Extract Links from a HTML page

   1: <cfhttp

   2:     url    = "http://www.google.com/search?hl=en&q=paris+hilton&aq=f&oq="

   3:     userAgent = "#cgi.HTTP_USER_AGENT#">   4: </cfhttp>    5: <cfdump var="#getlinks(CFHTTP.FileContent)#">    6: <cffunction name="getLinks" access="public" returntype="array" output="yes" hint="seperate Links from given HTML string, output as a array">   7:  <cfargument name="html"    hint="HTML String with links"    required="yes">   8:     <cfset local.startpos = 1>   9:     <cfset local.list = ArrayNew(1)>  10:       11:     <cfloop condition="local.startpos GREATER THAN 0">  12:      <cfset local.linkpos = reFindNoCase('<a\b[^>]*>(.*?)</a>',arguments.html,local.startpos,'true')>  13:    14:         <cfif val(local.linkpos.len[1])>  15:     <cfset local.startpos = local.linkpos.len[1]+local.linkpos.pos[1]>  16:     <cfset local.string = mid(arguments.html,local.linkpos.pos[1],local.linkpos.len[1])>  17:             <cfset local.hrefpos = reFindNoCase('(http|ftp|https):\/\/[\w\-_]+(\.[\w\-_]+)+([\w\-\.,@?^=%&:/~\+##]*[\w\-\@?^=%&/~\+##])?',local.string,1,'true')>  18:     <cfif val(local.hrefpos.pos[1])>  19:                 <cfset local.this.a = mid(local.string,local.hrefpos.pos[1],local.hrefpos.len[1])>                  20:                 <cfset local.this.title = reReplacenocase(local.string,'<a\b[^>]*.>',"")>  21:                 <cfset local.this.title = reReplacenocase(local.this.title,'</a*>',"")>  22:                 <cfset ArrayAppend(local.list,local.this)>  23:                 <cfset StructDelete(local,'this')>  24:             </cfif>  25:  <cfelse>  26:          <cfbreak>  27:  </cfif>  28:     </cfloop>  29:       30:  <cfreturn local.list>  31: </cffunction>