Python自动化办公中的应用说明和脚本示例

from openpyxl import Workbook

data = [
    ['姓名', '部门', '成绩'],
    ['张三', '销售部', 89],
    ['李四', '技术部', 95]
]

wb = Workbook()
ws = wb.active
ws.title = "员工成绩表"

for row in data:
    ws.append(row)

wb.save("员工成绩表.xlsx")
print(" Excel 报表已生成。")

import smtplib
from email.message import EmailMessage

msg = EmailMessage()
msg['Subject'] = '日报 - 自动发送'
msg['From'] = 'your_email@example.com'
msg['To'] = 'receiver@example.com'
msg.set_content('请查收今日日报，见附件。')

# 添加附件
with open('日报.xlsx', 'rb') as f:
    msg.add_attachment(f.read(), maintype='application',
                       subtype='vnd.openxmlformats-officedocument.spreadsheetml.sheet',
                       filename='日报.xlsx')

# 发送邮件（使用QQ邮箱为例）
with smtplib.SMTP_SSL('smtp.qq.com', 465) as smtp:
    smtp.login('your_email@example.com', 'your_app_password')
    smtp.send_message(msg)

print(" 邮件已发送。")

import pdfplumber

with pdfplumber.open('文件.pdf') as pdf:
    all_text = ''
    for page in pdf.pages:
        all_text += page.extract_text() + '\n'

with open('提取内容.txt', 'w', encoding='utf-8') as f:
    f.write(all_text)

print(" PDF 文本已提取。")

import webbrowser
import pyautogui
import time

# 打开网页
webbrowser.open('https://www.google.com')
time.sleep(3)  # 等待页面加载

# 模拟输入搜索内容
pyautogui.write('Python automation', interval=0.1)
pyautogui.press('enter')

print(" 自动搜索已完成。")

import schedule
import time

def job():
    print("现在是：", time.strftime("%H:%M:%S"), " → 执行任务")

# 每天早上 9 点执行
schedule.every().day.at("09:00").do(job)

while True:
    schedule.run_pending()
    time.sleep(1)

pip install openpyxl pandas

import pandas as pd
import os

folder = './excel_files'  # Excel 文件所在文件夹
output_file = '合并结果.xlsx'

all_data = []

for file in os.listdir(folder):
    if file.endswith('.xlsx'):
        file_path = os.path.join(folder, file)
        df = pd.read_excel(file_path)
        df['来源文件'] = file  # 可选：添加来源文件列
        all_data.append(df)

# 合并所有数据
merged_df = pd.concat(all_data, ignore_index=True)
merged_df.to_excel(output_file, index=False)

print(" 所有 Excel 文件已合并到：", output_file)

import pandas as pd
import os

folder = './excel_files'

for file in os.listdir(folder):
    if file.endswith('.xlsx'):
        path = os.path.join(folder, file)
        df = pd.read_excel(path)

        # 修改 “状态” 列中的“未完成”为“完成”
        df['状态'] = df['状态'].replace('未完成', '完成')

        # 保存覆盖原文件
        df.to_excel(path, index=False)
        print(f" 已修改：{file}")

import pandas as pd
import os

input_file = '员工信息表.xlsx'
df = pd.read_excel(input_file)

# 筛选工资大于10000的员工
filtered = df[df['工资'] > 10000]

filtered.to_excel('高薪员工.xlsx', index=False)
print(" 筛选结果已保存。")

import pandas as pd
import os

df = pd.read_excel('员工信息.xlsx')

output_dir = './员工报表'
os.makedirs(output_dir, exist_ok=True)

# 按“姓名”分组，每个员工一个文件
for name, group in df.groupby('姓名'):
    filename = os.path.join(output_dir, f'{name}_报表.xlsx')
    group.to_excel(filename, index=False)
    print(f" 已生成：{filename}")

import os
import pandas as pd

# === 配置区域 ===
input_folder = r"./excel_input"       # 待处理Excel文件所在文件夹
output_folder = r"./excel_output"     # 清洗后文件保存文件夹
subset_columns = None                 # 去重依据的列，例如 ["姓名", "身份证号"]，None表示全列去重
keep_rule = "first"                   # 保留规则: "first" 保留首次出现, "last" 保留最后一次, False 保留所有重复(不常用)

# 创建输出文件夹
os.makedirs(output_folder, exist_ok=True)

# 遍历文件夹中的所有Excel文件
for filename in os.listdir(input_folder):
    if filename.lower().endswith((".xls", ".xlsx")):
        file_path = os.path.join(input_folder, filename)
        
        try:
            # 读取Excel（保留所有sheet）
            xls = pd.ExcelFile(file_path)
            cleaned_sheets = {}
            
            for sheet_name in xls.sheet_names:
                df = pd.read_excel(xls, sheet_name=sheet_name)
                
                # 去重
                before_rows = len(df)
                df_cleaned = df.drop_duplicates(subset=subset_columns, keep=keep_rule)
                after_rows = len(df_cleaned)
                
                print(f"{filename} - {sheet_name}: {before_rows} -> {after_rows} 行")
                
                cleaned_sheets[sheet_name] = df_cleaned
            
            # 保存清洗后的文件
            output_path = os.path.join(output_folder, filename)
            with pd.ExcelWriter(output_path, engine="openpyxl") as writer:
                for sheet_name, df_cleaned in cleaned_sheets.items():
                    df_cleaned.to_excel(writer, sheet_name=sheet_name, index=False)
        
        except Exception as e:
            print(f"处理文件 {filename} 时出错: {e}")

print(" 数据清洗完成！")