Read Clarin on your iPad or Kindle in no time. Click download to load the free ebook on your reader.

Check out all the available public recipes or write your own with these quick start guides. ReadBeam is built on calibre, so everything in the docs and the fora applies here as well.

Download for free »

Noticias de Argentina y mundo

Language: es

Requires Subscription: No, it's available as free ebook

Schedule Every morning

			  
__license__   = 'GPL v3'
__copyright__ = '2008-2011, Darko Miletic <darko.miletic at gmail.com>'
'''
clarin.com
'''

from calibre.web.feeds.news import BasicNewsRecipe

class Clarin(BasicNewsRecipe):
    title                 = 'Clarin'
    __author__            = 'Darko Miletic'
    description           = 'Noticias de Argentina y mundo'
    publisher             = 'Grupo Clarin'
    category              = 'news, politics, Argentina'
    oldest_article        = 2
    max_articles_per_feed = 100
    use_embedded_content  = False
    no_stylesheets        = True
    encoding              = 'utf8'
    delay                 = 1
    language              = 'es_AR'
    publication_type      = 'newspaper'
    INDEX                 = 'http://www.clarin.com'
    masthead_url          = 'http://www.clarin.com/static/CLAClarin/images/logo-clarin-print.jpg'
    extra_css             = """ 
                               body{font-family: Arial,Helvetica,sans-serif} 
                               h2{font-family: Georgia,serif; font-size: xx-large} 
                               .hora{font-weight:bold} 
                               .hd p{font-size: small} 
                               .nombre-autor{color: #0F325A} 
                            """

    conversion_options = {
                          'comment'  : description
                        , 'tags'     : category
                        , 'publisher': publisher
                        , 'language' : language
                        }

    keep_only_tags    = [dict(attrs={'class':['hd','mt']})]
    remove_tags       = [dict(name=['meta','base','link'])]
    remove_attributes = ['lang','_mce_bogus']

    feeds = [
               (u'Pagina principal', u'http://www.clarin.com/rss/'             )
              ,(u'Politica'        , u'http://www.clarin.com/rss/politica/'    )
              ,(u'Deportes'        , u'http://www.clarin.com/rss/deportes/'    )
              ,(u'Economia'        , u'http://www.clarin.com/economia/'        )
              ,(u'Mundo'           , u'http://www.clarin.com/rss/mundo/'       )
              ,(u'Espectaculos'    , u'http://www.clarin.com/rss/espectaculos/')
              ,(u'Sociedad'        , u'http://www.clarin.com/rss/sociedad/'    )
              ,(u'Ciudades'        , u'http://www.clarin.com/rss/ciudades/'    )
              ,(u'Policiales'      , u'http://www.clarin.com/rss/policiales/'  )
              ,(u'Internet'        , u'http://www.clarin.com/rss/internet/'    )
              ,(u'Ciudades'        , u'http://www.clarin.com/rss/ciudades/'    )
            ]

    
    def get_article_url(self, article):
        return article.get('guid',  None)
    
    def print_version(self, url):
        return url + '?print=1'

    def get_cover_url(self):
        cover_url = None
        soup = self.index_to_soup(self.INDEX)
        cover_item = soup.find('div',attrs={'class':'bb-md bb-md-edicion_papel'})
        if cover_item:
           ap = cover_item.find('a',attrs={'href':'/edicion-impresa/'})
           if ap:
              cover_url = self.INDEX + ap.img['src']
        return cover_url