Here is the code with the above suggestions applied.
#!/usr/bin/perl use strict; use warnings; use LWP::UserAgent; use HTML::LinkExtor; use URI::URL; my $site = shift @ARGV; # Why not just take an uri as argument? my $domain = shift @ARGV; # Should really be an uri. # Assume it's a HTTP server if not. if ($site !~ /^\w+:/) { $site = "http://site"; } my $first_uri = URI->new($site)->canonical; my @to_visit = ( $first_uri ); my %seen = map { $_ => 1 } @to_visit; my $ua = LWP::UserAgent->new(); while (@to_visit) { my $uri = shift(@to_visit); # Make the parser my $p = HTML::LinkExtor->new(sub { my ($tag, %attr) = @_; # Only interested in A elements. return if $tag ne 'a'; # Only interested in the HREF attribute. return if not exists $attr{href}; my $link_uri = URI->new_abs($attr{href}, $uri)->canonical; # Ignore links outside of the domain. return if $link_uri->rel($first_uri) eq $link_uri; # Ignore links already in the queue and links already visited. return if $seen{$link_uri}++; push @to_visit, $link_uri; }); my $response = $ua->request( HTTP::Request->new(GET => $uri), sub { $p->parse($_[0]) } ); $p->eof; } my @links = keys %seen;
You should use LWP::RobotUA instead of LWP::UserAgent for this kind of application.
Untested.
Updated: The call to request was accidently removed! oops. Readded. Added $p->eof.
In reply to Re^2: Newbie memory leak
by ikegami
in thread Newbie memory leak
by memwaster
| For: | Use: | ||
| & | & | ||
| < | < | ||
| > | > | ||
| [ | [ | ||
| ] | ] |