import re
from calibre.web.feeds.news import BasicNewsRecipe


class PortalR7(BasicNewsRecipe):
    title = 'Noticias R7'
    __author__ = 'Diniz Bortolotto'
    description = 'Noticias Portal R7'
    oldest_article = 2
    max_articles_per_feed = 20
    encoding = 'utf8'
    publisher = 'Rede Record'
    category = 'news, Brazil'
    language = 'pt_BR'
    publication_type = 'newsportal'
    use_embedded_content = False
    no_stylesheets = True
    remove_javascript = True
    remove_attributes = ['style']

    feeds = [
        (u'Brasil', u'http://www.r7.com/data/rss/brasil.xml'),
        (u'Economia', u'http://www.r7.com/data/rss/economia.xml'),
        (u'Internacional',
         u'http://www.r7.com/data/rss/internacional.xml'),
        (u'Tecnologia e Ci\xeancia',
         u'http://www.r7.com/data/rss/tecnologiaCiencia.xml')
    ]
    reverse_article_order = True

    keep_only_tags = [dict(name='div', attrs={'class': 'materia'})]
    remove_tags = [
        dict(id=['espalhe', 'report-erro']),
        dict(name='ul', attrs={'class': 'controles'}),
        dict(name='ul', attrs={'class': 'relacionados'}),
        dict(name='div', attrs={'class': 'materia_banner'}),
        dict(name='div', attrs={'class': 'materia_controles'})
    ]

    preprocess_regexps = [
        (re.compile(r'<div class="materia">.*<div class="materia_cabecalho">', re.DOTALL | re.IGNORECASE),
         lambda match: '<div class="materia"><div class="materia_cabecalho">')
    ]