mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
61 lines
2.2 KiB
Plaintext
61 lines
2.2 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
|
|
'''
|
|
Profile to download CNN
|
|
'''
|
|
|
|
import re
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class CNN(BasicNewsRecipe):
|
|
|
|
title = 'CNN'
|
|
description = 'Global news'
|
|
timefmt = ' [%d %b %Y]'
|
|
__author__ = 'Kovid Goyal'
|
|
language = 'en'
|
|
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
oldest_article = 15
|
|
#recursions = 1
|
|
#match_regexps = [r'http://sportsillustrated.cnn.com/.*/[1-9].html']
|
|
max_articles_per_feed = 25
|
|
|
|
preprocess_regexps = [
|
|
(re.compile(r'<!--\[if.*if\]-->', re.DOTALL), lambda m: ''),
|
|
(re.compile(r'<script.*?</script>', re.DOTALL), lambda m: ''),
|
|
(re.compile(r'<style.*?</style>', re.DOTALL), lambda m: ''),
|
|
]
|
|
|
|
keep_only_tags = [dict(id=['cnnContentContainer', 'storycontent'])]
|
|
remove_tags = [
|
|
{'class':['cnn_strybtntools', 'cnn_strylftcntnt',
|
|
'cnn_strybtntools', 'cnn_strybtntoolsbttm', 'cnn_strybtmcntnt',
|
|
'cnn_strycntntrgt', 'hed_side', 'foot']},
|
|
dict(id=['ie_column']),
|
|
]
|
|
|
|
|
|
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)
|
|
return ans.partition('?')[0]
|
|
|