Python实现的大数据分析操作系统日志功能示例实现的大数据分析操作系统日志功能示例
主要介绍了Python实现的大数据分析操作系统日志功能,涉及Python大文件切分、读取、多线程操作等相关使用
技巧,需要的朋友可以参考下
本文实例讲述了Python实现的大数据分析操作系统日志功能。分享给大家供大家参考,具体如下:
一一 代码代码
1、大文件切分
import os
import os.path
import time
def FileSplit(sourceFile, targetFolder):
if not os.path.isfile(sourceFile):
print(sourceFile, ' does not exist.')
return
if not os.path.isdir(targetFolder):
os.mkdir(targetFolder)
tempData = []
number = 1000
fileNum = 1
linesRead = 0
with open(sourceFile, 'r') as srcFile:
dataLine = srcFile.readline().strip()
while dataLine:
for i in range(number):
tempData.append(dataLine)
dataLine = srcFile.readline()
if not dataLine:
break
desFile = os.path.join(targetFolder, sourceFile[0:-4] + str(fileNum) + '.txt')
with open(desFile, 'a+') as f:
f.writelines(tempData)
tempData = []
fileNum = fileNum + 1
if __name__ == '__main__':
#sourceFile = input('Input the source file to split:')
#targetFolder = input('Input the target folder you want to place the split files:')
sourceFile = 'test.txt'
targetFolder = 'test'
FileSplit(sourceFile, targetFolder)
2、Mapper代码
import os
import re
import threading
import time
def Map(sourceFile):
if not os.path.exists(sourceFile):
print(sourceFile, ' does not exist.')
return
pattern = re.compile(r'[0-9]{1,2}/[0-9]{1,2}/[0-9]{4}')
result = {}
with open(sourceFile, 'r') as srcFile:
for dataLine in srcFile:
r = pattern.findall(dataLine)
if r:
t = result.get(r[0], 0)
t += 1
result[r[0]] = t
desFile = sourceFile[0:-4] + '_map.txt'
with open(desFile, 'a+') as fp:
for k, v in result.items():
fp.write(k + ':' + str(v) + '')
if __name__ == '__main__':
desFolder = 'test'
files = os.listdir(desFolder)
#如果不使用多线程,可以直接这样写
'''for f in files:
Map(desFolder + '\' + f)'''
#使用多线程
def Main(i):
Map(desFolder + '\' + files[i])
fileNumber = len(files)
评论0