quickly fetch all of the annotations on refseq

fetch-refseq-annotations.rb

#!/usr/bin/env ruby

require "open-uri"
require "parallel"

open("https://ftp.ncbi.nlm.nih.gov/genomes/refseq/bacteria/assembly_summary.txt") do |handle|
  handle.gets # skip header
  handle.gets
  Parallel.each(handle, :in_processes => 6, :progress => 'downloading') do |line|
    row = line.split("\t")
    uri_base = row[-3]
    filename = "#{uri_base.split('/')[-1]}_genomic.gbff.gz"
    full_uri = "#{uri_base}/#{filename}"
    cmd =  "wget --quiet -O #{filename} #{full_uri}"
    `#{cmd}`
  end
end