当前位置：首页 > article >正文

pdf内容三张以上转图片，使用spire.pdf.free

article 2024/12/25 13:30:24

一、依赖

   <spire.pdf.free.version>9.13.0</spire.pdf.free.version>
        <itextpdf.version>5.5.13</itextpdf.version>
   <dependency>
                <groupId>e-iceblue</groupId>
                <artifactId>spire.pdf.free</artifactId>
                <version>${spire.pdf.free.version}</version>
            </dependency>
            <dependency>
                <groupId>com.itextpdf</groupId>
                <artifactId>itextpdf</artifactId>
                <version>${itextpdf.version}</version>
            </dependency>

二、思路：

①问题：

1、spire.pdf.free只能免费转换每个PDF的前三页

2、转换速度慢

3、多线程合并后页数顺序问题

②解决

1、将PDF文档根据页数截断为多个PDF，每个PDF最多三页

2、使用线程池多线程异步处理

3、map里的索引

三、代码：

1、转换的类

package com.shiqiao.nev.business.infra.adapter.pdftoPic;

import com.itextpdf.text.Document;
import com.itextpdf.text.DocumentException;
import com.itextpdf.text.pdf.PdfCopy;
import com.itextpdf.text.pdf.PdfImportedPage;
import com.itextpdf.text.pdf.PdfReader;
import com.spire.pdf.PdfDocument;
import com.spire.pdf.graphics.PdfImageType;

import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.List;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Future;

public class PdfToPicConverter {

    private final byte[] pdfFileByteStream;
    private final Integer pageCount;
    private List<InputStream> picResult;


    public PdfToPicConverter(InputStream pdfFile) {
        try {
            pdfFileByteStream = inputStreamToByteArray(pdfFile);
        } catch (Exception e) {
            throw new RuntimeException("pdf文件转换为字节流失败", e);
        }
        PdfDocument pdf = new PdfDocument();
        pdf.loadFromStream(new ByteArrayInputStream(pdfFileByteStream));
        pageCount = pdf.getPages().getCount();
   
    }

    public PdfToPicConverter(byte[] pdfFile) {
        pdfFileByteStream = pdfFile;
      PdfDocument pdf = new PdfDocument();
        pdf.loadFromStream(new ByteArrayInputStream(pdfFileByteStream));
        pageCount = pdf.getPages().getCount();
   
    }

    public List<InputStream> convertToPictures(ExecutorService executorService) {

        picResult = new ArrayList<>();

        // 每三页为一组
        int groupSize = 3;
        int numGroups = (pageCount + groupSize - 1) / groupSize;

        List<Future<List<InputStream>>> futures = new ArrayList<>();
        for (int i = 0; i < numGroups; i++) {
            int startPage = i * groupSize;
            int endPage = Math.min(startPage + groupSize, pageCount);
            if (executorService != null) {
                futures.add(executorService.submit(() -> convertGroup(startPage, endPage)));
            }

        }

        // 等待所有任务完成并合并结果
        for (Future<List<InputStream>> future : futures) {
            try {
                picResult.addAll(future.get());
            } catch (Exception e) {
                throw new RuntimeException("图片转换失败", e);
            }
        }

        return picResult;
    }

    private InputStream splitPDFFile(byte[] pdfFileByteStream, int from, int end) {
        Document document = null;
        PdfCopy copy = null;

        try (ByteArrayInputStream bais = new ByteArrayInputStream(pdfFileByteStream);
             ByteArrayOutputStream baos = new ByteArrayOutputStream()) {

            PdfReader reader = new PdfReader(bais);
            int n = reader.getNumberOfPages();
            if (end == 0 || end > n) {
                end = n;
            }
            document = new Document(reader.getPageSize(1));
            copy = new PdfCopy(document, baos);
            document.open();
            for (int j = from + 1; j <= end; j++) {  // 注意这里j从from+1开始
                document.newPage();
                PdfImportedPage page = copy.getImportedPage(reader, j);
                copy.addPage(page);
            }
            document.close();
            return new ByteArrayInputStream(baos.toByteArray());
        } catch (IOException | DocumentException e) {
            throw new RuntimeException("PDF文件拆分失败", e);
        }
    }


    private List<InputStream> convertGroup(int startPage, int endPage) {
        InputStream inputStream = splitPDFFile(pdfFileByteStream, startPage, endPage);
        PdfDocument pdf = new PdfDocument();
        pdf.loadFromStream(inputStream);
        int end = endPage - startPage;
        List<InputStream> groupResult = new ArrayList<>();
        for (int i = 0; i < end; i++) {
            BufferedImage image = pdf.saveAsImage(i, PdfImageType.Bitmap, 500, 500);
            try (ByteArrayOutputStream baos = new ByteArrayOutputStream()) {
                ImageIO.write(image, "PNG", baos);
                groupResult.add(new ByteArrayInputStream(baos.toByteArray()));
            } catch (IOException e) {
                throw new RuntimeException("图片保存失败", e);
            }
        }
        pdf.close();
        return groupResult;

        return new ArrayList<>();
    }

    protected byte[] inputStreamToByteArray(InputStream inputStream) throws IOException {
        int bufferSize = 4096;
        byte[] buffer = new byte[bufferSize];
        int bytesRead;
        ByteArrayOutputStream baos = new ByteArrayOutputStream();

        while ((bytesRead = inputStream.read(buffer)) != -1) {
            baos.write(buffer, 0, bytesRead);
        }

        return baos.toByteArray();
    }
}

2、使用的地方

  public List<FileDTO> pdfToPng(byte[] filebyte, String fileName) {
        List<FileDTO> fileDTOS = new ArrayList<>();
        PdfToPicConverter pdfToPicConverter = new PdfToPicConverter(filebyte);
        List<InputStream> inputStreams = pdfToPicConverter.convertToPictures(pdfCovertPicExectorPool);

        inputStreams.forEach((e) -> {
            // 生成文件名
            String pgnNames = "fileName"+inputStreams.indexOf(e) + ".png";
            FileDTO fileDTO = new FileDTO(e, pgnNames);
            fileDTOS.add(fileDTO);
        });
        return fileDTOS;
    }