web crawler / spider a website
I want to know , How to make web crawler / spider a website in asp.net ?
Know the answer? Post it — somebody with the same question will find it here.
Sign in to answer this question
It is the same account you read, post and publish with — and you will come straight back to this page.
Dipankar BiswasPosted Aug 18, 2014, 2:28 AM
Web spider code
public class WebSpider
{
const int LIMIT = 10;
string[] invalidTypes = { ".zip", ".doc", ".css", ".pdf", ".xls", ".txt", ".js", ".ico" };
public List Links;
public bool IsRunning { get; set; }
public WebSpider()
{
this.Links = new List();
}
public void Execute(string url)
{
this.Links.Clear();
this.Links.Add(new Link() { Status = HttpStatusCode.OK, NavigateUrl = url });
this.IsRunning = true;
WaitCallback item = delegate(object state) { this.FindLinks((UrlState)state); };
ThreadPool.QueueUserWorkItem(item, new UrlState() { Url = url, Level = 0 });
}
public void FindLinks(UrlState state)
{
try
{
string html = new WebClient().DownloadString(state.Url);
MatchCollection matches = Regex.Matches(html, "href[ ]*=[ ]*['|\"][^\"'\r\n]*['|\"]");
foreach (Match match in matches)
{
string value = match.Value;
value = Regex.Replace(value, "(href[ ]*=[ ]*')|(href[ ]*=[ ]*\")", string.Empty);
if (value.EndsWith("\"") || value.EndsWith("'"))
value = value.Remove(value.Length - 1, 1);
if (!Regex.Match(value, @"\((.*)\)").Success)
{
if (!value.Contains("http:"))
{
Uri baseUri = new Uri(state.Url);
Uri absoluteUri = new Uri(baseUri, value);
value = absoluteUri.ToString();
}
if (this.Links.Exists(x => x.NavigateUrl.Equals(value))) continue;
try
{
bool validLink = true;
foreach (string invalidType in invalidTypes)
{
string v = value.ToLower();
if (v.EndsWith(invalidType) || v.Contains(string.Format("{0}?", invalidType)))
{
validLink = false;
break;
}
}
if (validLink)
{
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(value);
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
this.Links.Add(new Link() { Status = response.StatusCode, NavigateUrl = value });
if (response.StatusCode == HttpStatusCode.OK && state.Level < LIMIT)
{
WaitCallback item = delegate(object s) { FindLinks((UrlState)s); };
ThreadPool.QueueUserWorkItem(
item, new UrlState() { Url = value, Level = state.Level + 1 });
}
}
}
catch
{
this.Links.Add(new Link()
{
Status = HttpStatusCode.ExpectationFailed,
NavigateUrl = value
});
}
}
}
}
catch
{
///
/// If downloading times out, just ignore...
///
}
}
}
public class Link : HyperLink
{
public HttpStatusCode Status { get; set; }
}
public class UrlState
{
public string Url { get; set; }
public int Level { get; set; }
public UrlState()
{
this.Level = 0;
this.Url = string.Empty;
}
}
Page code
public partial class Test : Page
{
private string script = @"setTimeout(""__doPostBack('{0}','')"", 5000);";
private WebSpider WebSpider
{
get { return (WebSpider)(Session["webSpider"] ?? (Session["webSpider"] = new WebSpider())); }
}
protected override void OnLoad(EventArgs e)
{
base.OnLoad(e);
if (!this.WebSpider.IsRunning)
{
string url = "http://www.charith.gunasekara.web-sphere.co.uk";
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url);
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
if (response.StatusCode == HttpStatusCode.OK)
this.WebSpider.Execute(url);
}
if (this.WebSpider.IsRunning)
{
this.lblStatus.Text = "Processing...";
ScriptManager.RegisterStartupScript(this, this.GetType(),
this.GetType().Name, string.Format(script, this.btnUpdateResults.ClientID), true);
}
this.grvLinks.DataSource = this.WebSpider.Links;
this.grvLinks.DataBind();
}
}
Markup
Listing all the links for site: http://www.charith.gunasekara.web-sphere.co.uk
Width the maximum depth of 10
Riddhi ValechaPosted Aug 18, 2014, 6:53 AM
I tried this code in VS2010 web application.
But, it did not work.
Can you please share the working code if you have??
Waqeeh Ul HasanPosted Aug 18, 2014, 6:22 AM