开源PDF工具 Apache PDFBox 认识及使用(知识点+案例) - ToB企服应用市场:ToB评测及商务社交产业平台

<dependencies>
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>pdfbox</artifactId>
<version>2.0.28</version>
</dependency>
</dependencies>

复制代码

package com.changlu.demos;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import java.io.File;
import java.net.URLDecoder;
/**
* @Description:
* @Author: changlu
* @Date: 1:28 PM
*/
public class Demo1 {
public static void main(String[] args) throws Exception{
//读取resources目录下input.pdf文件
String inputFile = URLDecoder.decode(Demo1.class.getClassLoader().getResource("input.pdf").getFile(), "UTF-8");
PDDocument pdDocument = PDDocument.load(new File(inputFile));
PDFTextStripper pdfTextStripper = new PDFTextStripper();
//读取pdf中所有的文件
String fullText = pdfTextStripper.getText(pdDocument);
System.out.println(fullText);
}
}

复制代码

package com.changlu;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import java.io.InputStream;
/**
* @Description:
* @Author: changlu
* @Date: 11:19 AM
*/
public class Main {
public static void main(String[] args) throws Exception{
//读取resources目录下input.pdf文件
InputStream is = Main.class.getClassLoader().getResourceAsStream("input.pdf");
PDDocument pdDocument = PDDocument.load(is);
PDFTextStripper pdfTextStripper = new PDFTextStripper();
//读取所有的分页
for (int i = 1; i <= pdDocument.getNumberOfPages(); i++) {
//设置起始-结束页这里设置指定某页
pdfTextStripper.setStartPage(i);
pdfTextStripper.setEndPage(i);
//读取每一页
String pageText = pdfTextStripper.getText(pdDocument);
System.out.println(String.format("第%s页读取内容：", i));
System.out.println(pageText);
}
}
}

复制代码

package com.changlu.demos;
import com.changlu.Main;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDPageContentStream;
import org.apache.pdfbox.pdmodel.font.PDType0Font;
import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
import org.apache.pdfbox.pdmodel.graphics.state.PDExtendedGraphicsState;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStream;
import java.net.URLDecoder;
import java.nio.file.Files;
import java.nio.file.Paths;
/**
* @Description: 添加页眉、页脚
* @Author: changlu
* @Date: 1:38 PM
*/
public class Demo3 {
public static void main(String[] args) throws Exception{
//读取resources目录下input.pdf文件
InputStream is = Main.class.getClassLoader().getResourceAsStream("input.pdf");
PDDocument pdDocument = PDDocument.load(is);
//自定义字体 C:\Users\93997\Desktop\watermark tools\watermarkTools\target\classes\ttfs
//URLDecoder.decode() 方法来解码 URL 编码的路径，将 %20 转换回空格
String fontFile = URLDecoder.decode(Main.class.getClassLoader().getResource(File.separator + "ttfs" + File.separator + "Alibaba_PuHuiTi_2.0_65_Medium_65_Medium.ttf").getFile(), "UTF-8");
PDType0Font font = PDType0Font.load(pdDocument, new File(fontFile));
float fontSize = 10; // 设置字体大小为12
// 设置透明度状态对象
PDExtendedGraphicsState graphicsState = new PDExtendedGraphicsState();
graphicsState.setNonStrokingAlphaConstant(0.2f);
graphicsState.setAlphaSourceFlag(true);
graphicsState.setStrokingAlphaConstant(0.2f);
//设置新的页眉
String headerText = "咨询专转本默默学课程联系官方报名处QQ：3503851091，更多资料可加群828303961";
String footerText = "江苏专转本公众号：专转本智慧树";
//遍历原先的pdf文档
for (PDPage page : pdDocument.getPages()) {
float pageWidth = page.getMediaBox().getWidth();
//计算页眉的居中位置
float headerTextWidth = font.getStringWidth(headerText) / 1000 * fontSize;
float headerCenteredX = (pageWidth - headerTextWidth) / 2; // 计算水平居中位置
//计算页脚的居中位置
float footerTextWidth = font.getStringWidth(footerText) / 1000 * fontSize;
float footerCenteredX = (pageWidth - footerTextWidth) / 2; // 计算水平居中位置
// 创建用于页眉的内容流
PDPageContentStream headerContentStream = new PDPageContentStream(pdDocument, page, PDPageContentStream.AppendMode.APPEND, true, true);
headerContentStream.beginText(); // 开始文本操作
headerContentStream.setFont(font, fontSize); // 设置字体和字号
headerContentStream.newLineAtOffset(headerCenteredX, page.getMediaBox().getHeight() - 30); // 设置文本起始位置
headerContentStream.showText(headerText); // 绘制页眉内容
headerContentStream.endText(); // 结束文本操作
headerContentStream.close(); // 关闭内容流
// 添加页脚
PDPageContentStream footerContentStream = new PDPageContentStream(pdDocument, page, PDPageContentStream.AppendMode.APPEND, true, true);
footerContentStream.beginText(); // 开始文本操作
footerContentStream.setFont(font, fontSize); // 设置字体和字号
footerContentStream.newLineAtOffset(footerCenteredX, 30); // 设置文本起始位置
footerContentStream.showText(footerText); // 绘制页脚内容
footerContentStream.endText(); // 结束文本操作
footerContentStream.close(); // 关闭内容流
}
//目标目录 Thread.currentThread().getContextClassLoader().getResource("").getPath() 当前工程目录路径
//String targetPDFPath = URLDecoder.decode(Demo3.class.getClassLoader().getResource("resources").getPath() + File.separator + "output.pdf", "UTF-8");
// String targetPDFPath = URLDecoder.decode(Main.class.getClassLoader().getResource("output.pdf").getFile(), "UTF-8");
String targetPDFPath = "F:\\00核心知识、成果、视频产出区\\技术视频\\2024.2.15 自制默默学打水印工具 watermark tools\\watermarkTools\\src\\main\\resources\\output.pdf";
File outputFile = new File(targetPDFPath);
// 若是文件存在先进行删除
Files.deleteIfExists(Paths.get(outputFile.toURI()));
// 保存修改后的文档
pdDocument.save(outputFile);
System.out.println("转换任务：" + targetPDFPath + " 成功！");
// 关闭文档
pdDocument.close(); // 关闭文档
}
}

