当前位置:Gxlcms > PHP教程 > 基于Snoopy的PHP近似完美获取网站编码的代码_PHP

基于Snoopy的PHP近似完美获取网站编码的代码_PHP

时间:2021-07-01 10:21:17 帮助过:6人阅读

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>?> </div> <div class=""> <ul class="m-news-opt fix"> <li class="opt-item"> <a href='/PHPjiqiao-90138.html' target='_blank'><p>< 上一篇</p><p class="ellipsis">简单的PHP缓存设计实现代码_PHP</p></a> </li> <li class="opt-item ta-r"> <a href='/PHPjiqiao-90140.html' target='_blank'><p>下一篇 ></p><p class="ellipsis">PHP安全防范技巧分享_PHP</p></a> </li> </ul> </div> </div> </div> <div class="g-title fix"> <h2 class="title-txt">人气教程排行</h2> </div> <div class="m-rank u-dashed mb40"> <ul> <li class="rank-item"> <a href="/PHPjiqiao-379253.html" title='php如何获取跳转前的url' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num top">1</span> php如何获取跳转前的url </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-379019.html" title='php格林威治时间转换成当前时间的方法' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num second">2</span> php格林威治时间转换成当前时间的方法 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-366629.html" title='为什么php不能做大型系统?' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num third">3</span> 为什么php不能做大型系统? </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-207623.html" title='range函数怎么用' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num ">4</span> range函数怎么用 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-162433.html" title='php中计算页面加载时间几种方法总结_PHP教程' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num ">5</span> php中计算页面加载时间几种方法总结_PHP教程 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-140221.html" title='求帮助,关于paypal支付返回值修改订单状态' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num ">6</span> 求帮助,关于paypal支付返回值修改订单状态 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-103588.html" title='typecho怎么配置文章内容页?' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num ">7</span> typecho怎么配置文章内容页? </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-99213.html" title='PhpStorm左侧structure不显示文件的方法列表是这么回事?' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num ">8</span> PhpStorm左侧structure不显示文件的方法列表是这么回事? </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-92208.html" title='查看PHP的环境变量_PHP' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num ">9</span> 查看PHP的环境变量_PHP </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-170.html" title='PHP Primary script unknown 解决方法总结' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num ">10</span> PHP Primary script unknown 解决方法总结 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-148.html" title='php的命名空间与自动加载实现方法' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num ">11</span> php的命名空间与自动加载实现方法 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-133.html" title='解决laravel 出现ajax请求419(unknown status)的问题' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num ">12</span> 解决laravel 出现ajax请求419(unknown status)的问题 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-462817.html" title='php 如何删除mysql记录' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">173次</span> <span class="g-sort-num ">13</span> php 如何删除mysql记录 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-388448.html" title='PHP如何替换数组中的指定元素' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">173次</span> <span class="g-sort-num ">14</span> PHP如何替换数组中的指定元素 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-124270.html" title='怎么去除字符串中非汉字、非字母、非数字的字符' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">173次</span> <span class="g-sort-num ">15</span> 怎么去除字符串中非汉字、非字母、非数字的字符 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-112291.html" title='mysql如何一次执行多条SQL语句' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">173次</span> <span class="g-sort-num ">16</span> mysql如何一次执行多条SQL语句 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-110669.html" title='修改header里面的Connection为close解决方法' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">173次</span> <span class="g-sort-num ">17</span> 修改header里面的Connection为close解决方法 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-153.html" title='PHP基于session.upload_progress 实现文件上传进度显示功能详解' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">173次</span> <span class="g-sort-num ">18</span> PHP基于session.upload_progress 实现文件上传进度显示功能详解 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-125.html" title='php5.6.x到php7.0.x特性小结' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">173次</span> <span class="g-sort-num ">19</span> php5.6.x到php7.0.x特性小结 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-378118.html" title='php为什么会出现504错误' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">172次</span> <span class="g-sort-num ">20</span> php为什么会出现504错误 </a> </li> </ul> </div> </div> </div> <!