PHP code example of paslandau / guzzle-rotating-proxy-subscriber

    
        
<?php
require_once('vendor/autoload.php');

/* Start to develop here. Best regards https://php-download.com/ */

    

paslandau / guzzle-rotating-proxy-subscriber example snippets

// define proxies
$proxy1 = new RotatingProxy("username:[email protected]:4711");
$proxy2 = new RotatingProxy("username:[email protected]:4711");

// setup and attach subscriber
$rotator = new ProxyRotator([$proxy1,$proxy2]);
$sub = new RotatingProxySubscriber($rotator);
$client = new Client();
$client->getEmitter()->attach($sub);

// perform the requests
$num = 10;
$url = "http://www.myseosolution.de/scripts/myip.php";
for ($i = 0; $i < $num; $i++) {
    $request =  $client->createRequest("GET",$url);
    try {
        $response = $client->send($request);
        echo "Success with " . $request->getConfig()->get("proxy") . " on $i. request\n";
    } catch (Exception $e) {
        echo "Failed with " . $request->getConfig()->get("proxy") . " on $i. request: " . $e->getMessage() . "\n";
    }
}

$evaluation = function(RotatingProxyInterface $proxy, AbstractTransferEvent $event){
    if($event instanceof CompleteEvent){
        $content = $event->getResponse()->getBody();
        // example of a custom message returned by a target system
        // for a blocked IP
        $pattern = "#Sorry! You made too many requests, your IP is blocked#";
        if(preg_match($pattern,$content)){
            // The current proxy seems to be blocked
            // so let's mark it as blocked
            $proxy->block();
            return false;
        }else{
            // nothing went wrong, the request was successful
            return true;
        }
    }else{
        // We didn't get a CompleteEvent maybe
        // due to some connection issues at the proxy
        // so let's mark the request as failed
        return false;
    }
};

$proxy = new RotatingProxy("username:[email protected]:4711", $evaluation);
// or
$proxy->setEvaluationFunction($evaluation);

// function specific to your domain model that performs the evaluation
function domain_specific_evaluation(AbstractTransferEvent $event){
    if($event instanceof CompleteEvent){
        $content = $event->getResponse()->getBody();
        // example of a custom message returned by a target system
        // for a blocked IP
        $pattern = "#Sorry! You made too many requests, your IP is blocked#";
        if(preg_match($pattern,$content)){
            // The current proxy seems to be blocked
            // so let's mark it as blocked
            $event->getRequest()->getConfig()->set(RotatingProxyInterface::GUZZLE_CONFIG_KEY_REQUEST_RESULT, RotatingProxyInterface::GUZZLE_CONFIG_VALUE_REQUEST_RESULT_BLOCKED);
            return false;
        }else{
            // nothing went wrong, the request was successful
            $event->getRequest()->getConfig()->set(RotatingProxyInterface::GUZZLE_CONFIG_KEY_REQUEST_RESULT, RotatingProxyInterface::GUZZLE_CONFIG_VALUE_REQUEST_RESULT_SUCCESS);
            return true;
        }
    }else{
        // We didn't get a CompleteEvent maybe
        // due to some connection issues at the proxy
        // so let's mark the request as failed
        $event->getRequest()->getConfig()->set(RotatingProxyInterface::GUZZLE_CONFIG_KEY_REQUEST_RESULT, RotatingProxyInterface::GUZZLE_CONFIG_VALUE_REQUEST_RESULT_FAILURE);
        return false;
    }
}

$evaluation = function(RotatingProxyInterface $proxy, AbstractTransferEvent $event){
    $result = $event->getRequest()->getConfig()->get(RotatingProxyInterface::GUZZLE_CONFIG_KEY_REQUEST_RESULT);
    switch($result){
        case RotatingProxyInterface::GUZZLE_CONFIG_VALUE_REQUEST_RESULT_SUCCESS:{
            return true;
        }
        case RotatingProxyInterface::GUZZLE_CONFIG_VALUE_REQUEST_RESULT_FAILURE:{
            return false;
        }
        case RotatingProxyInterface::GUZZLE_CONFIG_VALUE_REQUEST_RESULT_BLOCKED:{
            $proxy->block();
            return false;
        }
        default: throw new RuntimeException("Unknown value '{$result}' for config key ".RotatingProxyInterface::GUZZLE_CONFIG_KEY_REQUEST_RESULT);
    }
};

$proxy = new RotatingProxy("username:[email protected]:4711", $evaluation);
// or
$proxy->setEvaluationFunction($evaluation);

$maximumFails = 100;
$consecutiveFails = 5;

$proxy = new RotatingProxy("username:[email protected]:4711", null,$consecutiveFails,$maximumFails);
// or
$proxy->setMaxTotalFails($maximumFails);
$proxy->setMaxConsecutiveFails($consecutiveFails);

$from = 1;
$to = 5;
$wait = new RandomTimeInterval($from,$to);

