验证码识别，爬虫永远的话题~

用打码兔总体的体验就是单线程速度太慢~

  1. import java.io.IOException;
  2. import java.net.MalformedURLException;
  3. import java.util.Date;
  4.  
  5. import org.apache.log4j.Logger;
  6. import org.jsoup.Jsoup;
  7. import org.jsoup.nodes.Document;
  8. import org.jsoup.select.Elements;
  9.  
  10. import com.gargoylesoftware.htmlunit.BrowserVersion;
  11. import com.gargoylesoftware.htmlunit.FailingHttpStatusCodeException;
  12. import com.gargoylesoftware.htmlunit.WebClient;
  13. import com.gargoylesoftware.htmlunit.html.HtmlButton;
  14. import com.gargoylesoftware.htmlunit.html.HtmlForm;
  15. import com.gargoylesoftware.htmlunit.html.HtmlPage;
  16. import com.gargoylesoftware.htmlunit.html.HtmlSubmitInput;
  17.  
  18. import cn.smy.dama2.Dama2Web;
  19. import cn.smy.dama2.Dama2Web.DecodeResult;
  20. import cn.smy.dama2.Dama2Web.ReadBalanceResult;
  21.  
  22. /**
  23. * @Title: main.java
  24. * @Package
  25. * @Description: TODO(用一句话描述该文件做什么)
  26. * @author A18ccms A18ccms_gmail_com
  27. * @date 2017年2月15日 下午3:42:00
  28. * @version V1.0
  29. */
  30.  
  31. /**
  32.  * @ClassName: main
  33.  * @Description: TODO
  34.  * @author zeze
  35.  * @date 2017年2月15日 下午3:42:00
  36.  *
  37.  */
  38. public class main {
  39.     private static Logger logger = Logger.getLogger(main.class);
  40.     private static final long serialVersionUID = 1325980466616825****;
  41.     private static Dama2Web dama2 = new Dama2Web(46****, "41c5a58de6********d23b67f61645e3a7", "***", "****");
  42.     private static int id;
  43.  
  44.     private static long nd = 1000 * 24 * 60 * 60;
  45.     private static long nh = 1000 * 60 * 60;
  46.     private static long nm = 1000 * 60;
  47.     private static long ns = 1000;
  48.     // 获得两个时间的毫秒时间差异
  49.     private static Date nowDate;
  50.     private static Date endDate;
  51.     private static long diff;// getTime返回的是一个long型的毫秒数
  52.     // 计算差多少分钟
  53.     private static long min;
  54.     // 计算差多少秒//输出结果
  55.     private static long sec;
  56.     // 计算多少毫秒
  57.     private static long ms;
  58.  
  59.     public static void main(String[] agrs) {
  60.         String emailAccount = "asd@qq.com";
  61.  
  62.         for (int i = 0; i < 10; i++) {
  63.             nowDate = new Date();
  64.  
  65.             emailAccount = "asd" + i + "@qq.com";
  66.             if(i==0)
  67.                 emailAccount="asd@qq.com";
  68.  
  69.             int statusCode=checkEbayAccount(emailAccount);
  70.             if(statusCode==0){
  71.                 System.out.println(emailAccount + " 该邮箱号不是ebay账号");
  72.             }else if(statusCode==1){
  73.                 System.out.println(emailAccount + " 该账号是eBay账号!");
  74.             }else if(statusCode==101){
  75.                 System.out.println("打码错误!");
  76.                 statusCode=checkEbayAccount(emailAccount);
  77.                 while(statusCode==101){
  78.                     statusCode=checkEbayAccount(emailAccount);
  79.                 }
  80.             }else{
  81.                 System.out.println(statusCode);
  82.             }
  83.  
  84.             endDate = new Date();
  85.             diff = endDate.getTime() - nowDate.getTime();
  86.             min = diff % nd % nh / nm;
  87.             sec = diff % nd % nh % nm / ns;
  88.             ms = diff % nd % nh % nm % ns;
  89.             System.out.println(min + "分钟" + sec + "秒" + ms + "毫秒");
  90.         }
  91.  
  92.     }
  93.  
  94.     // 验证邮箱是否为eBay账号
  95.     public static int checkEbayAccount(String emailAccount) {
  96.         System.out.println("开始验证账号：" + emailAccount);
  97.         WebClient webClient = new WebClient(BrowserVersion.FIREFOX_17);
  98.         HtmlPage page = null;
  99.         try {
  100.             page = webClient.getPage("http://fyp.ebay.com/");
  101.         } catch (FailingHttpStatusCodeException e) {
  102.             logger.error(e);
