use strict;
my $str = '<!DOCTYPE html>
<html>
<head>
<title>Hyperlinks</title>
<link href="theme.css" rel="stylesheet" />
</head>
<body>
<ul><li><a href="/" id="home">Home</a></li><li><a
class="selected" href="/courses">Courses</a>
</li><li><a href =
\'/forum\' >Forum</a></li><li><a class="href"
onclick="go()" href= "#">Forum</a></li>
<li><a id="js" href =
"javascript:alert(\'hi yo\')" class="new">click</a></li>
<li><a id=\'nakov\' href =
http://www.nakov.com class=\'new\'>nak</a></li></ul>
a href="#empty"></a>
<a id="href">href=\'fake\'<img src=\'http://abv.bg/i.gif\'
alt=\'abv\'/></a><a href="#"><a href=\'hello\'></a>
<!-- This code is commented:
<a href="#commented">commentex hyperlink</a> -->
</body>
';
my $regex = qr/(?<=<a)(.+)\s?href\s*=\s*("|')(.+?)(\2)/sp;
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