Question

我正在尝试登录MCA门户网站（POST网址：http://www.mca.gov.in/mcafoportal/loginValidateUser.do）

我尝试使用Google Chrome上的POSTMAN应用登录，效果很好。但是，它在PHP / Python中都不起作用。我无法通过PHP / Python登录

这是PHP代码：

$url="http://www.mca.gov.in/mcafoportal/loginValidateUser.do"; 

$post_fields = array();

$post_fields['userNamedenc']='hGJfsdnk`1t';
$post_fields['passwordenc']='675894242fa9c66939d9fcf4d5c39d1830f4ddb9';
$post_fields['accessCode'] = ""

$str = call_post_mca($url, $post_fields);
$str = str_replace("&nbsp;","",$str);   

$dom = new DOMDocument();
$dom->loadHTML($str);
$xpath = new DOMXPath($dom);

$input_id =  '//input[@id="login_accessCode"]/@value';
$input_val = $xpath->query($input_id)->item(0);
$input_val1 = $input_val->nodeValue;

$url="http://www.mca.gov.in/mcafoportal/loginValidateUser.do"; 

$post_fields['userNamedenc']='hGJfsdnk`1t';
$post_fields['passwordenc']='675894242fa9c66939d9fcf4d5c39d1830f4ddb9';
$post_fields['accessCode'] = $input_val1;  //New Accesscode 

function  call_post_mca($url, $params)
{   
    #$user_agent = getRandomUserAgent();
    $user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36";
    $str = "";
    foreach($params as $key=>$value)
    {
        $str = $str . "$key=$value" . "&";
    }
    $postData = rtrim($str, "&");

    $ch = curl_init();  

    curl_setopt($ch,CURLOPT_URL,$url);
    curl_setopt($ch,CURLOPT_RETURNTRANSFER,true);
    curl_setopt($ch,CURLOPT_HEADER, false); 
    #curl_setopt($ch, CURLOPT_CAINFO, DOC_ROOT . '/includes/cacert.pem');

    curl_setopt($ch, CURLOPT_POST, 1);
    curl_setopt($ch, CURLOPT_POSTFIELDS, $postData);   


    curl_setopt($ch,CURLOPT_USERAGENT, $user_agent);
    curl_setopt ($ch, CURLOPT_FOLLOWLOCATION, 1);
    curl_setopt ($ch, CURLOPT_REFERER, $url); 

    $cookie= DOC_ROOT . "/cookie.txt";
    curl_setopt ($ch, CURLOPT_COOKIEJAR, $cookie); 
    curl_setopt ($ch, CURLOPT_COOKIEFILE, $cookie); 

    $output=curl_exec($ch);

    curl_close($ch);
    return $output;

}

知道缺少什么吗？

Answer 1

网站会进行重定向，因此您需要添加

CURLOPT_FOLLOWLOCATION => 1

到您的选项数组。如果对cURL有疑问，请尝试

$status = curl_getinfo($curl);
echo json_encode($status, JSON_PRETTY_PRINT);

给予：

{
"url": "http:\/\/www.mca.gov.in\/mcafoportal\/loginValidateUser.do?userNamedenc=hGJfsdnk%601t&passwordenc=675894242fa9c66939d9fcf4d5c39d1830f4ddb9&accessCode=-825374456",
"content_type": "text\/plain",
"http_code": 302,
"header_size": 1560,
"request_size": 245,
"filetime": -1,
"ssl_verify_result": 0,
"redirect_count": 0,
"total_time": 1.298891,
"namelookup_time": 0.526375,
"connect_time": 0.999786,
"pretransfer_time": 0.999844,
"size_upload": 0,
"size_download": 0,
"speed_download": 0,
"speed_upload": 0,
"download_content_length": 0,
"upload_content_length": -1,
"starttransfer_time": 1.298875,
"redirect_time": 0,
"redirect_url": "http:\/\/www.mca.gov.in\/mcafoportal\/login.do",
"primary_ip": "115.114.108.120",
"certinfo": [],
"primary_port": 80,
"local_ip": "192.168.1.54",
"local_port": 62524
}

