mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
52 lines
1.6 KiB
Python
52 lines
1.6 KiB
Python
#!/usr/bin/env python2
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
granma.cubaweb.cu
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class Granma(BasicNewsRecipe):
|
|
title = 'Diario Granma'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Organo oficial del Comite Central del Partido Comunista de Cuba'
|
|
publisher = 'Granma'
|
|
category = 'news, politics, Cuba'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
encoding = 'cp1252'
|
|
cover_url = 'http://www.granma.cubaweb.cu/imagenes/granweb229d.jpg'
|
|
language = 'es_CU'
|
|
|
|
remove_javascript = True
|
|
|
|
html2lrf_options = [
|
|
'--comment', description, '--category', category, '--publisher', publisher, '--ignore-tables'
|
|
]
|
|
|
|
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + \
|
|
description + '"\ntags="' + category + '"\nlinearize_tables=True'
|
|
|
|
keep_only_tags = [dict(name='table', attrs={'height': '466'})]
|
|
|
|
remove_tags = [dict(name=['embed', 'link', 'object'])]
|
|
|
|
feeds = [(u'Noticias', u'http://www.granma.cubaweb.cu/noticias.xml')]
|
|
|
|
def preprocess_html(self, soup):
|
|
mtag = '<meta http-equiv="Content-Language" content="es-CU"/>'
|
|
soup.head.insert(0, mtag)
|
|
for item in soup.findAll('table'):
|
|
if item.has_key('width'): # noqa
|
|
del item['width']
|
|
if item.has_key('height'): # noqa
|
|
del item['height']
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
return soup
|