日期:2014-05-17 浏览次数:20959 次
public static string GetHtml(string url, Encoding encoding)
        {
            HttpWebResponse response = null;
            Stream dataStream = null;
            StreamReader reader = null;
            try
            {
                WebRequest request = WebRequest.Create(url);
                request.Credentials = CredentialCache.DefaultCredentials;
                request.Timeout = 300000;
                response = (HttpWebResponse)request.GetResponse();
                dataStream = response.GetResponseStream();
                reader = new StreamReader(dataStream, encoding);
                return reader.ReadToEnd();
            }
            catch (Exception ex)
            {
                WriteLog(ex);
                return "";
            }
        }
使用上面这个方法获取网页的源码,出现中文乱码,但不是所有的中文都是乱码,只是部分出现乱码,如:
<table width="90%" border="0" cellspacing="1" cellpadding="1" class="font" align="center">
                    <tr bgcolor="#CADBFF"> 
                      <td bgcolor="#CADBFF" width="15%" align="right" height="25">箱号:</td>
                      <td width="35%" bgcolor="#ACBEFF">
                        WHLU2412918
                      </td>
                      <td width="15%" bgcolor="#CADBFF" align="right">尺寸:</td>
                      <td width="35%" bgcolor="#ACBEFF">
                        20?卞昂
                      </td>
                    </tr>
                    <tr bgcolor="#E6EDFD" > 
                      <td bgcolor="#CADBFF" width="15%" align="right" height="25">箱型:</td>
                      <td width="35%" >
                        
                      </td>
                      <td width="15%" bgcolor="#CADBFF" align="right" >高度:</td>
                      <td width="35%" >
                        8?卞昂6?卞?
                      </td>
                    </tr>
                    <tr bgcolor="#ACBEFF" > 
                      <td bgcolor="#CADBFF" width="15%" align="right" height="25" >状态:</td>
                      <td width="35%" bgcolor="#ACBEFF" >
                        ?哄????
                      </td>
我试过好几种获取源码的方法,都不能解决这个问题?请问如何解决这个问题呢?