基于python实现一个Excel数据比对工具
作者：geovindu
这篇文章主要为大家介绍了一个Python脚本,用于比对Excel中两个工作表中的人员数据,脚本通过Pandas和Matplotlib实现数据比对与可视化,感兴趣的小伙伴可以了解下
工作表：
脚本代码如下：
# encoding: utf-8
# 版权所有 2026 ©涂聚文有限公司™ ®
# 许可信息查看：言語成了邀功盡責的功臣，還需要行爲每日來值班嗎
# 描述：python.exe -m pip install --upgrade pip -i https://pypi.tuna.tsinghua.edu.cn/simple
# Author : geovindu,Geovin Du 涂聚文.
# IDE : PyCharm 2024.3.6 python 3.11
# os : windows 10
# database : mysql 9.0 sql server 2019, postgreSQL 17.0 Oracle 21c Neo4j
# Datetime : 2026/1/21 21:25
# User : geovindu pip install pandas -i https://pypi.tuna.tsinghua.edu.cn/simple pip install matplotlib -i https://pypi.tuna.tsinghua.edu.cn/simple pip3 install numpy -i https://pypi.tuna.tsinghua.edu.cn/simple
# Product : PyCharm
# Project : PyExceport
# File : Main.py
'''
pip install openpyxl -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install xlwt -i https://pypi.tuna.tsinghua.edu.cn/simple
python.exe -m pip install --upgrade pip -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install openpyxl -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install matplotlib -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install pandas -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install xlwt -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install xlsxwriter -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install ttkbootstrap -i https://pypi.tuna.tsinghua.edu.cn/simple
'''
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.font_manager as fm
import os
from typing import Dict
import warnings
warnings.filterwarnings('ignore')
# 修复中文字体问题（核心修改部分）
def setup_chinese_font():
"""
配置matplotlib中文字体
:return:
"""
try:
# 优先尝试微软雅黑（Windows默认）
plt.rcParams['font.sans-serif'] = ['Microsoft YaHei', 'SimHei', 'DejaVu Sans']
plt.rcParams['axes.unicode_minus'] = False
plt.rcParams['font.family'] = 'sans-serif'
print("中文字体配置成功（使用微软雅黑）")
except:
# 备选方案：自动查找系统中文字体
font_paths = fm.findSystemFonts(fontext='ttf')
chinese_fonts = [f for f in font_paths if any(c in f.lower() for c in ['hei', 'yahei', 'song'])]
if chinese_fonts:
font_prop = fm.FontProperties(fname=chinese_fonts[0])
plt.rcParams['font.sans-serif'] = [font_prop.get_name(), 'DejaVu Sans']
plt.rcParams['axes.unicode_minus'] = False
print(f"中文字体配置成功（使用系统字体：{font_prop.get_name()}）")
else:
print("警告：未找到中文字体，图表中文可能显示异常")
# 初始化字体
setup_chinese_font()
def check_dependencies() -> bool:
"""
检查必要的依赖是否安装
:return:
"""
required_packages = ['openpyxl', 'matplotlib']
missing_packages = []
for pkg in required_packages:
try:
__import__(pkg)
except ImportError:
missing_packages.append(pkg)
if missing_packages:
print(f"错误：缺少必要的依赖包：{', '.join(missing_packages)}")
print(f"请执行安装命令：pip install {' '.join(missing_packages)}")
return False
return True
def compare_two_sheets(excel_path: str,sheet1_name: str = 'Sheet1',sheet2_name: str = 'Sheet2', key_column: str = '员工号', output_excel: str = '人员比对详细报告.xlsx', output_image: str = '人员比对结果图表.png') -> Dict:
"""
比对两个Excel工作表中的人员数据
:param excel_path: Excel文件路径
:param sheet1_name: 第一个工作表名称
:param sheet2_name: 第二个工作表名称
:param key_column: 用于比对的关键字段（如员工号、身份证号）
:param output_excel: 输出报告的Excel路径
:param output_image: 输出图表的路径
:return: 比对结果字典
"""
# 先检查依赖
if not check_dependencies():
raise ImportError("依赖检查失败，请先安装缺失的包")
# 检查文件是否存在
if not os.path.exists(excel_path):
