#!/usr/bin/perl -w
use strict;
$|++;

### CONFIG

# the CPAN url to fetch
my $REMOTE = "http://www.cpan.org/";
# my $REMOTE = "file://Users/merlyn/MIRROR/CPAN/";
# my $REMOTE = "http://fi.cpan.org/";
# my $REMOTE = "http://au.cpan.org/";

# the path to the local mirror
# warning: unknown files below this dir are deleted!
my $LOCAL = "/Users/merlyn/Perl/MINICPAN/";

# how verbose?  false means nothing but errors
my $TRACE = 1;

## END CONFIG

## core:
use File::Path qw(mkpath);
use File::Basename qw(dirname);
use File::Spec::Functions qw(catfile);
use File::Find qw(find);

## LWP:
use URI ();
use LWP::Simple qw(mirror RC_OK RC_NOT_MODIFIED);

## Compress::Zlib
use Compress::Zlib qw(gzopen $gzerrno);

## first, get index files
my_mirror($_) for qw(
             authors/01mailrc.txt.gz
             modules/02packages.details.txt.gz
             modules/03modlist.data.gz
            );

## now walk the packages list
my $gz = gzopen(catfile($LOCAL, "modules/02packages.details.txt.gz"), 
+"rb")
  or die "Cannot open details: $gzerrno";
my $state = 1;
while ($gz->gzreadline($_) > 0) {
  if ($state == 1) {        # in header
    $state = 2 unless /\S/;
    next;
  }
  if ($state == 2) {        # blank following header
    $state = 3;
    next;
  }

  my ($module, $version, $path) = split;
  my_mirror("authors/id/$path");
}

## finally, clean the files we didn't stick there
clean_unmirrored();

exit 0;

BEGIN {
  my %mirrored;

  sub my_mirror {
    my $path = shift;

    my $remote_uri = URI->new_abs($path, $REMOTE)->as_string;
    my $local_file = catfile($LOCAL, $path);

    return if $mirrored{$local_file}++;

    ## presume "authors/id/*" is up to date if it is present
    return if $path =~ m{^authors/id} and -f $local_file;

    print "$remote_uri -> $local_file\n" if $TRACE;

    mkpath(dirname($local_file), 1, 0711);
    my $status = mirror($remote_uri, $local_file);

    return if $status == RC_OK or $status == RC_NOT_MODIFIED;
    warn "$remote_uri: $status!\n";
  }

  sub clean_unmirrored {
    find sub {
      return unless -f and not $mirrored{$File::Find::name};
      print "removing $File::Find::name\n" if $TRACE;
      unlink $_ or warn "Cannot remove $File::Find::name: $!";
    }, $LOCAL;
  }
}

[download]

In reply to Mirror only the installable parts of CPAN by merlyn

Title:
Use:  <p> text here (a paragraph) </p>
and:  <code> code here </code>
to format your post, it's "PerlMonks-approved HTML":


  • Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!
  • Titles consisting of a single word are discouraged, and in most cases are disallowed outright.
  • Read Where should I post X? if you're not absolutely sure you're posting in the right place.
  • Please read these before you post! —
  • Posts may use any of the Perl Monks Approved HTML tags:
    a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, details, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, summary, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr
  • You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)
            For:     Use:
    & &amp;
    < &lt;
    > &gt;
    [ &#91;
    ] &#93;
  • Link using PerlMonks shortcuts! What shortcuts can I use for linking?
  • See Writeup Formatting Tips and other pages linked from there for more info.