如您所见，您获得了302重定向状态，但redirect_count为0。添加选项后，我得到：

{
"url": "http:\/\/www.mca.gov.in\/mcafoportal\/login.do",
"content_type": "text\/html;charset=ISO-8859-1",
"http_code": 200,
"header_size": 3131,
"request_size": 376,
"filetime": -1,
"ssl_verify_result": 0,
"redirect_count": 1,
"total_time": 2.383609,
"namelookup_time": 1.7e-5,
"connect_time": 1.7e-5,
"pretransfer_time": 4.4e-5,
"size_upload": 0,
"size_download": 42380,
"speed_download": 17779,
"speed_upload": 0,
"download_content_length": 42380,
"upload_content_length": -1,
"starttransfer_time": 0.30734,
"redirect_time": 0.915858,
"redirect_url": "",
"primary_ip": "14.140.191.120",
"certinfo": [],
"primary_port": 80,
"local_ip": "192.168.1.54",
"local_port": 62642
}

编辑 url对请求参数进行编码，然后按照重定向

进行操作

 $str = urlencode("userNamedenc=hGJfsdnk%601t&passwordenc=675894242fa9c66939d9fcf4d5c39d1830f4ddb9&accessCode=-825374456");
curl_setopt_array(
    $curl , array (
    CURLOPT_URL            => "http://www.mca.gov.in/mcafoportal/loginValidateUser.do" , // <- removed parameters here
    CURLOPT_RETURNTRANSFER => true ,
    CURLOPT_ENCODING       => "" ,
    CURLOPT_FOLLOWLOCATION => 1 ,
    CURLOPT_MAXREDIRS      => 10 ,
    CURLOPT_TIMEOUT        => 30 ,
    CURLOPT_HTTP_VERSION   => CURL_HTTP_VERSION_1_1 ,
    CURLOPT_CUSTOMREQUEST  => "POST" ,
    CURLOPT_POSTFIELDS     => $str,       // <- added this here
    CURLOPT_HTTPHEADER     => array (
        "cache-control: no-cache"
    ) ,
)
);

Answer 2

老实说，这是我很长一段时间见过的奇怪网站之一。首先要知道它是如何工作的。所以我决定使用chrome，看看当我们使用错误的数据登录时会发生什么

观察：

空白用户名和密码字段
生成用户名和密码字段的SHA1哈希，然后设置userNamedenc和respectively
我们可以直接在JavaScript中覆盖用户名和密码，只需从控制台覆盖详细信息即可登录您的帐户。
有很多不同的请求可以生成cookie，但没有一个看起来有用

因此解决问题的方法是遵循以下步骤

获取登录网址login.do
从访问代码的响应中获取表单详细信息
将表单提交至loginValidateUser.do

表单发送以下参数

现在，一个有趣的部分是在帖子数据之下

displayCaptcha:true
userEnteredCaptcha:strrty

如果我们将displayCaptcha覆盖为false，则不再需要验证码。这是一次精彩的绕行

displayCaptcha: false

接下来是在PHP中对上述所有内容进行编码，但该网站似乎很奇怪，许多尝试都失败了。所以最后我意识到我们需要更接近浏览器登录，并且我觉得需要在呼叫之间延迟

<?php

    require_once("curl.php");

    $curl = new CURL();
    $default_headers = Array(
        "Accept" => "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
        "Accept-Encoding" => "deflate",
        "Accept-Language" => "en-US,en;q=0.8",
        "Cache-Control" => "no-cache",
        "Connection" => "keep-alive",
        "DNT" => "1",
        "Pragma" => "no-cache",
        "Referer" => "http://www.mca.gov.in/mcafoportal/login.do",
        "Upgrade-Insecure-Requests" => "1"
    );

    // Get the login page 
    $curl
        ->followlocation(0)
        ->cookieejar("")
        ->verbose(1)
        ->get("http://www.mca.gov.in/mcafoportal/login.do")
        ->header($default_headers)
        ->useragent("Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36")
        ->execute();


    // Save the postfileds and access code as we would need them later for the POST field
    $post = $curl->loadInputFieldsFromResponse()
        ->updatePostParameter(array(
            "displayCaptcha" => "false",
            "userNamedenc" => "hGJfsdnk`1t",
            "passwordenc" => "675894242fa9c66939d9fcf4d5c39d1830f4ddb9",
            "userName" => "",
            "Cert" => ""))
        ->referrer("http://www.mca.gov.in/mcafoportal/login.do")
        ->removePostParameters(
            Array("dscBasedLoginFlag", "maxresults", "fe", "query", "SelectCert", "newUserRegistration")
        );

    $postfields = $curl->getPostFields();

    var_dump($postfields);


