python读取不同文件夹里的目标xls文件，汇总写入一个csv文件

# @Author: BigMoore
# @Time: 2022/3/29 17:59
import importlib
import sys
import csv
import os
import traceback
import xlrd


def Profiles(dir, ids, profiles):
    for town_dir in os.listdir(dir):
        newDir = os.path.join(dir, town_dir)
        if os.path.isfile(newDir):
            profiles.append(newDir)
        else:
            Profiles(newDir, ids, profiles)
    return profiles


def Profiles2(dir, ids, profiles):
    for town_dir in os.listdir(dir):
        if '青城山' in town_dir:
            mount_dir = os.path.join(dir, '青城山镇')
            for grop in os.listdir(mount_dir):
                grop_dir = os.path.join(mount_dir, grop)
                for proj_file in os.listdir(grop_dir):
                    # ids存放项目编号
                    ids.append(proj_file[0:19])
                    # C:\Users\Moore\Desktop\已核对附表\青城山镇\1组\510181012005JB99057邱伟等
                    proj_file_path = os.path.join(grop_dir, proj_file)
                    profiles.append(proj_file_path)
        else:
            # 进入下一级、镇或街道的文件夹
            newDir = os.path.join(dir, town_dir)
            # os.listdir(*)输出所有文件和文件夹
            for proj in os.listdir(newDir):
                ids.append(proj[0:19])
                proj_file_path = os.path.join(newDir, proj)
                profiles.append(proj_file_path)
    return ids, profiles


def readExcel(path, writer, identifier):
    try:
        # 连接excel，连接工作簿
        # 打开工作表,选定要读的表,(index+1)
        # 设置开始读取数据行
        # 遍历数据，设置循环结束条件，读入，结束
        workbook = xlrd.open_workbook(path)
        worksheet = workbook.sheet_by_index(0)
        rowNum = 5
        # worksheet.nrows:数据有效行
        while rowNum < worksheet.nrows:
            row_info = worksheet.row_values(rowNum)
            # 去掉第一列序号
            row_info = row_info[1:]
            # 若有一行没有这3项信息的一项，则跳出if判断，执行rowNum++
            if not (row_info[0] == '' and row_info[8] == '' and row_info[-1] == ''):
                if row_info[0] != '':
                    # 将编号放到第一列
                    row_info.insert(0, identifier)
                else:
                    row_info.insert(0, ' ')
                writer.writerow(row_info)
            rowNum += 1
    except Exception:
        print('Error ' + path + ' ' + traceback.format_exc())


def xlsProcess(dir, path):
    ids = []
    profiles = []
    # Profiles(dir, ids, profiles)
    Profiles2(dir, ids, profiles)
    print(len(profiles))
    # print(os.listdir(profiles[0]))
    print(len(ids))
    # 查看所有文件和编号
    # for item in profiles:
    #     print(item)
    # for item in ids:
    #     print(item)
    f = open(path, 'w', encoding='utf-8', newline='')
    writer = csv.writer(f)
    # 1 遍历所有文件
    # 2 取对应编号
    # 3 显示所有项目所在下的文件，判断'安置房用地'是否在path内
    # 4 有的话通过readExcel写入
    # 遍历所有项目
    for i in range(len(profiles)):
        identifier = ids[i]
        for proj in os.listdir(profiles[i]):
            if "安置房用地" in proj:
                path = os.path.join(profiles[i], proj)
                print(path)
                readExcel(path, writer, identifier)


if __name__ == '__main__':
    importlib.reload(sys)
    dir = r'C:\Users\Moore\Desktop\已核对附表'
    csv_path = r'C:\Users\Moore\Desktop\已核对附表写入文件\安置房总表.csv'
    xlsProcess(dir, csv_path)

    # print(os.listdir(dir))
    # mounDir = os.path.join(dir, '青城山镇')
    # print(mounDir)
    # print(os.listdir(mounDir))