raise FileNotFoundError(f"Excel文件不存在：{excel_path}")
try:
# 读取两个工作表
df1 = pd.read_excel(excel_path, sheet_name=sheet1_name)
df2 = pd.read_excel(excel_path, sheet_name=sheet2_name)
# 检查关键字段是否存在
if key_column not in df1.columns:
raise ValueError(f"Sheet1中缺少关键字段：{key_column}")
if key_column not in df2.columns:
raise ValueError(f"Sheet2中缺少关键字段：{key_column}")
# 去除空值和重复值
df1_clean = df1.dropna(subset=[key_column]).drop_duplicates(subset=[key_column])
df2_clean = df2.dropna(subset=[key_column]).drop_duplicates(subset=[key_column])
# 获取两个表的关键字段集合
set1 = set(df1_clean[key_column].astype(str))
set2 = set(df2_clean[key_column].astype(str))
# 计算交集、差集
common = set1 & set2 # 两个表都有的
only_in_sheet1 = set1 - set2 # 仅Sheet1有的
only_in_sheet2 = set2 - set1 # 仅Sheet2有的
# 筛选对应的数据
df_common = df1_clean[df1_clean[key_column].astype(str).isin(common)]
df_only1 = df1_clean[df1_clean[key_column].astype(str).isin(only_in_sheet1)]
df_only2 = df2_clean[df2_clean[key_column].astype(str).isin(only_in_sheet2)]
# 生成统计结果
result = {
'total_sheet1': len(df1_clean),
'total_sheet2': len(df2_clean),
'common_count': len(common),
'only_sheet1_count': len(only_in_sheet1),
'only_sheet2_count': len(only_in_sheet2),
'common_data': df_common,
'only_sheet1_data': df_only1,
'only_sheet2_data': df_only2
}
# 生成Excel报告
with pd.ExcelWriter(output_excel, engine='openpyxl') as writer:
# 汇总表
summary_df = pd.DataFrame({
'项目': ['Sheet1总人数', 'Sheet2总人数', '两个表都有', '仅Sheet1有', '仅Sheet2有'],
'数量': [
result['total_sheet1'],
result['total_sheet2'],
result['common_count'],
result['only_sheet1_count'],
result['only_sheet2_count']
]
})
summary_df.to_excel(writer, sheet_name='比对汇总', index=False)
# 各分类数据
df_only1.to_excel(writer, sheet_name='仅在Sheet1', index=False)
df_only2.to_excel(writer, sheet_name='仅在Sheet2', index=False)
df_common.to_excel(writer, sheet_name='两个表都有', index=False)
# 生成可视化图表
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(15, 6))
# 饼图：人员分布比例
pie_labels = ['仅Sheet1', '仅Sheet2', '两个表都有']
pie_sizes = [len(only_in_sheet1), len(only_in_sheet2), len(common)]
ax1.pie(pie_sizes, labels=pie_labels, autopct='%1.1f%%', startangle=90)
ax1.set_title('人员分布比例')
# 柱状图：数量对比
bar_x = ['总人数', '独有人员', '共有人员']
bar_sheet1 = [
result['total_sheet1'],
result['only_sheet1_count'],
result['common_count']
]
bar_sheet2 = [
result['total_sheet2'],
result['only_sheet2_count'],
result['common_count']
]
x = range(len(bar_x))
width = 0.35
ax2.bar([i - width / 2 for i in x], bar_sheet1, width, label='Sheet1')
ax2.bar([i + width / 2 for i in x], bar_sheet2, width, label='Sheet2')
ax2.set_xlabel('人员类型')
ax2.set_ylabel('人数')
ax2.set_title('两个表人员数量对比')
ax2.set_xticks(x)
ax2.set_xticklabels(bar_x)
ax2.legend()
ax2.grid(axis='y', alpha=0.3)
plt.tight_layout()
plt.savefig(output_image, dpi=300, bbox_inches='tight')
plt.close()
print(f"比对完成！")
print(f"- 报告已保存至：{output_excel}")
print(f"- 图表已保存至：{output_image}")
print(f"- 仅Sheet1有 {result['only_sheet1_count']} 人，仅Sheet2有 {result['only_sheet2_count']} 人")
return result
except Exception as e:
print(f"比对过程中出现错误: {str(e)}")
raise
# 调用示例
if __name__ == "__main__":
"""
主输出
"""
try:
result = compare_two_sheets(
excel_path='人员比对.xlsx', # 替换为你的Excel文件路径
sheet1_name='Sheet1',
sheet2_name='Sheet2',
key_column='员工号',
output_excel='人员比对详细报告.xlsx',
output_image='人员比对结果图表.png'
)
except Exception as e:
