Tcl

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". Tcl

load ./chilkat.dll

set success 0

set spider [new_CkSpider]

# 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
CkSpider_Initialize $spider "www.chilkatsoft.com"

# Add the 1st URL:
CkSpider_AddUnspidered $spider "http://www.chilkatsoft.com/"

# Avoid URLs matching these patterns:
CkSpider_AddAvoidPattern $spider "*java*"
CkSpider_AddAvoidPattern $spider "*python*"
CkSpider_AddAvoidPattern $spider "*perl*"

# Begin crawling the site by calling CrawlNext repeatedly.

for {set i 0} {$i <= 9} {incr i} {

    set success [CkSpider_CrawlNext $spider]
    if {$success == 1} then {
        # Show the URL of the page just spidered.
        puts [CkSpider_lastUrl $spider]
        # The HTML is available in the LastHtml property
    }     else {
        # Did we get an error or are there no more URLs to crawl?
        if {[CkSpider_get_NumUnspidered $spider] == 0} then {
            puts "No more URLs to spider"
        }         else {
            puts [CkSpider_lastErrorText $spider]
        }

    }

    # Sleep 1 second before spidering the next URL.
    CkSpider_SleepMs $spider 1000
}

delete_CkSpider $spider