解析iTunes播放列表

• XML和属性列表（p-list）文件
• 使用numpy数组
• 用matplotlib绘制直方图和散点图

  import argparse
  from matplotlib import pyplot
  #用来读取播放列表文件
  import plistlib
  #用来存储数据
  import numpy as np
  
  
  def findCommonTracks(filenames):
      trackNameSets = []
      for f in filenames:
          tracknames = set()
          plist = plistlib.readPlist(f)
          tracks = plist['Tracks']
          for id,track in tracks.items():
              try:
                  tracknames.add(track['Name'])
              except:
                  pass
      trackNameSets.append(tracknames)
      #找到重复的放到文件里
      commonTracks = set.intersection(*trackNameSets)
      if len(commonTracks)>0:
          f = open("common.txt",'wb')
          for val in commonTracks:
              val += '\n'
              f.write(val.encode('utf-8'))
          f.close()
          print("重复的音轨已写入到common.txt中")
      else:
          print("没有重复的音轨")
  
  
  #查找重复的曲目
  def findDuplicates(filename):
      plist = plistlib.readPlist(filename)
      tracks = plist['Tracks']
      tracknames ={}
      for id,track in tracks.items():
          try:
              name = track['name']
              duration = track['Total Time']
              if name in tracknames:
                  if duration//1000 == tracknames[name][0]//1000:
                      count = tracknames[name][1]
                      tracknames[name] = (duration,count+1)
              else:
                  tracknames[name] = (duration, 1)
          except:
              pass
  
          #提取重复的音轨
          dups = []
          for k,v in tracknames.items():
              if v[1] > 1:
                  dups.append((v[1],k))
          if len(dups):
              print("存在重复的音轨，已经记录到dups.txt中")
          else:
              print("没有重复的音轨")
          f = open("dups.txt","wb")
          for val in dups:
              f.write(val[0])
              f.write(val[1])
          f.close()
  
  
  #收集信息并绘制
  def plotStats(filename):
      plist = plistlib.readPlist(filename)
      tracks = plist['Tracks']
      #评级和持续时间
      ratings = []
      durations = []
      for id,track in tracks.items():
          try:
              ratings.append(track['Album Rating'])
              durations.append(track['Total Time'])
          except:
              pass
  
      if ratings == [] or durations == []:
          print("%s的评级和持续时间不合理"%filename)
          return
      #柱状图
      x = np.array(durations,np.int32)
      x = x/60000
      y = np.array(ratings,np.int32)
      pyplot.subplot(2,1,1)
      pyplot.plot(x,y,'o')
      pyplot.axis([0,1.05*np.max(x),-1,110])
      pyplot.xlabel("Track Duration")
      pyplot.ylabel("Track rating")
      #散点图
      pyplot.subplot(2,1,2)
      pyplot.hist(x,bins = 20)
      pyplot.xlabel("Track duration")
      pyplot.ylabel("count")
  
      pyplot.show()
  
      #命令行选项
  def main():
      descStr ="this programm analyzes playlist files(.xml) exported from iTunes."
      parser = argparse.ArgumentParser(description=descStr)
      group = parser.add_mutually_exclusive_group()
  
      group.add_argument('--common',nargs='*',dest='plFiles',required=False)
      group.add_argument('--stats', dest='plFile', required=False)
      group.add_argument('--dup', dest='plFileD', required=False)
  
      args = parser.parse_args()
      if args.plFiles:
          findCommonTracks(args.plFiles)
      elif args.plFile:
          plotStats(args.plFile)
      elif args.plFileD:
          findDuplicates(args.plFileD)
      else:
           print('error!')
  
  
  if __name__ == "__main__":
      main()

  

  运行实例