WPS 365 CLI实战：让AI助手直接操控文档，自动化办公的正确姿势

WPS 365 CLI实战：让AI助手直接操控文档，自动化办公的正确姿势

前言

WPS 365发布了CLI工具，支持AI助手直接操控WPS文档。

这对做GEO的人意味着什么？

意味着：以后可以让AI自动读写文档、自动生成报告、自动整理数据——不用再手动复制粘贴了。

本文分享WPS 365 CLI的实战用法，包括：

• CLI安装与配置
• 文档自动化操作
• 与AI助手集成
• 完整代码示例

一、WPS 365 CLI是什么？

WPS 365 CLI是WPS官方发布的命令行工具，允许通过命令行操作WPS文档：

• 读取文档内容
• 写入/修改文档
• 批量处理文档
• 与其他系统集成

# 安装
npm install -g wps-cli

# 登录
wps-cli login –account your@email.com –password yourpass

# 查看帮助
wps-cli –help

二、核心功能实战

1. 文档读取与解析

import subprocess
import json

class WPSDocumentReader:
"""WPS文档读取器"""

def __init__(self, cli_path: str = "wps-cli"):
self.cli = cli_path

def read_document(self, file_path: str) –> str:
"""读取文档内容"""
cmd = [
self.cli, "doc", "read",
"–file", file_path,
"–format", "markdown" # 输出为markdown格式
]

result = subprocess.run(
cmd,
capture_output=True,
text=True
)

if result.returncode == 0:
return result.stdout
else:
raise Exception(f"读取失败: {result.stderr}")

def extract_tables(self, file_path: str) –> list:
"""提取文档中的表格"""
cmd = [
self.cli, "doc", "extract",
"–file", file_path,
"–type", "tables",
"–format", "json"
]

result = subprocess.run(
cmd,
capture_output=True,
text=True
)

if result.returncode == 0:
return json.loads(result.stdout)
else:
raise Exception(f"提取失败: {result.stderr}")

def get_metadata(self, file_path: str) –> dict:
"""获取文档元信息"""
cmd = [
self.cli, "doc", "info",
"–file", file_path
]

result = subprocess.run(
cmd,
capture_output=True,
text=True
)

if result.returncode == 0:
return json.loads(result.stdout)
else:
raise Exception(f"获取元信息失败: {result.stderr}")

2. 文档写入与修改

class WPSDocumentWriter:
"""WPS文档写入器"""

def __init__(self, cli_path: str = "wps-cli"):
self.cli = cli_path

def create_document(self, content: str, output_path: str, title: str = ""):
"""创建新文档"""
# 先写入临时markdown文件
temp_file = "/tmp/wps_content.md"
with open(temp_file, "w", encoding="utf-8") as f:
if title:
f.write(f"# {title}\\n\\n")
f.write(content)

# 转换为WPS格式
cmd = [
self.cli, "doc", "convert",
"–input", temp_file,
"–output", output_path,
"–format", "docx"
]

result = subprocess.run(cmd, capture_output=True, text=True)

if result.returncode != 0:
raise Exception(f"创建文档失败: {result.stderr}")

return output_path

def append_content(self, file_path: str, content: str):
"""向现有文档追加内容"""
cmd = [
self.cli, "doc", "append",
"–file", file_path,
"–content", content
]

result = subprocess.run(cmd, capture_output=True, text=True)

if result.returncode != 0:
raise Exception(f"追加内容失败: {result.stderr}")

def replace_text(self, file_path: str, old_text: str, new_text: str):
"""替换文档中的文本"""
cmd = [
self.cli, "doc", "replace",
"–file", file_path,
"–search", old_text,
"–replace", new_text
]

result = subprocess.run(cmd, capture_output=True, text=True)

if result.returncode != 0:
raise Exception(f"替换文本失败: {result.stderr}")

3. 批量处理

import os
from pathlib import Path
from concurrent.futures import ThreadPoolExecutor

class WPSBatchProcessor:
"""WPS批量处理器"""

def __init__(self, cli_path: str = "wps-cli"):
self.cli = cli_path
self.reader = WPSDocumentReader(cli_path)
self.writer = WPSDocumentWriter(cli_path)

def process_directory(
self,
input_dir: str,
output_dir: str,
processor_func,
max_workers: int = 4
):
"""
批量处理目录中的文档

Args:
input_dir: 输入目录
output_dir: 输出目录
processor_func: 处理函数，接收文档内容，返回处理后内容
max_workers: 最大并发数
"""
os.makedirs(output_dir, exist_ok=True)

# 获取所有文档文件
doc_files = list(Path(input_dir).glob("**/*.docx"))
doc_files.extend(Path(input_dir).glob("**/*.wps"))
doc_files.extend(Path(input_dir).glob("**/*.doc"))

results = []

def process_single(file_path: Path):
try:
# 读取文档
content = self.reader.read_document(str(file_path))

# 处理内容
processed = processor_func(content)

# 生成输出路径
output_path = os.path.join(
output_dir,
file_path.stem + "_processed.docx"
)

# 写入新文档
self.writer.create_document(
processed,
output_path,
title=file_path.stem
)

return {"status": "success", "file": str(file_path)}

except Exception as e:
return {"status": "error", "file": str(file_path), "error": str(e)}

# 并发处理
with ThreadPoolExecutor(max_workers=max_workers) as executor:
futures = [executor.submit(process_single, f) for f in doc_files]
results = [f.result() for f in futures]

