如何用 Guzzle 和 cookie jar 在 PHP 中识别 CaptchaFox

# PHP 8.4 or later, then the SDK and Guzzle 7 or 8
composer require capskip/capskip guzzlehttp/guzzle

<?php
// composer require capskip/capskip guzzlehttp/guzzle
declare(strict_types=1);

require __DIR__ . '/vendor/autoload.php';

use GuzzleHttp\Client;
use GuzzleHttp\TransferStats;

const PAGE_URL = 'https://example.com/signup';

// cookies: one jar for every request, redirects included.
// http_errors: a 403 comes back as a response, not an exception.
$http = new Client(['cookies' => true, 'http_errors' => false]);

$pageUrl = PAGE_URL;
$page = $http->get(PAGE_URL, [
    // Runs for every hop, so it ends on the address the page came from.
    'on_stats' => function (TransferStats $stats) use (&$pageUrl) {
        $pageUrl = (string) $stats->getEffectiveUri();
    },
]);
// With http_errors off, a blocked or missing page arrives as a response.
if ($page->getStatusCode() !== 200) {
    throw new RuntimeException("GET $pageUrl returned " . $page->getStatusCode());
}
$html = (string) $page->getBody();

// PHP 8.4's HTML5 parser; it reads UTF-8 without a meta charset.
$doc = Dom\HTMLDocument::createFromString($html, LIBXML_NOERROR);

// The container, matched on the whole class name.
$widget = $doc->querySelector('.captchafox');
// MAM pages load this package and may carry the key in its src.
$mamSrc = $doc->querySelector('script[src*="mampkg/@mamdev/core.frontend.libs.captchafox"]')?->getAttribute('src');

$sitekey = $widget?->getAttribute('data-sitekey');
if ($sitekey === null && $mamSrc !== null) {
    parse_str((string) parse_url($mamSrc, PHP_URL_QUERY), $query);
    $sitekey = $query['key'] ?? null;
}
if ($sitekey === null && preg_match('/captchafox\.render\([\s\S]{0,300}?["\']?sitekey["\']?\s*:\s*["\']([^"\']+)/', $html, $m)) {
    $sitekey = $m[1];
}
$form = $widget?->closest('form') ?? $doc->querySelector('form');
if ($sitekey === null || $form === null) {
    throw new RuntimeException('No sitekey or form in the HTML; find them in DevTools.');
}
echo $sitekey, $mamSrc !== null ? ' (MAM page)' : '', PHP_EOL;

use CapSkip\CapSkip;

// Copied from the script tag on MAM pages.
const MAM_PACKAGE = 'https://s.uicdn.com/mampkg/@mamdev/core.frontend.libs.captchafox/';

$solver = new CapSkip(['host' => '127.0.0.1', 'port' => 8080]);

$result = $solver->captchafox($sitekey, $pageUrl, [
    // null is dropped, so the standard widget sends nothing extra.
    'api_server' => $mamSrc !== null ? MAM_PACKAGE : null,
]);

echo substr($result['token'], 0, 24), PHP_EOL;     // goes in cf-captcha-response
echo $result['userAgent'] ?? '(none)', PHP_EOL;    // the browser that minted it

use GuzzleHttp\Psr7\Uri;
use GuzzleHttp\Psr7\UriResolver;

// The fields a browser would send for this form, CSRF token included.
$fields = [];
foreach ($form->querySelectorAll('input[name]:not([disabled])') as $input) {
    $type = strtolower($input->getAttribute('type') ?? 'text');
    if (in_array($type, ['submit', 'button', 'image', 'file', 'reset'], true)) continue;
    $checkable = in_array($type, ['checkbox', 'radio'], true);
    if ($checkable && !$input->hasAttribute('checked')) continue;
    // A checked box with no value attribute submits "on".
    $fields[$input->getAttribute('name')] = $input->getAttribute('value') ?? ($checkable ? 'on' : '');
}
$fields['email'] = 'YOUR_EMAIL';
$fields['cf-captcha-response'] = $result['token'];

// Browsers send the page as Referer; strict servers want one.
$headers = ['Referer' => $pageUrl];
// Without this, Guzzle announces itself as GuzzleHttp/8 (or /7).
if (isset($result['userAgent'])) {
    $headers['User-Agent'] = $result['userAgent'];
}

// Resolve the form's action against the page, as a browser would.
$action = UriResolver::resolve(new Uri($pageUrl), new Uri(trim($form->getAttribute('action') ?? '')));
$response = $http->post($action, ['form_params' => $fields, 'headers' => $headers]);
echo $response->getStatusCode(), PHP_EOL;

use CapSkip\Exceptions\ApiException;

function solveCaptchaFox(\CapSkip\CapSkip $solver, string $sitekey, string $url, array $options = [], int $attempts = 3): array
{
    for ($attempt = 1; ; $attempt++) {
        try {
            return $solver->captchafox($sitekey, $url, $options);
        } catch (ApiException $e) {
            // Select, audio and unreadable slide draws come back unsolvable;
            // redraw. Anything else, such as a wrong API key, is final.
            if (!str_contains($e->getMessage(), 'UNSOLVABLE') || $attempt === $attempts) {
                throw $e;
            }
        }
    }
}