  103.         } catch (MalformedURLException e) {
  104.             logger.error(e);
  105.         } catch (IOException e) {
  106.             logger.error(e);
  107.         }
  108.         HtmlForm form = page.getForms().get(1);
  109.         form.getInputByName("input").setValueAttribute(emailAccount);
  110.         HtmlButton button = (HtmlButton) form.getElementsByTagName("button").get(0);
  111.  
  112.         try {
  113.             page = button.click();
  114.         } catch (IOException e1) {
  115.             logger.error(e1);
  116.         }
  117.         if (page.asText().indexOf("Select how you want to reset your password") != -1) {
  118. //            System.out.println(emailAccount + " 该账号是eBay账号!");
  119.             return 1;
  120.         }
  121.  
  122.         while (page.asText().indexOf("Security Measure") != -1) {
  123.  
  124.             Document doc = Jsoup.parse(page.asXml());
  125.             Elements imgSrc = doc.getElementsByTag("iframe");
  126.             String imgUrl = imgSrc.attr("src");
  127.             System.out.println("验证码图片链接：" + imgUrl);
  128.             String code = getCode(imgUrl);
  129.  
  130.             // 提交验证码
  131.             form = page.getForms().get(0);
  132.             form.getInputByName("tokenText").setValueAttribute(code);
  133.             HtmlSubmitInput input = (HtmlSubmitInput) form.getElementsByTagName("input").get(5);
  134.             try {
  135.                 page = input.click();
  136.             } catch (IOException e1) {
  137.                 logger.error(e1);
  138.             }
  139.  
  140.             if (page.asText().indexOf("the verification code you entered doesn't match against the image") != -1) {
  141. //                System.out.println("打码错误！");
  142.                 dama2.reportError(id);
  143.                 return 101;
  144.             }
  145.  
  146.             // 再次提交邮箱
  147.             form = page.getForms().get(1);
  148.             form.getInputByName("input").setValueAttribute(emailAccount);
  149.             button = (HtmlButton) form.getElementsByTagName("button").get(0);
  150.             try {
  151.                 page = button.click();
  152.             } catch (IOException e1) {
  153.                 logger.error(e1);
  154.             }
  155.  
  156.             if (page.asText().indexOf("Security Measure") != -1){// 如果还是验证码页面
  157.                 System.out.println("提交还是验证码页面!");
  158.                 continue;
  159.             }
  160.  
  161.             if (page.asText().indexOf("Oops, that's not a match. Try again?") != -1) {
  162. //                System.out.println(emailAccount + " 该邮箱号不是ebay账号");
  163.                 return 0;
  164.             } else if (page.asText().indexOf("Select how you want to reset your password") != 1) {
  165. //                System.out.println(emailAccount + " 该账号是eBay账号!");
  166.                 return 1;
  167.             } else {
  168.                 System.out.println(page.asText());
  169.                 return 2;
  170.             }
  171.         }
  172.         return 3;
  173.     }
  174.  
  175.     // 打码兔获取验证码
  176.     public static String getCode(String imgUrl) {
  177.         // 打码兔
  178.         int type = 6;
  179.         int timeout = 30;
  180.         ReadBalanceResult balanceResult = dama2.getBalance();
  181.         // System.out.println(balanceResult);
  182.         DecodeResult res = dama2.decodeUrlAndGetResult(imgUrl, type, timeout);
  183.         String s;
  184.         if (res.ret >= 0) {
  185.             id = res.ret;
  186.             s = "success: result=" + res.result + "; id=" + res.ret;
  187.             System.out.println(s);
  188.         } else {
  189.             s = "failed: ret = " + res.ret + "; desc=" + res.desc;
  190.             System.err.println(s);
  191.         }
  192.         return res.result;
  193.     }
  194.  
  195. }

