mirror of
git://github.com/kovidgoyal/calibre.git
synced 2026-04-21 15:33:18 +02:00
49 lines
2 KiB
Text
49 lines
2 KiB
Text
__license__ = 'GPL v3'
|
|
__copyright__ = '2010-2011, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
msnbc.msn.com
|
|
'''
|
|
|
|
from calibre.web.feeds.recipes import BasicNewsRecipe
|
|
|
|
class MsNBC(BasicNewsRecipe):
|
|
title = 'msnbc.com'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'A Fuller Spectrum of News'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
encoding = 'utf8'
|
|
publisher = 'msnbc.com'
|
|
language = 'en'
|
|
remove_empty_feeds = True
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
keep_only_tags=[
|
|
dict(itemprop='headline'),
|
|
dict(attrs={'class':lambda x: x and set(x.split()).intersection({'byline_article', 'article_main'})}),
|
|
dict(attrs={'class':lambda x: x and set(x.split()).intersection({'authors-names', 'pane-node-body'})}),
|
|
]
|
|
remove_tags = [
|
|
dict(name=['iframe', 'button', 'meta', 'link']),
|
|
dict(attrs={'class':lambda x: x and set(x.split()).intersection({'widget_video', 'ad-container'})}),
|
|
]
|
|
|
|
feeds = [
|
|
('Latest', 'http://www.msnbc.com/feeds/latest'),
|
|
(u'US News' , u'http://rss.msnbc.msn.com/id/3032524/device/rss/rss.xml')
|
|
,(u'Politics' , u'http://rss.msnbc.msn.com/id/3032552/device/rss/rss.xml')
|
|
,(u'Business' , u'http://rss.msnbc.msn.com/id/3032071/device/rss/rss.xml')
|
|
,(u'Health' , u'http://rss.msnbc.msn.com/id/3088327/device/rss/rss.xml')
|
|
,(u'Tech & Science', u'http://rss.msnbc.msn.com/id/3032117/device/rss/rss.xml')
|
|
]
|
|
|
|
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
|