use strict;
my $str = '<div>
<div class="asd">
<div>
<div>
Hello
</div>
</div>
</div>
</div>';
my $regex = qr%<div\s+class="asd"> # match an opening 'div' with an id that starts with 't' and some digits
[^<>]* # match zero or more chars other than '<' and '>'
( # open group 1
<div[^>]*> # match an opening 'div'
(?: # open a non-matching group
[^<>]* # match zero or more chars other than '<' and '>'
| # OR
(?1) # recursively match what is defined by group 1
)* # close the non-matching group and repeat it zero or more times
</div> # match a closing 'div'
) # close group 1
[^<>]* # match zero or more chars other than '<' and '>'
</div> %msixp;
if ( $str =~ /$regex/ ) {
print "Whole match is ${^MATCH} and its start/end positions can be obtained via \$-[0] and \$+[0]\n";
# print "Capture Group 1 is $1 and its start/end positions can be obtained via \$-[1] and \$+[1]\n";
# print "Capture Group 2 is $2 ... and so on\n";
}
# ${^POSTMATCH} and ${^PREMATCH} are also available with the use of '/p'
# Named capture groups can be called via $+{name}
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Perl, please visit: http://perldoc.perl.org/perlre.html