__license__ = 'GPL v3' __copyright__ = '2009-2010, Darko Miletic ' ''' 24sata.rs ''' import re from calibre.web.feeds.recipes import BasicNewsRecipe class Ser24Sata(BasicNewsRecipe): title = '24 Sata - Sr' __author__ = 'Darko Miletic' description = '24 sata portal vesti iz Srbije' publisher = 'Ringier d.o.o.' category = 'news, politics, entertainment, Serbia' oldest_article = 2 max_articles_per_feed = 100 no_stylesheets = True encoding = 'utf-8' use_embedded_content = False language = 'sr' publication_type = 'newspaper' 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')] feeds = [(u'Vesti Dana', u'http://www.24sata.rs/rss.php')] def preprocess_html(self, soup): return self.adeify_images(soup) def print_version(self, url): article = url.partition('#')[0] article_id = article.partition('id=')[2] return 'http://www.24sata.rs/_print.php?id=' + article_id