如何用PHP语言使用爬虫ip代码示例

对于经常做数据抓取的技术员应该知道，优化好的爬虫程序能事半功倍，对于工作量增加或者调整业务类型也是方便快捷，下面几种PHP语言下使用爬虫IP的代码给大家提供参考：

PHP curl

/**
 * 请求
 *
 * @param [type] $targetUrl 目标站点
 * @param [type] $proxyIp   爬虫IP
 * @param [type] $proxyPort  代理端口
 * @param [type] $proxyUser   authKey(key)
 * @param [type] $proxyPassword  authpwd(密码)
 * @return void
 */
function sendRequest($targetUrl, $proxyIp, $proxyPort, $proxyUser, $proxyPassword){
  $ch = curl_init();
  curl_setopt($ch, CURLOPT_URL, $targetUrl);
  curl_setopt($ch, CURLOPT_HEADER, 0);
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
  curl_setopt($ch, CURLOPT_PROXYPORT, $proxyPort);
  curl_setopt($ch, CURLOPT_PROXYTYPE, 'HTTP');
  curl_setopt($ch, CURLOPT_PROXY, $proxyIp);
  curl_setopt($ch, CURLOPT_PROXYUSERPWD, $proxyUser . ':' . $proxyPassword);
  curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, FALSE);
  curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, FALSE);
  $data = curl_exec($ch);
  curl_close($ch);
  return $data;
}
$data = sendRequest('http://jshk.com.cn/ip', '219.151.125.106', 31615, '895314XY', '24D6YB309ZCB');
var_dump($data);

PHP stream

/**
 * 请求
 *
 * @param [type] $targetUrl 目标站点
 * @param [type] $proxyIp   爬虫IP
 * @param [type] $proxyPort  代理端口
 * @param [type] $proxyUser   authKey(key)
 * @param [type] $proxyPassword  authpwd(密码)
 * @return void
 */
function sendRequest($targetUrl, $proxyIp, $proxyPort, $proxyUser, $proxyPassword){
  $proxyAuth = base64_encode($proxyUser . ":" . $proxyPassword);
  $headers = implode("\r\n", [
    "Proxy-Authorization: Basic {$proxyAuth}"
  ]);
  // 目标站为https时需要
  // $sniServer = parse_url($targetUrl, PHP_URL_HOST);
  $options = [
    "http" => [
      "proxy"  => $proxyIp . ':' . $proxyPort,
      "header" => $headers,
      "method" => "GET",
      "request_fulluri" => true,
    ],
    // 目标站为https时需要
    // 'ssl' => array(
    //         'SNI_enabled' => true, 
    //         'SNI_server_name' => $sniServer
    // )
  ];
  $context = stream_context_create($options);
  $result = file_get_contents($targetUrl, false, $context);
  return $result;
}
$data = sendRequest('http://jshk.com.cn/ip', '219.151.125.106', 31615, '895314XY', '24D6YB309ZCB');
var_dump($data);

PHP GuzzleHttp

/**
 * 请求
 *
 * @param [type] $targetUrl 目标站点
 * @param [type] $proxyIp   爬虫IP
 * @param [type] $proxyPort  代理端口
 * @param [type] $proxyUser   authKey(key)
 * @param [type] $proxyPassword  authpwd(密码)
 * @return void
 */
function sendRequest($targetUrl, $proxyIp, $proxyPort, $proxyUser, $proxyPassword){
  $client = new \GuzzleHttp\Client();
  $proxyAuth = base64_encode($proxyUser . ":" . $proxyPassword);
  $options = [
    "proxy"  => $proxyIp . ':' . $proxyPort,
    "headers" => [
      "Proxy-Authorization" => "Basic " . $proxyAuth
    ]
  ];
  $result = $client->request('GET', $targetUrl, $options);
  return $result->getBody()->getContents();
}
$data = sendRequest('http://jshk.com.cn/ip', '219.151.125.106', 31615, '895314XY', '24D6YB309ZCB');
var_dump($data);