Il Sole 24 Ore - proposed changes

[duluoz]

Hi Kovid,

The rss feed addresses are out of date in Il Sole 24 Ore. I have suggested the updated feeds on your Github, but if you prefer also copied them below. In addition, the recipe still fails


Thanks
Jamie

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

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

from calibre.web.feeds.news import BasicNewsRecipe


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          = [
        ('Italia', 'https://www.ilsole24ore.com/rss/italia.xml'),
        ('Mondo', 'https://www.ilsole24ore.com/rss/mondo.xml'),
        ('Economia', 'https://www.ilsole24ore.com/rss/economia.xml'),
        ('Finanzia', 'https://www.ilsole24ore.com/rss/finanza.xml'),
        ('Commenti', 'https://www.ilsole24ore.com/rss/commenti.xml'),
        ('Risparmio', 'https://www.ilsole24ore.com/rss/risparmio.xml'),
        ('Norme e Tributi', 'https://www.ilsole24ore.com/rss/norme-e-tributi.xml'),
        ('Management', 'https://www.ilsole24ore.com/rss/management.xml'),
        ('Cultura', 'https://www.ilsole24ore.com/rss/cultura.xml'),
        ('Tecnologia', 'https://www.ilsole24ore.com/rss/tecnologia.xml'),
        ('Food', 'https://www.ilsole24ore.com/rss/food.xml'),
        ('Moda', 'https://www.ilsole24ore.com/rss/moda.xml'),
        ('Motori', 'https://www.ilsole24ore.com/rss/motori.xml'),
        ('Casa', 'https://www.ilsole24ore.com/rss/casa.xml'),
        ('Viaggi', 'https://www.ilsole24ore.com/rss/viaggi.xml'),
        ('Salute', 'https://www.ilsole24ore.com/rss/salute.xml'),
        ('Arteconomy', 'https://www.ilsole24ore.com/rss/arteconomy.xml'),
        ('Sport', 'https://www.ilsole24ore.com/rss/sport24.xml'),
    ]

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