""" Prints the number of duplicate songs in itunes, then prints a list of duplicated songs. A "duplicate song" means multiple references to the same sound file in iTunes. USAGE: python duplicates.txt the argument is your iTunes music library XML file. typically, this is whereever you have iTunes installed. for example, mine is: /Users/paulsanwald/Music/iTunes/iTunes Music Library.xml """ import codecs import sys if __name__ == '__main__': file = codecs.open(sys.argv[1],"r","utf-8") # find all the duplicate filenames in itunes. files = [] duplicates = [] for line in file: if line.find("file:") != -1: start = line.find("") + len("") end = line.find("") fileName = line[start:end] if fileName in files: duplicates.append(fileName) else: files.append(fileName) print ("total songs: ",len(files)) print ("number of duplicates:",len(duplicates)) print (duplicates) file.close()