通过pdfBox读取pdf内容

引入依赖:

<dependency>
			 <groupId>org.apache.pdfbox</groupId>
			 <artifactId>pdfbox</artifactId>
			 <version>2.0.1</version>
		 </dependency>
		<dependency>
			<groupId>org.apache.pdfbox</groupId>
			<artifactId>fontbox</artifactId>
			<version>2.0.0</version>
		</dependency>
		<dependency>
			<groupId>org.apache.pdfbox</groupId>
			<artifactId>jempbox</artifactId>
			<version>1.8.11</version>
		</dependency>
		<dependency>
			<groupId>org.apache.pdfbox</groupId>
			<artifactId>xmpbox</artifactId>
			<version>2.0.0</version>
		</dependency>
		<dependency>
			<groupId>org.apache.pdfbox</groupId>
			<artifactId>preflight</artifactId>
            <version>2.0.0</version>
		</dependency>
		<dependency>
			<groupId>org.apache.pdfbox</groupId>
			<artifactId>pdfbox-tools</artifactId>
			<version>2.0.0</version>
        </dependency>

2、通过引用处理文档,代码示例如下:

import org.apache.pdfbox.multipdf.PDFMergerUtility;
import org.apache.pdfbox.multipdf.Splitter;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDPageContentStream;
import org.apache.pdfbox.pdmodel.PDPageTree;
import org.apache.pdfbox.pdmodel.common.PDRectangle;
import org.apache.pdfbox.pdmodel.font.PDFont;
import org.apache.pdfbox.pdmodel.font.PDType0Font;
import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
import org.apache.pdfbox.text.PDFTextStripper;

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;

public class PdfBoxUtil {

    /**
     * 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());
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            try {
                //关闭文档
                if (doc != null) {
                    doc.close();
                }
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
        return content;
    }

    /**
     * 插入文字到pdf中
     *
     * @param inputFilePath
     * @param outputFilePath
     * @param pageNum
     * @param message
     * @throws Exception
     */
    public static void insertWordContent(String inputFilePath, String outputFilePath, Integer pageNum, String message) throws Exception {
        File inputPDFFile = new File(inputFilePath);
        File outputPDFFile = new File(outputFilePath);
        PDDocument doc = null;
        try {
            doc = PDDocument.load(inputPDFFile);
            PDPageTree allPages = doc.getDocumentCatalog().getPages();
//            PDFont font = PDType1Font.HELVETICA_BOLD;
            PDFont font = PDType0Font.load(doc, new File("C:\\Users\\DELL\\Desktop\\FZLTHJW.TTF"));
            // 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;
            // 计算页面的中心位置
            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();
            // 设置字体和字体大小
            contentStream.setFont(font, fontSize);
            // 设置字体颜色(如下为红色)
            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);
            }
            // 写入文字
            contentStream.drawString(message);
            contentStream.endText();
            contentStream.close();
            // 保存到新文档中
            doc.save(outputPDFFile);
            System.out.println("成功向pdf插入文字");
        } finally {
            if (doc != null) {
                doc.close();
            }
        }
    }

    /**
     * 在pdf中插入图片
     *
     * @param inputFilePath
     * @param imagePath
     * @param outputFilePath
     * @param pageNum
     * @throws Exception
     */
    public static void insertImageContent(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();
        }
    }

    /**
     * 合并pdf文件
     *
     * @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();
            }
        }
    }


    /**
     * 将pdf文件分割成多个
     *
     * @param sourcePdfPath
     * @param splitPath
     * @param splitFileName
     * @throws Exception
     */
    public static void spiltPdf(String sourcePdfPath, String splitPath, String splitFileName) throws Exception {
        File targetDir = new File(splitPath);
        if (!targetDir.exists()) {
            targetDir.mkdirs();
        }
        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();
    }


    public static void main(String args[]) throws IOException {
        // 1、读取pdf文件
//        String filePath = "F:\\image_test\\sample.pdf";
//        String content = readPdf(filePath);
//        System.out.println("读取内容:" + content);

        // 2、pdf中插入文字
//        String inFilePath = "F:\\image_test\\sample.pdf";
//        String outFilePath = "F:\\image_test\\sample2.pdf";
//        try {
//            insertWordContent(inFilePath,outFilePath,1,"插入的小狗文字");
//        } catch (Exception e) {
//            e.printStackTrace();
//        }

        // 3、pdf文件插入图片
//        String inFilePath = "F:\\image_test\\sample.pdf";
//        String imagePath = "F:\\image_test\\sun1.jpg";
//        String outFilePath = "F:\\image_test\\sample3.pdf";
//        try {
//            insertImageContent(inFilePath,imagePath,outFilePath,1);
//        } catch (Exception e) {
//            e.printStackTrace();
//        }

        // 4、合并pdf文件
//        String filePath1 = "F:\\image_test\\sample.pdf";
//        String filePath2 = "F:\\image_test\\sample2.pdf";
//        String outFilePath = "F:\\image_test\\sample4.pdf";
//        List filePathList = new ArrayList<>();
//        filePathList.add(filePath1);
//        filePathList.add(filePath2);
//        try {
//            mergePdf(filePathList, outFilePath);
//        } catch (Exception e) {
//            e.printStackTrace();
//        }

        // 5、拆分pdf文件
        String inFilePath = "F:\\image_test\\sample4.pdf";
        String targetPath = "F:\\image_test\\11";
        String targetFileName = "aa";
        try {
            spiltPdf(inFilePath, targetPath, targetFileName);
        } catch (Exception e) {
            e.printStackTrace();
        }

    }
}

如上的示例代码,依次按照顺序执行main方法示例
(1)、执行1效果:
通过pdfBox读取pdf内容_第1张图片
(2)执行2效果:创建新文件且插入文字。
通过pdfBox读取pdf内容_第2张图片
示例2需要我们自行下载字体,可以以下地址下载:
https://www.fontke.com/font/10279514/download/
在代码的如下位置引入该字体文件
通过pdfBox读取pdf内容_第3张图片

(3)、3执行效果,插入图片成功
通过pdfBox读取pdf内容_第4张图片
(4)、4执行效果,合并pdf会出现2页
通过pdfBox读取pdf内容_第5张图片
(5)、5执行效果,将多页的pdf文件进行一页一页分割
通过pdfBox读取pdf内容_第6张图片

学海无涯苦作舟!!!

你可能感兴趣的:(Java初探,javaWEB,pdf)