使用PDFbox获取pdf文件的内容和图片

	<!-- 依赖 -->
    <dependency>
      <groupId>org.apache.pdfbox</groupId>
      <artifactId>pdfbox</artifactId>
      <version>2.0.23</version>
    </dependency>

获取传入的pdf的图片

我这里是分页读取的，更灵活

    public static void main(String[] args) throws IOException {
        Integer count = 0;
        File file = new File("D:\\Data\\电子图书馆_使用文档.pdf");
        FileInputStream fis = new FileInputStream(file);
        PDDocument document = PDDocument.load(fis);
        int allPages = document.getNumberOfPages();
        for (int i = 0; i < allPages; i++) {
            PDPage page = document.getPage(i);
            PDResources resources = page.getResources();
            Iterable<COSName> xObjectNames = resources.getXObjectNames();
            if (xObjectNames != null){
                Iterator<COSName> iterator = xObjectNames.iterator();
                while (iterator.hasNext()){
                    COSName key =  iterator.next();
                    if (resources.isImageXObject(key)){
                        PDImageXObject image = (PDImageXObject) resources.getXObject(key);
                        BufferedImage bImage = image.getImage();
                        ImageIO.write(bImage, "PNG", new File("D:\\image\\"+"image_"+ (i+1) + "页" + count + ".png"));
                        count++;
                    }
                }
            }
        }
        document.close();
    }

获取传入的pdf的文字内容

同样的分页读取

    public static void main(String[] args) throws IOException {
        PDDocument doc = new PDDocument();
        File file = new File("D:\\Data\\Java课件\\xxx.pdf");
        FileInputStream fis = new FileInputStream(file);
        doc = PDDocument.load(fis);
        PDFTextStripper pdfStripper = new PDFTextStripper();

        Splitter splitter = new Splitter();
        List<PDDocument> split = splitter.split(doc);
        for (int i = 0; i < split.size(); i++) {
            doc = split.get(i);
            PDFRenderer pdfRenderer = new PDFRenderer(doc);
            String text = pdfStripper.getText(doc);
            System.out.println("第"+(i+1)+"页内容："+text);
        }
        doc.close();
    }