PDFbox的一些用法

1.到PDFbox官网下载相关的jar包

https://pdfbox.apache.org/download

2.读取文件并进行相应操作

package kang;


import java.awt.print.Book;
import java.awt.print.PageFormat;
import java.awt.print.Paper;
import java.awt.print.PrinterException;
import java.awt.print.PrinterJob;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.io.OutputStreamWriter;
import java.io.Writer;
import java.util.Iterator;


import javax.print.attribute.HashPrintRequestAttributeSet;
import javax.print.attribute.PrintRequestAttributeSet;
import javax.print.attribute.standard.PageRanges;


import org.apache.pdfbox.cos.COSName;
import org.apache.pdfbox.io.RandomAccessBuffer;
import org.apache.pdfbox.pdfparser.PDFParser;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDPageContentStream;
import org.apache.pdfbox.pdmodel.PDPageContentStream.AppendMode;
import org.apache.pdfbox.pdmodel.PDResources;
import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
import org.apache.pdfbox.printing.PDFPageable;
import org.apache.pdfbox.printing.PDFPrintable;
import org.apache.pdfbox.text.PDFTextStripper;


public class PdfReader {


	public static void main(String[] args) throws IOException{
		// 待解析PDF
		File pdfFile = new File("C:\\Users\\Administrator\\Desktop\\java线程池执行原理分析.pdf");      
		// 空白PDF
		File pdfFile_out = new File("C:\\Users\\Administrator\\Desktop\\Doc1.pdf");
		File pdfFile_outDoc = new File("C:\\Users\\Administrator\\Desktop\\3.doc");
		String imagePath="C:\\Users\\Administrator\\Desktop\\1.jpg";
		test1(pdfFile,imagePath,pdfFile_out,pdfFile_outDoc);

	}


	/*输出到doc文件，没有图片
	 * */
	private static void PrintToDoc(PDDocument document,File pdfFile_outDoc) throws IOException {
		// 获取页码
		int pages = document.getNumberOfPages();


		// 读文本内容
		PDFTextStripper stripper=new PDFTextStripper();
		// 设置按顺序输出
		FileOutputStream fos=new FileOutputStream(pdfFile_outDoc);
		Writer writer=new OutputStreamWriter(fos,"UTF-8");
		stripper.setSortByPosition(true);
		stripper.setStartPage(1);
		stripper.setEndPage(pages);
//		String content = stripper.getText(document);
//		System.out.println(content); 
		stripper.writeText(document,writer);
		writer.close();
		fos.close();
		document.close();
	}


	/**
	 * PDFprint the document at its actual size. This is the recommended way to print.
	 * 将pdf文件输出为xps格式文档
	 * XPS 是XML Paper Specification（XML文件规格书）的简称，是一种电子文件格式，它是微软公司开发的一种文档保存与查看的规范。
	 */
	private static void PDFprint(PDDocument document) throws IOException, PrinterException
	{
		PrinterJob job = PrinterJob.getPrinterJob();
		job.setPageable(new PDFPageable(document));
		job.print();
	}


	/**
	 * Prints using custom PrintRequestAttribute values.
	 * 带上要复制的页数，复制特定的页数
	 */
	private static void printWithAttributes(PDDocument document)
			throws IOException, PrinterException
	{
		PrinterJob job = PrinterJob.getPrinterJob();
		job.setPageable(new PDFPageable(document));


		PrintRequestAttributeSet attr = new HashPrintRequestAttributeSet();
		attr.add(new PageRanges(1, 1)); // pages 1 to 1


		job.print(attr);
	}


	/**
	 * Prints with a print preview dialog.
	 * 跳出提示框，问要从哪里开始复制，复制到哪里，还有一些其他参数
	 */
	private static void printWithDialog(PDDocument document) throws IOException, PrinterException
	{
		PrinterJob job = PrinterJob.getPrinterJob();
		job.setPageable(new PDFPageable(document));


		if (job.printDialog())
		{
			job.print();
		}
	}


	/**
	 * Prints with a print preview dialog and custom PrintRequestAttribute values.
     	跳出提示框，参数设置可选项比较多
	 */
	private static void printWithDialogAndAttributes(PDDocument document)
			throws IOException, PrinterException
	{
		PrinterJob job = PrinterJob.getPrinterJob();
		job.setPageable(new PDFPageable(document));


