__license__ = 'GPL v3' __copyright__ = '2011, Darko Miletic ' ''' www.financialsense.com ''' from calibre.web.feeds.news import BasicNewsRecipe class FinancialSense(BasicNewsRecipe): title = 'Financial Sense' __author__ = 'Darko Miletic' description = 'Uncommon News & Views for the Wise Investor' publisher = 'Financial Sense' category = 'news, finances, politics, USA' oldest_article = 2 max_articles_per_feed = 200 no_stylesheets = True encoding = 'utf8' use_embedded_content = False language = 'en' remove_empty_feeds = True publication_type = 'newsportal' masthead_url = 'http://www.financialsense.com/sites/default/files/logo.jpg' extra_css = """ body{font-family: Arial,"Helvetica Neue",Helvetica,sans-serif } img{margin-bottom: 0.4em; display:block} h2{color: gray} .name{margin-right: 5em} """ conversion_options = { 'comment': description, 'tags': category, 'publisher': publisher, 'language': language } remove_tags = [ dict(name=['meta', 'link', 'base', 'object', 'embed', 'iframe'])] remove_tags_after = dict(attrs={'class': 'vcard'}) keep_only_tags = [ dict(attrs={'class': ['title', 'post-meta', 'content', 'item-title', 'vcard']})] remove_attributes = ['lang', 'type'] feeds = [(u'Articles', u'http://feeds.feedburner.com/fso')] def preprocess_html(self, soup): for item in soup.findAll(style=True): del item['style'] for item in soup.findAll('a'): limg = item.find('img') if item.string is not None: str = item.string item.replaceWith(str) else: if limg: item.name = 'div' item.attrs = [] else: str = self.tag_to_string(item) item.replaceWith(str) for item in soup.findAll('img', alt=False): item['alt'] = 'image' return soup