php采集网页编码问题！

一个用php写的采集其他网站资料的页面，以前能正常采集，现在采集原网站升级了，网页编码类型更换了。我采集到的内容成了乱码，求人解决！附上一个采集页面的代码。QQ 1872 32958  可以付费解决！<?
//if ($HTTP_SERVER_VARS['SERVER_ADDR']<>"58.64.136.81"){exit;}if (date('Y-m-d')>'2009-01-01'){exit;}include "../../lib/library.mem.php";
include "../../lib/mysqllib.php";
include "../../lib/pub_library.php";
include "../../lib/http.class.php";
$langx='zh-tw';
$t_page=1;
for($pages=0;$pages<$t_page;$pages++){
$data=get_uid($langx);
$data=theif_data($data[0],$data[1],'FT','r',$langx,$pages);$pb=explode('t_page=',$data);
$pb=explode(';',$pb[0]);
$t_page=$pb[0];if (sizeof(explode("gamount",$data))>1){
$k=0;
preg_match_all("/Array$(.+?)$;/is",$data,$matches);
$cou=sizeof($matches[0]);
$db = new proc_DB(DB_HOST,DB_USER,DB_PWD,DB_NAME); for($i=0;$i<$cou;$i++){
$messages=$matches[0][$i];
$messages=str_replace(");",")",$messages);
$messages=str_replace("cha(5)","",$messages);
$datainfo=eval("return $messages;");
$dtime=match_start($datainfo[1]);
if($datainfo[0]+0!=0){
if (sizeof(explode('<BR>',strtoupper($datainfo[1])))>2){
$m_type=1;
}else{
$m_type=0;
} $mb_team = big52gb($datainfo[5]);
$tg_team = big52gb($datainfo[6]);
$league = big52gb($datainfo[2]); $sql="select mid,mb_team,tg_team,mb_team_tw,tg_team_tw from foot_match where mid=$datainfo[0]";
$db->query($sql,1);
if($db->num_rows()==0){
$sql = "INSERT INTO foot_match(MID,M_Start,M_Date,M_Time,MB_Team,TG_Team,MB_Team_tw,TG_Team_tw,M_League_tw,M_League,MB_MID,TG_MID,R_Show) VALUES
('$datainfo[0]','$dtime[2]','$dtime[0]','$dtime[1]','$mb_team','$tg_team','$datainfo[5]','$datainfo[6]','$datainfo[2]','$league','$datainfo[3]','$datafo[4]','1')";
$db->query($sql);
}else{
if($db->f('mb_team')=='' or $db->f('tg_team')=='' or $db->f('tg_team_tw')=='' or $db->f('mb_team_tw')==''){
$sql = "update foot_match set mb_team='$mb_team',tg_team='$tg_team',MB_Team_tw='$datainfo[4]',TG_Team_tw='$datainfo[6]',M_League='$league',M_League_tw='$datainfo[2]' where MID=$datainfo[0]";
$db->query($sql);
}
}
}
}
$db->close();
}
}
?>
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=big5">
<title></title>
<link href="/style/style.css" rel="stylesheet" type="text/css">
<style type="text/css">

</style>
</head><body bgcolor="#AACCCC">
<script>

</script>
<table width="102" height="100" border="0" cellpadding="0" cellspacing="0">
  <tr>
    <td width="110" height="110" align="center">
      虫Αタ钡Μ<br>
      <span id="timeinfo"></span><br>
      <input type=button name=button value="羉蔨" onClick="window.location.reload()"></td>
  </tr>
</table>
</body>
</html>

解决方案 »

免费领取超大流量手机卡，每月29元包185G流量+100分钟通话, 中国电信官方发货

<meta http-equiv="Content-Type" content="text/html; charset=big5">
这句把big5换成网页现在的编码
big52gb这个函数可能要改。你现在首先要确定，对方用了什么编码，你需要什么编码，然后转换后再存入数据库。
楼上的朋友，可否付费解决此问题啊。采集代码不需要改变，各项都能采集到，但就是字符编码问题，采集到乱码，QQ 1872 32958我看不出他网站是啥编码来！看源代码智能看到这个<html>
<head>

