将一个PDF文件按页拆分成多个PDF,或者将某一页中某一部分内容单独拆分出来作为一个新的PDF
本文使用pdfbox实现,因此需要先导入pdfbox的依赖
<!-- https://mvnrepository.com/artifact/org.apache.pdfbox/pdfbox -->
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>pdfbox</artifactId>
<version>2.0.25</version>
</dependency>
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>jbig2-imageio</artifactId>
<version>3.0.2</version>
</dependency>
代码如下(示例):
public static void splitPdf(File sourceFile) throws IOException {
splitPdf(sourceFile, 1);
}
public static void splitPdf(File sourceFile, String targetPath) throws IOException {
splitPdf(sourceFile, targetPath, 1);
}
public static void splitPdf(File sourceFile, Integer pageStep) throws IOException {
splitPdf(sourceFile, sourceFile.getParentFile().getPath(), 1);
}
/**
* @return void
* @Description //TODO pdf拆分,结果命名规则为原文件名-startPage_endPage.pdf
* @Date 2022/2/16 10:20
* @Param [sourceFile:要拆分的pdf文件, targetPath:结果输出目录, pageStep:以多少页为基准拆分]
**/
public static void splitPdf(File sourceFile, String targetPath, Integer pageStep) throws IOException {
String fileName = sourceFile.getName().replace(".pdf", "");
PDDocument document = PDDocument.load(sourceFile);
int pageSize = document.getNumberOfPages();
int count = pageSize / pageStep + (pageSize % pageStep == 0 ? 0 : 1);
log.info("pageSize : {}, pageStep : {}, count : {}", pageSize, pageStep, count);
PDDocument doc = new PDDocument();
PDPage page = null;
String splitName = null;
for (int i = 0; i < count; i++) {
PDFContentTool.clearDocument(doc);
int startPage = i * pageStep;
int endPage = startPage + pageStep;
if (endPage > pageSize) {
endPage = pageSize;
}
splitName = fileName + "-" + (startPage + 1) + "_" + endPage + ".pdf";
for (int index = startPage; index < endPage; index++) {
page = document.getPage(index);
doc.addPage(page);
}
File outFile = new File(targetPath, splitName);
doc.save(outFile);
}
document.close();
doc.close();
}
/**
* @return void
* @Description //TODO pdf拆分,结果命名规则为原文件名-startPage_endPage.pdf
* @Date 2022/2/16 10:20
* @Param [sourceFile:要拆分的pdf文件, targetPath:结果输出目录, pageIndex,:从哪里开始拆分]
**/
public static void splitPdfWithPageIndex(File sourceFile, String targetFile, Integer pageIndex) throws IOException {
splitPdfWithPageIndex(sourceFile,targetFile,pageIndex,1);
}
/**
* @return void
* @Description //TODO pdf拆分,结果命名规则为原文件名-startPage_endPage.pdf
* @Date 2022/2/16 10:20
* @Param [sourceFile 要拆分的pdf文件, targetFile 结果输出目录, pageIndex 从哪里开始拆分, totalPages 总共拆出多少页]
**/
public static void splitPdfWithPageIndex(File sourceFile, String targetFile, Integer pageIndex, Integer totalPages) throws IOException {
PDDocument document = PDDocument.load(sourceFile);
PDDocument doc = new PDDocument();
PDPage page = null;
for (int index = pageIndex; index < pageIndex + totalPages; index++) {
page = document.getPage(index - 1);
doc.addPage(page);
}
doc.save(targetFile);
document.close();
doc.close();
}
代码解析:
splitPdf:splitPdf的作用在于将一个pdf以pageStep为步长,按照没pageStep页拆分一个PDF的规则将整个PDF文件全部拆出。
splitPdfWithPageIndex:splitPdfWithPageIndex的作用在于将一个PDF文件从pageIndex位置开始,选totalPages页数据,生成一个新的PDF文件。
将PDF中某一部分内容拆分出来,这一部分的处理思路是先将PDF文件转换成图片,然后采用截图的方式将需要的内容截取出来生成新的图片,然后再将这个图片转换成PDF文件。
PDF转换图片的部分在java使用pdfbox将PDF转化为图片这一篇中有描述,感兴趣的可以去看看
代码如下(示例):
public static BufferedImage splitPdfWithImage(PDDocument document, Integer page) throws IOException {
PDFRenderer renderer = new PDFRenderer(document);
BufferedImage bufferedImage = renderer.renderImage(page - 1, 5);
return bufferedImage;
}
public static void cutPdfWithImage(PDDocument document, CutInfoEntity cutInfo) throws IOException {
File file = new File(cutInfo.getOutFile());
cutPdfWithImage(document, cutInfo.getPage(), cutInfo.getReceiptCount(), cutInfo.getCutRange().getStart(), cutInfo.getCutRange().getEnd(), file);
}
public static void cutPdfWithImage(PDDocument document, Integer page, Integer receiptCount, Integer start, Integer end, String outFile) throws IOException {
File file = new File(outFile);
cutPdfWithImage(document, page, receiptCount, start, end, file);
}
/**
* @Description //TODO 纵向切分,切分内容为宽为PDF文件宽度,高为制动高度的矩形区域
* @Date 2022/3/4 16:35
* @Param [document 要切分的PDF文件
* page表示要切分的内容在第几页
* receiptCount 本工具哟用于拆分银行回单,一页可能有多张回单,这个参数表示一页PDF有多少张。主要用于计算切分后的内容转换成A4大小的PDF时的高度。
* start 从x轴哪个位置开始切分
* end 切到那个位置
* outFile 输出文件
* @return void
**/
public static void cutPdfWithImage(PDDocument document, Integer page, Integer receiptCount, Integer start, Integer end, File outFile) throws IOException {
BufferedImage image = splitPdfWithImage(document, page);
int subWidth = image.getWidth();
int subHeight = end - start;
image = image.getSubimage(0, start, subWidth, subHeight);
PDDocument outDocument = new PDDocument();
PDImageXObject imageXObject = LosslessFactory.createFromImage(outDocument, image);
PDPage pdPage = new PDPage(PDRectangle.A4);
PDPage documentPage = document.getPage(page - 1);
PDResources resources = documentPage.getResources();
Iterable<COSName> fontNames = resources.getFontNames();
for (COSName cosName : fontNames) {
PDFont font = resources.getFont(cosName);
PDResources pdResources = pdPage.getResources();
if (pdResources == null) {
pdResources = new PDResources();
pdPage.setResources(pdResources);
}
pdPage.getResources().put(cosName, font);
}
outDocument.addPage(pdPage);
PDPageContentStream pageContentStream = new PDPageContentStream(outDocument, pdPage);
float height = pdPage.getMediaBox().getHeight() / receiptCount;
float y = pdPage.getMediaBox().getHeight() - height;
pageContentStream.drawImage(imageXObject, 0, y, pdPage.getMediaBox().getWidth(), height);
pageContentStream.close();
if (!outFile.getParentFile().exists()) {
outFile.getParentFile().mkdirs();
}
outDocument.save(outFile);
outDocument.close();
}