calibre/resources/recipes/infobae.recipe

97 lines
3.3 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
'''
infobae.com
'''
import re
import urllib, urlparse
from calibre.web.feeds.news import BasicNewsRecipe
class Infobae(BasicNewsRecipe):
title = 'Infobae.com'
__author__ = 'Darko Miletic and Sujata Raman'
description = 'Informacion Libre las 24 horas'
publisher = 'Infobae.com'
category = 'news, politics, Argentina'
oldest_article = 1
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
language = 'es'
lang = 'es-AR'
encoding = 'cp1252'
cover_url = 'http://www.infobae.com/imgs/header/header.gif'
remove_javascript = True
preprocess_regexps = [(re.compile(
r'<meta name="Description" content="[^"]+">'), lambda m:'')]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True'
extra_css = '''
.col-center{font-family:Arial,Helvetica,sans-serif;}
h1{font-family:Arial,Helvetica,sans-serif; color:#0D4261;}
.fuenteIntNota{font-family:Arial,Helvetica,sans-serif; color:#1D1D1D; font-size:x-small;}
'''
keep_only_tags = [dict(name='div', attrs={'class':['content']})]
remove_tags = [
dict(name='div', attrs={'class':['options','col-right','controles', 'bannerLibre','tiulo-masleidas','masleidas-h']}),
dict(name='a', attrs={'name' : 'comentario',}),
dict(name='iframe'),
dict(name='img', alt = "Ver galerias de imagenes"),
]
feeds = [
(u'Noticias' , u'http://www.infobae.com/adjuntos/html/RSS/hoy.xml' )
,(u'Salud' , u'http://www.infobae.com/adjuntos/html/RSS/salud.xml' )
,(u'Tecnologia', u'http://www.infobae.com/adjuntos/html/RSS/tecnologia.xml')
,(u'Deportes' , u'http://www.infobae.com/adjuntos/html/RSS/deportes.xml' )
]
# def print_version(self, url):
# main, sep, article_part = url.partition('contenidos/')
# article_id, rsep, rrest = article_part.partition('-')
# return u'http://www.infobae.com/notas/nota_imprimir.php?Idx=' + article_id
def get_article_url(self, article):
ans = article.get('link').encode('utf-8')
parts = list(urlparse.urlparse(ans))
parts[2] = urllib.quote(parts[2])
ans = urlparse.urlunparse(parts)
return ans.decode('utf-8')
def preprocess_html(self, soup):
for tag in soup.head.findAll('strong'):
tag.extract()
for tag in soup.findAll('meta'):
del tag['content']
tag.extract()
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">\n<meta http-equiv="Content-Language" content="es-AR"/>\n'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
def postprocess_html(self, soup, first):
for tag in soup.findAll(name='strong'):
tag.name = 'b'
return soup