20_minutos.recipe

__license__ = 'GPL v3'
__author__ = 'Luis Hernandez'
__copyright__ = 'Luis Hernandez<tolyluis@gmail.com>'
__version__ = 'v0.85'
__date__ = '31 January 2011'

'''
www.20minutos.es
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe


class AdvancedUserRecipe1294946868(BasicNewsRecipe):

    title = u'20 Minutos new'
    publisher = u'Grupo 20 Minutos'

    __author__ = 'Luis Hernandez'
    description = 'Free spanish newspaper'
    cover_url = 'http://estaticos.20minutos.es/mmedia/especiales/corporativo/css/img/logotipos_grupo20minutos.gif'

    oldest_article = 2
    max_articles_per_feed = 100

    remove_javascript = True
    no_stylesheets = True
    use_embedded_content = False

    encoding = 'ISO-8859-1'
    language = 'es'
    timefmt = '[%a, %d %b, %Y]'
    remove_empty_feeds = True

    keep_only_tags = [
        dict(name='div', attrs={'id': ['content', 'vinetas', ]}), dict(name='div', attrs={'class': ['boxed', 'description', 'lead', 'article-content', 'cuerpo estirar']}), dict(name='span', attrs={'class': ['photo-bar']}), dict(name='ul', attrs={'class': ['article-author']})  # noqa
    ]

    remove_tags_before = dict(name='ul', attrs={'class': ['servicios-sub']})
    remove_tags_after = dict(
        name='div', attrs={'class': ['related-news', 'col']})

    remove_tags = [
        dict(name='ol', attrs={'class': ['navigation', ]}), dict(name='span', attrs={'class': ['action']}), dict(name='div', attrs={'class': ['twitter comments-list hidden', 'related-news', 'col', 'photo-gallery', 'photo-gallery side-art-block', 'calendario', 'article-comment', 'postto estirar', 'otras_vinetas estirar', 'kment', 'user-actions']}), dict( name='div', attrs={'id': ['twitter-destacados', 'eco-tabs', 'inner', 'vineta_calendario', 'vinetistas clearfix', 'otras_vinetas estirar', 'MIN1', 'main', 'SUP1', 'INT']}), dict(name='ul', attrs={'class': ['article-user-actions', 'stripped-list']}), dict(name='ul', attrs={'id': ['site-links']}), dict(name='li', attrs={'class': ['puntuacion', 'enviar', 'compartir']})  # noqa
    ]

    extra_css             = """
                               p{text-align: justify; font-size: 100%}
                               body{ text-align: left; font-size:100% }
                               h3{font-family: sans-serif; font-size:150%; font-weight:bold; text-align: justify; }
                                 """

    preprocess_regexps = [(re.compile(
        r'<a href="http://estaticos.*?[0-999]px;" target="_blank">', re.DOTALL), lambda m: '')]

    feeds = [

    (u'Portada', u'http://www.20minutos.es/rss/'),
    (u'Nacional', u'http://www.20minutos.es/rss/nacional/'),
    (u'Internacional', u'http://www.20minutos.es/rss/internacional/'),
    (u'Economia', u'http://www.20minutos.es/rss/economia/'),
    (u'Deportes', u'http://www.20minutos.es/rss/deportes/'),
    (u'Tecnologia', u'http://www.20minutos.es/rss/tecnologia/'),
    (u'Gente - TV', u'http://www.20minutos.es/rss/gente-television/'),
    (u'Motor', u'http://www.20minutos.es/rss/motor/'),
    (u'Salud', u'http://www.20minutos.es/rss/belleza-y-salud/'),
    (u'Viajes', u'http://www.20minutos.es/rss/viajes/'),
    (u'Vivienda', u'http://www.20minutos.es/rss/vivienda/'),
    (u'Empleo', u'http://www.20minutos.es/rss/empleo/'),
    (u'Cine', u'http://www.20minutos.es/rss/cine/'),
    (u'Musica', u'http://www.20minutos.es/rss/musica/'),
    (u'Vinetas', u'http://www.20minutos.es/rss/vinetas/'),
    (u'Comunidad20', u'http://www.20minutos.es/rss/zona20/')
    ]