__license__ = 'GPL v3' __copyright__ = '2012-2015, Eddie Lau' from calibre.web.feeds.news import BasicNewsRecipe class AdvancedUserRecipeHouseNews(BasicNewsRecipe): title = u'The House News Bloggers 主場博客' __author__ = 'Eddie Lau' publisher = 'The House News Bloggers' oldest_article = 1 max_articles_per_feed = 100 auto_cleanup = False no_stylesheets = True language = 'zh' encoding = 'utf-8' description = 'http://thehousenewsbloggers.net' category = 'Chinese, Blogs, Opinion, News, Hong Kong' masthead_url = 'http://thehousenewsbloggers.files.wordpress.com/2014/09/screen-shot-2014-09-11-at-8-55-13.png' extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px; max-height:90%;} p[class=date] {font-size:50%;} div[class=author] {font-size:75%;} p[class=caption] {font-size:50%;}' # noqa feeds = [(u'Latest', u'http://thehousenewsbloggers.net/feed/')] keep_only_tags = [dict(name='h1', attrs={'class': ['title']}), dict(name='span', attrs={'class': ['author vcard']}), dict(name='time', attrs={'class': ['entry-date']}), dict(name='section', attrs={'class': ['entry']})] remove_tags = [dict(name='div', attrs={'id': ['jp-post-flair']})] def populate_article_metadata(self, article, soup, first): if first and hasattr(self, 'add_toc_thumbnail'): picdiv = soup.find('img') if picdiv is not None: self.add_toc_thumbnail(article, picdiv['src'])