基于Snoopy的PHP近似完美获取网站编码的代码

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

先要到网上下载Snoopy.class.php
调用方法:
复制代码 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();
?>

复制代码 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>?> <br></div></div><p>以上就是基于Snoopy的PHP近似完美获取网站编码的代码的详细内容,更多请关注0133技术站其它相关文章!</p></article><div class="post-actions"><a href="javascript:;" etap="like" class="post-like action action-like" data-pid="0"><i class="fa fa-thumbs-o-up"></i>赞(<span>0</span>)</a><a href="javascript:;" class="action action-rewards" data-event="rewards"><i class="fa fa-jpy"></i> 打赏</a></div><div class="post-copyright">未经允许不得转载:<a href="/">0133技术站首页</a> » <a href="/cate153/">PHP编程</a></div><!--<div class="article-tags">标签:<a href="/archives/tag/javascript" rel="tag">JavaScript</a><a href="/archives/tag/%e5%be%ae%e4%bf%a1" rel="tag">微信</a><a href="/archives/tag/%e5%be%ae%e4%bf%a1%e7%9a%84%e7%89%88%e6%9c%ac%e5%8f%b7" rel="tag">微信的版本号</a><a href="/archives/tag/%e7%89%88%e6%9c%ac%e5%8f%b7" rel="tag">版本号</a><a href="/archives/tag/%e8%af%ad%e4%b9%89%e5%8c%96" rel="tag">语义化</a></div>--><nav class="article-nav"><span class="article-nav-prev">上一篇<br><a href="/cate153/1161506440025.html" rel="prev">摘自织梦CMS的HTTP文件下载类</a></span><span class="article-nav-next">下一篇<br><a href="/cate153/1161536204225.html" rel="next">thinkphp中字符截取函数msubstr()用法分析</a></span></nav><div class="relates relates-thumb"><div class="title"><h3>相关文章</h3></div><ul><li><a href="/cate153/1114368776900.html"><img data-src="https://ss.0133.cn/article/64/2a/15/642a15d53978530b59926bd274131468.jpg-160" alt="thinkPHP5使用Rabc实现权限管理" class="thumb"></a><a href="/cate153/1114368776900.html">thinkPHP5使用Rabc实现权限管理</a></li><li><a href="/cate153/1114615561025.html"><img data-src="https://ss.0133.cn/article/31/68/3d/31683d3113636bc99952c06ff8d4bfbd.jpg-160" alt="php4的session功能评述(二)" class="thumb"></a><a href="/cate153/1114615561025.html">php4的session功能评述(二)</a></li><li><a href="/cate153/1114672436900.html"><img data-src="https://ss.0133.cn/article/7c/c8/6c/7cc86ca9ff7e48b453c41ba7f1b7eb98.jpg-160" alt="php比较两个指定的日期的实例讲解" class="thumb"></a><a href="/cate153/1114672436900.html">php比较两个指定的日期的实例讲解</a></li><li><a href="/cate153/1114673648225.html"><img data-src="https://ss.0133.cn/article/7c/c8/6c/7cc86ca9ff7e48b453c41ba7f1b7eb98.jpg-160" alt="laravel多视图共享数据实例代码" class="thumb"></a><a href="/cate153/1114673648225.html">laravel多视图共享数据实例代码</a></li><li><a href="/cate153/1114674859600.html"><img data-src="https://ss.0133.cn/article/58/93/a1/5893a175f403b71a1ad32a1cbe84cb91.jpg-160" alt="图文详解laravel多对多关联模型" class="thumb"></a><a href="/cate153/1114674859600.html">图文详解laravel多对多关联模型</a></li><li><a href="/cate153/1114676071025.html"><img data-src="https://ss.0133.cn/article/58/93/a1/5893a175f403b71a1ad32a1cbe84cb91.jpg-160" alt="HTTP中header头部信息详解" class="thumb"></a><a href="/cate153/1114676071025.html">HTTP中header头部信息详解</a></li><li><a href="/cate153/1114677282500.html"><img data-src="https://ss.0133.cn/article/58/93/a1/5893a175f403b71a1ad32a1cbe84cb91.jpg-160" alt="Elasticsearch属性单词常用解析说明" class="thumb"></a><a href="/cate153/1114677282500.html">Elasticsearch属性单词常用解析说明</a></li><li><a href="/cate153/1114678494025.html"><img data-src="https://ss.0133.cn/article/58/93/a1/5893a175f403b71a1ad32a1cbe84cb91.jpg-160" alt="PHP之CI框架学习讲解" class="thumb"></a><a href="/cate153/1114678494025.html">PHP之CI框架学习讲解</a></li></ul></div><!