__license__   = 'GPL v3'
__copyright__ = '2012, Darko Miletic <darko.miletic at gmail.com>'
'''
www.telam.com.ar
'''

from calibre.web.feeds.news import BasicNewsRecipe

class Telam(BasicNewsRecipe):
    title                 = 'Telam'
    __author__            = 'Darko Miletic'
    description           = 'AGENCIA DE NOTICIAS DE LA REPUBLICA ARGENTINA'
    publisher             = 'Telam S.E.'
    category              = 'news, politics, Argentina'
    oldest_article        = 2
    max_articles_per_feed = 200
    no_stylesheets        = True
    encoding              = 'utf8'
    use_embedded_content  = False
    language              = 'es_AR'
    remove_empty_feeds    = True
    publication_type      = 'newsportal'
    masthead_url          = 'http://www.telam.com.ar/front/imagenes/encabezado/logotelam.jpg'
    extra_css             = """
                               body{font-family: Arial,Helvetica,sans-serif }
                               img{margin-bottom: 0.4em; display:block}
                            """

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

    remove_tags        = [dict(name=['meta','link'])]
    remove_tags_before = dict(attrs={'class':'nota_fecha'})
    remove_tags_after  = dict(attrs={'class':'nota_completa'})
    remove_attributes  = ['lang']


    feeds = [
              (u'Ultimas noticias', u'http://www.telam.com.ar/xml/rss/' )
             ,(u'Politica'        , u'http://www.telam.com.ar/xml/rss/1')
             ,(u'Economia'        , u'http://www.telam.com.ar/xml/rss/2')
             ,(u'Sociedad'        , u'http://www.telam.com.ar/xml/rss/3')
             ,(u'Policiales'      , u'http://www.telam.com.ar/xml/rss/4')
             ,(u'Internacionales' , u'http://www.telam.com.ar/xml/rss/6')
             ,(u'Espectaculos'    , u'http://www.telam.com.ar/xml/rss/7')
             ,(u'Cultura'         , u'http://www.telam.com.ar/xml/rss/8')
             ,(u'Deportes'        , u'http://www.telam.com.ar/xml/rss/9')
             ,(u'Telam Investiga' , u'http://www.telam.com.ar/xml/rss/5')
            ]

    def print_version(self, url):
        artid = url.rpartition('/')[2]
        return 'http://www.telam.com.ar/?codProg=imprimir-nota&id=' + artid

    def preprocess_html(self, soup):
        for item in soup.findAll(style=True):
            del item['style']
        return soup