use strict;
my $str = ' <div>
<span class="ljuser i-ljuser i-ljuser-type-P " data-ljuser="canonf" lj:user="canonf" ><a href="http://canonf.livejournal.com/profile" target="_self" class="i-ljuser-profile" ><img class="i-ljuser-userhead" src="http://l-stat.livejournal.net/img/userinfo.gif?v=17080?v=134.3" /></a><a href="http://canonf.livejournal.com/" class="i-ljuser-username" target="_self" ><b>canonf</b></a></span> — Растоптать от души.
</div>
<div>
<span class="ljuser i-ljuser i-ljuser-type-I " data-ljuser="ext_2056646" lj:user="ext_2056646" ><a href="http://www.livejournal.com/profile?userid=65329483&t=I" target="_self" class="i-ljuser-profile" ><img class="i-ljuser-userhead" src="http://l-stat.livejournal.net/img/icons/facebook-16.png?v=29916?v=134.3" /></a><a href="http://www.facebook.com/profile.php?id=100001197014517" class="i-ljuser-username" target="_self" ><b>Летающий Котёнок</b></a></span> — Растоптать от души.
</div>';
my $regex = qr/^\s+<span.+lj:user="
([-\w]{1,15})
".+<b>
([-\w\s]+)
<\/b>.+ —\s
([-\.\w\s]+)
<\/div>$/xmup;
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