Python大数据， 一些简单的 *** 作

#coding:utf-8

#file: FileSplit.py

import os,os.path,time

def FileSplit(sourceFile, targetFolder):

sFile = open(sourceFile, 'r')

number = 100000 #每个小文件中保存100000条数据

dataLine = sFile.readline()

tempData = [] #缓存列表

fileNum = 1

if not os.path.isdir(targetFolder): #如果目标目录不存在，则创建

os.mkdir(targetFolder)

while dataLine: #有数据

for row in range(number):

tempData.append(dataLine) #将一行数据添加到列表中

dataLine = sFile.readline()

if not dataLine :

break

tFilename = os.path.join(targetFolder,os.path.split(sourceFile)[1] + str(fileNum) + ".txt")

tFile = open(tFilename, 'a+') #创建小文件

tFile.writelines(tempData) #将列表保存到文件中

tFile.close()

tempData = [] #清空缓存列表

print(tFilename + " 创建于: " + str(time.ctime()))

fileNum += 1 #文件编号

sFile.close()

if __name__ == "__main__" :

FileSplit("access.log","access")

#coding:utf-8

#file: Map.py

import os,os.path,re

def Map(sourceFile, targetFolder):

sFile = open(sourceFile, 'r')

dataLine = sFile.readline()

tempData = {} #缓存列表

if not os.path.isdir(targetFolder): #如果目标目录不存在，则创建

os.mkdir(targetFolder)

while dataLine: #有数据

p_re = re.compile(r'(GET|POST)\s(.*?)\sHTTP/1.[01]',re.IGNORECASE) #用正则表达式解析数据

match = p_re.findall(dataLine)

if match:

visitUrl = match[0][1]

if visitUrl in tempData:

tempData[visitUrl] += 1

else:

tempData[visitUrl] = 1

dataLine = sFile.readline() #读入下一行数据

sFile.close()

tList = []

for key,value in sorted(tempData.items(),key = lambda k:k[1],reverse = True):

tList.append(key + " " + str(value) + '\n')

tFilename = os.path.join(targetFolder,os.path.split(sourceFile)[1] + "_map.txt")

tFile = open(tFilename, 'a+') #创建小文件

tFile.writelines(tList) #将列表保存到文件中

tFile.close()

if __name__ == "__main__" :

Map("access\\access.log1.txt","access")

Map("access\\access.log2.txt","access")

Map("access\\access.log3.txt","access")

#coding:utf-8

#file: Reduce.py

import os,os.path,re

def Reduce(sourceFolder, targetFile):

tempData = {} #缓存列表

p_re = re.compile(r'(.*?)(\d{1,}$)',re.IGNORECASE) #用正则表达式解析数据

for root,dirs,files in os.walk(sourceFolder):

for fil in files:

if fil.endswith('_map.txt'): #是reduce文件

sFile = open(os.path.abspath(os.path.join(root,fil)), 'r')

dataLine = sFile.readline()

while dataLine: #有数据

subdata = p_re.findall(dataLine) #用空格分割数据

#print(subdata[0][0]," ",subdata[0][1])

if subdata[0][0] in tempData:

tempData[subdata[0][0]] += int(subdata[0][1])

else:

tempData[subdata[0][0]] = int(subdata[0][1])

dataLine = sFile.readline() #读入下一行数据

sFile.close()

tList = []

for key,value in sorted(tempData.items(),key = lambda k:k[1],reverse = True):

tList.append(key + " " + str(value) + '\n')

tFilename = os.path.join(sourceFolder,targetFile + "_reduce.txt")

tFile = open(tFilename, 'a+') #创建小文件

tFile.writelines(tList) #将列表保存到文件中

tFile.close()

if __name__ == "__main__" :

Reduce("access","access")

这个是 python2.7 的代码，如果是 python3.x 的话，改一下 print 函数就好。 if __name__ == '__main__': list_three = [] list_six = [] list_nine = [] for i in range(1, 301): if i % 3 == 0 or str(i).find('3') -1: list_three.append(i) ...

---