Swift

A Simple Web Crawler

See more Spider Examples

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

func chilkatTest() {
    var success: Bool = false

    let spider = CkoSpider()!

    let seenDomains = CkoStringArray()!
    let seedUrls = CkoStringArray()!

    seenDomains.unique = true
    seedUrls.unique = true

    // You will need to change the start URL to something else...
    seedUrls.append(str: "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(pattern: "*?id=*")
    spider.addAvoidOutboundLinkPattern(pattern: "*.mypages.*")
    spider.addAvoidOutboundLinkPattern(pattern: "*.personal.*")
    spider.addAvoidOutboundLinkPattern(pattern: "*.comcast.*")
    spider.addAvoidOutboundLinkPattern(pattern: "*.aol.*")
    spider.addAvoidOutboundLinkPattern(pattern: "*~*")

    // 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.intValue > 0 {

        var url: String? = seedUrls.pop()
        spider.initialize(domain: url)

        // Spider 5 URLs of this domain.
        // but first, save the base domain in seenDomains
        var domain: String? = spider.getUrlDomain(url: url)
        seenDomains.append(str: spider.getBaseDomain(domain: domain))

        var i: Int

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

                // Display the URL we just crawled.
                print("\(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(millisec: 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.intValue - 1; i++ {

            url = spider.getOutboundLink(index: i)
            var domain: String? = spider.getUrlDomain(url: url)
            var baseDomain: String? = spider.getBaseDomain(domain: domain)
            if seenDomains.contains(str: baseDomain) == false {
                // Don't let our list of seedUrls grow too large.
                if seedUrls.count.intValue < 1000 {
                    seedUrls.append(str: url)
                }

            }

        }

    }


}