基于Snoopy的PHP近似完美获取网站编码
时间:2021-07-01 10:21:17
帮助过:5人阅读
基于Snoopy的PHP近似完美获取网站编码
用于php爬虫,获取编码准确率99.9%, 还有部分不能获取,求大牛完善
代码来源:
站云网
www.siteyun.com
先要到网上下载Snoopy.class.php
调用方法: echo $go->getCharset();
?>
[code]url=$url;
}
//打开网站
private function open($url)
{
if($this->request!==null)
{
if($this->request->status==200)
{
return true;
}
else
{
return false;
}
}
else
{
$this->request=new Snoopy();
$this->request->fetch($url);
if($this->request->status==200)
{
$this->request->results=strtolower($this->request->results);
$charset=$this->getCharset();
if($charset!="utf-8")
{
if($charset=="windows-1252")
{
$this->request->results=$this->uni_decode($this->request->results);
}
else
{
$this->request->results=mb_convert_encoding($this->request->results,"UTF-8",$charset);
}
}
return true;
}
else
{
return false;
}
}
}
//获取网站title,keywords,description
public function getWebinfo()
{
$info=array(
'title'=>'',
'keywords'=>'',
'desc'=>'',
'ip'=>''
);
if(!$this->open($this->url)){return $info;exit;}
// print_r($this->request->results);exit;
preg_match('/([^>]*)<\/title>/si', $this->request->results, $titlematch );
if (isset($titlematch) && is_array($titlematch) && count($titlematch) > 0)
{
$info['title'] = strip_tags($titlematch[1]);
}
preg_match_all('/<[\s]*meta[\s]*name="?' . '([^>"]*)"?[\s]*' . 'content="?([^>"]*)"?[\s]*[\/]?[\s]*>/si', $this->request->results, $match);
$ft=0;
foreach($match[1] as $mt)
{
if($mt=="keywords" || $mt=="description")
{
$ft=1;
}
}
if($ft==0)
{
preg_match_all('/<[\s]*meta[\s]*content="?([^>"]*)"?[\s]*name="?' . '([^>"]*)"?[\s]*[\/]?[\s]*>/si', $this->request->results, $match);
if (isset($match) && is_array($match) && count($match) == 3)
{
$originals = $match[0];
$names = $match[2];
$values = $match[1];
if (count($originals) == count($names) && count($names) == count($values))
{
$metaTags = array();
for ($i=0, $limiti=count($names); $i < $limiti; $i++)
{
$metaTags[$names[$i]] = array (
'html' => htmlentities($originals[$i]),
'value' => $values[$i]
);
}
}
}
}
else
{
if (isset($match) && is_array($match) && count($match) == 3)
{
$originals = $match[0];
$names = $match[1];
$values = $match[2];
if (count($originals) == count($names) && count($names) == count($values))
{
$metaTags = array();
for ($i=0, $limiti=count($names); $i < $limiti; $i++)
{
$metaTags[$names[$i]] = array (
'html' => htmlentities($originals[$i]),
'value' => $values[$i]
);
}
}
}
}
$result = array (
'metaTags' => $metaTags
);
if(isset($result['metaTags']['keywords']['value']))
{
$info['keywords']=$result['metaTags']['keywords']['value'];
}
else
{
$info['keywords']="";
}
if(isset($result['metaTags']['description']['value']))
{
$info['desc']=$result['metaTags']['description']['value'];
}
else
{
$info['desc']="";
}
$domain=preg_replace('/http\:\/\//si', '', $this->url);
$ip=@gethostbyname($domain);
$ip_arr=explode(".", $ip);
if(count($ip_arr)==4)
{
$info['ip']=$ip;
}
return $info;
}
public function t($string,$o)
{
for($i=0;$iopen($this->url)){return false;exit;}
//首先从html获取编码
preg_match("/request->results,$temp) ? strtolower($temp[1]):"";
if($temp[1]!="")
{
if(in_array($temp[1], $this->charset_arr))
{
if($temp[1]=="gb2312")
{
$tmp_charset=$this->t($this->request->results,$temp[1]);
if($tmp_charset==$temp[1])
{
return $temp[1];
}
}
else
{
return $temp[1];
}
}
}
if(!empty($this->request->headers))
{
//从header中获取编码
$hstr=strtolower(implode(" |