from calibre.web.feeds.news import BasicNewsRecipe class APOD(BasicNewsRecipe): title = u'Astronomy Picture of the Day' __author__ = 'Starson17' description = 'Astronomy Pictures' language = 'en' use_embedded_content = False no_stylesheets = True cover_url = 'http://apod.nasa.gov/apod/image/1003/m78_torregrosa.jpg' remove_javascript = True recursions = 0 oldest_article = 14 remove_attributes = ['onmouseover', 'onmouseout'] feeds = [ (u'Astronomy Picture of the Day', u'http://apod.nasa.gov/apod.rss') ] extra_css = ''' h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;} h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;} p{font-family:Arial,Helvetica,sans-serif;font-size:small;} body{font-family:Helvetica,Arial,sans-serif;font-size:small;} ''' def postprocess_html(self, soup, first_fetch): center_tags = soup.findAll(['center']) p_tags = soup.findAll(['p']) last_center = center_tags[-1:] last_center[0].extract() first_p = p_tags[:1] for tag in first_p: tag.extract() last2_p = p_tags[-2:] for tag in last2_p: tag.extract() return soup