当前位置：首页 > news >正文

完整教程：PDFBox - PDDocument 与 byte 数组、PDF 加密

news 2026/6/11 4:39:45

一、PDDocument 与 byte 数组

1、由 byte 数组创建 PDDocument

（1）基本介绍

调用 PDDocument 的 load 静态方法，由 byte 数组创建 PDDocument

public static PDDocument load(byte[] input) throws IOException {
return load(input, "");
}

（2）演示

File pdfFile = new File("pdf/image_example.pdf");
InputStream pdfInputStream;
try {
pdfInputStream = new FileInputStream(pdfFile);
} catch (FileNotFoundException e) {
e.printStackTrace();
System.out.println("PDF 文件不存在");
return;
}
ByteArrayOutputStream pdfBuffer = new ByteArrayOutputStream();
int nRead;
byte[] data = new byte[1024];
try {
while ((nRead = pdfInputStream.read(data, 0, data.length)) != -1) {
pdfBuffer.write(data, 0, nRead);
}
} catch (IOException e) {
e.printStackTrace();
System.out.println("PDF 读取文件失败");
return;
}
byte[] pdfBytes = pdfBuffer.toByteArray();
try (PDDocument document = PDDocument.load(pdfBytes)) {
PDPage page = new PDPage();
document.addPage(page);
File imgFile = new File("pdf/dzs.jpeg");
InputStream imgInputStream;
try {
imgInputStream = new FileInputStream(imgFile);
} catch (FileNotFoundException e) {
e.printStackTrace();
System.out.println("图片不存在");
return;
}
ByteArrayOutputStream imgBuffer = new ByteArrayOutputStream();
int nReadImg;
byte[] dataImg = new byte[1024];
try {
while ((nReadImg = imgInputStream.read(dataImg, 0, dataImg.length)) != -1) {
imgBuffer.write(dataImg, 0, nReadImg);
}
} catch (IOException e) {
e.printStackTrace();
System.out.println("图片读取失败");
return;
}
byte[] imgBytes = imgBuffer.toByteArray();
PDImageXObject pdImage = PDImageXObject.createFromByteArray(document, imgBytes, "dzs.jpeg");
try (PDPageContentStream contentStream = new PDPageContentStream(document, page)) {
contentStream.drawImage(pdImage, 100, 600, pdImage.getWidth() * 0.25f, pdImage.getHeight() * 0.25f);
} catch (IOException e) {
e.printStackTrace();
}
document.save("pdf/image_example.pdf");
} catch (IOException e) {
e.printStackTrace();
}

2、由 PDDocument 得到 byte 数组

（1）基本介绍

调用 PDDocument 的 save 方法，使用 ByteArrayOutputStream 来捕获输出，由 PDDocument 得到 byte 数组

public void save(OutputStream output) throws IOException {
if (this.document.isClosed()) {
throw new IOException("Cannot save a document which has been closed");
} else {
Iterator var2 = this.fontsToSubset.iterator();
while(var2.hasNext()) {
PDFont font = (PDFont)var2.next();
font.subset();
}
this.fontsToSubset.clear();
COSWriter writer = new COSWriter(output);
try {
writer.write(this);
} finally {
writer.close();
}
}
}

（2）演示

File pdfFile = new File("pdf/image_example.pdf");
InputStream pdfInputStream;
try {
pdfInputStream = new FileInputStream(pdfFile);
} catch (FileNotFoundException e) {
e.printStackTrace();
System.out.println("PDF 文件不存在");
return;
}
ByteArrayOutputStream pdfBuffer = new ByteArrayOutputStream();
int nRead;
byte[] data = new byte[1024];
try {
while ((nRead = pdfInputStream.read(data, 0, data.length)) != -1) {
pdfBuffer.write(data, 0, nRead);
}
} catch (IOException e) {
e.printStackTrace();
System.out.println("PDF 读取文件失败");
return;
}
byte[] pdfBytes = pdfBuffer.toByteArray();
try (PDDocument document = PDDocument.load(pdfBytes)) {
PDPage page = new PDPage();
document.addPage(page);
File imgFile = new File("pdf/dzs.jpeg");
InputStream imgInputStream;
try {
imgInputStream = new FileInputStream(imgFile);
} catch (FileNotFoundException e) {
e.printStackTrace();
System.out.println("图片不存在");
return;
}
ByteArrayOutputStream imgBuffer = new ByteArrayOutputStream();
int nReadImg;
byte[] dataImg = new byte[1024];
try {
while ((nReadImg = imgInputStream.read(dataImg, 0, dataImg.length)) != -1) {
imgBuffer.write(dataImg, 0, nReadImg);
}
} catch (IOException e) {
e.printStackTrace();
System.out.println("图片读取失败");
return;
}
byte[] imgBytes = imgBuffer.toByteArray();
PDImageXObject pdImage = PDImageXObject.createFromByteArray(document, imgBytes, "dzs.jpeg");
try (PDPageContentStream contentStream = new PDPageContentStream(document, page)) {
contentStream.drawImage(pdImage, 100, 600, pdImage.getWidth() * 0.25f, pdImage.getHeight() * 0.25f);
} catch (IOException e) {
e.printStackTrace();
}
ByteArrayOutputStream output = new ByteArrayOutputStream();
document.save(output);
byte[] bytes = output.toByteArray();
System.out.println("PDF 字节数：" + bytes.length);
} catch (IOException e) {
e.printStackTrace();
}

# 输出结果
PDF 字节数：86736

二、PDF 加密

1、基本介绍

（1）用户密码

用户密码（User Password / Open Password）用于打开 PDF 文件，也叫打开密码或文档密码
如果设置了用户密码，任何人在打开该 PDF 时都必须输入这个密码，否则无法查看内容

（2）所有者密码

所有者密码（Owner Password / Permissions Password）用于解除权限限制
所有者密码用于禁止某些操作，例如，打印、复制、编辑
只有拥有所有者密码的用户，才能移除这些限制，普通用户即使能打开 PDF，也无法绕过这些限制

2、创建加密的 PDF

try (PDDocument document = new PDDocument()) {
PDPage page = new PDPage();
document.addPage(page);
try (PDPageContentStream contentStream = new PDPageContentStream(document, page)) {
contentStream.beginText();
contentStream.setFont(PDType1Font.HELVETICA_BOLD, 12);
contentStream.newLineAtOffset(100, 700);
contentStream.showText("Hello PDFBox");
contentStream.endText();
} catch (IOException e) {
e.printStackTrace();
}
// 设置权限
AccessPermission accessPermission = new AccessPermission();
accessPermission.setReadOnly();
// 设置保护策略
StandardProtectionPolicy policy = new StandardProtectionPolicy("12345", "12345", accessPermission);
document.protect(policy);
document.save("pdf/test.pdf");
} catch (IOException e) {
e.printStackTrace();
}

3、读取加密的 PDF

读取时未设置密码或设置了错误的密码

try (PDDocument document = PDDocument.load(new File("pdf/test.pdf"), "abc")) {
PDFTextStripper stripper = new PDFTextStripper();
String text = stripper.getText(document);
System.out.println(text);
} catch (Exception e) {
e.printStackTrace();
}

# 输出结果
org.apache.pdfbox.pdmodel.encryption.InvalidPasswordException: Cannot decrypt PDF, the password is incorrect

读取时设置了正确的密码

try (PDDocument document = PDDocument.load(new File("pdf/test.pdf"), "12345")) {
PDFTextStripper stripper = new PDFTextStripper();
String text = stripper.getText(document);
System.out.println(text);
} catch (Exception e) {
e.printStackTrace();
}