PHP 檢測遠程 URL 是否可訪問的多種方法

PHP 判斷遠程頁面存在性的完整方案對比

在開發友鏈檢測、鏈接驗證、內容聚合等功能時，需要判斷遠程 URL 是否真實可訪問。本文詳細對比三種主流方法：file_get_contents、cURL、get_headers，分析其優缺點、適用場景及最佳實踐。

方法一：file_get_contents（最簡單但有局限）

<?php
$url = 'https://www.example.com';

// 基礎用法
if (@file_get_contents($url)) {
    echo 'URL 可訪問';
} else {
    echo 'URL 不可訪問';
}

// 進階：設置超時上下文
$context = stream_context_create([
    'http' => [
        'timeout' => 10,           // 10秒超時
        'method' => 'HEAD',        // 僅請求頭部，不下載內容
        'user_agent' => 'PHP URL Checker 1.0'
    ]
]);

$content = @file_get_contents($url, false, $context);
if ($content !== false) {
    echo '可訪問';
} else {
    echo '不可訪問';
}
?>

方法二：cURL（功能最強大、可控性最高）

<?php
function checkUrlCurl($url, $timeout = 10) {
    $ch = curl_init($url);
    
    curl_setopt_array($ch, [
        CURLOPT_NOBODY => true,        // 僅獲取頭部 (HEAD 請求)
        CURLOPT_RETURNTRANSFER => true,
        CURLOPT_TIMEOUT => $timeout,   // 總超時
        CURLOPT_CONNECTTIMEOUT => 5,   // 連接超時
        CURLOPT_FOLLOWLOCATION => true, // 跟隨重定向
        CURLOPT_MAXREDIRS => 5,        // 最大重定向次數
        CURLOPT_USERAGENT => 'PHP URL Checker 1.0',
        CURLOPT_SSL_VERIFYPEER => false, // 開發環境可關閉 SSL 驗證
        CURLOPT_HEADER => true         // 包含頭部信息
    ]);
    
    $response = curl_exec($ch);
    $httpCode = curl_getinfo($ch, CURLINFO_HTTP_CODE);
    $error = curl_error($ch);
    curl_close($ch);
    
    return [
        'accessible' => $httpCode >= 200 && $httpCode < 400,
        'http_code' => $httpCode,
        'error' => $error,
        'response_time' => curl_getinfo($ch, CURLINFO_TOTAL_TIME)
    ];
}

// 使用示例
$result = checkUrlCurl('https://www.google.com');
if ($result['accessible']) {
    echo "可訪問 (HTTP {$result['http_code']})";
} else {
    echo "不可訪問: {$result['error']}";
}
?>

方法三：get_headers（輕量級、原生支持）

<?php
function checkUrlHeaders($url, $timeout = 10) {
    // 設置流超時
    $ctx = stream_context_create([
        'http' => ['timeout' => $timeout]
    ]);
    
    $headers = @get_headers($url, 1, $ctx);
    
    if ($headers === false) return ['accessible' => false, 'error' => '連接失敗'];
    
    // 解析狀態碼
    $statusLine = $headers[0] ?? '';
    preg_match('/HTTP\/\d\.\d\s+(\d+)/', $statusLine, $matches);
    $httpCode = isset($matches[1]) ? (int)$matches[1] : 0;
    
    return [
        'accessible' => $httpCode >= 200 && $httpCode < 400,
        'http_code' => $httpCode,
        'headers' => $headers
    ];
}
?>

三種方法詳細對比

最佳實踐：統一檢測類

<?php
class UrlChecker {
    private $timeout = 10;
    private $userAgent = 'UrlChecker/1.0';
    
    public function __construct($timeout = 10) {
        $this->timeout = $timeout;
    }
    
