PHP头条
热点:

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]*' . 'content="?([^>"]*)"?[\s]*[\/]?[\s]*>/si', $this->request->results, $match); <BR>$ft=0; <BR>foreach($match[1] as $mt) <BR>{ <BR>if($mt=="keywords" || $mt=="description") <BR>{ <BR>$ft=1; <BR>} <BR>} <BR>if($ft==0) <BR>{ <BR>preg_match_all('/<[\s]*meta[\s]*content="?([^>"]*)"?[\s]*name="?' . '([^>"]*)"?[\s]*[\/]?[\s]*>/si', $this->request->results, $match); <BR>if (isset($match) && is_array($match) && count($match) == 3) <BR>{ <BR>$originals = $match[0]; <BR>$names = $match[2]; <BR>$values = $match[1]; <BR>if (count($originals) == count($names) && count($names) == count($values)) <BR>{ <BR>$metaTags = array(); <BR>for ($i=0, $limiti=count($names); $i < $limiti; $i++) <BR>{ <BR>$metaTags[$names[$i]] = array ( <BR>'html' => htmlentities($originals[$i]), <BR>'value' => $values[$i] <BR>); <BR>} <BR>} <BR>} <BR>} <BR>else <BR>{ <BR>if (isset($match) && is_array($match) && count($match) == 3) <BR>{ <BR>$originals = $match[0]; <BR>$names = $match[1]; <BR>$values = $match[2]; <BR>if (count($originals) == count($names) && count($names) == count($values)) <BR>{ <BR>$metaTags = array(); <BR>for ($i=0, $limiti=count($names); $i < $limiti; $i++) <BR>{ <BR>$metaTags[$names[$i]] = array ( <BR>'html' => htmlentities($originals[$i]), <BR>'value' => $values[$i] <BR>); <BR>} <BR>} <BR>} <BR>} <BR>$result = array ( <BR>'metaTags' => $metaTags <BR>); <BR>if(isset($result['metaTags']['keywords']['value'])) <BR>{ <BR>$info['keywords']=$result['metaTags']['keywords']['value']; <BR>} <BR>else <BR>{ <BR>$info['keywords']=""; <BR>} <BR>if(isset($result['metaTags']['description']['value'])) <BR>{ <BR>$info['desc']=$result['metaTags']['description']['value']; <BR>} <BR>else <BR>{ <BR>$info['desc']=""; <BR>} <BR>$domain=preg_replace('/http\:\/\//si', '', $this->url); <BR>$ip=@gethostbyname($domain); <BR>$ip_arr=explode(".", $ip); <BR>if(count($ip_arr)==4) <BR>{ <BR>$info['ip']=$ip; <BR>} <BR>return $info; <BR>} <BR>public function t($string,$o) <BR>{ <BR>for($i=0;$i<strlen($string);$i++) <BR>{ <BR>if(ord($string{$i})<128) <BR>continue; <BR>if((ord($string{$i})&224)==224) <BR>{ <BR>//第一个字节判断通过 <BR>$char = $string{++$i}; <BR>if((ord($char)&128)==128) <BR>{ <BR>//第二个字节判断通过 <BR>$char = $string{++$i}; <BR>if((ord($char)&128)==128) <BR>{ <BR>$encoding = "UTF-8"; <BR>break; <BR>} <BR>} <BR>} <BR>if((ord($string{$i})&192)==192) <BR>{ <BR>//第一个字节判断通过 <BR>$char = $string{++$i}; <BR>if((ord($char)&128)==128) <BR>{ <BR>//第二个字节判断通过 <BR>$encoding = "GB2312"; <BR>break; <BR>} <BR>} <BR>} <BR>return strtolower($encoding); <BR>} <BR>function uni_decode ($str, $code = 'utf-8'){ <BR>$str = json_decode(preg_replace_callback('/&#(\d{5});/', create_function('$dec', 'return \'\\u\'.dechex($dec[1]);'), '"'.$str.'"')); <BR>if($code != 'utf-8'){ $str = iconv('utf-8', $code, $str); } <BR>return $str; <BR>} <BR>//获取网站编码 <BR>public function getCharset() <BR>{ <BR>if(!$this->open($this->url)){return false;exit;} <BR>//首先从html获取编码 <BR>preg_match("/<meta.+?charset=[^\w]?([-\w]+)/i",$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>?></p> <p align="left"><div style="display:none;"><span id="url" itemprop="url">/php/12936.html</span><span id="indexUrl" itemprop="indexUrl">www.phpzy.com</span><span id="isOriginal" itemprop="isOriginal">true</span><span id="isBasedOnUrl" itemprop="isBasedOnUrl">/php/12936.html</span><span id="genre" itemprop="genre">TechArticle</span><span id="description" itemprop="description">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...</span></div></p></div> <div class="art_confoot"><script src='http://www.phpzy.com/ad/art_confoot.js' type="text/javascript"></script></div> <div class="page"></div> <div class="post-related"> <h3 class="tit_3">相关文章</h3><div class="clearfix m_5"> <ul> <li><a href='/php/12935.html' title='php数组函数序列之prev()' target='_blank'>php数组函数序列之prev()</a></li><li><a href='/php/12934.html' title='php数组函数序列之krsort()-对数组的元素键名进行' target='_blank'>php数组函数序列之krsort()-对数组的元素键</a></li><li><a href='/php/12933.html' title='用PHP实现的四则运算表达式计算实现代码' target='_blank'>用PHP实现的四则运算表达式计算实现代码</a></li><li><a href='/php/12932.html' title='php简单的会话类代码' target='_blank'>php简单的会话类代码</a></li><li><a