2 回答
TA贡献1893条经验 获得超10个赞
#coding:utf-8
#file: FileSplit.py
import os,os.path,time
def FileSplit(sourceFile, targetFolder):
sFile = open(sourceFile, 'r')
number = 1000 #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")
TA贡献1795条经验 获得超7个赞
# -*- coding:utf-8 -*- F = [] with open ( 'test.txt' , 'r' ) as f: lines = f.readlines() flen = len (lines) for i in range ( 0 ,flen, 3 ): temp = [] temp.append(lines[i].strip()) temp.append(lines[i + 1 ].strip()) temp.append(lines[i + 2 ].strip()) F.append(temp) #序号从0开始 print F[ 0 ][ 0 ] print F[ 0 ][ 1 ] print F[ 0 ][ 2 ] print F[ 1 ][ 0 ] print F[ 1 ][ 1 ] print F[ 1 ][ 2 ] |
>>>
2016-05-23
文本1
文本2
2016-05-24
文本1
文本2
添加回答
举报