提取网页中的超链接

using System;
using System.Xml;
using System.Text;
using System.Net;
using System.IO;
using System.Collections;
using System.Text.RegularExpressions;

public class App
{
public static void Main()
{
string strCode;
ArrayList alLinks;

Console.Write(“请输入一个网页地址：”);
string strURL = Console.ReadLine();
if(strURL.Substring(0,7) != @”http://”)
{
strURL = @”http://” + strURL;
}

Console.WriteLine(“正在获取页面代码，请稍侯…”);
strCode = GetPageSource(strURL);

Console.WriteLine(“正在提取超链接，请稍侯…”);
alLinks = GetHyperLinks(strCode);

Console.WriteLine(“正在写入文件，请稍侯…”);
WriteToXml(strURL,alLinks);
}

// 获取指定网页的HTML代码
static string GetPageSource(string URL)
{
Uri uri =new Uri(URL);

HttpWebRequest hwReq = (HttpWebRequest)WebRequest.Create(uri);
HttpWebResponse hwRes = (HttpWebResponse)hwReq.GetResponse();

hwReq.Method = “Get”;

hwReq.KeepAlive = false;

StreamReader reader = new StreamReader(hwRes.GetResponseStream(),System.Text.Encoding.GetEncoding(“GB2312”));

return reader.ReadToEnd();
}

// 提取HTML代码中的网址
static ArrayList GetHyperLinks(string htmlCode)
{
ArrayList al = new ArrayList();

string strRegex = @”http://([\w-]+\.)+[\w-]+(/[\w- ./?%&=]*)?”;

Regex r = new Regex(strRegex,RegexOptions.IgnoreCase);
MatchCollection m = r.Matches(htmlCode);

for(int i=0; i<=m.Count-1; i++)
{
bool rep = false;
string strNew = m[i].ToString();

// 过滤重复的URL
foreach(string str in al)
{
if(strNew==str)
{
rep =true;
break;
}
}

if(!rep) al.Add(strNew);
}

al.Sort();

return al;
}

// 把网址写入xml文件
static void WriteToXml(string strURL, ArrayList alHyperLinks)
{
XmlTextWriter writer = new XmlTextWriter(“HyperLinks.xml”,Encoding.UTF8);

writer.Formatting = Formatting.Indented;
writer.WriteStartDocument(false);
writer.WriteDocType(“HyperLinks”, null, “urls.dtd”, null);
writer.WriteComment(“提取自” + strURL + “的超链接”);
writer.WriteStartElement(“HyperLinks”);
writer.WriteStartElement(“HyperLinks”, null);
writer.WriteAttributeString(“DateTime”,DateTime.Now.ToString());

foreach(string str in alHyperLinks)
{
string title = GetDomain(str);
string body = str;
writer.WriteElementString(title,null,body);
}

writer.WriteEndElement();
writer.WriteEndElement();

writer.Flush();
writer.Close();
}

// 获取网址的域名后缀
static string GetDomain(string strURL)
{
string retVal;

string strRegex = @”(\.com/|\.net/|\.cn/|\.org/|\.gov/)”;

Regex r = new Regex(strRegex,RegexOptions.IgnoreCase);
Match m = r.Match(strURL);
retVal = m.ToString();

strRegex = @”\.|/$”;
retVal = Regex.Replace(retVal, strRegex, “”).ToString();

if(retVal == “”)
retVal = “other”;

return retVal;
}
}

本文来自CSDN博客，转载请标明出处：http://blog.csdn.net/21aspnet/archive/2007/03/24/1540012.aspx