多文件脚本

# -*- coding:utf-8 -*-

import os

import numpy as np
import re
import  pandas as pd


def traverse(filepath):
    files = os.listdir(filepath)
    for fi in files:
        fi_d = os.path.join(filepath, fi)
        if os.path.isdir(fi_d):  # 判断是否为文件夹
            if not os.listdir(fi_d):  # 如果文件夹为空
                os.rmdir(fi_d)  # 删除这个空文件夹
            else:
                traverse(fi_d)
        else:
            file = os.path.join(filepath, fi_d)
            if os.path.getsize(file) == 0:  # 文件大小为0
                os.remove(file)  # 删除这个文件


def get_file(path):  # 创建一个空列表
    files = os.listdir(path)
    files.sort()  # 排序
    loglist = []
    txtlist=[]
    for file in files:
        if not os.path.isdir(path + file):  # 判断该文件是否是一个文件夹
            f_name = str(file)
            #             print(f_name)
            tr = '\\'  # 多增加一个斜杠
            filename = path + tr + f_name
            if(filename[-3:]=="log"):
                loglist.append(filename)
                # print(filename)
            if(filename[-3:]=="txt"):
                txtlist.append(filename)
    return (loglist,txtlist)



if __name__ == '__main__':
    path = r'E:\zzztest\zzzzDEMO\file2'
    outpath= r'E:\zzztest\zzzzDEMO\file2'
    # path= input("Please intput file path:")
    # outpath = input("Please intput the ouput file address:")
    num=len(path)
    traverse(path)
    loglist,txtlist = get_file(path)
    # print(list)
    right=0
    dictlog=[]
    dicttxt=[]
    final=[]
    for i in range(len(loglist)):
        # print(loglist[i])
        for line in open(loglist[i],"r",encoding='UTF-8'):
            # print(line)
            if(line[0:11]=="    gauss 1"):
                right=1
                # print(1)
            if(right==6):
                right=0
            if(right):
                # print(line)
                right=right+1
                result = re.findall(r'-?\d+\.?\d*e?-?\d*?', line[12:])
                # print(result)
                l=loglist[i][num+1:]
                result[0]=l+"-"+result[0]
                dictlog.append(result)
    for i in range(len(txtlist)):
        # print(txtlist[i])
        for line in open(txtlist[i],"r",encoding='ISO-8859-1'):
            # print(line)
            # if(line[0:9]=="     guass"):
            #     right=1
            #     print(1)
            # if(line[0:10])==("Writing ou"):
            #     right=0
            # if(right==1):
            #     # print(line)
            result = re.findall(r'-?\d+\.?\d*e?-?\d*?', line)
            l=txtlist[i][num+1:]
            result[0]=l+"-"+result[0]
            dicttxt.append(result)
    # print(dictlog)
    # print(dictlog[0],dictlog[1])

    for i in range(len(dicttxt)):
       final.append([dictlog[i*5+0][0][0:8],dictlog[i*5+0][0][20:],dictlog[i*5+1][0][20:],dictlog[i*5+2][0][20:],
                    dictlog[i*5+3][0][20:],dictlog[i*5+4][0][20:],dicttxt[i*1+0][0][18:]])
    print(final)
    # df=pd.read_excel(r'E:\zzztest\zzzzDEMO\file2\machinelearning.xlsx')
    # print(df)
    df = pd.DataFrame(final, columns= pd.MultiIndex.from_tuples(
        [('cmpname','cmpname'),('input','input1'),('input','input2'),('input','input3'),('input','input4'),
         ('input','input5'),('output','output')]
    ))
    print(df)
    df.to_excel(outpath+ '\\result.xlsx')
    # df["affinity(kcal/mol)"] = pd.to_numeric(df["affinity(kcal/mol)"],errors='coerce')
    # df["RMSD l.b."] = pd.to_numeric(df["RMSD l.b."],errors='coerce')
    # df["RMSD u.b.()"] = pd.to_numeric(df["RMSD u.b.()"],errors='coerce')
    # c=df.sort_values(by=['affinity(kcal/mol)'], ascending=True)
    # # print (c)
    # # writer = pd.ExcelWriter('result.xlsx')
    # # os.chdir(outpath)
    # # print(os.getcwd())
    # # c.to_excel(writer,float_format='%.5f')
    # c.to_csv(outpath+ '\\result.csv')
    # # writer.save()
    # print("输出成功")