RevistaBla.recipe

#!/usr/bin/env  python

__license__   = 'GPL v3'
__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
'''
http://www.revistabla.com
'''

from calibre.web.feeds.news import BasicNewsRecipe

class Noticias(BasicNewsRecipe):
    title                 = 'Revista Bla'
    __author__            = 'Gustavo Azambuja'
    description           = 'Moda | Uruguay'
    language       = 'es'
    timefmt        = '[%a, %d %b, %Y]'
    use_embedded_content  = False
    recursion             = 5
    encoding = 'utf8'
    remove_javascript = True
    no_stylesheets = True

    oldest_article        = 20
    max_articles_per_feed = 100
    keep_only_tags = [dict(id=['body_container'])]
    remove_tags = [
				 dict(name='div', attrs={'class':['date_text', 'comments', 'form_section', 'share_it']}),
				 dict(name='div', attrs={'id':['relatedPosts', 'spacer', 'banner_izquierda', 'right_container']}),
				 dict(name='p', attrs={'class':'FacebookLikeButton'}),
				 dict(name=['object','link']) ]

    extra_css = '''
                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#000000;}
                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
                p {font-family:Arial,Helvetica,sans-serif;}
                '''
    feeds = [
           (u'Articulos', u'http://www.revistabla.com/feed/')
        ]

    def get_cover_url(self):
	cover_url = None
	index = 'http://www.revistabla.com'
	soup = self.index_to_soup(index)
	link_item = soup.find('div',attrs={'class':'header_right'})
	if link_item:
		cover_url = link_item.img['src']
	return cover_url

    def preprocess_html(self, soup):
        for item in soup.findAll(style=True):
            del item['style']
        return soup