PDFBox: A Powerful Open‑Source Java Library for PDF Manipulation

1. Introduction

Apache PDFBox® is an open‑source Java library for creating, modifying and extracting content from PDF documents. It also provides several command‑line utilities.

Core Features

Extract Text – Unicode text extraction and page‑wise parsing.

Split & Merge – Split a PDF into multiple files or merge several PDFs into one.

Fill Forms – Read form data, populate interactive fields.

Preflight – Validate PDF/A‑1b compliance.

Print – Directly print PDFs via Java’s standard printing API.

Save as Image – Export pages to PNG, JPEG, etc.

Create PDFs – Generate PDFs from scratch, embed fonts, images, draw graphics.

Signing – Apply digital signatures for tamper‑proofing.

2. Practical Examples (Spring Boot 3.5.0)

2.1 Extract Text

File file = new File("e:/技术架构.pdf");
try (PDDocument document = Loader.loadPDF(file)) {
    AccessPermission ap = document.getCurrentAccessPermission();
    if (!ap.canExtractContent()) {
        throw new IOException("没有权限抽取文本内容");
    }
    PDFTextStripper stripper = new PDFTextStripper();
    stripper.setSortByPosition(true);
    for (int p = 1; p <= document.getNumberOfPages(); ++p) {
        stripper.setStartPage(p);
        stripper.setEndPage(p);
        String text = stripper.getText(document);
        System.out.println(String.format("page %d:", p));
        System.out.println("----------");
        System.out.println(text.trim());
        System.out.println();
    }
}

2.2 Extract Region Text

File file = new File("e:/技术架构.pdf");
try (PDDocument document = Loader.loadPDF(file)) {
    PDFTextStripperByArea stripper = new PDFTextStripperByArea();
    stripper.setSortByPosition(true);
    Rectangle rect = new Rectangle(10, 280, 275, 60);
    stripper.addRegion("f-region", rect);
    PDPage firstPage = document.getPage(0);
    stripper.extractRegions(firstPage);
    System.out.println("该区域的文本内容: %s".formatted(rect));
    System.out.println(stripper.getTextForRegion("f-region"));
}

2.3 Extract Metadata

public static void main(String[] args) throws IOException, XmpParsingException, BadFieldValueException {
    File file = new File("e:/技术架构.pdf");
    try (PDDocument document = Loader.loadPDF(file)) {
        PDDocumentCatalog catalog = document.getDocumentCatalog();
        PDMetadata meta = catalog.getMetadata();
        if (meta != null) {
            DomXmpParser xmpParser = new DomXmpParser();
            try {
                XMPMetadata metadata = xmpParser.parse(meta.toByteArray());
                showDublinCoreSchema(metadata);
                showAdobePDFSchema(metadata);
                showXMPBasicSchema(metadata);
            } catch (XmpParsingException e) {
                System.err.println("An error occurred when parsing the metadata: " + e.getMessage());
            }
        } else {
            PDDocumentInformation information = document.getDocumentInformation();
            if (information != null) {
                showDocumentInformation(information);
            }
        }
    }
}
// helper methods omitted for brevity

2.4 Add Image to PDF

public class AddImageToPdf {
    public void createPDFFromImage(String inputFile, String imagePath, String outputFile) throws IOException {
        try (PDDocument doc = Loader.loadPDF(new File(inputFile))) {
            PDPage page = doc.getPage(0);
            PDImageXObject pdImage = PDImageXObject.createFromFile(imagePath, doc);
            try (PDPageContentStream contentStream = new PDPageContentStream(doc, page, AppendMode.APPEND, true, true)) {
                float scale = 1f;
                contentStream.drawImage(pdImage, 20, 20, pdImage.getWidth() * scale, pdImage.getHeight() * scale);
            }
            doc.save(outputFile);
        }
    }
    public static void main(String[] args) throws IOException {
        new AddImageToPdf().createPDFFromImage("e:/技术架构.pdf", "d:/images/8.png", "e:/技术架构2.pdf");
    }
}

2.5 Add Text Message to Each Page

public class AddMessageToEachPage {
    public void doIt(String src, String message, String outfile) throws IOException {
        try (PDDocument doc = Loader.loadPDF(new File(src))) {
            File fontFile = new File("C:/Windows/Fonts/simhei.ttf");
            FileInputStream fis = new FileInputStream(fontFile);
            PDType0Font font = PDType0Font.load(doc, fis, true);
            float fontSize = 22.0f;
            for (PDPage page : doc.getPages()) {
                PDRectangle pageSize = page.getMediaBox();
                float stringWidth = font.getStringWidth(message) * fontSize / 1000f;
                int rotation = page.getRotation();
                boolean rotate = rotation == 90 || rotation == 270;
                float pageWidth = rotate ? pageSize.getHeight() : pageSize.getWidth();
                float pageHeight = rotate ? pageSize.getWidth() : pageSize.getHeight();
                float centerX = rotate ? pageHeight / 2f : (pageWidth - stringWidth) / 2f;
                float centerY = rotate ? (pageWidth - stringWidth) / 2f : pageHeight / 2f;
                try (PDPageContentStream contentStream = new PDPageContentStream(doc, page, AppendMode.PREPEND, true, true)) {
                    contentStream.beginText();
                    contentStream.setFont(font, fontSize);
                    contentStream.setNonStrokingColor(Color.red);
                    if (rotate) {
                        contentStream.setTextMatrix(Matrix.getRotateInstance(Math.PI / 2, centerX, centerY));
                    } else {
                        contentStream.setTextMatrix(Matrix.getTranslateInstance(centerX, centerY));
                    }
                    contentStream.showText(message);
                    contentStream.endText();
                }
            }
            doc.save(outfile);
        }
    }
    public static void main(String[] args) throws IOException {
        new AddMessageToEachPage().doIt("e:/技术架构.pdf", "Spring Boot3实战案例300讲", "e:/技术架构2.pdf");
    }
}