-- / 教程内容页 --> </div> </div> <!-- 页尾 --> <div class="footer"> 本站所有资源全部来源于网络,若本站发布的内容侵害到您的隐私或者利益,请联系我们删除!</div> <!-- / 页尾 --> <script type="text/javascript" src="/kan/js/read.js"></script> <div style="display:none"> <div class="login-box" id="login-dialog"> <div class="login-top"><a class="current" rel="nofollow" id="login1" onclick="setTab('login',1,2);" >登录</a></div> <div class="login-form" id="nav-signin"> <!-- <div class="login-ico"><a rel="nofollow" class="qq" id="qqlogin" target="_blank" href="/user-center-qqlogin.html"> QQ </a></div> --> <div class="login-box-form" id="con_login_1"> <form id="loginform" action="/user-center-login.html" method="post" onsubmit="return false;"> <p class="int-text"> <input class="email" id="username" name="username" type="text" value="用户名或Email" onfocus="if(this.value=='用户名或Email'){this.value='';}" onblur="if(this.value==''){this.value='用户名或Email';};" ></p> <p class="int-text"> <input class="password1" type="password" id="password" name="password" value="******" onBlur="if(this.value=='') this.value='******';" onFocus="if(this.value=='******') this.value='';" > </p> <p class="int-info"> <label class="ui-label"> </label> <label for="agreement" class="ui-label-checkbox"> <input type="checkbox" value="" name="cookietime" id="cookietime" checked="checked" value="2592000"> <input type="hidden" name="notforward" id="notforward" value="1"> <input type="hidden" name="dosubmit" id="dosubmit" value="1">记住我的登录 </label> <a rel="nofollow" class="aright" href="/user-center-forgetpwd.html" target="_blank"> 忘记密码? </a></p> <p class="int-btn"><a rel="nofollow" id="loginbt" class="loginbtn"><span>登录</span></a></p> </form> </div> <form id="regform" action="/user-center-reg.html" method="post"> <div class="login-reg" style="display: none;" id="con_login_2"> <input type="hidden" name="t" id="t"/> <p class="int-text"> <input id="email" name="email" type="text" value="Email" onfocus="if(this.value=='Email'){this.value='';}" onblur="if(this.value==''){this.value='Email';};"></p> <p class="int-text"> <input id="uname" name="username" type="text" value="用户名或昵称" onfocus="if(this.value=='用户名或昵称'){this.value='';}" onblur="if(this.value==''){this.value='用户名或昵称';};"></p> <p class="int-text"> <input type="password" id="pwd" name="password" value="******" onBlur="if(this.value=='') this.value='******';" onFocus="if(this.value=='******') this.value='';"> </p> <p class="int-text1"><span class="inputbox"> <input id="validate" name="validate" type="text" value="验证码" onfocus="if(this.value=='验证码'){this.value='';}" onblur="if(this.value==''){this.value='验证码';};"> </span><span class="yzm-img"><img src="/user-checkcode-index" alt="看不清楚换一张" id="indexlogin"></p> <p class="int-info"> <label> <input value="" name="agreement" id="agreement" CHECKED="checked" type="checkbox"> 我已阅读<a rel="nofollow" href="/user-center-agreement.html">用户协议</a>及<a rel="nofollow" href="/user-center-agreement.html">版权声明</a></label> </p> <p class="int-btn"><input type="hidden" name="dosubmit"/> <a rel="nofollow" class="loginbtn" id="register"><span>注册</span></a></p> </div> </form> </div> </div> </div> </div> <script type="text/javascript" src="/kan/js/foot_js.js"></script> <script> var _hmt = _hmt || []; (function() { var hm = document.createElement("script"); hm.src = "https://hm.baidu.com/hm.js?6dc1c3c5281cf70f49bc0bc860ec24f2"; var s = document.getElementsByTagName("script")[0]; s.parentNode.insertBefore(hm, s); })(); </script> <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, skin: 'notepad', title: 'php怎么实现数据库验证跳转代码块', encode: true //是否转义html标签。默认不开启 }); }); </script> </body> </html>