PHP获取网页内容的几种方法

共计 3382 个字符，预计需要花费 9 分钟才能阅读完成。

 方法 1: 用 file_get_contents 以 get 方式获取内容

<?php

$url='http://www.domain.com/?para=123';

$html= file_get_contents($url);

echo$html;

?>

 

方法 2：用 file_get_contents 函数, 以 post 方式获取 url

<?php

$url= 'http://www.domain.com/test.php?id=123';

$data= array('foo'=> 'bar');

$data= http_build_query($data);

 

$opts= array(

'http'=> array(

   'method'=> 'POST',

   'header'=>"Content-type: application/x-www-form-urlencoded\r\n"  .

                     "Content-Length:"  . strlen($data) . "\r\n",

   'content'=> $data

)

);

$ctx= stream_context_create($opts);

$html= @file_get_contents($url,'',$ctx);

 

如果需要再传递 cookie 数据, 则把

'header'=>"Content-type: application/x-www-form-urlencoded\r\n"  .

                  "Content-Length:"  . strlen($data) . "\r\n",

修改为

'header'=>"Content-type: application/x-www-form-urlencoded\r\n"  .

                 "Content-Length:"  . strlen($data) . "\r\n".

                 "cookie:cookie1=c1;cookie2=c2\r\n";

即可

 

方法 3: 用 fopen 打开 url, 以 get 方式获取内容

<?php

$fp= fopen($url,'r');

$header= stream_get_meta_data($fp);// 获取报头信息

while(!feof($fp)) {$result.= fgets($fp, 1024);

}

echo"url header: {$header} <br>":

echo"url body: $result";

fclose($fp);

?>

 

方法 4: 用 fopen 打开 url, 以 post 方式获取内容

<?php

$data= array('foo2'=> 'bar2','foo3'=>'bar3');

$data= http_build_query($data);

 

$opts= array(

'http'=> array(

'method'=> 'POST',

'header'=>"Content-type: application/x-www-form-urlencoded\r\nCookie:cook1=c3;cook2=c4\r\n"  .

"Content-Length:"  . strlen($data) . "\r\n",

'content'=> $data

)

);

 

$context= stream_context_create($opts);

$html= fopen('http://www.test.com/zzzz.php?id=i3&id2=i4','rb',false, $context);

$w=fread($html,1024);

echo$w;

?>

 

方法 5：用 fsockopen 函数打开 url，以 get 方式获取完整的数据，包括 header 和 body

<?php

functionget_url ($url,$cookie=false)

{$url= parse_url($url);

$query= $url[path]."?".$url[query];

echo"Query:".$query;

$fp= fsockopen($url[host],$url[port]?$url[port]:80 , $errno,$errstr, 30);

if(!$fp) {returnfalse;}else{

$request= "GET $query HTTP/1.1\r\n";

$request.= "Host: $url[host]\r\n";

$request.= "Connection: Close\r\n";

if($cookie)$request.="Cookie:   $cookie\n";

$request.="\r\n";

fwrite($fp,$request);

while(!@feof($fp)) {$result.= @fgets($fp, 1024);

}

fclose($fp);

return$result;

}

}

// 获取 url 的 html 部分，去掉 header

functionGetUrlHTML($url,$cookie=false)

{$rowdata= get_url($url,$cookie);

if($rowdata)

{$body=stristr($rowdata,"\r\n\r\n");

$body=substr($body,4,strlen($body));

return$body;

}

 

   returnfalse;

}

?>

 

方法 6：用 fsockopen 函数打开 url，以 POST 方式获取完整的数据，包括 header 和 body

<?php

functionHTTP_Post($URL,$data,$cookie,$referrer="")

{

 

   // parsing the given URL

$URL_Info=parse_url($URL);

 

   // Building referrer

if($referrer=="")// if not given use this script as referrer

$referrer="111";

 

   // making string from $data

foreach($dataas
$key=>$value)

$values[]="$key=".urlencode($value);

$data_string=implode("&",$values);

 

   // Find out which port is needed - if not given use standard (=80)

if(!isset($URL_Info["port"]))

$URL_Info["port"]=80;

 

   // building POST-request:

$request.="POST".$URL_Info["path"]."HTTP/1.1\n";

$request.="Host:".$URL_Info["host"]."\n";

$request.="Referer: $referer\n";

$request.="Content-type: application/x-www-form-urlencoded\n";

$request.="Content-length:".strlen($data_string)."\n";

$request.="Connection: close\n";

 

   $request.="Cookie:   $cookie\n";

 

   $request.="\n";

$request.=$data_string."\n";

 

   $fp= fsockopen($URL_Info["host"],$URL_Info["port"]);

fputs($fp,$request);

while(!feof($fp)) {$result.= fgets($fp, 1024);

}

fclose($fp);

 

   return$result;

}

 

?>

 

方法 7: 使用 curl 库，使用 curl 库之前，可能需要查看一下 php.ini 是否已经打开了 curl 扩展

<?php

$ch= curl_init();

$timeout= 5;

curl_setopt ($ch, CURLOPT_URL, 'http://www.domain.com/');

curl_setopt ($ch, CURLOPT_RETURNTRANSFER, 1);

curl_setopt ($ch, CURLOPT_CONNECTTIMEOUT, $timeout);

$file_contents= curl_exec($ch);

curl_close($ch);

 

echo$file_contents;

?>