| 1 |
__license__ = 'GPL v3' |
| 2 |
__copyright__ = '2013, Alexander Schremmer <[email protected]>, Robert Riemann <[email protected]>' |
| 3 |
|
| 4 |
import re |
| 5 |
|
| 6 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 7 |
|
| 8 |
|
| 9 |
class TazRSSRecipe(BasicNewsRecipe): |
| 10 |
title = 'Taz - die Tageszeitung' |
| 11 |
description = 'Taz.de - die tageszeitung (Anpassung von Robert)' |
| 12 |
__author__ = 'Alexander Schremmer, Robert Riemann' |
| 13 |
language = 'de' |
| 14 |
lang = 'de-DE' |
| 15 |
category = 'news, Germany' |
| 16 |
timefmt = ' [%a, %d %b %Y]' |
| 17 |
publication_type = 'newspaper' |
| 18 |
remove_empty_feeds = True |
| 19 |
use_embedded_content = False |
| 20 |
oldest_article = 7 |
| 21 |
max_articles_per_feed = 100 |
| 22 |
publisher = 'taz Entwicklungs GmbH & Co. Medien KG' |
| 23 |
# masthead_url = u'http://galeria-autonomica.de/wp-content/uploads/a_taz-logo.gif' |
| 24 |
masthead_url = 'http://upload.wikimedia.org/wikipedia/de/thumb/1/15/Die-Tageszeitung-Logo.svg/500px-Die-Tageszeitung-Logo.svg.png' |
| 25 |
|
| 26 |
conversion_options = { |
| 27 |
'publisher': publisher, |
| 28 |
'language': lang, |
| 29 |
} |
| 30 |
feeds = [ |
| 31 |
('Schlagzeilen', 'http://www.taz.de/!p3270;rss/'), |
| 32 |
('Politik', 'http://www.taz.de/Politik/!p2;rss/'), |
| 33 |
('Zukunft', 'http://www.taz.de/Zukunft/!p4;rss/'), |
| 34 |
('Netz', 'http://www.taz.de/Netz/!p5;rss/'), |
| 35 |
('Debatte', 'http://www.taz.de/Debatte/!p9;rss/'), |
| 36 |
('Leben', 'http://www.taz.de/Leben/!p10;rss/'), |
| 37 |
('Sport', 'http://www.taz.de/Sport/!p12;rss/'), |
| 38 |
('Wahrheit', 'http://www.taz.de/Wahrheit/!p13;rss/'), |
| 39 |
('Berlin', 'http://www.taz.de/Berlin/!p14;rss/'), |
| 40 |
('Nord', 'http://www.taz.de/Nord/!p11;rss/'), |
| 41 |
] |
| 42 |
# omit articles already linked in Schlagzeilen feed |
| 43 |
ignore_duplicate_articles = {'title', 'url'} |
| 44 |
|
| 45 |
# use the cover presented on the homepage |
| 46 |
cover_url = 'http://www.taz.de/digitaz/.s1jpeg320' |
| 47 |
|
| 48 |
no_stylesheets = True # default value is False, but True makes process much faster |
| 49 |
keep_only_tags = [dict(name=['div'], attrs={'class': re.compile(r'.*\bsect_article\b.*')})] |
| 50 |
remove_tags = [ |
| 51 |
dict(name=['div'], attrs={'class': 'sectfoot'}), |
| 52 |
# remove: taz paywall |
| 53 |
dict(name=['div'], attrs={'id': 'tzi_paywall'}), |
| 54 |
] |
| 55 |
|
| 56 |
|
| 57 |
# with article pictures on Kindle super-slow |
| 58 |
# def populate_article_metadata(self, article, soup, first): |
| 59 |
# if first and hasattr(self, 'add_toc_thumbnail'): |
| 60 |
# picdiv = soup.find('img') |
| 61 |
# if picdiv is not None: |
| 62 |
# self.add_toc_thumbnail(article,picdiv['src']) |