#!/usr/bin/env python __author__ = 'Darko Spasovski' __license__ = 'GPL v3' __copyright__ = '2011, Darko Spasovski ' ''' utrinski.com.mk ''' import re import datetime from calibre.web.feeds.news import BasicNewsRecipe from calibre.ebooks.BeautifulSoup import BeautifulSoup from calibre import browser class UtrinskiVesnik(BasicNewsRecipe): INDEX = 'http://www.utrinski.com.mk/' title = 'Utrinski Vesnik' description = 'Daily Macedonian newspaper' masthead_url = 'http://www.utrinski.com.mk/images/LogoTop.jpg' language = 'mk' remove_javascript = True publication_type = 'newspaper' category = 'news, Macedonia' max_articles_per_feed = 100 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'