目標網頁編碼多樣(UTF-8、GB2312、Big5 等),若不正確解碼即會產生亂碼。核心解法:抓取原始位元組流 → 偵測編碼 → 指定編碼轉字串。
<%@LANGUAGE="JAVASCRIPT" CODEPAGE="65001"%>
<%
Server.ScriptTimeout = 9999999;
function send_request(url) {
var http = Server.CreateObject("Microsoft.XMLHTTP");
http.Open("GET", url, false);
http.Send(null);
if (http.ReadyState == 4) {
// 1. 從 HTTP 標頭或 Meta 標籤偵測編碼
var charResult = http.ResponseText.match(/charset=["']?([\w-]+)/i);
var charset = (charResult != null) ? charResult[1] : "gb2312";
// 2. 以 ADODB.Stream 正確解碼位元組流
return bytesToBSTR(http.ResponseBody, charset);
}
return "Error";
}
function bytesToBSTR(body, charset) {
var stream = Server.CreateObject("ADODB.Stream");
stream.Type = 1; // adTypeBinary
stream.Mode = 3; // adModeReadWrite
stream.Open();
stream.Write(body);
stream.Position = 0;
stream.Type = 2; // adTypeText
stream.Charset = charset;
var text = stream.ReadText;
stream.Close();
return text;
}
// 使用範例
Response.Write(send_request("https://example.com/"));
%>
ResponseBody:回傳未解碼的原始位元組陣列(安全)ResponseText:嘗試用預設編碼解碼(易產生亂碼)Content-Type: text/html; charset=utf-8<meta charset="utf-8"> 或 <meta http-equiv="Content-Type" content="text/html; charset=gb2312">Type=1 (Binary) → Write(bytes) → Position=0 → Type=2 (Text) → Charset=編碼 → ReadText()
try-catch 捕捉連線失敗、編碼不支援等異常Content-Encoding 標頭)此方案以 XMLHTTP 取得二進位流 + ADODB.Stream 指定編碼解碼 為核心,解決 90% 以上採集亂碼問題,是 ASP 採集器的標準作法。