calibre/recipes/deutsche_welle_en.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

76 lines
2.4 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>'
'''
Deutsche Welle (english) - dw.com/en
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class DeutscheWelle_en(BasicNewsRecipe):
title = 'Deutsche Welle'
__author__ = 'Darko Miletic'
description = 'News from Germany and the world'
publisher = 'Deutsche Welle'
language = 'en'
oldest_article = 1
max_articles_per_feed = 50
no_stylesheets = True
remove_javascript = True
remove_empty_feeds = True
ignore_duplicate_articles = {'title', 'url'}
feeds = [
('Top Stories', 'http://rss.dw-world.de/rdf/rss-en-top'),
('World', 'http://rss.dw.de/rdf/rss-en-world'),
('Germany', 'http://rss.dw.de/rdf/rss-en-ger'),
('Europe', 'http://rss.dw.de/rdf/rss-en-eu'),
('Business', 'http://rss.dw.de/rdf/rss-en-bus'),
('Culture & Lifestyle', 'http://rss.dw.de/rdf/rss-en-cul'),
('Sports', 'http://rss.dw.de/rdf/rss-en-sports'),
('Visit Germany', 'http://rss.dw.de/rdf/rss-en-visitgermany'),
('Asia', 'http://rss.dw.de/rdf/rss-en-asia')
]
keep_only_tags = [
dict(name='div', attrs={'class': 'col3'})
]
remove_tags_after = [
dict(name='div', attrs={'class': 'group'})
]
remove_tags = [
dict(name='div', attrs={'class': 'col1'}),
dict(name='div', attrs={'class': re.compile('gallery')}),
dict(name='div', attrs={'class': re.compile('audio')}),
dict(name='div', attrs={'class': re.compile('video')})
]
remove_attributes = ['height', 'width',
'onclick', 'border', 'lang', 'link']
extra_css = '''
h1 {font-size: 1.6em; margin-top: 0em}
.artikel {font-size: 1em; text-transform: uppercase; margin: 0em}
'''
def preprocess_html(self, soup):
# convert local hyperlinks
for a in soup.findAll('a', href=True):
if a['href'].startswith('/'):
a['href'] = 'http://www.dw.com' + a['href']
elif a['href'].startswith('#'):
del a['href']
# remove all style attributes with an effect on font size
for item in soup.findAll(attrs={'style': re.compile('font-size')}):
del item['style']
return soup