    // 推薦使用 cURL（功能最全）
    public function check($url) {
        if (!function_exists('curl_init')) {
            return $this->checkWithGetHeaders($url);
        }
        return $this->checkWithCurl($url);
    }
    
    private function checkWithCurl($url) {
        $ch = curl_init($url);
        curl_setopt_array($ch, [
            CURLOPT_NOBODY => true,
            CURLOPT_RETURNTRANSFER => true,
            CURLOPT_TIMEOUT => $this->timeout,
            CURLOPT_CONNECTTIMEOUT => 5,
            CURLOPT_FOLLOWLOCATION => true,
            CURLOPT_MAXREDIRS => 3,
            CURLOPT_USERAGENT => $this->userAgent,
            CURLOPT_SSL_VERIFYPEER => true,  // 生產環境建議開啟
        ]);
        
        curl_exec($ch);
        $httpCode = curl_getinfo($ch, CURLINFO_HTTP_CODE);
        $error = curl_error($ch);
        $time = curl_getinfo($ch, CURLINFO_TOTAL_TIME);
        curl_close($ch);
        
        return [
            'url' => $url,
            'accessible' => $httpCode >= 200 && $httpCode < 400,
            'http_code' => $httpCode,
            'response_time' => round($time * 1000, 2), // 毫秒
            'error' => $error ?: null,
            'method' => 'curl'
        ];
    }
    
    private function checkWithGetHeaders($url) {
        $ctx = stream_context_create(['http' => ['timeout' => $this->timeout]]);
        $headers = @get_headers($url, 1, $ctx);
        
        if ($headers === false) {
            return ['url' => $url, 'accessible' => false, 'error' => 'Connection failed', 'method' => 'get_headers'];
        }
        
        $statusLine = $headers[0] ?? '';
        preg_match('/HTTP\/\d\.\d\s+(\d+)/', $statusLine, $matches);
        $httpCode = isset($matches[1]) ? (int)$matches[1] : 0;
        
        return [
            'url' => $url,
            'accessible' => $httpCode >= 200 && $httpCode < 400,
            'http_code' => $httpCode,
            'method' => 'get_headers'
        ];
    }
}

// 批量檢測示例
$checker = new UrlChecker(5);
$urls = [
    'https://www.google.com',
    'https://www.github.com',
    'https://nonexistent-domain-12345.com'
];

foreach ($urls as $url) {
    $result = $checker->check($url);
    $status = $result['accessible'] ? '✅ 可訪問' : '❌ 不可訪問';
    echo "{$status} [{$result['http_code']}] {$url} ({$result['response_time']}ms)\n";
}
?>

常見問題與解決方案

1. allow_url_fopen 關閉導致 file_get_contents 失效

// php.ini 設置
allow_url_fopen = On

// 或運行時檢查
if (ini_get('allow_url_fopen')) {
    // 使用 file_get_contents
} else {
    // 回退到 cURL
}

2. SSL 證書驗證失敗

// 開發環境臨時關閉（生產嚴禁）
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, false);

// 正確做法：配置 CA 證書包
curl_setopt($ch, CURLOPT_CAINFO, '/path/to/cacert.pem');

3. 大量並發檢測性能優化

// 使用 curl_multi 並發請求
function checkUrlsConcurrent($urls, $concurrency = 10) {
    $mh = curl_multi_init();
    $handles = [];
    $results = [];
    
    foreach ($urls as $i => $url) {
        $ch = curl_init($url);
        curl_setopt_array($ch, [
            CURLOPT_NOBODY => true,
            CURLOPT_RETURNTRANSFER => true,
            CURLOPT_TIMEOUT => 10,
            CURLOPT_FOLLOWLOCATION => true,
        ]);
        curl_multi_add_handle($mh, $ch);
        $handles[$i] = $ch;
    }
    
    $running = null;
    do {
        curl_multi_exec($mh, $running);
        curl_multi_select($mh);
    } while ($running > 0);
    
    foreach ($handles as $i => $ch) {
        $httpCode = curl_getinfo($ch, CURLINFO_HTTP_CODE);
        $results[$urls[$i]] = [
            'accessible' => $httpCode >= 200 && $httpCode < 400,
            'http_code' => $httpCode
        ];
        curl_multi_remove_handle($mh, $ch);
        curl_close($ch);
    }
    curl_multi_close($mh);
    
    return $results;
}

HTTP 狀態碼判斷標準

綜合來看，cURL 是功能最完整、生產環境最推薦的方案。若環境受限無法安裝擴展，get_headers 是不錯的備選。實際項目中建議封裝統一檢測類，支持多種後端自動降級，並結合緩存機制避免重複檢測同一 URL。