PHP获取网页所有连接的方法(附demo源码下载)

malike

            本文实例讲述了PHP获取网页所有连接的方法。分享给大家供大家参考，具体如下：
function getHtml($url, $charset='utf-8')
{
  $curl = curl_init();
  //curl_setopt($curl, CURLOPT_HTTPHEADER, array('X-FORWARDED-FOR:192.168.168.1', 'CLIENT-IP:192.168.168.1'));//IP
  curl_setopt($curl, CURLOPT_URL, $url);
  curl_setopt($curl, CURLOPT_REFERER, "");  //来路
  $user_agent = isset($_SERVER['HTTP_USER_AGENT']) ? $_SERVER['HTTP_USER_AGENT'] : 'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.31 (KHTML, like Gecko) Chrome/26.0.1410.43 Safari/537.31';
  curl_setopt($curl, CURLOPT_USERAGENT, $user_agent);
  // 只需返回HTTP header
  // curl_setopt($curl, CURLOPT_HEADER, 1);
  // 页面内容我们并不需要
  // curl_setopt($curl, CURLOPT_NOBODY, 1);
  // 返回结果，而不是输出它
  curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
  $html = curl_exec($curl);
  //$info = curl_getinfo($curl);
  //echo var_dump($info);
  if ($html === false) {
    //echo "cURL Error: " . curl_error($ch);
    return '';
  }
  curl_close($curl);
  if ($charset != 'utf-8')
  {
    $html = iconv($charset, "UTF-8", $html);
  }
  return $html;
}
header("Content-type: text/html; charset=utf-8");
include('simple_html_dom.php');
// 要打开 extension=php_mbstring.dll
//$url = 'http://www.baidu.com/s?wd=kaka';
$url = 'http://www.163.com/';
$str_html = getHtml($url, 'gbk');
$html = str_get_html($str_html);
$links = $html->find('a');
foreach($links as $link)
{
  $txt = trim($link->plaintext);
  echo $link->href . '[' . $txt . ']
';
}
$html = null;