#!/usr/bin/env python __license__ = 'GPL v3' __copyright__ = '2009, Darko Miletic ' ''' 24sata.hr ''' import re from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.ebooks.BeautifulSoup import Tag def new_tag(soup, name, attrs=()): impl = getattr(soup, 'new_tag', None) if impl is not None: return impl(name, attrs=dict(attrs)) return Tag(soup, name, attrs=attrs or None) class Cro24Sata(BasicNewsRecipe): title = '24 Sata - Hr' __author__ = 'Darko Miletic' description = "News Portal from Croatia" publisher = '24sata.hr' category = 'news, politics, Croatia' oldest_article = 2 max_articles_per_feed = 100 delay = 4 no_stylesheets = True encoding = 'utf-8' use_embedded_content = False language = 'hr' lang = 'hr-HR' 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}' # noqa conversion_options = { 'comment': description, 'tags': category, 'publisher': publisher, 'language': lang, 'pretty_print': True } preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] remove_tags = [ dict(name=['object', 'link', 'embed']), dict( name='table', attrs={'class': 'enumbox'}) ] feeds = [(u'Najnovije Vijesti', u'http://www.24sata.hr/index.php?cmd=show_rss&action=novo')] def preprocess_html(self, soup): soup.html['lang'] = self.lang mlang = new_tag(soup, 'meta', [ ("http-equiv", "Content-Language"), ("content", self.lang)]) mcharset = new_tag(soup, 'meta', [ ("http-equiv", "Content-Type"), ("content", "text/html; charset=UTF-8")]) soup.head.insert(0, mlang) soup.head.insert(1, mcharset) for item in soup.findAll(style=True): del item['style'] return soup def print_version(self, url): return url + '&action=ispis'