linkextract.aspx.cs

Web application for link extract used in seo

using System;
using System.Data;
using System.Configuration;
using System.Collections;
using System.Web;
using System.Web.Security;
using System.Web.UI;
using System.Web.UI.WebControls;
using System.Web.UI.WebControls.WebParts;
using System.Web.UI.HtmlControls;
using System.Collections.Generic;
using System.Net;
using System.Text;
using System.IO;
public partial class LinkExtract : System.Web.UI.Page
{
    protected void Page_Load(object sender, EventArgs e)
    {
    }
    protected void btnExtract_click(object sender, EventArgs e)
    {
        string rawCode = DownloadData(txtURL.Text);
        List<string> links=ExtractLinks(rawCode);

        int count = 0;
        txtLinks.Items.Clear();
        foreach (string link in links)
        {
            //txtLinks.Text += link + Environment.NewLine;
            txtLinks.Items.Add(link.ToString());
            count++;
        }
        //Show how many links there are
        lCount.Text = count.ToString() + " Link(s) Found";
    }

    private List<string> ExtractLinks(string rawCode)
    {
        List<string> links = new List<string>();
        string startSquence = "<a href=\"";
        string endSequence = "\"";

        rawCode = rawCode.ToLower();

        while (rawCode.IndexOf("<a href") != -1)
        {
            int start = rawCode.IndexOf(startSquence) + startSquence.Length;
            int end = rawCode.IndexOf(endSequence, start);

            //Extract the link, and add it to the list
            if (end > start)
            {
                string link = rawCode.Substring(start, end - start);

                if (link != string.Empty)
                {
                    if (!link.StartsWith("http://"))
                    {
                        //It's a relative link, add a ..
                        link = "../" + link;
                    }

                    links.Add(link);

                }
            }

            //Trim the raw data
            rawCode = rawCode.Substring(end + endSequence.Length);
        }

        return links;
    }


    private string DownloadData(string url)
    {
        byte[] downloadedData = new byte[0];
        try
        {
            //Get a data stream from the url
            WebRequest req = WebRequest.Create(url);
            WebResponse response = req.GetResponse();
            Stream stream = response.GetResponseStream();

            //Download in chuncks
            byte[] buffer = new byte[1024];

            //Get Total Size
            int dataLength = (int)response.ContentLength;

            //Download to memory
            MemoryStream memStream = new MemoryStream();
            while (true)
            {
                //Try to read the data
                int bytesRead = stream.Read(buffer, 0, buffer.Length);

                //Avoid application freezing
                //Application.DoEvents();

                if (bytesRead == 0)
                {
                    //Finished downloading                       
                    break;
                }
                else
                {
                    //Write the downloaded data
                    memStream.Write(buffer, 0, bytesRead);
                }
            }

            //Convert the downloaded stream to a byte array
            downloadedData = memStream.ToArray();

            //Clean up
            stream.Close();
            memStream.Close();
        }
        catch (Exception)
        {
            //May not be connected to the internet
            //Or the URL might not exist
            //txtLinks.Items.Clear();
            Response.Write("There was an error accessing the URL.");
        }

        //Convert the data into string
        return ASCIIEncoding.ASCII.GetString(downloadedData);
    }
    protected void txtLinks_SelectedIndexChanged(object sender, EventArgs e)
    {

    }
}