calibre/resources/recipes/corriere_della_sera_en.recipe

56 lines
1.9 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
__author__ = 'Lorenzo Vigentini, based on Darko Miletic'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>, Lorenzo Vigentini <l.vigentini at gmail.com>'
__version__ = 'v1.01'
__date__ = '10, January 2010'
__description__ = 'Italian daily newspaper (english version)'
'''
http://www.corriere.it/
'''
from calibre.web.feeds.news import BasicNewsRecipe
class ilCorriere(BasicNewsRecipe):
__author__ = 'Lorenzo Vigentini, based on Darko Miletic'
description = 'Italian daily newspaper (english version)'
cover_url = 'http://images.corriereobjects.it/images/static/common/logo_home.gif?v=200709121520'
title = u'Il Corriere della sera (english) '
publisher = 'RCS Digital'
category = 'News, politics, culture, economy, general interest'
language = 'en'
timefmt = '[%a, %d %b, %Y]'
oldest_article = 1
max_articles_per_feed = 100
use_embedded_content = False
recursion = 10
remove_javascript = True
no_stylesheets = 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='div', attrs={'class':['news-dettaglio article','article']})]
remove_tags = [
dict(name=['base','object','link','embed']),
dict(name='div', attrs={'class':'news-goback'}),
dict(name='ul', attrs={'class':'toolbar'})
]
remove_tags_after = dict(name='p', attrs={'class':'footnotes'})
feeds = [
(u'News' , u'http://www.corriere.it/rss/english.xml' )
]