# Last Edit: 2013-08-23 # From: Armin Geller __license__ = 'GPL v3' __copyright__ = '2010, NA' ''' consumerist.com ''' from calibre.web.feeds.news import BasicNewsRecipe class Consumerist(BasicNewsRecipe): title = 'Consumerist' __author__ = 'NA' description = "Consumerist, Shoppers Bite Back." publisher = 'consumerist.com' category = 'news, consumer news, consumer rights' oldest_article = 2 max_articles_per_feed = 100 no_stylesheets = True encoding = 'utf-8' use_embedded_content = False language = 'en' # AGe 2013-08-23 masthead_url = 'http://consumermediallc.files.wordpress.com/2013/02/consumerist.png' extra_css = ''' body{font-family: "Lucida Grande",Helvetica,Arial,sans-serif} img{margin-bottom: 1em} h1{font-family :Arial,Helvetica,sans-serif; font-size:x-large} h2{font-family :Arial,Helvetica,sans-serif; font-size:large} ''' conversion_options = { 'comment': description, 'tags': category, 'publisher': publisher, 'language': language, } remove_attributes = ['width', 'height'] keep_only_tags = dict( name='div', attrs={'class': ['hfeed', ]}) # AGe 2013-08-23 remove_tags = [dict(name='div', attrs={'class': ['navigation', # AGe 2013-08-23 'wpcom-related-posts widget widget_related_posts', # AGe 2013-08-23 'sharedaddy sd-like-enabled sd-sharing-enabled', ]}), # AGe 2013-08-23 # AGe 2013-08-23 dict(name='div', attrs={'id': ['comments', ]}), ] feeds = [(u'Articles', u'http://consumerist.com/index.xml')] def preprocess_html(self, soup): return self.adeify_images(soup)