podgetter.pl

#!/usr/bin/perl 
#
#   podgetter.pl
#
#   Podcast downloader exclusively for BBC Radio
#   
#   2014/04/11 v1.0
#   2014/06/10 v1.1
#

use strict;
#use warnings;

my $Download = "./download";
my $Keepdays = 60;
my $Maxfiles = 3;

my ($mday, $mon, $year) = (localtime(time-60*60*24*$Keepdays))[3..5];
my $Keepdate = sprintf ("%04d%02d%02d", $year+1900, $mon+1, $mday);

sub list_urls {
    my @url_list;
    my @rss_list = @_;
    my ($rss, $url, $count);

    foreach $rss (@rss_list) {
        $count = 1;
        open (IN, "curl $rss 2>/dev/null|");
        while (<IN>) {
            if ($_ =~ m!<media:content url="(http://[^>]+\.mp3)"!) {
                $url = $1;
                $url =~ m!/[^/]+_(\d{8})-.+\.mp3$!;
                if ($1 >= $Keepdate && $count <= $Maxfiles) {
                    $count += 1;
                    push @url_list, $url;
                    print $url. "\n";
                }
            }
        }
        close IN;
    }
    return @url_list;
}

sub get_rss {
    my @rss_list;

    open (IN, $_[0]);
    while (<IN>) {
        next if ($_ =~ m/^\s*#/);
        if ($_ =~ m!(http://.*/rss.xml)!) {
            push @rss_list, $1;
        }
    }
    close IN;
    return @rss_list;
}

sub clean_files {
    my ($date, $count, $title, $file);
    my @files;

    $title = "";
    $count = 0;

    opendir(IN, $Download);
    @files = readdir(IN);
    closedir IN;
    
    foreach $file (reverse(sort @files)) {
        next unless ($file =~ m/(.*)_(\d{8})-.+\.mp3$/);
        if ($1 ne $title) {
            $count = 0;
            $title = $1;
        }
        $count += 1;
        if ($2 < $Keepdate || $count > $Maxfiles ) {
            print "Delete: $file\n";
            unlink "$Download/$file";
        }
    }
}

sub get_files {
    my @url_list = @_;
    my ($url, $file);

    for $url (@url_list) {
        $url =~ m!/([^/]+.mp3)$!;
        $file = $1;
        next if ( -f "$Download/$file" );
        system ("wget -O $Download/$file $url");
    }
}

MAIN:{
    my $s;
    my (@rss_list, @url_list);
    @rss_list = get_rss($ARGV[0]);
    @url_list = list_urls(@rss_list);
    get_files(@url_list);
    clean_files();
}


#####
$ cat bbcnews.txt 
http://downloads.bbc.co.uk/podcasts/radio4/wtonight/rss.xml
http://downloads.bbc.co.uk/podcasts/radio4/fooc/rss.xml
http://downloads.bbc.co.uk/podcasts/radio4/ta/rss.xml
http://downloads.bbc.co.uk/podcasts/worldservice/newshour/rss.xml
http://downloads.bbc.co.uk/podcasts/worldservice/docarchive/rss.xml
http://downloads.bbc.co.uk/podcasts/radio4/today/rss.xml