ASP.NET使用正则表达式抓取网页中的全部链接

添加如下命名空间
using System.Text.RegularExpressions;
using System.IO;
using System.Collections;
using System.Net;

关键代码：
(使用TextBox1获取网址，在TextBox2中显示该网页中的所有链接)

String web_url = this.TextBox1.Text.Trim();
//要获取的网址URL
String code = String.Empty;

//存放网页的源文件

HttpWebRequest request = (HttpWebRequest)WebRequest.Create(web_url);

WebResponse response = request.GetResponse();

StreamReader sr = new StreamReader(response.GetResponseStream());

//获取源文件

code = sr.ReadToEnd();

sr.Close();

ArrayList list = new ArrayList();

//用来存放链接

String reg = @" http://([\w-]+\.)+[\w-]+(/[\w- ./?%&=]*)?";

//链接的正则表达式

Regex regex = new Regex(reg, RegexOptions.IgnoreCase);

MatchCollection mc = regex.Matches(code);

//存放匹配的集合

for (int i = 0; i < mc.Count; i++)

     {

        bool hasExist = false;

        //链接存在与否的标记

        String name = mc[i].ToString();

        foreach (String one in list)

             {

                if (name == one)

                      {

                          hasExist = true;

                          //链接已存在

                          break;

                      }

            }

        //链接不存在，添加

        if (!hasExist) this.TextBox2.Text += name + "\n";

    }

转载于:https://www.cnblogs.com/jerrypen/archive/2011/09/22/2185666.html