calibre/recipes/dn_se.recipe
2011-05-15 10:46:46 -06:00

50 lines
1.7 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
dn.se
'''
from calibre.web.feeds.news import BasicNewsRecipe
class DN_se(BasicNewsRecipe):
title = 'Dagens Nyheter'
__author__ = 'Darko Miletic'
description = 'News from Sweden'
publisher = 'Dagens Nyheter'
category = 'news, politics, Sveden'
oldest_article = 2
delay = 1
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
language = 'sv'
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
feeds = [
(u'Nyheter', u'http://www.dn.se/m/rss/toppnyheter')
,(u'Ekonomi', u'http://www.dn.se/ekonomi-rss' )
,(u'Sport' , u'http://www.dn.se/sport-rss' )
,(u'Debatt' , u'http://www.dn.se/debatt-rss' )
,(u'Ledare' , u'http://www.dn.se/ledare-rss' )
,(u'Kultur' , u'http://www.dn.se/kultur-rss' )
]
keep_only_tags = [dict(name='div', attrs={'id':'article-content'})]
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div',attrs={'id':'byline'})
remove_tags = [
dict(name=['object','link','base'])
,dict(name='div',attrs={'id':'hook'})
]