下列的函数分别用于获取HTML页面和提取页面中的超链接。
using System.Net;
using System.IO;
using System.Text;
using System.Text.RegularExpressions;
string[] GetLink(string strHtml)
{
string RegexStr = "(?<=href[//s//r]*=[//s//r]*[/"/'])([^/"/'//s//r>]*)(?<=[/"/'//s//r]{0,1})";
Regex reg = new Regex(RegexStr, RegexOptions.IgnoreCase);
MatchCollection mc = reg.Matches(strHtml);
if (mc.Count > 0)
{
string[] strHref = new string[mc.Count];
int i = 0;
foreach (Match m in mc)
{
strHref[i] = m.Groups[1].Value;
++i;
}
return strHref;
}
return null;
}
string GetHttp(string strUrl)
{
string strHtml = "";
WebResponse wrp = null;
try
{
WebRequest wrq = WebRequest.Create(strUrl);
wrq.Timeout = 60000;
wrp = wrq.GetResponse();
}
catch (WebException e)
{
}
catch (Exception e)
{
}
finally
{
if (wrp != null)
{
StreamReader sr = new StreamReader(wrp.GetResponseStream(), Encoding.GetEncoding("GB2312"));
strHtml = sr.ReadToEnd();
sr.Close();
wrp.Close();
}
}
return strHtml;
}
可首先使用GetHttp获取指定URL的页面内容,然后将此内容作为参数传给GetLink,GetLink返回的String数组中的每个元素代表一个超链接。