基于Python实现大文件分割和命名脚本过程解析

 # -*- coding:utf-8 -*-

 import os,re,shutil
 import platform

 sys_name = platform.system().lower()
 SPLIT_CHAR = '\\' if sys_name.find('windows') != -1 else '/'

 print('input big files`s path:')
 _path = raw_input()
 names = []
 pathes = []
 if os.path.isfile(_path):
   print('is file')
   names.append(_path)
 else:
   print('is nothing')
 '''
 elif os.path.isdir(_path):
   print('This is dir')
   pathes = os.listdir(_path)
   print('pathes='+str(pathes))
   for i in range(len(pathes)):
     fullpath = _path+SPLIT_CHAR+pathes[i]
     print('fullpath='+fullpath)
     if os.path.isfile(fullpath):
       names.append(fullpath)
       files.append(open(fullpath).read().split('\n'))
 '''

 print(len(names))

 line_num = int(raw_input('every file`line num = '))
 print('line number='+str(line_num))

 for i in range(len(names)):
   _name = names[i]
   ori_name = _name.split(SPLIT_CHAR)[len(_name.split(SPLIT_CHAR))-1]
   dir_name = _name.replace(ori_name,'DIR_'+ori_name)
   dir_name = dir_name.replace('.','_')
   print ori_name
   print dir_name
   os.system('mkdir '+dir_name)
   count = 1
   print '已处理：'+str(count)+'行'
   part_file = open(dir_name+SPLIT_CHAR+str(0)+'.part.txt','w')
   with open(_name, 'rb') as f:
     for line in f:
     if count%line_num == 0:
       part_file.close()
       part_file = open(dir_name+SPLIT_CHAR+str(int(count/line_num))+'.part.txt','w')
     part_file.write(line+'\n')
     count+=1
     if count%100000 == 0:
       print '已处理：'+str(count)+'行'
   print '已处理：'+str(count)+'行'
   os.system('python ./get_name_logfile.py '+dir_name)

  # -*- coding:utf-8 -*-


  import os,re,shutil
  import sys
  import platform

  sys_name = platform.system().lower()
  SPLIT_CHAR = '\\' if sys_name.find('windows') != -1 else '/'

  _path = sys.argv[1]
  names = []
  files = []
  pathes = []
  if os.path.isfile(_path):
    print('is file')
    names[0] = _path
  elif os.path.isdir(_path):
    print('This is dir')
    pathes = os.listdir(_path)
    print('pathes='+str(pathes))
    for i in range(len(pathes)):
      fullpath = _path+SPLIT_CHAR+pathes[i]
      print('fullpath='+fullpath)
      if os.path.isfile(fullpath):
        names.append(fullpath)
  else:
    print('is nothing')
    
  print(len(names))

  #  日期格式 ： 05-26 18:20:42.093  r'\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}.\d{3}'
  #  
  #  05-26 18:20:43.093：r'\d{2}-\d{2} {1,}\d{2}:\d{2}:\d{2}.\d{1,10}'

  date_reg = r'\d{2}-\d{2} {1,}\d{2}:\d{2}:\d{2}.\d{1,10}'
  time_reg = r'\d{2}:\d{2}:\d{2}.\d{1,10}'

  for i in range(len(names)):
    _name = names[i]
    print('name='+_name)
    # head 尝试在10行内查找日期
    head_len = 10
    start_time = '(start_time-'
    _file_ = open(_name, 'rb')
    reads = _file_.read()
    _file = reads.split('\n')
    if len(_file)/2 < 10:
      head_len = len(_file)/2
    for j in range(head_len):
      res = re.search(date_reg, _file[j])
      if res!=None and res.group(0)!=None:
        start_time = res.group(0)
        print('start_time='+start_time)
        break
    # tail
    tail_len = len(_file)-head_len
    end_time = '-end_time)'
    for j in range(len(_file)-1,tail_len-1,-1):
      res = re.search(time_reg, _file[j])
      if res!=None and res.group(0)!=None:
        end_time = res.group(0)
        print('end_time='+end_time)
        break
    _file_.close()
    ori_name = _name.split(SPLIT_CHAR)[len(_name.split(SPLIT_CHAR))-1]
    print('ori_name='+ori_name)
    new_name = start_time.replace(':','-')+'__'+end_time.replace(':','-')+os.path.splitext(ori_name)[1]
    print('new_name='+new_name)
    print("copy %s %s" % (_name, _name.replace(ori_name,new_name)))
    #os.system ("copy %s %s" % (_name, _name.replace(ori_name,new_name)))
    shutil.copy(_name,_name.replace(ori_name,new_name))
    os.system ("rm -rf "+_name)