测试结果如下：

用多线程测试，明显快多了

  1. package test;
  2.  
  3. import java.io.IOException;
  4. import java.net.MalformedURLException;
  5. import java.util.ArrayList;
  6. import java.util.Date;
  7. import java.util.concurrent.Callable;
  8. import java.util.concurrent.ExecutorService;
  9. import java.util.concurrent.Executors;
  10. import java.util.concurrent.Future;
  11.  
  12. import org.apache.log4j.Logger;
  13. import org.jsoup.Jsoup;
  14. import org.jsoup.nodes.Document;
  15. import org.jsoup.select.Elements;
  16.  
  17. import com.gargoylesoftware.htmlunit.BrowserVersion;
  18. import com.gargoylesoftware.htmlunit.FailingHttpStatusCodeException;
  19. import com.gargoylesoftware.htmlunit.WebClient;
  20. import com.gargoylesoftware.htmlunit.html.HtmlButton;
  21. import com.gargoylesoftware.htmlunit.html.HtmlForm;
  22. import com.gargoylesoftware.htmlunit.html.HtmlPage;
  23. import com.gargoylesoftware.htmlunit.html.HtmlSubmitInput;
  24.  
  25. import cn.smy.dama2.Dama2Web;
  26. import cn.smy.dama2.Dama2Web.DecodeResult;
  27. import cn.smy.dama2.Dama2Web.ReadBalanceResult;
  28.  
  29. /***
  30.  *
  31.  * @ClassName: EbayMultiplyThreadCheck
  32.  * @Description: TODO
  33.  * @author zeze
  34.  * @date 2017年2月16日 上午8:49:46
  35.  *
  36.  */
  37. public class EbayMultiplyThreadCheck {
  38.  
  39.     private static int threadNum = 30;
  40.  
  41.     private static long nd = 1000 * 24 * 60 * 60;
  42.     private static long nh = 1000 * 60 * 60;
  43.     private static long nm = 1000 * 60;
  44.     private static long ns = 1000;
  45.     private static Date nowDate;
  46.     private static Date endDate;
  47.     private static long diff;
  48.     private static long min;
  49.     private static long sec;
  50.     private static long ms;
  51.  
  52.     public static void main(String[] args) {
  53.         nowDate = new Date();
  54.  
  55.         ExecutorService exec = Executors.newFixedThreadPool(threadNum);
  56.         ArrayList<Future<Integer>> results = new ArrayList<Future<Integer>>();
  57.  
  58.         for (int i = 0; i < threadNum; i++) {
  59.             String email = "asd" + i + "@qq.com";
  60.             if (i == 0)
  61.                 email = "asd@qq.com";
  62.             results.add(exec.submit(new CheckEbayAccount(email)));
  63.         }
  64.  
  65.         boolean isDone = false;
  66.         while (!isDone) {
  67.             isDone = true;
  68.             for (Future<Integer> future : results) {
  69.                 if (!future.isDone()) {
  70.                     isDone = false;
  71.                     try {
  72.                         Thread.sleep(1000);
  73.                     } catch (InterruptedException e) {
  74.                     }
  75.                     break;
  76.                 }
  77.             }
  78.         }
  79.         exec.shutdown();
  80.  
  81.         endDate = new Date();
  82.         diff = endDate.getTime() - nowDate.getTime();
  83.         min = diff % nd % nh / nm;
  84.         sec = diff % nd % nh % nm / ns;
  85.         ms = diff % nd % nh % nm % ns;
  86.         System.out.println(min + "分钟" + sec + "秒" + ms + "毫秒");
  87.  
  88.     }
  89. }
  90.  
  91. class CheckEbayAccount implements Callable<Integer> {
  92.  
  93.     private String email;
