HtmlCleaner ,Html文档解析器

/**
 * HtmlCleaner xpath解析html获取值
 */
private String analyzeLoginResult(String html) {
String result = "";
try {
String xpath = "//div[@class='success']/h2/text()"; // 获取class=success的div下，h2标签的内容
// html内容
// <div id="msg" class="success">
// <h2>Log In Successful</h2>
// <p>You have successfully logged into the Central Authentication Service.</p>
// <p>For security reasons, please Log Out and Exit your web browser when you are done accessing services that require authentication!</p>
// </div>


// 中文结果
// <div id="msg" class="success">
// <h2>登录成功</h2>


HtmlCleaner hc = new HtmlCleaner();
TagNode tn = hc.clean(html);
Object[] objarr = tn.evaluateXPath(xpath);


if (objarr != null && objarr.length > 0) {
result = objarr[0] + "";
}
} catch (XPatherException e) {
e.printStackTrace();
}
return result;
}