#!/usr/bin/env python # -*- coding: utf-8 -*- __license__ = 'GPL v3' __copyright__ = u'2011, Silviu Cotoar\u0103' ''' natgeo.ro ''' from calibre.web.feeds.news import BasicNewsRecipe class NationalGeoRo(BasicNewsRecipe): title = u'National Geographic RO' __author__ = u'Silviu Cotoar\u0103' description = u'S\u0103 avem grij\u0103 de planet\u0103' publisher = 'National Geographic' oldest_article = 35 language = 'ro' max_articles_per_feed = 100 no_stylesheets = True use_embedded_content = False category = 'Reviste' encoding = 'utf-8' cover_url = 'http://wiki.benecke.com/images/c/c4/NatGeographic_Logo.jpg' conversion_options = { 'comments': description, 'tags': category, 'language': language, 'publisher': publisher } keep_only_tags = [ dict(name='h2', attrs={'class': 'contentheading clearfix'}), dict( name='div', attrs={'class': 'article-content'}) ] remove_tags = [ dict(name='div', attrs={'class': ['phocagallery']}) ] feeds = [ (u'Feeds', u'http://www.natgeo.ro/index.php?format=feed&type=rss') ] def preprocess_html(self, soup): return self.adeify_images(soup)