{ local $/; # slurpmode my $html = ; my @link = grep {$_ =~ /^[RT]\d+$/} $html =~ m~]+>([^<>]+)~ig; print "$_\n" for @link; } _ _ D A T A _ _ BS     -202   -135   R00929; HS$IFNB_14. BS     -167    -94   R00916; HS$IFNB_01; Binding factors: R2 T00712. BS     -100    -61   R00917; HS$IFNB_02; Binding factors: IRF1 T00422, IRF-2 BS     T00425.