Python调用LibreOffice处理自动化文档的完整指南

sudo apt install libreoffice python3 python3-pip

find / -name "soffice" 2>/dev/null

pip install pyoo  # 或通过LibreOffice安装包中的UNO组件

import subprocess

# 将DOCX转为PDF
subprocess.run([
    "/usr/bin/soffice",
    "--headless",
    "--convert-to", "pdf:writer_pdf_Export",
    "input.docx",
    "--outdir", "/output/path"
])

# 转换当前目录下所有DOCX文件
libreoffice --headless --convert-to pdf *.docx

import uno
from subprocess import Popen

# 启动LibreOffice服务
process = Popen([
    "soffice",
    "--headless",
    "--accept=socket,host=localhost,port=2002;urp;"
])

# Python连接服务
local_context = uno.getComponentContext()
resolver = local_context.ServiceManager.createInstanceWithContext(
    "com.sun.star.bridge.UnoUrlResolver", local_context
)
context = resolver.resolve("uno:socket,host=localhost,port=2002;urp;StarOffice.ComponentContext")
desktop = context.ServiceManager.createInstanceWithContext(
    "com.sun.star.frame.Desktop", context
)

def add_bookmark(document, name, text):
    """在文档开头添加书签"""
    text_doc = document.Text
    cursor = text_doc.createTextCursor()
    cursor.gotoStart(False)
    text_doc.insertString(cursor, text, False)
    
    bookmark = document.createInstance("com.sun.star.text.Bookmark")
    bookmark.Name = name
    text_doc.insertTextContent(cursor, bookmark, False)

# 使用示例
doc = desktop.loadComponentFromURL("file:///tmp/test.odt", "_blank", 0, ())
add_bookmark(doc, "Section1", "这是第一章标题")
doc.storeToURL("file:///tmp/test_with_bookmark.odt", ())

subprocess.run([
    "soffice",
    "--headless",
    "--convert-to", "csv:Text - txt - csv (StarCalc)",
    "data.xlsx"
])

export LC_ALL=zh_CN.UTF-8
libreoffice --headless --convert-to pdf report.docx

import os

input_file = "input.docx"
output_dir = "/output"
os.makedirs(output_dir, exist_ok=True)

subprocess.run([
    "soffice",
    "--headless",
    "--convert-to", "pdf",
    input_file,
    "--outdir", output_dir
])