输入banner图图片脚本导航/分类

snoopy图片基于Snoopy的PHP近似完美获取网站编码的代码

先要到网上下载Snoopy.class.php
调用方法:

代码如下:


require 'lib/Snoopy.class.php';
require 'lib/WebCrawl.class.php';//包含下面代码
$go=new WebCrawl('http://www.baidu.com');
echo $go->getCharset();
?>


代码如下:


class WebCrawl
{
private $url;
private $request;
public $charset_arr=array(
'gb2312',
'utf-8',
'big5',
'gbk',
'ascii',
'cp936',
'ibm037',
'ibm437',
'ibm500',
'asmo-708',
'dos-720',
'ibm737',
'ibm775',
'ibm850',
'ibm852',
'ibm855',
'ibm857',
'ibm00858',
'ibm861',
'ibm860',
'dos-862',
'ibm863',
'ibm864',
'ibm865',
'cp866',
'ibm869',
'ibm870',
'windows-874',
'cp875',
'shift_jis',
'ks_c_5601-1987',
'ibm1026',
'ibm01047',
'ibm01047',
'ibm01040',
'ibm01041',
'ibm01042',
'ibm01043',
'ibm01044',
'ibm01045',
'ibm01046',
'ibm01047',
'ibm01048',
'ibm01049',
'utf-16',
'unicodefffe',
'windows-1250',
'windows-1251',
'windows-1252',
'windows-1253',
'windows-1254',
'windows-1255',
'windows-1256',
'windows-1257',
'windows-1258',
'johab',
'macintosh',
'x-mac-japanese',
'x-mac-chinesetrad',
'x-mac-korean',
'x-mac-arabic',
'x-mac-hebrew',
'x-mac-greek',
'x-mac-cyrillic',
'x-mac-chinesesimp',
'x-mac-romanian',
'x-mac-ukrainian',
'x-mac-thai',
'x-mac-ce',
'x-mac-icelandic',
'x-mac-turkish',
'x-mac-croatian',
'x-chinese-cns',
'x-cp20001',
'x-chinese-eten',
'x-cp20003',
'x-cp20004',
'x-cp20005',
'x-ia5',
'x-ia5-german',
'x-ia5-swedish',
'x-ia5-norwegian',
'us-ascii',
'x-cp20261',
'x-cp20269',
'ibm273',
'ibm277',
'ibm278',
'ibm280',
'ibm284',
'ibm285',
'ibm290',
'ibm420',
'ibm423',
'ibm424',
'x-ebcdic-koreanextended',
'ibm-thai',
'koi8-r',
'ibm871',
'ibm880',
'ibm905',
'ibm00924',
'x-cp20936',
'x-cp20949',
'cp1025',
'koi8-u',
'iso-8859-1',
'iso-8859-2',
'iso-8859-3',
'iso-8859-4',
'iso-8859-5',
'iso-8859-6',
'iso-8859-7',
'iso-8859-8',
'iso-8859-9',
'iso-8859-13',
'iso-8859-15',
'x-europa',
'iso-8859-8-i',
'iso-2022-jp',
'csiso2022jp',
'iso-2022-jp',
'iso-2022-kr',
'x-cp50227',
'euc-jp',
'euc-cn',
'euc-kr',
'hz-gb-2312',
'gb18030',
'x-iscii-de',
'x-iscii-be',
'x-iscii-ta',
'x-iscii-te',
'x-iscii-as',
'x-iscii-or',
'x-iscii-ka',
'x-iscii-ma',
'x-iscii-gu',
'x-iscii-pa',
'utf-7',
'utf-32',
'utf-32be'
);
public function __construct($url)
{
$this->url=$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, $titlematch ); <BR>if (isset($titlematch) && is_array($titlematch) && count($titlematch) > 0) <BR>{ <BR>$info['title'] = strip_tags($titlematch[1]); <BR>} <BR>preg_match_all('/<[\s]*meta[\s]*name="?' . '([^>"]*)"?[\s]*' . 'c || $mt=="description") <BR>{ <BR>$ft=1; <BR>} <BR>} <BR>if($ft==0) <BR>{ <BR>preg_match_all('/<[\s]*meta[\s]*c/<meta.+?charset=[^\w]?([-\w]+)/i",$this->request->results,$temp) ? strtolower($temp[1]):""; <BR>if($temp[1]!="") <BR>{ <BR>if(in_array($temp[1], $this->charset_arr)) <BR>{ <BR>if($temp[1]=="gb2312") <BR>{ <BR>$tmp_charset=$this->t($this->request->results,$temp[1]); <BR>if($tmp_charset==$temp[1]) <BR>{ <BR>return $temp[1]; <BR>} <BR>} <BR>else <BR>{ <BR>return $temp[1]; <BR>} <BR>} <BR>} <BR>if(!empty($this->request->headers)) <BR>{ <BR>//从header中获取编码 <BR>$hstr=strtolower(implode("|||",$this->request->headers)); <BR>preg_match("/charset=[^\w]?([-\w]+)/is",$hstr,$lang) ? strtolower($lang[1]):""; <BR>if($lang[1]!="") <BR>{ <BR>return $lang[1]; <BR>} <BR>} <BR>$encode_arr=array("UTF-8","GB2312","GBK","BIG5","ASCII","EUC-JP","Shift_JIS","CP936","ISO-8859-1","JIS","eucjp-win","sjis-win"); <BR>$encoded=mb_detect_encoding($this->request->results,$encode_arr); <BR>if($encoded) <BR>{ <BR>return strtolower($encoded); <BR>} <BR>else <BR>{ <BR>return false; <BR>} <BR>} <BR>} <BR>?> <BR></p> <p> 以上就介绍了snoopy图片 基于Snoopy的PHP近似完美获取网站编码的代码,包括了snoopy图片方面的内容,希望对PHP教程有兴趣的朋友有所帮助。 </div> </div> <script type="text/javascript" src="/layui/layui.js"></script> <script> layui.use('code', function(){ layui.code({ elem: 'pre', //默认值为.layui-code about:false, title:'snoopy图片基于Snoopy的PHP近似完美获取网站编码的代码代码块', encode: true //是否转义html标签。默认不开启 }); }); </script> <footer class="comm-footer"> <ul class="channels"> <li> <a target="_top" href="/system/">操作系统</a> </li><li> <a target="_top" href="/down/">程序下载</a> </li><li> <a target="_top" href="/jquery/">jquery插件库</a> </li><li> <a target="_top" href="/jiaoben/">编程</a> </li><li> <a target="_top" href="/db/">数据库</a> </li><li> <a target="_top" href="/tools/">在线工具</a> </li><li> <a target="_top" href="/framebook/">框架书籍</a> </li><li> <a target="_top" href="/xitongjiaocheng/">系统教程</a> </li><li> <a target="_top" href="/ruanjianxiazai/">软件下载</a> </li> </ul> <ul class="versions"> <li> <a href="https://m.gxlcms.com" class="active">触屏版</a> </li> <li> <a href="https://www.gxlcms.com" target="_top">电脑版</a> </li> </ul> <p><a href="https://beian.miit.gov.cn/" target="_blank" style="color:#ffffff"></a><script> var _hmt = _hmt || []; (function() { var hm = document.createElement("script"); hm.src = "https://hm.baidu.com/hm.js?6c9b8cea1903c9f813f150c04aeebc3c"; var s = document.getElementsByTagName("script")[0]; s.parentNode.insertBefore(hm, s); })(); </script></p> </footer> </body> </html>