java中pdfbox处理pdf常用方法(读取、写入、合并、拆分、写文字、写图片)

本篇文档将介绍pdfbox处理pdf常用方法(读取、写入、合并、拆分、写文字、写图片)。

图中为pdfbox用到的包

1.读取pdf

方法代码：

/**
     * 读取pdf中文字信息(全部)
     * @param inputFile
     * @return
     */
    public static String ReadPdf(String inputFile){
        //创建文档对象
        PDDocument doc =null;
        String content="";
        try {
            //加载一个pdf对象
            doc =PDDocument.load(new File(inputFile));
            //获取一个PDFTextStripper文本剥离对象  
            PDFTextStripper textStripper =new PDFTextStripper();
            content=textStripper.getText(doc);
            System.out.println("内容:"+content);
            System.out.println("全部页数"+doc.getNumberOfPages());  
            //关闭文档
            doc.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
        return content;
    }

测试用例：

public static void main(String[] args) throws Exception {
        
        String content = ReadPdf("C:\\pdfFolder\\target.pdf");
        System.out.println("内容如下：\n" + content);

}

2.写入pdf

2.1写文字

方法代码：

/**
     * 指定页插入一段文字
     * @param inputFilePath
     * @param outputFilePath
     * @param pageNum
     * @param message
     * @throws Exception
     */
    public static void InsertPageContent (String inputFilePath, String outputFilePath, Integer pageNum, String message) throws Exception {
        File inputPDFFile = new File(inputFilePath);
        File outputPDFFile = new File(outputFilePath);
        // the document
        PDDocument doc = null;
        try{
            doc = PDDocument.load(inputPDFFile);
            PDPageTree allPages = doc.getDocumentCatalog().getPages();
            PDFont font = PDType1Font.HELVETICA_BOLD;
            //字体大小
            float fontSize = 36.0f;
            PDPage page = (PDPage)allPages.get(pageNum - 1);
            PDRectangle pageSize = page.getMediaBox();
            float stringWidth = font.getStringWidth(message)*fontSize/1000f;
            // calculate to center of the page
            int rotation = page.getRotation(); 
            boolean rotate = rotation == 90 || rotation == 270;
            float pageWidth = rotate ? pageSize.getHeight() : pageSize.getWidth();
            float pageHeight = rotate ? pageSize.getWidth() : pageSize.getHeight();
            double centeredXPosition = rotate ? pageHeight/2f : (pageWidth - stringWidth)/2f;
            double centeredYPosition = rotate ? (pageWidth - stringWidth)/2f : pageHeight/2f;
            // append the content to the existing stream
            PDPageContentStream contentStream = new PDPageContentStream(doc, page, true, true,true);
            contentStream.beginText();
            // set font and font size
            contentStream.setFont( font, fontSize );
            // set text color to red
            contentStream.setNonStrokingColor(255, 0, 0);
            if (rotate) {
                // rotate the text according to the page rotation
                contentStream.setTextRotation(Math.PI/2, centeredXPosition, centeredYPosition);
            } else {
                contentStream.setTextTranslation(centeredXPosition, centeredYPosition);
            }
            contentStream.drawString(message);
            contentStream.endText();
            contentStream.close();
            doc.save(outputPDFFile);
            System.out.println("成功向pdf插入文字");
        } finally {
            if( doc != null ) {
                doc.close();
            }
        }
    }

测试用例：

    public static void main(String[] args) throws Exception {
        String inputFilePath = "C:\\pdfFolder\\A.pdf";
        String outputFilePath = "C:\\pdfFolder\\A2.pdf";
        //只能写英文，写中文会报错
        InsertPageContent(inputFilePath, outputFilePath, 1, "testMessage");
}

A.pdf:

A2.pdf:

2.2写图片

方法代码：

    /**
     * 在pdf中插入图片
     * @param inputFilePath
     * @param imagePath
     * @param outputFilePath
     * @param pageNum
     * @throws Exception
     */
    public static void insertImage(String inputFilePath, String imagePath, String outputFilePath, Integer pageNum) throws Exception {
        File inputPDFFile = new File(inputFilePath);
        File outputPDFFile = new File(outputFilePath);
        
        try {
            PDDocument doc = PDDocument.load(inputPDFFile);
            PDImageXObject pdImage = PDImageXObject.createFromFile(imagePath, doc);
    
