PHP抓取网页内容的几种方法

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); 

$opts = array ( 
'http' => array ( 
   'method' => 'POST', 
   'header'=> "Content-type: application/x-www-form-urlencoded
" . 
                     "Content-Length: " . strlen($data) . "
", 
   '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
" . 
                  "Content-Length: " . strlen($data) . "
", 
修改为 
'header'=> "Content-type: application/x-www-form-urlencoded
" . 
                 "Content-Length: " . strlen($data) . "
". 
                 "cookie:cookie1=c1;cookie2=c2
" ; 
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); 

$opts = array ( 
'http' => array ( 
'method' => 'POST', 
'header'=> "Content-type: application/x-www-form-urlencoded
Cookie:cook1=c3;cook2=c4
" . 
"Content-Length: " . strlen($data) . "
", 
'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 
function get_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) { 
return false; 
} else { 
$request = "GET $query HTTP/1.1
"; 
$request .= "Host: $url[host]
"; 
$request .= "Connection: Close
"; 
if($cookie) $request.="Cookie:   $cookie
"; 
$request.="
"; 
fwrite($fp,$request); 
while(!@feof($fp)) { 
$result .= @fgets($fp, 1024); 
} 
fclose($fp); 
return $result; 
} 
} 
//获取url的html部分,去掉header 
function GetUrlHTML($url,$cookie=false) 
{ 
$rowdata = get_url($url,$cookie); 
if($rowdata) 
{ 
$body= stristr($rowdata,"

"); 
$body=substr($body,4,strlen($body)); 
return $body; 
} 

   return false; 
} 
?> 

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 
function HTTP_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 $data 
foreach($data as $key=>$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
"; 
$request.="Host: ".$URL_Info["host"]."
"; 
$request.="Referer: $referer
"; 
$request.="Content-type: application/x-www-form-urlencoded
"; 
$request.="Content-length: ".strlen($data_string)."
"; 
$request.="Connection: close
"; 

   $request.="Cookie:   $cookie
"; 

   $request.="
"; 
$request.=$data_string."
"; 

   $fp = fsockopen($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; 
?>
原文地址:https://www.cnblogs.com/myphper/p/3305500.html