  94.     private static Logger logger = Logger.getLogger(CheckEbayAccount.class);
  95.     private static Dama2Web dama2 = new Dama2Web(****, "41c5a58de68ebe2*******", "***", "****");
  96.     private static int id;
  97.  
  98.     public CheckEbayAccount(String email) {
  99.         this.email = email;
  100.     }
  101.  
  102.     @Override
  103.     public Integer call() {
  104.  
  105.         System.out.println(Thread.currentThread().getName() + " 开始验证账号：" + email);
  106.         WebClient webClient = new WebClient(BrowserVersion.FIREFOX_17);
  107.         HtmlPage page = null;
  108.         try {
  109.             page = webClient.getPage("http://fyp.ebay.com/");
  110.         } catch (FailingHttpStatusCodeException e) {
  111.             logger.error(e);
  112.         } catch (MalformedURLException e) {
  113.             logger.error(e);
  114.         } catch (IOException e) {
  115.             logger.error(e);
  116.         }
  117.         HtmlForm form = page.getForms().get(1);
  118.         form.getInputByName("input").setValueAttribute(email);
  119.         HtmlButton button = (HtmlButton) form.getElementsByTagName("button").get(0);
  120.  
  121.         try {
  122.             page = button.click();
  123.         } catch (IOException e1) {
  124.             logger.error(e1);
  125.         }
  126.  
  127.         if (page.asText().indexOf("Select how you want to reset your password") != -1) {
  128.             System.out.println(Thread.currentThread().getName() + " " + email + " 该账号是eBay账号!");
  129.             return 1;
  130.         } else if (page.asText().indexOf("Oops, that's not a match. Try again?") != -1) {
  131.             System.out.println(Thread.currentThread().getName() + " " + email + " 该邮箱号不是ebay账号");
  132.             return 0;
  133.         }
  134.  
  135.         while (page.asText().indexOf("Security Measure") != -1) {
  136.  
  137.             Document doc = Jsoup.parse(page.asXml());
  138.             Elements imgSrc = doc.getElementsByTag("iframe");
  139.             String imgUrl = imgSrc.attr("src");
  140.             System.out.println(Thread.currentThread().getName() + " " + "验证码图片链接：" + imgUrl);
  141.             String code = getCode(imgUrl);
  142.  
  143.             // 提交验证码
  144.             form = page.getForms().get(0);
  145.             form.getInputByName("tokenText").setValueAttribute(code);
  146.             HtmlSubmitInput input = (HtmlSubmitInput) form.getElementsByTagName("input").get(5);
  147.             try {
  148.                 page = input.click();
  149.             } catch (IOException e1) {
  150.                 System.out.println(Thread.currentThread().getName() + " " + e1);
  151.             }
  152.  
  153.             while (page.asText().indexOf("Sorry") != -1) {
  154.                 System.out.println(Thread.currentThread().getName() + " 打码错误！重试");
  155.                 dama2.reportError(id);
  156.  
  157.                 doc = Jsoup.parse(page.asXml());
  158.                 imgSrc = doc.getElementsByTag("iframe");
  159.                 imgUrl = imgSrc.attr("src");
  160.                 System.out.println(Thread.currentThread().getName() + " " + "验证码图片链接：" + imgUrl);
  161.                 code = getCode(imgUrl);
  162.  
  163.                 // 提交验证码
