mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
96 lines
3.6 KiB
Plaintext
96 lines
3.6 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
|
|
ignore_duplicate_articles = {'url'}
|
|
# recursions = 1
|
|
# match_regexps = [r'http://sportsillustrated.cnn.com/.*/[1-9].html']
|
|
max_articles_per_feed = 25
|
|
compress_news_images = True
|
|
compress_news_images_auto_size = 12
|
|
|
|
extra_css = '''
|
|
h1 {font-size:xx-large; font-family:Arial,Helvetica,sans-serif;}
|
|
.cnn_story_author, .cnn_stryathrtmp {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;}
|
|
.cnn_strycaptiontxt, .cnnArticleGalleryPhotoContainer {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;}
|
|
.cnn_strycbftrtxt, .cnnEditorialNote {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;}
|
|
.cnn_strycntntlft {font-size:medium; font-family:Arial,Helvetica,sans-serif;}
|
|
'''
|
|
|
|
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=['body-text', 'storycontent']),
|
|
dict(attrs={'class': ['pg-headline', 'metadata']}),
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(attrs={'class': lambda x: x and bool({
|
|
'video__end-slate', 'owl-filmstrip', 'el-embed-instagram',
|
|
}.intersection(set(x.split())))}),
|
|
]
|
|
|
|
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 preprocess_html(self, soup):
|
|
body = soup.find('body')
|
|
for h2 in soup.findAll(attrs={'class': 'pg-headline'}):
|
|
h2.extract()
|
|
body.insert(0, h2)
|
|
for img in soup.findAll('img', attrs={'data-src-medium': True}):
|
|
img['src'] = img['data-src-medium']
|
|
return soup
|
|
|
|
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
|