    // Access some dummy URLs to make it look like browser
    $curl
        ->get("http://www.mca.gov.in/mcafoportal/js/global.js")->header($default_headers)->execute()->sleep(2)
        ->get("http://www.mca.gov.in/mcafoportal/js/loginValidations.js")->header($default_headers)->execute()->sleep(2)
        ->get("http://www.mca.gov.in/mcafoportal/css/layout.css")->header($default_headers)->execute()->sleep(2)
        ->get("http://www.mca.gov.in/mcafoportal/img/bullet.png")->header($default_headers)->execute()->sleep(2)
        ->get("http://www.mca.gov.in/mcafoportal/getCapchaImage.do")->header($default_headers)->execute()->sleep(2);


    // POST to the login form the postfields saved earlier
    $curl
        ->sleep(20)
        ->header($default_headers)
        ->postfield($postfields)
        ->referrer("http://www.mca.gov.in/mcafoportal/login.do")
        ->post("http://www.mca.gov.in/mcafoportal/loginValidateUser.do")
        ->execute(false)
        ->sleep(3)
        ->get("http://www.mca.gov.in/mcafoportal/login.do")
        ->header($default_headers)
        ->execute(true);

    // Get the response from last GET of login.do
    $curl->getResponseText($output);

    //Check if user name is present in the output or not
    if (stripos($output, "Kiran") > 0) {
        echo "Hurray!!!! Login succeeded";
    } else {
        echo "Login failed please retry after sometime";
    }

运行代码后，它运行了几次，几次没有运行。我的观察

一次只允许一次登录。所以不确定其他人在我测试时是否使用了登录
没有延迟，大部分时间都会失败
除了站点在服务器端执行某些操作以阻止请求之外，没有明显的原因可以登录

我创建并用于链接方法的可重用curl.php位于

之下

<?php

class CURL
{
    protected $ch;
    protected $postfields;

    public function getPostFields() {
        return $this->postfields;
    }

    public function newpost()
    {
        $this->postfields = array();
        return $this;
    }

    public function addPostFields($key, $value)
    {
        $this->postfields[$key]=$value;
        return $this;
    }

    public function __construct()
    {
        $ch       = curl_init();
        $this->ch = $ch;
        $this->get()->followlocation()->retuntransfer(); //->connectiontimeout(20)->timeout(10);
    }

    function url($url)
    {
        curl_setopt($this->ch, CURLOPT_URL, $url);
        return $this;
    }

    function verbose($value = true)
    {
        curl_setopt($this->ch, CURLOPT_VERBOSE, $value);
        return $this;
    }

    function post($url='')
    {
        if ($url !== '')
            $this->url($url);
        curl_setopt($this->ch, CURLOPT_POST, count($this->postfields));
        curl_setopt($this->ch, CURLOPT_POSTFIELDS, http_build_query($this->postfields));
        return $this;
    }

    function postfield($fields)
    {
        if (is_array($fields)){
            $this->postfields = $fields;
        }
        return $this;
    }

    function close()
    {
        curl_close($this->ch);
        return $this;
    }

    function cookieejar($cjar)
    {
        curl_setopt($this->ch, CURLOPT_COOKIEJAR, $cjar);
        return $this;
    }

    function cookieefile($cfile)
    {
        curl_setopt($this->ch, CURLOPT_COOKIEFILE, $cfile);
        return $this;
    }

    function followlocation($follow = 1)
    {
        curl_setopt($this->ch, CURLOPT_FOLLOWLOCATION, $follow);
        return $this;
    }

    function loadInputFieldsFromResponse($response ='')
    {
        if ($response)
            $doc = $response;
        else
            $doc = $this->lastCurlRes;


        /* @var $doc DOMDocument */
        //simplexml_load_string($data)
        $this->getResponseDoc($doc);
        $this->postfields = array();

        foreach ($doc->getElementsByTagName('input') as $elem) {
            /* @var $elem DomNode */
            $name = $elem->getAttribute('name');
//            if (!$name)
//                $name = $elem->getAttribute('id');
            if ($name)
                $this->postfields[$name] = $elem->getAttribute("value");

