PHP Linux脚本操作实例：实现网络爬虫

sudo apt-get install php-curl

function gethtmlContent($url)
{
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, $url);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
    $html = curl_exec($ch);
    curl_close($ch);
    
    return $html;
}

$url = 'https://example.com';  // 指定要抓取的网页URL

$html = getHtmlContent($url);  // 获取网页内容

// 在获取到的网页内容中查找所需的信息
preg_match('/<h1>(.*?)</h1>/s', $html, $matches);

if (isset($matches[1])) {
    $title = $matches[1];  // 提取标题
    echo "标题：".$title;
} else {
    echo "未找到标题";
}

$urls = ['https://example.com/page1', 'https://example.com/page2', 'https://example.com/page3'];

foreach ($urls as $url) {
    $html = getHtmlContent($url);  // 获取网页内容

    // 在获取到的网页内容中查找所需的信息
    preg_match('/<h1>(.*?)</h1>/s', $html, $matches);

    if (isset($matches[1])) {
        $title = $matches[1];  // 提取标题
        echo "标题：".$title;
    } else {
        echo "未找到标题";
    }
}