print(f"执行失败：{e}")输出：
改动一下：
Domain Layer
# encoding: utf-8
# 版权所有 2026 ©涂聚文有限公司™ ®
# 许可信息查看：言語成了邀功盡責的功臣，還需要行爲每日來值班嗎
# 描述：
# Author : geovindu,Geovin Du 涂聚文.
# IDE : PyCharm 2024.3.6 python 3.11
# os : windows 10
# database : mysql 9.0 sql server 2019, postgreSQL 17.0 Oracle 21c Neo4j
# Datetime : 2026/1/24 14:00
# User : geovindu
# Product : PyCharm
# Project : PyExceport
# File : ComparisonResult.py
import os
import threading
from typing import List, Dict, Tuple, Optional
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.backends.backend_tkagg import FigureCanvasTkAgg
class ComparisonResult:
"""
领域模型：比对结果封装
"""
def __init__(self):
"""
"""
self.common_data: pd.DataFrame = pd.DataFrame() # 两表都有的数据
self.only_sheet1_data: pd.DataFrame = pd.DataFrame() # 仅表1有的数据
self.only_sheet2_data: pd.DataFrame = pd.DataFrame() # 仅表2有的数据
self.total_sheet1: int = 0
self.total_sheet2: int = 0
self.common_count: int = 0
self.only_sheet1_count: int = 0
self.only_sheet2_count: int = 0
# encoding: utf-8
# 版权所有 2026 ©涂聚文有限公司™ ®
# 许可信息查看：言語成了邀功盡責的功臣，還需要行爲每日來值班嗎
# 描述：
# Author : geovindu,Geovin Du 涂聚文.
# IDE : PyCharm 2024.3.6 python 3.11
# os : windows 10
# database : mysql 9.0 sql server 2019, postgreSQL 17.0 Oracle 21c Neo4j
# Datetime : 2026/1/24 14:01
# User : geovindu
# Product : PyCharm
# Project : PyExceport
# File : ComparisonRule.py
import os
import threading
from typing import List, Dict, Tuple, Optional
class ComparisonRule:
"""
领域模型：比对规则（比对列、工作表名称）
"""
def __init__(self, sheet1_name: str, sheet2_name: str, compare_columns: List[str]):
"""
:param sheet1_name:
:param sheet2_name:
:param compare_columns:
"""
self.sheet1_name = sheet1_name
self.sheet2_name = sheet2_name
self.compare_columns = compare_columns
if not compare_columns:
raise ValueError("至少选择一列作为比对依据")
# encoding: utf-8
# 版权所有 2026 ©涂聚文有限公司™ ®
# 许可信息查看：言語成了邀功盡責的功臣，還需要行爲每日來值班嗎
# 描述：
# Author : geovindu,Geovin Du 涂聚文.
# IDE : PyCharm 2024.3.6 python 3.11
# os : windows 10
# database : mysql 9.0 sql server 2019, postgreSQL 17.0 Oracle 21c Neo4j
# Datetime : 2026/1/24 13:59
# User : geovindu
# Product : PyCharm
# Project : PyExceport
# File : ExcelData.py
import os
import threading
from typing import List, Dict, Tuple, Optional
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.backends.backend_tkagg import FigureCanvasTkAgg
class ExcelData:
"""
领域模型：Excel数据封装
"""
def __init__(self, file_path: str):
"""
:param file_path:
"""
self.file_path = file_path
self.sheet_names: List[str] = []
self.sheet_data: Dict[str, pd.DataFrame] = {}
self.load_sheets()
def load_sheets(self):
"""
加载Excel所有工作表名称和数据
:return:
"""
try:
self.sheet_names = pd.ExcelFile(self.file_path).sheet_names
for sheet in self.sheet_names:
self.sheet_data[sheet] = pd.read_excel(self.file_path, sheet_name=sheet).fillna("")
except Exception as e:
raise ValueError(f"加载Excel失败：{str(e)}")
def get_sheet_columns(self, sheet_name: str) -> List[str]:
"""
获取指定工作表的列名
:param sheet_name:
:return:
"""""
if sheet_name not in self.sheet_data:
raise ValueError(f"工作表{sheet_name}不存在")
return list(self.sheet_data[sheet_name].columns)
def get_sheet_data(self, sheet_name: str) -> pd.DataFrame:
"""
获取指定工作表的原始数据"
:param sheet_name:
:return:
"""""
