原文件是一个6.8G大小的csv文件，太大了，不好处理，需要将其切分成多个小文件

    1. import os
    2. import time
    5. def mkSubFile(lines, head, srcName, sub):
    6.     [des_filename, extname] = os.path.splitext(srcName)
    7.     # 命名格式
    8.     filename = des_filename + '_' + str(sub) + extname
    9.     print('make file: %s' % filename)
    10.     fout = open(filename, 'w',encoding='utf-8')
    11.     try:
    12.         fout.writelines([head])
    13.         fout.writelines(lines)
    14.         return sub + 1
    15.     finally:
    16.         fout.close()
    19. def splitByLineCount(filename, count):
    20.     fin = open(filename, 'r',encoding='utf-8')
    21.     try:
    22.         head = fin.readline()
    23.         buf = []
    24.         sub = 1
    25.         for line in fin:
    26.             buf.append(line)
    27.             if len(buf) == count:
    28.                 sub = mkSubFile(buf, head, filename, sub)
    29.                 buf = []
    30.         if len(buf) != 0:
    31.             sub = mkSubFile(buf, head, filename, sub)
    32.     finally:
    33.         fin.close()
    36. if __name__ == '__main__':
    37.     begin = time.time()
    38.     splitByLineCount('D:\\Rexel数据\\EHSY_DATA_V1.csv', 100000)   # 100000为切分的行数，每100000切分成一个文件
    39.     end = time.time()
    40.     print('time is %d seconds ' % (end - begin))

    原文件：
    image.png

    切分后的文件：
    image.png