用httpclient模拟登陆网站注意事项

最近一直在用httpclient进行模拟登陆网站，即先用httpwatch记录手动登陆时浏览器与服务器之间的数据交互，然后用httpclient模拟浏览器的行为进行登陆。

但是一开始进行模拟时总是登陆不成功，即使发送的内容与httpwatch中记录的内容一致时，也是返回不了正确的结果，经过网上搜索和尝试，发现是发送请求时，请求头的信息不够完整。同样的请求体，如果把请求头的信息尽量完善，就能够成功登陆，否则则是登陆失败。

其次还要注意第一次向服务器请求时，服务器一般都会返回一个“Set-Cookie”字段，把这个字段中的内容（如sessionid）记录下来，添加到cookie中，再次向服务器发请求时带上cookie，这样就能有很大概率登陆成功了。

下面是一个模拟登陆的代码，其中包括对于验证码的处理

public static void main(String[] args) throws HttpException, IOException {
		HttpClient client = new HttpClient();
		String url = "http://www.xxxxx.com/user/login.html";
		GetMethod getMethod = new GetMethod(url);
		getMethod.setRequestHeader("Host", "www.xxxxxx.com");  
        getMethod.setRequestHeader("User-Agent", "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; NP06; .NET4.0C; .NET4.0E; InfoPath.3; Media Center PC 6.0)");  
        getMethod.setRequestHeader("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8");  
        getMethod.setRequestHeader("Accept-Language", "zh-cn,zh;q=0.5");  
        getMethod.setRequestHeader("Accept-Charset", "GB2312,utf-8;q=0.7,*;q=0.7");  
        getMethod.setRequestHeader("Connection", "keep-alive");  
        getMethod.setRequestHeader("Cache-Control", "max-age=0");
	client.executeMethod(getMethod);
	Header header = getMethod.getResponseHeader("Set-cookie");//记录服务器返回的cookie值   
        System.out.println(header.getValue());  
        String headerCookie = header.getValue();  
        String SessionId = headerCookie.substring(headerCookie.indexOf("ASP.NET_SessionId=") + "ASP.NET_SessionId=".length(), headerCookie.indexOf(";"));  
        System.out.println(SessionId); 
        StringBuffer sb = new StringBuffer();
        sb.append("Hm_lvt_ebd37b04edd1e0fceaa52dc641b8ff6f=1412760752,1412820282; sgsa_id=anxin.com|1412760752435322; _ga=GA1.2.1171830066.1412760753; cuuid=E407DF6BFFBF4599; _gat=1; Hm_lpvt_ebd37b04edd1e0fceaa52dc641b8ff6f=1412820282; sgsa_vt_187935_192889=1412820281676; CNZZDATA1252986781=736053870-1412760776-%7C1412820303; dntadmin=;");
        sb.append("ASP.NET_SessionId=").append(SessionId).append("; ");
		String cookie = sb.toString();
		System.out.println(cookie);
		getMethod = new GetMethod("http://www.xxxxxx.com/vcode.aspx?xxxx=xxxxx&x=x");//获取验证码
		client.executeMethod(getMethod);
		InputStream is = getMethod.getResponseBodyAsStream();
		File file = new File("D:/image.png");//图片格式根据具体情况而定（有些网站在获取验证码时也要发送带cookie的请求头，要注意具体情况具体分析）
		FileOutputStream fos = new FileOutputStream(file);
		byte b[] = new byte[1024];
		int j = 0;
		while((j=is.read(b))!=-1){
			fos.write(b, 0, j);
		}
		fos.flush();
		fos.close();
		String key = "";
		System.out.println("请输入验证码");
		Scanner scanner = new Scanner(System.in);
		key = scanner.nextLine();
		
		client.getHostConfiguration().setHost("www.xxxxxx.com", 80, "http");  
        PostMethod method = getPostMethod(key);  
        method.setRequestHeader("User-Agent", "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; NP06; .NET4.0C; .NET4.0E; InfoPath.3; Media Center PC 6.0)");  
        method.setRequestHeader("Host", "www.xxxxxx.com");  
        method.setRequestHeader("Accept", "application/json, text/javascript, */*");  
        method.setRequestHeader("Accept-Language", "zh-cn,zh;q=0.5");  
//      method.setRequestHeader("Accept-Encoding", "gzip, deflate");  
        method.setRequestHeader("Accept-Charset", "GB2312,utf-8;q=0.7,*;q=0.7");  
        method.setRequestHeader("Connection", "keep-alive");  
        method.setRequestHeader("Content-Type", "application/x-www-form-urlencoded; charset=UTF-8");  
        method.setRequestHeader("X-Requested-With", "XMLHttpRequest");  
        method.setRequestHeader("Referer", "http://www.xxxxxx.com/user/login.html");  
        method.setRequestHeader("Cookie", cookie);   
        client.executeMethod(method);  
        System.out.println(method.getStatusCode());  
        System.out.println(method.getResponseBodyAsString());

        Header header1 = method.getResponseHeader("Set-cookie");   
        sb.append(header1.getValue());  
        Cookie[] cookies = client.getState().getCookies();  
        method.releaseConnection();  
        String my = "http://www.xxxxx.com/usercenter";  
        System.out.println(sb.toString());  
        getMethod = new GetMethod(my);  
        getMethod.setRequestHeader("Host", "www.xxxxx.com");  
        getMethod.setRequestHeader("User-Agent", "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; NP06; .NET4.0C; .NET4.0E; InfoPath.3; Media Center PC 6.0)");  
        getMethod.setRequestHeader("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8");  
        getMethod.setRequestHeader("Accept-Language", "zh-cn,zh;q=0.5");  
        getMethod.setRequestHeader("Accept-Charset", "GB2312,utf-8;q=0.7,*;q=0.7");  
        getMethod.setRequestHeader("Connection", "keep-alive");  
        getMethod.setRequestHeader("Referer", "http://www.xxxxx.com/user/login.html");  
        getMethod.setRequestHeader("Cookie", sb.toString());  
        int code = client.executeMethod(getMethod);  
        System.out.println(getMethod.getStatusCode());  
        System.out.println(getMethod.getResponseBodyAsString());  
        
	}

	private static PostMethod getPostMethod(String ValidCode) {  
        PostMethod post = new PostMethod("/ajax/xxxx.xxxx");  
        NameValuePair[] simcard = {  
                new NameValuePair("Action", "post"),  
                new NameValuePair("Keep", "0"),  
                new NameValuePair("sPassword", "xxxxx"),  
                new NameValuePair("sUserName", "xxxxx"),  
                new NameValuePair("sVerCode", ValidCode),  
                };  
        post.setRequestBody(simcard);  
        return post;  
    }