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

83 lines
2.8 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
'''
Profile to download CNN
'''
from calibre.web.feeds.news import BasicNewsRecipe, classes
class CNN(BasicNewsRecipe):
title = 'CNN'
description = 'Global news'
timefmt = ' [%d %b %Y]'
__author__ = 'Kovid Goyal'
language = 'en_US'
no_stylesheets = True
use_embedded_content = False
oldest_article = 2
ignore_duplicate_articles = {'url'}
max_articles_per_feed = 25
remove_attributes = ['style', 'height', 'width']
keep_only_tags = [
classes('headline__wrapper headline__sub-container article__main'),
]
remove_tags = [classes('video-inline_carousel')]
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)
feeds = [
('Top News', 'http://rss.cnn.com/rss/cnn_topstories.rss'),
('World', 'http://rss.cnn.com/rss/cnn_world.rss'),
('U.S.', 'http://rss.cnn.com/rss/cnn_us.rss'),
# ('Sports', 'http://rss.cnn.com/rss/si_topstories.rss'),
('Business', 'http://rss.cnn.com/rss/money_latest.rss'),
('Politics', 'http://rss.cnn.com/rss/cnn_allpolitics.rss'),
('Law', 'http://rss.cnn.com/rss/cnn_law.rss'),
('Technology', 'http://rss.cnn.com/rss/cnn_tech.rss'),
('Science & Space', 'http://rss.cnn.com/rss/cnn_space.rss'),
('Health', 'http://rss.cnn.com/rss/cnn_health.rss'),
('Entertainment', 'http://rss.cnn.com/rss/cnn_showbiz.rss'),
('Education', 'http://rss.cnn.com/rss/cnn_education.rss'),
('Offbeat', 'http://rss.cnn.com/rss/cnn_offbeat.rss'),
('Most Popular', 'http://rss.cnn.com/rss/cnn_mostpopular.rss')
]
def get_article_url(self, article):
ans = BasicNewsRecipe.get_article_url(self, article)
ans = ans.partition('?')[0]
if '.com/videos/' in ans:
ans = None
return ans
def get_masthead_url(self):
masthead = 'http://i.cdn.turner.com/cnn/.element/img/3.0/global/header/intl/hdr-globe-central.gif'
br = BasicNewsRecipe.get_browser(self)
try:
br.open(masthead)
except:
self.log('\nCover unavailable')
masthead = None
return masthead
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'src':lambda x: x and x.endswith('.svg')}):
img.extract()
return soup