return self.sheet_data[sheet_name].copy()Application Layer
# encoding: utf-8
# 版权所有 2026 ©涂聚文有限公司™ ®
# 许可信息查看：言語成了邀功盡責的功臣，還需要行爲每日來值班嗎
# 描述：
# Author : geovindu,Geovin Du 涂聚文.
# IDE : PyCharm 2024.3.6 python 3.11
# os : windows 10
# database : mysql 9.0 sql server 2019, postgreSQL 17.0 Oracle 21c Neo4j
# Datetime : 2026/1/24 14:03
# User : geovindu
# Product : PyCharm
# Project : PyExceport
# File : ExcelComparisonService.py
import os
import threading
from typing import List, Dict, Tuple, Optional
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.backends.backend_tkagg import FigureCanvasTkAgg
from Domain.ExcelData import ExcelData
from Domain.ComparisonResult import ComparisonResult
from Domain.ComparisonRule import ComparisonRule
class ExcelComparisonService:
"""
应用服务：封装比对业务流程
"""
@staticmethod
def generate_unique_key(df: pd.DataFrame, columns: List[str]) -> pd.Series:
"""
生成多列组合的唯一键（用于多列比对）
:param df:
:param columns:
:return:
"""
return df[columns].astype(str).agg('|'.join, axis=1)
@staticmethod
def compare(excel_data: ExcelData, rule: ComparisonRule) -> ComparisonResult:
"""
执行核心比对逻辑
:param excel_data:
:param rule:
:return:
"""
result = ComparisonResult()
# 获取两个工作表的数据
df1 = excel_data.get_sheet_data(rule.sheet1_name)
df2 = excel_data.get_sheet_data(rule.sheet2_name)
# 生成唯一键（单列/多列）
df1['_unique_key'] = ExcelComparisonService.generate_unique_key(df1, rule.compare_columns)
df2['_unique_key'] = ExcelComparisonService.generate_unique_key(df2, rule.compare_columns)
# 去重（基于唯一键）
df1_clean = df1.drop_duplicates(subset=['_unique_key']).reset_index(drop=True)
df2_clean = df2.drop_duplicates(subset=['_unique_key']).reset_index(drop=True)
# 计算集合差集/交集
set1 = set(df1_clean['_unique_key'])
set2 = set(df2_clean['_unique_key'])
common_keys = set1 & set2
only_sheet1_keys = set1 - set2
only_sheet2_keys = set2 - set1
# 筛选结果（移除临时唯一键）
result.common_data = df1_clean[df1_clean['_unique_key'].isin(common_keys)].drop(columns=['_unique_key'])
result.only_sheet1_data = df1_clean[df1_clean['_unique_key'].isin(only_sheet1_keys)].drop(
columns=['_unique_key'])
result.only_sheet2_data = df2_clean[df2_clean['_unique_key'].isin(only_sheet2_keys)].drop(
columns=['_unique_key'])
# 统计数量
result.total_sheet1 = len(df1_clean)
result.total_sheet2 = len(df2_clean)
result.common_count = len(common_keys)
result.only_sheet1_count = len(only_sheet1_keys)
result.only_sheet2_count = len(only_sheet2_keys)
return result
@staticmethod
def create_chart(result: ComparisonResult) -> plt.Figure:
"""
生成比对结果图表
:param result:
:return:
"""
# 设置中文字体
plt.rcParams['font.sans-serif'] = ['Microsoft YaHei', 'SimHei', 'DejaVu Sans']
plt.rcParams['axes.unicode_minus'] = False
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 5))
# 饼图：分布比例
pie_labels = ['仅表1', '仅表2', '两表共有']
pie_sizes = [result.only_sheet1_count, result.only_sheet2_count, result.common_count]
ax1.pie(pie_sizes, labels=pie_labels, autopct='%1.1f%%', startangle=90,
colors=['#ff9999', '#66b3ff', '#99ff99'])
ax1.set_title('人员分布比例', fontsize=12)
# 柱状图：数量对比
bar_x = ['总条数', '独有条数', '共有条数']
bar_sheet1 = [result.total_sheet1, result.only_sheet1_count, result.common_count]
bar_sheet2 = [result.total_sheet2, result.only_sheet2_count, result.common_count]
x = range(len(bar_x))
