t

from calibre.web.feeds.news import BasicNewsRecipe from calibre.ebooks.BeautifulSoup import BeautifulSoup class TimesOfIndia(BasicNewsRecipe): title = u'Times of India' language = 'en_IN' __author__ = 'Krittika Goyal' oldest_article = 1 #days max_articles_per_feed = 25 remove_stylesheets = True remove_tags = [ dict(name='iframe'), dict(name='td', attrs={'class':'newptool1'}), dict(name='div', attrs={'id':'newptool'}), dict(name='ul', attrs={'class':'newtabcontent_tabs_new'}), dict(name='b', text='Topics'), dict(name='span', text=':'), ] feeds = [ ('Top Stories', 'http://timesofindia.indiatimes.com/rssfeedstopstories.cms'), ('India', 'http://timesofindia.indiatimes.com/rssfeeds/-2128936835.cms'), ('World', 'http://timesofindia.indiatimes.com/rssfeeds/296589292.cms'), ('Mumbai', 'http://timesofindia.indiatimes.com/rssfeeds/-2128838597.cms'), ('Entertainment', 'http://timesofindia.indiatimes.com/rssfeeds/1081479906.cms'), ('Cricket', 'http://timesofindia.indiatimes.com/rssfeeds/4719161.cms'), ('Sunday TOI', 'http://timesofindia.indiatimes.com/rssfeeds/1945062111.cms'), ('Life and Style', 'http://timesofindia.indiatimes.com/rssfeeds/2886704.cms'), ('Business', 'http://timesofindia.indiatimes.com/rssfeeds/1898055.cms'), ('Mad Mad World', 'http://timesofindia.indiatimes.com/rssfeeds/2178430.cms'), ('Most Read', 'http://timesofindia.indiatimes.com/rssfeedmostread.cms') ] def preprocess_html(self, soup): heading = soup.find(name='h1', attrs={'class':'heading'}) td = heading.findParent(name='td') td.extract() soup = BeautifulSoup('t') body = soup.find(name='body') body.insert(0, td) td.name = 'div' return soup