httpclient 模拟登录 及线程安全

//登录csdn
//        String uri = "https://passport.csdn.net/account/login";
//        String html = HttpUtil.DownHtml(uri);
        
//        <input type="hidden" name="lt" value="LT-207426-moK0sGnfCa9aqijJKeLYhFDYiEe2id" />
//         <input type="hidden" name="execution" value="e1s1" /> 
//        <input type="hidden" name="_eventId" value="submit" /> 
        
//        String lt = getGroup_1("name=\"lt\" value=\"(.*?)\"", html);
//        String execution = getGroup_1("name=\"execution\" value=\"(.*?)\"", html);
//        System.out.println(lt + "\t" + execution);
//        
//        //构建cookie
//        Map<String, String> params = new HashMap<String,String>();
//        params.put("_eventId", "submit");
//        params.put("execution", execution);
//        params.put("lt", lt);
//        params.put("password", "biantai123");
//        params.put("username", "tidal.melon@gmail.com");
//        
//        HttpUtil.Post(uri, params);









模拟登录流程：

1 请求host_url

2 从host_url中解析出 隐藏表单 的值 添加到POST_DATA中

3 添加账户，密码到POST_DATA中

4 编码后，发送POST请求
    要点1：java下，HttpClient必须是单例模式
    要点2：post的url可能跟登录界面的url不同。post_url可以从host_url的返回结果中得到（具体情况自行分析）
    
5 通过firefox，chrome等相关插件验证登录完成

6 测试需要登录的采集任务




登录插件工厂设计：

设计目标（粗略）：

接口设计：

public interface ILogin {
    //HttpClient 
    public HttpClient login(String usr, String pwd, Map<k, v> metadata);
}


example:

public class BaiduLogin implements ILogin {

    @Override
    public HttpClient login(String usr, String pwd, Map<k, v> metadata) {
        System.out.println("萤火虫在飞");
    }
    
}

//采用线程安全的方式返回HttpClient。。。返回HttpClient  或者 返回cookie  具体待定
public static synchronized HttpClient getSaveHttpClient(){  
        if(mHttpClient == null){  
            HttpParams params = new BasicHttpParams();  
            //设置基本参数  
            HttpProtocolParams.setVersion(params, HttpVersion.HTTP_1_1);  
            HttpProtocolParams.setContentCharset(params, CHARSET);  
            HttpProtocolParams.setUseExpectContinue(params, true);  
            //超时设置  
            /*从连接池中取连接的超时时间*/  
            ConnManagerParams.setTimeout(params, 1000);  
            /*连接超时*/  
            HttpConnectionParams.setConnectionTimeout(params, 2000);  
            /*请求超时*/  
            HttpConnectionParams.setSoTimeout(params, 4000);  
            //设置HttpClient支持HTTp和HTTPS两种模式  
            SchemeRegistry schReg = new SchemeRegistry();  
            schReg.register(new Scheme("http", PlainSocketFactory.getSocketFactory(), 80));  
            schReg.register(new Scheme("https", SSLSocketFactory.getSocketFactory(), 443));  
            //使用线程安全的连接管理来创建HttpClient  
            ClientConnectionManager conMgr = new ThreadSafeClientConnManager(params, schReg);  
            mHttpClient = new DefaultHttpClient(conMgr, params);  
        }  
        return mHttpClient;  
    }  






HttpClient(http://hc.apache.org/httpcomponents-client-ga/)自动管理了cookie信息，
只需要先传递登录信息执行登录过程，然后直接访问想要的页面，跟访问一个普通的页面没有任何区别，
因为HttpClient已经帮忙发送了Cookie信息。下面的例子实现了这样一个访问的过程。


http://xugou4-yahoo-com-cn.iteye.com/blog/1308457
http://blog.csdn.net/yanzi1225627/article/details/24937439

public class RenRen {
// 配置参数
private static String userName = "邮箱地址";
private static String password = "密码";
private static String redirectURL =
"http://blog.renren.com/blog/304317577/449470467"; //要抓取的网址

// 登录URL地址
private static String renRenLoginURL = "http://www.renren.com/PLogin.do";

// 用于取得重定向地址
private HttpResponse response;
// 在一个会话中用到的httpclient对象
private DefaultHttpClient httpclient = new DefaultHttpClient();

//登录到页面
private boolean login() {
//根据登录页面地址初始化httpost对象
HttpPost httpost = new HttpPost(renRenLoginURL);
//POST给网站的所有参数
List<NameValuePair> nvps = new ArrayList<NameValuePair>();
nvps.add(new BasicNameValuePair("origURL", redirectURL));
nvps.add(new BasicNameValuePair("domain", "renren.com"));
nvps.add(new BasicNameValuePair("isplogin", "true"));
nvps.add(new BasicNameValuePair("formName", ""));
nvps.add(new BasicNameValuePair("method", ""));
nvps.add(new BasicNameValuePair("submit", "登录"));
nvps.add(new BasicNameValuePair("email", userName));
nvps.add(new BasicNameValuePair("password", password));
try {
httpost.setEntity(new UrlEncodedFormEntity(nvps, HTTP.UTF_8));
response = httpclient.execute(httpost);
} catch (Exception e) {
e.printStackTrace();
return false;
} finally {
httpost.abort();
}
return true;
}

//取得重定向地址
private String getRedirectLocation() {
Header locationHeader = response.getFirstHeader("Location");
if (locationHeader == null) {
return null;
}
return locationHeader.getValue();
}

//根据重定向地址返回内容
private String getText(String redirectLocation) {
HttpGet httpget = new HttpGet(redirectLocation);
// 创建一个响应处理器
ResponseHandler<String> responseHandler = new BasicResponseHandler();
String responseBody = "";
try {
//取得网页内容
responseBody = httpclient.execute(httpget, responseHandler);
} catch (Exception e) {
e.printStackTrace();
responseBody = null;
} finally {
httpget.abort();
httpclient.getConnectionManager().shutdown();//关闭连接
}
return responseBody;
}

public void printText() {
if (login()) {
String redirectLocation = getRedirectLocation();
if (redirectLocation != null) {
System.out.println(getText(redirectLocation));
}
}
}

public static void main(String[] args) {
RenRen renRen = new RenRen();
renRen.printText();
}
}