m/]* # an anchor tag href= # the Href in the anchor (["'])((?:(?!\1).)*)\1 # the value in the href [^>]*> # anything to the end of the anchor [^<>]* # the content in the anchor tag <\/a> # the end of the anchor (?:\s|<[^>]*>)+ # any whitespace or html tags (\d{9}) # the 9 digit number /isxm; my $href = $2; my $number = $3; ##

##

my $re = qr/]*                   # an anchor tag
  href=                     # the Href in the anchor
  (["'])((?:(?!\1).)*)\1    # the value in the href
  [^>]*>                    # anything to the end of the anchor
  [^<>]*                    # the content in the anchor tag
  <\/a>                     # the end of the anchor
  (?:\s|<[^>]*>)+           # any whitespace or html tags
  (\d{9})                   # the 9 digit number
 /isxm;

my $string = do{local $/; };
 
while($string =~ m/$re/g){
	my $href = $2;
	my $number = $3;
	print "$number - $href\n";
}

__DATA__
            
            A
            
               
                  
                     
                        
                           Abbott, Evelyn
110136892
Agnew, Thomas
110377660

                           Allison, David
108116112
Allison, Gary Owen
116815754

                           Arsenault, Michael
108318866
Arsenault, Normand A.
113069066

                        
                     
                  
               
            



##

##

110136892 - pdf\c76b834e-36e1-497b-b13e-eba2348dc04
+4.pdf
110377660 - pdf\8a956f66-1c60-48fc-905c-b49d617aa6c5.pdf
108116112 - pdf\37d3e78b-1adb-458b-9e89-0df78
+0909f08.pdf
116815754 - pdf\6c0a5bb4-143d-4305-957b-796c8193d07a.pdf
108318866 - pdf\ae8d51e0-005b-44be-84cb-3c9b5733575
+5.pdf
113069066 - pdf\e646f948-f78d-4463-a01d-0261aebf70dc.pdf