Download all of pubchem

pubchem-download.rb

require 'net/ftp'

Net::FTP.open('ftp.ncbi.nlm.nih.gov') do |ftp|
  ftp.passive = true
  ftp.login
  ftp.chdir('/pubchem/Compound/CURRENT-Full/SDF')
  files = ftp.list('*')
  total = 0
  sdf_files = files.select { |f| f.match(/\.sdf\.gz$/) }
  sdf_files.each_with_index do |file, index|
    tokens = file.split(/\s+/)
    size = tokens[4].to_i
    total += size
    filename = tokens.last
    puts "Getting [#{filename}] [#{size}] [#{index} of #{sdf_files.count}]"
    ftp.getbinaryfile(filename, filename, 1024)
  end
  puts "#{total} :: #{total.to_f/(1024*1024*1024).to_f}"
end; nil