Python--通过索引excel表将文件进行文件夹分类的脚本+读取指定目录下所有文件名的脚本

Posted 2021-10-20 pureqh

1.通过索引excel表将文件进行文件夹分类的脚本,此脚本由于将ip和id对应并生成对应id的文件夹将文件进行分类，也可以任意规定表格内容，通过vul_sc_ip.txt和xlsx文件进行索引。

# -*- coding:utf8 -*-
import sys
import os
import pandas as pd
import shutil
import stat

def find(path,ip):
    # open the excel file
    df = pd.read_excel(path)
    if ip in df["ip1"].values:
        s1 = df[df["ip1"]==ip]["man"].values.tolist()[0]
        return {s1:ip}
    else:
        return 0
def mkdir(path,filename,desname):
    path = path.strip()
    path = path.rstrip("\\")
    path_e = str(path) + ‘\\‘ + filename.decode(‘utf-8‘) + ‘_‘ +  desname
    isExists = os.path.exists(path_e)
    if not isExists:
        os.makedirs(path_e)
        print (path_e + ‘ 创建成功‘.decode(‘utf-8‘))
        return path_e
    else:
        print (path_e + ‘ 目录已存在‘.decode(‘utf-8‘))
        return path_e

def save(rootdir,newpath,ip):
    list = os.listdir(rootdir)
    ip_name = ip+‘.html‘
    all_path_name = []
    for i in range(0, len(list)):
        path = os.path.join(rootdir, list[i])
        all_path_name.append(os.path.basename(path))
    s_media = os.path.join(rootdir,‘media‘)
    d_media = os.path.join(newpath,‘media‘)
    isExists_media = os.path.exists(d_media)
    if not isExists_media:
        shutil.copytree(s_media,d_media)
    else:
        print (d_media + ‘ 目录已存在‘.decode(‘utf-8‘))
    if ip_name in all_path_name:
        dst_path = os.path.join(rootdir,ip_name)
        newfp = os.path.join(newpath,ip_name)
        isExists_newfp = os.path.exists(newfp)
        if not isExists_newfp:
            shutil.copy(dst_path, newfp)
            print ("copy %s -> %s"%(dst_path,newfp))
        else:
            print (newfp + ‘ 文件已存在‘.decode(‘utf-8‘))
    else:
        return 0

if __name__ == "__main__":
    
    path_report = "D:"#需要分类的文件路径
    file_name = "文件名"#每个文件夹的名字
    path_xlsx = "D:/ip.xlsx"#索引表路径
    host_path = "D:/"#保存文件夹的位置
    f = open("vul_sc_ip.txt", ‘r‘)#索引的txt文件，由于此脚本是根据ip索引的所以txt内为IP地址
    all_ip = f.readlines()
    f.close()
    for each_ip in all_ip:
        dict_name = find(path_xlsx,each_ip.strip(‘\n‘))
        for des_name in dict_name.keys():
            new_path = mkdir(path_report,file_name,des_name)
            #print new_path
            save(host_path,new_path,dict_name.get(des_name))

2.读取指定目录下所有文件名的脚本:

#!/usr/bin/env python
# -*- coding:utf8 -*-
 
      
import os  

f = open("ip.txt", ‘w+‘)
   
def file_name(file_dir):   
    for root, dirs, files in os.walk(file_dir):  
        
        print >>f,(files) #当前路径下所有非目录子文件

file_name(‘D:/‘)