#!/usr/bin/env python # -*- coding: utf-8 -*- __license__ = 'GPL v3' __copyright__ = u'2011, Silviu Cotoar\u0103' ''' tabu.ro ''' from calibre.web.feeds.news import BasicNewsRecipe class TabuRo(BasicNewsRecipe): title = u'Tabu' __author__ = u'Silviu Cotoar\u0103' description = 'Cel mai curajos site de femei' publisher = 'Tabu' oldest_article = 5 language = 'ro' max_articles_per_feed = 100 no_stylesheets = True use_embedded_content = False category = 'Ziare,Reviste,Femei' encoding = 'utf-8' cover_url = 'http://www.tabu.ro/img/tabu-logo2.png' conversion_options = { 'comments': description, 'tags': category, 'language': language, 'publisher': publisher } keep_only_tags = [ dict(name='h2', attrs={'class': 'articol_titlu'}), dict(name='div', attrs={'class': 'poza_articol_featured'}), dict(name='div', attrs={'class': 'articol_text'}) ] remove_tags = [ dict(name='div', attrs={'class': 'asemanatoare'}), dict(name='div', attrs={'class': 'social'}) ] remove_tags_after = [ dict(name='div', attrs={'class': 'social'}), dict(name='div', attrs={'id': 'comments'}), dict(name='div', attrs={'class': 'asemanatoare'}) ] feeds = [ (u'Feeds', u'http://www.tabu.ro/feed/') ] def preprocess_html(self, soup): return self.adeify_images(soup)