width = 0.35
ax2.bar([i - width / 2 for i in x], bar_sheet1, width, label='表1', color='#ff9999')
ax2.bar([i + width / 2 for i in x], bar_sheet2, width, label='表2', color='#66b3ff')
ax2.set_xlabel('数据类型')
ax2.set_ylabel('数量')
ax2.set_title('数据数量对比', fontsize=12)
ax2.set_xticks(x)
ax2.set_xticklabels(bar_x)
ax2.legend()
ax2.grid(axis='y', alpha=0.3)
plt.tight_layout()
return fig
@staticmethod
def export_result(result: ComparisonResult, file_path: str, rule: ComparisonRule):
"""
导出比对结果到Excel
:param result:
:param file_path:
:param rule:
:return:
"""
with pd.ExcelWriter(file_path, engine='openpyxl') as writer:
# 汇总表
summary_df = pd.DataFrame({
'项目': ['表1总条数', '表2总条数', '两表共有', '仅表1有', '仅表2有'],
'数量': [
result.total_sheet1,
result.total_sheet2,
result.common_count,
result.only_sheet1_count,
result.only_sheet2_count
]
})
summary_df.to_excel(writer, sheet_name='比对汇总', index=False)
# 详细数据
result.common_data.to_excel(writer, sheet_name='两表共有', index=False)
result.only_sheet1_data.to_excel(writer, sheet_name=f'仅{rule.sheet1_name}有', index=False)
result.only_sheet2_data.to_excel(writer, sheet_name=f'仅{rule.sheet2_name}有', index=False)Presentation Layer
# encoding: utf-8
# 版权所有 2026 ©涂聚文有限公司™ ®
# 许可信息查看：言語成了邀功盡責的功臣，還需要行爲每日來值班嗎
# 描述：
# Author : geovindu,Geovin Du 涂聚文.
# IDE : PyCharm 2024.3.6 python 3.11
# os : windows 10
# database : mysql 9.0 sql server 2019, postgreSQL 17.0 Oracle 21c Neo4j
# Datetime : 2026/1/24 14:09
# User : geovindu
# Product : PyCharm
# Project : PyExceport
# File : ComparisonApp.py
import tkinter as tk
import ttkbootstrap as ttk
from ttkbootstrap.constants import *
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.backends.backend_tkagg import FigureCanvasTkAgg
import os
import threading
from typing import List, Dict, Tuple, Optional
import warnings
from Domain.ExcelData import ExcelData
from Domain.ComparisonResult import ComparisonResult
from Domain.ComparisonRule import ComparisonRule
from Application.ExcelComparisonService import ExcelComparisonService
warnings.filterwarnings('ignore')
class ComparisonApp:
"""
UI界面：基于ttkbootstrap的桌面应用
"""
def __init__(self, root):
self.root = root
self.root.title("Excel数据比对工具")
self.root.geometry("1200x800")
# 全局变量
self.excel_data: Optional[ExcelData] = None
self.comparison_result: Optional[ComparisonResult] = None
# 初始化界面
self._setup_ui()
def _setup_ui(self):
"""
构建UI布局
"""
# 1. 顶部文件选择区
file_frame = ttk.LabelFrame(self.root, text="文件选择")
file_frame.pack(fill=X, padx=10, pady=5)
self.file_path_var = ttk.StringVar()
ttk.Label(file_frame, text="Excel文件：").grid(row=0, column=0, sticky=W)
ttk.Entry(file_frame, textvariable=self.file_path_var, width=50).grid(row=0, column=1, padx=5)
ttk.Button(file_frame, text="选择文件", command=self._select_excel_file, bootstyle=PRIMARY).grid(row=0,
column=2)
ttk.Button(file_frame, text="加载工作表", command=self._load_sheets, bootstyle=SUCCESS).grid(row=0, column=3,
padx=5)
# 2. 比对配置区
config_frame = ttk.LabelFrame(self.root, text="比对配置")
config_frame.pack(fill=X, padx=10, pady=5)
# 2.1 工作表选择
ttk.Label(config_frame, text="表1：").grid(row=0, column=0, sticky=W)
self.sheet1_var = ttk.StringVar()
self.sheet1_combobox = ttk.Combobox(config_frame, textvariable=self.sheet1_var, width=20, state="readonly")
