Python实现批量删除Excel前缀工具的完整指南

pip install openpyxl

import openpyxl
from openpyxl.utils import get_column_letter
import os

def remove_prefix_from_column(file_path, sheet_name, column_index, prefix_length=None, delimiter=None):
    """
    批量删除Excel指定列单元格内容的前缀
    
    参数:
        file_path: Excel文件路径
        sheet_name: 工作表名称
        column_index: 列索引(从1开始)
        prefix_length: 要删除的前缀长度(可选)
        delimiter: 分隔符，删除分隔符前的内容(可选)
    """
    # 加载工作簿
    wb = openpyxl.load_workbook(file_path)
    
    try:
        # 获取工作表
        sheet = wb[sheet_name]
    except KeyError:
        print(f"错误：工作表 '{sheet_name}' 不存在")
        return False
    
    # 获取列字母
    column_letter = get_column_letter(column_index)
    
    # 遍历列中的每个单元格
    for cell in sheet[column_letter]:
        if cell.value and isinstance(cell.value, str):
            original_value = cell.value
            # 根据参数选择处理方式
            if prefix_length:
                # 按固定长度删除前缀
                if len(original_value) > prefix_length:
                    cell.value = original_value[prefix_length:]
            elif delimiter:
                # 按分隔符删除前缀
                if delimiter in original_value:
                    cell.value = original_value.split(delimiter)[-1]
    
    # 保存修改
    new_file_path = f"{os.path.splitext(file_path)[0]}_modified.xlsx"
    wb.save(new_file_path)
    print(f"处理完成，新文件已保存为: {new_file_path}")
    return True

# 使用示例
if __name__ == "__main__":
    # 按固定长度删除前缀
    remove_prefix_from_column("data.xlsx", "Sheet1", 2, prefix_length=4)
    
    # 按分隔符删除前缀
    # remove_prefix_from_column("data.xlsx", "Sheet1", 2, delimiter="-")

def advanced_remove_prefix(cell_value, prefix_length=None, delimiter=None, prefix_str=None):
    """
    高级前缀处理函数
    """
    if not cell_value or not isinstance(cell_value, str):
        return cell_value
    
    if prefix_length:
        if len(cell_value) > prefix_length:
            return cell_value[prefix_length:]
    
    if delimiter:
        if delimiter in cell_value:
            return cell_value.split(delimiter)[-1]
    
    if prefix_str:
        if cell_value.startswith(prefix_str):
            return cell_value[len(prefix_str):]
    
    return cell_value

def batch_process_files(folder_path, sheet_name, column_index, **kwargs):
    """
    批量处理文件夹中的所有Excel文件
    """
    for filename in os.listdir(folder_path):
        if filename.endswith(".xlsx") or filename.endswith(".xls"):
            file_path = os.path.join(folder_path, filename)
            print(f"正在处理文件: {filename}")
            remove_prefix_from_column(file_path, sheet_name, column_index, **kwargs)

import PySimpleGUI as sg

def create_gui():
    layout = [
        [sg.Text("Excel文件路径:"), sg.Input(), sg.FileBrowse()],
        [sg.Text("工作表名称:"), sg.InputText("Sheet1")],
        [sg.Text("列索引:"), sg.InputText("1")],
        [sg.Radio("按长度删除", "prefix_type", default=True, key="prefix_length"), 
         sg.InputText("4", size=(5,1))],
        [sg.Radio("按分隔符删除", "prefix_type", key="delimiter"), 
         sg.InputText("-", size=(5,1))],
        [sg.Button("执行"), sg.Button("退出")]
    ]
    
    window = sg.Window("Excel前缀批处理工具", layout)
    
    while True:
        event, values = window.read()
        if event in (None, "退出"):
            break
        if event == "执行":
            file_path = values[0]
            sheet_name = values[1]
            column_index = int(values[2])
            
            if values["prefix_length"]:
                prefix_length = int(values[3])
                remove_prefix_from_column(file_path, sheet_name, column_index, 
                                         prefix_length=prefix_length)
            else:
                delimiter = values[4]
                remove_prefix_from_column(file_path, sheet_name, column_index, 
                                         delimiter=delimiter)
    
    window.close()

wb = openpyxl.load_workbook(file_path, read_only=True)

from openpyxl import Workbook
wb_new = Workbook(write_only=True)
ws_new = wb_new.create_sheet()
# 添加处理后的数据
wb_new.save(new_file_path)

import re

def clean_string(value):
    if not value or not isinstance(value, str):
        return value
    # 替换各种空白字符为单个空格
    return re.sub(r'\s+', ' ', value).strip()

with open('data.xlsx', 'rb') as f:
    # 检测文件编码
    rawdata = f.read()
    result = chardet.detect(rawdata)
    encoding = result['encoding']
    
# 重新以正确编码打开文件

remove_prefix_from_column("purchase_orders.xlsx", "Orders", 3, delimiter="-")

remove_prefix_from_column("employees.xlsx", "Sheet1", 5, prefix_length=3)

remove_prefix_from_column("products.xlsx", "SKU", 2, delimiter="-")

import logging

logging.basicConfig(filename='excel_processor.log', level=logging.INFO)

def log_change(original, modified):
    logging.info(f"Original: {original} → Modified: {modified}")

try:
    wb = openpyxl.load_workbook(file_path)
except Exception as e:
    print(f"无法加载文件 {file_path}: {str(e)}")
    return False

total_cells = len(sheet[column_letter])
processed = 0
for cell in sheet[column_letter]:
    processed += 1
    if processed % 100 == 0:
        print(f"已处理 {processed}/{total_cells} 单元格...")