如何判断在网页中是否有某一个敏感的字。

Request取得这个网页的代码，
再查找就OK了。

解决方案 »

免费领取超大流量手机卡，每月29元包185G流量+100分钟通话, 中国电信官方发货

抓取网页html源文件
<%@ Page language="C#" Trace="True" %>
<%@ Import Namespace="System.Net" %>
<%@ Import Namespace="System.IO" %><html>
<head>
<SCRIPT runat="server">
  void Page_Load(Object sender, EventArgs e) {    WebRequest req = WebRequest.Create("http://www.im286.com/index.php");
string urliii="src="; //图片使用绝对连接
urliii+="http://www.im286.com/";
    try {
        WebResponse result = req.GetResponse();
        Stream ReceiveStream = result.GetResponseStream();        Byte[] read = new Byte[512];
        int bytes = ReceiveStream.Read(read, 0, 512);        lblHTML.Text = "";
        while (bytes > 0)
        {          // 注意：
          // 下面假定响应使用 gb2312 作为编码方式。
          // 如果内容以 ANSI 代码页形式（例如，932）发送，则使用类似下面的语句：
          //Encoding encode = System.Text.Encoding.GetEncoding("shift-jis");
          Encoding encode = System.Text.Encoding.GetEncoding("gb2312");
          lblHTML.Text = lblHTML.Text + encode.GetString(read, 0, bytes);

          bytes = ReceiveStream.Read(read, 0, 512);

        }
    } catch(Exception) {
        lblHTML.Text = "检索页时出错";
    }
lblHTML.Text = lblHTML.Text.Replace("src=",""+urliii+"");
lblHTML.Text = lblHTML.Text.Replace("\"","");
  }
</SCRIPT>
</head><body>  <form method="post" action="Webrequest.aspx" runat="server">

    <asp:Label runat=server ID="lblHTML" Rows="30" Cols="80" EnableViewState="false"  Wrap="True"></asp:Label>
  </form></body>
</html>
这个是我抓Tom 2004 奥运金牌榜的代码
演示
http://www.aspxboy.com/jp/default.aspx<%@ Page language="C#"%>
<%@ Import Namespace="System.Net" %>
<%@ Import Namespace="System.IO" %>
<html>
<head>
<title> 2004奥运奖牌榜 </title>
<meta http-equiv="Content-Type" content="text/html; charset=gb2312" />
<meta name="title" content="" />
<meta name="author" content="活靶子,Huobazi,www.AspxBoy.com" />
<meta name="subject" content="" />
<meta name="language" content="gb2312" />
<meta name="keywords" content="" />
<meta name="Copyright" content="www.AspxBoy.com" />
<meta name="robots" content="all" />
<style type="text/css">

</style>
<SCRIPT runat="server">
  public string strDisply = "";
  public string GetContentFromUrl(string url)
{ string strResult = "";
System.Net.WebClient client=new WebClient();
byte[] page=client.DownloadData(url);
strResult=System.Text.Encoding.Default.GetString(page);
return strResult.Replace(Environment.NewLine,""); }
private string GetJpContent(string content)
{
string str="";
Regex re = new Regex(@"<table width=""98%"" border=""0"" cellspacing=""1"" cellpadding=""2"" align=""center"" bgcolor=""#0066A0"">(?<HtmlCode>.*?)<center><hr width=""750"" size=""1"" noshade>",RegexOptions.IgnoreCase | RegexOptions.Singleline);
foreach (Match m in re.Matches(content))
{
str = m.Groups["HtmlCode"].Value;

}
return str;
}
  public void Page_Load(Object sender, EventArgs e) {
string strHtml = GetContentFromUrl("http://2004.sports.tom.com/2004/ayjpb/index.html");
strDisply = GetJpContent(strHtml);
  }
</SCRIPT>
</head>
<body><div id="ss" align="center">
<H2><BR>
    <font color="#990000">2004奥运奖牌榜</font></H2>
<table width="80%" border="0">
<tr>
<td>
<%Response.Write(strDisply.Replace(".html",".aspx").Replace(".htm",".aspx"));%>
<td>
</tr>
</table>
</div></body>
</html>
找到了一个地址：
http://dotnet.aspx.cc/ShowDetail.aspx?id=0A6660CE-4138-41EF-B882-15DB65564709谢谢诸位。