函数式编程
#!/usr/bin/env python3# -*- coding: utf-8 -*- def zhidao_560604345(infile, outfile): reader = open(infile, 'r') set_dict = {} setenv_dict = {} while True: line = reader.readline() if len(line) == 0: break a, b, c = line.strip().split(maxsplit=2) if a == 'set': if not b in set_dict: set_dict[b] = set() set_dict[b].add(c.strip()) elif a == 'setenv': if not b in setenv_dict: setenv_dict[b] = set() setenv_dict[b].update(c.strip().split(':')) reader.close() buff = [] for k, v in set_dict.items(): buff.append('set %s "%s"' % (k, ':'.join(list(v)))) for k, v in setenv_dict.items(): tmp = [] for item in list(v): if item == '$' + k: pass elif item.startswith('/mnt/'): tmp.append('{mntpath}/' + item[5:]) else: tmp.append(item) tmp.sort() buff.append('setenv %s "%s"' % (k, ':'.join(tmp))) writer = open(outfile, 'w') writer.write('\n'.join(buff)) writer.close() if __name__ == '__main__': zhidao_560604345('zhidao_560604345.input', 'zhidao_560604345.output')运行结果：set value2 "/asd:/xyz"set value1 "/usr:/sys"setenv path2 "/aaa:/abc:/usr"setenv path1 "/usr/abc:/usr/asd:/usr/lib:{mntpath}/abc:{mntpath}/ccc:{mntpath}/ddd:{mntpath}/xyz"
白衣染霜花
分隔日志文件存为小文件#coding:utf-8 #file: FileSplit.pyimport os,os.path,timedef 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 = 1if 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 :breaktFilename = 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")分类汇总小文件：#coding:utf-8 #file: Map.pyimport os,os.path,redef 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] += 1else:tempData[visitUrl] = 1dataLine = 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")3. 再次将多个文件分类汇总为一个文件。#coding:utf-8 #file: Reduce.pyimport os,os.path,redef 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")