解决网爬工具爬取页面信息出现乱码的问题_asp.net技巧

问题：
   网爬工具中自动搜集页面信息时，有的页面出现了出现乱码现象
原因：
   读取页面信息是使用了错误的编码类型。C#.NET从现在的类中获取得来的编码信息有时是错误的，本人认为对不是ASP.NET的应用程序，它读过来的编码信息都是错误的。
解决：
   思路：必须先在运行时获取得该页面的编码，再去读取页面的内容，这样得来的页面内容才不会出现乱码现象。
   方法：
   1:使用ASCII编码去读取页面内容。
   2:使用正则表达式从读取的页面内容中筛选出页面的编码信息。上个步骤获取的页面信息可能会有乱码。但HTML标志是正确的，所有可以从HTML标志中得到编码的信息。
   3.用正确的编码类型去读取页面信息。
   如果哪位有更好的方法，请多赐教啊！

  
   下面附上代码：   

代码演示
using System;
using System.Collections.Generic;
using System.Text;
using System.Net;
using System.Web;
using System.IO;
using System.Text.RegularExpressions;
namespace charset
{
    class Program
    {
       
        static void Main(string[] args)
        {
            string url = “http://www.gdqy.edu.cn“;
            GetCharset1(url);
            GetChartset2(url);

            Console.Read();
        }
        // 通过HttpWebResponse直接获取页面编码
        static void GetCharset1(string url)
        {
            try
            {
                WebRequest webRequest = WebRequest.Create(url);
                HttpWebResponse webResponse = (HttpWebResponse)webRequest.GetResponse();

                string charset = webResponse.CharacterSet;
                string contentEncoding = webResponse.ContentEncoding;
                string contentType = webResponse.ContentType;

                Console.WriteLine(“context type:{0}”, contentType);

                Console.WriteLine(“charset:{0}”, charset);

                Console.WriteLine(“content encoding:{0}”, contentEncoding);
                //测试或取页面是否出现乱码
                //Console.WriteLine(getHTML(url,charset));
               
            }
            catch (UriFormatException ex)
            {

                Console.WriteLine(ex.Message);
            }
            catch(WebException ex)
            {
           
                Console.WriteLine(ex.Message);
            }
           
           
            

        }
        //使用正则表达式获取页面编码
        static void GetChartset2(string url)
        {

            try
            {
                string html = getHTML(url,Encoding.ASCII.EncodingName);
                Regex reg_charset = new Regex(@”charset\b\s*=\s*(?<charset>[^””]*)”);
                string enconding = null;
                if (reg_charset.IsMatch(html))
                {
                    enconding = reg_charset.Match(html).Groups[“charset”].Value;
                    Console.WriteLine(“charset:{0}”,enconding);
                }
                else
                {
                    enconding = Encoding.Default.EncodingName;
                }
                //测试或取页面是否出现乱码
                //Console.WriteLine(getHTML(url,enconding));
             }
            catch (UriFormatException ex)
            {

                Console.WriteLine(ex.Message);
            }
            catch(WebException ex)
            {
           
                Console.WriteLine(ex.Message);
            }
       
        }
        //读取页面内容方法
        static string  getHTML(string url,string encodingName)
        {

            try
            {
                WebRequest webRequest = WebRequest.Create(url);
                WebResponse webResponse = webRequest.GetResponse();
                Stream stream = webResponse.GetResponseStream();
                StreamReader sr = new StreamReader(stream, Encoding.GetEncoding(encodingName));
                string html = sr.ReadToEnd();
                return html;
            }
            catch (UriFormatException ex)
            {

                Console.WriteLine(ex.Message);
                return null;
            }
            catch (WebException ex)
            {

                Console.WriteLine(ex.Message);
                return null;
            }
        }
       
    }
}

 http://www.gdqy.edu.cn页面的使用的编码格式是：gb2312
第一个方法显示的内容是：
context type:text/html
charset:ISO-8859-1
content encoding:
第二个方法显示的内容是：
charset:gb2312

所以第一个方法获取的信息是错误的，第二个方法是对的。
为什么第一个方法获取的的编码格式是：ISO-8859-1呢？
我用Reflector反射工具获取了CharacterSet属性的源代码，从中不难看出其原因。如果能获取出ContentType属性的源代码就不以看出其出错的原因了，但是搞了许久都没找出，如果那位那补上，那就太感谢了。
下面我附上Reflector反射工具获取了CharacterSet属性的源代码，有兴趣的朋友看一看。

CharacterSet源码
public string CharacterSet
{
      get
      {
            this.CheckDisposed();
            string text1 = this.m_HttpResponseHeaders.ContentType;
            if ((this.m_CharacterSet == null) && !ValidationHelper.IsBlankString(text1))
            {
                  this.m_CharacterSet = string.Empty;
                  string text2 = text1.ToLower(CultureInfo.InvariantCulture);
                  if (text2.Trim().StartsWith(“text/”))
                  {
                        this.m_CharacterSet = “ISO-8859-1”;
                  }
                  int num1 = text2.IndexOf(“;”);
                  if (num1 > 0)
                  {
                        while ((num1 = text2.IndexOf(“charset”, num1)) >= 0)
                        {
                              num1 += 7;
                              if ((text2[num1 – 8] == 😉 || (text2[num1 – 8] == ))
                              {
                                    while ((num1 < text2.Length) && (text2[num1] == ))
                                    {
                                          num1++;
                                    }
                                    if ((num1 < (text2.Length – 1)) && (text2[num1] == =))
                                    {
                                          num1++;
                                          int num2 = text2.IndexOf(;, num1);
                                          if (num2 > num1)
                                          {
                                                this.m_CharacterSet = text1.Substring(num1, num2).Trim();
                                                break;
                                          }
                                          this.m_CharacterSet = text1.Substring(num1).Trim();
                                          break;
                                    }
                              }
                        }
                  }
            }
            return this.m_CharacterSet;
      }

http://www.cnblogs.com/xuanfeng/archive/2007/01/21/626296.html