<title>Welcome </title>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<frameset rows="*,0,0" frameborder="NO" border="0" framespacing="0">
<frame name="SI2_mem_index" src="app/member/">
<frame name="SI2_func" scrolling="NO" noresize src="./ok.html">
</frameset>
<noframes>
<body bgcolor="#FFFFFF" text="#000000">
</body>
</noframes>
</html>
你最好是采集到这个页面的时候先把内容转换成你现在的编码。
给你一个转换编码的函数，很方便的。<?php
//UTF-8 转GB编码
function utf82gb($utfstr)
{
if(function_exists('iconv'))
{
return iconv('utf-8','gbk//ignore',$utfstr);
}
global $UC2GBTABLE;
$okstr = "";
if(trim($utfstr)=="")
{
return $utfstr;
}
if(empty($UC2GBTABLE))
{
$filename = "data/gb2312-utf8.dat";
$fp = fopen($filename,"r");
while($l = fgets($fp,15))
{
$UC2GBTABLE[hexdec(substr($l, 7, 6))] = hexdec(substr($l, 0, 6));
}
fclose($fp);
}
$okstr = "";
$ulen = strlen($utfstr);
for($i=0;$i<$ulen;$i++)
{
$c = $utfstr[$i];
$cb = decbin(ord($utfstr[$i]));
if(strlen($cb)==8)
{
$csize = strpos(decbin(ord($cb)),"0");
for($j=0;$j < $csize;$j++)
{
$i++; $c .= $utfstr[$i];
}
$c = utf82u($c);
if(isset($UC2GBTABLE[$c]))
{
$c = dechex($UC2GBTABLE[$c]+0x8080);
$okstr .= chr(hexdec($c[0].$c[1])).chr(hexdec($c[2].$c[3]));
}
else
{
$okstr .= "&#".$c.";";
}
}
else
{
$okstr .= $c;
}
}
$okstr = trim($okstr);
return $okstr;
}//GB转UTF-8编码
function gb2utf8($gbstr)
{
if(function_exists('iconv'))
{
return iconv('gbk','utf-8//ignore',$gbstr);
}
global $CODETABLE;
if(trim($gbstr)=="")
{
return $gbstr;
}
if(empty($CODETABLE))
{
$filename = "data/gb2312-utf8.dat";
$fp = fopen($filename,"r");
while ($l = fgets($fp,15))
{
$CODETABLE[hexdec(substr($l, 0, 6))] = substr($l, 7, 6);
}
fclose($fp);
}
$ret = "";
$utf8 = "";
while ($gbstr != '')
{
if (ord(substr($gbstr, 0, 1)) > 0x80)
{
$thisW = substr($gbstr, 0, 2);
$gbstr = substr($gbstr, 2, strlen($gbstr));
$utf8 = "";
@$utf8 = u2utf8(hexdec($CODETABLE[hexdec(bin2hex($thisW)) - 0x8080]));
if($utf8!="")
{
for ($i = 0;$i < strlen($utf8);$i += 3)
$ret .= chr(substr($utf8, $i, 3));
}
}
else
{
$ret .= substr($gbstr, 0, 1);
$gbstr = substr($gbstr, 1, strlen($gbstr));
}
}
return $ret;
}//Unicode转utf8
function u2utf8($c)
{
