使用openpyxl追加写入Excel的成功案例，以及遇到的坑

1. 想实现的功能

程序循环多次，每次向指定的excel中追加写入数据，
想看成功方案，可以直接跳转到：Try-3

2. 尝试方法

Try-1：

使用其他网友提供的openpyxl代码：参考链接, 代码如下：

# pandas 不覆盖写入 excel 同一张 Sheet 表
import pandas as pd
from openpyxl import load_workbook
 
def append_df_to_excel(filename, df, sheet_name='Sheet1', startrow=None,
                       truncate_sheet=False, 
                       **to_excel_kwargs):
    """
    Append a DataFrame [df] to existing Excel file [filename]
    into [sheet_name] Sheet.
    If [filename] doesn't exist, then this function will create it.
    Parameters:
      filename : File path or existing ExcelWriter
                 (Example: '/path/to/file.xlsx')
      df : dataframe to save to workbook
      sheet_name : Name of sheet which will contain DataFrame.
                   (default: 'Sheet1')
      startrow : upper left cell row to dump data frame.
                 Per default (startrow=None) calculate the last row
                 in the existing DF and write to the next row...
      truncate_sheet : truncate (remove and recreate) [sheet_name]
                       before writing DataFrame to Excel file
      to_excel_kwargs : arguments which will be passed to `DataFrame.to_excel()`
                        [can be dictionary]
    Returns: None
    """
   # from openpyxl import load_workbook
 
   # import pandas as pd
 
    # ignore [engine] parameter if it was passed
    if 'engine' in to_excel_kwargs:
        to_excel_kwargs.pop('engine')
 
    writer = pd.ExcelWriter(filename, engine='openpyxl')
 
    # Python 2.x: define [FileNotFoundError] exception if it doesn't exist 
    try:
        FileNotFoundError
    except NameError:
        FileNotFoundError = IOError
 
 
    try:
        # try to open an existing workbook
        writer.book = load_workbook(filename)
 
        # get the last row in the existing Excel sheet
        # if it was not specified explicitly
        if startrow is None and sheet_name in writer.book.sheetnames:
            startrow = writer.book[sheet_name].max_row
 
        # truncate sheet
        if truncate_sheet and sheet_name in writer.book.sheetnames:
            # index of [sheet_name] sheet
            idx = writer.book.sheetnames.index(sheet_name)
            # remove [sheet_name]
            writer.book.remove(writer.book.worksheets[idx])
            # create an empty sheet [sheet_name] using old index
            writer.book.create_sheet(sheet_name, idx)
 
        # copy existing sheets
        writer.sheets = {ws.title:ws for ws in writer.book.worksheets}
    except FileNotFoundError:
        # file does not exist yet, we will create it
        pass
 
    if startrow is None:
        startrow = 0
 
    # write out the new sheet
    df.to_excel(writer, sheet_name, **to_excel_kwargs)
 
    # save the workbook
    writer.save()

出现问题：

一开始运行是OK的，但是后来总是出现两个错误：

• 控制台报错： BadZipFile: File is not a zip file
• 打开excel报错：Excel无法打开文件xxx.xlsx，因为文件格式或文件扩展名无效。请确定文件未损坏

解决办法：
找了N多种方法都没解决，所以放弃了

Try-2：

读取：xlrd
写入：xlwt
修改（追加写入）：xlutils
同样参照其他网友提供的代码：参考链接， 代码如下：

import xlrd
import xlwt
from xlutils.copy import copy
 
def write_excel_xls(path, sheet_name, value):
    index = len(value)  # 获取需要写入数据的行数
    workbook = xlwt.Workbook()  # 新建一个工作簿
    sheet = workbook.add_sheet(sheet_name)  # 在工作簿中新建一个表格
    for i in range(0, index):
        for j in range(0, len(value[i])):
            sheet.write(i, j, value[i][j])  # 像表格中写入数据（对应的行和列）
    workbook.save(path)  # 保存工作簿
    print("xls格式表格写入数据成功！")
 
 
def write_excel_xls_append(path, value):
    index = len(value)  # 获取需要写入数据的行数
    workbook = xlrd.open_workbook(path)  # 打开工作簿
    sheets = workbook.sheet_names()  # 获取工作簿中的所有表格
    worksheet = workbook.sheet_by_name(sheets[0])  # 获取工作簿中所有表格中的的第一个表格
    rows_old = worksheet.nrows  # 获取表格中已存在的数据的行数
    new_workbook = copy(workbook)  # 将xlrd对象拷贝转化为xlwt对象
    new_worksheet = new_workbook.get_sheet(0)  # 获取转化后工作簿中的第一个表格
    for i in range(0, index):
        for j in range(0, len(value[i])):
            new_worksheet.write(i+rows_old, j, value[i][j])  # 追加写入数据，注意是从i+rows_old行开始写入
    new_workbook.save(path)  # 保存工作簿
    print("xls格式表格【追加】写入数据成功！")
 
