python 统计目录下文件以及读写xlsx表格

背景：ovirt平台数据库故障，数据库恢复成两个月前的数据，平台数据管理虚拟机变少，出现很多野虚拟机-------脱离平台管理，在数据域下有许多磁盘文件目录，需要统计数据整合。

1、存储域下目录文件整合

目录下有磁盘目录928个，每个目录下至少有3个文件

其中meta文件中有disk的一些信息，可以做分类

# !/usr/bin/env python
# -*- coding: utf-8 -*-
import os
import json
import xlwt

DomainDir = "/xxxxxxxxxx/"


class ImageInfo(object):
    # 获取目录下文件
    @staticmethod
    def find_all_image_file(file_path):
        images_list = []
        three_file_list = []
        for root, dirs, files in os.walk(file_path, topdown=False):
            image_dict = {}
            image_dict["image_id"] = root.split(file_path)[-1]
            files.sort()
            image_dict["files_list"] = files
            images_list.append(image_dict)
            if len(files) == 3:
                three_file_list.append(image_dict)

        # with open('/home/test_data', 'w') as dict_file:
        #     dict_file.writelines(str(line) + '\n' for line in images_list)
        # with open('/home/test_data2', 'w') as dict_file:
        #     dict_file.writelines(str(line) + '\n' for line in three_file_list)
        return images_list, three_file_list
    # 读取meta文件，分类信息
    @staticmethod
    def get_image_detail(image_info_list):
        detail_info = []
        for file_info in image_info_list:
            meta_file = DomainDir + file_info.get('image_id') + '/' + file_info.get('files_list')[-1]
            with open(meta_file, 'r') as file_to_read:
                for line in file_to_read.readlines():
                    if "DESCRIPTION" in line:
                        try:
                            file_info["DiskAlias"] = json.loads(line.strip('\n').split("=")[-1]).get('DiskAlias') if "DiskAlias" in line else None
                        except:
                            file_info["DiskAlias"] = None
                        try:
                            file_info["DiskDescription"] = json.loads(line.strip('\n').split("=")[-1]).get('DiskDescription') if "DiskDescription" in line else None
                        except:
                            file_info["DiskDescription"] = None
                    if "DISKTYPE" in line:
                        file_info["DISKTYPE"] = line.strip('\n').split("=")[-1]
                    if "VOLTYPE" in line:
                        file_info["VOLTYPE "] = line.strip('\n').split("=")[-1]
            detail_info.append(file_info)
            file_info["files_list"] = file_info.get("files_list")[0]
        # with open('/home/test_data3', 'w') as dict_file:
        #     dict_file.writelines(str(line) + '\n' for line in detail_info)
        return detail_info


if __name__ == '__main__':
    all_image_info, three_file_info = ImageInfo.find_all_image_file(DomainDir)
    image_detail_info = ImageInfo.get_image_detail(three_file_info)
    # 信息写入xls文件中
    wb = xlwt.Workbook(encoding='utf-8')
    ws = wb.add_sheet('image_info', cell_overwrite_ok=True)
    columns = list(image_detail_info[0].keys())
    for j, col in enumerate(columns):
        ws.write(0, j, col)
    for i, row in enumerate(image_detail_info, 1):
        for j, col in enumerate(columns):
            ws.write(i, j, row[col])
    wb.save('data.xls')

2、目录下文件获取后，简单过滤下目录下有三个文件的目录，然后和之前的迁移列表匹配，过滤出可以恢复的虚拟机写入表格

# !/usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import print_function
import xlrd
import xlwt

DomainDir = "/XXX/"


def read_xlsx(book, i):
    sheet = book.sheets()[i]
    nor = sheet.nrows
    nol = sheet.ncols
    info_list = []
    for i in range(1, nor):
        dict_info = {}
        for j in range(nol):
            title = sheet.cell_value(0, j).encode('utf-8')
            value = sheet.cell_value(i, j).encode('utf-8')
            dict_info[title] = value
        info_list.append(dict_info)
    return info_list


if __name__ == '__main__':
    book = xlrd.open_workbook("upload_disk.xlsx")
    vm_upload_info_list = read_xlsx(book, 0)
    vm_migration_list = read_xlsx(book, 1)
    vm_merge_info = {}
    vm_not_merge_info = {}
    for vm_migration in vm_migration_list:
        vm_disk_list=[]
        for vm_upload_info in vm_upload_info_list:
            vm_upload_disk_name = vm_upload_info.get("DiskAlias")
            vm_name = None
            if "systemdisk" in vm_upload_disk_name:
                vm_name = vm_upload_disk_name.split("_systemdis")[0]
            if "datadisk" in vm_upload_disk_name:
                vm_name = vm_upload_disk_name.split("_datadis")[0]
            if vm_migration.get("迁移后VM名称") == vm_name:
                vm_disk_list.append(vm_upload_info)
        if len(vm_disk_list) > 0:
            vm_merge_info[vm_migration.get("迁移后VM名称")] = vm_disk_list
    vm_merge_info_list = []
    for key, value in vm_merge_info.items():
        value[0]["vm_name"] = key
        vm_merge_info_list.append(value[0])
    print (vm_merge_info_list[0])
    wb = xlwt.Workbook(encoding='utf-8')
    ws = wb.add_sheet('image_info', cell_overwrite_ok=True)
    columns = list(vm_merge_info_list[0].keys())
    for j, col in enumerate(columns):
        ws.write(0, j, col)
    for i, row in enumerate(vm_merge_info_list, 1):
        for j, col in enumerate(columns):
            ws.write(i, j, row[col])
    wb.save('merge_info.xls')

3、后续根据过滤的虚拟机，调用ovirt sdk接口，upload磁盘，创建vm，挂盘与之前迁移脚本雷同，不再累述。