2.6 Create Interactive Form

public class CreateForm {
    public static void main(String[] args) throws IOException {
        try (PDDocument document = new PDDocument()) {
            PDPage page = new PDPage(PDRectangle.A4);
            document.addPage(page);
            File fontFile = new File("C:/Windows/Fonts/simhei.ttf");
            FileInputStream fis = new FileInputStream(fontFile);
            PDType0Font chineseFont = PDType0Font.load(document, fis, true);
            PDResources resources = new PDResources();
            resources.put(COSName.getPDFName("SimHei"), chineseFont);
            PDAcroForm acroForm = new PDAcroForm(document);
            document.getDocumentCatalog().setAcroForm(acroForm);
            acroForm.setDefaultResources(resources);
            acroForm.setDefaultAppearance("/SimHei 10 Tf 0 0 0 rg");
            float pageWidth = PDRectangle.A4.getWidth();
            float formWidth = 460;
            float left = (pageWidth - formWidth) / 2f;
            float labelWidth = 130;
            float fieldX = left + labelWidth;
            float fieldW = formWidth - labelWidth - 10;
            float rowHeight = 42;
            float baseY = page.getMediaBox().getHeight() - 80;
            try (PDPageContentStream cs = new PDPageContentStream(document, page)) {
                cs.beginText();
                cs.setFont(chineseFont, 16);
                cs.newLineAtOffset(left, baseY + 10);
                cs.showText("用户问卷调查");
                cs.endText();
                cs.setFont(chineseFont, 11);
                // 1. 姓名
                drawText(cs, left, baseY, "1. 姓名：");
                addTextField(document, acroForm, page, "name", fieldX, baseY - 14, fieldW, 24);
                baseY -= rowHeight;
                // 2. 联系电话
                drawText(cs, left, baseY, "2. 联系电话：");
                addTextField(document, acroForm, page, "phone", fieldX, baseY - 14, fieldW, 24);
                baseY -= rowHeight;
                // 3. 年龄
                drawText(cs, left, baseY, "3. 年龄：");
                addTextField(document, acroForm, page, "age", fieldX, baseY - 14, fieldW, 24);
                baseY -= rowHeight;
                // 4. 产品满意度意见
                drawText(cs, left, baseY, "4. 产品满意度意见：");
                addMultilineField(document, acroForm, page, "satisfyOpinion", fieldX, baseY - 70, fieldW, 60);
                baseY -= 88;
                // 5. 是否愿意继续使用
                drawText(cs, left, baseY, "5. 是否愿意继续使用：");
                float checkBoxSize = 18;
                float textOffsetY = 4;
                addCheckBox(document, acroForm, page, "useYes", fieldX, baseY - 10, checkBoxSize, checkBoxSize);
                cs.beginText();
                cs.setFont(chineseFont, 11);
                cs.newLineAtOffset(fieldX + 22, baseY + textOffsetY);
                cs.showText("愿意");
                cs.endText();
                float noX = fieldX + 90;
                addCheckBox(document, acroForm, page, "useNo", noX, baseY - 10, checkBoxSize, checkBoxSize);
                cs.beginText();
                cs.setFont(chineseFont, 11);
                cs.newLineAtOffset(noX + 22, baseY + textOffsetY);
                cs.showText("不愿意");
                cs.endText();
                baseY -= rowHeight;
                // 6. 其他备注
                drawText(cs, left, baseY, "6. 其他备注：");
                addMultilineField(document, acroForm, page, "otherRemark", fieldX, baseY - 70, fieldW, 60);
            }
            document.save("e:/survey_form.pdf");
            System.out.println("问卷表单生成完成：e:/survey_form.pdf");
        }
    }
    // helper methods drawText, addTextField, addMultilineField, addCheckBox omitted for brevity
}

2.7 Add JavaScript Action

try (PDDocument document = Loader.loadPDF(new File("e:/技术架构.pdf"))) {
    PDActionJavaScript javascript = new PDActionJavaScript(
        "app.alert( {cMsg: 'PDFBox rocks!', nIcon: 3, nType: 0, cTitle: 'PDFBox Javascript' } );");
    document.getDocumentCatalog().setOpenAction(javascript);
    if (document.isEncrypted()) {
        throw new IOException("Encrypted documents are not supported for this example");
    }
    document.save("e:/技术架构2.pdf");
}

2.8 Add Bookmarks (Outline)

try (PDDocument document = Loader.loadPDF(new File("e:/技术架构.pdf"))) {
    PDDocumentOutline outline = new PDDocumentOutline();
    document.getDocumentCatalog().setDocumentOutline(outline);
    PDOutlineItem pagesOutline = new PDOutlineItem();
    pagesOutline.setTitle("前后端技术架构");
    outline.addLast(pagesOutline);
    int pageNum = 0;
    for (PDPage page : document.getPages()) {
        pageNum++;
        PDPageDestination dest = new PDPageFitWidthDestination();
        dest.setPage(page);
        PDOutlineItem bookmark = new PDOutlineItem();
        bookmark.setDestination(dest);
        bookmark.setTitle("Page " + pageNum);
        pagesOutline.addLast(bookmark);
    }
    pagesOutline.openNode();
    outline.openNode();
    document.getDocumentCatalog().setPageMode(PageMode.USE_OUTLINES);
    document.save("e:/技术架构2.pdf");
}