python实现大文件切割操作

import os
import time


def mkSubFile(lines, srcName, sub):
    [des_filename, extname] = os.path.splitext(srcName)
    filename = des_filename + '_' + str(sub) + extname
    print 'make file: %s' % filename
    fout = open(filename, 'w')
    try:
        fout.writelines(lines)
        return sub + 1
    finally:
        fout.close()


def splitByLineCount(filename, count):
    with open(filename, 'rb') as fin:
        try:
            head = fin.readline()
            buf = []
            sub = 1
            buf.append(head)
            for line in fin:
                buf.append(line)
                if len(buf) == count:
                    sub = mkSubFile(buf, filename, sub)
                    buf = []
            if len(buf) != 0:
                sub = mkSubFile(buf, filename, sub)
        finally:
            fin.close()


if __name__ == '__main__':
    # 每个文件存储40000行数据
    begin = time.time()
    splitByLineCount('/home/python/Desktop/sum.txt', 40000)
    end = time.time()
    print('time is %d seconds ' % (end - begin))

 

来源：CSDN

作者：xiao_xia_ming

链接：https://blog.csdn.net/xiao_xia_ming/article/details/103460683