20minutos.recipe

__license__ = 'GPL v3'
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
'''
www.20minutos.es
'''

from calibre.web.feeds.news import BasicNewsRecipe


class t20Minutos(BasicNewsRecipe):
    title = '20 Minutos'
    __author__ = 'Darko Miletic'
    description = 'Diario de informacion general y local mas leido de Espania, noticias de ultima hora de Espania, el mundo, local, deportes, noticias curiosas y mas'  # noqa
    publisher = '20 Minutos Online SL'
    category = 'news, politics, Spain'
    oldest_article = 2
    max_articles_per_feed = 200
    no_stylesheets = True
    encoding = 'utf8'
    use_embedded_content = True
    language = 'es'
    remove_empty_feeds = True
    publication_type = 'newspaper'
    masthead_url = 'http://estaticos.20minutos.es/css4/img/ui/logo-301x54.png'
    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(attrs={'class': 'mf-viral'})]
    remove_attributes = ['border']

    feeds = [

    (u'Principal', u'http://20minutos.feedsportal.com/c/32489/f/478284/index.rss'),
    (u'Cine', u'http://20minutos.feedsportal.com/c/32489/f/478285/index.rss'),
    (u'Internacional', u'http://20minutos.feedsportal.com/c/32489/f/492689/index.rss'),
    (u'Deportes', u'http://20minutos.feedsportal.com/c/32489/f/478286/index.rss'),
    (u'Nacional', u'http://20minutos.feedsportal.com/c/32489/f/492688/index.rss'),
    (u'Economia', u'http://20minutos.feedsportal.com/c/32489/f/492690/index.rss'),
    (u'Tecnologia', u'http://20minutos.feedsportal.com/c/32489/f/478292/index.rss')
    ]

    def preprocess_html(self, soup):
        for item in soup.findAll(style=True):
            del item['style']
        for item in soup.findAll('a'):
            limg = item.find('img')
            if item.string is not None:
                str = item.string
                item.replaceWith(str)
            else:
                if limg:
                    item.name = 'div'
                    item.attrs = []
                else:
                    str = self.tag_to_string(item)
                    item.replaceWith(str)
        for item in soup.findAll('img'):
            if not item.has_key('alt'):  # noqa
                item['alt'] = 'image'
        return soup