mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
65 lines
2.0 KiB
Python
65 lines
2.0 KiB
Python
#!/usr/bin/env python
|
|
# vim:fileencoding=utf-8
|
|
from __future__ import unicode_literals, division, absolute_import, print_function
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
|
|
|
|
'''
|
|
kurier.at
|
|
'''
|
|
|
|
import re
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class Kurier(BasicNewsRecipe):
|
|
title = 'Kurier'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'News from Austria'
|
|
publisher = 'KURIER'
|
|
category = 'news, politics, Austria'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 100
|
|
timeout = 30
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
language = 'de_AT'
|
|
remove_empty_feeds = True
|
|
publication_type = 'newspaper'
|
|
|
|
conversion_options = {
|
|
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
|
|
}
|
|
|
|
feeds = [
|
|
('Politik', 'http://kurier.at/politik/xml/rss'),
|
|
('Wirtschaft', 'http://kurier.at/wirtschaft/xml/rss'),
|
|
('Chronik', 'http://kurier.at/chronik/xml/rss'),
|
|
('Kultur', 'http://kurier.at/kultur/xml/rss'),
|
|
('Leben', 'http://kurier.at/leben/xml/rss'),
|
|
('Menschen', 'http://kurier.at/menschen/xml/rss'),
|
|
('Sport', 'http://kurier.at/sport/xml/rss')
|
|
]
|
|
|
|
keep_only_tags = [
|
|
dict(name='article', attrs={'class': re.compile('main-article')})
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name='div', attrs={'class': 'social-media-container'}),
|
|
dict(name='section', attrs={'class': 'tags'}),
|
|
dict(name='section', attrs={'class': re.compile('comment-box')}),
|
|
dict(name='section', attrs={'class': re.compile('related-content')}),
|
|
dict(name='section', attrs={'class': re.compile('article-slider')}),
|
|
dict(name='section', attrs={'class': re.compile('commentcontainer')}),
|
|
dict(name='blockquote')
|
|
]
|
|
|
|
remove_attributes = ['width', 'height']
|
|
|
|
def preprocess_html(self, soup):
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
return self.adeify_images(soup)
|