python实现大文件分割与合并

import osFILE_DIR = os.path.dirname(os.path.abspath(__file__))#========================================================# 文件操作#========================================================def get_filelist1(dir, postfix):  '''  按照后缀返回文件名列表  INPUT -> 目录地址, 文件后缀  OUTPUT -> 文件名列表  '''  return [os.path.join(dir, f) for f in os.listdir(dir) if f.endswith(postfix)]def get_filelist2(dir, preffix):  '''  按照前缀返回文件名列表  INPUT -> 目录地址, 文件前缀  OUTPUT -> 文件名列表  '''  return [os.path.join(dir, f) for f in os.listdir(dir) if f.startswith(preffix)]def get_file_postfix(filename):  '''  获取文件名后缀  INPUT -> 文件名  OUTPUT -> 文件后缀  '''  file = os.path.splitext(filename)  preffix, postfix = file  return postfixdef get_file_preffix(filename):  '''  获取文件名前缀  INPUT -> 文件名  OUTPUT -> 文件前缀  '''  file = os.path.splitext(filename)  preffix, postfix = file  return preffixdef file_chunkspilt(path, filename, chunksize):  '''  文件按照数据块大小分割为多个子文件  INPUT -> 文件目录, 文件名, 每个数据块大小  '''  if chunksize > 0:    filepath = path+'/'+filename    partnum = 0    inputfile = open(filepath, 'rb')    while True:      chunk = inputfile.read(chunksize)      if not chunk:        break      partnum += 1      newfilename = os.path.join(path, (filename+'_%04d' % partnum))      sub_file = open(newfilename, 'wb')      sub_file.write(chunk)      sub_file.close()    inputfile.close()  else:    print('chunksize must bigger than 0!')def file_linespilt(path, filename, limit):  '''  文件按照行分割成多个子文件  INPUT -> 文件目录, 文件名, 行数  '''  if limit > 0:    preffix = get_file_preffix(filename)    postfix = get_file_postfix(filename)    file_count = 0    l_list = []    with open(path+'/'+filename, 'rb') as f:      for line in f:        l_list.append(line)        if len(l_list) < limit:          continue        subfile = preffix+"_"+str(file_count)+"."+postfix        with open(FILE_DIR+'/'+subfile, 'wb') as file:          for l in l_list[:-1]:            file.write(l)          file.write(l_list[-1].strip())          l_list=[]          file_count += 1  else:    print('limit must bigger than 0!')def file_combine(path, filename):  '''  子文件合并  INPUT -> 文件目录, 文件名  '''  filepath = path+'/'+filename  partnum = 0  outputfile = open(filepath, 'wb')  subfile_list = get_filelist2(FILE_DIR, filename+'_')  for subfile in subfile_list:    temp = open(subfile, 'rb')    outputfile.write(temp.read())    temp.close()  outputfile.close()