__license__ = 'GPL v3' __copyright__ = '2008, Kovid Goyal ' ''' Fetch zdnet. ''' from calibre.web.feeds.news import BasicNewsRecipe class cdnet(BasicNewsRecipe): title = 'zdnet' description = 'zdnet security' __author__ = 'Oliver Niesner, Krittika Goyal' language = 'en' use_embedded_content = False timefmt = ' [%d %b %Y]' max_articles_per_feed = 40 no_stylesheets = True encoding = 'latin1' auto_cleanup = True # remove_tags = [dict(id='eyebrows'), # dict(id='header'), # dict(id='search'), # dict(id='nav'), # dict(id='blog-author-info'), # dict(id='post-tags'), # dict(id='bio-naraine'), # dict(id='bio-kennedy'), # dict(id='author-short-disclosure-kennedy'), # dict(id=''), feeds = [('zdnet', 'http://feeds.feedburner.com/zdnet/security')] def preprocess_html(self, soup): for item in soup.findAll(style=True): del item['style'] return soup