乱码问题

[haihuan23]

public partial class Search : System.Web.UI.Page
{
    protected void Page_Load(object sender, EventArgs e)
    {
        Response.Write(GetUrlData("http://www.google.com.hk"));
    }

    public string GetUrlData(string url)
    {
        System.Net.HttpWebRequest webRequest = (System.Net.HttpWebRequest)System.Net.WebRequest.Create(url);
        System.Net.WebResponse webResponse = webRequest.GetResponse();      
        System.IO.Stream iStream = webResponse.GetResponseStream();
        System.IO.StreamReader sr = new System.IO.StreamReader(iStream, System.Text.Encoding.Default);
        string str = sr.ReadToEnd();
        sr.Close();
        iStream.Close();
        webResponse.Close();
        return str;
    }
}

System.Text.Encoding.ASCII UTF8 等都尝试过，都是乱码。。请教各位

[子夜__]

自动获取编码

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Net;
using System.IO;
using System.IO.Compression;
using System.Text.RegularExpressions;

namespace WikiPageCreater.Common
{
    public class PageHelper
    {
        /// <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;
        }

        /// <summary>
        /// 根据 url 和 encoding 获取当前url页面的 html 源代码        
       /// </summary>
        /// <param name="url"></param>
        /// <param name="encoding"></param>
        /// <returns></returns>
        public static string GetHtml(string url, Encoding encoding)
        {
            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), encoding);
                    else
                        reader = new StreamReader(response.GetResponseStream(), encoding);
                    string html = reader.ReadToEnd();

                    return html;
                }
            }
            catch
            {
            }
            finally
            {

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

                if (request != null)
                    request = null;

            }

            return string.Empty;
        }
    }
}

[天下在我心]

你传过来的那个页面编码是什么，两边需要统一

[haihuan23]

查看Google 源文件 是UTF-8的。
<meta http-equiv="content-type" content="text/html; charset=UTF-8">

[md5e]

using System;
using System.Collections;
using System.Configuration;
using System.Data;
using System.Web;
using System.Web.Security;
using System.Web.UI;
using System.Web.UI.HtmlControls;
using System.Web.UI.WebControls;
using System.Web.UI.WebControls.WebParts;
using System.Xml;
using System.Net;
using System.IO;
using System.Text;
namespace NetCMS.Web
{
    public partial class AjaxGeturl : System.Web.UI.Page
    {
        protected void Page_Load(object sender, EventArgs e)
        {
            if (!IsPostBack)
            {
                string url = string.Empty;
                url = Request.QueryString["url"];
                Response.Write(GetResStr(url, "utf-8"));
                Response.End();
            }
        }
        string GetResStr(string url, string Encod)
        {
            WebRequest WReq;
            WebResponse WResp;
            StreamReader sr;
            WReq = WebRequest.Create(url);
            WResp = WReq.GetResponse();
            sr = new StreamReader(WResp.GetResponseStream(), Encoding.GetEncoding(Encod));
            string retValue = sr.ReadToEnd();
            sr.Close();
            return retValue;
        }
    }

}

[haihuan23]

奇怪。断点读取 str的内容 发现在
<meta http-equiv="content-type" content="text/html; charset=Big5">

Big5是神马编码。

[zhanglong_longlong]

<meta http-equiv="content-type" content="text/html; charset=UTF-8">

[haihuan23]

google 怎么 从response 里得的big5码 变成页面显示的 uft-8 的。


各路大哥有研究的，给个提示也好啊。

[md5e]

sr = new StreamReader(WResp.GetResponseStream(), Encoding.GetEncoding("big5"));
不管什么编码过来，.net都是utf-8

[haihuan23]

为什么用浏览器得到的响应里 的编码是 utf-8 用

        System.Net.HttpWebRequest webRequest = (System.Net.HttpWebRequest)System.Net.WebRequest.Create(url);
        System.Net.WebResponse webResponse = webRequest.GetResponse();      
        System.IO.Stream iStream = webResponse.GetResponseStream();
        System.IO.StreamReader sr = new System.IO.StreamReader(iStream, System.Text.Encoding.Default);
        string str = sr.ReadToEnd();

得到 的却是Big5 呢。

[fxsy6669]

页面中的转码方式要与后台的编码方式一致。。

[檸檬香草]

我来看看。。。。

[v_yao]

这个你要看你页面的编码！

[haihuan23]

子夜大哥的方法很好用，谢谢。

另外再请教：google 怎么 从response 里得的big5码 变成页面显示的 uft-8 的。

[wylp_19]

编码不一致