#!/usr/bin/env python # -*- coding: utf-8 -*- __license__ = 'GPL v3' __copyright__ = u'2011, Silviu Cotoar\u0103' ''' financiarul.com ''' from calibre.web.feeds.news import BasicNewsRecipe class Financiarul(BasicNewsRecipe): title = u'Financiarul' __author__ = u'Silviu Cotoar\u0103' description = u'FIN.ro' publisher = u'Financiarul' oldest_article = 25 language = 'ro' max_articles_per_feed = 100 no_stylesheets = True use_embedded_content = False category = 'Ziare,Stiri' encoding = 'utf-8' cover_url = 'http://www.financiarul.com/templates/default/images/logo.png' conversion_options = { 'comments': description, 'tags': category, 'language': language, 'publisher': publisher } keep_only_tags = [ dict(name='div', attrs={'class': 'col2ContentLeftL'}) ] remove_tags = [ dict(name='div', attrs={'class': ['infoArticol']}), dict(name='ul', attrs={'class': 'navSectiuni'}), dict(name='div', attrs={'class': 'separator separatorTop'}), dict(name='div', attrs={'class': 'infoArticol infoArticolBottom'}), dict(name='ul', attrs={'class': ['related']}), dict(name='div', attrs={'class': ['slot panel300 panelGri300 panelGri300s panelGri300sm']}) # noqa ] remove_tags_after = [ dict(name='ul', attrs={'class': ['related']}) ] feeds = [ (u'Feeds', u'http://www.financiarul.com/rss') ] def preprocess_html(self, soup): return self.adeify_images(soup)