t

from calibre.web.feeds.news import BasicNewsRecipe from calibre.ebooks.BeautifulSoup import BeautifulSoup class JSOnline(BasicNewsRecipe): title = u'Milwaukee Journal Sentinel' language = 'en' __author__ = 'Krittika Goyal' oldest_article = 2 #days max_articles_per_feed = 25 no_stylesheets = True remove_tags_before = dict(name='div', attrs={'id':'wrapper'}) #remove_tags_after = dict(name='td', attrs={'class':'asset-bar'}) remove_tags = [ dict(name='iframe'), dict(name='div', attrs={'class':['right_float', 'headlines', 'side_section_container poll', 'side_section_container html']}), #dict(name='div', attrs={'id':['rightColumn']}), #dict(name='span', attrs={'class':'comment_forbidden'}), #dict(name='ul', attrs={'class':'links inline'}), #dict(name='p', attrs={'id':'commentadvisory'}), #dict(name='div', attrs={'style':['width: 300px; margin-right: 2em; float: left;']}), #dict(name='div', style="float:right; width: 300px;"), #dict(name='p', style="clear:both;"), #dict(name='p', attrs={'name':'&lpos=footer_textlinks'}), #dict(name='span', text=':'), ] feeds = [ ('Main Headlines', 'http://www.jsonline.com/rss?c=y&path=%2F'), ('Business', 'http://www.jsonline.com/rss?c=y&path=%2Fbusiness'), ('Milwaukee marketplace', 'http://www.jsonline.com/rss?c=y&path=%2Fmarketplace'), ('Top Entertainment Stories', 'http://www.jsonline.com/rss?c=y&path=%2Fentertainment%2Ftopstories'), ('Arts and Books', 'http://www.jsonline.com/rss?c=y&path=%2Fentertainment%2Farts'), ('Movies', 'http://www.jsonline.com/rss?c=y&path=%2Fentertainment%2Fmovies'), ('Music and Nightlife', 'http://www.jsonline.com/rss?c=y&path=%2Fentertainment%2Fmusicandnightlife'), ('Dining', 'http://www.jsonline.com/rss?c=y&path=%2Ffeatures%2Fdining'), ('Fashion', 'http://www.jsonline.com/rss?c=y&path=%2Ffeatures%2Ffashion'), ('Health and Fitness', 'http://www.jsonline.com/rss?c=y&path=%2Ffeatures%2Fhealth'), ('Top Metro Stories', 'http://www.jsonline.com/rss?c=y&path=%2Fnews%2Ftopstories'), ('Crime', 'http://www.jsonline.com/rss?c=y&path=%2Fnews%2Fcrime'), ('Sports', 'http://www.jsonline.com/rss?c=y&path=%2Fsports'), ] #def print_version(self, url): #return url+'/0' def preprocess_html(self, soup): story = soup.find(name='div', attrs={'id':'mainContent'}) #td = heading.findParent(name='td') #td.extract() soup = BeautifulSoup('t') body = soup.find(name='body') body.insert(0, story) #td.name = 'div' return soup