C#获取远程网页中的所有链接URL（网络蜘蛛实现原理）

</pre></p><span style="line-height: 21px;"></span><pre name="code" class="csharp">using System;
using System.Net;
using System.Text;
using System.Text.RegularExpressions;
namespace HttpGet
{
class Class1
{
[STAThread]
static void Main(string[] args)
{
System.Net.WebClient client = new WebClient();
byte[] page = client.DownloadData("http://news.163.com");
string content = System.Text.Encoding.UTF8.GetString(page);
string regex = "href=[\\\"\\\'](http:\\/\\/|\\.\\/|\\/)?\\w+(\\.\\w+)*(\\/\\w+(\\.\\w+)?)*(\\/|\\?\\w*=\\w*(&\\w*=\\w*)*)?[\\\"\\\']";
Regex re = new Regex(regex);
MatchCollection matches = re.Matches(content);
System.Collections.IEnumerator enu = matches.GetEnumerator();
while (enu.MoveNext() && enu.Current != null)
{
Match match = (Match)(enu.Current);
Console.Write(match.Value + "\r\n");
}
}
}
}

.csharpcode, .csharpcode pre
{
font-size: small;
color: black;
font-family: consolas, "Courier New", courier, monospace;
background-color: #ffffff;
/*white-space: pre;*/
}
.csharpcode pre { margin: 0em; }
.csharpcode .rem { color: #008000; }
.csharpcode .kwrd { color: #0000ff; }
.csharpcode .str { color: #006080; }
.csharpcode .op { color: #0000c0; }
.csharpcode .preproc { color: #cc6633; }
.csharpcode .asp { background-color: #ffff00; }
.csharpcode .html { color: #800000; }
.csharpcode .attr { color: #ff0000; }
.csharpcode .alt
{
background-color: #f4f4f4;
width: 100%;
margin: 0em;
}
.csharpcode .lnum { color: #606060; }