#!/usr/bin/env python # -*- coding: utf-8 -*- __license__ = 'GPL v3' __copyright__ = u'2011, Silviu Cotoar\u0103' ''' sfin.ro ''' from calibre.web.feeds.news import BasicNewsRecipe class Sfin(BasicNewsRecipe): title = u'S\u0103pt\u0103m\u00e2na Financiar\u0103' __author__ = u'Silviu Cotoar\u0103' description = 'SFIN' publisher = 'SFIN' oldest_article = 5 language = 'ro' max_articles_per_feed = 100 no_stylesheets = True use_embedded_content = False category = 'Ziare,Stiri,Economie,Business' encoding = 'utf-8' cover_url = 'http://img.9am.ro/images/logo_surse/saptamana_financiara.gif' conversion_options = { 'comments': description, 'tags': category, 'language': language, 'publisher': publisher } keep_only_tags = [ dict(name='div', attrs={'class': 'col2ContentLeft'}), dict( name='div', attrs={'id': 'contentArticol'}) ] remove_tags = [ dict(name='div', attrs={'class': ['infoArticol']}), dict(name='div', attrs={'class': ['separator']}), dict(name='div', attrs={ 'class': ['tags']}), dict(name='div', attrs={'id': ['comments']}), dict(name='div', attrs={'class': 'boxForm'}) ] remove_tags_after = [ dict(name='div', attrs={'class': 'tags'}) ] feeds = [ (u'Feeds', u'http://www.sfin.ro/rss') ] def preprocess_html(self, soup): return self.adeify_images(soup)