<随便写>比较两个文件夹下所有文件的文件名和内容(哈希值)

import os
# 导入工作簿
import openpyxl
# 哈希值
import hashlib


def get_Filelist(dir, Filelist):
    ‘‘‘
    :param dir: 文件夹的路径,形如：E:\\software\\Notepad++
    :param Filelist:列表,形如:[]
    :return:返回该文件夹下所有文件的路径
    ‘‘‘
    newDir = dir
    if os.path.isfile(dir):
        Filelist.append(dir)
        # # 若只是要返回文件文，使用这个
        # Filelist.append(os.path.basename(dir))
    elif os.path.isdir(dir):
        for s in os.listdir(dir):
            # 如果需要忽略某些文件夹，使用以下代码
            # if s == "xxx":
            # continue
            newDir = os.path.join(dir, s)
            get_Filelist(newDir, Filelist)
    return Filelist


def name_hash_list(fake_file_list, real_file_list):
    ‘‘‘
    :param fake_file_list:私服文件路径
    :param real_file_list:官服文件路径
    :return:私服和官服哈希文件列表
    ‘‘‘
    fake_hash_list = []
    real_hash_list = []
    fake_name_list = []
    real_name_list = []
    for i in fake_file_list:
        with open(i, "rb") as f:
            bytes = f.read()  # read file as bytes
            fake_hash = hashlib.md5(bytes).hexdigest()
            fake_hash_list.append(fake_hash)
            # 不区分大小写
            fake_name_list.append(os.path.split(i)[-1].upper())
    for i in real_file_list:
        with open(i, "rb") as f:
            bytes = f.read()  # read file as bytes
            real_hash = hashlib.md5(bytes).hexdigest()
            real_hash_list.append(real_hash)
            # 不区分大小写
            real_name_list.append(os.path.split(i)[-1].upper())
    return fake_hash_list, fake_name_list, real_hash_list, real_name_list


def select_name_hash(fake_hash_list, fake_name_list, real_hash_list, real_name_list):
    # 同名且同哈希
    result_list_1 = []
    # 同名不同哈希
    result_list_2 = []
    # 不同名同哈希
    result_list_3 = []
    # 不同名不同哈希
    result_list_4 = []
    for i in range(len(fake_hash_list)):
        if fake_name_list[i] in real_name_list and fake_hash_list[i] in real_hash_list:
            real_name = fake_name_list[i]
            real_hash = fake_hash_list[i]
            result_list_1.append([fake_name_list[i], real_name, fake_hash_list[i], real_hash])
        elif fake_name_list[i] in real_name_list and fake_hash_list[i] not in real_hash_list:
            real_name = fake_name_list[i]
            real_hash = real_hash_list[real_name_list.index(real_name)]
            result_list_2.append([fake_name_list[i], real_name, fake_hash_list[i], real_hash])
        elif fake_name_list[i] not in real_name_list and fake_hash_list[i] in real_hash_list:
            real_hash = fake_hash_list[i]
            # 存在不同名,但是同时有很多重复的情况
            real_name = real_name_list[real_hash.index(real_hash)]
            result_list_3.append([fake_name_list[i], real_name, fake_hash_list[i], real_hash])
        else:
            result_list_4.append([fake_name_list[i], 0, fake_hash_list[i], 0])
    return result_list_1, result_list_2, result_list_3, result_list_4


def write_xlsx(dir, name):
    # 初始化表格1
    wb = openpyxl.Workbook()
    ws = wb.active
    # 表名
    ws.title = name
    id = 1
    for i in range(1, len(dir) + 1):
        ws.cell(row=i, column=1, value=id)
        ws.cell(row=i, column=2, value=dir[i - 1][0])
        ws.cell(row=i, column=3, value=dir[i - 1][1])
        ws.cell(row=i, column=4, value=dir[i - 1][2])
        ws.cell(row=i, column=5, value=dir[i - 1][3])
        id += 1
    wb.save(str(name) + ‘.xlsx‘)


if __name__ == ‘__main__‘:
    # 私服文件夹路径
    fake_file_name = ‘F:\\火龙服务器文件\\热血传奇\\wav‘
    # 官服文件夹路径
    real_file_name = ‘E:\\doc\\Legend of mir\\wav‘
    # 1. 找出该文件夹下所有文件路径
    fake_file_list = get_Filelist(fake_file_name, [])
    real_file_list = get_Filelist(real_file_name, [])
    print(len(fake_file_list), len(real_file_list))
    # 2.找出路径对应的文件名列表和哈希列表
    fake_hash_list, fake_name_list, real_hash_list, real_name_list = name_hash_list(fake_file_list, real_file_list)
    # print(len(fake_hash_list))
    # 3.判断名字和哈希是否相同情况(可以使用文件名和哈希是否在官服的列表里)
    result_list_1, result_list_2, result_list_3, result_list_4 = select_name_hash(fake_hash_list, fake_name_list,
                                                                                  real_hash_list, real_name_list)
    # 4.写入表格
    if len(result_list_1) > 0:
        write_xlsx(result_list_1, "同名同哈希")
    else:
        print("不存在同名同哈希的文件")
    if len(result_list_2) > 0:
        write_xlsx(result_list_2, "同名不同哈希")
    else:
        print("不存在同名不同哈希的文件")
    if len(result_list_3) > 0:
        write_xlsx(result_list_3, "不同名同哈希")
    else:
        print("不存在不同名同哈希的文件")
    if len(result_list_4) > 0:
        write_xlsx(result_list_4, "不同名不同哈希")
    else:
        print("不存在不同名不同哈希的文件")

    # 5.总数统计
    result_1 = len(result_list_1) / len(fake_hash_list)
    result_2 = len(result_list_2) / len(fake_hash_list)
    result_3 = len(result_list_3) / len(fake_hash_list)
    result_4 = len(result_list_4) / len(fake_hash_list)

    print("总文件数:{},同名同哈希数:{},占比数:{:.2%}".format(len(fake_hash_list), len(result_list_1), result_1))
    print("总文件数:{},同名不同哈希数:{},占比数:{:.2%}".format(len(fake_hash_list), len(result_list_2), result_2))
    print("总文件数:{},不同名同哈希数:{},占比数:{:.2%}".format(len(fake_hash_list), len(result_list_3), result_3))
    print("总文件数:{},不同名不同哈希数:{},占比数:{:.2%}".format(len(fake_hash_list), len(result_list_4), result_4))