PHP 抓取内容的方法

zhangbinmy

　　示例代码1: 用file_get_contents 以get方式获取内容
<?php
$url='http://www.baidu.com/';
$html=file_get_contents($url);
//print_r($http_response_header);
ec($html);
printhr();
printarr($http_response_header);
printhr();
?>

示例代码2: 用fopen打开url, 以get方式获取内容

<?
$fp=fopen($url,'r');
printarr(stream_get_meta_data($fp));
printhr();
while(!feof($fp)){
$result.=fgets($fp,1024);
}
echo"url body: $result";
printhr();
fclose($fp);
?>


示例代码3：用file_get_contents函数,以post方式获取url

<?php
$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
),
);
$context=stream_context_create($opts);
$html=file_get_contents('http://localhost/e/admin/test.html',false,$context);
echo$html;
?>
示例代码4：用fsockopen函数打开url，以get方式获取完整的数据，包括header和body

<?
functionget_url($url,$cookie=false){
$url=parse_url($url);
$query=$url[path]."?".$url[query];
ec("Query:".$query);
$fp=fsockopen($url[host],$url[port]?$url[port]:80,$errno,$errstr,30);
if(!$fp){
returnfalse;
}else{
$request="GET$queryHTTP/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;
}
?>


示例代码5：用fsockopen函数打开url，以POST方式获取完整的数据，包括header和body

<?
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;
}
printhr();
?>


示例代码6:使用curl库，使用curl库之前，你可能需要查看一下php.ini，查看是否已经打开了curl扩展
<?
$ch = curl_init();
$timeout = 5;
curl_setopt ($ch, CURLOPT_URL, 'http://www.baidu.com/');
curl_setopt ($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt ($ch, CURLOPT_CONNECTTIMEOUT, $timeout);
$file_contents = curl_exec($ch);
curl_close($ch);
echo $file_contents;
?>