B4X

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". B4X

Dim success As Boolean = False

Dim spider As ChilkatSpider
spider.Initialize("spider")

'  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.InitializeSpider("www.chilkatsoft.com")

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

'  Avoid URLs matching these patterns:
spider.AddAvoidPattern("*java*")
spider.AddAvoidPattern("*python*")
spider.AddAvoidPattern("*perl*")

'  Begin crawling the site by calling CrawlNext repeatedly.
Dim i As Int
For i = 0 To 9

    success = spider.CrawlNext
    If success = True Then
        '  Show the URL of the page just spidered.
        Log(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 = 0 Then
            Log("No more URLs to spider")
        Else
            Log(spider.LastErrorText)
        End If

    End If

    '  Sleep 1 second before spidering the next URL.
    spider.SleepMs(1000)
Next