# 统计结果
success_count = sum(1 for r in results if r["status"] == "success")
error_count = len(results) – success_count

return {
"total": len(results),
"success": success_count,
"errors": error_count,
"results": results
}

三、与AI助手集成

1. AI文档分析助手

from openai import OpenAI

class AIDocumentAnalyzer:
"""AI文档分析助手"""

def __init__(
self,
wps_reader: WPSDocumentReader,
api_key: str = None
):
self.reader = wps_reader
self.client = OpenAI(api_key=api_key)

def analyze_document(
self,
file_path: str,
analysis_type: str = "summary"
) –> str:
"""
分析文档

Args:
file_path: 文档路径
analysis_type: 分析类型 (summary/keywords/issues)
"""
# 读取文档
content = self.reader.read_document(file_path)

# 构建分析提示词
prompts = {
"summary": f"请总结以下文档的核心内容，用简洁的语言表达：\\n\\n{content}",
"keywords": f"请提取以下文档的关键词（10个以内）：\\n\\n{content}",
"issues": f"请分析以下文档存在的问题和改进建议：\\n\\n{content}"
}

prompt = prompts.get(analysis_type, prompts["summary"])

# 调用AI分析
response = self.client.chat.completions.create(
model="gpt-4",
messages=[{"role": "user", "content": prompt}]
)

return response.choices[0].message.content

def generate_report(
self,
file_paths: list,
report_template: str
) –> str:
"""
批量分析多个文档并生成报告
"""
results = []

for path in file_paths:
try:
content = self.reader.read_document(path)
metadata = self.reader.get_metadata(path)

# AI分析
summary = self.analyze_document(path, "summary")

results.append({
"file": path,
"title": metadata.get("title", ""),
"summary": summary
})
except Exception as e:
results.append({
"file": path,
"error": str(e)
})

# 生成汇总报告
report = report_template.format(
count=len(results),
items="\\n\\n".join([
f"## {r.get('title', r['file'])}\\n\\n{r.get('summary', '分析失败: ' + r.get('error', ''))}"
for r in results
])
)

return report

2. AI文档生成助手

class AIDocumentGenerator:
"""AI文档生成助手"""

def __init__(
self,
wps_writer: WPSDocumentWriter,
api_key: str = None
):
self.writer = wps_writer
self.client = OpenAI(api_key=api_key)

def generate_from_prompt(
self,
prompt: str,
output_path: str,
doc_type: str = "report"
):
"""
根据提示词生成文档
"""
# 调用AI生成内容
response = self.client.chat.completions.create(
model="gpt-4",
messages=[
{"role": "system", "content": "你是一个专业的文档撰写助手。请根据用户要求生成结构清晰、内容完整的文档。"},
{"role": "user", "content": prompt}
]
)

content = response.choices[0].message.content

# 生成文档
title = self._extract_title(content)
self.writer.create_document(content, output_path, title)

return output_path

def complete_template(
self,
template_path: str,
context: dict,
output_path: str
):
"""
填充文档模板
"""
reader = WPSDocumentReader()
template_content = reader.read_document(template_path)

# 替换占位符
content = template_content
for key, value in context.items():
content = content.replace(f"{{{key}}}", str(value))

# 生成文档
self.writer.create_document(content, output_path)

return output_path

def _extract_title(self, content: str) –> str:
"""从内容中提取标题"""
lines = content.split("\\n")
for line in lines:
line = line.strip()
if line and line.startswith("#"):
return line.lstrip("# ").strip()
return "未命名文档"

四、完整使用示例

def main():
# 初始化
reader = WPSDocumentReader()
writer = WPSDocumentWriter()
batch = WPSBatchProcessor()
analyzer = AIDocumentAnalyzer(reader)
generator = AIDocumentGenerator(writer)

# 示例1：读取并分析单个文档
print("=== 分析文档 ===")
content = reader.read_document("/path/to/report.docx")
metadata = reader.get_metadata("/path/to/report.docx")
print(f"标题: {metadata.get('title')}")
print(f"字数: {len(content)}")

# 示例2：批量处理
print("\\n=== 批量处理 ===")
results = batch.process_directory(
input_dir="/path/to/input",
output_dir="/path/to/output",
processor_func=lambda c: f"# 处理后的内容\\n\\n{c[:1000]}…" # 示例处理函数
)
print(f"处理完成: {results['success']}/{results['total']}")

# 示例3：AI生成报告
print("\\n=== AI生成报告 ===")
report = generator.generate_from_prompt(
prompt="生成一份Q1季度工作总结，包含：工作回顾、成果数据、下季度计划",
output_path="/path/to/quarterly_report.docx",
doc_type="report"
)
print(f"报告已生成: {report}")

# 示例4：批量分析生成汇总
print("\\n=== 批量分析汇总 ===")
files = [
"/path/to/doc1.docx",
"/path/to/doc2.docx",
"/path/to/doc3.docx"
]
summary_report = analyzer.generate_report(
file_paths=files,
report_template="# 文档分析汇总\\n\\n共分析 {count} 份文档：\\n\\n{items}"
)
print(summary_report)

if __name__ == "__main__":
main()

五、注意事项

六、总结

WPS 365 CLI让AI操作文档成为可能，核心价值：

代码可直接使用，配合WPS 365 CLI即可实现文档自动化。

#Python #WPS #文档自动化 #AI助手 #办公自动化