diff --git a/recipes/accountancyage.recipe b/recipes/accountancyage.recipe index 2765f4b799..4a73c13e09 100644 --- a/recipes/accountancyage.recipe +++ b/recipes/accountancyage.recipe @@ -7,7 +7,6 @@ www.accountancyage.com ''' from calibre.web.feeds.news import BasicNewsRecipe -from calibre.ebooks.BeautifulSoup import Tag class AccountancyAge(BasicNewsRecipe): title = 'Accountancy Age' @@ -24,36 +23,12 @@ class AccountancyAge(BasicNewsRecipe): lang = 'en' language = 'en' - - html2lrf_options = [ - '--comment', description - , '--category', category - , '--publisher', publisher - ] - - html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' - - keep_only_tags = [dict(name='div', attrs={'class':'bodycol'})] - remove_tags = [dict(name=['embed','object'])] - remove_tags_after = dict(name='div', attrs={'id':'permalink'}) - remove_tags_before = dict(name='div', attrs={'class':'gap6'}) - feeds = [(u'All News', u'http://feeds.accountancyage.com/rss/latest/accountancyage/all')] - def print_version(self, url): - rest, sep, miss = url.rpartition('/') - rr, ssep, artid = rest.rpartition('/') - return u'http://www.accountancyage.com/articles/print/' + artid + keep_only_tags = [ + dict(name='h1'), + dict(attrs={'class':'article_content'}), + ] def get_article_url(self, article): return article.get('guid', None) - - def preprocess_html(self, soup): - soup.html['xml:lang'] = self.lang - soup.html['lang'] = self.lang - mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)]) - mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=UTF-8")]) - soup.head.insert(0,mlang) - soup.head.insert(1,mcharset) - return self.adeify_images(soup) -