$VAR1 = [ 'Status', 'Results', 'Schedule Start', 'Actual Start', 'Schedule Name', 'Node Name', 'Domain Name', ]; #### $VAR1 = [ 'á', 'Status', 'Results', 'Schedule Start', 'Actual Start', 'Schedule Name', 'Node Name', 'Domain Name', 'á', 'Node Name', 'Node Version', 'OS Platform', 'OS Version', 'Activity', 'Bytes Transferred' ]; #### use HTML::TreeBuilder; use Data::Dumper; use 5.16.0; my $h = HTML::TreeBuilder->new; $h->parse_content( do{ local $/; } ); my @headers = map @{ $_->content }, ($h->look_down ( _tag => 'td', class => qr/HeaderTitle\b?/ , ) ) ; print Dumper \@headers; __DATA__ TSM Operational Reporting
Daily Report TSM 24 hour Report for TSM2T generated at 2016-01-18 09:00:14 on NJ covering 2016-01-17 09:00:14 to 2016-01-18 09:00:13
Server name: TSM, platform: Linux/ppc64, version: 7.1.3.0, date/time: 01/18/2016 08:55:01

Client Schedules
  Status Results Schedule Start Actual Start Schedule Name Node Name Domain Name
Completed Successful 2016-01-17-17.00 2016-01-17-17.09 NJDLYBACKUP_5PM APX23 ST15_DOMAIN
Missed Successful 2016-01-17-17.00 2016-01-17-17.09 NJDLYBACKUP_5PM APX24 ST15_DOMAIN

Node Activity Summary
  Node Name Node Version OS Platform OS Version Activity Bytes Transferred
RDFXDB11 7.1.0.0 WinNT 6.01 BACKUP 105,806,011,655