t

from calibre.web.feeds.news import BasicNewsRecipe from calibre.ebooks.BeautifulSoup import BeautifulSoup class DenverPost(BasicNewsRecipe): title = u'Denver Post' language = 'en' __author__ = 'Krittika Goyal' oldest_article = 1 #days max_articles_per_feed = 20 conversion_options = {'linearize_tables':True} no_stylesheets = True #remove_tags_before = dict(name='h1', attrs={'class':'heading'}) #remove_tags_after = dict(name='td', attrs={'class':'newptool1'}) remove_tags = [ dict(name='iframe'), dict(name='img', src=lambda x: not x or '/tracking/' in x), dict(name='span', attrs={'fd-id':True}), dict(name='div', attrs={'class':['articleOptions', 'articlePosition2']}), #dict(name='div', attrs={'id':['qrformdiv', 'inSection', 'alpha-inner']}), #dict(name='ul', attrs={'class':'article-tools'}), #dict(name='ul', attrs={'class':'articleTools'}), ] feeds = [ ('Top Stories', 'http://feeds.denverpost.com/dp-news-topstories'), ('Business', 'http://feeds.denverpost.com/dp-business'), ('Sports', 'http://feeds.denverpost.com/dp-sports'), ('Lifestyles', 'http://feeds.denverpost.com/dp-lifestyles'), ('Politics', 'http://feeds.denverpost.com/dp-politics'), ('Entertainment', 'http://feeds.denverpost.com/dp-entertainment'), ] def preprocess_html(self, soup): story = soup.find(name='td', attrs={'class':'articleBox'}) #td = heading.findParent(name='td') #td.extract() story.extract() soup = BeautifulSoup('t') body = soup.find(name='body') body.insert(0, story) story.name = 'div' for img in soup.findAll(name='img', style='visibility:hidden;'): del img['style'] for div in soup.findAll(id='caption', style=True): del div['style'] return soup