前段时间做RSS阅读器,在获取某些博客时出现了编码问题,比如网易博客。
网易博客的RSS,通过跟踪调试发现其编码 CharacterSet = "ISO-8859-1" 因此利用传统的简单转换方式,无法将其转换为默认编码(UTF-8或GB2312/GBK),在多次试验以后发现利用下面的方法可以转换其编码格式:
privatre void TestDecodeISO88591(string RssUrl)
{
string sResult = "";
System.IO.Stream ResponseStream =null;
HttpWebResponse hwrp = null;
System.IO.StreamReader oStreamReader =null;
Encoding UrlEncoding;
System.Net.HttpWebRequest hwr = (HttpWebRequest)HttpWebRequest.Create(RssUrl);
hwr.Method = "GET";
hwrp = (HttpWebResponse)hwr.GetResponse();
UrlEncoding = Encoding.GetEncoding(hwrp.CharacterSet);
ResponseStream = hwrp.GetResponseStream();
oStreamReader = new System.IO.StreamReader(ResponseStream, UrlEncoding);
sResult = oStreamReader.ReadToEnd();
if (hwrp.CharacterSet == "ISO-8859-1") //如果编码为ISO-8859-1才转换
{
sResult = ConvertISO88591ToEncoding(sResult, Encoding.Default);
}
hwrp.Close();
//处理RSS返回的数据
//.......
}
//转换
private static string ConvertISO88591ToEncoding(string srcString, Encoding dstEncode)
{
String sResult;
Encoding ISO88591Encoding = Encoding.GetEncoding("ISO-8859-1");
Encoding GB2312Encoding = Encoding.GetEncoding("GB2312"); //这个地方很特殊,必须利用GB2312编码
byte[] srcBytes = ISO88591Encoding.GetBytes(srcString);
//将原本存储ISO-8859-1的字节数组当成GB2312转换成目标编码(关键步骤)
byte[] dstBytes = Encoding.Convert(GB2312Encoding, dstEncode, srcBytes);
char[] dstChars = new char[dstEncode.GetCharCount(dstBytes, 0, dstBytes.Length)];
dstEncode.GetChars(dstBytes, 0, dstBytes.Length, dstChars, 0);//利用char数组存储字符
sResult = new string(dstChars);
return sResult;
}