<dependency><groupId>net.sf.cssbox</groupId><artifactId>pdf2dom</artifactId><version>1.7</version></dependency><dependency><groupId>org.apache.pdfbox</groupId><artifactId>pdfbox</artifactId><version>2.0.12</version></dependency><dependency><groupId>org.apache.pdfbox</groupId><artifactId>pdfbox-tools</artifactId><version>2.0.12</version></dependency>

　　/*读取pdf文字*/@Testpublic void readPdfTextTest() throws IOException {byte[] bytes = getBytes("D:\\code\\pdf\\HashMap.pdf");//加载PDF文档PDDocument document = PDDocument.load(bytes);readText(document);}public void readText(PDDocument document) throws IOException {PDFTextStripper stripper = new PDFTextStripper();String text = stripper.getText(document);System.out.println(text);}

/*pdf转换html*/@Testpublic void pdfToHtmlTest()  {String outputPath = "D:\\code\\pdf\\HashMap.html";byte[] bytes = getBytes("D:\\code\\pdf\\HashMap.pdf");
//        try() 写在()里面会自动关闭流try (BufferedWriter out = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(new File(outputPath)),"UTF-8"));){//加载PDF文档PDDocument document = PDDocument.load(bytes);PDFDomTree pdfDomTree = new PDFDomTree();pdfDomTree.writeText(document,out);} catch (Exception e) {e.printStackTrace();}}/*将文件转换为byte数组*/private byte[] getBytes(String filePath){byte[] buffer = null;try {File file = new File(filePath);FileInputStream fis = new FileInputStream(file);ByteArrayOutputStream bos = new ByteArrayOutputStream(1000);byte[] b = new byte[1000];int n;while ((n = fis.read(b)) != -1) {bos.write(b, 0, n);}fis.close();bos.close();buffer = bos.toByteArray();} catch (FileNotFoundException e) {e.printStackTrace();} catch (IOException e) {e.printStackTrace();}return buffer;}

@RequestMapping("ud")
@Controller
public class UpAndDownController {@RequestMapping("upload.do")@ResponseBodypublic Map<String,Object> upload(@RequestParam("file") MultipartFile file, HttpServletRequest request){Map<String, Object> map = new HashMap<>();map.put("code","200");try {PdfConvertUtil pdfConvertUtil = new PdfConvertUtil();String pdfName = file.getOriginalFilename();int lastIndex = pdfName.lastIndexOf(".pdf");String fileName = pdfName.substring(0, lastIndex);String htmlName = fileName + ".html";String realPath = ResourceUtils.getURL("classpath:").getPath() + "/templates/file";File f = new File(realPath);if(!f.exists()){f.mkdirs();}String htmlPath = realPath + "\\" + htmlName;pdfConvertUtil.pdftohtml(file.getBytes(), htmlPath);} catch (Exception e) {map.put("code","500");e.printStackTrace();}return map;}}