用java 自动登录一个网站的例子

在这个例子中，我将用java的HttpURLConnection,去登录一个web 站点。用这种方法的时候，一般是在一个form 中登录的。

在这个例子中，用到如下工具 ：
1. Google chrome 浏览器。
2. jsoup 库,用来提取html form 表单中的值. (你可以在这里下载 http://jsoup.org/ )
3. jdk 6.

一。分析http header,form data
要登录一个网站，必须知道的几件事：
1. 登录的 URL
2. 登录所需要的数据
3. 认证的URL
4. Http request/response header.
用chrome 浏览器打开上述页面，然后右键点击页面，可以看到 "查看元素" inspect element, 然后选择 网络 network Tab 页。首先打开gooogle 网站，并尝试登录，查看http request,response 数据，在后面我们会模拟这些数据.



二. 用 HttpsURLConnection 完成demo
1. 发送 http get 请求 到 google 的登录form: https://accounts.google.com/ServiceLoginAuth
2. 通过google 浏览器分析 网络 tab 页面，
3. 利用jsoup 得到form 里面隐藏的数据，然后放入自己的username 和 password
4. 发送post 请求
5. 认证完毕，发送另外一个请求到gmail 页面。（这里仅仅是例子，如果是为了访问gmail ,可以直接利用google 提供的 GMAIL API 去完成）

import java.io.BufferedReader;
import java.io.DataOutputStream;
import java.io.InputStreamReader;
import java.io.UnsupportedEncodingException;
import java.net.CookieHandler;
import java.net.CookieManager;
import java.net.URL;
import java.net.URLEncoder;
import java.util.ArrayList;
import java.util.List;
import javax.net.ssl.HttpsURLConnection;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
 
public class HttpUrlConnectionExample {
 
  private List cookies;
  private HttpsURLConnection conn;
 
  private final String USER_AGENT = "Mozilla/5.0";
 
  public static void main(String[] args) throws Exception {
 
	String url = "https://accounts.google.com/ServiceLoginAuth";
	String gmail = "https://mail.google.com/mail/";
 
	HttpUrlConnectionExample http = new HttpUrlConnectionExample();
 
	// make sure cookies is turn on
	CookieHandler.setDefault(new CookieManager());
 
	// 1. Send a "GET" request, so that you can extract the form's data.
	String page = http.GetPageContent(url);
	String postParams = http.getFormParams(page, "username@gmail.com", "password");
 
	// 2. Construct above post's content and then send a POST request for
	// authentication
	http.sendPost(url, postParams);
 
	// 3. success then go to gmail.
	String result = http.GetPageContent(gmail);
	System.out.println(result);
  }
 
  private void sendPost(String url, String postParams) throws Exception {
 
	URL obj = new URL(url);
	conn = (HttpsURLConnection) obj.openConnection();
 
	// Acts like a browser
	conn.setUseCaches(false);
	conn.setRequestMethod("POST");
	conn.setRequestProperty("Host", "accounts.google.com");
	conn.setRequestProperty("User-Agent", USER_AGENT);
	conn.setRequestProperty("Accept",
		"text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8");
	conn.setRequestProperty("Accept-Language", "en-US,en;q=0.5");
	for (String cookie : this.cookies) {
		conn.addRequestProperty("Cookie", cookie.split(";", 1)[0]);
	}
	conn.setRequestProperty("Connection", "keep-alive");
	conn.setRequestProperty("Referer", "https://accounts.google.com/ServiceLoginAuth");
	conn.setRequestProperty("Content-Type", "application/x-www-form-urlencoded");
	conn.setRequestProperty("Content-Length", Integer.toString(postParams.length()));
 
	conn.setDoOutput(true);
	conn.setDoInput(true);
 
	// Send post request
	DataOutputStream wr = new DataOutputStream(conn.getOutputStream());
	wr.writeBytes(postParams);
	wr.flush();
	wr.close();
 
	int responseCode = conn.getResponseCode();
	System.out.println("\nSending 'POST' request to URL : " + url);
	System.out.println("Post parameters : " + postParams);
	System.out.println("Response Code : " + responseCode);
 
	BufferedReader in = 
             new BufferedReader(new InputStreamReader(conn.getInputStream()));
	String inputLine;
	StringBuffer response = new StringBuffer();
 
	while ((inputLine = in.readLine()) != null) {
		response.append(inputLine);
	}
	in.close();
	// System.out.println(response.toString());
 
  }
 
  private String GetPageContent(String url) throws Exception {
 
	URL obj = new URL(url);
	conn = (HttpsURLConnection) obj.openConnection();
 
	// default is GET
	conn.setRequestMethod("GET");
 
	conn.setUseCaches(false);
 
	// act like a browser
	conn.setRequestProperty("User-Agent", USER_AGENT);
	conn.setRequestProperty("Accept",
		"text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8");
	conn.setRequestProperty("Accept-Language", "en-US,en;q=0.5");
	if (cookies != null) {
		for (String cookie : this.cookies) {
			conn.addRequestProperty("Cookie", cookie.split(";", 1)[0]);
		}
	}
	int responseCode = conn.getResponseCode();
	System.out.println("\nSending 'GET' request to URL : " + url);
	System.out.println("Response Code : " + responseCode);
 
	BufferedReader in = 
            new BufferedReader(new InputStreamReader(conn.getInputStream()));
	String inputLine;
	StringBuffer response = new StringBuffer();
 
	while ((inputLine = in.readLine()) != null) {
		response.append(inputLine);
	}
	in.close();
 
	// Get the response cookies
	setCookies(conn.getHeaderFields().get("Set-Cookie"));
 
	return response.toString();
 
  }
 
  public String getFormParams(String html, String username, String password)
		throws UnsupportedEncodingException {
 
	System.out.println("Extracting form's data...");
 
	Document doc = Jsoup.parse(html);
 
	// Google form id
	Element loginform = doc.getElementById("gaia_loginform");
	Elements inputElements = loginform.getElementsByTag("input");
	List paramList = new ArrayList();
	for (Element inputElement : inputElements) {
		String key = inputElement.attr("name");
		String value = inputElement.attr("value");
 
		if (key.equals("Email"))
			value = username;
		else if (key.equals("Passwd"))
			value = password;
		paramList.add(key + "=" + URLEncoder.encode(value, "UTF-8"));
	}
 
	// build parameters list
	StringBuilder result = new StringBuilder();
	for (String param : paramList) {
		if (result.length() == 0) {
			result.append(param);
		} else {
			result.append("&" + param);
		}
	}
	return result.toString();
  }
 
  public List getCookies() {
	return cookies;
  }
 
  public void setCookies(List cookies) {
	this.cookies = cookies;
  }
 
}

输出

Sending 'GET' request to URL : https://accounts.google.com/ServiceLoginAuth
Response Code : 200
Extracting form data...
 
Sending 'POST' request to URL : https://accounts.google.com/ServiceLoginAuth
Post parameters : dsh=-293322094146108856&GALX=CExqdUbvEr4&timeStmp=&secTok=&_utf8=%E2%98%83
&bgresponse=js_disabled&Email=username&Passwd=password&signIn=Sign+in&PersistentCookie=yes&rmShown=1
Response Code : 200
 
Sending 'GET' request to URL : https://mail.google.com/mail/
Response Code : 200

From：一号门