使用PHP实现Web爬虫

<?php
// 定义URL
$startUrl = "https://www.example.com";
$depth = 2;

// 放置已经处理的URL和当前的深度
$processedUrls = [
    $startUrl => 0
];

// 运行爬虫
getAllLinks($startUrl, $depth);

//获取给定URL的HTML
function getHTML($url) {
    $curl = curl_init();
    curl_setopt($curl, CURLOPT_URL, $url);
    curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
    $html = curl_exec($curl);
    curl_close($curl);
    return $html;
}

//获取所有链接
function getAllLinks($url, $depth) {
    global $processedUrls;
    
    if ($depth === 0) {
        return;
    }
    
    $html = getHTML($url);
    $dom = new DOMDocument();
    @$dom->loadHTML($html);
    
    $links = $dom->getElementsByTagName('a');
    foreach ($links as $link) {
        $href = $link->getAttribute('href');
        if (strpos($href, $url) !== false && !array_key_exists($href, $processedUrls)) {
            $processedUrls[$href] = $processedUrls[$url] + 1;
            echo $href . " (Depth: " . $processedUrls[$href] . ")" . PHP_EOL;
            getAllLinks($href, $depth - 1);
        }
    }
}