Updated version with better page parsing and some CSS for eye candy.
Spoiler:
Code:
import re
from calibre.web.feeds.news import BasicNewsRecipe
class ElMundoTodayRecipe(BasicNewsRecipe):
title = 'El Mundo Today'
description = u'La actualidad del maņana'
category = 'Noticias, humor'
cover_url = 'http://www.elmundotoday.com/wp-content/themes/EarthlyTouch/images/logo.png'
oldest_article = 30
max_articles_per_feed = 60
auto_cleanup = False
no_stylesheets = True
remove_javascript = True
language = 'es_ES'
use_embedded_content = False
preprocess_regexps = [
(re.compile(r'</title>.*<!--Begin Article Single-->', re.DOTALL),
lambda match: '</title><body>'),
#(re.compile(r'^\t{5}<a href.*Permanent Link to ">$'), lambda match: ''),
#(re.compile(r'\t{5}</a>$'), lambda match: ''),
(re.compile(r'<div class="social4i".*</body>', re.DOTALL),
lambda match: '</body>'),
]
keep_only_tags = [
dict(name='div', attrs={'class':'post-wrapper'})
]
remove_attributes = [ 'href', 'title', 'alt' ]
extra_css = '''
.antetitulo{font-variant:small-caps; font-weight:bold} .articleinfo{font-size:small}
img{margin-bottom:0.4em; display:block; margin-left:auto; margin-right:auto}
'''
feeds = [('El Mundo Today', 'http://www.elmundotoday.com/feed/')]
def get_broser(self):
br = BasicNewsRecipe.get_browser(self)
br.set_handle_gzip(True)
return br