pdf和html互相转换demo

前言

仅记录学习笔记，如有错误欢迎指正。

最近项目需要把用户上传的pdf裁剪出一部分，和另外一个pdf拼接，基于目前的代码，记录一下pdf和html相互转换的demo。网上大多数的转换都有问题。

pdf转html

mavan引入jar包：
这个jar还会依赖其他jar包，maven会自动一起导入的。

    
            net.sf.cssbox
            pdf2dom
            1.7
        

注释的代码可以输出为html文件
path为：“D:\xxx\abc.html”

  public static void  pdfToHtmlTest(String inPdfPath, String outputHtmlPath) {
        try {
//            BufferedWriter out = new BufferedWriter(new OutputStreamWriter(
//                    new FileOutputStream(new File(filePath)), StandardCharsets.UTF_8));
            //加载PDF文档
            //PDDocument document = PDDocument.load(bytes);
            PDDocument document = PDDocument.load(new File("1.pdf"));
            PDFDomTree pdfDomTree = new PDFDomTree();
            Writer out = new StringWriter();
            pdfDomTree.writeText(document, out);
//            String htmlOutput = out.toString();
            System.out.println(out.toString());
        } catch (Exception e) {
            e.printStackTrace();


        }
    }

这种方法转为html后，css样式就确定了，所以如果要拼接其他的html内容，如何在不影响其他css样式的情况下去拼接并且成功显示？很麻烦。暂时未能实现。

html转pdf

maven

   

        
            com.itextpdf
            html2pdf
            3.0.2
        
        
        
            com.itextpdf
            font-asian
            7.1.13
        

demo:

package com.test.util.HtmlToPdf;

import com.itextpdf.html2pdf.ConverterProperties;
import com.itextpdf.html2pdf.HtmlConverter;
import com.itextpdf.io.font.PdfEncodings;
import com.itextpdf.kernel.font.PdfFont;
import com.itextpdf.kernel.font.PdfFontFactory;
import com.itextpdf.kernel.geom.PageSize;
import com.itextpdf.kernel.pdf.PdfDocument;
import com.itextpdf.kernel.pdf.PdfWriter;
import com.itextpdf.layout.font.FontProvider;
import com.itextpdf.styledxmlparser.jsoup.helper.StringUtil;

import java.io.*;
import java.nio.charset.StandardCharsets;



public class Html2PdfUtil {

    /**
     * html转pdf
     *
     * @param  inputStream 输入流
     * @param fontPath 字体路径，ttc后缀的字体需要添加,0
     * @param  outputStream 输出流
     * @date : 2021/1/15 14:07
     */
    public static void convertToPdf(InputStream inputStream, String fontPath, OutputStream outputStream) throws IOException, IOException {
        PdfWriter pdfWriter = new PdfWriter(outputStream);
        PdfDocument pdfDocument = new PdfDocument(pdfWriter);
        //设置为A4大小
        pdfDocument.setDefaultPageSize(PageSize.A4);
        //添加水印
//        pdfDocument.addEventHandler(PdfDocumentEvent.END_PAGE, new WaterMarkEventHandler(waterMark));

        //添加中文字体支持
        ConverterProperties properties = new ConverterProperties();
        FontProvider fontProvider = new FontProvider();

        PdfFont sysFont = PdfFontFactory.createFont("STSongStd-Light", "UniGB-UCS2-H", false);
        fontProvider.addFont(sysFont.getFontProgram(), "UniGB-UCS2-H");

        //添加自定义字体，例如微软雅黑
        if (!StringUtil.isBlank(fontPath)){
            PdfFont microsoft = PdfFontFactory.createFont(fontPath, PdfEncodings.IDENTITY_H, false);
            fontProvider.addFont(microsoft.getFontProgram(), PdfEncodings.IDENTITY_H);
        }

        properties.setFontProvider(fontProvider);
        HtmlConverter.convertToPdf(inputStream, pdfDocument, properties);

        pdfWriter.close();
        pdfDocument.close();
    }


    public static void main(String[] args) throws IOException {
        String htmlText = " \n" +
                "\n" +
                "\n" +
                "      
iText
\n" +
                "      
大发发发萨法发发呆发呆东方大厦发
\n" +
                "      
Your developer here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的journey with iText begins here法大大是地方大发顺丰萨法发顺丰的
\n" +
                " \n" +
                "      
Your developer here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的journey with iText begins here法大大是地方大发顺丰萨法发顺丰的
\n" +
                " \n" +
                "      
iText
\n" +
                "      
大发发发萨法发发呆发呆东方大厦发
\n" +
                "      
Your developer here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的journey with iText begins here法大大是地方大发顺丰萨法发顺丰的
\n" +
                " \n" +
                "      
Your developer here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的here法大大是地方大发顺丰萨法发顺丰的journey with iText begins here法大大是地方大发顺丰萨法发顺丰的
\n" +
                " ";
        File file = new File("test.pdf");
        convertToPdf(convertStringToInputStream(htmlText),"",new FileOutputStream(file));
    }
    // String -> InputStream
    private static InputStream convertStringToInputStream(String name) {

        InputStream result = new ByteArrayInputStream(name.getBytes(StandardCharsets.UTF_8));
        return result;
    }


    /**
     * pdf文件转byte数组
     * @param filePath
     * @return
     */
    private byte[] getBytes(String filePath){
        byte[] buffer = null;
        try {
            File file = new File(filePath);
            FileInputStream fis = new FileInputStream(file);
            ByteArrayOutputStream bos = new ByteArrayOutputStream(1000);
            byte[] b = new byte[1000];
            int n;
            while ((n = fis.read(b)) != -1) {
                bos.write(b, 0, n);
            }
            fis.close();
            bos.close();
            buffer = bos.toByteArray();
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return buffer;
    }


}