$url = 'http://google.com';
$not_url = 'stp://google.com';

if (@file_get_contents($url)): echo "Found '$url'!";
else: echo "Can't find '$url'.";
endif;
if (@file_get_contents($not_url)): echo "Found '$not_url!";
else: echo "Can't find '$not_url'.";
endif;

// Found 'http://google.com'!Can't find 'stp://google.com'.

get_headers()返回一个数组，其中包含服务器响应HTTP请求时发送的报头。

$image_path = 'https://your-domain.com/assets/img/image.jpg';

$file_headers = @get_headers($image_path);
//Prints the response out in an array
//print_r($file_headers); 

if($file_headers[0] == 'HTTP/1.1 404 Not Found'){
   echo 'Failed because path does not exist.</br>';
}else{
   echo 'It works. Your good to go!</br>';
}

function URLIsValid($URL)
{
    $exists = true;
    $file_headers = @get_headers($URL);
    $InvalidHeaders = array('404', '403', '500');
    foreach($InvalidHeaders as $HeaderVal)
    {
            if(strstr($file_headers[0], $HeaderVal))
            {
                    $exists = false;
                    break;
            }
    }
    return $exists;
}

简单的方法是卷曲(和更快)

<?php
$mylinks="http://site.com/page.html";
$handlerr = curl_init($mylinks);
curl_setopt($handlerr,  CURLOPT_RETURNTRANSFER, TRUE);
$resp = curl_exec($handlerr);
$ht = curl_getinfo($handlerr, CURLINFO_HTTP_CODE);


if ($ht == '404')
     { echo 'OK';}
else { echo 'NO';}

?>

我运行一些测试，看看我的网站上的链接是否有效-提醒我当第三方改变他们的链接。我有一个网站的问题，有一个配置不良的证书，这意味着php的get_headers不能工作。

所以，我读到卷曲更快，并决定给一个尝试。然后我在领英上遇到了一个问题，给了我一个999错误，后来证明是用户代理的问题。

我不关心证书是否对该测试无效，也不关心响应是否为重定向。

然后我认为使用get_headers无论如何，如果卷曲失败....

试试看....

/**
 * returns true/false if the $url is valid.
 *
 * @param string $url assumes this is a valid url.
 *
 * @return bool
 */
private function urlExists(string $url): bool
{
    $ch = curl_init($url);
    curl_setopt($ch, CURLOPT_URL, $url);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);     // do not output response in stdout
    curl_setopt($ch, CURLOPT_NOBODY, true);             // this does a head request to make it faster.
    curl_setopt($ch, CURLOPT_HEADER, true);             // just the headers
    curl_setopt($ch, CURLOPT_SSL_VERIFYSTATUS, false);  // turn off that pesky ssl stuff - some sys admins can't get it right.
    curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
    // set a real user agent to stop linkedin getting upset.
    curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36');
    curl_exec($ch);
    $http_code = curl_getinfo($ch, CURLINFO_HTTP_CODE);
    if (($http_code >= 200 && $http_code < 400) || $http_code === 999) {
        curl_close($ch);
        return true;
    }
    //$error = curl_error($ch); // used for debugging.
    curl_close($ch);

    // just try the get_headers - it might work!
    stream_context_set_default(
        ['http' => ['method' => 'HEAD']]
    );
    $file_headers = @get_headers($url);

    if ($file_headers !== false) {
        $response_code = substr($file_headers[0], 9, 3);
        return $response_code >= 200 && $response_code < 400;
    }

    return false;
}

karim79的get_headers()解决方案并没有为我工作，因为我得到了疯狂的结果与Pinterest。

get_headers(): SSL operation failed with code 1. OpenSSL Error messages: error:14090086:SSL routines:SSL3_GET_SERVER_CERTIFICATE:certificate verify failed

Array
(
    [url] => https://www.pinterest.com/jonathan_parl/
    [exists] => 
)

get_headers(): Failed to enable crypto

Array
(
    [url] => https://www.pinterest.com/jonathan_parl/
    [exists] => 
)

get_headers(https://www.pinterest.com/jonathan_parl/): failed to open stream: operation failed

Array
(
    [url] => https://www.pinterest.com/jonathan_parl/
    [exists] => 
) 

不管怎样，这个开发人员演示了cURL比get_headers()快得多:

http://php.net/manual/fr/function.get-headers.php#104723

由于许多人要求karim79修复的是cURL解决方案，这里是我今天构建的解决方案。

/**
* Send an HTTP request to a the $url and check the header posted back.
*
* @param $url String url to which we must send the request.
* @param $failCodeList Int array list of code for which the page is considered invalid.
*
* @return Boolean
*/
public static function isUrlExists($url, array $failCodeList = array(404)){

