calibre/recipes/diario_sport.recipe

from calibre.web.feeds.news import BasicNewsRecipe

class DiarioSport(BasicNewsRecipe):
    title          = u'Diario Sport'
    oldest_article = 2
    max_articles_per_feed = 75
    __author__  = 'Jefferson Frantz'
    description = 'Todas las noticias del Barça y del mundo del deporte en general'
    timefmt = ' [%d %b, %Y]'
    language = 'es'
    no_stylesheets = True

    feeds          = [(u'Sport', u'http://feeds.feedburner.com/sport/ultimahora')]

    extra_css              = '''
                                h2{font-family: serif; font-size: small; font-weight: bold; color: #000000; text-align: justify}
                                '''

    keep_only_tags = [dict(name='div', attrs={'id':['noticiasMedio']})]

    remove_tags        = [
                             dict(name=['object','link','script','ul'])
                            ,dict(name='div', attrs={'id':['scrAdSense','herramientas2','participacion','participacion2','bloque1resultados','bloque2resultados','cont_vinyetesAnt','tinta','noticiasSuperior','cintillopublicidad2']})
                            ,dict(name='p', attrs={'class':['masinformacion','hora']})
                            ,dict(name='a', attrs={'class':["'link'"]})
                            ,dict(name='div', attrs={'class':['addthis_toolbox addthis_default_style','firma','pretitularnoticia']})
                            ,dict(name='form', attrs={'id':['formularioDeBusquedaAvanzada']})
                         ]

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


    def postprocess_html(self, soup, first_fetch):
        img = soup.find('img',src='/img/videos/mascaravideo.png')
        if not img is None:
            img.extract()

        return soup