            PDPage page = doc.getPage(0);
            //注释的这行代码会覆盖原内容，没注释的那行不会覆盖
//            PDPageContentStream contentStream = new PDPageContentStream(doc, page);
            PDPageContentStream contentStream = new PDPageContentStream(doc, page, true, true, true);
            contentStream.drawImage(pdImage, 70, 250);
            contentStream.close();
            doc.save(outputPDFFile);
            doc.close();
            System.out.println("成功插入图片");
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

测试用例：

public static void main(String[] args) throws Exception {
        String inputFilePath = "C:\\pdfFolder\\A.pdf";
        String outputFilePath = "C:\\pdfFolder\\A2.pdf";
        String imagePath = "C:\\pdfFolder\\pic.jpg";
        insertImage(inputFilePath, imagePath, outputFilePath, 1);
}

A.pdf:

pic.jpg:

A2.pdf:

3.合并pdf

方法代码：

    /**
     * 
     * @param pathList
     * @param targetPDFPath
     * @throws Exception
     */
    public static void MergePdf(List<String> pathList, String targetPDFPath) throws Exception {
        List<InputStream> inputStreams = new ArrayList<>();
        for(String path : pathList) {
            inputStreams.add(new FileInputStream(new File(path)));
        }
        PDFMergerUtility mergePdf = new PDFMergerUtility();
        File file = new File(targetPDFPath);
        
        if (!file.exists()) {
            file.delete();
        }
        
        mergePdf.addSources(inputStreams);
        mergePdf.setDestinationFileName(targetPDFPath);
        mergePdf.mergeDocuments();
        for (InputStream in : inputStreams) {
        if (in != null) {
            in.close();
            }
        }
    }

测试用例：

    public static void main(String[] args) throws Exception {
        List<String> pathList = new ArrayList<String>();
        String targetPDFPath = "C:\\pdfFolder\\target.pdf";
        pathList.add("C:\\pdfFolder\\A.pdf");
        pathList.add("C:\\pdfFolder\\B.pdf");
        pathList.add("C:\\pdfFolder\\C.pdf");
        pathList.add("C:\\pdfFolder\\D.pdf");
        pathList.add("C:\\pdfFolder\\E.pdf");
        
        MergePdf(pathList, targetPDFPath);
    }

4.拆分pdf

方法代码：

/**
     * 将pdf逐页分割
     * @param sourcePdfPath
     * @param splitPath
     * @param splitFileName
     * @throws Exception
     */
    public static void SpiltPdf(String sourcePdfPath, String splitPath, String splitFileName) throws Exception {
        int j = 1;
        String splitPdf = splitPath + File.separator + splitFileName + "_";

        // Loading an existing PDF document
        File file = new File(sourcePdfPath);
        PDDocument document = PDDocument.load(file);
        // Instantiating Splitter class
        Splitter splitter = new Splitter();
        splitter.setStartPage(1);
        splitter.setSplitAtPage(1);
        splitter.setEndPage(5);
        // splitting the pages of a PDF document
        List<PDDocument> Pages = splitter.split(document);
        // Creating an iterator
        Iterator<PDDocument> iterator = Pages.listIterator();
        // Saving each page as an individual document
        while(iterator.hasNext()) {
            PDDocument pd = iterator.next();
            String pdfName = splitPdf + j++ + ".pdf";
            pd.save(pdfName);
        }
        document.close();
    }

测试用例：

public static void main(String[] args) throws Exception {
        String sourcePdfPath = ("C:\\pdfFolder\\target.pdf");
        String splitPath = ("C:\\pdfFolder");
        String splitFileName = ("splitPDF");
        spiltPdf(sourcePdfPath, splitPath, splitFileName);
}

引用链接：

(17条消息) 使用Apache PDFBox实现拆分、合并PDF_似有风中泣的博客-CSDN博客

(17条消息) Java使用PDFBox操作PDF文件_pdfbox 打印 token_一个傻子程序媛的博客-CSDN博客

(17条消息) PDFbox基本操作_pdtype0font_静若繁花_jingjing的博客-CSDN博客