        }

        return $this;
    }

    function retuntransfer($transfer=1)
    {
        curl_setopt($this->ch, CURLOPT_RETURNTRANSFER, $transfer);
        return $this;
    }

    function connectiontimeout($connectiontimeout)
    {
        curl_setopt($this->ch, CURLOPT_CONNECTTIMEOUT, $connectiontimeout);
        return $this;
    }

    function timeout($timeout)
    {
        curl_setopt($this->ch, CURLOPT_TIMEOUT, $timeout);
        return $this;
    }
    function useragent($useragent)
    {
        curl_setopt($this->ch, CURLOPT_USERAGENT, $useragent);
        return $this;
    }

    function referrer($referrer)
    {
        curl_setopt($this->ch, CURLOPT_REFERER, $referrer);
        return $this;
    }

    function getCURL()
    {
        return $this->ch;
    }

    protected $lastCurlRes;
    protected $lastCurlResInfo;

    function get($url = '')
    {
        if ($url !== '')
            $this->url($url);
        curl_setopt($this->ch, CURLOPT_POST, 0);
        curl_setopt($this->ch, CURLOPT_HTTPGET, true);
        return $this;
    }

    function sleep($seconds){
        sleep($seconds);
        return $this;
    }

    function execute($output=false)
    {
        $this->lastCurlRes = curl_exec($this->ch);

        if ($output == true)
        {
            echo "Response is \n " . $this->lastCurlRes;
            file_put_contents("out.html", $this->lastCurlRes);
        }
        $this->lastCurlResInfo = curl_getinfo($this->ch);
        $this->postfields = array();
        return $this;
    }

    function header($headers)
    {
        //curl_setopt($this->ch, CURLOPT_HEADER, true);
        curl_setopt($this->ch, CURLOPT_HTTPHEADER, $headers);
        return $this;
    }
    function getResponseText(&$text){
        $text = $this->lastCurlRes;
        return $this;
    }


    /*
     *
    * @param DOMDocument $doc
    *
    *
    */
    function getResponseDoc(&$doc){
        $doc = new DOMDocument();
        libxml_use_internal_errors(false);
        libxml_disable_entity_loader();
        @$doc->loadHTML($this->lastCurlRes);
        return $this;
    }

    function removePostParameters($keys) {
        if (!is_array($keys))
            $keys = Array($keys);

        foreach ($keys as $key){
            if (array_key_exists($key, $this->postfields))
                unset($this->postfields[$key]);
        }

        return $this;
    }

    function keepPostParameters($keys) {
        $delete = Array();
        foreach ($this->postfields as $key=>$value){
            if (!in_array($key, $keys)){
                array_push($delete, $key);
            }
        }

        foreach ($delete as $key) {
            unset($this->postfields[$key]);
        }

        return $this;
    }

    function updatePostParameter($postarray, $encoded=false)
    {
        if (is_array($postarray))
        {
            foreach ($postarray as $key => $value) {
                if (is_null($value))
                    unset($this->postfields[$key]);
                else
                    $this->postfields[$key] = $value;
            }}
        elseif (is_string($postarray))
        {
            $parr = preg_split("/&/",$postarray);
            foreach ($parr as $postvalue) {
                if (($index = strpos($postvalue, "=")) != false)
                {
                    $key = substr($postvalue, 0,$index);
                    $value = substr($postvalue, $index + 1);
                    if ($encoded)
                        $this->postfields[$key]=urldecode($value);
                    else
                        $this->postfields[$key]=$value;
                }
                else
                    $this->postfields[$postvalue] = "";
            }


        }

        return $this;
    }

    function getResponseXml(){
        //SimpleXMLElement('<INPUT/>')->asXML();
    }

    function SSLVerifyPeer($verify=false)
    {
        curl_setopt($this->ch, CURLOPT_SSL_VERIFYPEER, $verify);
        return $this;
    }
}

?>

Answer 3

@yvesleborg和@ tarun-lalwani给出了正确的提示。您需要处理cookie和重定向。但是，它总是不适合我。我想站点运营商要求两个请求之间有一些超时。

我稍微改写了你的代码来玩它。 mycurl.php：

function my_curl_init() {
    $url="http://www.mca.gov.in/mcafoportal/loginValidateUser.do"; 
    $user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36";

    $ch = curl_init();  

    curl_setopt($ch, CURLOPT_USERAGENT, $user_agent);
    curl_setopt($ch, CURLOPT_URL, $url);
    curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);

    return $ch;
}

/*
 * first call in order to get accessCode and sessionCookie
 */
$ch = my_curl_init();
curl_setopt($ch, CURLOPT_COOKIEJAR, __DIR__ . "/cookie.txt"); // else cookielist is empty

$output = curl_exec($ch);

file_put_contents(__DIR__ . '/loginValidateUser.html', $output);

// save cookie info
$cookielist = curl_getinfo($ch, CURLINFO_COOKIELIST);
//print_r($cookielist);

curl_close($ch);

// parse accessCode from output
$re = '/\<input.*name="accessCode".*value="([-0-9]+)"/';
preg_match_all($re, $output, $matches, PREG_SET_ORDER, 0);
if ($matches) {
    $accessCode = $matches[0][1];

