C#抓取网页乱码

[pjw100]

我抓取的地址是搜狐焦点论坛的，例如这个地址：
http://sz.focus.cn/msglist/51806/

编码我试过很多种，gb2312,utf-8...都试过了，始终是乱码。
抓取html代码的程序很简单

能否有哪位大神写个简单的抓取，就应对上面那个地址，乱码整的心慌慌啊。

public static void GetWebContent(string url)
        {
            try
            {
                
                HttpWebRequest myHttpWebRequest = (HttpWebRequest)WebRequest.Create(url);
                //myHttpWebRequest.SendChunked = true;
                //myHttpWebRequest.TransferEncoding = "gb2312";
                HttpWebResponse myHttpWebResponse = (HttpWebResponse)myHttpWebRequest.GetResponse();
                myHttpWebRequest.ContentType = "text/html";
                //Console.WriteLine("The encoding method used is: " + myHttpWebResponse.ContentEncoding);
                Console.WriteLine("字符编码:" + myHttpWebResponse.CharacterSet);
                Stream webStream = myHttpWebResponse.GetResponseStream();
                string encoding = myHttpWebResponse.CharacterSet;
                //经过大量测试发现.NET会将gb2312的编码格式识别为ISO-8859-1，故作此处理
                encoding = (encoding == "ISO-8859-1") ? "gb2312" : encoding;
                //获取的内容是否属于文本
                char seperator = '/';
                String contenttype = myHttpWebResponse.ContentType;
                // 返回 'text' 如果文本类型是'text/html.
                String maintype = contenttype.Substring(0, contenttype.IndexOf(seperator));
                // 只保存内容为'text'类型的网页，不保存示图片等其他文件
                if (String.Compare(maintype, "text") == 0)
                {
                    Console.WriteLine("\n Content type is 'text'.");
                    StreamReader sw = new StreamReader(webStream, System.Text.Encoding.GetEncoding(encoding));
                    Console.WriteLine("网页内容：");
                    StringBuilder sb = new StringBuilder();
                    while (sw.Peek() >= 0)
                    {
                        string strWebContent = sw.ReadLine();
                        sb.Append(strWebContent);
                    }
                    sw.Close();
                    sw.Dispose();
                    webStream.Close();

                    Console.WriteLine(sb.ToString());
                }
                else
                {
                    Console.Write("网页内容不是文本无法显示!");
                }
            }
            catch (Exception ex)
            {
                Console.WriteLine("Error:" + ex.Message);
            }

        }

[机器人]

http://topic.csdn.net/u/20110415/10/c9c33327-a072-420d-bf41-365c4ef86e05.html

[ycproc]

是你抓取后接收的编码问题吧？

[子夜__]

可以获取网页编码

/// <summary>
        /// 根据 url 获取网页编码
        /// </summary>
        /// <param name="url"></param>
        /// <returns></returns>
        public static string GetEncoding(string url)
        {
            HttpWebRequest request = null;
            HttpWebResponse response = null;
            StreamReader reader = null;
            try
            {
                request = (HttpWebRequest)WebRequest.Create(url);
                request.Timeout = 20000;
                request.AllowAutoRedirect = false;

                response = (HttpWebResponse)request.GetResponse();
                if (response.StatusCode == HttpStatusCode.OK && response.ContentLength < 1024 * 1024)
                {
                    if (response.ContentEncoding != null && response.ContentEncoding.Equals("gzip", StringComparison.InvariantCultureIgnoreCase))
                        reader = new StreamReader(new GZipStream(response.GetResponseStream(), CompressionMode.Decompress));
                    else
                        reader = new StreamReader(response.GetResponseStream(), Encoding.ASCII);

                    string html = reader.ReadToEnd();

                    Regex reg_charset = new Regex(@"charset\b\s*=\s*(?<charset>[^""]*)");
                    if (reg_charset.IsMatch(html))
                    {
                        return reg_charset.Match(html).Groups["charset"].Value;
                    }
                    else if (response.CharacterSet != string.Empty)
                    {
                        return response.CharacterSet;
                    }
                    else
                        return Encoding.Default.BodyName;
                }
            }
            catch
            {
            }
            finally
            {

                if (response != null)
                {
                    response.Close();
                    response = null;
                }
                if (reader != null)
                    reader.Close();

                if (request != null)
                    request = null;

            }

            return Encoding.Default.BodyName;
        }