<?php
// composer require capskip/capskip guzzlehttp/guzzle
// signup.php: run with php signup.php (PHP 8.4 or later)
declare(strict_types=1);

require __DIR__ . '/vendor/autoload.php';

use CapSkip\CapSkip;
use CapSkip\Exceptions\ApiException;
use CapSkip\Exceptions\CapSkipError;
use CapSkip\Exceptions\TimeoutException;
use CapSkip\Exceptions\ValidationException;
use GuzzleHttp\Client;
use GuzzleHttp\Psr7\Uri;
use GuzzleHttp\Psr7\UriResolver;
use GuzzleHttp\TransferStats;

const PAGE_URL = 'https://example.com/signup';
// Copied from the script tag on MAM pages.
const MAM_PACKAGE = 'https://s.uicdn.com/mampkg/@mamdev/core.frontend.libs.captchafox/';

function solveCaptchaFox(CapSkip $solver, string $sitekey, string $url, array $options = [], int $attempts = 3): array
{
    for ($attempt = 1; ; $attempt++) {
        try {
            return $solver->captchafox($sitekey, $url, $options);
        } catch (ApiException $e) {
            // Select, audio and unreadable slide draws come back unsolvable.
            if (!str_contains($e->getMessage(), 'UNSOLVABLE') || $attempt === $attempts) {
                throw $e;
            }
            echo "attempt $attempt: ", $e->getMessage(), PHP_EOL;
        }
    }
}

function signUp(CapSkip $solver, string $url, string $email): int
{
    // A new client per run, so its cookie jar holds this session only.
    $http = new Client(['cookies' => true, 'http_errors' => false]);
    $pageUrl = $url;
    $page = $http->get($url, [
        'on_stats' => function (TransferStats $stats) use (&$pageUrl) {
            $pageUrl = (string) $stats->getEffectiveUri();
        },
    ]);
    if ($page->getStatusCode() !== 200) {
        throw new RuntimeException("GET $pageUrl returned " . $page->getStatusCode());
    }
    $html = (string) $page->getBody();
    $doc = Dom\HTMLDocument::createFromString($html, LIBXML_NOERROR);

    $widget = $doc->querySelector('.captchafox');
    $mamSrc = $doc->querySelector('script[src*="mampkg/@mamdev/core.frontend.libs.captchafox"]')?->getAttribute('src');
    $sitekey = $widget?->getAttribute('data-sitekey');
    if ($sitekey === null && $mamSrc !== null) {
        parse_str((string) parse_url($mamSrc, PHP_URL_QUERY), $query);
        $sitekey = $query['key'] ?? null;
    }
    if ($sitekey === null && preg_match('/captchafox\.render\([\s\S]{0,300}?["\']?sitekey["\']?\s*:\s*["\']([^"\']+)/', $html, $m)) {
        $sitekey = $m[1];
    }
    $form = $widget?->closest('form') ?? $doc->querySelector('form');
    if ($sitekey === null || $form === null) {
        throw new RuntimeException('No sitekey or form in the HTML; find them in DevTools.');
    }

    $result = solveCaptchaFox($solver, $sitekey, $pageUrl, [
        'api_server' => $mamSrc !== null ? MAM_PACKAGE : null,
    ]);

    $fields = [];
    foreach ($form->querySelectorAll('input[name]:not([disabled])') as $input) {
        $type = strtolower($input->getAttribute('type') ?? 'text');
        if (in_array($type, ['submit', 'button', 'image', 'file', 'reset'], true)) continue;
        $checkable = in_array($type, ['checkbox', 'radio'], true);
        if ($checkable && !$input->hasAttribute('checked')) continue;
        $fields[$input->getAttribute('name')] = $input->getAttribute('value') ?? ($checkable ? 'on' : '');
    }
    $fields['email'] = $email;
    $fields['cf-captcha-response'] = $result['token'];

    $headers = ['Referer' => $pageUrl];
    if (isset($result['userAgent'])) {
        $headers['User-Agent'] = $result['userAgent'];
    }
    $action = UriResolver::resolve(new Uri($pageUrl), new Uri(trim($form->getAttribute('action') ?? '')));

    return $http->post($action, ['form_params' => $fields, 'headers' => $headers])->getStatusCode();
}

$solver = new CapSkip([
    'apiKey' => getenv('CAPSKIP_API_KEY') ?: 'capskip',
    'host' => getenv('CAPSKIP_HOST') ?: '127.0.0.1',
    'port' => (int) (getenv('CAPSKIP_PORT') ?: 8080),
]);

try {
    $status = signUp($solver, PAGE_URL, 'YOUR_EMAIL');
    echo $status, PHP_EOL;
    // A 4xx from the site means the post was refused.
    exit($status < 400 ? 0 : 1);
} catch (ValidationException $e) {
    fwrite(STDERR, 'not sent: ' . $e->getMessage() . PHP_EOL);
    exit(1);
} catch (TimeoutException $e) {
    fwrite(STDERR, 'gave up after recaptchaTimeout' . PHP_EOL);
    exit(1);
} catch (CapSkipError | RuntimeException $e) {
    // Guzzle's transfer errors are RuntimeExceptions too.
    fwrite(STDERR, get_class($e) . ': ' . $e->getMessage() . PHP_EOL);
    exit(1);
}