Recipe for Il Sole 24 Ore

[bosplans]

Fot the italian reader of Il Sole 24 Ore here the working recipe (the one embedded in Calibre is not working anymore!).
You can download the recipe here (http://s.2climb.com/gALJ0B) where you can find the instruction in italian or just copy/paste the code:

__author__    = 'Marco Saraceno'
__copyright__ = '2010, Marco Saraceno <marcosaraceno at gmail.com>'
description   = 'Italian daily newspaper - v 1.1 (Mar14,2011)'

'''
http://www.ilsole24ore.com
'''


class IlSole24Ore(BasicNewsRecipe):
    __author__        = 'Marco Saraceno'
    description   = 'Italian financial daily newspaper'

    cover_url      = 'http://www.shopping24.ilsole24ore.com/ProductRelated/rds/img/logo_sole.gif'
    title          = u'Il Sole 24 Ore'
    publisher      = 'Gruppo editoriale GRUPPO 24ORE'
    category       = 'News, politics, culture, economy, financial, Italian'

    language       = 'it'
    timefmt        = '[%a, %d %b, %Y]'

    oldest_article = 2
    max_articles_per_feed = 100
    use_embedded_content  = False
    extra_css      = '.headline {font-size: x-large;} \n .fact { padding-top: 10pt  }'

         
    remove_tags = [
                            dict(name='div', attrs={'class':['header','titolo']}),
                            dict(name='table', attrs={'class':['footer1024','footerdown']}),
                            ]
                            

    def get_article_url(self, article):
       link = article.get('link', None)
       if link is None:
           return article
       if link.split('/')[-1]=="story01.htm":
           link=link.split('/')[-2]
           a=['0B','0C','0D','0E','0F','0G','0N'  ,'0L0S','0A']
           b=['.' ,'/' ,'?' ,'-' ,'=' ,'&' ,'.com','www.','0']
           for i in range(0,len(a)):
              link=link.replace(a[i],b[i])
           link="http://"+link
       return link

    feeds = [
                  (u'Notizie Italia', u'http://www.ilsole24ore.com/rss/notizie/italia.xml'),
                  (u'Notizie Europa', u'http://www.ilsole24ore.com/rss/notizie/europa.xml'),
                  (u'Notizie USA', u'http://www.ilsole24ore.com/rss/notizie/usa.xml'),
                  (u'Notizie Americhe', u'http://www.ilsole24ore.com/rss/notizie/americhe.xml'),
                  (u'Notizie Medio Oriente e Africa', u'http://www.ilsole24ore.com/rss/notizie/medio-oriente-e-africa.xml'),
                  (u'Notizie Asia e Oceania', u'http://www.ilsole24ore.com/rss/notizie/asia-e-oceania.xml'),
                  (u'Commenti', u'http://www.ilsole24ore.com/rss/commenti-e-idee.xml'),
                  (u'Norme e tributi', u'http://www.ilsole24ore.com/rss/norme-e-tributi.xml'),
                  (u'Finanza', u'http://www.ilsole24ore.com/rss/finanza-e-mercati.xml'),
                  (u'Economia', u'http://www.ilsole24ore.com/rss/economia.xml'),
                  (u'Tecnologia', u'http://www.ilsole24ore.com/rss/tecnologie.xml'),
                  (u'Cultura', u'http://www.ilsole24ore.com/rss/cultura.xml'),
                  ]

    def print_version(self, url):
          return url.replace('.shtml', '_PRN.shtml')