fetch genomes from NCBI in parallel

ncbi-fetch.rb

#!/usr/bin/env ruby

# download all genomes from ncbi using 8 processes
# ./ncbi-fetch.rb | xargs -I {} -n1 -p 8 wget {}

File.open('assembly_summary.txt').each do |line|
  row = line.strip.split("\t")
  base_url = row[19]
  next if base_url.nil?
  dir = base_url.split('/').last
  full_url = "#{base_url}/#{dir}_genomic.gbff.gz".gsub(/ftp:\/\//, 'https://')
  puts full_url
end