__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
www.que-leer.com
'''

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


class QueLeer(BasicNewsRecipe):
    title = 'Que Leer'
    __author__ = 'Darko Miletic'
    description = 'Libros, Novedades en libros, Criticas, Noticias libro'
    publisher = 'MC Ediciones, S.A.'
    category = 'news, books, criticas, libros'
    oldest_article = 7
    max_articles_per_feed = 200
    no_stylesheets = True
    encoding = 'utf-8'
    use_embedded_content = False
    language = 'es'
    remove_empty_feeds = True
    masthead_url = 'http://www.que-leer.com/wp-content/themes/queleer/images/backgrounds/que-leer.jpg'
    extra_css = ' body{font-family: Arial,sans-serif } img{margin-bottom: 0.4em} '

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

    preprocess_regexps = [(re.compile(
        r'<h2 class="izq">.*?</body>', re.DOTALL | re.IGNORECASE), lambda match: '')]

    remove_tags = [
        dict(attrs={'class': ['post-ratings', 'post-ratings-loading', 'sociable', 'toc-anchor']}
             ), dict(name=['object', 'embed', 'iframe', 'link']), dict(attrs={'id': 'left'})
    ]

    remove_tags_after = dict(attrs={'class': 'sociable'})
    remove_attributes = ['width', 'height']
    keep_only_tags = [dict(attrs={'class': 'post'})]

    feeds = [(u'Articulos', u'http://www.que-leer.com/feed')]

    def preprocess_html(self, soup):
        for item in soup.findAll(style=True):
            del item['style']
        url = 'http://www.que-leer.com/comprar-libros-tienda-que-leer/libros-recomendados'
        fitem = soup.find('a', href=url)
        if fitem:
            par = fitem.parent
            par.extract()
        return self.adeify_images(soup)