欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页  >  后端开发

php中使用tesseract识别验证码,并且模拟登录,验证码错误

程序员文章站 2022-04-05 21:13:58
...
代码如下:
";
$curl = curl_init();
$timeout = 5;
curl_setopt($curl, CURLOPT_URL, $login_url);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($curl, CURLOPT_CONNECTTIMEOUT, $timeout);
curl_setopt($curl,CURLOPT_COOKIEJAR,$cookie_file); //获取COOKIE并存储
$contents = curl_exec($curl);
curl_close($curl);
//3.取出验证码
echo "COOKIE获取完成,正在取验证码...
"; $curl = curl_init(); curl_setopt($curl, CURLOPT_URL, $verify_code_url); curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_file);//保存cookie curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_file);//使用cookie curl_setopt($curl, CURLOPT_HEADER, 0); curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1); $img = curl_exec($curl); curl_close($curl); $codename = time(); $fp = fopen("/home/wwwroot/default/tesseract/Test/images/$codename.png","w"); echo "php中使用tesseract识别验证码,并且模拟登录,验证码错误"; fwrite($fp,$img); fclose($fp); //开始识别验证码 echo "验证码取出完成,正在休眠,正在识别验证码...
"; passthru("/usr/bin/tesseract /home/wwwroot/default/tesseract/Test/images/$codename.png /home/wwwroot/default/tesseract/Test/images/$codename"); $code = file_get_contents("./images/$codename.txt"); echo "验证码成功取出:$code
"; echo "正在准备模拟登录...
"; $post_url = "http://210.32.33.91:8080/reader/redr_verify.php"; //为安全性,此处密码不提供。 $post = "number=1111111&passwd=111111&captcha=$code&select=cert_no&returnUrl="; $curl = curl_init(); curl_setopt($curl, CURLOPT_URL, $post_url); curl_setopt($curl, CURLOPT_HEADER, false); curl_setopt($curl, CURLOPT_RETURNTRANSFER,1); curl_setopt($curl, CURLOPT_POSTFIELDS, $post); curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_file); curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_file); $result=curl_exec($curl); curl_close($curl); echo str_replace('captcha.php','http://210.32.33.91:8080/reader/captcha.php',$result);

回复内容:

代码如下:

";
$curl = curl_init();
$timeout = 5;
curl_setopt($curl, CURLOPT_URL, $login_url);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($curl, CURLOPT_CONNECTTIMEOUT, $timeout);
curl_setopt($curl,CURLOPT_COOKIEJAR,$cookie_file); //获取COOKIE并存储
$contents = curl_exec($curl);
curl_close($curl);
//3.取出验证码
echo "COOKIE获取完成,正在取验证码...
"; $curl = curl_init(); curl_setopt($curl, CURLOPT_URL, $verify_code_url); curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_file);//保存cookie curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_file);//使用cookie curl_setopt($curl, CURLOPT_HEADER, 0); curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1); $img = curl_exec($curl); curl_close($curl); $codename = time(); $fp = fopen("/home/wwwroot/default/tesseract/Test/images/$codename.png","w"); echo "php中使用tesseract识别验证码,并且模拟登录,验证码错误"; fwrite($fp,$img); fclose($fp); //开始识别验证码 echo "验证码取出完成,正在休眠,正在识别验证码...
"; passthru("/usr/bin/tesseract /home/wwwroot/default/tesseract/Test/images/$codename.png /home/wwwroot/default/tesseract/Test/images/$codename"); $code = file_get_contents("./images/$codename.txt"); echo "验证码成功取出:$code
"; echo "正在准备模拟登录...
"; $post_url = "http://210.32.33.91:8080/reader/redr_verify.php"; //为安全性,此处密码不提供。 $post = "number=1111111&passwd=111111&captcha=$code&select=cert_no&returnUrl="; $curl = curl_init(); curl_setopt($curl, CURLOPT_URL, $post_url); curl_setopt($curl, CURLOPT_HEADER, false); curl_setopt($curl, CURLOPT_RETURNTRANSFER,1); curl_setopt($curl, CURLOPT_POSTFIELDS, $post); curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_file); curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_file); $result=curl_exec($curl); curl_close($curl); echo str_replace('captcha.php','http://210.32.33.91:8080/reader/captcha.php',$result);

2016/1/25 14:51更新

Linux的话captcha目录,cookies目录给写权限
你一步步断点调试,看你那个程序生成的结果是多少,图片是多少,

php中使用tesseract识别验证码,并且模拟登录,验证码错误
代码在:https://github.com/rainwsy/sf/tree/master/library-OCR-login


更新:
你应该
1.将验证码存下来,跟文字结果对比下,
2.对比每次的session_id是否一致
3.CURLOPT_COOKIEJAR第一次用的时候存session_id就可以了,后面的操作用CURLOPT_COOKIEFILE来读取session_id,其实你可以对比下几次请求返回header头中的session_id是否一致
我的验证码识别结果:

php中使用tesseract识别验证码,并且模拟登录,验证码错误

写了个DEMO:

指出几个问题,获取session在获取验证码的那一步一并获取就OK,没必要先取得session再取验证码,
当看到账号密码隐藏的时候我再想这是给校友回答的吗?

php中使用tesseract识别验证码,并且模拟登录,验证码错误

getCaptcha();

/* 开始登陆 */
$username = '用户名';
$passwd = '密码';
$postArray = [
    'number' => $username,
    'passwd' => $passwd,
    'captcha' => $captcha,
    'select' => 'cert_no',
    'returnUrl' => ''
];
$postData = http_build_query($postArray);
echo post($loginUrl, $postData, $cookie_file);

function get($url, $cookie_file, $isCookiesSave = false)
{
    // 初始化
    $curl = curl_init($url);
    $header = array();
    $header[] = 'User-Agent: Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36';
    curl_setopt($curl, CURLOPT_HTTPHEADER, $header);
    // 不输出header头信息
    curl_setopt($curl, CURLOPT_HEADER, 0);
    if ($isCookiesSave) {
        curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_file); // 存储cookies
    } else {
        curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_file);
    }
    // 保存到字符串而不是输出
    curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
    // 是否抓取跳转后的页面
    curl_setopt($curl, CURLOPT_FOLLOWLOCATION, 1);
    $info = curl_exec($curl);
    curl_close($curl);
    return $info;
}

function post($url, $data, $cookie_file)
{
    // 初始化
    $curl = curl_init($url);
    $header = array();
    $header[] = 'User-Agent: Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36';
    curl_setopt($curl, CURLOPT_HTTPHEADER, $header);
    // 不输出header头信息
    curl_setopt($curl, CURLOPT_HEADER, 0);
    // 保存到字符串而不是输出
    curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
    curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_file);
    // post数据
    curl_setopt($curl, CURLOPT_POST, 1);
    // 请求数据
    curl_setopt($curl, CURLOPT_POSTFIELDS, $data);
    // 是否抓取跳转后的页面
    curl_setopt($curl, CURLOPT_FOLLOWLOCATION, 1);
    $response = curl_exec($curl);
    curl_close($curl);
    return $response;
}

网上的评论是 识别率低