self.sheet1_combobox.grid(row=0, column=1, padx=5)
self.sheet1_combobox.bind("<<ComboboxSelected>>", self._load_sheet_columns)
ttk.Label(config_frame, text="表2：").grid(row=0, column=2, sticky=W)
self.sheet2_var = ttk.StringVar()
self.sheet2_combobox = ttk.Combobox(config_frame, textvariable=self.sheet2_var, width=20, state="readonly")
self.sheet2_combobox.grid(row=0, column=3, padx=5)
self.sheet2_combobox.bind("<<ComboboxSelected>>", self._load_sheet_columns)
# 2.2 比对列选择
ttk.Label(config_frame, text="比对列（可多选）：").grid(row=1, column=0, sticky=W, pady=5)
self.columns_listbox = tk.Listbox(config_frame, selectmode=tk.MULTIPLE, width=50, height=4)
self.columns_listbox.grid(row=1, column=1, columnspan=3, pady=5)
# 2.3 操作按钮
ttk.Button(config_frame, text="执行比对", command=self._execute_comparison, bootstyle=WARNING).grid(row=2,
column=1,
pady=5)
ttk.Button(config_frame, text="导出结果", command=self._export_result, bootstyle=INFO).grid(row=2, column=2,
pady=5)
ttk.Button(config_frame, text="清空", command=self._clear_all, bootstyle=DANGER).grid(row=2, column=3, pady=5)
# 3. 结果展示区
result_frame = ttk.LabelFrame(self.root, text="比对结果")
result_frame.pack(fill=BOTH, expand=True, padx=10, pady=5)
# 3.1 结果标签页
self.notebook = ttk.Notebook(result_frame)
self.notebook.pack(fill=BOTH, expand=True)
# 3.1.1 统计摘要
summary_frame = ttk.Frame(self.notebook)
self.notebook.add(summary_frame, text="统计摘要")
self.summary_text = ttk.Text(summary_frame, height=8, width=80)
self.summary_text.pack(fill=X, padx=5, pady=5)
# 3.1.2 仅表1有
sheet1_only_frame = ttk.Frame(self.notebook)
self.notebook.add(sheet1_only_frame, text="仅表1有")
self._create_table_view(sheet1_only_frame, "sheet1_only")
# 3.1.3 仅表2有
sheet2_only_frame = ttk.Frame(self.notebook)
self.notebook.add(sheet2_only_frame, text="仅表2有")
self._create_table_view(sheet2_only_frame, "sheet2_only")
# 3.1.4 两表共有
common_frame = ttk.Frame(self.notebook)
self.notebook.add(common_frame, text="两表共有")
self._create_table_view(common_frame, "common")
# 3.1.5 图表展示
chart_frame = ttk.Frame(self.notebook)
self.notebook.add(chart_frame, text="图表展示")
self.chart_canvas = None
def _create_table_view(self, parent, table_type: str):
"""
创建结果表格视图（带滚动条）
:param parent:
:param table_type:
:return:
"""
# 滚动条
vscroll = ttk.Scrollbar(parent, orient=VERTICAL)
hscroll = ttk.Scrollbar(parent, orient=HORIZONTAL)
# 表格
table = ttk.Treeview(parent, yscrollcommand=vscroll.set, xscrollcommand=hscroll.set)
vscroll.config(command=table.yview)
hscroll.config(command=table.xview)
# 布局
table.pack(side=LEFT, fill=BOTH, expand=True)
vscroll.pack(side=RIGHT, fill=Y)
hscroll.pack(side=BOTTOM, fill=X)
# 保存表格引用
setattr(self, f"{table_type}_table", table)
def _select_excel_file(self):
"""
选择Excel文件
:return:
"""
from tkinter.filedialog import askopenfilename
file_path = askopenfilename(filetypes=[("Excel文件", "*.xlsx;*.xls")])
if file_path:
self.file_path_var.set(file_path)
def _load_sheets(self):
"""
加载Excel工作表列表
:return:
"""
file_path = self.file_path_var.get()
if not file_path or not os.path.exists(file_path):
ttk.dialogs.Messagebox.show_error("请选择有效的Excel文件！")
return
try:
self.excel_data = ExcelData(file_path)
# 更新工作表下拉框
self.sheet1_combobox['values'] = self.excel_data.sheet_names
self.sheet2_combobox['values'] = self.excel_data.sheet_names