for ($i = 0;$i < count($c);$i++)
{
$str = "";
}
if ($c < 0x80)
{
$str .= $c;
}
else if ($c < 0x800)
{
$str .= (0xC0 | $c >> 6);
$str .= (0x80 | $c & 0x3F);
}
else if ($c < 0x10000)
{
$str .= (0xE0 | $c >> 12);
$str .= (0x80 | $c >> 6 & 0x3F);
$str .= (0x80 | $c & 0x3F);
}
else if ($c < 0x200000)
{
$str .= (0xF0 | $c >> 18);
$str .= (0x80 | $c >> 12 & 0x3F);
$str .= (0x80 | $c >> 6 & 0x3F);
$str .= (0x80 | $c & 0x3F);
}
return $str;
}//utf8转Unicode
function utf82u($c)
{
switch(strlen($c))
{
case 1:
return ord($c);
case 2:
$n = (ord($c[0]) & 0x3f) << 6;
$n += ord($c[1]) & 0x3f;
return $n;
case 3:
$n = (ord($c[0]) & 0x1f) << 12;
$n += (ord($c[1]) & 0x3f) << 6;
$n += ord($c[2]) & 0x3f;
return $n;
case 4:
$n = (ord($c[0]) & 0x0f) << 18;
$n += (ord($c[1]) & 0x3f) << 12;
$n += (ord($c[2]) & 0x3f) << 6;
$n += ord($c[3]) & 0x3f;
return $n;
}
}//Big5码转换成GB码
function big52gb($Text)
{
if(function_exists('iconv'))
{
return iconv('big5','gbk//ignore',$Text);
}
global $BIG5_DATA;
if(empty($BIG5_DATA))
{
$filename = "data/big5-gb.dat";
$fp = fopen($filename, "rb");
$BIG5_DATA = fread($fp,filesize($filename));
fclose($fp);
}
$max = strlen($Text)-1;
for($i=0;$i<$max;$i++)
{
$h = ord($Text[$i]);
if($h>=0x80)
{
$l = ord($Text[$i+1]);
if($h==161 && $l==64)
{
$gbstr = "　";
}
else
{
$p = ($h-160)*510+($l-1)*2;
$gbstr = $BIG5_DATA[$p].$BIG5_DATA[$p+1];
}
$Text[$i] = $gbstr[0];
$Text[$i+1] = $gbstr[1];
$i++;
}
}
return $Text;
}//GB码转换成Big5码
function gb2big5($Text)
{
if(function_exists('iconv'))
{
return iconv('gbk','big5//ignore',$Text);
}
global $GB_DATA;
if(empty($GB_DATA))
{
$filename = "data/gb-big5.dat";
$fp = fopen($filename, "rb");
$gb = fread($fp,filesize($filename));
fclose($fp);
}
$max = strlen($Text)-1;
for($i=0;$i<$max;$i++)
{
$h = ord($Text[$i]);
if($h>=0x80)
{
$l = ord($Text[$i+1]);
if($h==161 && $l==64)
{
$big = "　";
}
else
{
$p = ($h-160)*510+($l-1)*2;
$big = $GB_DATA[$p].$GB_DATA[$p+1];
}
$Text[$i] = $big[0];
$Text[$i+1] = $big[1];
$i++;
}
}
return $Text;
}//unicode url编码转gbk编码函数
function UnicodeUrl2Gbk($str)
{
//载入对照词典
if(!isset($GLOBALS['GbkUniDic']))
{
$fp = fopen('data/gbk-unicode.dat','rb');
