Update Corriere della Serra

recipes/corriere_della_sera_it.recipe

@@ -1,89 +1,44 @@
-#!/usr/bin/env  python2
+#!/usr/bin/env python2
-__license__ = 'GPL v3'
+# vim:fileencoding=utf-8
-__author__ = 'Lorenzo Vigentini, based on Darko Miletic'
+from __future__ import unicode_literals, division, absolute_import, print_function
-__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>, Lorenzo Vigentini <l.vigentini at gmail.com>'
-__version__ = 'v1.01'
-__date__ = '10, January 2010'
-__description__ = 'Italian daily newspaper'
-
-'''
-http://www.corriere.it/
-'''
-import time
 from calibre.web.feeds.news import BasicNewsRecipe
 
+__author__ = 'Ruben Scopacasa'
+__license__ = 'GPL v3'
+__copyright__ = '2019, Ruben Scopacasa <ruben.scopacasa at gmail.com>'
+__version__ = 'v1.00'
+__date__ = '22, April 2019'
 
-class ilCorriere(BasicNewsRecipe):
-    __author__ = 'Lorenzo Vigentini, based on Darko Miletic, Gabriele Marini'
-    description = 'Italian daily newspaper'
-
-# cover_url      =
-# 'http://images.corriereobjects.it/images/static/common/logo_home.gif?v=200709121520
 
+class CorriereDellaSeraRecipe(BasicNewsRecipe):
     title = u'Il Corriere della sera'
     publisher = 'RCS Digital'
     category = 'News, politics, culture, economy, general interest'
 
-    encoding = 'cp1252'
     language = 'it'
     timefmt = '[%a, %d %b, %Y]'
 
-    oldest_article = 10
+    oldest_article = 3
     max_articles_per_feed = 100
-    use_embedded_content = False
+    simultaneous_downloads = 5
-    recursion = 10
 
-    remove_javascript = True
     no_stylesheets = True
-
+    remove_tags_before = dict(name='h1')
-    html2lrf_options = [
+    remove_tags = [dict(id='gallery')]
-        '--comment', description, '--category', category, '--publisher', publisher, '--ignore-tables'
+    ignore_duplicate_articles = {'title', 'url'}
-    ]
-
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + \
-        description + '"\ntags="' + category + '"\nlinearize_tables=True'
-
-    keep_only_tags = [
-        dict(name='div', attrs={'class': ['news-dettaglio article', 'article']})]
-
-    remove_tags = [
-        dict(name=['base', 'object', 'link', 'embed']),
-        dict(name='div', attrs={'class': 'news-goback'}),
-        dict(name='ul', attrs={'class': 'toolbar'})
-    ]
-
-    remove_tags_after = dict(name='p', attrs={'class': 'footnotes'})
-
-    def get_cover_url(self):
-        cover = None
-        st = time.localtime()
-        year = str(st.tm_year)
-        month = "%.2d" % st.tm_mon
-        day = "%.2d" % st.tm_mday
-        # http://images.corriere.it/primapagina/storico/2010_05_17/images/prima_pagina_grande.png
-        cover = 'http://images.corriere.it/primapagina/storico/' + year + \
-            '_' + month + '_' + day + '/images/prima_pagina_grande.png'
-        br = BasicNewsRecipe.get_browser(self)
-        try:
-            br.open(cover)
-        except:
-            self.log("\nCover unavailable")
-            cover = 'http://images.corriereobjects.it/images/static/common/logo_home.gif?v=200709121520'
-        return cover
 
     feeds = [
-        (u'Ultimora',  u'http://www.corriere.it/rss/ultimora.xml'),
+        ('Homepage', 'http://xml2.corriereobjects.it/rss/homepage.xml'),
-        (u'Editoriali',  u'http://www.corriere.it/rss/editoriali.xml'),
+        ('Editoriali', 'http://xml2.corriereobjects.it/rss/editoriali.xml'),
-        (u'Cronache',  u'http://www.corriere.it/rss/cronache.xml'),
+        ('Cronache', 'http://xml2.corriereobjects.it/rss/cronache.xml'),
-        (u'Politica',  u'http://www.corriere.it/rss/politica.xml'),
+        ('Politica', 'http://xml2.corriereobjects.it/rss/politica.xml'),
-        (u'Esteri',  u'http://www.corriere.it/rss/esteri.xml'),
+        ('Esteri', 'http://xml2.corriereobjects.it/rss/esteri.xml'),
-        (u'Economia',  u'http://www.corriere.it/rss/economia.xml'),
+        ('Economia', 'http://xml2.corriereobjects.it/rss/economia.xml'),
-        (u'Cultura',  u'http://www.corriere.it/rss/cultura.xml'),
+        ('Cultura', 'http://xml2.corriereobjects.it/rss/cultura.xml'),
-        (u'Scienze',  u'http://www.corriere.it/rss/scienze.xml'),
-        (u'Salute',  u'http://www.corriere.it/rss/salute.xml'),
-        (u'Spettacolo',  u'http://www.corriere.it/rss/spettacoli.xml'),
-        (u'Cinema e TV',  u'http://www.corriere.it/rss/cinema.xml'),
-        (u'Sport',  u'http://www.corriere.it/rss/sport.xml'),
-        (u'Roma',   u'http://www.corriere.it/rss/homepage_roma.xml'),
-        (u'Milano', u'http://www.corriere.it/rss/homepage_milano.xml')
     ]
+
+    def print_version(self, url):
+        return url.replace('.shtml', '_print.html')
+
+    def get_cover_url(self):
+        return 'http://www.corriere.it/rss/images/logo_small.gif'