本文目录导读：
我来详细介绍几种常见的文档结构转换方法,包括不同场景下的脚本方案。
Python方案（最通用）
安装依赖
pip install python-docx openpyxl pandas PyPDF2 reportlab
基本文档结构转换脚本
import os
from docx import Document
import pandas as pd
class DocumentConverter:
def __init__(self, input_file):
self.input_file = input_file
self.output_dir = "converted_output"
os.makedirs(self.output_dir, exist_ok=True)
def docx_to_txt(self):
"""Word转纯文本"""
doc = Document(self.input_file)
output_path = os.path.join(self.output_dir, "output.txt")
with open(output_path, 'w', encoding='utf-8') as f:
for paragraph in doc.paragraphs:
f.write(paragraph.text + '\n')
print(f"转换完成：{output_path}")
return output_path
def docx_to_markdown(self):
"""Word转Markdown"""
doc = Document(self.input_file)
output_path = os.path.join(self.output_dir, "output.md")
with open(output_path, 'w', encoding='utf-8') as f:
for paragraph in doc.paragraphs:
# 根据样式判断标题级别
if paragraph.style.name.startswith('Heading'):
level = int(paragraph.style.name[-1])
f.write('#' * level + ' ' + paragraph.text + '\n\n')
else:
# 检测列表
if paragraph.style.name.startswith('List'):
f.write('- ' + paragraph.text + '\n')
else:
f.write(paragraph.text + '\n\n')
print(f"转换完成：{output_path}")
return output_path
def docx_structure_extract(self):
"""提取文档结构（大纲）"""
doc = Document(self.input_file)
structure = []
for paragraph in doc.paragraphs:
if paragraph.style.name.startswith('Heading'):
level = int(paragraph.style.name[-1])
structure.append({
'level': level,
'text': paragraph.text,
'style': paragraph.style.name
})
# 保存为CSV
df = pd.DataFrame(structure)
output_path = os.path.join(self.output_dir, "structure.csv")
df.to_csv(output_path, index=False)
return structure
def docx_to_json(self, output_format='json'):
"""Word转JSON格式"""
doc = Document(self.input_file)
data = {
'metadata': {
'file': self.input_file,
'paragraphs': len(doc.paragraphs),
'tables': len(doc.tables)
},
'content': []
}
# 提取段落
for para in doc.paragraphs:
if para.text.strip():
data['content'].append({
'type': 'paragraph',
'style': para.style.name,
'text': para.text
})
# 提取表格
for table in doc.tables:
table_data = []
for row in table.rows:
row_data = [cell.text for cell in row.cells]
table_data.append(row_data)
data['content'].append({
'type': 'table',
'data': table_data
})
# 保存
if output_format == 'json':
import json
output_path = os.path.join(self.output_dir, "output.json")
with open(output_path, 'w', encoding='utf-8') as f:
json.dump(data, f, ensure_ascii=False, indent=2)
return data
# 使用示例
if __name__ == "__main__":
converter = DocumentConverter("example.docx")
# 转换格式
converter.docx_to_txt()
converter.docx_to_markdown()
converter.docx_to_json()
# 提取结构
structure = converter.docx_structure_extract()
print("文档结构：", structure)
Bash/Shell方案（Linux/Mac）
使用Pandoc进行格式转换
#!/bin/bash
# document_converter.sh
# 安装pandoc
# sudo apt-get install pandoc # Ubuntu
# brew install pandoc # Mac
# 定义输入输出
INPUT_FILE="$1"
OUTPUT_FORMAT="$2"
convert_document() {
local input=$1
local output_format=$2
local filename=$(basename "$input" .${input##*.})
case $output_format in
"txt")
pandoc "$input" -f docx -t plain -o "${filename}.txt"
echo "转换为TXT: ${filename}.txt"
;;
"md")
pandoc "$input" -f docx -t markdown -o "${filename}.md"
echo "转换为Markdown: ${filename}.md"
;;
"html")
pandoc "$input" -f docx -t html -o "${filename}.html"
echo "转换为HTML: ${filename}.html"
;;
"pdf")
pandoc "$input" -f docx -o "${filename}.pdf"
echo "转换为PDF: ${filename}.pdf"
;;
"all")
# 转换为所有格式
pandoc "$input" -f docx -t plain -o "${filename}.txt"
pandoc "$input" -f docx -t markdown -o "${filename}.md"
pandoc "$input" -f docx -t html -o "${filename}.html"
echo "全部转换完成"
;;
*)
echo "支持的格式: txt, md, html, pdf, all"
exit 1
;;
esac
}
# 批量转换目录下所有Word文档
batch_convert() {
