如果一个域名对应多个IP，取得指定IP下的网页内容

最新推荐文章于 2025-05-03 23:14:20 发布

原创最新推荐文章于 2025-05-03 23:14:20 发布 · 737 阅读

本内容遵循CC 4.0 BY-SA版权协议

本文介绍了一种使用PHP实现的网页内容抓取方法，通过解析URL并利用socket连接来获取网页内容，适用于需要从指定IP地址抓取数据的场景。

<?php
class Files
{
   public static function getUrlContentList($url, $ip = '')
   {
       if (empty ( $url )) {
           return false;
       }
       $parsed = parse_url ( $url );
       $host = $parsed ['host'];
       $uri = $parsed ['path'] ? $parsed ['path'] : '';
       $uri .= $parsed ['query'] ? '?' . $parsed ['query'] : '';
       $uri .= $parsed ['fragment'] ? '#' . $parsed ['fragment'] : '';
       unset ( $parsed );
       $ips = gethostbynamel ( $host );
       $rets = array ();
       if (! empty ( $ip )) {
           if (! in_array ( $ip, $ips )) {
               return false;
           } else {
               $rets [] = self::HttpVisit ( $ip, $host, $uri );
               return $rets;
           }
       }
       foreach ( $ips as $ip ) {
           $rets [] = self::HttpVisit ( $ip, $host, $uri );
       }
       return $rets;
   }

   public static function HttpVisit($ip, $host, $uri)
   {
       $errstr = '';
       $errno = '';
       $fp = fsockopen ( $ip, 80, $errno, $errstr, 90 );
       if (! $fp) {
           return false;
       } else {
           $out = "GET {$uri} HTTP/1.1/r/n";
           $out .= "Host:{$host}/r/n";
           $out .= "Connection: close/r/n/r/n";
           fputs ( $fp, $out );
           while ( $line = fread ( $fp, 4096 ) ) {
               $response .= $line;
           }
           fclose ( $fp );
           //去掉Header头信息
           $pos = strpos ( $response, "/r/n/r/n" );
           $response = substr ( $response, $pos + 4 );
           return $response;
       }
   }
}

/*
调用方法：
$data = Files::getUrlContentList('http://xxx/xxx.htm', '192.168.xxx.xxx');
print_r($data);
*/
?>

标签

#fp #function #url #query #path