A Simple Web Crawler

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

Download Chilkat Spider ActiveX

'  The Chilkat Spider component/library is free.
Dim spider As New Spider

Dim seenDomains As New CkStringArray
Dim seedUrls As New CkStringArray

seenDomains.Unique = 1
seedUrls.Unique = 1

seedUrls.Append "http://directory.google.com/Top/Recreation/Outdoors/Hiking/Backpacking/"

'  Set our outbound URL exclude patterns
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 = 1
spider.UpdateCache = 1

Do While seedUrls.Count > 0

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

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

    Dim i As Long
    Dim success As Long
    For i = 0 To 4
        success = spider.CrawlNext()
        If (success <> 1) Then
            Exit For
        End If

        '  Display the URL we just crawled.
        Text1.Text = Text1.Text & spider.LastUrl & vbCrLf

        '  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 <> 1) Then
            spider.SleepMs 1000
        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)

        domain = spider.GetDomain(url)
        Dim baseDomain As String
        baseDomain = spider.GetBaseDomain(domain)
        If (Not seenDomains.Contains(baseDomain)) Then
            seedUrls.Append url
        End If

        '  Don't let our list of seedUrls grow too large.
        If (seedUrls.Count > 1000) Then
            Exit For
        End If

    Next

Loop