.NET2.0抓取网页全部链接【月儿原创】
.NET2.0抓取網(wǎng)頁(yè)全部鏈接
作者：清清月兒
主頁(yè)：http://blog.csdn.net/21aspnet/?????????? 時(shí)間：2007.4.18?
該方法經(jīng)過(guò)對(duì)各大門戶網(wǎng)站測(cè)試結(jié)果是抓取率100%！
效果圖
后臺(tái)代碼：
using System;
using System.Data;
using System.Configuration;
using System.Web;
using System.Web.Security;
using System.Web.UI;
using System.Web.UI.WebControls;
using System.Web.UI.WebControls.WebParts;
using System.Web.UI.HtmlControls;
using System.Text.RegularExpressions;
using System.Net;
using System.IO;
using System.Collections;
public partial class _Default : System.Web.UI.Page
{
??? protected void Page_Load(object sender, EventArgs e)
??? {
??????? if (!IsPostBack)
??????? {
???????????
??????? }
???????
??? }
??? protected void Button1_Click(object sender, EventArgs e)
??? {
??????? 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;
??????????????? }
??????????? }//過(guò)濾
??????????? if (!_foo)
??????????? {
??????????????? TextBox2.Text += name + "/n";
??????????? }
??????? }
??? }
}
前臺(tái)
<%@ 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>抓取網(wǎng)頁(yè)所有鏈接</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>
總結(jié)
以上是生活随笔為你收集整理的.NET2.0抓取网页全部链接【月儿原创】的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。
- 上一篇： 一斤海参多少钱啊？
- 下一篇： ASP.NET2.0图片格式转换【月儿原