-- <div class="title" id="comments"><h3>评论 <small>抢沙发</small></h3></div><div id="respond" class="no_webshot"><form action="return false;" method="post" id="commentform"><div class="comt"><div class="comt-title"><img data-src="https://secure.gravatar.com/avatar/?s=100&d=mm" class="avatar avatar-100" height="50" width="50"><p><a id="cancel-comment-reply-link" href="javascript:;">取消</a></p></div><div class="comt-box"><textarea placeholder="你的评论可以一针见血" class="input-block-level comt-area" name="comment" id="comment" cols="100%" rows="3" tabindex="1" onkeydown="if(event.ctrlKey&&event.keyCode==13){document.getElementById('submit').click();return false};"></textarea><div class="comt-ctrl"><div class="comt-tips"><input type='hidden' name='comment_post_ID' value='6053' id='comment_post_ID'/><input type='hidden' name='comment_parent' id='comment_parent' value='0'/><p style="display: none;"><input type="hidden" id="akismet_comment_nonce" name="akismet_comment_nonce" value="40dd7081eb"/></p><label for="comment_mail_notify" class="checkbox inline hide" style="padding-top:0"><input type="checkbox" name="comment_mail_notify" id="comment_mail_notify" value="comment_mail_notify" checked="checked"/>有人回复时邮件通知我</label><p style="display: none;"><input type="hidden" id="ak_js" name="ak_js" value="245"/></p></div><button type="button" name="submit" id="submit" tabindex="5">提交评论</button>--><!-- <span data-type="comment-insert-smilie" class="muted comt-smilie"><i class="icon-thumbs-up icon12"></i> 表情</span> --><!-- </div></div><div class="comt-comterinfo" id="comment-author-info"><ul><li class="form-inline"><label class="hide" for="author">昵称</label><input class="ipt" type="text" name="author" id="author" value="" tabindex="2" placeholder="昵称"><span class="text-muted">昵称 (必填)</span></li><li class="form-inline"><label class="hide" for="email">邮箱</label><input class="ipt" type="text" name="email" id="email" value="" tabindex="3" placeholder="邮箱"><span class="text-muted">邮箱 (必填)</span></li><li class="form-inline"><label class="hide" for="url">网址</label><input class="ipt" type="text" name="url" id="url" value="" tabindex="4" placeholder="网址"><span class="text-muted">网址</span></li></ul></div></div></form></div>--></div></div><div class="sidebar"><div class="widget widget_ui_tags"><h3>编程</h3><div class="items"><a href="/cate104/">Java</a><a href="/cate105/">C语言</a><a href="/cate133/">新手学堂</a><a href="/cate149/">数据库</a><a href="/cate151/">ASP编程</a><a href="/cate153/">PHP编程</a><a href="/cate154/">XML/RSS</a><a href="/cate155/">Flex</a><a href="/cate156/">正则表达式</a><a href="/cate158/">R语言</a><a href="/cate159/">汇编语言</a><a href="/cate160/">其他教程</a><a href="/cate165/">移动</a></div></div><form method="get" class="search-form clearfix" id="search-formhybrid-search" target="_blank" action="/search/article/"><div class="search-input-wrap"><input type="text" class="search-text" placeholder="来搜我" name="word" id="search-texthybrid-search" value="" data-placeholder=""><b class="search-liaosheji"></b><button type="submit" class="search-button"><i class="icon-search"></i></button></div></form><div style="text-align:center;margin:0 auto;"><ul class='hot-search layui-clear'><li style="float:left;margin-right:20px;">热门搜索:</li><li style="float:left;margin-right:20px;"><a href='/search/article/?word=网站的代码'>网站的代码</a></li><li style="float:left;margin-right:20px;"><a href='/search/article/?word=网站编码'>网站编码</a></li><li style="float:left;margin-right:20px;"><a href='/search/article/?word=近似等于'>近似等于</a></li><li style="float:left;margin-right:20px;"><a href='/search/article/?word=php编码'>php编码</a></li><li style="float:left;margin-right:20px;"><a href='/search/article/?word=完美暂停代码'>完美暂停代码</a></li></ul></div><br/><div class="widget widget_ui_posts"><h3>置顶推荐</h3><ul><li><a href="/cate99/113247636454400.html"><span class="thumbnail"><img data-src="https://ss.0133.cn/upload/article/000/000/001/61c030e32e4d9281.jpg" alt="qq火花是过了24小时断吗" class="thumb"></span><span class="text">qq火花是过了24小时断吗</span><span class="muted">2021-12-20</span></a></li></ul></div><div class="widget widget_recent_entries"><h3>猜你喜欢</h3><ul><li><a href="/cate153/11555762755025.html" target="_blank">php网页标题中文乱码的有效解决方法</a><span class="post-date">2021-10-08</span></li><li><a href="/cate153/11550237528400.html" target="_blank">深入掌握include_once与require_once的区别</a><span class="post-date">2021-10-08</span></li><li><a href="/cate153/1156448968100.html" target="_blank">用PHP实现弹出消息提示框的两种方法</a><span class="post-date">2021-09-13</span></li><li><a href="/cate153/1157700804100.html" target="_blank">利用PHP扩展Xhprof分析项目性能实践教程</a><span