Python操作Office(Word/Excel/PowerPoint)文档的功能库使用详解

# 安装: pip install openpyxl
from openpyxl import Workbook

wb = Workbook()
ws = wb.active
ws['A1'] = 42
ws.append([1, 2, 3])
wb.save("example.xlsx")

# 安装: pip install xlwings
import xlwings as xw

wb = xw.Book()  # 新建Excel
sheet = wb.sheets['Sheet1']
sheet.range('A1').value = 'Hello'
wb.save('test.xlsx')
wb.close()

# 安装: pip install pandas openpyxl
import pandas as pd

# 读取
df = pd.read_excel("input.xlsx", sheet_name="Sheet1")

# 处理数据
df['new_col'] = df['col1'] * 2

# 写入
df.to_excel("output.xlsx", index=False)

# 安装: pip install python-docx
from docx import Document

doc = Document()
doc.add_heading('Python生成的文档', 0)
doc.add_paragraph('这是一个段落')
doc.add_table(rows=2, cols=2)
doc.save('demo.docx')

# 安装: pip install docx2pdf
from docx2pdf import convert
convert("input.docx", "output.pdf")

# 安装: pip install python-pptx
from pptx import Presentation

prs = Presentation()
slide = prs.slides.add_slide(prs.slide_layouts[1])
slide.shapes.title.text = "Python生成的PPT"
slide.placeholders[1].text = "内容区域"
prs.save('test.pptx')

# 安装: pip install PyPDF2
from PyPDF2 import PdfFileReader, PdfFileWriter

reader = PdfFileReader("input.pdf")
writer = PdfFileWriter()
writer.addPage(reader.getPage(0))
with open("output.pdf", "wb") as f:
    writer.write(f)

# 安装: pip install pdfkit
# 需要额外安装wkhtmltopdf
import pdfkit
pdfkit.from_file('input.html', 'output.pdf')

# 安装: pip install reportlab
from reportlab.pdfgen import canvas

c = canvas.Canvas("hello.pdf")
c.drawString(100, 750, "Welcome to ReportLab!")
c.save()

import smtplib
from email.mime.multipart import MIMEMultipart
from email.mime.text import MIMEText

msg = MIMEMultipart()
msg['From'] = 'me@example.com'
msg['To'] = 'you@example.com'
msg['Subject'] = 'Python邮件测试'
msg.attach(MIMEText('邮件正文内容', 'plain'))

server = smtplib.SMTP('smtp.example.com', 587)
server.starttls()
server.login('user', 'password')
server.send_message(msg)
server.quit()

import imaplib
import email

mail = imaplib.IMAP4_SSL('imap.example.com')
mail.login('user@example.com', 'password')
mail.select('inbox')

typ, data = mail.search(None, 'ALL')
for num in data[0].split():
    typ, msg_data = mail.fetch(num, '(RFC822)')
    msg = email.message_from_bytes(msg_data[0][1])
    print(msg['Subject'])

# 安装: pip install pywin32
import win32com.client

excel = win32com.client.Dispatch("Excel.Application")
excel.Visible = True
wb = excel.Workbooks.Add()
ws = wb.Worksheets(1)
ws.Cells(1,1).Value = "Hello Excel"
wb.SaveAs("test.xlsx")
excel.Quit()

# 需要安装LibreOffice
import os

os.system('unoconv -f pdf test.docx')  # Word转PDF

# 大批量Excel数据处理技巧
chunksize = 10**4
for chunk in pd.read_excel('large.xlsx', chunksize=chunksize):
    process(chunk)

try:
    doc = Document("corrupted.docx")
except PackageNotFoundError:
    print("文件已损坏或不是有效的Word文档")