public List<Newsitem> parseContent(String content) throws Exception { List<Newsitem> newsitems = new ArrayList<Newsitem>(); Tag newsDiv = this.extractTagByClassName(this.stripHtmlComments(content), "box_news"); NodeList nodes = this.extractTagsByClassName(newsDiv.toHtml(), "subItem"); for (int i = 0; i < nodes.size(); i++) { NewsitemImpl newsitem = new NewsitemImpl(); Tag itemTable = (Tag) nodes.elementAt(i); Tag titleTag = this.extractTagByClassName(itemTable.toHtml(), "subItemtitle"); newsitem.setTitle(titleTag.toPlainTextString()); Node descriptionSpan = titleTag.getNextSibling().getNextSibling().getNextSibling().getNextSibling(); newsitem.setDescription( descriptionSpan .toPlainTextString() .replaceAll("[^\\u0000-\\u00FF]", " ") .replace(" Read More...", "") .trim()); Tag linkTag = (Tag) extractLinks(itemTable.toHtml(), "/index.php.*").elementAt(0); newsitem.setUrl(URL_PREFIX + linkTag.getAttribute("href")); newsitems.add(newsitem); } return newsitems; }