| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
from __future__ import absolute_import, division, print_function, unicode_literals |
| 4 |
|
| 5 |
__license__ = 'GPL v3' |
| 6 |
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>' |
| 7 |
|
| 8 |
''' |
| 9 |
kurier.at |
| 10 |
''' |
| 11 |
|
| 12 |
import re |
| 13 |
|
| 14 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 15 |
|
| 16 |
|
| 17 |
class Kurier(BasicNewsRecipe): |
| 18 |
title = 'Kurier' |
| 19 |
__author__ = 'Darko Miletic' |
| 20 |
description = 'News from Austria' |
| 21 |
publisher = 'KURIER' |
| 22 |
category = 'news, politics, Austria' |
| 23 |
oldest_article = 2 |
| 24 |
max_articles_per_feed = 100 |
| 25 |
timeout = 30 |
| 26 |
no_stylesheets = True |
| 27 |
use_embedded_content = False |
| 28 |
language = 'de_AT' |
| 29 |
remove_empty_feeds = True |
| 30 |
publication_type = 'newspaper' |
| 31 |
|
| 32 |
conversion_options = {'comment': description, 'tags': category, 'publisher': publisher, 'language': language} |
| 33 |
|
| 34 |
feeds = [ |
| 35 |
('Politik', 'http://kurier.at/politik/xml/rss'), |
| 36 |
('Wirtschaft', 'http://kurier.at/wirtschaft/xml/rss'), |
| 37 |
('Chronik', 'http://kurier.at/chronik/xml/rss'), |
| 38 |
('Kultur', 'http://kurier.at/kultur/xml/rss'), |
| 39 |
('Leben', 'http://kurier.at/leben/xml/rss'), |
| 40 |
('Menschen', 'http://kurier.at/menschen/xml/rss'), |
| 41 |
('Sport', 'http://kurier.at/sport/xml/rss'), |
| 42 |
] |
| 43 |
|
| 44 |
keep_only_tags = [dict(name='article', attrs={'class': re.compile(r'main-article')})] |
| 45 |
|
| 46 |
remove_tags = [ |
| 47 |
dict(name='div', attrs={'class': 'social-media-container'}), |
| 48 |
dict(name='section', attrs={'class': 'tags'}), |
| 49 |
dict(name='section', attrs={'class': re.compile(r'comment-box')}), |
| 50 |
dict(name='section', attrs={'class': re.compile(r'related-content')}), |
| 51 |
dict(name='section', attrs={'class': re.compile(r'article-slider')}), |
| 52 |
dict(name='section', attrs={'class': re.compile(r'commentcontainer')}), |
| 53 |
dict(name='blockquote'), |
| 54 |
] |
| 55 |
|
| 56 |
remove_attributes = ['width', 'height'] |
| 57 |
|
| 58 |
def preprocess_html(self, soup): |
| 59 |
for item in soup.findAll(style=True): |
| 60 |
del item['style'] |
| 61 |
return self.adeify_images(soup) |