.NET2.0抓取网页全部链接
点击次数:68 次 发布日期:2008-11-06 07:56:05 作者:源代码网
|
源代码网整理以下效果图 源代码网整理以下 软件开发网 www.mscto.com 源代码网整理以下后台代码 TextBox2.Text = ""; string web_url = this.TextBox1.Text;//"http://blog.csdn.net/21aspnet/" string all_code = ""; HttpWebRequest all_codeRequest = (HttpWebRequest)WebRequest.Create(web_url); WebResponse all_codeResponse = all_codeRequest.GetResponse(); StreamReader the_Reader = new StreamReader(all_codeResponse.GetResponseStream()); all_code = the_Reader.ReadToEnd(); the_Reader.Close(); ArrayList my_list = new ArrayList(); string p = @"http://([w-]+.)+[w-]+(/[w- ./?%&=]*)?"; Regex re = new Regex(p, RegexOptions.IgnoreCase); MatchCollection mc = re.Matches(all_code); for (int i = 0; i <= mc.Count - 1; i++) { bool _foo = false; string name = mc[i].ToString(); foreach (string list in my_list) { if (name == list) { _foo = true; break; } }//过滤 if (!_foo) { TextBox2.Text += name + " "; } } } } 前台 以下为引用的内容: <%@ Page Language="C#" AutoEventWireup="true" CodeFile="Default.aspx.cs" Inherits="_Default" %> <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> <html xmlns="http://www.w3.org/1999/xhtml" > <head runat="server"> <title>抓取网页所有链接</title> </head> <body > <form id="form1" runat="server"> <div> <asp:TextBox ID="TextBox1" runat="server" Width="481px"></asp:TextBox> <asp:Button ID="Button1" runat="server" OnClick="Button1_Click" Text="提取" /> <br /> <asp:TextBox ID="TextBox2" runat="server" Height="304px" TextMode="MultiLine" Width="524px"></asp:TextBox></div> </form> </body> </html> 源代码网推荐 源代码网供稿. |