		PrintRequestAttributeSet attr = new HashPrintRequestAttributeSet();
		attr.add(new PageRanges(1, 1)); // pages 1 to 1


		if (job.printDialog(attr))
		{
			job.print(attr);
		}
	}


	/**
	 * Prints using a custom page size and custom margins.
	 * 设置纸张页面的大小
	 */
	private static void printWithPaper(PDDocument document)
			throws IOException, PrinterException
	{
		PrinterJob job = PrinterJob.getPrinterJob();
		job.setPageable(new PDFPageable(document));


		// define custom paper
		Paper paper = new Paper();
		paper.setSize(306, 396); // 1/72 inch
		paper.setImageableArea(0, 0, paper.getWidth(), paper.getHeight()); // no margins


		// custom page format
		PageFormat pageFormat = new PageFormat();
		pageFormat.setPaper(paper);


		// override the page format
		Book book = new Book();
		// append all pages
		book.append(new PDFPrintable(document), pageFormat, document.getNumberOfPages());
		job.setPageable(book);


		job.print();
	}


	/**
	 * Add an image to an existing PDF document.
	 *将图片插入pdf文件并另存到另一个pdf文件中
	 * @param inputFile The input PDF to add the image to.
	 * @param imagePath The filename of the image to put in the PDF.
	 * @param outputFile The file to write to the pdf to.
	 *
	 */
	public static void createPDFFromImage( File inputFile, String imagePath, File outputFile )
			throws IOException
	{
		try (PDDocument doc = PDDocument.load(inputFile))
		{
			//we will add the image to the first page.
			PDPage page = doc.getPage(0);


			// createFromFile is the easiest way with an image file
			// if you already have the image in a BufferedImage, 
			// call LosslessFactory.createFromImage() instead
			PDImageXObject pdImage = PDImageXObject.createFromFile(imagePath, doc);


			try (PDPageContentStream contentStream = new PDPageContentStream(doc, page, AppendMode.APPEND, true, true))
			{
				// contentStream.drawImage(ximage, 20, 20 )  // better method inspired by http://stackoverflow.com/a/22318681/535646
				// reduce this value if the image is too large
				float scale = 1f;
				contentStream.drawImage(pdImage, 20, 20, pdImage.getWidth() * scale, pdImage.getHeight() * scale);
			}
			doc.save(outputFile);
		}
	}


	private static void test1(File pdfFile ,String imagePath,File pdfFile_out, File pdfFile_outDoc) {


		PDDocument document = null;


		try
		{
			// 方式一：
			/**
           		 InputStream input = null;
           		 input = new FileInputStream( pdfFile );
           		 //加载 pdf 文档
           		 PDFParser parser = new PDFParser(new RandomAccessBuffer(input));
           		 parser.parse();
           		 document = parser.getPDDocument();
			 **/


			// 方式二：(方便很多)
			document=PDDocument.load(pdfFile);


			//			document.save("C:\\Users\\Administrator\\Desktop\\aa.pdf");//直接复制pdf
						PrintToDoc(document, pdfFile_outDoc);
			//			PDFprint(document);
			//			printWithAttributes(document);
			//			printWithDialog(document);
			//			printWithDialogAndAttributes(document);
			//			printWithPaper(document);
			//			createPDFFromImage(pdfFile,imagePath,pdfFile_out);
		}
		catch(Exception e)
		{
			System.out.println(e);


		}


	}
}

各种文档就产生了：