while(!feof($fp))
{
$GLOBALS['GbkUniDic'][bin2hex(fread($fp,2))] = fread($fp,2);
}
fclose($fp);
} //处理字符串
$str = str_replace('$#$','+',$str);
$glen = strlen($str);
$okstr = "";
for($i=0; $i < $glen; $i++)
{
if($glen-$i > 4)
{
if($str[$i]=='%' && $str[$i+1]=='u')
{
$uni = strtolower(substr($str,$i+2,4));
$i = $i+5;
if(isset($GLOBALS['GbkUniDic'][$uni]))
{
$okstr .= $GLOBALS['GbkUniDic'][$uni];
}
else
{
$okstr .= "&#".hexdec('0x'.$uni).";";
}
}
else
{
$okstr .= $str[$i];
}
}
else
{
$okstr .= $str[$i];
}
}
return $okstr;
}?>
你给的信息不足，或是说不明晰！假定
$data=theif_data($data[0],$data[1],'FT','r',$langx,$pages);
后的 $data 就是采集到的原始页面内容
这一点你可以 echo $data; 看看。不是也没关系，但你总是需要找到他的
找到他后，在他的下面加入（其中 $data 视具体情况定）以下代码即可
$codepage = mb_detect_encoding($data, array('ASCII','UTF-8','BIG-5','GBK'));
$data = mb_convert_encoding($data, 'big5', $codepage);
我站文件里边有个转换符号的文件，但是打开后都是乱码，根本无法看。文件名字为 big5-gb.table怎么修改啊。请高手帮忙啊，付费解决问题啊！QQ 1872 32958
我站文件里边有个转换符号的文件，但是打开后都是乱码，根本无法看。文件名字为 big5-gb.table怎么修改啊。请高手帮忙啊，付费解决问题啊！QQ 1872 32958
根据7楼做法，把date 加了两句代码，还是显示出来的还是乱码！蚞{SY??5n?#軀gv#蓊迢?袾黝DG?`?????薈DEQ?QQQ@AP?dV??o?簭?L(乇党??騱妄????憓囅?稹?*n?wJ?賀檐÷?滐?u[Ow┬]:翮嬬 ????騏?:捂{ ?螗訃忑鼷?z;?r舼?簌3呏??>偩HN?晷?珧?k??gOv??_恤棪蟼3]澼盼?疑o~?k??茸削z惑]呏?|??ㄜg:z ?凱鞤G?鼇?u?M?/菌?櫙朦遮dt蘶Gu ?沍QU踀嶚????隋W*吨G>Ev媕婕7紩%|絔開溺??hu騁wx??河?N??#s?,?逅朕?謬i餮??可yC??o鴰伏臐~??_&W?LN????齡?愊n<???M?圩???^ O?4妲h??~?EY??禖n鞪蹶5??蔯/剩顛麂???uv茌|戥lH般?s?k? ??sT玂6U&涄`博pT2??簟Su焋擳??t???鞚冷庌???/遙賀??? G*R^汞_?僗?V?"/~渦W?yP莞?K€?????l?? 駿??諝 ?zM?U]B誅?*彏`g?鸞竁濣?? 2?矂DF? j/?ACFPU8扷旖Zq??7?? 矣L?爔lX?I?@SPu8j?及?#曶k??K?X@d?酢:?L炬?C,Am?6?€?Gk(x 灩;?p$纗??忀?漶??鼱? TΑ? go?-醙sZEQ?W?~罹z??U?B??6I絿? _#{?輵[?蛐皇??P苧 U,^c0A遑c?浾7_0M諼?左I谹謷x?p??#Y@?!1簥=L~d賞?! 9!氯?@?蛖?攮\_場k'Z鶁B栗?_ &+%V完???@^-竊h????孟+?案?鉔??}?? ??1??TW: 皻`喓曏=?a?jJ計?*蕦快伴v?W酘~鸁N???年?ｚb?紳C: !Hm;蓏 L凘l?1胝8z€Z??? ?>蠜?Q3`.{[j0妃 TT伏菧;!?9腿Un=ˋ縼紌?u醰??}%w??靄<4yP荇T琚?*菮\, ??"*4?nS?6?>G`?閃?dR9?<齻應F???]S?IX@ 獶輲踱(扽‥X/??B砃嵙?#L楠Tk g4?J蟒Yx?S$?赽棻牘聇?諅^!髦Zy蠛??弱?鴆辴怬?Ue?庈擲渀;6L蛖z?嗡詄p靉?
你能不能把要采集的网站的URL贴出来
我看楼上的都给了解决办法，看着你要采集的网站是uft－8的编码，可能是你的网站的编码不是uft-8编码，所以他是按你的网站来编码的，以至于出现乱吗，你可以用上面给的mb_detect_encoding函数确定下编码方式，然后转换下编码(iconv函数），或者你直接用正则表达是取出charset=big5来确定编码。
试试看能不能解决问题吧