#!/usr/bin/env python # -*- coding: utf-8 -*- __license__ = 'GPL v3' __copyright__ = u'2011, Silviu Cotoar\u0103' ''' timesnewroman.ro ''' from calibre.web.feeds.news import BasicNewsRecipe class TimesNewRoman(BasicNewsRecipe): title = u'Times New Roman' __author__ = u'Silviu Cotoar\u0103' description = u'Cotidian independent de umor voluntar' publisher = u'Times New Roman' oldest_article = 25 language = 'ro' max_articles_per_feed = 100 no_stylesheets = True use_embedded_content = False category = 'Ziare,Reviste,Fun' encoding = 'utf-8' cover_url = 'http://www.timesnewroman.ro/templates/TNRV2/images/logo.gif' conversion_options = { 'comments': description, 'tags': category, 'language': language, 'publisher': publisher } keep_only_tags = [ dict(name='div', attrs={'id': 'page'}) ] remove_tags = [ dict(name='p', attrs={'class': ['articleinfo']}), dict(name='div', attrs={'class': ['shareTools']}), dict( name='div', attrs={'class': 'fb_iframe_widget'}), dict(name='div', attrs={'id': 'jc'}) ] remove_tags_after = [ dict(name='div', attrs={'class': 'fb_iframe_widget'}), dict(name='div', attrs={'id': 'jc'}) ] feeds = [ (u'Feeds', u'http://www.timesnewroman.ro/index.php?format=feed&type=rss') ] def preprocess_html(self, soup): return self.adeify_images(soup)