php云采集

// 设置请求超时时间
$timeout = 10; // 单位为秒
$options = array(
    'http' => array(
        'timeout' => $timeout
    )
);
$context = stream_context_create($options);
$html = file_get_contents('http://example.com', false, $context);

// 设置User-Agent
$opts = array(
    'http' => array(
        'method' => "GET",
        'header' => "User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"
    )
);
$context = stream_context_create($opts);
$html = file_get_contents('http://example.com', false, $context);

// 使用DOMDocument解析HTML
$doc = new DOMDocument();
@$doc->loadHTML($html);
$xpath = new DOMXPath($doc);
$elements = $xpath->query('//div[@class="example"]');
foreach ($elements as $element) {
    echo $element->nodeValue . "\n";
}