基于Snoopy的PHP近似完美获取网站编码的代码_PHP
程序员文章站
2022-05-09 16:44:00
...
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('/([^>]*)/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]*' . '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]*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); $i { <br>$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); $i { <br>$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;$i<strlen>{ <br>if(ord($string{$i})continue; <br>if((ord($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($this->url)){return false;exit;} <br>//首先从html获取编码 <br>preg_match("/<meta.>request->results,$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>?></meta.></strlen>
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('/