网络爬虫_网页登录（苏宁 有验证码）—基于HtmlUnit

输入验证码：

public static String getCode(){    System.out.println("请输入验证码：");    Scanner sc = new Scanner(System.in);    String code = sc.nextLine();    return code;}

初始化WebClient方法：

public WebClient getClient(){    webClient = new WebClient(BrowserVersion.FIREFOX_24);    webClient.getOptions().setCssEnabled(false);    webClient.getOptions().setJavaScriptEnabled(true);    webClient.getOptions().setThrowExceptionOnFailingStatusCode(false);    webClient.getOptions().setThrowExceptionOnScriptError(false);    webClient.setAjaxController(new NicelyResynchronizingAjaxController());    webClient.getOptions().setThrowExceptionOnScriptError(false);    webClient.getOptions().setThrowExceptionOnFailingStatusCode(false);    return webClient;}

爬取数据代码示例：

/** * Create by lingfx on 2017/8/18 */public class SuNingLoginTest {    private Logger logger = Logger.getLogger(SuNingLoginTest.class);    private WebClient client;    private String username = "用户名";    private String kkk = "密码";

    private String filePath = "E://code.jpg";
    public void login() throws IOException {        client = new WebClientTool().getClient();        HtmlPage htmlPage = client.getPage("https://mpassport.suning.com/ids/login?service=https%3A%2F%2Fscs.suning.com%2Fsps%2Fauth%3FtargetUrl%3Dhttp%253A%252F%252Fscs.suning.com%252Fsps%252Fmember%252Flogon.do&loginTheme=scs");//        logger.info(htmlPage.asText());        HtmlInput un = htmlPage.getHtmlElementById("username");        un.setValueAttribute(username);        HtmlInput pwd = htmlPage.getHtmlElementById("pwd");        pwd.setValueAttribute(kkk);        HtmlImage codeImg = htmlPage.getHtmlElementById("vcodeimg1");
codeImg.saveAs(new File(filePath));logger.info("验证码存储位置："+filePath);
        String code = ScannerTool.getCode();        HtmlInput codeInput = htmlPage.getHtmlElementById("validateCode");        codeInput.setValueAttribute(code);                ScriptResult res  = htmlPage.executeJavaScript("javascript:logon();");        HtmlPage page2 = (HtmlPage) res.getNewPage();        logger.info(page2.asText());        if(page2.asText().contains("您好！欢迎回来！")){            logger.info("登录成功！");        }    }        public static void main(String[] args) throws IOException {        SuNingLoginTest test = new SuNingLoginTest();        test.login();    }}

已测试，无异常。

2017-8-18