    // debug
    echo "accessCode: $accessCode" . PHP_EOL;   


    /*
     * second call in order to login
     */ 

    $post_fields = array(
        'userNamedenc' => 'hGJfsdnk`1t',
        'passwordenc'  => '675894242fa9c66939d9fcf4d5c39d1830f4ddb9',
        'accessCode'   => $accessCode
    );

    $cookiedata = preg_split('/\s+/', $cookielist[0]);
    $session_cookie = $cookiedata[5] . '=' . $cookiedata[6];

    // debug
    echo "sessionCookie: $session_cookie" . PHP_EOL;
    file_put_contents(__DIR__ . '/cookie2.txt', $session_cookie);

    /* 
     * !!! pause !!!
     */  
    sleep(20);

    // debug
    echo "curl -v -L -X POST -b '$session_cookie;' --data 'userNamedenc=hGJfsdnk`1t&passwordenc=675894242fa9c66939d9fcf4d5c39d1830f4ddb9&accessCode=$accessCode' http://www.mca.gov.in/mcafoportal/loginValidateUser.do > loginValidateUser2.html";

    $ch = my_curl_init();  

    curl_setopt($ch, CURLOPT_POST, 1);
    curl_setopt($ch, CURLOPT_POSTFIELDS, $post_fields);   

    curl_setopt($ch, CURLOPT_COOKIE, $session_cookie);

    $output = curl_exec($ch);

    file_put_contents(__DIR__ . '/loginValidateUser2.html', $output);

    curl_close($ch);
}

该脚本向网站发出两个请求。第一个的输出用于读取accessCode并存储会话cookie。然后在稍微休息之后，使用accessCode和会话信息以及登录凭证发布第二个。

我使用PHP5.6从终端（php -f mycurl.php）测试了它。该脚本调试所有必要的信息，输出您可以在终端中使用的curl命令，并将HTML和cookie信息记录到脚本等同一文件夹中的某些文件。

经常运行脚本不起作用。登录无效。因此，请花时间在尝试之间等待几分钟。或者更改您的IP;）

希望它有所帮助。

Answer 4

问题的复制

我在Postman中做了同样的事情，就像截图一样，但无法登录：

我能看到的唯一区别是你的请求有cookie，我怀疑这是你能够在没有所有其他输入字段的情况下登录的原因。似乎有很多输入字段：

使用邮递员

所以，我使用postman拦截来捕获登录期间使用的所有字段，包括验证码和访问代码，我能够登录：

更新1

我发现，一旦您解决了验证码以便登录，在您退出后，您可以在表格数据中没有displayCaptcha和userEnteredCaptcha的情况下重新登录，已提供您使用的Cookie与您用于成功登录的Cookie相同。您只需从登录页面获取有效的accessCode。

Answer 5

it doesnt work either in PHP/Python那是（正如其他人已经指出的那样），因为您使用的是浏览器现有的cookie会话，已经解决了验证码。清除您的浏览器cookie，获得一个新的cookie会话，并且不要解决CAPTCHA，Postman也将无法登录。 Any idea what is missing ?有几件事，其中包括几个帖子后登录参数（browserFlag，loginType，__checkbox_dscBasedLoginFlag等等，这里你的编码循环也是错误的$str = $str . "$key=$value" . "&";，只要键和值都只包含[a-zA-Z0-9]字符，它几乎只能工作并且由于您的userNamedenc包含严重的重音字符，因此您的编码循环不足。

是一个固定的循环

foreach($params as $key=>$value){
    $str = $str . urlencode($key)."=".urlencode($value) . "&";
}
$str=substr($str,0,-1);

，但是这正是为什么我们有http_build_query函数，整个循环和以下修剪可以用这一行代替：

$str=http_build_query($params);

，似乎你在没有预先存在的cookie会话的情况下尝试登录，那不行。当您对登录页面发出GET请求时，您会获得一个cookie和一个唯一的验证码，验证码答案与您的cookie会话相关联，需要在您尝试登录之前解决，你也没有提供代码来处理验证码。另外，在解析“userName”输入元素时，它将默认为“输入用户名”，用javascript清空并替换为userNamedenc，你必须在PHP中复制它，另外，它将有一个名为“dscBasedLoginFlag”的输入元素，使用javascript删除，你还必须在php中执行此部分，它还有一个名为“Cert”的输入元素，它有一个默认值，但这个值用javascript清除，在php中也一样，和一个名为“newUserRegistration”的输入元素，使用javascript删除，执行此操作，

