kill_dupes

#!/usr/bin/env python
from gmusicapi import Mobileclient

def map_track_duplication(tracks):
    album_track_duplicate_map = {}
    for track in tracks:
        if 'album' in track.keys():
          albumNorm = track['album'].lower()
          titleNorm = track['title'].lower()
          if albumNorm not in album_track_duplicate_map:
              album_track_duplicate_map.update({albumNorm: {}})
          if titleNorm in album_track_duplicate_map[albumNorm]:
              album_track_duplicate_map[albumNorm][titleNorm] += 1
          else:
              album_track_duplicate_map[albumNorm][titleNorm] = 1
    return album_track_duplicate_map


def sort_tracks_by_album(tracks):
    tracks_by_album = {}
    for track in tracks:
        if 'album' in track.keys():
          albumNorm = track['album'].lower()
          if albumNorm not in tracks_by_album:
              tracks_by_album[albumNorm] = []
          tracks_by_album[albumNorm].append(track)
    return tracks_by_album


def get_duplicate_tracks(all_tracks_by_album, album_track_duplicate_map):
    duplicate_tracks = []
    for album_title in album_track_duplicate_map:
        for track_title in album_track_duplicate_map[album_title]:
            duplicates = album_track_duplicate_map[album_title][track_title] - 1
            if duplicates > 0:
                for album in all_tracks_by_album:
                    if album_title == album:
                        for track in all_tracks_by_album[album]:
                            if 'album' in track.keys():
                              albumNorm = track['album'].lower()
                              titleNorm = track['title'].lower()
                              if titleNorm == track_title and duplicates > 0:
                                  duplicate_tracks.append(track)
                                  print "Queueing for removal: '" + track['title'].encode('utf-8').strip() + "' from album '" + track['album'].encode('utf-8').strip() + "' by '" + track['artist'].encode('utf-8').strip()
                                  all_tracks.remove(track)
                                  duplicates += -1

    return duplicate_tracks

import sys

def query_yes_no(question, default="yes"):
    """Ask a yes/no question via raw_input() and return their answer.
    "question" is a string that is presented to the user.
    "default" is the presumed answer if the user just hits <Enter>.
        It must be "yes" (the default), "no" or None (meaning
        an answer is required of the user).
    The "answer" return value is one of "yes" or "no".
    """
    valid = {"yes":True,   "y":True,  "ye":True,
             "no":False,     "n":False}
    if default == None:
        prompt = " [y/n] "
    elif default == "yes":
        prompt = " [Y/n] "
    elif default == "no":
        prompt = " [y/N] "
    else:
        raise ValueError("invalid default answer: '%s'" % default)

    while True:
        sys.stdout.write(question + prompt)
        choice = raw_input().lower()
        if default is not None and choice == '':
            return valid[default]
        elif choice in valid:
            return valid[choice]
        else:
            sys.stdout.write("Please respond with 'yes' or 'no' "\
                             "(or 'y' or 'n').\n")


def get_track_ids(tracks):
    track_ids = []
    for track in tracks:
        track_ids.append(track['id'])
    return track_ids


api = Mobileclient()
logged_in = api.login('username', 'password', Mobileclient.FROM_MAC_ADDRESS)

if logged_in:
    print "Successfully logged in. Beginning duplicate detection process."
    all_tracks = api.get_all_songs()
    album_track_duplicate_map = map_track_duplication(all_tracks)
    all_tracks_by_album = sort_tracks_by_album(all_tracks)
    duplicate_tracks = get_duplicate_tracks(all_tracks_by_album, album_track_duplicate_map)
    duplicate_track_ids = get_track_ids(duplicate_tracks)
    if len(duplicate_track_ids) > 0:
        if query_yes_no("Found " + str(len(duplicate_track_ids)) + " duplicate tracks. Delete duplicates?", "no"):
            deleted_track_ids = api.delete_songs(duplicate_track_ids)
            print "Successfully deleted " + str(len(deleted_track_ids)) + " of " + str(len(duplicate_track_ids)) + " queued songs for removal."
    else:
        print "I didn't find any duplicate tracks."
    print "Thank you!"