Read Observa Digital on your iPad or Kindle in no time. Click download to load the free ebook on your reader.
Check out all the available public recipes or write your own with these quick start guides. ReadBeam is built on calibre, so everything in the docs and the fora applies here as well.
Noticias desde Uruguay
Language: es
Requires Subscription: No, it's available as free ebook
Schedule Every morning
#!/usr/bin/env python
__license__ = 'GPL v3'
__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
'''
observa.com.uy
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Noticias(BasicNewsRecipe):
title = 'Observa Digital'
__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
description = 'Noticias desde Uruguay'
language = 'es_UY'
timefmt = '[%a, %d %b, %Y]'
use_embedded_content = False
recursion = 5
encoding = 'utf8'
remove_javascript = True
no_stylesheets = True
oldest_article = 2
max_articles_per_feed = 100
keep_only_tags = [dict(id=['contenido'])]
remove_tags = [
dict(name='div', attrs={'id':'contenedorVinculadas'}),
dict(name='p', attrs={'id':'nota_firma'}),
dict(name=['object','link'])
]
remove_attributes = ['width','height', 'style', 'font', 'color']
extra_css = '''
h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
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'Actualidad', u'http://www.observa.com.uy/RSS/actualidad.xml'),
(u'Deportes', u'http://www.observa.com.uy/RSS/deportes.xml'),
(u'Vida', u'http://www.observa.com.uy/RSS/vida.xml'),
(u'Ciencia y Tecnologia', u'http://www.observa.com.uy/RSS/ciencia.xml')
]
def get_cover_url(self):
cover_url = None
index = 'http://www.elobservador.com.uy/elobservador/nav_portada.asp?suplemento=dia'
soup = self.index_to_soup(index)
link_item = soup.find('img',attrs={'usemap':'#mapeo_imagenes'})
if link_item:
cover_url = 'http://www.elobservador.com.uy'+link_item['src'].strip()
print cover_url
return cover_url
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup