#!/usr/bin/env python from __future__ import print_function __author__ = 'Darko Spasovski' __license__ = 'GPL v3' __copyright__ = '2011, Darko Spasovski ' ''' dnevnik.com.mk ''' import re import datetime from calibre.web.feeds.news import BasicNewsRecipe from calibre import browser from calibre.ebooks.BeautifulSoup import BeautifulSoup class Dnevnik(BasicNewsRecipe): INDEX = 'http://www.dnevnik.com.mk' __author__ = 'Darko Spasovski' title = 'Dnevnik - mk' description = 'Daily Macedonian newspaper' masthead_url = 'http://www.dnevnik.com.mk/images/re-logo.gif' language = 'mk' publication_type = 'newspaper' category = 'news, Macedonia' max_articles_per_feed = 100 remove_javascript = True no_stylesheets = True use_embedded_content = False preprocess_regexps = [(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in [ # Remove anything before the start of the article. (r'', lambda match: ''), # Remove anything after the end of the article. (r'