href='/phpyy/12916.html' title='说明的比较细的php正则学习实例' target='_blank'>说明的比较细的php正则学习实例</a></li><li><a href='/phpyy/12915.html' title='phputf-8转unicode的函数' target='_blank'>phputf-8转unicode的函数</a></li></ul></div> </div> <div class="option-btns"> <div class="art_confoot"><script src='http://www.phpzy.com/ad/xgart_confoot.js' type="text/javascript"></script></div> </div> <div id="related_reading" class="haman-box"> <ul class="xgyd clearfix"> <div class="xgyd_new"><span class="fast-nav-bar"><a href="http://www.phpzy.com/fenlei/list-11-1.html">今日最新</a></span><strong>相关阅读:</strong></div> <li><a href="/php/12935.html">php数组函数序列之prev()</a></li> <li><a href="/php/12934.html">php数组函数序列之krsort()-对数组的元素键名进</a></li> <li><a href="/php/12933.html">用PHP实现的四则运算表达式计算实现代码</a></li> <li><a href="/php/12932.html">php简单的会话类代码</a></li> <li><a href="/php/12931.html">如何运用PHP rmdir()函数删除目录</a></li> <li><a href="/php/12930.html">同你分享PHP文件上传的一些注意事项</a></li> </ul></div> <footer><div class="hot_c"><span><b>相关频道:</b> </span></div> </footer> </div> <div class="info_more" id="info_more"></div> <div class="clearfix mt10 art_commentstop" id="commentTopAd"><script src='http://www.phpzy.com/ad/art_commentstop.js' type="text/javascript"></script></div> <div id="hm_t_46468"></div> <a name="comment"></a><div class="comment" id="commentTopAd" itemprop="comment"><h3>PHP之友评论</h3></div> <div class="wb_comment_box" id="commentsiframe"><script type="text/javascript" src='http://www.phpzy.com/ad/comments.js'></script></div> </article> <div class="syzp mt10" style="overflow:hidden;"><div class="tit_7">今天推荐</div><script type="text/javascript" src="http://www.phpzy.com/ad/left_foot_ad.js"></script></div> </div> <aside class="right" id="main_right"> <div class="art_rightad1"><script src='http://www.phpzy.com/ad/art_rightad1.js' type="text/javascript"></script></div> <div class="r_bd mt10 pb10"> <div class="tit_5 tit_6">php教程最近更新</div> <ul id="bbsRank_1" class="rank_ul2 rank_dot" style="border-top:1px solid #AAC5F2;margin-top: -1px;"> <li><a href="/php/12936.html">基于Snoopy的PHP近似完美获取网站编码的代</a> </li> <li><a href="/php/12935.html">php数组函数序列之prev()</a> </li> <li><a href="/php/12934.html">php数组函数序列之krsort()-对数组的元素键</a> </li> <li><a href="/php/12933.html">用PHP实现的四则运算表达式计算实现代码</a> </li> <li><a href="/php/12932.html">php简单的会话类代码</a> </li> </ul></div> <div class="art_rightad2 mt10"><script src='http://www.phpzy.com/ad/art_rightad2.js' type="text/javascript"></script></div> <div class="r_bd mt10 pb10"> <div class="tit_5 tit_6">热门推荐</div> <ul id="bbsRank_1" class="rank_ul2 rank_dot" style="border-top:1px solid #AAC5F2;margin-top: -1px;"> <li><a href="/php/12478.html">php实现文件下载简单示例</a> </li> <li><a href="/php/440.html">PHP数组和Json之间的转换详解</a> </li> <li><a href="/php/7849.html">PHP会话控制</a> </li> <li><a href="/php/3157.html">通过PHP程序知道蜘蛛是否访问你的网站</a> </li> <li><a href="/php/10673.html">PHP3 safe_mode 失效漏洞</a> </li> </ul> </div> <div class="r_bd mt10 pb10"><div style="margin-top: 0pt;" class="tit_5 tit_6">有意思</div> <script type="text/javascript" src="http://www.phpzy.com/ad/right_ad5.js"></script></div> <div class="art_rightad3"><script src='http://www.phpzy.com/ad/art_rightad3.js' type="text/javascript"></script></div> <div id="focus_look" class="instant-focus mt10"><div class="instant-focus-header clearfix"><h3>实时看点</h3><span>看啥好</span></div> <script type="text/javascript" src="http://www.phpzy.com/ad/right_ad6.js"></script></div> <div class="art_rightad4 mt10"><script src='http://www.phpzy.com/ad/art_rightad4.js' type="text/javascript"></script></div> </aside></div></div> <footer id="footer" class="div_body"> <script type="text/javascript" src="http://www.phpzy.com/ad/arc_foot_ad.js"></script> <script type="text/javascript" src="http://www.phpzy.com/templets/js/foot.js"></script> <div style="display:none;"><script src='http://www.phpzy.com/ad/tongji.js' type="text/javascript"></script></div> <div id="roll"></i><a title="回顶部" id="roll_top" href="#top" style="opacity: 0.7;" target="_self" rel="nofllow"></a></div> </footer> <script type="text/javascript" src="http://www.phpzy.com/ad/maintop.js?131231"></script> </body> </html>