Die Presse recipe

[jr17oo]

I'm having issues with the recipe for "Die Presse" (an Austrian newspaper). Special characters are not shown correctly: "ü" is "ü", "ß" is "Ã" and so forth.
To be honest, I do not fully understand the code (see here). But by simply removing all parts that seemed to have something to do with the encoding I was able to fix this problem. I also added a "remove_tags_after" entry to get rid of the page footer.

#!/usr/bin/env python2
# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function

__license__   = 'GPL v3'
__copyright__ = '2009, Gerhard Aigner <gerhard.aigner at gmail.com>'

''' http://www.diepresse.at - Austrian Newspaper '''

import re
from calibre.web.feeds.news import BasicNewsRecipe

class DiePresseRecipe(BasicNewsRecipe):
    title = 'Die Presse'
    __author__ = 'Gerhard Aigner'
    description = 'DiePresse.com - Die Online-Ausgabe der Österreichischen Tageszeitung Die Presse.' 
    publisher = 'Die Presse Verlags-Gesellschaft m.b.H. Co KG'
    language = 'de_AT'
    category = 'news, politics, nachrichten, Austria'
    use_embedded_content = False
    remove_empty_feeds = True
    no_stylesheets = True

    recursions = 0
    oldest_article = 1
    max_articles_per_feed = 100

    html2lrf_options = [
                          '--comment'  , description
                        , '--category' , category
                        , '--publisher', publisher
                        ]

    html2epub_options  = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 

    preprocess_regexps = [
	(re.compile(r'Textversion', re.DOTALL), lambda match: ''),
    ]

    remove_tags = [dict(name='hr'),
	dict(name='br'),
	dict(name='small'),
	dict(name='img'),
	dict(name='div', attrs={'class':'textnavi'}),
	dict(name='h1', attrs={'class':'titel'}),
	dict(name='a', attrs={'class':'print'}),
	dict(name='div', attrs={'class':'hline'})]

    remove_tags_after = [
        dict(name='div', attrs={'class':'articletext'})
    ]

    feeds = [
        ('Politik', 'http://diepresse.com/rss/Politik'),
        ('Wirtschaft', 'http://diepresse.com/rss/Wirtschaft'),
        ('Europa', 'http://diepresse.com/rss/EU'),
        ('Panorama', 'http://diepresse.com/rss/Panorama'),
        ('Sport', 'http://diepresse.com/rss/Sport'),
        ('Kultur', 'http://diepresse.com/rss/Kultur'),
        ('Leben', 'http://diepresse.com/rss/Leben'),
        ('Tech', 'http://diepresse.com/rss/Tech'),
        ('Wissenschaft', 'http://diepresse.com/rss/Science'),
        ('Bildung', 'http://diepresse.com/rss/Bildung'),
        ('Gesundheit', 'http://diepresse.com/rss/Gesundheit'),
        ('Recht', 'http://diepresse.com/rss/Recht'),
        ('Spectrum', 'http://diepresse.com/rss/Spectrum'),
        ('Meinung', 'http://diepresse.com/rss/Meinung')
    ]

    def print_version(self, url):
        return url.replace('home','text/home')