使用修改后的外部链接保存后，Openpyxl 会损坏 Excel 工作簿

Question

我遇到了 openpyxl 的问题，该问题似乎导致我的 Excel 工作簿损坏。我使用的是 openpyxl 版本 3.0.10。

这是我的代码的概述：

import openpyxl
import glob
from tkinter import Tk
from tkinter.filedialog import askdirectory
from openpyxl import __version__

# function to get existing data sources in a workbook
def get_existing_data_sources(file_path):
    
    # Set data sources
    data_sources = {}

    # Try getting external links
    try:
        workbook = openpyxl.load_workbook(excel_file_path)
        items = workbook._external_links

        # Iterate through list and extract url
        for index, item in enumerate(items):

            # reformat link string
            Mystr = workbook._external_links[index].file_link.Target
            Mystr = Mystr.replace("file:///","")

            # update key-pair
            data_sources[index] = Mystr.replace("%20"," ")

    except Exception as e:
        print(f"An error occurred while extracting data sources: {str(e)}")

    # return statement
    return(data_sources, workbook)


# Function to modify the existing data sources in the workbook
def modify_data_source_links(data_sources, workbook):
    try:
        # Flag false
        modified = False
        
        # get workbook external links (unformatted links)
        items = workbook._external_links

        # Copy data sources to have them relinked
        modified_data_sources = data_sources.copy()

        # Correct data sources to new pattern
        for i in modified_data_sources:
            modified_data_sources[i] = modified_data_sources[i].replace('<OLD LINK>','<NEW LINK>')

        # Enumerate through external links and replace values based on the link index in the cell
        for index, item in enumerate(items):
            link_str = data_sources.get(index)

            if link_str:
                # Reformat the new link string
                new_link = modified_data_sources[index]

                # Reformat newlink (make spaces to %20)
                new_link = new_link.replace(" ","%20")

                # Replace link target
                workbook._external_links[index].file_link.Target = new_link

                # flag modified as true
                modified = True
                
        if modified:
            print("Data source links modified successfully.")
        else:
            print("No data source links matching the old data source found.")
    
    # Return Error
    except Exception as e:
        print(f"An error occurred: {str(e)}")
        
        
if __name__ == "__main__":
    
    # Path to the workbook
    path = askdirectory(title='Select Folder') # shows dialog box and return the path
    print(path)  
    excel_file_paths = glob.glob('{}/*.xlsx'.format(path), recursive = True)
    
    # Process each file
    for excel_file_path in excel_file_paths:
        
        # get existing data sources
        existing_data_sources, workbook = get_existing_data_sources(excel_file_path)

        # if data sources do not exist, prompt message
        if not existing_data_sources:
            print("No data source links found in the workbook. Moving on...")
            
        # else relink the data sources
        else:
            print("Existing data source links:")
            for i, data_source in enumerate(existing_data_sources, 1):
                print(f"{i}. {data_source}")

            modify_data_source_links(existing_data_sources, workbook)
            
            # Save workbook
            excel_file_path = excel_file_path.replace('\\','/')
            workbook.save(excel_file_path)
            workbook.close()
    
            print('Modified the links in: {}, moving on...'.format(excel_file_path))

    print('Script completed!')
        

代码运行没有出现任何错误，并且工作簿已成功生成。但是，当我尝试写入工作簿时，Excel 显示一条错误消息，指出文件已损坏并提示进行恢复。在 Excel 工作簿中处理外部链接时，是否有其他人遇到过 openpyxl 的此问题？我是否在代码中遗漏了某些内容，或者是否有解决方法可以防止使用 openpyxl 修改外部链接时工作簿损坏？任何见解或解决方案将不胜感激。谢谢！

Answer 1

试试这个方法： 工作簿 = load_workbook(文件名= file_path,data_only=True,keep_links=False)