fetch DICOM DE

table6-1.rb

require 'nokogiri'
require 'open-uri'

fname = ARGV.shift
if fname
  html = File.read(fname)
else
  url = "http://dicom.nema.org/medical/dicom/current/output/chtml/part06/chapter_6.html"
  html = URI.open(url).read
  File.write("/tmp/chapter6.html", html)
end

tree = Nokogiri::HTML(html)
tbody = tree.at_css("#table_6-1 ~ div > table > tbody")
table6_1 = tbody.css('tr').map do |tr|
  ary = tr.css('td').map {|x| x.text.strip}
  ary[0] = ary[0].scan(/\((....),(....)\)/).flatten.join
  ary[2] = ary[2].split("\u200b").join
  ary[0,5]
end

pp table6_1