java获取word文档标题和内容

 导包：

<dependency>
        <groupId>org.apache.poi</groupId>
        <artifactId>poi-ooxml</artifactId>
        <version>3.17</version>
    </dependency>
    <dependency>
        <groupId>org.apache.poi</groupId>
        <artifactId>poi-scratchpad</artifactId>
        <version>3.17</version>
    </dependency>
</dependencies>

代码：

import lombok.extern.slf4j.Slf4j;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.springframework.stereotype.Component;
import org.springframework.web.bind.annotation.RequestParam;
import org.springframework.web.multipart.MultipartFile;

import java.io.InputStream;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

@Slf4j
@Component
public class FileParsingUtil {
    public static Map<String, String> getFileNameAndContent(MultipartFile file) {
        String title = "";
        String content = "";
        Map map = new HashMap<String, String>();
        try {
            InputStream inputStream = file.getInputStream();
            String fileName = file.getOriginalFilename();
            if (!fileName.endsWith("doc") && !fileName.endsWith("docx")) {
                return map;
            }
            if (fileName.endsWith("doc")) {
                WordExtractor xwpfWordExtractor = new WordExtractor(inputStream);
                String[] paragraphText = xwpfWordExtractor.getParagraphText();
                title = paragraphText[0].trim();
                for (int i = 1; i < paragraphText.length; i++) {
                    content = content + paragraphText[i].trim();
                }
            }
            if (fileName.endsWith("docx")) {
                XWPFDocument doc = new XWPFDocument(file.getInputStream());
                List<XWPFParagraph> paras=doc.getParagraphs();
                title = paras.get(0).getText().trim();
                for (int i = 1; i < paras.size(); i++) {
                    content = content + paras.get(i).getText().trim();
                }
            }
            map.put("title", title);
            map.put("content", content);
            log.error("word文档解析成功");
        } catch (Exception e) {
            e.getMessage();
            log.error("word文档解析失败");
        }
        return map;
    }
}