Python：在特定文件夹上将多个/多个 .docx 文件从 ANSI 转换为 UTF-8

import os
import zipfile
import io
import chardet

# Set the folder path where the .docx files are located
folder_path = os.getcwd()

# Loop through all files in the folder
for filename in os.listdir(folder_path):
    if filename.endswith(".docx"):
        # Open the .docx file
        file_path = os.path.join(folder_path, filename)
        try:
            with zipfile.ZipFile(file_path) as docx_file:
                # Read the contents of the document.xml file
                xml_content = docx_file.read('word/document.xml')
        except Exception as e:
            print(f"Error opening {file_path}: {e}")
            continue

        # Detect the current encoding of the file
        detected_encoding = chardet.detect(xml_content)['encoding']
        print(f"{file_path} is encoded in {detected_encoding}")
        # If the detected encoding is not UTF-8, save the file in UTF-8 format
        if detected_encoding != "utf-8":
            new_filename = os.path.splitext(filename)[0] + "_utf8.docx"
            new_file_path = os.path.join(folder_path, new_filename)
            with zipfile.ZipFile(new_file_path, "w") as docx_file:
                # Write the contents of the modified document.xml file
                docx_file.writestr('word/document.xml', xml_content.decode(detected_encoding).encode('utf-8'))
            print(f"Converted {file_path} from {detected_encoding} to UTF-8 and saved as {new_file_path}")
        else:
            print(f"{file_path} is already in UTF-8 format")