calibre/recipes/deutsche_welle_de.recipe
2025-01-24 11:14:22 +01:00

59 lines
2.1 KiB
Python

from calibre.web.feeds.news import BasicNewsRecipe, classes
class DeutscheWelle(BasicNewsRecipe):
title = 'Deutsche Welle'
description = 'Nachrichten der Deutschen Welle (DW)'
publisher = 'DW - info@dw.com'
language = 'de'
__author__ = 'unkn0wn'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
remove_javascript = True
remove_empty_feeds = True
ignore_duplicate_articles = {'title', 'url'}
remove_attributes = ['height', 'width', 'style']
keep_only_tags = [
dict(name='article')
]
recipe_specific_options = {
'days': {
'short': 'Oldest article to download from this news source. In days ',
'long': 'For example, 0.5, gives you articles from the past 12 hours',
'default': str(oldest_article)
}
}
def __init__(self, *args, **kwargs):
BasicNewsRecipe.__init__(self, *args, **kwargs)
d = self.recipe_specific_options.get('days')
if d and isinstance(d, str):
self.oldest_article = float(d)
remove_tags = [
dict(name=['footer', 'source']),
dict(attrs={'data-tracking-name':'sharing-icons-inline'}),
classes('kicker advertisement vjs-wrapper')
]
# watch out https://www.dw.com/de/service/rss/s-9773 for description of possible rss feeds
feeds = [
('Nachrichten', 'http://rss.dw.com/xml/rss-de-news'),
('Wissenschaft', 'http://rss.dw.com/xml/rss-de-wissenschaft'),
('Sport', 'http://rss.dw.com/xml/rss-de-sport'),
('Deuschland entdecken', 'http://rss.dw.com/xml/rss-de-deutschlandentdecken'),
('Presse', 'http://rss.dw.com/xml/presse'),
('Politik', 'http://rss.dw.com/xml/rss_de_politik'),
('Wirtschaft', 'http://rss.dw.com/xml/rss-de-eco'),
('Kultur und Leben', 'http://rss.dw.com/xml/rss-de-cul'),
('Thema des Tages', 'http://rss.dw.com/xml/rss-de-top'),
]
def preprocess_html(self, soup):
for img in soup.findAll('img', srcset=True):
img['src'] = img['srcset'].split()[6]
return soup