Swift

Avoid URLs Matching Any of a Set of Patterns

See more Spider Examples

Demonstrates how to use "avoid patterns" to prevent spidering any URL that matches a wildcarded pattern. This example avoids URLs containing the substrings "java", "python", or "perl". Swift

func chilkatTest() {
    var success: Bool = false

    let spider = CkoSpider()!

    // The spider object crawls a single web site at a time.  As you'll see
    // in later examples, you can collect outbound links and use them to 
    // crawl the web.  For now, we'll simply spider 10 pages of chilkatsoft.com
    spider.initialize(domain: "www.chilkatsoft.com")

    // Add the 1st URL:
    spider.addUnspidered(url: "http://www.chilkatsoft.com/")

    // Avoid URLs matching these patterns:
    spider.addAvoidPattern(pattern: "*java*")
    spider.addAvoidPattern(pattern: "*python*")
    spider.addAvoidPattern(pattern: "*perl*")

    // Begin crawling the site by calling CrawlNext repeatedly.
    var i: Int
    for i = 0; i <= 9; i++ {

        success = spider.crawlNext()
        if success == true {
            // Show the URL of the page just spidered.
            print("\(spider.lastUrl!)")
            // The HTML is available in the LastHtml property
        }
        else {
            // Did we get an error or are there no more URLs to crawl?
            if spider.numUnspidered.intValue == 0 {
                print("No more URLs to spider")
            }
            else {
                print("\(spider.lastErrorText!)")
            }

        }

        // Sleep 1 second before spidering the next URL.
        spider.sleepMs(millisec: 1000)
    }


}