':'article__image'})
+    ]
+
+    remove_tags = [
+        dict(name=['embed', 'object']),
+        dict(name='div', attrs={'class':['note NotePortrait', 'note']}),
+        dict(name='ul', attrs={'class':re.compile('article__share')}),
+        dict(name='div', attrs={'class':'slideshow__controls'}),
+        dict(name='a', attrs={'role':'button'}),
+        dict(name='figure', attrs={'class':re.compile('video')})
+    ]
+
+    remove_attributes = ['width', 'height']
 
     def preprocess_html(self, soup):
         del soup.body['onload']
         for item in soup.findAll(style=True):
             del item['style']
-        soup.html['lang']     = self.lang
-        soup.html['dir' ]     = self.direction
-        mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
-        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
-        soup.head.insert(0,mlang)
-        soup.head.insert(1,mcharset)
         return soup
-