use strict;
my $str = '<EightSquaredSchema xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:xdt="http://www.w3.org/2005/xpath-datatypes" xmlns:fn="http://www.w3.org/2005/xpath-functions">
<A>
<nested-A>valid text</nested-A>
Remove text not inside valid xml braces
<nested-B>more valid text here</nested-B>
</A>
</EightSquaredSchema>
';
my $regex = qr/<(.+?)>[^<]+<\/\1>/mp;
if ( $str =~ /$regex/g ) {
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