how to extract image from PDF in java:
public static void readImageFromPDF(String filePath, String imagePath) {
try {
// 加载PDF文件
PDDocument document = PDDocument.load(filePath);
// 将PDF根据每页读入到list中
List<?> pages = document.getDocumentCatalog().getAllPages();
Iterator<?> iter = pages.iterator();
while (iter.hasNext()) {
PDPage page = (PDPage) iter.next();
PDResources resources = page.getResources();
// 取出图片
Map<?, ?> images = resources.getImages();
if (images != null) {
Iterator<?> imageIter = images.keySet().iterator();
while (imageIter.hasNext()) {
String key = (String) imageIter.next();
PDXObjectImage image = (PDXObjectImage) images.get(key);
File file = getUniqueFileName(key, image.getSuffix(), imagePath);
System.out.println("file name: " + file.getName());
// 将图片写入到已经定义好的文件中
image.write2file(file);
}
}
}
} catch (Exception e) {
e.printStackTrace();
}
}
/**
* 生成唯一的图片名称
* @param prefix 图片的前缀
* @param suffix 图片的后缀,也即图片的格式
* @param imagePath 图片的存储路径
* @return 返回结果为创建好的文件
*/
private static File getUniqueFileName(String prefix, String suffix, String imagePath) {
String uniqueName = null;
File f = null;
while (f == null || f.exists()) {
uniqueName = prefix + "-" + imageCounter;
f = new File(imagePath + uniqueName + "." + suffix);
imageCounter++;
}
return f;
}