正则获取页面编码 判断当前页面的编码

 

        //根据指定网址判断当前页面的编码
        static public string GetWebpageCode(string url)
        {
            string charSet = "";

            WebClient myWebClient = new WebClient();    

            myWebClient.Credentials = CredentialCache.DefaultCredentials;

            //从资源下载数据并返回字节数组。（加@是因为网址中间有"/"符号） 
            byte[] myDataBuffer = myWebClient.DownloadData(url);
            string strWebData = Encoding.Default.GetString(myDataBuffer);

            //获取网页字符编码描述信息 
            Match charSetMatch = Regex.Match(strWebData, "<meta([^<]*)charset=([^<]*)\"", RegexOptions.IgnoreCase | RegexOptions.Multiline);
            string webCharSet = charSetMatch.Groups[2].Value;
            if (charSet == null || charSet == "")
                charSet = webCharSet;
            
            return charSet;

        }