local dir=$1
local format=$2
for doc in "$dir"/*.docx; do
if [ -f "$doc" ]; then
convert_document "$doc" "$format"
fi
done
}
# 主函数
main() {
if [ $# -lt 2 ]; then
echo "用法: $0 <输入文件/目录> <输出格式>"
echo "输出格式: txt, md, html, pdf, all"
exit 1
fi
if [ -d "$1" ]; then
batch_convert "$1" "$2"
elif [ -f "$1" ]; then
convert_document "$1" "$2"
else
echo "文件不存在: $1"
exit 1
fi
}
main "$@"
使用方式
# 单个文件转换 chmod +x document_converter.sh ./document_converter.sh example.docx md # 批量转换目录 ./document_converter.sh ./docs/ all
Node.js方案
安装依赖
npm install mammoth marked
转换脚本
// document-converter.js
const fs = require('fs');
const path = require('path');
const mammoth = require('mammoth'); // Word转换
const marked = require('marked'); // Markdown渲染
class DocumentConverter {
constructor() {
this.outputDir = './converted';
if (!fs.existsSync(this.outputDir)) {
fs.mkdirSync(this.outputDir);
}
}
// Word转HTML
async docxToHtml(inputFile) {
const result = await mammoth.convertToHtml({
path: inputFile
});
const outputPath = path.join(this.outputDir, 'output.html');
fs.writeFileSync(outputPath, result.value);
console.log('HTML转换完成');
return result.value;
}
// Word转Markdown（通过HTML中转）
async docxToMarkdown(inputFile) {
const html = await this.docxToHtml(inputFile);
// 简单HTML转Markdown（实际使用需要更完善的转换）
const md = html
.replace(/<h1>/g, '# ')
.replace(/<h2>/g, '## ')
.replace(/<h3>/g, '### ')
.replace(/<\/h[1-3]>/g, '\n\n')
.replace(/<p>/g, '')
.replace(/<\/p>/g, '\n\n')
.replace(/<strong>/g, '**')
.replace(/<\/strong>/g, '**')
.replace(/<em>/g, '*')
.replace(/<\/em>/g, '*')
.replace(/<[^>]*>/g, ''); // 移除剩余HTML标签
const outputPath = path.join(this.outputDir, 'output.md');
fs.writeFileSync(outputPath, md);
return md;
}
// 提取文档结构
async extractStructure(inputFile) {
const result = await mammoth.convertToHtml({
path: inputFile
});
const html = result.value;
const structure = [];
// 提取标题
const headingRegex = /<h([1-6])>(.*?)<\/h\1>/g;
let match;
while ((match = headingRegex.exec(html)) !== null) {
structure.push({
level: parseInt(match[1]),
text: match[2].replace(/<[^>]*>/g, '')
});
}
// 保存结构
const outputPath = path.join(this.outputDir, 'structure.json');
fs.writeFileSync(outputPath, JSON.stringify(structure, null, 2));
return structure;
}
}
// 使用示例
async function main() {
const converter = new DocumentConverter();
const inputFile = 'example.docx';
await converter.docxToHtml(inputFile);
await converter.docxToMarkdown(inputFile);
await converter.extractStructure(inputFile);
}
main().catch(console.error);
特定格式转换
表格提取脚本
# table_extractor.py
from docx import Document
import csv
def extract_tables(docx_file):
"""提取Word中的表格"""
doc = Document(docx_file)
for i, table in enumerate(doc.tables):
output_file = f"table_{i+1}.csv"
with open(output_file, 'w', newline='', encoding='utf-8') as f:
writer = csv.writer(f)
for row in table.rows:
writer.writerow([cell.text for cell in row.cells])
print(f"表格 {i+1} 已保存到 {output_file}")
目录结构生成
# toc_generator.py
from docx import Document
import re
def generate_toc(docx_file):
"""生成目录结构"""
doc = Document(docx_file)
toc = []
for paragraph in doc.paragraphs:
if paragraph.style.name.startswith('Heading'):
level = int(re.findall(r'\d+', paragraph.style.name)[0])
indent = " " * (level - 1)
toc.append(f"{indent}{paragraph.text}")
return '\n'.join(toc)
实用批处理命令
# Linux/Mac批量转换
for file in *.docx; do
pandoc "$file" -f docx -t markdown -o "${file%.docx}.md"
done
# Windows PowerShell
Get-ChildItem -Filter *.docx | ForEach-Object {
pandoc $_ -f docx -t markdown -o ($_.BaseName + ".md")
}
选择建议
- 简单文本转换：使用Pandoc命令行最快
- 结构化提取：Python脚本最灵活
- Web应用集成：Node.js方案适合
- 批量处理：Shell脚本最适用
- 精确控制：Python + python-docx库
需要更具体的转换需求（如特定格式解析、批量处理规则等）？请告诉我你的具体场景。
