JAVA PDF操作之实现截取N页和多个PDF合并

<dependency>
    <groupid>com.itextpdf</groupid>
    <artifactid>itextpdf</artifactid>
    <version>5.5.13</version>
</dependency>

import com.itextpdf.text.document;
import com.itextpdf.text.pdf.pdfcopy;
import com.itextpdf.text.pdf.pdfimportedpage;
import com.itextpdf.text.pdf.pdfreader;
import org.apache.pdfbox.pdmodel.pddocument;
import org.apache.pdfbox.pdmodel.pdpagetree;
import org.apache.pdfbox.rendering.pdfrenderer;

import javax.imageio.imageio;
import java.awt.image.bufferedimage;
import java.io.*;

public class pdfutil {

    /**
     * 截取pdffile的第from页至第end页，组成一个新的文件名
     *
     * @param pdffile 要切割的pdf文件
     * @param newfile 切割后形成的新的pdf文件
     * @param from    从第n页开始
     * @param end     到第n页结束
     */
    public static void partitionpdf(string pdffile, string newfile, int from, int end) {
        document document = null;
        pdfcopy copy = null;
        pdfreader reader = null;
        try {
            reader = new pdfreader(pdffile);
            int pagecount = reader.getnumberofpages();
            if (from < 1) {
                from = 1;
            }
            if (from > pagecount) {
                from = pagecount;
            }
            if (end == 0 || end > pagecount) {
                end = pagecount;
            }
            document = new document(reader.getpagesize(1));
            copy = new pdfcopy(document, new fileoutputstream(newfile));
            document.open();
            for (int j = from; j <= end; j++) {
                document.newpage();
                pdfimportedpage page = copy.getimportedpage(reader, j);
                copy.addpage(page);
            }
        } catch (exception e) {
            e.printstacktrace();
        } finally {
            if (document != null) {
                document.close();
            }
            if (copy != null) {
                copy.close();
            }
            if (reader != null) {
                reader.close();
            }
        }
    }

    /**
     * pdf转图片
     *
     * @param pdffile   pdf 文件
     * @param imagefile 输出的图片文件
     * @param from      开始页 从1开始
     * @param end       结束页 最大为pdf总页数
     * @throws exception
     */
    public static void pdftoimage(string pdffile, string imagefile, int from, int end) throws exception {
        pddocument doc = null;
        bytearrayoutputstream os = null;
        inputstream stream = null;
        outputstream out = null;
        try {
            //pdf路径
            stream = new fileinputstream(pdffile);
            // 加载解析pdf文件
            doc = pddocument.load(stream);
            pdfrenderer pdfrenderer = new pdfrenderer(doc);
            pdpagetree pages = doc.getpages();
            int pagecount = pages.getcount();
            if (from < 1) {
                from = 1;
            }
            if (from > pagecount) {
                from = pagecount;
            }
            if (end == 0 || end > pagecount) {
                end = pagecount;
            }
            for (int i = from; i <= end; i++) {
                bufferedimage bim = pdfrenderer.renderimagewithdpi(i - 1, 200); //pdfbox 是从0开始的，from初始值为1，所以这边要减 i-1
                os = new bytearrayoutputstream();
                imageio.write(bim, "jpg", os);
                byte[] datalist = os.tobytearray(); 
                //只取一页，等于传进来的名称，多页时，加上 页号
                string imagefilepath = from == end ? saveimgfile : saveimgfile.replace(".jpg", "_" + i + ".jpg");
                file file = new file(imagefilepath);
                if (!file.getparentfile().exists()) {
                    // 不存在则创建父目录及子文件
                    file.getparentfile().mkdirs();
                    file.createnewfile();
                }
                out = new fileoutputstream(file);
                out.write(datalist);
            }
        } catch (exception e) {
            e.printstacktrace();
        } finally {
            if (doc != null) {
                doc.close();
            }
            if (os != null) {
                os.close();
            }
            if (stream != null) {
                stream.close();
            }
            if (out != null) {
                out.close();
            }
        }
    }

    //多个pdf合并成一个
    public static void mergepdffiles(list<string> pdffiles, string outputpdf) throws ioexception {
        // 创建一个新的 pdf 阅读器对象和一个新的 pdf 写入对象
        pdfreader reader = null;
        pdfcopy copy = null;
        document document = new document();
        try {
            // 创建 pdf 阅读器对象和写入对象
            reader = new pdfreader(pdffiles.get(0));
            copy = new pdfcopy(document, new fileoutputstream(outputpdf));
            // 打开文档准备写入内容
            document.open();

            // 将第一个 pdf 的所有页面复制到输出 pdf 中
            for (int i = 1; i <= reader.getnumberofpages(); i++) {
                pdfimportedpage page = copy.getimportedpage(reader, i);
                copy.addpage(page);
            }

            // 将其它pdf的所有页，输出到 pdf 中
            for (int i = 1; i < pdffiles.size(); i++) {
                reader = new pdfreader(pdffiles.get(i));
                for (int j = 1; j <= reader.getnumberofpages(); j++) {
                    pdfimportedpage page = copy.getimportedpage(reader, j);
                    copy.addpage(page);
                }
            }

        } catch (exception e) {
            e.printstacktrace();
        } finally {
            if (document != null) {
                document.close();
            }
            if (copy != null) {
                copy.close();
            }
            if (reader != null) {
                reader.close();
            }
        }
    }
}

@test
void pdf() throws exception {
    string pdffile = "d:\\desktop\\20220117.pdf";
    string jpgfile = "d:\\desktop\\20220117.jpg";
    pdfutil.pdftoimage(pdffile, jpgfile, 1, 1); 
}

@test
 void testmerge() throws ioexception {
    list<string> pdffiles = new arraylist<>();
    pdffiles.add("d:\\projects\\20231225180735.pdf");
    pdffiles.add("d:\\projects\\20231225182535.pdf");
    pdffiles.add("d:\\projects\\20231225184135.pdf");
    pdfutil.mergepdffiles(pdffiles, "d:\\projects\\new.pdf");
}