(VB.NET) A Simple Web Crawler

This demonstrates a very simple web crawler using the Chilkat Spider component.

Chilkat .NET Downloads Chilkat .NET Framework Chilkat for .NET Core

Dim spider As New Chilkat.Spider

Dim seenDomains As New Chilkat.StringArray
Dim seedUrls As New Chilkat.StringArray

seenDomains.Unique = True
seedUrls.Unique = True

' You will need to change the start URL to something else...
seedUrls.Append("http://something.whateverYouWant.com/")

' Set outbound URL exclude patterns
' URLs matching any of these patterns will not be added to the 
' collection of outbound links.
spider.AddAvoidOutboundLinkPattern("*?id=*")
spider.AddAvoidOutboundLinkPattern("*.mypages.*")
spider.AddAvoidOutboundLinkPattern("*.personal.*")
spider.AddAvoidOutboundLinkPattern("*.comcast.*")
spider.AddAvoidOutboundLinkPattern("*.aol.*")
spider.AddAvoidOutboundLinkPattern("*~*")

' Use a cache so we don't have to re-fetch URLs previously fetched.
spider.CacheDir = "c:/spiderCache/"
spider.FetchFromCache = True
spider.UpdateCache = True

While seedUrls.Count > 0

    Dim url As String = seedUrls.Pop()
    spider.Initialize(url)

    ' Spider 5 URLs of this domain.
    ' but first, save the base domain in seenDomains
    Dim domain As String = spider.GetUrlDomain(url)
    seenDomains.Append(spider.GetBaseDomain(domain))

    Dim i As Integer
    Dim success As Boolean
    For i = 0 To 4
        success = spider.CrawlNext()
        If (success = True) Then

            ' Display the URL we just crawled.
            Debug.WriteLine(spider.LastUrl)

            ' If the last URL was retrieved from cache,
            ' we won't wait.  Otherwise we'll wait 1 second
            ' before fetching the next URL.
            If (spider.LastFromCache <> True) Then
                spider.SleepMs(1000)
            End If


        Else
            ' cause the loop to exit..
            i = 999
        End If


    Next

    ' Add the outbound links to seedUrls, except
    ' for the domains we've already seen.
    For i = 0 To spider.NumOutboundLinks - 1

        url = spider.GetOutboundLink(i)
        Dim domain As String = spider.GetUrlDomain(url)
        Dim baseDomain As String = spider.GetBaseDomain(domain)
        If (seenDomains.Contains(baseDomain) = False) Then
            ' Don't let our list of seedUrls grow too large.
            If (seedUrls.Count < 1000) Then
                seedUrls.Append(url)
            End If

        End If


    Next

End While