    $exists = false;

    if(!StringManager::stringStartWith($url, "http") and !StringManager::stringStartWith($url, "ftp")){

        $url = "https://" . $url;
    }

    if (preg_match(RegularExpression::URL, $url)){

        $handle = curl_init($url);


        curl_setopt($handle, CURLOPT_RETURNTRANSFER, true);

        curl_setopt($handle, CURLOPT_SSL_VERIFYPEER, false);

        curl_setopt($handle, CURLOPT_HEADER, true);

        curl_setopt($handle, CURLOPT_NOBODY, true);

        curl_setopt($handle, CURLOPT_USERAGENT, true);


        $headers = curl_exec($handle);

        curl_close($handle);


        if (empty($failCodeList) or !is_array($failCodeList)){

            $failCodeList = array(404); 
        }

        if (!empty($headers)){

            $exists = true;

            $headers = explode(PHP_EOL, $headers);

            foreach($failCodeList as $code){

                if (is_numeric($code) and strpos($headers[0], strval($code)) !== false){

                    $exists = false;

                    break;  
                }
            }
        }
    }

    return $exists;
}

让我来解释一下旋度选项:

CURLOPT_RETURNTRANSFER:返回一个字符串，而不是在屏幕上显示调用页面。

CURLOPT_SSL_VERIFYPEER: cUrl不会签出证书

CURLOPT_HEADER:在字符串中包含头文件

CURLOPT_NOBODY:不要在字符串中包含body

CURLOPT_USERAGENT:一些站点需要它才能正常运行(例如:https://plus.google.com)

附加说明:在这个函数中，我使用Diego Perini的正则表达式在发送请求之前验证URL:

const URL = "%^(?:(?:https?|ftp)://)(?:\S+(?::\S*)?@|\d{1,3}(?:\.\d{1,3}){3}|(?:(?:[a-z\d\x{00a1}-\x{ffff}]+-?)*[a-z\d\x{00a1}-\x{ffff}]+)(?:\.(?:[a-z\d\x{00a1}-\x{ffff}]+-?)*[a-z\d\x{00a1}-\x{ffff}]+)*(?:\.[a-z\x{00a1}-\x{ffff}]{2,6}))(?::\d+)?(?:[^\s]*)?$%iu"; //@copyright Diego Perini

附加说明2:我将标题字符串和用户标题[0]分开，以确保只验证返回代码和消息(例如:200、404、405等)。

附加说明3:有时仅验证代码404是不够的(参见单元测试)，因此有一个可选的$failCodeList参数提供所有要拒绝的代码列表。

当然，这里还有单元测试(包括所有流行的社交网络)来证明我的代码是合法的:

public function testIsUrlExists(){

//invalid
$this->assertFalse(ToolManager::isUrlExists("woot"));

$this->assertFalse(ToolManager::isUrlExists("https://www.facebook.com/jonathan.parentlevesque4545646456"));

$this->assertFalse(ToolManager::isUrlExists("https://plus.google.com/+JonathanParentL%C3%A9vesque890800"));

$this->assertFalse(ToolManager::isUrlExists("https://instagram.com/mariloubiz1232132/", array(404, 405)));

$this->assertFalse(ToolManager::isUrlExists("https://www.pinterest.com/jonathan_parl1231/"));

$this->assertFalse(ToolManager::isUrlExists("https://regex101.com/546465465456"));

$this->assertFalse(ToolManager::isUrlExists("https://twitter.com/arcadefire4566546"));

$this->assertFalse(ToolManager::isUrlExists("https://vimeo.com/**($%?%$", array(400, 405)));

$this->assertFalse(ToolManager::isUrlExists("https://www.youtube.com/user/Darkjo666456456456"));


//valid
$this->assertTrue(ToolManager::isUrlExists("www.google.ca"));

$this->assertTrue(ToolManager::isUrlExists("https://www.facebook.com/jonathan.parentlevesque"));

$this->assertTrue(ToolManager::isUrlExists("https://plus.google.com/+JonathanParentL%C3%A9vesque"));

$this->assertTrue(ToolManager::isUrlExists("https://instagram.com/mariloubiz/"));

$this->assertTrue(ToolManager::isUrlExists("https://www.facebook.com/jonathan.parentlevesque"));

$this->assertTrue(ToolManager::isUrlExists("https://www.pinterest.com/"));

$this->assertTrue(ToolManager::isUrlExists("https://regex101.com"));

$this->assertTrue(ToolManager::isUrlExists("https://twitter.com/arcadefire"));

$this->assertTrue(ToolManager::isUrlExists("https://vimeo.com/"));

$this->assertTrue(ToolManager::isUrlExists("https://www.youtube.com/user/Darkjo666"));
}

祝大家取得巨大成功，

Jonathan Parent-Lévesque在蒙特利尔报道