use strict;
my $str = '<div> <br> <a data-some-id="3-6-9;id-1-2-3" data-more-id="1-3-5" data-extra-url="https://somehost.api/sub-id-1-2-3?someparam=3-6-9;id-1-2-3" href="https://somehost.api/sub-id-1-2-3?someparam=3-6-9;id-1-2-3" class="some-class">someDuplicateHere1</a></div> wysiwyg<br> <div><a class="popup-wrap-id-1-2-3" href="https://somehost.api/app/id-1-2-3?someparam=sub-id-1-2-3;sub-sub-id-1-2-3">firstImage</a></div> <br> <div>somecontent</div> <div> <span> <div><a data-some-id="456;789" href="https://somehost.api/app/id-4-5-6?someparam=sub-id-4-5-6;sub-sub-1-2-3">second</a></div> <br> </span> also some more content </div> <div> <span> <div><a data-some-id="3-6-9;id-1-2-3" data-more-id="1-3-5" data-extra-url="https://somehost.api/app/sub-id-1-2-3?someparam=3-6-9;id-1-2-3" href="https://somehost.api/app/sub-id-1-2-3?someparam=3-6-9;id-1-2-3" class="some-class">someDuplicateHere</a></div> rtf<br> </span> <br> </div> </div>';
my $regex = qr/<a.*?data-extra-url=".*?<\/a>/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