calibre/recipes/rmf24_opinie.recipe
Kovid Goyal 29cd8d64ea
Change shebangs to python from python2
Also remove a few other miscellaneous references to python2
2020-08-22 18:47:51 +05:30

56 lines
1.8 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = u'2010, Tomasz Dlugosz <tomek3d@gmail.com>'
'''
rmf24.pl
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class RMF24_opinie(BasicNewsRecipe):
title = u'Rmf24.pl - Opinie'
description = u'Blogi, wywiady i komentarze ze strony rmf24.pl'
language = 'pl'
oldest_article = 7
max_articles_per_feed = 100
__author__ = u'Tomasz D\u0142ugosz'
no_stylesheets = True
remove_javascript = True
remove_empty_feeds = True
feeds = [(u'Blogi', u'http://www.rmf24.pl/opinie/blogi/feed'),
(u'Kontrwywiad',
u'http://www.rmf24.pl/opinie/wywiady/kontrwywiad/feed'),
(u'Przes\u0142uchanie',
u'http://www.rmf24.pl/opinie/wywiady/przesluchanie/feed'),
(u'Komentarze', u'http://www.rmf24.pl/opinie/komentarze/feed')]
keep_only_tags = [
dict(name='header', attrs={'class': 'article-header'}),
dict(name='div', attrs={'class': 'article-container'})]
remove_tags = [dict(name='div', attrs={'id': 'ReklamaMobile'})]
extra_css = '''
h1 { font-size: 1.2em; }
'''
# thanks to Kovid Goyal
def get_article_url(self, article):
link = article.get('link')
if '/audio,aId' not in link:
return link
preprocess_regexps = [
(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
[
(r'<h2>Zdj.cie</h2>', lambda match: ''),
(r'embed embed(Left|Right|Center) articleEmbed(Audio|Wideo articleEmbedVideo|ArticleFull|ArticleTitle|ArticleListTitle|AlbumHorizontal)">', lambda match: 'REMOVE">'), # noqa
(r'<a href="http://www.facebook.com/pages/RMF24pl/.*?>RMF24.pl</a> on Facebook</div>',
lambda match: '</div>')
]
]