Missing wwdc2013 videos from my own renaming format

missing_vids.rb

require 'nokogiri'

doc = Nokogiri::HTML(File.open("Videoswwdc.html"))
items = {}
doc.xpath("//li[@class='session']").each do |session|
  session_id = session['id'].sub('-video', '').to_i
  title = session.children.xpath("li[@class='title']").text
  items[session_id] = title
end

items.each {|k,v| puts "#{k} => #{v}"}


PREFIX="/Volumes/GTech/WWDC2013/"
# PREFIX="/Users/kim/Downloads/pdfs/"
files = Dir["#{PREFIX}WWDC2013*.mov"]
base_names = files.map {|d| d.sub(PREFIX, '') }


have_numbers = []
base_names.each do |file|
  have_numbers << $1.to_i if file =~ /WWDC2013 ([0-9]+) /
end

# build a list of missing session
have_nots = (items.keys - have_numbers).sort
missing_sessions = have_nots.map do |num|
   "#{num} - #{items[num]}"
end
puts missing_sessions.sort