java 读取word文档结构_使用POI读取word文档内容

1.pom.xml 中新增

org.apache.poi

poi

4.0.0

org.apache.poi

poi-ooxml

4.0.0

org.apache.poi

poi-scratchpad

4.0.0

org.apache.poi

poi-scratchpad

3.17

2.service

import lombok.extern.slf4j.Slf4j;

import org.apache.poi.hwpf.HWPFDocument;

import org.apache.poi.xwpf.extractor.XWPFWordExtractor;

import org.apache.poi.xwpf.usermodel.XWPFDocument;

import org.springframework.beans.factory.annotation.Autowired;

import org.springframework.core.io.ClassPathResource;

import org.springframework.stereotype.Service;

import java.io.InputStream;

@Slf4j

@Service

public class PdfService {

public void sendPdf(WorkFlowRequestDTO requestDTO) throws Exception {

testReadByDoc("pdf/aa.docx");

}

public void testReadByDoc(String filePath) throws Exception {

String text = "";

InputStream is = new ClassPathResource((filePath)).getInputStream();

if (filePath.endsWith("docx")) {

HWPFDocument doc = new HWPFDocument(is);

//输出书签信息

//输出文本

System.out.println(doc.getDocumentText());

XWPFDocument doc1= new XWPFDocument(is);

XWPFWordExtractor extractor = new XWPFWordExtractor(doc1);

text = extractor.getText();

extractor.close();

is.close();

}

}

}

3.注意

docx 和doc不能互转 会抛异常(内部的结构不一样)