 
def read_excel_xls(path):
    workbook = xlrd.open_workbook(path)  # 打开工作簿
    sheets = workbook.sheet_names()  # 获取工作簿中的所有表格
    worksheet = workbook.sheet_by_name(sheets[0])  # 获取工作簿中所有表格中的的第一个表格
    for i in range(0, worksheet.nrows):
        for j in range(0, worksheet.ncols):
            print(worksheet.cell_value(i, j), "\t", end="")  # 逐行逐列读取数据
        print()
 
 
book_name_xls = 'xls格式测试工作簿.xls'
 
sheet_name_xls = 'xls格式测试表'
 
value_title = [["姓名", "性别", "年龄", "城市", "职业"],]
 
value1 = [["张三", "男", "19", "杭州", "研发工程师"],
          ["李四", "男", "22", "北京", "医生"],
          ["王五", "女", "33", "珠海", "出租车司机"],]
 
value2 = [["Tom", "男", "21", "西安", "测试工程师"],
          ["Jones", "女", "34", "上海", "产品经理"],
          ["Cat", "女", "56", "上海", "教师"],]
 
 
write_excel_xls(book_name_xls, sheet_name_xls, value_title)
write_excel_xls_append(book_name_xls, value1)
write_excel_xls_append(book_name_xls, value2)
read_excel_xls(book_name_xls)

出现问题：
xlwt最多只能写入65535行，255列，满足不了我的需求

解决办法：
还是回到openpyxl

Try-3：

# 使用openpyxl追加写入数据到Excel
import openpyxl
import os

def create_excel_xlsx(path, sheet_name):
    workbook = openpyxl.Workbook()
    sheet = workbook.active
    sheet.title = sheet_name
    workbook.save(path)

def write_excel_xlsx_append(path, value, truncate_sheet=False):
    # 如果不存在就创建该excel
    if not os.path.exists(path):
        create_excel_xlsx(path, 'Sheet1')

    value = value.values #将dataframe转为array
    data = openpyxl.load_workbook(path)
    # 取第一张表
    sheetnames = data.sheetnames
    sheet = data[sheetnames[0]]
    sheet = data.active
    if(truncate_sheet): #truncate_sheet为True，覆盖原表中的数据
        startrows = 0
    else:
        # print(sheet.title)  # 输出表名
        startrows = sheet.max_row  # 获得行数
    index = len(value)
    for i in range(0, index):
        for j in range(0, len(value[i])):
            sheet.cell(row=startrows + i + 1, column=j + 1, value=str(value[i][j]))
    data.save(path)
    print("xlsx格式表格追加写入数据成功！")

def read_excel_xlsx(path, sheet_name):
    workbook = openpyxl.load_workbook(path)
    # sheet = wb.get_sheet_by_name(sheet_name)这种方式已经弃用，不建议使用
    sheet = workbook[sheet_name]
    for row in sheet.rows:
        for cell in row:
            print(cell.value, "\t", end="")
        print()

book_name_xlsx = 'xlsx格式测试工作簿.xlsx'
sheet_name_xlsx = 'xlsx格式测试表'
value3 = [["111", "女", "66", "石家庄", "运维工程师"],
          ["222", "男", "55", "南京", "饭店老板"],
          ["333", "女", "27", "苏州", "保安"], ]

write_excel_xlsx_append(book_name_xlsx, sheet_name_xlsx, value3)
read_excel_xlsx(book_name_xlsx, sheet_name_xlsx)

至此成功！

后记：期间也尝试过要用xlxswriter，但是遇到一个问题，

用上面这个方法死活读不到原有的sheet，所以无法实现追加数据，看到Stack Overflow上有个老哥跟我一样情况，但是没有正确的answer，如果有人知道原因，欢迎answer：Stack overflow 问题

---

后来我自己Answer掉了:

data = openpyxl.load_workbook(path)
# 取第一张表
sheetnames = data.sheetnames
sheet = data[sheetnames[0]]

sheet = wb.get_sheet_by_name(sheet_name)这种方式已经弃用，不建议使用，可以直接使用wb[sheetname]

---

在此一并感谢大佬们的博文，为我解决问题提供思路！