calibre/recipes/msnbc.recipe
2025-01-04 17:51:20 +05:30

58 lines
1.9 KiB
Python

__license__ = 'GPL v3'
__copyright__ = '2010-2011, Darko Miletic <darko.miletic at gmail.com>'
'''
msnbc.msn.com
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class MsNBC(BasicNewsRecipe):
title = 'MSNBC'
__author__ = 'Darko Miletic'
description = 'A Fuller Spectrum of News from msnbc.com and nbcnews.com'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf8'
publisher = 'msnbc.com'
language = 'en_US'
remove_empty_feeds = True
ignore_duplicate_articles = {'title', 'url'}
keep_only_tags = [
classes('article-hero__container article-body')
]
remove_tags = [
dict(name=['iframe', 'button', 'meta', 'link']),
classes('widget_video ad-container related'),
dict(attrs={'data-test': ['social-share-inline']}),
dict(name='source'),
]
feeds = [
('Latest', 'https://feeds.nbcnews.com/msnbc/public/news'),
('Top stories', 'https://feeds.nbcnews.com/nbcnews/public/news'),
('Politics', 'https://feeds.nbcnews.com/nbcnews/public/politics'),
('U.S. News', 'https://feeds.nbcnews.com/nbcnews/public/us-news'),
('World', 'https://feeds.nbcnews.com/nbcnews/public/world'),
('Business', 'https://feeds.nbcnews.com/nbcnews/public/business'),
('Opinion', 'https://feeds.nbcnews.com/nbcnews/public/think'),
]
def get_article_url(self, article):
ans = article.get('guid')
if '/video/' not in ans:
return ans
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-original': True}):
img['src'] = img['data-original']
return soup