Go

A Simple Web Crawler

See more Spider Examples

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

    success := false

    spider := chilkat.NewSpider()

    seenDomains := chilkat.NewStringArray()
    seedUrls := chilkat.NewStringArray()

    seenDomains.SetUnique(true)
    seedUrls.SetUnique(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.SetCacheDir("c:/spiderCache/")
    spider.SetFetchFromCache(true)
    spider.SetUpdateCache(true)

    for seedUrls.Count() > 0 {

        url := seedUrls.Pop()
        spider.Initialize(*url)

        // Spider 5 URLs of this domain.
        // but first, save the base domain in seenDomains
        domain := spider.GetUrlDomain(*url)
        seenDomains.Append(*spider.GetBaseDomain(*domain))

        var i int

        for i = 0; i <= 4; i++ {
            success = spider.CrawlNext()
            if success == true {

                // Display the URL we just crawled.
                fmt.Println(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 {
                    spider.SleepMs(1000)
                }

            } else {
                // cause the loop to exit..
                i = 999
            }

        }

        // Add the outbound links to seedUrls, except
        // for the domains we've already seen.
        for i = 0; i <= spider.NumOutboundLinks() - 1; i++ {

            url = spider.GetOutboundLink(i)
            domain := spider.GetUrlDomain(*url)
            baseDomain := spider.GetBaseDomain(*domain)
            if seenDomains.Contains(*baseDomain) == false {
                // Don't let our list of seedUrls grow too large.
                if seedUrls.Count() < 1000 {
                    seedUrls.Append(*url)
                }

            }

        }

    }


    spider.DisposeSpider()
    seenDomains.DisposeStringArray()
    seedUrls.DisposeStringArray()