PHP爬取网页内容

1.使用file_get_contents方法实现

$url = "http://www.baidu.com";
  $html = file_get_contents($url);
  //如果出现中文乱码使用下面代码
  //$getcontent = iconv("gb2312", "utf-8",$html);

  echo "<textarea style='width:800px;height:600px;'>".$html."</textarea>";

2.使用CURL扩展

$url = "http://www.baidu.com"; 

// 执行请求
        $ch = curl_init();
        curl_setopt($ch, CURLOPT_URL, $url);
        curl_setopt($ch, CURLOPT_HEADER, 0);
        curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
        curl_setopt($ch, CURLOPT_USERAGENT, $this->userAgent);
        curl_setopt($ch, CURLOPT_TIMEOUT, $this->timeout);
        curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, 0);
        curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 0);
        curl_setopt($ch, CURLOPT_POST, 1);
        curl_setopt($ch, CURLOPT_POSTFIELDS, $body);
        $json_string = curl_exec($ch);
        $this->debugInfo = $json_string;

        curl_close($ch);

echo $json_string;