#-*-encoding:utf-8-*-
import os, sys, time, datetime, glob
fo1 = open("C:/Users/Administrator/Desktop/areainfo.txt", "w")
fo2 = open("C:/Users/Administrator/Desktop/personinfo.txt", "w")
for root, dirs, files, in os.walk("E:/test", topdown=False):
    for name in files:
        file_name = os.path.join(root,name)
        if os.path.splitext(file_name)[1] == '.txt':
            print(file_name)
            with open(file_name) as a_file:
                for data in a_file.readlines():
                    str2=[]
                    str4=[]
                    for i in [0, 1, 2, 3, 7]:
                        str2.append(data.split('||~||')[i])
                    fo1.write("||~||".join(str2)+"\n")
                    for i in [4, 5, 6, 7, 8, 9, 10, 11]:
                        str4.append(data.split('||~||')[i])
                    fo2.write("||~||".join(str4)+"\n")
fo1.close()
fo2.close()

# -*- coding: utf-8 -*-
"""
Created on Mon Mar 30 18:05:35 2020
@author: fengzi
"""
import os
import pandas as pd
from datetime import datetime
 
def main():
    source_dir = 'E:/服管部/滿(mǎn)意度調(diào)研/滿(mǎn)意度影響因子分析/3.18\BI提單數(shù)據(jù)/BI2020031700005分開(kāi)/分列測(cè)試/集團(tuán)成員.txt'
    target_dir = 'E:/服管部/滿(mǎn)意度調(diào)研/滿(mǎn)意度影響因子分析/3.18\BI提單數(shù)據(jù)/BI2020031700005分開(kāi)/分列測(cè)試/集團(tuán)成員.xlsx'
    new_colums = "look\r\n"
    
    start_time = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
    print("開(kāi)始時(shí)間：",start_time)
    
    #文件開(kāi)頭增加新的一列內(nèi)容作為列名（原列名太長(zhǎng)/不可用）
    f = open(source_dir, 'r')
    content = f.read()  # 讀取文件內(nèi)容
    f_new = open('b.txt', 'w')
    f_new.write(new_colums)  # 開(kāi)頭寫(xiě)入內(nèi)容并換行
    f_new.write(content)    # 寫(xiě)入原文件內(nèi)容
    f_list=list(set(f.readlines()))  #先把內(nèi)容readlines()為列表，然后用set集合去重后再轉(zhuǎn)化為列表，賦值于變量f_list
    for i in f_list:   #for循環(huán)列表f_list,判斷是否有“\n”字符，如果有，將元素‘\n'移除
        if i=='\n':
           f_list.remove(i)
    f_new.writelines(f_list) #將列表f_list的內(nèi)容(此時(shí)列表已去除換行空白行)，通過(guò)writelines的方式寫(xiě)入新文件,      
    f.close()
    f_new.close()
    os.remove(source_dir)  # 移除老文件
    os.rename('b.txt', source_dir) # 新文件命名為老文件名
    data = pd.read_csv(source_dir,"rb",engine='python') #讀入數(shù)據(jù)出現(xiàn)亂碼可添加engine='python'
    
    #字符串切分后結(jié)果分列展示
    df = pd.DataFrame(data, columns=["look"]) #需要分列的列名
    df=df["look"].str.split('', expand=True)  # 分列的字符，split默認(rèn)輸出list,設(shè)置expand=True結(jié)果會(huì)分列展示  
    #print(df)
    df.to_excel(target_dir) #列表df存儲(chǔ)至excel
    
    end_time = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
    print("完成時(shí)間",end_time)
    
if __name__ == "__main__":
    main()