pip install --break-system-packages python-docx openpyxl python-pptx pypdf
sudo apt install libreoffice-writer libreoffice-calc libreoffice-impress pandoc

from docx import Document
doc = Document('file.docx')
for para in doc.paragraphs:
    print(para.text)

# 带格式提取
import subprocess
result = subprocess.run(['pandoc', '--track-changes=all', 'file.docx', '-t', 'markdown'], 
    capture_output=True, text=True)
print(result.stdout)

from docx import Document
from docx.shared import Pt, Inches

doc = Document()
# 标题
doc.add_heading('文档标题', 0)

# 段落
p = doc.add_paragraph('正文内容')
p.runs[0].bold = True  # 加粗
p.runs[0].font.size = Pt(12)
p.runs[0].font.name = 'Arial'

# 引用
doc.add_paragraph('引用内容', style='Intense Quote')

# 表格
table = doc.add_table(rows=2, cols=3)
table.style = 'Light Grid Accent 1'
table.rows[0].cells[0].text = '表头1'
table.rows[0].cells[1].text = '表头2'

doc.save('output.docx')

import openpyxl
wb = openpyxl.load_workbook('file.xlsx')
ws = wb.active
for row in ws.iter_rows(values_only=True):
    print(row)

import openpyxl
from openpyxl.styles import Font, PatternFill, Alignment

wb = openpyxl.Workbook()
ws = wb.active
ws.title = '数据'

# 写入
ws['A1'] = '姓名'
ws['B1'] = '年龄'
ws['A2'] = '张三'
ws['B2'] = 25

# 格式化
header_fill = PatternFill(start_color='4472C4', end_color='4472C4', fill_type='solid')
ws['A1'].fill = header_fill
ws['A1'].font = Font(color='FFFFFF', bold=True)
ws['A1'].alignment = Alignment(horizontal='center')

# 保存
wb.save('output.xlsx')

from pptx import Presentation
prs = Presentation('file.pptx')
for slide in prs.slides:
    for shape in slide.shapes:
        if hasattr(shape, 'text'):
            print(shape.text)

from pptx import Presentation
from pptx.util import Inches, Pt

prs = Presentation()
prs.slide_width = Inches(10)
prs.slide_height = Inches(7.5)

# 使用空白布局
slide = prs.slides.add_slide(prs.slide_layouts[6])
title = slide.shapes.title
subtitle = slide.placeholders[1]
title.text = '演示标题'
subtitle.text = '副标题'

prs.save('output.pptx')

from pypdf import PdfReader
reader = PdfReader('file.pdf')
print(f'页数: {len(reader.pages)}')
for page in reader.pages:
    print(page.extract_text())

from pypdf import PdfWriter, PdfReader
writer = PdfWriter()
for pdf_file in ['doc1.pdf', 'doc2.pdf']:
    reader = PdfReader(pdf_file)
    for page in reader.pages:
        writer.add_page(page)
with open('merged.pdf', 'wb') as f:
    writer.write(f)

reader = PdfReader('input.pdf')
for i, page in enumerate(reader.pages):
    writer = PdfWriter()
    writer.add_page(page)
    with open(f'page_{i+1}.pdf', 'wb') as f:
        writer.write(f)

page = reader.pages[0]
page.rotate(90)  # 顺时针90度