复制代码

package com.changlu.demos;
import com.changlu.Main;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDPageContentStream;
import org.apache.pdfbox.pdmodel.font.PDType0Font;
import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
import org.apache.pdfbox.pdmodel.graphics.state.PDExtendedGraphicsState;
import java.io.File;
import java.io.InputStream;
import java.net.URLDecoder;
import java.nio.file.Files;
import java.nio.file.Paths;
/**
* @Description: Apache PDFBox案例：对pdf每页都添加上旋转45°水印。
* @Author: changlu
* @Date: 1:38 PM
*/
public class Demo4 {
public static void main(String[] args) throws Exception{
//读取resources目录下input.pdf文件
InputStream is = Main.class.getClassLoader().getResourceAsStream("input.pdf");
PDDocument pdDocument = PDDocument.load(is);
//自定义字体 C:\Users\93997\Desktop\watermark tools\watermarkTools\target\classes\ttfs
//URLDecoder.decode() 方法来解码 URL 编码的路径，将 %20 转换回空格
String fontFile = URLDecoder.decode(Main.class.getClassLoader().getResource(File.separator + "ttfs" + File.separator + "Alibaba_PuHuiTi_2.0_65_Medium_65_Medium.ttf").getFile(), "UTF-8");
PDType0Font font = PDType0Font.load(pdDocument, new File(fontFile));
// 设置透明度状态对象
PDExtendedGraphicsState graphicsState = new PDExtendedGraphicsState();
graphicsState.setNonStrokingAlphaConstant(0.2f);
graphicsState.setAlphaSourceFlag(true);
graphicsState.setStrokingAlphaConstant(0.2f);
//设置水印名
String waterText = "江苏专转本网课报名vx：mmxchanglu";
//遍历原先的pdf文档
for (PDPage page : pdDocument.getPages()) {
float pageWidth = page.getMediaBox().getWidth();
float pageHeight = page.getMediaBox().getHeight();
//添加水印要求：旋转45°，不透明度30%
float waterTextWidth = font.getStringWidth(waterText) / 1000 * 30;
float waterCenteredX = (pageWidth - waterTextWidth) / 2;
float waterCenteredY = pageHeight / 2;
//创建一个水印内容流
PDPageContentStream waterContentStream = new PDPageContentStream(pdDocument, page, PDPageContentStream.AppendMode.APPEND, true, true);
waterContentStream.beginText();
waterContentStream.setFont(font, 30);
// 设置不透明度
waterContentStream.setNonStrokingColor(0, 0, 0); // black color
waterContentStream.setStrokingColor(0, 0, 0); // black color
waterContentStream.setGraphicsStateParameters(graphicsState);//设置透明度
//设置旋转文本 45° 对于tx、ty是以左下角为偏移位置中心来进行旋转角度
waterContentStream.setTextRotation(Math.toRadians(45), 400, -50);
//设置文本
waterContentStream.newLineAtOffset(waterCenteredX, waterCenteredY);
waterContentStream.showText(waterText);
waterContentStream.endText();
waterContentStream.close();
}
//目标目录 Thread.currentThread().getContextClassLoader().getResource("").getPath() 当前工程目录路径
String targetPDFPath = "F:\\00核心知识、成果、视频产出区\\技术视频\\2024.2.15 自制默默学打水印工具 watermark tools\\watermarkTools\\src\\main\\resources\\output.pdf";
File outputFile = new File(targetPDFPath);
// 若是文件存在先进行删除
Files.deleteIfExists(Paths.get(outputFile.toURI()));
// 保存修改后的文档
pdDocument.save(outputFile);
System.out.println("转换任务：" + targetPDFPath + " 成功！");
// 关闭文档
pdDocument.close(); // 关闭文档
}
}

