__license__   = 'GPL v3'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
cubadebate.cu
'''

from calibre.web.feeds.news import BasicNewsRecipe

class CubaDebate(BasicNewsRecipe):
    title                 = 'CubaDebate'
    __author__            = 'Darko Miletic'
    description           = 'Contra el Terorismo Mediatico'
    oldest_article        = 15
    language              = 'es_CU'
    max_articles_per_feed = 100
    no_stylesheets        = True
    use_embedded_content  = False
    publisher             = 'Cubadebate'
    category              = 'news, politics, Cuba'
    encoding              = 'utf-8'
    masthead_url          = 'http://www.cubadebate.cu/wp-content/themes/cubadebate/images/logo.gif'
    publication_type      = 'newsportal'
    extra_css             = """
                               #BlogTitle{font-size: xx-large; font-weight: bold}
                               body{font-family: Verdana, Arial, Tahoma, sans-serif}
                            """

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

    keep_only_tags = [dict(name='div', attrs={'id':'Outline'})]
    remove_tags_after = dict(name='div',attrs={'id':'BlogContent'})
    remove_tags = [
                     dict(name=['link','base','embed','object','meta','iframe'])
                    ,dict(attrs={'id':'addthis_container'})
                  ]

    feeds          = [(u'Articulos', u'http://www.cubadebate.cu/feed/')]
    remove_attributes=['width','height','lang']

    def print_version(self, url):
        return url + 'print/'

    def preprocess_html(self, soup):
        for item in soup.findAll(style=True):
            del item['style']
        for item in soup.findAll('img'):
            if not item.has_key('alt'):
               item['alt'] = 'image'
        return soup