#!/usr/bin/env python # -*- coding: utf-8 -*- __license__ = 'GPL v3' __copyright__ = u'2011, Silviu Cotoar\u0103' ''' bucataras.ro ''' from calibre.web.feeds.news import BasicNewsRecipe class Bucataras(BasicNewsRecipe): title = u'Bucataras' __author__ = u'Silviu Cotoar\u0103' description = '' publisher = 'Bucataras' oldest_article = 5 language = 'ro' max_articles_per_feed = 100 no_stylesheets = True use_embedded_content = False category = 'Ziare,Bucatarie,Retete' encoding = 'utf-8' cover_url = 'http://www.bucataras.ro/templates/default/images/pink/logo.jpg' conversion_options = { 'comments': description, 'tags': category, 'language': language, 'publisher': publisher } keep_only_tags = [ dict(name='h1', attrs={'class': 'titlu'}), dict(name='div', attrs={ 'class': 'contentL'}), dict(name='div', attrs={'class': 'contentBottom'}) ] remove_tags = [ dict(name='div', attrs={'class': ['sociale']}), dict(name='div', attrs={'class': ['contentR']}), dict( name='a', attrs={'target': ['_self']}), dict(name='div', attrs={'class': ['comentarii']}) ] remove_tags_after = [ dict(name='div', attrs={'class': ['comentarii']}) ] feeds = [ (u'Feeds', u'http://www.bucataras.ro/rss/retete/') ] def preprocess_html(self, soup): return self.adeify_images(soup)