jsoup 就是用来处理 html dom的一个组件。其与dom4j、xstream等xml dom组件类似。
jsoup加载完html文本生成document对象之后,用来操作dom的通用操作就可以使用了。如:getElementById、getElementsByName等。
代码:加载html文本为dom对象,获取id为username的元素的属性value的值
Document doc = Jsoup.parse(htmlString); String username = doc.getElementById("username").attr("value");
另附上 httpclient jar包 jsoup jar包
httpclient设置头部参数,以及获取头部参数,设置消息体参数的代码:
httpclient设置头部参数
/** * 设置请求头 * @param post */ private static void setHeaders(HttpPost post) { post.setHeader("Accept", "text/html, application/xhtml+xml, */*"); post.setHeader("Accept-Language", "zh-CN"); post.setHeader("User-Agent", "Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko"); post.setHeader("Content-Type", "application/x-www-form-urlencoded"); post.setHeader("Accept-Encoding", "gzip, deflate"); post.setHeader("DNT", "1"); post.setHeader("Connection", "Keep-Alive"); post.setHeader("Cache-Control", "no-cache"); post.setHeader("Cookie", Cookie); } /** * 设置请求头 * @param get */ private static void setHeaders(HttpGet get) { get.setHeader("Accept", "text/html, application/xhtml+xml, */*"); get.setHeader("Accept-Language", "zh-CN"); get.setHeader("User-Agent", "Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko"); get.setHeader("Content-Type", "application/x-www-form-urlencoded"); get.setHeader("Accept-Encoding", "gzip, deflate"); get.setHeader("DNT", "1"); get.setHeader("Connection", "Keep-Alive"); get.setHeader("Cache-Control", "no-cache"); get.setHeader("Cookie", Cookie); }
httpclient发送get请求
private static String getSessionId() throws IOException, Exception { HttpClient client = new DefaultHttpClient(); HttpGet get = new HttpGet("http://url/"); HttpResponse responsex = client.execute(get); Header[] headers = responsex.getAllHeaders(); for (int i = 0; i < headers.length; i++) { Header header = headers[i]; String name = header.getName(); String value = header.getValue(); if("Set-Cookie".equals(name)){ String[] vals = value.split(";"); for (int j = 0; j < vals.length; j++) { String val = vals[j]; if(val.contains("ASP.NET_SessionId")){ Cookie = val; } } } } if(!responsex.getStatusLine().toString().contains("HTTP/1.1 200 OK")){ throw new RuntimeException("某某失败"); } HttpEntity entityx = responsex.getEntity(); String entityMsgx = EntityUtils.toString(entityx); //解析html dom 得到输入参数 Document doc = Jsoup.parse(entityMsgx); resetAllParams(); __VIEWSTATE = doc.getElementById("__VIEWSTATE").attr("value"); __EVENTVALIDATION = doc.getElementById("__EVENTVALIDATION").attr("value"); isOpen = doc.getElementById("isOpen").attr("value"); btlogin = doc.getElementById("btlogin").attr("value"); return Cookie; }
发送post请求
/** * 登录 * @param username * @param password * @throws IOException * @throws Exception */ public static boolean login(String username, String password) throws IOException, Exception { //先访问首页获取sessionid getSessionId(); //执行登陆过程 HttpClient client = new DefaultHttpClient(); HttpPost post = new HttpPost("http://loginurl"); post.setHeader("Referer", "http://loginurl"); setHeaders(post); // 登录表单的信息 Listqparams = new ArrayList (); qparams.add(new BasicNameValuePair("__VIEWSTATE", __VIEWSTATE)); qparams.add(new BasicNameValuePair("__EVENTVALIDATION", __EVENTVALIDATION)); qparams.add(new BasicNameValuePair("isOpen", isOpen)); qparams.add(new BasicNameValuePair("Text1", username)); qparams.add(new BasicNameValuePair("Password1", password)); qparams.add(new BasicNameValuePair("btlogin", btlogin)); UrlEncodedFormEntity params = new UrlEncodedFormEntity(qparams, "utf-8"); post.setEntity(params); // 相当于按了下确定登录的按钮,也就是浏览器调转了 HttpResponse response = client.execute(post); if(!response.getStatusLine().toString().contains("HTTP/1.1 200 OK")){ throw new RuntimeException("离校系统登陆失败"); } HttpEntity entity = response.getEntity(); String entityMsg = EntityUtils.toString(entity); if(entityMsg.contains("该用户不存在或用户名密码错误")){ throw new RuntimeException("该用户不存在或用户名密码错误"); } return true; }