Find all unique video codecs in specific directories - requires mediainfo

find_unique_codecs_vs6.rb

#developed by Maile Thiesen
#!/usr/bin/ruby

require 'json'
require 'time'
require 'nokogiri'



library_path = ARGV[0]

files_list = Dir.glob("#{library_path}/**/*")
total_capture_scatch_and_exports_size = 0
counter = 0
duration_of_all_videos = 0

video_info = []


files_list.each do |filepath|
filename = File.basename(filepath.to_s)
  codecs = {}
  video_duration = {}
  filepath.chomp!
  folders_to_scan = ["/capture scratch/", "/capturescratch/", "/capture-scratch/", "/capture_scratch/", "exports", "export"]
  file_extensions_to_exclude = [".TIFF", ".TIF", ".tif", ".tiff", ".jpg", ".jpeg", ".JPG", ".JPEG", ".CR2", ".pek", ".PRV", ".caf", ".prproj", ".fcp", ".FCP", ".THM", ".XML", ".BMP"]

  
  file_size = File.size(filepath)
  file_extension = File.extname(filepath)
  if 
  	folders_to_scan.any? { |folder| filepath.downcase.include? folder }
	  
	if 
	  File.file?(filepath) && filename[0] != "." && !file_extensions_to_exclude.any? {|extension| filepath.include? extension}
	  	# puts filepath
	    xml_mediainfo_output =  %x[mediainfo --Output=XML '#{filepath}']
	    doc = Nokogiri::XML(xml_mediainfo_output)

	    duration = %x[mediainfo --Inform="General;%Duration%" '#{filepath}'].to_i
		general_format = doc.xpath('//File/track[@type="General"]/Format/text()')
		video_format = doc.xpath('//File/track[@type="Video"]/Format/text()') 
		general_commercial_name = doc.xpath('//File/track[@type="General"]/Commercial_name/text()')
		general_format_profile = doc.xpath('//File/track[@type="General"]/Format_profile/text()')
		general_writing_library = doc.xpath('//File/track[@type="General"]/Writing_library/text()')
		 	

		codecs[:general_format] = general_format
		codecs[:video_format] = video_format
		codecs[:general_commercial_name] = general_commercial_name
		codecs[:general_format_profile] = general_format_profile
		codecs[:general_writing_library] = general_writing_library
		codecs[:file_extension] = file_extension
		

		video_duration[:duration] = duration
		total_capture_scatch_and_exports_size += file_size

		counter += 1
		puts "You are on file number #{counter}"
	  	video_info << codecs
	  	puts "the duration of the video is #{duration}"
	  	duration_of_all_videos = duration_of_all_videos + duration
	  	puts "the duration of videos counted so far is: #{duration_of_all_videos}"
	end	
  end

end
puts "the total duation in milliseconds is: #{duration_of_all_videos}"
t = duration_of_all_videos/1000

mm, ss = t.divmod(60)
hh, mm = mm.divmod(60)
dd, hh = hh.divmod(24) 
puts "%d days, %d hours, %d minutes and %d seconds" % [dd, hh, mm, ss]

unique_codecs = video_info.uniq

puts "THE UNIQUE CODECS ARE: #{JSON.pretty_generate(unique_codecs)}"
puts "THE TOTAL FILESIZE IS : #{total_capture_scatch_and_exports_size/(1000**3).to_f} GB"

open('find_unique_codecs_vs5_output.txt', 'w') do |f|
  f << "the total duation in milliseconds is: #{duration_of_all_videos}"
  f << "%d days, %d hours, %d minutes and %d seconds" % [dd, hh, mm, ss]
  f << "THE UNIQUE CODECS ARE: #{JSON.pretty_generate(video_info.uniq)}"
  f << "THE TOTAL FILESIZE IS : #{total_capture_scatch_and_exports_size/(1000**3).to_f} GB"
end

👍 But you should add a flag that would then save it to a file :)

&& ! [".tiff", ".tif",".jpg",".jpeg"].include? file_extension.downcase