t

from calibre.web.feeds.news import BasicNewsRecipe from calibre.ebooks.BeautifulSoup import BeautifulSoup class NewYorkTimesBookReview(BasicNewsRecipe): title = u'New York Times Book Review' language = 'en' __author__ = 'Krittika Goyal' oldest_article = 8 #days max_articles_per_feed = 1000 recursions = 2 #encoding = 'latin1' remove_stylesheets = True #remove_tags_before = dict(name='h1', attrs={'class':'heading'}) remove_tags_after = dict(name='div', attrs={'id':'authorId'}) remove_tags = [ dict(name='iframe'), dict(name=['div', 'a'], attrs={'class':['enlargeThis', 'jumpLink']}), dict(name='div', attrs={'id':['sidebarArticles', 'toolsRight']}), #dict(name='ul', attrs={'class':'article-tools'}), #dict(name='ul', attrs={'class':'articleTools'}), ] match_regexps = [ r'http://www.nytimes.com/.+pagewanted=[2-9]+' ] feeds = [ ('New York Times Sunday Book Review', 'http://feeds.nytimes.com/nyt/rss/SundayBookReview'), ] def preprocess_html(self, soup): story = soup.find(name='div', attrs={'id':'article'}) #td = heading.findParent(name='td') #td.extract() soup = BeautifulSoup('t') body = soup.find(name='body') body.insert(0, story) #for x in soup.findAll(name='p', text=lambda x:x and '-->' in x): #p = x.findParent('p') #if p is not None: #p.extract() return soup def postprocess_html(self, soup, first): for div in soup.findAll(id='pageLinks'): div.extract() if not first: h1 = soup.find('h1') if h1 is not None: h1.extract() t = soup.find(attrs={'class':'timestamp'}) if t is not None: t.extract() return soup