这是你应该做的：向登录页面发出GET请求，保存cookie会话并确保为所有进一步的请求提供它，并解析所有登录表单的元素并将它们添加到您的登录请求中（但是小心，有2x表单输入，1个属于搜索栏，只解析登录表单的子项，不要混合2 ），并记得清除/删除特殊输入标签模仿javascript，如上所述，然后向验证码网址发出GET请求，确保提供会话cookie，解决验证码，然后使用验证码答案，userNamedenc和passwordenc以及所有其他元素进行最终登录请求从登录页面解析出...应该可以工作。现在，以编程方式解决验证码， captha看起来不太硬，破解它可能是自动化的，但直到有人真的这样做，你可以使用Deathbycaptcha为你做，但请注意，它不是免费服务。

这是一个经过全面测试的实用示例实现，使用我的hhb_curl库（来自https://github.com/divinity76/hhb_.inc.php/blob/master/hhb_.inc.php）和Deathbycaptcha api：

<?php
declare(strict_types = 1);
header ( "content-type: text/plain;charset=utf8" );
require_once ('hhb_.inc.php');
const DEATHBYCATPCHA_USERNAME = '?';
const DEATHBYCAPTCHA_PASSWORD = '?';
$hc = new hhb_curl ( '', true );
$hc->setopt(CURLOPT_TIMEOUT,20);// im on a really slow net atm :(
$html = $hc->exec ( 'http://www.mca.gov.in/mcafoportal/login.do' )->getResponseBody (); // cookie session etc
$domd = @DOMDocument::loadHTML ( $html );
$inputs = getDOMDocumentFormInputs ( $domd, true ) ['login'];
$params = [ ];
foreach ( $inputs as $tmp ) {
    $params [$tmp->getAttribute ( "name" )] = $tmp->getAttribute ( "value" );
}
assert ( isset ( $params ['userNamedenc'] ), 'username input not found??' );
assert ( isset ( $params ['passwordenc'] ), 'passwordenc input not found??' );
$params ['userName'] = ''; // defaults to "Enter Username", cleared with javascript
unset ( $params ['dscBasedLoginFlag'] ); // removed with javascript
$params ['Cert'] = ''; // cleared to emptystring with javascript
unset ( $params ['newUserRegistration'] ); // removed with javascript
unset ( $params ['SelectCert'] ); // removed with javascript
$params ['userNamedenc'] = 'hGJfsdnk`1t';
$params ['passwordenc'] = '675894242fa9c66939d9fcf4d5c39d1830f4ddb9';
echo 'parsed login parameters: ';
var_dump ( $params );
$captchaRaw = $hc->exec ( 'http://www.mca.gov.in/mcafoportal/getCapchaImage.do' )->getResponseBody ();
$params ['userEnteredCaptcha'] = solve_captcha2 ( $captchaRaw );
// now actually logging in.
$html = $hc->setopt_array ( array (
        CURLOPT_POST => true,
        CURLOPT_POSTFIELDS => http_build_query ( $params ) 
) )->exec ( 'http://www.mca.gov.in/mcafoportal/loginValidateUser.do' )->getResponseBody ();
var_dump ( $hc->getStdErr (), $hc->getStdOut () ); // printing debug data
$domd = @DOMDocument::loadHTML ( $html );
$xp = new DOMXPath ( $domd );
$loginErrors = $xp->query ( '//ul[@class="errorMessage"]' );
if ($loginErrors->length > 0) {
    echo 'encountered following error(s) logging in: ';
    foreach ( $loginErrors as $err ) {
        echo $err->textContent, PHP_EOL;
    }
    die ();
}
echo "logged in successfully!";
/**
 * solves the captcha manually, by doing: echo ANSWER>captcha.txt
 *
 * @param string $raw_image
 *          raw image bytes
 * @return string answer
 */
function solve_captcha2(string $raw_image): string {
    $imagepath = getcwd () . DIRECTORY_SEPARATOR . 'captcha.png';
    $answerpath = getcwd () . DIRECTORY_SEPARATOR . 'captcha.txt';
    @unlink ( $imagepath );
    @unlink ( 'captcha.txt' );
    file_put_contents ( $imagepath, $raw_image );
    echo 'the captcha is saved in ' . $imagepath . PHP_EOL;
    echo ' waiting for you to solve it by doing: echo ANSWER>' . $answerpath, PHP_EOL;
    while ( true ) {
        sleep ( 1 );
        if (file_exists ( $answerpath )) {
            $answer = trim ( file_get_contents ( $answerpath ) );
            echo 'solved: ' . $answer, PHP_EOL;
            return $answer;
        }
    }
}
function solve_captcha(string $raw_image): string {
    echo 'solving captcha, hang on, with DEATBYCAPTCHA this usually takes between 10 and 20 seconds.';
    {
        // unfortunately, CURLFile requires a filename, it wont accept a string, so make a file of it
        $tmpfileh = tmpfile ();
        fwrite ( $tmpfileh, $raw_image ); // TODO: error checking (incomplete write or whatever)
        $tmpfile = stream_get_meta_data ( $tmpfileh ) ['uri'];
    }
    $hc = new hhb_curl ( '', true );
    $hc->setopt_array ( array (
            CURLOPT_URL => 'http://api.dbcapi.me/api/captcha',
            CURLOPT_POSTFIELDS => array (
                    'username' => DEATHBYCATPCHA_USERNAME,
                    'password' => DEATHBYCAPTCHA_PASSWORD,
                    'captchafile' => new CURLFile ( $tmpfile, 'image/png', 'captcha.png' ) 
            ) 
