Extract a hyperlink from a Web page (C #)

Links | web 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 ("Please enter a Web address:");
String strurl = Console.ReadLine ();
if (strurl.substring (0,7)!= @ "http://")
{
strURL = @ "http://" + strurl;
}

Console.WriteLine ("Getting the page code, please wait ...");
Strcode = Getpagesource (strURL);

Console.WriteLine ("Fetching hyperlinks, please wait ...");
Allinks = Gethyperlinks (Strcode);

Console.WriteLine ("Writing file, please wait ...");
Writetoxml (strurl,allinks);
}

Gets the HTML code for the specified Web page
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 ();
}

Extract URLs from HTML code
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 ();

Filter for duplicate URLs
foreach (String str in AL)
{
if (STRNEW==STR)
{
Rep =true;
Break
}
}

if (!rep) al. ADD (strnew);
}

Al. Sort ();

Return al;
}

Write URLs to XML files
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 ("Extract from" + strURL + "HYPERLINK");
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 ();
}

Get the domain name suffix of the URL
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;
}
}