__license__ = 'GPL v3' __copyright__ = '2008-2010, Darko Miletic ' ''' b92.net ''' import re from calibre.web.feeds.news import BasicNewsRecipe class B92(BasicNewsRecipe): title = 'B92' __author__ = 'Darko Miletic' description = 'B92 info, najnovije vesti iz Srbije, regiona i sveta' publisher = 'B92' category = 'news, politics, Serbia' oldest_article = 2 max_articles_per_feed = 100 no_stylesheets = True use_embedded_content = False encoding = 'cp1250' language = 'sr' publication_type = 'newsportal' extra_css = ' @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: serif1, serif} ' conversion_options = { 'comment' : description , 'tags' : category , 'publisher' : publisher , 'language' : language , 'linearize_tables' : True } preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] keep_only_tags = [dict(name='table', attrs={'class':'maindocument'})] remove_tags = [ dict(name='ul', attrs={'class':'comment-nav'}) ,dict(name=['embed','link','base'] ) ,dict(name='div', attrs={'class':'udokum'} ) ] feeds = [ (u'Vesti', u'http://www.b92.net/info/rss/vesti.xml') ,(u'Biz' , u'http://www.b92.net/info/rss/biz.xml' ) ] def print_version(self, url): return url + '&version=print' def preprocess_html(self, soup): return self.adeify_images(soup)