采集站php源码

<?php
// 示例代码：使用cURL进行并发请求
$urls = [
    'http://example.com/page1',
    'http://example.com/page2',
    // ...
];

$mh = curl_multi_init();
$ch = [];

foreach ($urls as $url) {
    $ch[$url] = curl_init($url);
    curl_setopt($ch[$url], CURLOPT_RETURNTRANSFER, 1);
    curl_multi_add_handle($mh, $ch[$url]);
}

do {
    $mrc = curl_multi_exec($mh, $active);
} while ($mrc == CURLM_CALL_MULTI_PERFORM);

while ($active && $mrc == CURLM_OK) {
    if (curl_multi_select($mh) != -1) {
        do {
            $mrc = curl_multi_exec($mh, $active);
        } while ($mrc == CURLM_CALL_MULTI_PERFORM);
    }
}

foreach ($ch as $url => $chandle) {
    $result = curl_multi_getcontent($chandle);
    curl_multi_remove_handle($mh, $chandle);
    curl_close($chandle);
}

curl_multi_close($mh);
?>

<?php
// 示例代码：使用PHP Simple HTML DOM Parser解析网页
require 'simple_html_dom.php';

$html = file_get_html('http://example.com');
$titles = $html->find('h2.title');

foreach ($titles as $title) {
    echo $title->plaintext . '<br>';
}
?>