ttk.dialogs.Messagebox.show_info(f"成功加载{len(self.excel_data.sheet_names)}个工作表！")
except Exception as e:
ttk.dialogs.Messagebox.show_error(f"加载失败：{str(e)}")
def _load_sheet_columns(self, event=None):
"""
加载选中工作表的列名
:param event:
:return:
"""
if not self.excel_data:
return
# 优先取表1的列（表1/表2列名尽量保持一致）
sheet_name = self.sheet1_var.get() or self.sheet2_var.get()
if not sheet_name:
return
try:
columns = self.excel_data.get_sheet_columns(sheet_name)
self.columns_listbox.delete(0, tk.END)
for col in columns:
self.columns_listbox.insert(tk.END, col)
except Exception as e:
ttk.dialogs.Messagebox.show_error(f"加载列名失败：{str(e)}")
def _execute_comparison(self):
"""
执行比对（异步执行，避免UI卡顿）
:return:
"""
# 校验输入
if not self.excel_data:
ttk.dialogs.Messagebox.show_error("请先加载Excel文件！")
return
sheet1_name = self.sheet1_var.get()
sheet2_name = self.sheet2_var.get()
if not sheet1_name or not sheet2_name:
ttk.dialogs.Messagebox.show_error("请选择要比对的两个工作表！")
return
# 获取选中的比对列
selected_indices = self.columns_listbox.curselection()
if not selected_indices:
ttk.dialogs.Messagebox.show_error("请至少选择一列作为比对依据！")
return
compare_columns = [self.columns_listbox.get(i) for i in selected_indices]
# 异步执行比对
def _compare_task():
try:
# 创建比对规则
rule = ComparisonRule(sheet1_name, sheet2_name, compare_columns)
# 执行比对
self.comparison_result = ExcelComparisonService.compare(self.excel_data, rule)
# 更新UI
self.root.after(0, self._update_result_display)
# 生成图表
self.root.after(0, self._update_chart)
except Exception as e:
self.root.after(0, lambda: ttk.dialogs.Messagebox.show_error(f"比对失败：{str(e)}"))
threading.Thread(target=_compare_task, daemon=True).start()
ttk.dialogs.Messagebox.show_info("正在执行比对，请稍候...")
def _update_result_display(self):
"""
更新结果展示
:return:
"""
if not self.comparison_result:
return
# 1. 更新统计摘要
summary_text = f"""
比对规则：
- 表1：{self.sheet1_var.get()}
- 表2：{self.sheet2_var.get()}
- 比对列：{', '.join([self.columns_listbox.get(i) for i in self.columns_listbox.curselection()])}
统计结果：
- 表1总条数：{self.comparison_result.total_sheet1}
- 表2总条数：{self.comparison_result.total_sheet2}
- 两表共有条数：{self.comparison_result.common_count}
- 仅表1有条数：{self.comparison_result.only_sheet1_count}
- 仅表2有条数：{self.comparison_result.only_sheet2_count}
"""
self.summary_text.delete(1.0, tk.END)
self.summary_text.insert(tk.END, summary_text)
# 2. 更新表格数据
self._update_table("sheet1_only", self.comparison_result.only_sheet1_data)
self._update_table("sheet2_only", self.comparison_result.only_sheet2_data)
self._update_table("common", self.comparison_result.common_data)
def _update_table(self, table_type: str, df: pd.DataFrame):
"""
更新表格数据
:param table_type:
:param df:
:return:
"""
table = getattr(self, f"{table_type}_table")
# 清空原有数据
table.delete(*table.get_children())
if df.empty:
return
# 设置列名
table["columns"] = list(df.columns)
table["show"] = "headings"
for col in df.columns:
table.heading(col, text=col)
table.column(col, width=100)
# 插入数据
for _, row in df.iterrows():
table.insert("", tk.END, values=list(row))
def _update_chart(self):
"""
更新图表展示
:return:
"""
if not self.comparison_result:
return
# 生成图表
fig = ExcelComparisonService.create_chart(self.comparison_result)
# 清除原有图表
if self.chart_canvas:
self.chart_canvas.get_tk_widget().destroy()