复制代码

package com.changlu.demos;
import com.changlu.Main;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDPageContentStream;
import org.apache.pdfbox.pdmodel.font.PDType0Font;
import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
import org.apache.pdfbox.pdmodel.graphics.state.PDExtendedGraphicsState;
import java.io.File;
import java.io.InputStream;
import java.net.URLDecoder;
import java.nio.file.Files;
import java.nio.file.Paths;
/**
* @Description: Apache PDFBox案例：将图片缩小25%后插入到右上角。
* @Author: changlu
* @Date: 1:38 PM
*/
public class Demo5 {
public static void main(String[] args) throws Exception{
//读取resources目录下input.pdf文件
InputStream is = Main.class.getClassLoader().getResourceAsStream("input.pdf");
PDDocument pdDocument = PDDocument.load(is);
//自定义字体 C:\Users\93997\Desktop\watermark tools\watermarkTools\target\classes\ttfs
//URLDecoder.decode() 方法来解码 URL 编码的路径，将 %20 转换回空格
String fontFile = URLDecoder.decode(Main.class.getClassLoader().getResource(File.separator + "ttfs" + File.separator + "Alibaba_PuHuiTi_2.0_65_Medium_65_Medium.ttf").getFile(), "UTF-8");
PDType0Font font = PDType0Font.load(pdDocument, new File(fontFile));
//遍历原先的pdf文档
for (PDPage page : pdDocument.getPages()) {
float pageWidth = page.getMediaBox().getWidth();
float pageHeight = page.getMediaBox().getHeight();
//添加图片水印
//创建一个水印内容流
PDPageContentStream imageContentStream = new PDPageContentStream(pdDocument, page, PDPageContentStream.AppendMode.APPEND, true, true);
// 创建图像对象
// PDImageXObject image = PDImageXObject.createFromFile("C:\\Users\\93997\\Desktop\\watermark tools\\watermarkTools\\src\\main\\resources\\images\\ConsultationGroupQRCode.jpg", pdDocument);
String pictureFile = URLDecoder.decode(Main.class.getClassLoader().getResource(File.separator + "images" + File.separator + "ConsultationGroupQRCode.jpg").getFile(), "UTF-8");
PDImageXObject image = PDImageXObject.createFromFile(pictureFile, pdDocument);
// 计算图像的宽度和高度（缩小比例为0.3）
float imageWidth = (float) (image.getWidth() * 0.25);
float imageHeight = (float) (image.getHeight() * 0.25);
//具体图片位置
float imageX = pageWidth - imageWidth - 10;
float imageY = pageHeight - imageHeight - 10;
// 在指定位置绘制图像
imageContentStream.drawImage(image, imageX, imageY, imageWidth, imageHeight);
imageContentStream.close();
}
//目标目录 Thread.currentThread().getContextClassLoader().getResource("").getPath() 当前工程目录路径
String targetPDFPath = "F:\\00核心知识、成果、视频产出区\\技术视频\\2024.2.15 自制默默学打水印工具 watermark tools\\watermarkTools\\src\\main\\resources\\output.pdf";
File outputFile = new File(targetPDFPath);
// 若是文件存在先进行删除
Files.deleteIfExists(Paths.get(outputFile.toURI()));
// 保存修改后的文档
pdDocument.save(outputFile);
System.out.println("转换任务：" + targetPDFPath + " 成功！");
// 关闭文档
pdDocument.close(); // 关闭文档
}
}

复制代码