calibre/recipes/gva_be.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

65 lines
2.3 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.gva.be
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class GazetvanAntwerpen(BasicNewsRecipe):
title = 'Gazet van Antwerpen'
__author__ = 'Darko Miletic'
description = 'News from Belgium in Dutch'
publisher = 'Mediahuis'
category = 'news, politics, Belgium'
language = 'nl_BE'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
remove_javascript = True
masthead_url = 'http://2.gvacdn.be/extra/assets/img/gazet-van-antwerpen-red.svg'
feeds = [
('Stad & Regio', 'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/stadenregio'),
('Economie', 'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/economie'),
('Binnenland', 'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/binnenland'),
('Buitenland', 'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/buitenland'),
('Media & Cultuur', 'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/mediaencultuur'),
('Sport', 'http://www.gva.be/syndicationservices/artfeedservice.svc/rss/mostrecent/sport')
]
keep_only_tags = [
dict(name='header', attrs={'class': 'article__header'}),
dict(name='footer', attrs={'class': 'article__meta'}),
dict(name='div', attrs={
'class': ['article', 'article__body', 'slideshow__intro']}),
dict(name='figure', attrs={'class': 'article__image'})
]
remove_tags = [
dict(name=['embed', 'object']),
dict(name='div', attrs={'class': ['note NotePortrait', 'note']}),
dict(name='ul', attrs={'class': re.compile('article__share')}),
dict(name='div', attrs={'class': 'slideshow__controls'}),
dict(name='a', attrs={'role': 'button'}),
dict(name='figure', attrs={'class': re.compile('video')})
]
remove_attributes = ['width', 'height']
def preprocess_html(self, soup):
del soup.body['onload']
for item in soup.findAll(style=True):
del item['style']
return soup