#!/usr/bin/env python __license__ = 'GPL v3' __author__ = 'GabrieleMarini, based on Darko Miletic' __copyright__ = '2009, Darko Miletic , Gabriele Marini' __version__ = 'v1.02 Marini Gabriele ' __date__ = '14062010' __description__ = 'Italian daily newspaper' ''' http://www.corrieredellosport.it/ ''' from calibre.web.feeds.news import BasicNewsRecipe class Auto(BasicNewsRecipe): __author__ = 'Gabriele Marini' description = 'Auto and Formula 1' cover_url = 'http://www.auto.it/res/imgs/logo_Auto.png' title = u'Auto' publisher = 'CONTE Editore' category = 'Sport' language = 'it' timefmt = '[%a, %d %b, %Y]' oldest_article = 60 max_articles_per_feed = 30 use_embedded_content = False recursion = 10 remove_javascript = True no_stylesheets = True html2lrf_options = [ '--comment', description, '--category', category, '--publisher', publisher, '--ignore-tables' ] html2epub_options = 'publisher="' + publisher + '"\ncomments="' + \ description + '"\ntags="' + category + '"\nlinearize_tables=True' keep_only_tags = [ dict(name='h2', attrs={'class': ['tit_Article y_Txt']}), dict(name='h2', attrs={'class': ['tit_Article']}), dict(name='div', attrs={'class': ['box_Img newsdet_new ']}), dict(name='div', attrs={'class': ['box_Img newsdet_as ']}), dict(name='table', attrs={'class': ['table_A']}), dict(name='div', attrs={'class': ['txt_Article txtBox_cms']}), dict(name='testoscheda')] feeds = [ (u'Tutte le News', u'http://www.auto.it/rss/articoli.xml'), (u'Prove su Strada', u'http://www.auto.it/rss/prove+6.xml'), (u'Novit\xe0', u'http://www.auto.it/rss/novita+3.xml') ]