Friday, September 4, 2015

Remove Duplicate URLs domain from Text or List

clear list(%urlOut)
clear list(%domain)
set(#urls,"http://www.talentigniter.com/educational-and-school-options-gifted-child
http://www.talentigniter.com/gifted-emotional-and-social-needs
http://www.talentigniter.com/how-do-i-ignite-and-encourage-my-childs-gifts-and-talents
http://www.enumclawchamber.com/blog/post/enumclaw-events-2013 
http://www.ubotstudio.com/forum/
http://www.ubotstudio.com/forum/235","Global")
add list to list(%domain,$find regular expression(#urls,".*\\://(?:www.)?([^\\/]+)"),"Delete","Global")
loop($list total(%domain)) {
    set(#nowDomain,$next list item(%domain),"Global")
    clear list(%temp)
    set(#nowDomain,$plugin function("Advanced Connection.dll""$url info"#nowDomain"Host"),"Global")
    add list to list(%temp,$find regular expression(#urls,"{$replace(#nowDomain,".","\\.")}.*"),"Delete","Global")
    add item to list(%urlOut,$list item(%temp,0),"Don\'t Delete","Global")
}
load html($replace(%urlOut,$new line,"<br>"))

No comments:

Post a Comment