#!/usr/bin/env python # -*- coding: utf-8 -*- __license__ = 'GPL v3' __copyright__ = u'2011, Silviu Cotoar\u0103' ''' avantaje.ro ''' from calibre.web.feeds.news import BasicNewsRecipe class Avantaje(BasicNewsRecipe): title = u'Avantaje' __author__ = u'Silviu Cotoar\u0103' description = u'' publisher = u'Avantaje' oldest_article = 25 language = 'ro' max_articles_per_feed = 100 no_stylesheets = True use_embedded_content = False category = 'Ziare,Reviste,Stiri' encoding = 'utf-8' cover_url = 'http://www.avantaje.ro/images/default/logo.gif' conversion_options = { 'comments': description, 'tags': category, 'language': language, 'publisher': publisher } keep_only_tags = [ dict(name='div', attrs={'id': 'articol'}), dict(name='div', attrs={ 'class': 'gallery clearfix'}), dict(name='div', attrs={'align': 'justify'}) ] remove_tags = [ dict(name='div', attrs={'id': ['color_sanatate_box']}), dict(name='div', attrs={'class': ['nav']}), dict(name='div', attrs={'class': ['voteaza_art']}), dict(name='div', attrs={'class': ['bookmark']}), dict(name='div', attrs={'class': ['links clearfix']}), dict(name='div', attrs={'class': ['title']}) # noqa ] remove_tags_after = [ dict(name='div', attrs={'class': ['title']}) ] feeds = [ (u'Feeds', u'http://feeds.feedburner.com/Avantaje') ] def preprocess_html(self, soup): return self.adeify_images(soup)