zoukankan html css js c++ java

Webdriver配合Tesseract-OCR 自动识别简单的验证码

验证码：如下，在进行自动化测试，遇到验证码的问题，一般有两种方式

1.找开发去掉验证码或者使用万能验证码

2.使用OCR自动识别

使用OCR自动化识别，一般识别率不是太高，处理一般简单验证码还是没问题

这里使用的是Tesseract-OCR,下载地址：https://github.com/A9T9/Free-Ocr-Windows-Desktop/releases

怎么使用呢？

进入安装后的目录：

tesseract.exe test.png test -1

准备一份网页，上面使用该验证码

<html>
<head>
<title>Table test by Young</title>
</head>
<body>
 </br>
<h1> Test </h1>
 <img src="http://csujwc.its.csu.edu.cn/sys/ValidateCode.aspx?t=1">
 </br>
</body>
</html>

要识别验证码，首先得取得验证码，这两款采取对页面元素部分截图的方式，首先获取整个页面的截图

然后找到页面元素坐标进行截取

/**
     * This method for screen shot element
     * 
     * @param driver
     * @param element
     * @param path
     * @throws InterruptedException
     */
    public static void screenShotForElement(WebDriver driver,
            WebElement element, String path) throws InterruptedException {
        File scrFile = ((TakesScreenshot) driver)
                .getScreenshotAs(OutputType.FILE);
        try {
            Point p = element.getLocation();
            int width = element.getSize().getWidth();
            int height = element.getSize().getHeight();
            Rectangle rect = new Rectangle(width, height);
            BufferedImage img = ImageIO.read(scrFile);
            BufferedImage dest = img.getSubimage(p.getX(), p.getY(),
                    rect.width, rect.height);
            ImageIO.write(dest, "png", scrFile);
            Thread.sleep(1000);
            FileUtils.copyFile(scrFile, new File(path));
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

截取完元素，就可以调用Tesseract-OCR生成text

// use Tesseract to get strings
        Runtime rt = Runtime.getRuntime();
        rt.exec("cmd.exe /C  tesseract.exe D:\Tesseract-OCR\test.png  D:\Tesseract-OCR\test -1 ");

接下来通过java读取txt

/**
     * This method for read TXT file
     * 
     * @param filePath
     */
    public static void readTextFile(String filePath) {
        try {
            String encoding = "GBK";
            File file = new File(filePath);
            if (file.isFile() && file.exists()) { // 判断文件是否存在
                InputStreamReader read = new InputStreamReader(
                        new FileInputStream(file), encoding);// 考虑到编码格式
                BufferedReader bufferedReader = new BufferedReader(read);
                String lineTxt = null;
                while ((lineTxt = bufferedReader.readLine()) != null) {
                    System.out.println(lineTxt);
                }
                read.close();
            } else {
                System.out.println("找不到指定的文件");
            }
        } catch (Exception e) {
            System.out.println("读取文件内容出错");
            e.printStackTrace();
        }
    }

整体代码如下：

  1 package com.dbyl.tests;
  2 
  3 import java.awt.Rectangle;
  4 import java.awt.image.BufferedImage;
  5 import java.io.BufferedReader;
  6 import java.io.File;
  7 import java.io.FileInputStream;
  8 import java.io.IOException;
  9 import java.io.InputStreamReader;
 10 import java.io.Reader;
 11 import java.util.concurrent.TimeUnit;
 12 
 13 import javax.imageio.ImageIO;
 14 
 15 import org.apache.commons.io.FileUtils;
 16 import org.openqa.selenium.By;
 17 import org.openqa.selenium.OutputType;
 18 import org.openqa.selenium.Point;
 19 import org.openqa.selenium.TakesScreenshot;
 20 import org.openqa.selenium.WebDriver;
 21 import org.openqa.selenium.WebElement;
 22 
 23 import com.dbyl.libarary.utils.DriverFactory;
 24 
 25 public class TesseractTest {
 26 
 27     public static void main(String[] args) throws IOException,
 28             InterruptedException {
 29 
 30         WebDriver driver = DriverFactory.getChromeDriver();
 31         driver.get("file:///C:/Users/validation.html");
 32         driver.manage().timeouts().pageLoadTimeout(30, TimeUnit.SECONDS);
 33         WebElement element = driver.findElement(By.xpath("//img"));
 34 
 35         // take screen shot for element
 36         screenShotForElement(driver, element, "D:\Tesseract-OCR\test.png");
 37 
 38         driver.quit();
 39         
 40         // use Tesseract to get strings
 41         Runtime rt = Runtime.getRuntime();
 42         rt.exec("cmd.exe /C  tesseract.exe D:\Tesseract-OCR\test.png  D:\Tesseract-OCR\test -1 ");
 43 
 44         Thread.sleep(1000);
 45         // Read text
 46         readTextFile("D:\Tesseract-OCR\test.txt");
 47     }
 48 
 49     /**
 50      * This method for read TXT file
 51      * 
 52      * @param filePath
 53      */
 54     public static void readTextFile(String filePath) {
 55         try {
 56             String encoding = "GBK";
 57             File file = new File(filePath);
 58             if (file.isFile() && file.exists()) { // 判断文件是否存在
 59                 InputStreamReader read = new InputStreamReader(
 60                         new FileInputStream(file), encoding);// 考虑到编码格式
 61                 BufferedReader bufferedReader = new BufferedReader(read);
 62                 String lineTxt = null;
 63                 while ((lineTxt = bufferedReader.readLine()) != null) {
 64                     System.out.println(lineTxt);
 65                 }
 66                 read.close();
 67             } else {
 68                 System.out.println("找不到指定的文件");
 69             }
 70         } catch (Exception e) {
 71             System.out.println("读取文件内容出错");
 72             e.printStackTrace();
 73         }
 74     }
 75 
 76     /**
 77      * This method for screen shot element
 78      * 
 79      * @param driver
 80      * @param element
 81      * @param path
 82      * @throws InterruptedException
 83      */
 84     public static void screenShotForElement(WebDriver driver,
 85             WebElement element, String path) throws InterruptedException {
 86         File scrFile = ((TakesScreenshot) driver)
 87                 .getScreenshotAs(OutputType.FILE);
 88         try {
 89             Point p = element.getLocation();
 90             int width = element.getSize().getWidth();
 91             int height = element.getSize().getHeight();
 92             Rectangle rect = new Rectangle(width, height);
 93             BufferedImage img = ImageIO.read(scrFile);
 94             BufferedImage dest = img.getSubimage(p.getX(), p.getY(),
 95                     rect.width, rect.height);
 96             ImageIO.write(dest, "png", scrFile);
 97             Thread.sleep(1000);
 98             FileUtils.copyFile(scrFile, new File(path));
 99         } catch (IOException e) {
100             e.printStackTrace();
101         }
102     }
103 
104 }

View Code

查看全文

相关阅读:
python datetime,字符串,时间戳相互转换
 python在linux环境读取access数据库mdb文件
 ruby 随机字符串rand方法避坑
 gin 页面重定向
 go语言 goquery爬虫
 Rails项目防止时序攻击
 Authorization With Pundit
Rails/ActiveRecord order by Array
java线程池
 Java安全API

原文地址：https://www.cnblogs.com/tobecrazy/p/4691045.html

Webdriver配合Tesseract-OCR 自动识别简单的验证码

验证码： 如下，在进行自动化测试，遇到验证码的问题，一般有两种方式

验证码：如下，在进行自动化测试，遇到验证码的问题，一般有两种方式