hymnologica.cz - check which Cantus IDs are available at CantusIndex

cantusindex_missing_ids.rb

# reads Cantus IDs on stdin, tries to fetch every one from CantusIndex, prints result

require 'mechanize'

def exists?(cantusid)
  uri = "http://www.cantusindex.org/id/#{cantusid}"

  agent = Mechanize.new

  begin
    agent.get uri
  rescue Mechanize::ResponseCodeError
    return false
  end

  true
end

ARGF.each do |cantusid|
  cantusid.strip!
  puts(cantusid + ',' + exists?(cantusid).to_s)

  sleep 2
end

hymnologica_sequence_id_list.rb

# prints all sequence Cantus IDs available at hymnologica.cz

require 'mechanize'

uri = 'http://hymnologica.cz/sequences-ids'

agent = Mechanize.new
page = agent.get uri

page.parser.css('table.views-table tbody tr td:first').collect do |i|
  puts i.text.strip
end

put_them_together.sh

#!/bin/bash

ruby hymnologica_sequence_id_list.rb | ruby cantusindex_missing_ids.rb