Bitacora.recipe

#!/usr/bin/env  python

__license__   = 'GPL v3'
__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
'''
bitacora.com.uy
'''

from calibre.web.feeds.news import BasicNewsRecipe

class General(BasicNewsRecipe):
    title                 = 'Bitacora UY'
    __author__            = 'Gustavo Azambuja'
    description           = 'Noticias de Uruguay'
    language       = 'es'
    timefmt        = '[%a, %d %b, %Y]'
    use_embedded_content  = False
    recursion             = 5
    encoding = 'iso-8859-1'
    remove_javascript = True
    no_stylesheets = True

    oldest_article        = 2
    max_articles_per_feed = 100
    keep_only_tags = [dict(id=['txt'])]
    remove_tags = [
             dict(name='div', attrs={'class':'tablafoot'}),
             dict(name=['object','h4']),
             dict(name=['object','link'])
                  ]

    remove_attributes = ['width','height', 'style', 'font', 'color']

    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'Titulares', u'http://www.bitacora.com.uy/anxml.cgi?15')
        ]

    def get_cover_url(self):
	cover_url = None
	index = 'http://www.bitacora.com.uy'
	soup = self.index_to_soup(index)
	link_item = soup.find('img',attrs={'class':'imgtapa'})
	if link_item:
		cover_url = "http://www.bitacora.com.uy/"+link_item['src']
	return cover_url


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