calibre/recipes/variety.recipe

47 lines
2.0 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
www.variety.com
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class Variety(BasicNewsRecipe):
title = 'Variety'
__author__ = 'Darko Miletic'
description = 'Breaking entertainment movie news, movie reviews, entertainment industry events, news and reviews from Cannes, Oscars, and Hollywood awards. Featuring box office charts, archives and more.'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
publisher = 'Red Business Information'
category = 'Entertainment Industry News, Daily Variety, Movie Reviews, TV, Awards, Oscars, Cannes, Box Office, Hollywood'
language = 'en'
masthead_url = 'http://a330.g.akamai.net/7/330/23382/20090528190853/www.variety.com/graphics/variety/Variety_logo_green_tm.gif'
extra_css = ' body{font-family: Georgia,"Times New Roman",Times,Courier,serif } img{margin-bottom: 1em} '
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
}
remove_tags = [dict(name=['object','link','map'])]
keep_only_tags = [dict(name='div', attrs={'id':'article'})]
feeds = [(u'News & Articles', u'http://feeds.feedburner.com/variety/headlines' )]
def print_version(self, url):
rpt = url.rpartition('?')[0]
artid = rpt.rpartition('/')[2]
catidr = url.rpartition('categoryid=')[2]
catid = catidr.partition('&')[0]
return 'http://www.variety.com/index.asp?layout=print_story&articleid=' + artid + '&categoryid=' + catid
def preprocess_html(self, soup):
return self.adeify_images(soup)