正規表現道場@2ch

>>22

#!/usr/bin/perl

use strict;
use HTML::LinkExtor;

my $p = new HTML::LinkExtor;

$p->parse(<<HTML);

HTML

my %link_set;
foreach my $l ($p->links ) {
my ($tag, %link) = @$l;
next if $tag ne 'a';

++$link_set{$link{href}} if exists $link{href};
}

foreach my $link (sort keys %link_set) {
print $link, "\n";
}

__END__

> $pattern = '<A href="([^"]+)">';
> while ( $html =~ /$pattern/is )
>　$html =~ s/$pattern//is;

+o