#!/usr/bin/env python2 __license__ = 'GPL v3' __copyright__ = '2012, faber1971' __version__ = 'v1.01' __date__ = '29, May 2012' from calibre.web.feeds.news import BasicNewsRecipe class AdvancedUserRecipe1324038402(BasicNewsRecipe): title = u'La Gazzetta del Mezzogiorno' language = 'it' __author__ = 'faber1971' description = 'Italian regional magazine - Apulia' oldest_article = 1 max_articles_per_feed = 100 auto_cleanup = False masthead_url = 'http://www.lagazzettadelmezzogiorno.it/images/GdM_Nuova_Testata_Interna.gif' feeds = [ (u'Home page', u'http://www.lagazzettadelmezzogiorno.it/rss.php?IDCategoria=1')] remove_tags = [ dict(name='table', attrs={'width': '100%'}), dict(name='div', attrs={'style': [ 'text-align:center; padding:5px; background-color:#B51C1F;', 'float:right; margin:0px 0px 4px 7px; border-left:2px dotted #B0CBE6; width:200px;']}), dict(name='td', attrs={'colspan': '5'}), dict(name='td', attrs={'width': '300'}) ] def get_article_url(self, article): link = BasicNewsRecipe.get_article_url(self, article) if link.split('/')[-1] == "story01.htm": link = link.split('/')[-2] a = ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'I', 'L', 'N', 'S'] b = ['0', '.', '/', '?', '-', '=', '&', '_', 'http://', '.com', 'www.'] for i in range(0, len(a)): link = link.replace('0' + a[-i], b[-i]) return link remove_javascript = True conversion_options = {'linearize_tables': True} extra_css = ''' .font7 {color: #555555; font-family: "Verdana"; font-size: 23px; font-weight: 700; height: auto; text-align: left; text-decoration: none; } .font16 { color: #000000; font-family: "Arial"; font-size: 14px; font-weight: 400; text-align: left; } '''