# 嵌入图表到UI
self.chart_canvas = FigureCanvasTkAgg(fig, master=self.notebook.nametowidget(self.notebook.tabs()[-1]))
self.chart_canvas.draw()
self.chart_canvas.get_tk_widget().pack(fill=BOTH, expand=True, padx=5, pady=5)
def _export_result(self):
"""
导出结果
:return:
"""
if not self.comparison_result:
ttk.dialogs.Messagebox.show_error("暂无比对结果可导出！")
return
from tkinter.filedialog import asksaveasfilename
save_path = asksaveasfilename(defaultextension=".xlsx", filetypes=[("Excel文件", "*.xlsx")])
if not save_path:
return
try:
rule = ComparisonRule(
self.sheet1_var.get(),
self.sheet2_var.get(),
[self.columns_listbox.get(i) for i in self.columns_listbox.curselection()]
)
ExcelComparisonService.export_result(self.comparison_result, save_path, rule)
ttk.dialogs.Messagebox.show_info(f"结果已导出至：{save_path}")
except Exception as e:
ttk.dialogs.Messagebox.show_error(f"导出失败：{str(e)}")
def _clear_all(self):
"""
清空所有状态
:return:
"""
self.file_path_var.set("")
self.sheet1_combobox['values'] = []
self.sheet2_combobox['values'] = []
self.columns_listbox.delete(0, tk.END)
self.summary_text.delete(1.0, tk.END)
# 清空表格
for table_type in ["sheet1_only", "sheet2_only", "common"]:
table = getattr(self, f"{table_type}_table")
table.delete(*table.get_children())
# 清空图表
if self.chart_canvas:
self.chart_canvas.get_tk_widget().destroy()
self.chart_canvas = None
# 重置全局变量
self.excel_data = None
self.comparison_result = None调用输出：
# encoding: utf-8
# 版权所有 2026 ©涂聚文有限公司™ ®
# 许可信息查看：言語成了邀功盡責的功臣，還需要行爲每日來值班嗎
# 描述：python.exe -m pip install --upgrade pip -i https://pypi.tuna.tsinghua.edu.cn/simple
# Author : geovindu,Geovin Du 涂聚文.
# IDE : PyCharm 2024.3.6 python 3.11
# os : windows 10
# database : mysql 9.0 sql server 2019, postgreSQL 17.0 Oracle 21c Neo4j
# Datetime : 2026/1/21 21:25
# User : geovindu pip install pandas -i https://pypi.tuna.tsinghua.edu.cn/simple pip install matplotlib -i https://pypi.tuna.tsinghua.edu.cn/simple pip3 install numpy -i https://pypi.tuna.tsinghua.edu.cn/simple
# Product : PyCharm
# Project : PyExceport
# File : Main.py
'''
pip install openpyxl -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install xlwt -i https://pypi.tuna.tsinghua.edu.cn/simple
python.exe -m pip install --upgrade pip -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install openpyxl -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install matplotlib -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install pandas -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install xlwt -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install xlsxwriter -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install ttkbootstrap -i https://pypi.tuna.tsinghua.edu.cn/simple
'''
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.font_manager as fm
import os
from typing import Dict
import warnings
import tkinter as tk
import ttkbootstrap as ttk
from ttkbootstrap.constants import *
from Presentation.ComparisonApp import ComparisonApp
warnings.filterwarnings('ignore')
# 调用示例
if __name__ == "__main__":
"""
主输出
"""
# 初始化ttkbootstrap
root = ttk.Window(themename="flatly") # 可选主题：flatly、darkly、cosmo、litera等
app = ComparisonApp(root)
root.mainloop()输出：
以上就是基于python实现一个Excel数据比对工具的详细内容，更多关于python Excel数据比对的资料请关注脚本之家其它相关文章！