网上有很多关于java连接http server 的文章，也有不少在http server 上通过用户认证后从后台获取网页的帖子。但是，很少有一个对于https server上通过用户验证的介绍。项目需要，我折腾了一整天，终于搞定了，现在来整理一下。概括的说， https 比之 http 只是多了一个加密解密过程，所以https的连接只是比http连接多了一个验证的过程，一旦验证通过，剩下的操作与http上的相同。也就是说，在https server上一旦certificate通过验证，剩下的用户验证就于http server上用户认证一致，概括起来，这整一个过程如下：
1. 建立第一个HttpsURLConnection（URL为登录页面url），  通过https上server certificate 与client的验证   
2. 用POST方式向登录页面传出userID 和 password （具体的变量名要参考单 
    中的名称）。 post操作成功后，取得上面connection的Cookie，通过cookie split出SessionID。
3. 建立第二个HttpsURLConnection（URL为要抓取页面的url）， 通过https上的证书验证
4. 用 URLConnetion.setPropertyValue("Cookie", SessionID),设置第二个URL的cookie，
    确保两个connection属于同一个登入后的Session
5. connection.getInputStream获得目标页面的内容

下面是我用到的一段testing code，是几个独立的片段，已通过测试，有兴趣的朋友改改后就可以用：

try
            {
                                if(protocol.equals("http")){
                                        
                    final HttpURLConnection connection = (HttpURLConnection)iSourceURL.openConnection();
                    connection.connect();
                    stream = connection.getInputStream();
//                    
//                    try{
//                        printIoStream(stream);
//                    }catch(Exception e){
//                        e.printStackTrace();
//                    }
                    
                    modelSource = new StreamSource(stream);
                    
//                    connection.disconnect();
                }
                else if(protocol.equals("https")){
                    try {
                        
                        SSLContext sc = SSLContext.getInstance("SSL");
                        sc.init(null, new TrustManager[] { new iTrustManager() },
                                new java.security.SecureRandom());
                        
//                        url = new URL("https://9.186.10.56:8443/LogonServlet");
                        URL url = new URL(iSourceURL.getProtocol() + "://" + iSourceURL.getHost() + ":" + iSourceURL.getPort() + "/LogonServlet");
                        String strPost = "intranetID=*****&password=******";
                        HttpsURLConnection conn = (HttpsURLConnection) url.openConnection();
                        conn.setSSLSocketFactory(sc.getSocketFactory());
                        conn.setHostnameVerifier(new TrustAnyHostnameVerifier());
                        
                        addProperty(conn);
                        
                        conn.setFollowRedirects(true);
                        conn.setInstanceFollowRedirects(true);
                        conn.setDoOutput(true); // IO input to Server
                        conn.setDoInput(true); // 
                        conn.setUseCaches(false); // obtain the newest info of server
                        conn.setAllowUserInteraction(false);
                        conn.setRequestMethod("POST");
                        
                        conn.getOutputStream().write(strPost.getBytes());
                        conn.getOutputStream().flush();
                        conn.connect();

                        String cookie = conn.getHeaderField("Set-Cookie");
                        
                        String SessionID = getSessionIdFromCookie(cookie);
                        
                        stream = conn.getInputStream();

                        conn.disconnect();
                        
//                        printIoStream(stream);
                
                        final HttpsURLConnection connection = (HttpsURLConnection)iSourceURL.openConnection();
                        connection.setSSLSocketFactory(sc.getSocketFactory());
                        connection.setHostnameVerifier(new TrustAnyHostnameVerifier());
                        connection.setRequestProperty("Cookie", SessionID);
                        connection.connect();

                        stream = connection.getInputStream();
                        modelSource = new StreamSource(stream);
                        
//                        printIoStream(stream);
                        
                    } catch (Exception e) {
                        TMCodePlugin.getInstance().writeToLog(
                                Status.ERROR,"Could not read data via URL(https):"+ iSourceURL, null);
                        e.printStackTrace();
                    }
                }else{
                    TMCodePlugin.getInstance().writeToLog(Status.ERROR, "Protocol illegal: "+iSourceURL, null);
                }
            }
            catch(IOException e)
            {
                TMCodePlugin.getInstance().writeToLog(Status.ERROR, "Could not read data via URL:"+iSourceURL, null);
            }
            catch(IllegalArgumentException e)
            {
                TMCodePlugin.getInstance().writeToLog(Status.ERROR, "Could not read data via URL - illegal argument in URL:"+iSourceURL, null);
            }
        }







/**
     * the protocal of SSL operation on java, visite the HTTPS server via socket
     * @author chaixzh
     */
    class iTrustManager implements X509TrustManager {
        iTrustManager() {
            
        }

        // check client trust status
        public void checkClientTrusted(X509Certificate chain[], String authType)
                throws CertificateException {
            System.out.println("check client trust status");
        }

        // check Server trust status
        public void checkServerTrusted(X509Certificate chain[], String authType)
                throws CertificateException {
            System.out.println("check Server trust status");
        }

        //get those accepted Issuers
        public X509Certificate[] getAcceptedIssuers() {
            return null;
        }
    }
    
    private static class TrustAnyHostnameVerifier implements HostnameVerifier {
        public boolean verify(String hostname, SSLSession session) {
            return true;
        }
    }
    
    /**
     * to split out the SessionID from a Cookie String
     * @param cookie
     * @return
     */
    private String getSessionIdFromCookie(String cookie){
        int index_1 = cookie.indexOf("JSESSIONID=");
        int index_2 = cookie.indexOf(";");
        return cookie.substring(index_1, index_2);
    }
    
    /**
     * just for the sake of debuging
     * @param stream
     * @throws Exception
     */
    private void printIoStream(InputStream stream) throws Exception{
        BufferedInputStream buff = new BufferedInputStream(stream);
        Reader r = new InputStreamReader(buff, "gbk");
        BufferedReader br = new BufferedReader(r);
        StringBuffer strHtml = new StringBuffer("");
        String strLine = null;
        while ((strLine = br.readLine()) != null) {
            strHtml.append(strLine + "\r\n");
        }
        System.out.print(strHtml.toString());
    }
    
    private void addProperty(URLConnection connection){
        connection.addRequestProperty("Accept", "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, application/x-shockwave-flash, application/msword, application/vnd.ms-excel, application/vnd.ms-powerpoint, application/x-silverlight, */*");
        connection.setRequestProperty("Referer", "https://9.186.10.56:8443/index.jsp");
        connection.setRequestProperty("Accept-Language", "zh-cn");
        connection.setRequestProperty("Content-Type", "application/x-www-form-urlencoded");
        connection.setRequestProperty("Accept-Encoding", "gzip, deflate");
        connection.setRequestProperty("User-Agent", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; Foxy/1; .NET CLR 2.0.50727;MEGAUPLOAD 1.0)");
        connection.setRequestProperty("Connection", "Keep-Alive");
        connection.setRequestProperty("Cache-Control", "no-cache");
    }


此外，还有通过socket连接， 或者借助apache 的httpclient连接的，不一而足，大同小异，总体就是通过验证后保持在同一个session中，进而抓取目标网页内容。

cxzforever