  164.                 form = page.getForms().get(0);
  165.                 form.getInputByName("tokenText").setValueAttribute(code);
  166.                 input = (HtmlSubmitInput) form.getElementsByTagName("input").get(5);
  167.                 try {
  168.                     page = input.click();
  169.                 } catch (IOException e1) {
  170.                     logger.error(e1);
  171.                 }
  172.             }
  173.  
  174.             // 再次提交邮箱
  175.             form = page.getForms().get(1);
  176.             form.getInputByName("input").setValueAttribute(email);
  177.             button = (HtmlButton) form.getElementsByTagName("button").get(0);
  178.             try {
  179.                 page = button.click();
  180.             } catch (IOException e1) {
  181.                 logger.error(e1);
  182.             }
  183.  
  184.             if (page.asText().indexOf("Security Measure") != -1) {// 如果还是验证码页面
  185.                 System.out.println(Thread.currentThread().getName() + " 提交还是验证码页面!");
  186.                 continue;
  187.             }
  188.  
  189.             if (page.asText().indexOf("Oops, that's not a match. Try again?") != -1) {
  190.                 System.out.println(Thread.currentThread().getName() + " " + email + " 该邮箱号不是ebay账号");
  191.                 return 0;
  192.             } else if (page.asText().indexOf("Select how you want to reset your password") != 1) {
  193.                 System.out.println(Thread.currentThread().getName() + " " + email + " 该账号是eBay账号!");
  194.                 return 1;
  195.             } else {
  196.                 System.out.println(Thread.currentThread().getName() + " " + page.asText());
  197.                 return 2;
  198.             }
  199.         }
  200.         System.out.println(Thread.currentThread().getName() + " " + page.asText());
  201.         return 3;
  202.  
  203.     }
  204.  
  205.     // 打码兔获取验证码
  206.     public static String getCode(String imgUrl) {
  207.         // 打码兔
  208.         int type = 6;
  209.         int timeout = 30;
  210.         ReadBalanceResult balanceResult = dama2.getBalance();
  211.         // System.out.println(balanceResult);
  212.         DecodeResult res = dama2.decodeUrlAndGetResult(imgUrl, type, timeout);
  213.         String s;
  214.         if (res.ret >= 0) {
  215.             id = res.ret;
  216.             s = "[打码结果=" + res.result + "] [id=" + res.ret + "] " + balanceResult;
  217.             System.out.println(Thread.currentThread().getName() + " " + s);
  218.         } else {
  219.             while (res.result == null) {
  220.                 s = "打码失败,重试: ret = " + res.ret + "; desc=" + res.desc;
  221.                 System.out.println(Thread.currentThread().getName() + " " + s);
  222.                 dama2.reportError(id);
  223.                 res = dama2.decodeUrlAndGetResult(imgUrl, type, timeout);
  224.                 if (res.ret >= 0) {
  225.                     id = res.ret;
  226.                     s = "[打码结果=" + res.result + "] [id=" + res.ret + "] " + balanceResult;
  227.                     System.out.println(Thread.currentThread().getName() + " " + s);
  228.                 }
  229.             }
  230.         }
  231.         return res.result;
  232.     }
  233.  
  234. }