    ) )->exec ();
    fclose ( $tmpfileh ); // when tmpfile() is fclosed(), its also implicitly deleted.
    $statusurl = $hc->getinfo ( CURLINFO_EFFECTIVE_URL ); // status url is given in a http 300x redirect, which hhb_curl auto-follows
    while ( true ) {
        // wait for captcha to be solved.
        sleep ( 10 );
        echo '.';
        $json = $hc->setopt_array ( array (
                CURLOPT_HTTPHEADER => array (
                        'Accept: application/json' 
                ),
                CURLOPT_HTTPGET => true 
        ) )->exec ()->getResponseBody ();
        $parsed = json_decode ( $json, false );
        if (! empty ( $parsed->captcha )) {
            echo 'captcha solved!: ' . $parsed->captcha, PHP_EOL;
            return $parsed->captcha;
        }
    }
}
function getDOMDocumentFormInputs(\DOMDocument $domd, bool $getOnlyFirstMatches = false): array {
    // :DOMNodeList?
    $forms = $domd->getElementsByTagName ( 'form' );
    $parsedForms = array ();
    $isDescendantOf = function (\DOMNode $decendant, \DOMNode $ele): bool {
        $parent = $decendant;
        while ( NULL !== ($parent = $parent->parentNode) ) {
            if ($parent === $ele) {
                return true;
            }
        }
        return false;
    };
    // i can't use array_merge on DOMNodeLists :(
    $merged = function () use (&$domd): array {
        $ret = array ();
        foreach ( $domd->getElementsByTagName ( "input" ) as $input ) {
            $ret [] = $input;
        }
        foreach ( $domd->getElementsByTagName ( "textarea" ) as $textarea ) {
            $ret [] = $textarea;
        }
        foreach ( $domd->getElementsByTagName ( "button" ) as $button ) {
            $ret [] = $button;
        }
        return $ret;
    };
    $merged = $merged ();
    foreach ( $forms as $form ) {
        $inputs = function () use (&$domd, &$form, &$isDescendantOf, &$merged): array {
            $ret = array ();
            foreach ( $merged as $input ) {
                // hhb_var_dump ( $input->getAttribute ( "name" ), $input->getAttribute ( "id" ) );
                if ($input->hasAttribute ( "disabled" )) {
                    // ignore disabled elements?
                    continue;
                }
                $name = $input->getAttribute ( "name" );
                if ($name === '') {
                    // echo "inputs with no name are ignored when submitted by mainstream browsers (presumably because of specs)... follow suite?", PHP_EOL;
                    continue;
                }
                if (! $isDescendantOf ( $input, $form ) && $form->getAttribute ( "id" ) !== '' && $input->getAttribute ( "form" ) !== $form->getAttribute ( "id" )) {
                    // echo "this input does not belong to this form.", PHP_EOL;
                    continue;
                }
                if (! array_key_exists ( $name, $ret )) {
                    $ret [$name] = array (
                            $input 
                    );
                } else {
                    $ret [$name] [] = $input;
                }
            }
            return $ret;
        };
        $inputs = $inputs (); // sorry about that, Eclipse gets unstable on IIFE syntax.
        $hasName = true;
        $name = $form->getAttribute ( "id" );
        if ($name === '') {
            $name = $form->getAttribute ( "name" );
            if ($name === '') {
                $hasName = false;
            }
        }
        if (! $hasName) {
            $parsedForms [] = array (
                    $inputs 
            );
        } else {
            if (! array_key_exists ( $name, $parsedForms )) {
                $parsedForms [$name] = array (
                        $inputs 
                );
            } else {
                $parsedForms [$name] [] = $tmp;
            }
        }
    }
    unset ( $form, $tmp, $hasName, $name, $i, $input );
    if ($getOnlyFirstMatches) {
        foreach ( $parsedForms as $key => $val ) {
            $parsedForms [$key] = $val [0];
        }
        unset ( $key, $val );
        foreach ( $parsedForms as $key1 => $val1 ) {
            foreach ( $val1 as $key2 => $val2 ) {
                $parsedForms [$key1] [$key2] = $val2 [0];
            }
        }
    }
    return $parsedForms;
}

