利用iText 合并PDF与分解PDF的例子

很久前记录过一篇创建PDF 的文章，可以参考这里 java 利用 itext 创建pdf . 一般只是创建pdf, 但有些特殊情况还需要合并pdf 与拆分pdf, 这些功能对一iText 来说，不过是小菜一碟。创建pdf 的方法还是参考以前的文章吧，毕竟里面给出的函数齐全一些。今天用iText 5.0 测试了PDF 的合并与拆分，效果还是很好的，而且性能也不错。

java itext 合并PDF
1. 首先准备要合并的pdf，将内容放在一个 InputStream list 中，准备好目标文件目录
2. 调用 合并 pdf 的方法: concatPDFs, 传入输入流list, 输出文件流，是否处理分页参数.
3. 在 concatPDFs 方法中循环处理 将输入流转换成 PdfReader，并处理页码.
4. 利用 Document class和 PdfWriter.getInstance() 方法生成目标文件
5. 在循环中将所有输入的 PDF 合并到输出文件中.
代码如下 ：

package com.yihaomen.pdf;

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

import com.itextpdf.text.Document;
import com.itextpdf.text.pdf.BaseFont;
import com.itextpdf.text.pdf.PdfContentByte;
import com.itextpdf.text.pdf.PdfImportedPage;
import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.PdfWriter;

public class MergePDF {

	public static void main(String[] args) {
		try {
			List pdfs = new ArrayList();
			for(int i=0;i<10;i++){
				pdfs.add(new FileInputStream("d:\\pdf\\" + i +".pdf"));
			}
			OutputStream output = new FileOutputStream("d:\\pdf\\merge.pdf");
			MergePDF.concatPDFs(pdfs, output, true);
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

	public static void concatPDFs(List streamOfPDFFiles,
			OutputStream outputStream, boolean paginate) {

		Document document = new Document();
		try {
			List pdfs = streamOfPDFFiles;
			List readers = new ArrayList();
			int totalPages = 0;
			Iterator iteratorPDFs = pdfs.iterator();

			// Create Readers for the pdfs.
			while (iteratorPDFs.hasNext()) {
				InputStream pdf = iteratorPDFs.next();
				PdfReader pdfReader = new PdfReader(pdf);
				readers.add(pdfReader);
				totalPages += pdfReader.getNumberOfPages();
			}
			// Create a writer for the outputstream
			PdfWriter writer = PdfWriter.getInstance(document, outputStream);

			document.open();
			BaseFont bf = BaseFont.createFont(BaseFont.HELVETICA,
					BaseFont.CP1252, BaseFont.NOT_EMBEDDED);
			PdfContentByte cb = writer.getDirectContent(); // Holds the PDF
			// data

			PdfImportedPage page;
			int currentPageNumber = 0;
			int pageOfCurrentReaderPDF = 0;
			Iterator iteratorPDFReader = readers.iterator();

			// Loop through the PDF files and add to the output.
			while (iteratorPDFReader.hasNext()) {
				PdfReader pdfReader = iteratorPDFReader.next();
				// Create a new page in the target for each source page.
				while (pageOfCurrentReaderPDF < pdfReader.getNumberOfPages()) {
					document.newPage();
					pageOfCurrentReaderPDF++;
					currentPageNumber++;
					page = writer.getImportedPage(pdfReader,
							pageOfCurrentReaderPDF);
					cb.addTemplate(page, 0, 0);

					// Code for pagination.
					if (paginate) {
						cb.beginText();
						cb.setFontAndSize(bf, 9);
						cb.showTextAligned(PdfContentByte.ALIGN_CENTER, ""
								+ currentPageNumber + " of " + totalPages, 520,
								5, 0);
						cb.endText();
					}
				}
				pageOfCurrentReaderPDF = 0;
			}
			outputStream.flush();
			document.close();
			outputStream.close();
		} catch (Exception e) {
			e.printStackTrace();
		} finally {
			if (document.isOpen())
				document.close();
			try {
				if (outputStream != null)
					outputStream.close();
			} catch (IOException ioe) {
				ioe.printStackTrace();
			}
		}
	}
}

java itext 根据页码拆分 pdf 文档
目前简单实现根据页码拆分pdf 文档,代码如下:

package com.yihaomen.pdf;

import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;

import com.itextpdf.text.Document;
import com.itextpdf.text.pdf.PdfContentByte;
import com.itextpdf.text.pdf.PdfImportedPage;
import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.PdfWriter;

public class SplitPDF {
	
	public static void main(String[] args) {
	    try {
	        splitPDF(new FileInputStream("d:\\pdf\\merge.pdf"), 
	                    new FileOutputStream("d:\\pdf\\output1.pdf"), 1, 5);
	        splitPDF(new FileInputStream("d:\\pdf\\merge.pdf"), 
	                    new FileOutputStream("d:\\pdf\\output2.pdf"), 6, 10);
	         
	    } catch (Exception e) {
	        e.printStackTrace();
	    }
	}

	public static void splitPDF(InputStream inputStream,
			OutputStream outputStream, int fromPage, int toPage) {
		
		Document document = new Document();
		try {
			PdfReader inputPDF = new PdfReader(inputStream);
			int totalPages = inputPDF.getNumberOfPages();

			// make fromPage equals to toPage if it is greater
			if (fromPage > toPage) {
				fromPage = toPage;
			}
			if (toPage > totalPages) {
				toPage = totalPages;
			}

			// Create a writer for the outputstream
			PdfWriter writer = PdfWriter.getInstance(document, outputStream);
			document.open();
			PdfContentByte cb = writer.getDirectContent(); // Holds the PDF data
			PdfImportedPage page;

			while (fromPage <= toPage) {
				document.newPage();
				page = writer.getImportedPage(inputPDF, fromPage);
				cb.addTemplate(page, 0, 0);
				fromPage++;
			}
			outputStream.flush();
			document.close();
			outputStream.close();
		} catch (Exception e) {
			e.printStackTrace();
		} finally {
			if (document.isOpen())
				document.close();
			try {
				if (outputStream != null)
					outputStream.close();
			} catch (IOException ioe) {
				ioe.printStackTrace();
			}
		}
	}
}

如果需要整个源代码的，可以在这里下载：

点击下载此文件

From：一号门