Running wget 

my $spider_cmd =
    "wget"
    . " --recursive"           # follow links (within site)
    . " --domains $host_name"  # don't follow off-site links
    . " --level=inf"           # go deep!
    . " --timestamping"        # probably not useful
    . " --html-extension"      # give resulting HTML files .html ext
    . " --convert-links"       # rewrite links to match new extensions
    . " --backup-converted"    # avoid re-downloading renamed files
    . " $config->{cms_url}"    # URL to start spidering from CMS site
    . " >spider.log 2>&1";     # Log STDOUT/STDERR in work dir