php 获取数据乱码有关问题

php 获取数据乱码问题

本帖最后由 qq_25293153 于 2015-01-13 15:42:18 编辑 file_get_contents 采集一个页面的数据，获取的数据是乱码，已经使用了检测编码的方式，
检测的是utf-8,我的页面编码也是utf-8，但是还是显示乱码，不知道为什么

<br /><br />$url="xxx";<br />$opts = array( <br />  'http'=>array( <br />    'user_agent' => "Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)",<br />  ) <br />); <br />$context = stream_context_create($opts); <br />$neirong = file_get_contents($url, false, $context);<br /><br /> header("content-Type: text/html; charset=Utf-8"); <br />	 ob_end_flush();<br />	 $encode = mb_detect_encoding($neirong, array("ASCII","UTF-8","GB2312","GBK","BIG5")); <br />	 <br />        echo $encode."<br>";<br />		<br />		if ($encode!="UTF-8")<br />		{<br />     $neirong=mb_convert_encoding($neirong, "UTF-8", $encode); <br />	  <br />	 } <br />	  <br />	 <br /><br />echo $neirong;<br /><br /><br /><br />

 $encode  输出：utf-8
$neirong 输出是乱码
我的页面编码是utf-8
------解决思路----------------------
你在輸出的html中加入

它源數據是做了些轉換的，我那個程序已經是轉換過來了。

我把採集的也寫出來，直接運行就可以了。

<br /><?php  <br />//http://www.ziyouge.com/conbdhekbefiab<br />//http://www.ziyouge.com/zy/4/4980/1333249.html<br /><br />// 獲取程序<br /><br />$url = 'http://www.ziyouge.com/conbdhekbefiab';<br /><br />$headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36';<br />$headerArr = array();  <br />foreach( $headers as $n => $v ) {  <br />    $headerArr[] = $n .':' . $v;   <br />}<br /><br />$ch = curl_init();<br />curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);	<br />curl_setopt($ch, CURLOPT_URL, $url);<br />curl_setopt($ch, CURLOPT_HTTPHEADER , $headerArr );  //构造IP<br />curl_setopt($ch, CURLOPT_REFERER, 'http://www.ziyouge.com/');   //构造来路<br />$content = curl_exec($ch);<br />$content = substr($content,3);<br />if($error=curl_error($ch)){<br />	die($error);<br />}<br />curl_close($ch);<br /><br />// 分析程序<br /><br />$result = '';<br />$str_length = mb_strlen($content);<br />$i=0;<br />while ($i<=$str_length)<br />{<br />	$temp_str=mb_substr($content,$i,1);<br />	$ascnum=Ord($temp_str);<br />	if ($ascnum>=224){<br />		$result .= change(mb_substr($content,$i,3));<br />		$i=$i+3;<br />	}else{<br />		$result .= mb_substr($content,$i,1);<br />		$i=$i+1;<br />	}<br />}<br /><br />echo '<meta http-equiv="content-type" content="text/html;charset=utf-8">';<br />echo $result;<br /><br />// 處理<br />function change($str){<br /><br />	$ignore = array('“','”','！','…','：','，','，');<br /><br />	if(in_array($str, $ignore)){<br />		return $str;<br />	}<br /><br />	$prefix = "%u";<br />	$postfix = "";<br />    $str = iconv('UTF-8', 'UCS-2', $str);<br />    $arrstr = str_split($str, 2);<br />    $unistr = '';<br />    for($i = 0, $len = count($arrstr); $i < $len; $i++) {<br />        $tmp = hexdec(bin2hex($arrstr[$i]));<br />		$tmp = str_pad(dechex($tmp),4,'0',STR_PAD_LEFT);<br />		$tmp = decrypt(substr($tmp,2,2).substr($tmp,0,2));<br />		$unistr .= $prefix . $tmp . $postfix;<br />    }<br />	return unescape($unistr);<br />}<br /><br />// 解密<br />function decrypt($d){<br />	$result = str_pad(dechex(hexdec($d)-100),4,'0',STR_PAD_LEFT);<br />	return $result;<br />}<br /><br />// 轉中文<br />function unescape($str) {  <br />    $ret = '';  <br />    $len = strlen ( $str );  <br />    for($i = 0; $i < $len; $i ++) {  <br />        if ($str [$i] == '%' && $str [$i + 1] == 'u') {  <br />            $val = hexdec ( substr ( $str, $i + 2, 4 ) );  <br />            if ($val < 0x7f)  <br />                $ret .= chr ( $val );  <br />            else if ($val < 0x800)  <br />                $ret .= chr ( 0xc0 <br><font color='#FF8000'>------解决思路----------------------</font><br> ($val >> 6) ) . chr ( 0x80 <br><font color='#FF8000'>------解决思路----------------------</font><br> ($val & 0x3f) );  <br />            else  <br />                $ret .= chr ( 0xe0 <br><font color='#FF8000'>------解决思路----------------------</font><br> ($val >> 12) ) . chr ( 0x80 <br><font color='#FF8000'>------解决思路----------------------</font><br> (($val >> 6) & 0x3f) ) . chr ( 0x80 <br><font color='#FF8000'>------解决思路----------------------</font><br> ($val & 0x3f) );  <br />            $i += 5;  <br />        } else if ($str [$i] == '%') {  <br />            $ret .= urldecode ( substr ( $str, $i, 3 ) );  <br />            $i += 2;  <br />        } else  <br />            $ret .= $str [$i];  <br />    }  <br />    return $ret;  <br />}   <br />?> <br />