导入了htmlparser.jar包
再通过一下代码实现了 内容的获取
Parser parser = Parser.createParser(str1, "utf-8");
// 获取span 所有
NodeList spanend = parser
.extractAllNodesThatMatch(filter_spanlist);
// System.err.println("============================"+spanend.size());//获取节点的个数
// 获取内容
String s = spanend.toHtml().replaceAll(" ", "")
.replace("\n", "").replace("\t", "");
System.out.println(s);
Pattern pattern = Pattern.compile(">(.*?)");
Matcher matcher = pattern.matcher(s);
String s1 = "";
while (matcher.find()) {
s1 = matcher.group(1);
}