__license__   = 'GPL v3'
__copyright__ = '2009-2011, Darko Miletic <darko.miletic at gmail.com>'
'''
www.diariobae.com
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe

class BsAsEconomico(BasicNewsRecipe):
    title                 = 'Buenos Aires Economico'
    __author__            = 'Darko Miletic'
    description           = 'Diario BAE es el diario economico-politico con mas influencia en la Argentina. Fuente de empresarios y politicos del pais y el exterior. El pozo estaria aportando en periodos breves un volumen equivalente a 800m3 diarios. Pero todavia deben efectuarse otras perforaciones adicionales.'
    publisher             = 'Diario BAE'
    category              = 'news, politics, economy, Argentina'
    oldest_article        = 2
    max_articles_per_feed = 100
    no_stylesheets        = True
    use_embedded_content  = False
    encoding              = 'utf-8'
    language              = 'es_AR'
    cover_url             = strftime('http://www.diariobae.com/imgs_portadas/%Y%m%d_portadasBAE.jpg')
    masthead_url          = 'http://www.diariobae.com/img/logo_bae.png'
    remove_empty_feeds    = True
    publication_type      = 'newspaper'
    extra_css             = """
                               body{font-family: Georgia,"Times New Roman",Times,serif}
                               #titulo{font-size: x-large}
                               #epi{font-size: small; font-style: italic; font-weight: bold}
                               img{display: block; margin-top: 1em}
                            """
    conversion_options = {
                          'comment'   : description
                        , 'tags'      : category
                        , 'publisher' : publisher
                        , 'language'  : language
                        }

    remove_tags_before= dict(attrs={'id':'titulo'})
    remove_tags_after = dict(attrs={'id':'autor' })
    remove_tags       = [
                            dict(name=['meta','base','iframe','link','lang'])
                           ,dict(attrs={'id':'barra_tw'})
                        ]
    remove_attributes = ['data-count','data-via']

    feeds = [
               (u'Argentina'   , u'http://www.diariobae.com/rss/argentina.xml'   )
              ,(u'Valores'     , u'http://www.diariobae.com/rss/valores.xml'     )
              ,(u'Finanzas'    , u'http://www.diariobae.com/rss/finanzas.xml'    )
              ,(u'Negocios'    , u'http://www.diariobae.com/rss/negocios.xml'    )
              ,(u'Mundo'       , u'http://www.diariobae.com/rss/mundo.xml'       )
              ,(u'5 dias'      , u'http://www.diariobae.com/rss/5dias.xml'       )
              ,(u'Espectaculos', u'http://www.diariobae.com/rss/espectaculos.xml')
            ]

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