#!/usr/bin/env python __license__ = 'GPL v3' __copyright__ = '2009, Darko Miletic ' ''' www.livemint.com ''' from calibre.web.feeds.news import BasicNewsRecipe class Edgesingapore(BasicNewsRecipe): title = 'The Edge Singapore' __author__ = 'Darko Miletic' description = 'Financial news from Singapore' publisher = 'The Edge Singapore' category = 'news, finances, singapore' language = 'en' lang = 'en_SG' oldest_article = 15 max_articles_per_feed = 100 no_stylesheets = True encoding = 'utf-8' use_embedded_content = False extra_css = ' .contentheading{font-size: x-large} .small{font-size: small} .createdate{font-size: small; font-weight: bold} ' conversion_options = { 'comment': description, 'tags': category, 'publisher': publisher, 'author': publisher, 'language': lang, 'pretty_print': True, 'linearize_tables': True } remove_tags = [ dict(name=['object', 'link', 'embed', 'form', 'iframe']), dict(name='div', attrs={ 'id': 'toolbar-article'}), dict(name='div', attrs={'class': 'backtotop'}), dict(name='img', attrs={'alt': 'Print'}) ] remove_tags_after = dict(name='div', attrs={'class': 'backtotop'}) feeds = [(u'Articles', u'http://feeds.feedburner.com/edgesg')] def print_version(self, url): return url + '?tmpl=component&print=1' def preprocess_html(self, soup): attribs = ['style', 'font', 'valign', 'colspan', 'width', 'height', 'rowspan', 'summary', 'align', 'cellspacing', 'cellpadding', 'frames', 'rules', 'border' # noqa ] for item in soup.body.findAll(name=['table', 'td', 'tr', 'th', 'caption', 'thead', 'tfoot', 'tbody', 'colgroup', 'col']): item.name = 'div' for attrib in attribs: item[attrib] = '' del item[attrib] return self.adeify_images(soup)