class="post-date">2021-09-13</span></li><li><a href="/cate153/11321024188100.html" target="_blank">php数据库的增删改查 php与javascript之间的交互</a><span class="post-date">2021-10-04</span></li><li><a href="/cate153/1159826674025.html" target="_blank">PHPstorm激活码2020年5月13日亲测有效</a><span class="post-date">2021-09-14</span></li><li><a href="/cate153/1160000462500.html" target="_blank">PHP中文分词的简单实现代码分享</a><span class="post-date">2021-09-14</span></li><li><a href="/cate153/11320814584025.html" target="_blank">thinkPHP5框架路由常用知识点汇总</a><span class="post-date">2021-10-04</span></li></ul></div><!--<div class="widget widget_ui_tags"><h3>热门标签</h3><div class="items"><a href="/archives/tag/javascript">JavaScript (324)</a></div></div><div class="widget widget_ui_comments"><h3>最新评论</h3><ul><li><a href="" title=""><img data-src="" class="avatar avatar-100" height="50" width="50"><strong></strong></a></li></ul></div>--></div><div id="leftbar" class="leftbar"><div class="leftbar-con"><div style="text-align: center; width: 160px;"></div></div></div></section><footer class="footer"><div class="container"><p>© 2022 <a href="/">WEB前端开发</a></p><p><a href="/cate88/">工具教程</a> | <a href="/cate71/">前端开发</a> | <a href="/cate61/">常见问题</a> | <a href="/cate129/">操作系统</a> | <a href="/cate103/">编程</a> | <a href="/cate108/">网络安全</a> | <a href="/cate120/">设计</a> | <a href="/cate137/">站长技巧</a></p><div class="footer-gav" style="margin-bottom: 10px ;font-size: 12px;"><img src="https://ss.0133.cn/newimg88/2016/06/beian-gov-cn.png" style="vertical-align: middle; height: 14px;"/><a href="https://beian.miit.gov.cn/" target="_blank">鄂ICP备2021014202号-2</a></div><div class="footer-qrcode"></div></div></footer><script> window.jsui = { www: '', uri: '/wp-content/themes/dux', ver: '5.2.5', roll: ["1", "2"], ajaxpager: '0', url_rp: '/about' }; </script><script type='text/javascript' src='/wp-content/themes/dux/js/libs/bootstrap.min.js?ver=5.2.5'></script><script type='text/javascript' src='/wp-content/themes/dux/js/loader.js?ver=5.2.5'></script><script type='text/javascript' src='/wp-includes/js/wp-embed.min.js?ver=5.0.2'></script><script async="async" type='text/javascript' src='/wp-content/plugins/akismet/_inc/form.js?ver=4.0.8'></script><script type="text/javascript"> var $win = jQuery(window); var $WindowW = $win.width(); var $threebar = jQuery("#leftbar"); if ($threebar.length) { var offsetT = $threebar.offset().top; $win.on("scroll.leftbar", function () { if ($WindowW >= 1200) { if ($win.scrollTop() >= (offsetT)) { $threebar.find(".leftbar-con").css({ "position": "fixed", "top": 0 }); } else { $threebar.find(".leftbar-con").css("position", "static") } } }); } // Array var imagesArr = []; $('#article-content').find("img").each(function (index, Element) { imagesArr.push(Element) }); mediumZoom(imagesArr, { margin: 24, background: '#FFFFFF', scrollOffset: 0 }) </script><script> (function (i, s, o, g, r, a, m) { i['GoogleAnalyticsObject'] = r; i[r] = i[r] || function () { (i[r].q = i[r].q || []).push(arguments) }, i[r].l = 1 * new Date(); a = s.createElement(o), m = s.getElementsByTagName(o)[0]; a.async = 1; a.src = g; m.parentNode.insertBefore(a, m) })(window, document, 'script', '//www.google-analytics.com/analytics.js', 'ga'); ga('create', 'UA-3448069-1', 'css88.com'); ga('send', 'pageview'); </script><script> var _hmt = _hmt || []; (function () { var hm = document.createElement("script"); hm.src = "https://hm.baidu.com/hm.js?08985692e4db1e8be1cff8097c2979b7"; var s = document.getElementsByTagName("script")[0]; s.parentNode.insertBefore(hm, s); })(); </script><script> (function () { var bp = document.createElement('script'); var curProtocol = window.location.protocol.split(':')[0]; if (curProtocol === 'https') { bp.src = 'https://zz.bdstatic.com/linksubmit/push.js'; } else { bp.src = 'http://push.zhanzhang.baidu.com/push.js'; } var s = document.getElementsByTagName("script")[0]; s.parentNode.insertBefore(bp, s); })(); </script></body></html>