示例用法：在终端中，写一下php foo.php | tee test.html，几秒后会说出类似的内容：

the captcha is saved in /home/captcha.png
 waiting for you to solve it by doing: echo ANSWER>/home/captcha.txt

然后查看/home/captcha.png中的验证码，解决它，并在另一个终端写入：echo ANSWER>/home/captcha.txt，现在脚本将登录，并将登录的html转储到test.html中，您可以在浏览器中打开，确认它实际登录，运行时截图：https://image.prntscr.com/image/_AsB_0J6TLOFSZuvQdjyNg.png

另请注意，我制作了2个验证码求解器函数，1个使用deathbycaptcha api，并且在第5行和第6行提供有效且有信誉的deathbycaptcha帐户之前不会工作，这不是免费的，另外1，solve_captcha2，问你自己解决验证码，并告诉你验证验证码图像的位置（这样你就可以看看它），以及要写入的命令行参数，以便为它提供答案。只需在第28行将solve_captcha替换为solve_captcha2，即可手动解决，反之亦然。使用solve_captcha2对脚本进行了全面测试，但是deadbycaptcha解算器未经测试，因为我的deathbycatpcha帐户是空的（如果你想捐款，所以我可以实际测试它，发送7美元到paypal帐户divinity76@gmail.com与链接到这个主题，我将购买最便宜的deathbycaptcha信用包并实际测试它）

免责声明：我不会以任何方式与deathbycaptcha联系（除了我几年前他们是他们的客户），这篇文章没有赞助。

Answer 6

你可以做的最简单的事情，因为你已经在POSTMAN中使用它，就是在POSTMAN中渲染PHP代码。 Here是从POSTMAN获取PHP代码的链接。然后，您可以将POSTMAN示例与您的代码进行比较。

<?php

$curl = curl_init();

curl_setopt_array($curl, array(
  CURLOPT_URL => "http://www.mca.gov.in/mcafoportal/loginValidateUser.do?userNamedenc=hGJfsdnk%601t&passwordenc=675894242fa9c66939d9fcf4d5c39d1830f4ddb9&accessCode=",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_HTTPHEADER => array(
    "cache-control: no-cache",
    "postman-token: b54abdc0-17be-f38f-9aba-dbf8f007de99"
  ),
));

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

立即突然出现的是这个＆＃39; hGJfsdnk`1t＆＃39;。向后引用可以是转义字符“＆＃39;”。这很可能会引发错误，错误处理会重定向回登录页面。 POSTMAN可能内置了一些内容来将转义字符呈现给＆＃39; hGJfsdnk％601t＆＃39;。因此，这适用于POSTMAN，但不适用于您的代码。

以下是此请求的状态：

{
"url": "http:\/\/www.mca.gov.in\/mcafoportal\/login.do",
"content_type": "text\/html;charset=ISO-8859-1",
"http_code": 200,
"header_size": 3020,
"request_size": 821,
"filetime": -1,
"ssl_verify_result": 0,
"redirect_count": 1,
"total_time": 2.920125,
"namelookup_time": 8.2e-5,
"connect_time": 8.7e-5,
"pretransfer_time": 0.000181,
"size_upload": 0,
"size_download": 42381,
"speed_download": 14513,
"speed_upload": 0,
"download_content_length": -1,
"upload_content_length": -1,
"starttransfer_time": 0.320995,
"redirect_time": 2.084554,
"redirect_url": "",
"primary_ip": "115.114.108.120",
"certinfo": [],
"primary_port": 80,
"local_ip": "192.168.1.3",
"local_port": 45086
}

此处显示成功登录。

PHP Curl请求不起作用，但在POSTMAN中工作正常

6 个答案: