1#!/usr/local/bin/python3.8 2 3__license__ = 'GPL v3' 4__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>' 5 6''' 7nacional.hr 8''' 9 10import re 11from calibre.web.feeds.recipes import BasicNewsRecipe 12from calibre.ebooks.BeautifulSoup import Tag 13 14 15def new_tag(soup, name, attrs=()): 16 impl = getattr(soup, 'new_tag', None) 17 if impl is not None: 18 return impl(name, attrs=dict(attrs)) 19 return Tag(soup, name, attrs=attrs or None) 20 21 22class NacionalCro(BasicNewsRecipe): 23 title = 'Nacional - Hr' 24 __author__ = 'Darko Miletic' 25 description = "news from Croatia" 26 publisher = 'Nacional.hr' 27 category = 'news, politics, Croatia' 28 oldest_article = 2 29 max_articles_per_feed = 100 30 delay = 4 31 no_stylesheets = True 32 encoding = 'utf-8' 33 use_embedded_content = False 34 language = 'hr' 35 36 lang = 'hr-HR' 37 direction = 'ltr' 38 39 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 40 41 conversion_options = { 42 'comment': description, 'tags': category, 'publisher': publisher, 'language': lang, 'pretty_print': True 43 } 44 45 preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] 46 47 remove_tags = [dict(name=['object', 'link', 'embed'])] 48 49 feeds = [(u'Najnovije Vijesti', u'http://www.nacional.hr/rss')] 50 51 def preprocess_html(self, soup): 52 soup.html['lang'] = self.lang 53 soup.html['dir'] = self.direction 54 mlang = new_tag(soup, 'meta', [ 55 ("http-equiv", "Content-Language"), ("content", self.lang)]) 56 mcharset = new_tag(soup, 'meta', [ 57 ("http-equiv", "Content-Type"), ("content", "text/html; charset=UTF-8")]) 58 soup.head.insert(0, mlang) 59 soup.head.insert(1, mcharset) 60 for item in soup.findAll(style=True): 61 del item['style'] 62 return soup 63 64 def print_version(self, url): 65 rest, sep, disc = url.rpartition('/') 66 return rest.replace('/clanak/', '/clanak/print/') 67