测试30个账号，平均每个3秒

Java 验证码识别之多线程打码兔的更多相关文章

  1. Java验证码识别解决方案

    建库,去重,切割,识别. package edu.fzu.ir.test; import java.awt.Color; import java.awt.image.BufferedImage; im ...

  2. Java 验证码识别库 Tess4j 学习

    Java 验证码识别库 Tess4j 学习 [在用java的Jsoup做爬虫爬取数据时遇到了验证码识别的问题(基于maven),找了网上挺多的资料,发现Tess4j可以自动识别验证码,在这里简单记录下 ...

  3. JAVA验证码识别：基于jTessBoxEditorFX和Tesseract-OCR训练样本

    JAVA验证识别:基于jTessBoxEditorFX和Tesseract-OCR训练样本 工具准备: jTessBoxEditorFX下载:https://github.com/nguyenq/jT ...

  4. java验证码识别

    首先参考了csdn大佬的文章,但是写的不全ImgUtils类没有给出代码,无法进行了 写不完整就是制造垃圾 不过这个大佬又说这个大佬的文章值得参考于是又查看这篇文章 有案例https://blog.c ...

  5. 【Java】验证码识别解决方案

    对于类似以下简单的验证码的识别方案: 1. 2 3 4. 1.建库:切割验证码为单个字符,人工标记,比如:A. 2.识别:给一个验证码:切割为单个字符,在库中查询识别. /*** * author:c ...

  6. Java 验证码、二维码

    Java 验证码.二维码 资源 需要:   jelly-core-1.7.0.GA.jar网站:   http://lychie.github.io/products.html将下载下来的 jelly ...

  7. uu云验证码识别平台,验证码,验证码识别,全自动验证码识别技术,优优云全自动打码,代答题系统,优优云远程打码平台,uu云打码

    uu云验证码识别平台,验证码,验证码识别,全自动验证码识别技术,优优云全自动打码,代答题系统,优优云远程打码平台,uu云打码 优优云验证码识别答题平台介绍 优优云|UU云(中国公司)是全球唯一领先的智 ...

  8. 基于tensorflow的‘端到端’的字符型验证码识别源码整理(github源码分享)

    基于tensorflow的‘端到端’的字符型验证码识别 1   Abstract 验证码(CAPTCHA)的诞生本身是为了自动区分 自然人 和 机器人 的一套公开方法, 但是近几年的人工智能技术的发展 ...

  9. 基于python语言的tensorflow的‘端到端’的字符型验证码识别源码整理(github源码分享)

    基于python语言的tensorflow的‘端到端’的字符型验证码识别 1   Abstract 验证码(CAPTCHA)的诞生本身是为了自动区分 自然人 和 机器人 的一套公开方法, 但是近几年的 ...

随机推荐

  1. 全国出现大面积DNS服务器故障 域名被劫持

    1月21日消息,继今日上午腾讯16项服务出现故障后,大量网站出现了无法访问的情况,据了解,该故障是由于国内DNS根服务器故障所致. 据了解,此次攻击式由于国内所有通用顶级域的根服务器出现异常,导致大量 ...

  2. tensorflow serving 打印调试log

    启动时添加环境变量 export TF_CPP_MIN_VLOG_LEVEL=1 ,这样可以打印VLOG(1)的log

  3. spring mvc上传、下载的实现

    下载 //下载 @RequestMapping(value="/download") public ResponseEntity<byte[]> download() ...

  4. listView滚动事件

    listView滚动事件 实现接口: android.widget.AbsListView.OnScrollListener Interface definition for a callback t ...

  5. Java虚拟机学习 - 对象引用强度 ( 8 )

    无论是通过计数算法判断对象的引用数量,还是通过根搜索算法判断对象引用链是否可达,判定对象是否存活都与“引用”相关. 引用主要分为 :强引用(Strong Reference).软引用(Soft Ref ...

  6. ASP.NET中UrlEncode应该用Uri.EscapeDataString()

    今天,茄子_2008反馈他博客中的“C++”标签失效.检查了一下代码,生成链接时用的是HttpUtility.UrlEncode(url),从链接地址获取标签时用的是HttpUtility.UrlDe ...

  7. mysql数据库以加索引方式提高性能

    数据库查询速率慢的情况下可以给对应的表加上对应的索引,能够有效的提高查询效率,mysql数据库添加索引的SQL入下: ALTER TABLE `table_name` ADD INDEX index_ ...

  8. 【转】python2与python3的主要区别

    摘自:http://www.cnblogs.com/codingmylife/archive/2010/06/06/1752807.html 1.性能 Py3.0运行 pystone benchmar ...

  9. CSS选择器的优化

    前面花了几个篇幅着重介绍了CSS的选择器的使用,我将其分成三个部分:CSS基本选择器.CSS属性选择器以及CSS伪类选择器.那么今天我主要想和大家一起来学习——CSS选择器方面的性能优化.因为对性能这 ...

  10. cocos2dx 3.x draw debug

    有时候需要用ccDrawXXX绘制debug线框来调试图形程序. 在cocos2dx 2.x中,由于是立即模式,所以如果在draw函数中用ccDrawXXX画线框,要用节点的局部坐标. 在cocos2 ...