通过java将 word(.doc) 转 md

说明：使用的jdk8的版本

1、添加相关依赖

        <!-- Apache POI 处理Word文档 --><dependency><groupId>org.apache.poi</groupId><artifactId>poi</artifactId><version>4.1.2</version></dependency><dependency><groupId>org.apache.poi</groupId><artifactId>poi-ooxml</artifactId><version>4.1.2</version></dependency><dependency><groupId>org.apache.poi</groupId><artifactId>poi-scratchpad</artifactId><version>4.1.2</version></dependency>

2、实现代码

// 转换 .doc 格式文件public void convertDoc(String inputPath, String outputPath) throws IOException {try (HWPFDocument document = new HWPFDocument(new FileInputStream(inputPath));FileWriter writer = new FileWriter(outputPath)) {Range range = document.getRange();for (int i = 0; i < range.numParagraphs(); i++) {Paragraph para = range.getParagraph(i);String text = para.text().trim();if (text.isEmpty()) continue;// 处理标题String mdText = processDocHeading(para, text);if (mdText != null) {writer.write(mdText + "\n\n");continue;}// 处理列表mdText = processDocList(para, text);if (mdText != null) {writer.write(mdText + "\n\n");continue;}// 普通段落 自定义过滤条件if (!text.contains("页 共")){writer.write(text + "\n\n");}}}}// 处理 .doc 标题private String processDocHeading(Paragraph para, String text) {int styleIndex = para.getStyleIndex();// 标题样式索引通常为 0-5 对应 1-6 级标题if (styleIndex >= 0 && styleIndex <= 5) {if (text.contains("？")){//自定义过滤条件return repeat("#", styleIndex + 1) + " " + text;//styleIndex + 1表示从标题1开始}}return null;}// 处理 .doc 列表private String processDocList(Paragraph para, String text) {// 兼容处理列表判断，避免使用可能不存在的方法try {// 通过反射检查是否有 getListFormat 方法Object listFormat = para.getClass().getMethod("getListFormat").invoke(para);if (listFormat != null) {// 检查是否有列表编号Object listNumber = listFormat.getClass().getMethod("getListNumber").invoke(listFormat);if (listNumber instanceof Integer && (Integer) listNumber > 0) {return "- " + text;}}} catch (Exception e) {// 没有列表格式，返回 null}return null;}@Testpublic  void a() {try {// 转换.doc文件  第一个参数是word文件所在路径，第二个是希望输出的文件路径及命名convertDoc("C:\\***\\***.doc", "D:\\***\\output_from_doc.md");log.info("转换完成");}catch (Exception e){log.error("转换失败："+e);}}

3、自此，转换已完成，若想要docx格式的转md 可参考下面

import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.usermodel.Paragraph;
import org.apache.poi.hwpf.usermodel.Range;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTP;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTPPr;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTNumPr;import java.io.FileInputStream;
import java.io.FileWriter;
import java.io.IOException;public class WordToMarkdown {// 转换 .doc 格式文件public void convertDoc(String inputPath, String outputPath) throws IOException {try (HWPFDocument document = new HWPFDocument(new FileInputStream(inputPath));FileWriter writer = new FileWriter(outputPath)) {Range range = document.getRange();for (int i = 0; i < range.numParagraphs(); i++) {Paragraph para = range.getParagraph(i);String text = para.text().trim();if (text.isEmpty()) continue;// 处理标题String mdText = processDocHeading(para, text);if (mdText != null) {writer.write(mdText + "\n\n");continue;}// 处理列表mdText = processDocList(para, text);if (mdText != null) {writer.write(mdText + "\n\n");continue;}// 普通段落writer.write(text + "\n\n");}}}// 转换 .docx 格式文件public void convertDocx(String inputPath, String outputPath) throws IOException {try (XWPFDocument document = new XWPFDocument(new FileInputStream(inputPath));FileWriter writer = new FileWriter(outputPath)) {for (XWPFParagraph para : document.getParagraphs()) {String text = para.getText().trim();if (text.isEmpty()) continue;// 处理标题String mdText = processDocxHeading(para, text);if (mdText != null) {writer.write(mdText + "\n\n");continue;}// 处理列表mdText = processDocxList(para, text);if (mdText != null) {writer.write(mdText + "\n\n");continue;}// 普通段落writer.write(text + "\n\n");}}}// 处理 .doc 标题private String processDocHeading(Paragraph para, String text) {int styleIndex = para.getStyleIndex();// 标题样式索引通常为 0-5 对应 1-6 级标题if (styleIndex >= 0 && styleIndex <= 5) {return repeat("#", styleIndex + 1) + " " + text;}return null;}// 处理 .doc 列表private String processDocList(Paragraph para, String text) {// 兼容处理列表判断，避免使用可能不存在的方法try {// 通过反射检查是否有 getListFormat 方法Object listFormat = para.getClass().getMethod("getListFormat").invoke(para);if (listFormat != null) {// 检查是否有列表编号Object listNumber = listFormat.getClass().getMethod("getListNumber").invoke(listFormat);if (listNumber instanceof Integer && (Integer) listNumber > 0) {return "- " + text;}}} catch (Exception e) {// 没有列表格式，返回 null}return null;}// 处理 .docx 标题private String processDocxHeading(XWPFParagraph para, String text) {String styleName = para.getStyle();if (styleName != null && styleName.startsWith("Heading")) {try {int level = Integer.parseInt(styleName.replaceAll("[^0-9]", ""));if (level >= 1 && level <= 6) {return repeat("#", level) + " " + text;}} catch (NumberFormatException e) {// 忽略格式错误的标题}}return null;}// 处理 .docx 列表private String processDocxList(XWPFParagraph para, String text) {CTP ctp = para.getCTP();if (ctp == null) return null;CTPPr pPr = ctp.getPPr();if (pPr == null) return null;CTNumPr numPr = pPr.getNumPr();if (numPr != null) {return "- " + text;}return null;}// 字符串重复方法（兼容 JDK8）private String repeat(String str, int times) {if (times <= 0) return "";StringBuilder sb = new StringBuilder();for (int i = 0; i < times; i++) {sb.append(str);}return sb.toString();}public static void main(String[] args) {WordToMarkdown converter = new WordToMarkdown();try {// 转换 .doc 文件converter.convertDoc("input.doc", "output_doc.md");// 转换 .docx 文件converter.convertDocx("input.docx", "output_docx.md");System.out.println("转换完成！");} catch (IOException e) {System.err.println("转换失败：" + e.getMessage());e.printStackTrace();}}
}