# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai from __future__ import with_statement __license__ = 'GPL v3' __copyright__ = '2009, Kovid Goyal ' __docformat__ = 'restructuredtext en' ''' Modified by Tony Stegall on 10/10/10 to include function to grab print version of articles ''' from datetime import date from calibre.web.feeds.news import BasicNewsRecipe ''' added by Tony Stegall ''' ####################################################### from calibre.ptempfile import PersistentTemporaryFile ####################################################### class AdvancedUserRecipe1249039563(BasicNewsRecipe): title = u'De Volkskrant' __author__ = 'acidzebra' oldest_article = 7 max_articles_per_feed = 100 no_stylesheets = True language = 'nl' extra_css = ''' body{font-family:Arial,Helvetica,sans-serif;font-size:small;} h1{font-size:large;} ''' ''' Change Log: Date: 10/10/10 - Modified code to include obfuscated to get the print version Author: Tony Stegall Date: 01/01/11 - Modified for better results around December/January. Author: Martin Tarenskeen ''' ####################################################################################################### temp_files = [] articles_are_obfuscated = True def get_obfuscated_article(self, url): br = self.get_browser() print 'THE CURRENT URL IS: ', url br.open(url) year = date.today().year try: response = br.follow_link(url_regex='.*?(%d)(\\/)(article)(\\/)(print)(\\/)'%year, nr = 0) html = response.read() except: year = year-1 try: response = br.follow_link(url_regex='.*?(%d)(\\/)(article)(\\/)(print)(\\/)'%year, nr = 0) html = response.read() except: response = br.open(url) html = response.read() self.temp_files.append(PersistentTemporaryFile('_fa.html')) self.temp_files[-1].write(html) self.temp_files[-1].close() return self.temp_files[-1].name ############################################################################################################### ''' Change Log: Date: 10/15/2010 Feeds updated by Martin Tarenskeen ''' feeds = [ (u'Laatste Nieuws', u'http://www.volkskrant.nl/rss/laatstenieuws.rss'), (u'Binnenland', u'http://www.volkskrant.nl/rss/nederland.rss'), (u'Buitenland', u'http://www.volkskrant.nl/rss/internationaal.rss'), (u'Economie', u'http://www.volkskrant.nl/rss/economie.rss'), (u'Sport', u'http://www.volkskrant.nl/rss/sport.rss'), (u'Cultuur', u'http://www.volkskrant.nl/rss/kunst.rss'), (u'Gezondheid & Wetenschap', u'http://www.volkskrant.nl/rss/wetenschap.rss'), (u'Internet & Media', u'http://www.volkskrant.nl/rss/media.rss') ]