phpfsockopen和file_get_contents,php读取网络文件(curl, fsockopen ,file_get_contents 几个方法的效率对比)...

最近需要获取别人网站上的音乐数据。用了file_get_contents函数&＃xff0c;但是总是会遇到获取失败的问题&＃xff0c;尽管按照手册中的

例子设置了超时&＃xff0c;可多数时候不会奏效&＃xff1a;

$config[&＃39;context&＃39;] &＃61; stream_context_create(array(‘http’

&＃61;> array(‘method’ &＃61;>

“GET”, ’timeout’ &＃61;>

5//这个超时时间不稳定&＃xff0c;经常不奏效 ) )); 这时候&＃xff0c;看一下服务器的连接池&＃xff0c;会发现一堆类似的错误&＃xff0c;让我头疼万分&＃xff1a; file_get_contents(http://***): failed to open

stream… 现在改用了curl库&＃xff0c;写了一个函数替换&＃xff1a; function curl_file_get_contents($durl){ $ch &＃61;

curl_init(); curl_setopt($ch, CURLOPT_URL,

$durl); curl_setopt($ch,

CURLOPT_TIMEOUT, 5); curl_setopt($ch,

CURLOPT_USERAGENT, _USERAGENT_); curl_setopt($ch,

CURLOPT_REFERER,_REFERER_); curl_setopt($ch,

CURLOPT_RETURNTRANSFER, 1); $r &＃61;

curl_exec($ch); curl_close($ch); return

$r; } 如此&＃xff0c;除了真正的网络问题外&＃xff0c;没再出现任何问题。 这是别人做过的关于curl和file_get_contents的测试&＃xff1a; file_get_contents抓取google.com需用秒数&＃xff1a;

2.31319094

2.30374217 2.21512604 3.30553889 2.30124092 curl使用的时间&＃xff1a;

0.68719101

0.64675593 0.64326 0.81983113 0.63956594 差距很大&＃xff1f;呵呵&＃xff0c;从我使用的经验来说&＃xff0c;这两个工具不只是速度有差异&＃xff0c;稳定性也相差很大。

建议对网络数据抓取稳定性要求比较高的朋友使用上面的

curl_file_get_contents函数&＃xff0c;不但稳定速度快&＃xff0c;还能假冒浏览器欺骗目标地址哦&＃xff01;

看到的其他文章收藏于此&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;

php

fsockopen

方法1:

用file_get_contents 以get方式获取内容

$url&＃61;&＃39;http://www.domain.com/&＃39;;

$html &＃61; file_get_contents($url);

echo $html;

?>

方法2:

用fopen打开url, 以get方式获取内容

$fp &＃61; fopen($url, &＃39;r&＃39;);

stream_get_meta_data($fp);

while(!feof($fp)) {

$result .&＃61; fgets($fp, 1024);

}

echo "url body: $result";

fclose($fp);

?>

方法3&＃xff1a;用file_get_contents函数,以post方式获取url

$data &＃61; array (&＃39;foo&＃39; &＃61;> &＃39;bar&＃39;);

$data &＃61; http_build_query($data);

$opts &＃61;

array (

&＃39;http&＃39; &＃61;> array (

&＃39;method&＃39; &＃61;> &＃39;POST&＃39;,

&＃39;header&＃39;&＃61;> "Content-type:

application/x-www-form-urlencoded\r\n" .

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

&＃39;content&＃39; &＃61;> $data

)

);

$context

&＃61; stream_context_create($opts);

$html &＃61; file_get_contents(&＃39;http://localhost/e/admin/test.html&＃39;,

false, $context);

echo

$html;

?>

方法4&＃xff1a;用fsockopen函数打开url&＃xff0c;以get方式获取完整的数据&＃xff0c;包括header和body

function get_url ($url,$COOKIE&＃61;false)

{

$url &＃61; parse_url($url);

$query &＃61; $url[path]."?".$url[query];

echo "Query:".$query;

$fp &＃61; fsockopen( $url[host], $url[port]?$url[port]:80 , $errno,

$errstr, 30);

if (!$fp) {

return false;

} else {

$request &＃61; "GET $query HTTP/1.1\r\n";

