先要到网上下载Snoopy.class.
php
调用方法：
复制代码代码如下:php
getCharset();?>复制代码代码如下:php
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('/ ([^>]*)/si', $this->request->results, $titlematch );if (isset($titlematch) && is_array($titlematch) && count($titlematch) > 0){$info['title'] = strip_tags($titlematch[1]);}preg_match_all('/"]*)"?[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]*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); $i {$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); $i {$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;$i{if(ord($string{$i})continue;if((ord($string{$i})&224)==224){//第一个字节判断通过$char = $string{++$i};if((ord($char)&128)==128){//第二个字节判断通过$char = $string{++$i};if((ord($char)&128)==128){$encoding = "UTF-8";break;}}}if((ord($string{$i})&192)==192){//第一个字节判断通过$char = $string{++$i};if((ord($char)&128)==128){//第二个字节判断通过$encoding = "GB2312";break;}}}return strtolower($encoding);}function uni_decode ($str, $code = 'utf-8'){$str = json_decode(preg_replace_callback('/(d{5});/', create_function('$dec', 'return '\u'.dechex($dec[1]);'), '"'.$str.'"'));if($code != 'utf-8'){ $str = iconv('utf-8', $code, $str); }return $str;}//获取网站编码public function getCharset(){if(!$this->open($this->url)){return false;exit;}//首先从html获取编码preg_match("/request->results,$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$hstr=strtolower(implode("|||",$this->request->headers));preg_match("/charset=[^w]?([-w]+)/is",$hstr,$lang) ? strtolower($lang[1]):"";if($lang[1]!=""){return $lang[1];}}$encode_arr=array("UTF-8","GB2312","GBK","BIG5","ASCII","EUC-JP","Shift_JIS","CP936","ISO-8859-1","JIS","eucjp-win","sjis-win");$encoded=mb_detect_encoding($this->request->results,$encode_arr);if($encoded){return strtolower($encoded);}else{return false;}}}?>