use strict;
my $str = '该网站共有 <b style="color:#333">1,647</b></b>
个网页被百度收录 </span>
<a class="c-gap-left" href="http://www.baidu.com/link?url=VJVYQ4ICi27sRCzv-qcP6aqwAFaTejX2cxgqpybZ5hSywsOxqZlnjP29Y930JNV8EHBPc4O7XPBnOOsZTAJRCK" target="_blank">到站长平台分析收录量>></a>
</p>';
my $regex = qr/该网站共有\s*<b[^>]*>([^<]*)<\/b>/p;
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