$request .&＃61; "Host: $url[host]\r\n";

$request .&＃61; "Connection: Close\r\n";

if($COOKIE) $request.&＃61;"COOKIE: $COOKIE\n";

$request.&＃61;"\r\n";

fwrite($fp,$request);

while()) {

$result .&＃61; &＃64;fgets($fp, 1024);

}

fclose($fp);

return $result;

}

}

//获取url的html部分&＃xff0c;去掉header

function GetUrlHTML($url,$COOKIE&＃61;false)

{

$rowdata &＃61; get_url($url,$COOKIE);

if($rowdata)

{

$body&＃61; stristr($rowdata,"\r\n\r\n");

$body&＃61;substr($body,4,strlen($body));

return $body;

}

return false;

}

?>

方法5&＃xff1a;用fsockopen函数打开url&＃xff0c;以POST方式获取完整的数据&＃xff0c;包括header和body

function HTTP_Post($URL,$data,$COOKIE, $referrer&＃61;"")

{

// parsing the given URL

$URL_Info&＃61;parse_url($URL);

// Building referrer

if($referrer&＃61;&＃61;"") // if not given use this script as

referrer

$referrer&＃61;"111";

// making string from $data

foreach($data as $key&＃61;>$value)

$values[]&＃61;"$key&＃61;".urlencode($value);

$data_string&＃61;implode("&",$values);

// Find out which port is needed - if not given use standard

(&＃61;80)

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

$URL_Info["port"]&＃61;80;

// building POST-request:

$request.&＃61;"POST ".$URL_Info["path"]." HTTP/1.1\n";

$request.&＃61;"Host: ".$URL_Info["host"]."\n";

$request.&＃61;"Referer: $referer\n";

$request.&＃61;"Content-type:

application/x-www-form-urlencoded\n";

$request.&＃61;"Content-length: ".strlen($data_string)."\n";

$request.&＃61;"Connection: close\n";

$request.&＃61;"COOKIE: $COOKIE\n";

$request.&＃61;"\n";

$request.&＃61;$data_string."\n";

$fp &＃61; fsockopen($URL_Info["host"],$URL_Info["port"]);

fputs($fp, $request);

while(!feof($fp)) {

$result .&＃61; fgets($fp, 1024);

}

fclose($fp);

return $result;

}

?>

方法6:使用curl库&＃xff0c;使用curl库之前&＃xff0c;可能需要查看一下php.ini是否已经打开了curl扩展

$ch &＃61; curl_init();

$timeout &＃61; 5;

curl_setopt ($ch, CURLOPT_URL, &＃39;http://www.domain.com/&＃39;);

curl_setopt ($ch, CURLOPT_RETURNTRANSFER, 1);

curl_setopt ($ch, CURLOPT_CONNECTTIMEOUT, $timeout);

$file_contents &＃61; curl_exec($ch);

curl_close($ch);

echo

$file_contents;

?>

php中

curl&＃xff0c; fsockopen &＃xff0c;file_get_contents 三个函数

都可以实现采集模拟发言 。

三者有什么区别&＃xff0c;或者讲究么

&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;

以下PHP抓取网页内容的范例是通curl_init函数来获取163天气预报

把php.ini里(

;extension&＃61;php_curl.dll )　前面的(;)去掉保存

把php_curl.dll,libeay32.dll,ssleay32.dll拷到c:\windows\system32里&＃xff0c;重启IIS即可&＃xff0c;没有装apache

//www.163.com/weatherxml/54511.xml");  //要求CURL返回数据  curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);  //执行请求  $result &＃61; curl_exec($ch) or die (curl_error());  //取得返回的结果&＃xff0c;并显示  //echo $result;  // echo curl_error($ch);  $qx&＃61;explode("\"",strstr($result,"qx&＃61;"));  $wd&＃61;explode("\"",strstr($result,"wd&＃61;"));  $qximg&＃61;explode("\"",strstr($result,"qximg&＃61;"));  $qximg_&＃61;explode(",",$qximg[1]);  echo "北京 ".$qx[1]."";  echo $wd[1];  //关闭CURL  curl_close($ch);  ?>