$proxy = new RotatingProxy("username:[email protected]:4711", null,null,null,$wait);
// or
$proxy->setWaitInterval($wait);

$rotator = new ProxyRotator($proxies);

$waitFn = function (WaitingEvent $event){
    $proxy = $event->getProxy();
    echo "All proxies have a timeout restriction, the lowest is {$proxy->getWaitingTime()}s!\n";
    // nah, we don't wanna wait
    $event->skipWaiting();
};

$rotator->getEmitter()->on(ProxyRotator::EVENT_ON_WAIT, $waitFn);

$proxies = [/* ... */];
$useOwnIp = true;
$rotator = new ProxyRotator($proxies,$useOwnIp);
// or
$rotator->setUseOwnIp($useOwnIp);

$infoFn = function (UseOwnIpEvent $event){
    echo "No proxies are left, making a direct request!\n";
};

$rotator->getEmitter()->on(ProxyRotator::EVENT_ON_USE_OWN_IP,$infoFn);

$s = "
username:[email protected]:4711
username:[email protected]:4711
username:[email protected]:4711
";

$rotator = Build::rotator()
    ->failsIfNoProxiesAreLeft()                         // throw exception if no proxies are left
    ->withProxiesFromString($s, "\n")                   // build proxies from a string of proxies
                                                        // where each proxy is seperated by a new line
    ->evaluatesProxyResultsByDefault()                  // use the default evaluation function
    ->eachProxyMayFailInfinitlyInTotal()                // don't care about total number of fails for a proxy
    ->eachProxyMayFailConsecutively(5)                  // but block a proxy if it fails 5 times in a row
    ->eachProxyNeedsToWaitSecondsBetweenRequests(1, 3)  // and let it wait between 1 and 3 seconds before making another request
    ->build();

$s = "
username:[email protected]:4711
username:[email protected]:4711
username:[email protected]:4711
";

$lines = explode("\n",$s);
$proxies = [];
foreach($lines as $line){
    $trimmed = trim($line);
    if($trimmed != ""){
        $wait = new RandomTimeInterval(1,3);
        $proxies[$trimmed] = new RotatingProxy($trimmed,null,5,-1,$wait);
    }
}
$rotator = new ProxyRotator($proxies,false);

$userAgent = "Mozilla/5.0 (Windows NT 6.3; WOW64; rv:37.0) Gecko/20100101 Firefox/37.0"; // common user agent string for firefox
$defaultRequestHeaders = ["Accept-Language" => "de,en"]; // add a preferred language to each of our requests
$cookieSession = new CookieJar(); // enable cookies for this identity

$identity = new Identity($userAgent,$defaultRequestHeaders,$cookieSession);
$identities = [$identity];
$proxy1 = new RotatingIdentityProxy($identities, "[PROXY 1]");

$userAgent = "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36"; // common user agent string for chrome
$defaultRequestHeaders = ["Accept-Language" => "de"]; // add a preferred language to each of our requests
$cookieSession = null; // disable cookies for this identity

$identity1 = new Identity($userAgent,$defaultRequestHeaders,$cookieSession);

$userAgent = "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)"; // common user agent string for Internet Explorer
$defaultRequestHeaders = ["Pragma" => "no-cache"]; // add a no-cache directive to each request
$cookieSession = new CookieJar(); // enable cookies for this identity

$identity2 = new Identity($userAgent,$defaultRequestHeaders,$cookieSession);

$identities = [$identity1,$identity2];
$systemRandomizer = new SystemRandomizer();

// switch identities randomly after 2 to 5 requests
$minRequests = 2;
$maxRequests = 5;
$counter = new RandomCounterInterval($minRequests,$maxRequests);
$proxy2 = new RotatingIdentityProxy($identities, "[PROXY 2]",$systemRandomizer,$counter);

$s = "
username:[email protected]:4711
username:[email protected]:4711
username:[email protected]:4711
";

$identities = [
    new Identity(/*...*/),
    new Identity(/*...*/),
    new Identity(/*...*/),
    new Identity(/*...*/),
    new Identity(/*...*/),
    /*..*/
];

$rotator = Build::rotator()
    ->failsIfNoProxiesAreLeft()                         // throw exception if no proxies are left
    ->withProxiesFromString($s, "\n")                   // build proxies from a string of proxies
                                                        // where each proxy is seperated by a new line
    ->evaluatesProxyResultsByDefault()                  // use the default evaluation function
    ->eachProxyMayFailInfinitlyInTotal()                // don't care about total number of fails for a proxy
    ->eachProxyMayFailConsecutively(5)                  // but block a proxy if it fails 5 times in a row
    ->eachProxyNeedsToWaitSecondsBetweenRequests(1, 3)  // and let it wait between 1 and 3 seconds before making another request
    // identity options
    ->distributeIdentitiesAmongProxies($identities)     // setup each proxy with a subset of $identities - no identity is assigne twice!       
    ->eachProxySwitchesIdentityAfterRequests(3,7)       // switch to another identity after between 3 and 7 requests
    ->build();