HTTPCLIENT 模拟登陆

第一步构建忽略https验证的httpclient

public static CloseableHttpClient getHttpClient() throws Exception {
        SSLConnectionSocketFactory sslsf = null;
        PoolingHttpClientConnectionManager cm = null;
        SSLContextBuilder builder = null;
        builder = new SSLContextBuilder();
         //全部信任 不做身份鉴定
        builder.loadTrustMaterial(null, new TrustStrategy() {
            @Override
            public boolean isTrusted(X509Certificate[] x509Certificates, String s) throws CertificateException {
                return true;
            }
        });
        sslsf = new SSLConnectionSocketFactory(builder.build(), new String[]{"SSLv2Hello", "SSLv3", "TLSv1", "TLSv1.2"}, null, NoopHostnameVerifier.INSTANCE);
        CloseableHttpClient httpClient = HttpClients.custom()
                .setSSLSocketFactory(sslsf)
                .setConnectionManager(cm)
                .setConnectionManagerShared(true)
                .setDefaultCookieStore(cookieStore)
                .build();
        return httpClient;
    }

　　第二步：第一次访问获取cookie;

public static void getCookie() throws Exception{
        HttpClient httpClient = getHttpClient();
        // HTTP请求
        HttpUriRequest request = new HttpGet("http://888.by3322.com:8088/Login");
        setHeader(request);
        HttpResponse response = httpClient.execute(request);
        HttpEntity entity = response.getEntity();
    }

　　

　　第三步：为避免目标网站的过滤，添加请求头相关信息

public static void setHeader(HttpUriRequest request){
        request.setHeader("User-Agent","Mozilla/5.0 (Windows NT 10.0; WOW64; rv:56.0) Gecko/20100101 Firefox/56.0");
        request.setHeader("Accept","text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8");
        request.setHeader("Accept-Encoding","gzip, deflate");
        request.setHeader("Accept-Language","zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3");
        request.setHeader("Cache-Control", "max-age=0");
        request.setHeader("Connection","keep-alive");
        request.setHeader("Host","888.by3322.com:8088");
        request.setHeader("Upgrade-Insecure-Requests","1");
    }

　　第四步：下载验证码图片；

public static String getAuthNum()throws Exception{
    String authnum = "";
    HttpGet httpGet = new HttpGet("http://888.by3322.com:8088/Login/authnum");
    setHeader(httpGet);
    httpGet.setHeader("Referer","http://888.by3322.com:8088/Login");
    HttpResponse response = getHttpClient().execute(httpGet);
    if(response.getStatusLine().getStatusCode() == 200){
        //下载图片
        String filepath = "E:"+ File.separator+"authNum.png";
        OutputStream outputStream = new FileOutputStream(filepath);
        response.getEntity().writeTo(outputStream);
        EntityUtils.consume(response.getEntity());
        //识别图片上的字母数字
        authnum = ImageUtil.readImgText(new File(filepath));
    }
    return  authnum;
}

　　第五步：

public static String readImgText(File file){
        String result = "";
        ITesseract instance = new Tesseract();
        File tessDataFolder = LoadLibs.extractTessResources("tessdata");
        instance.setLanguage("eng");//英文库识别数字比较准确
        instance.setDatapath(tessDataFolder.getAbsolutePath());
        try {
            result = instance.doOCR(file);
            System.out.println(result);
        } catch (TesseractException e) {
            System.err.println(e.getMessage());
        }
        return result;
    }

　　

　　备注：

　　在httpclient 请求url时，可能遇到norespones 之类没有响应，而用浏览器有相应的问题，问题可能是请求头的问题，或者是refener的参数设置

　　识别图片文字采用tess4j ；其中遇到的问题：找不到指定的模块，主要原因是在Windows环境下，gsdll64.dll,liblept170.dll,libtesseract304.dll等三个文件是通过vc2013编译的，所以需要相应地依赖库函数;这个地址：https://www.microsoft.com/zh-cn/download/default.aspx 下载，安装；

 

转载于:https://www.cnblogs.com/wangshunyao/p/7822476.html