2.0版本以后PDFBox抽取pdf文件内的图片

2.0版本以后PDFBox抽取pdf文件内的图片

 public static List<RenderedImage> getImagesFromPDF(PDDocument document) throws IOException {
   
	        List<RenderedImage> images = new ArrayList<RenderedImage>();
	    for (PDPage page : document.getPages()) {
   
	        images.addAll(getImagesFromResources(page.getResources()));
	    }

	    return images;
	}
	 private static List<RenderedImage> getImagesFromResources(PDResources resources) throws IOException {
   
		    List<RenderedImage> images = new ArrayList<RenderedImage>();

		    for (COSName xObjectName : resources.getXObjectNames()) {
   
		        PDXObject xObject = resources.getXObject(xObjectName);

		        if (xObject instanceof PDFormXObject) {
   
		        	continue;
		            //images.addAll(getImagesFromResources(((PDFormXObject) xObject).getResources()));
		        } else if (xObject instanceof PDImageXObject) {
   
		        	PDImageXObject obj = (PDImageXObject) xObject;
		        	//获取图片后缀
		        	System.out.println(obj.getSuffix());
		            images.add(obj.getImage());
		        }
		    }

		    return images;
		}