use strict;
my $str = '<table width="100%" cellspacing="0" cellpadding="4"><colgroup> <col width="85*" /> <col width="85*" /> <col width="85*" /> </colgroup>
<thead>
<tr valign="TOP">
<th width="33%">Th1</th>
<th width="33%">Th2</th>
<th width="33%">Th3</th>
</tr>
</thead>
<tbody>
<tr valign="TOP">
<td width="33%">C1</td>
<td width="33%">C2</td>
<td width="33%">C3</td>
</tr>
<tr valign="TOP">
<td width="33%">C4</td>
<td width="33%">C5</td>
<td width="33%">C6</td>
</tr>
<tr valign="TOP">
<td width="33%">C7</td>
<td width="33%">C8</td>
<td width="33%">C9</td>
</tr>
</tbody>
</table>
<h2>Title</h2>
<table width="100%" cellspacing="0" cellpadding="4"><colgroup> <col width="85*" /> <col width="85*" /> <col width="85*" /> </colgroup>
<thead>
<tr valign="TOP">
<th width="33%">Th1</th>
<th width="33%">Th2</th>
<th width="33%">Th3</th>
</tr>
</thead>
<tbody>
<tr valign="TOP">
<td width="33%">C1</td>
<td width="33%">C2</td>
<td width="33%">C3</td>
</tr>
<tr valign="TOP">
<td width="33%">C4</td>
<td width="33%">C5</td>
<td width="33%">C6</td>
</tr>
<tr valign="TOP">
<td width="33%">C7</td>
<td width="33%">C8</td>
<td width="33%">C9</td>
</tr>
</tbody>
</table>';
my $regex = qr/<table.*?>(([\s*].*(\s*))+)?<\/table>/p;
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