1.使用 documents4j
格式不会乱码,字体会改变
引用依赖
<dependency>
<groupId>com.documents4j</groupId>
<artifactId>documents4j-local</artifactId>
<version>1.0.3</version>
</dependency>
<dependency>
<groupId>com.documents4j</groupId>
<artifactId>documents4j-transformer-msoffice-word</artifactId>
<version>1.0.3</version>
</dependency>
实现代码
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.PDFRenderer;
import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.IOException;
public class PdfUtils {
public static void main(String[] args) {
pdf2png("E:\\wendang\\test","综合分析报告","png");
}
/**
* 转换全部的pdf
* @param fileAddress 文件地址
* @param filename PDF文件名
* @param type 图片类型
*/
public static void pdf2png(String fileAddress,String filename,String type) {
// 将pdf装图片 并且自定义图片得格式大小
File file = new File(fileAddress+"\\"+filename+".pdf");
try {
PDDocument doc = PDDocument.load(file);
PDFRenderer renderer = new PDFRenderer(doc);
int pageCount = doc.getNumberOfPages();
for (int i = 0; i < pageCount; i++) {
BufferedImage image = renderer.renderImageWithDPI(i, 144); // Windows native DPI
// BufferedImage srcImage = resize(image, 240, 240);//产生缩略图
ImageIO.write(image, type, new File(fileAddress+"\\"+filename+"_"+(i+1)+"."+type));
}
} catch (IOException e) {
e.printStackTrace();
}
}
/**
*自由确定起始页和终止页
* @param fileAddress 文件地址
* @param filename pdf文件名
* @param indexOfStart 开始页 开始转换的页码,从0开始
* @param indexOfEnd 结束页 停止转换的页码,-1为全部
* @param type 图片类型
*/
public static void pdf2png(String fileAddress,String filename,int indexOfStart,int indexOfEnd,String type) {
// 将pdf装图片 并且自定义图片得格式大小
File file = new File(fileAddress+"\\"+filename+".pdf");
try {
PDDocument doc = PDDocument.load(file);
PDFRenderer renderer = new PDFRenderer(doc);
int pageCount = doc.getNumberOfPages();
for (int i = indexOfStart; i < indexOfEnd; i++) {
BufferedImage image = renderer.renderImageWithDPI(i, 144); // Windows native DPI
// BufferedImage srcImage = resize(image, 240, 240);//产生缩略图
ImageIO.write(image, type, new File(fileAddress+"\\"+filename+"_"+(i+1)+"."+type));
}
} catch (IOException e) {
e.printStackTrace();
}
}
}
2.aspose-words
引用依赖
<dependency>
<groupId>org.docx4j</groupId>
<artifactId>docx4j-export-fo</artifactId>
<version>8.2.4</version>
</dependency>
<dependency>
<groupId>com.aspose</groupId>
<artifactId>aspose-words</artifactId>
<version>15.8.0</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.pdfbox/fontbox -->
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>fontbox</artifactId>
<version>2.0.9</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.pdfbox/pdfbox -->
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>pdfbox</artifactId>
<version>2.0.9</version>
</dependency>
实现代码
import com.aspose.words.Document;
import com.aspose.words.ImageSaveOptions;
import com.aspose.words.SaveFormat;
import javax.imageio.ImageIO;
import javax.imageio.stream.ImageInputStream;
import java.awt.*;
import java.awt.image.BufferedImage;
import java.io.*;
import java.util.ArrayList;
import java.util.Date;
import java.util.List;
public class AsposeUtils {
public static void file2Img(String filePath, String imgFilePath) {
//word2pdf("C:/Users/Administrator/Desktop/1.doc","C:/Users/Administrator/Desktop/xxxx.pdf");//word转pdf
//word转图片格式
try {
File file = new File(filePath);
InputStream inStream = new FileInputStream(file);
List<BufferedImage> word2Img = word2Img(inStream);
int i = 0;
for (BufferedImage image : word2Img) {
ImageIO.write(image, "jpg", new File(imgFilePath+i+".jpg")); //将其保存
i++;
}
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
/**
* 验证aspose.word组件是否授权:无授权的文件有水印标记
* 需要使用(aspose-words-15.8.0-jdk16.jar),版本要对应。无水印
*
* @return
*/
public static boolean isWordLicense() {
boolean result = false;
try {
String s = "<License><Data><Products><Product>Aspose.Total for Java</Product><Product>Aspose.Words for Java</Product></Products><EditionType>Enterprise</EditionType><SubscriptionExpiry>20991231</SubscriptionExpiry><LicenseExpiry>20991231</LicenseExpiry><SerialNumber>8bfe198c-7f0c-4ef8-8ff0-acc3237bf0d7</SerialNumber></Data><Signature>sNLLKGMUdF0r8O1kKilWAGdgfs2BvJb/2Xp8p5iuDVfZXmhppo+d0Ran1P9TKdjV4ABwAgKXxJ3jcQTqE/2IRfqwnPf8itN8aFZlV3TJPYeD3yWE7IT55Gz6EijUpC7aKeoohTb4w2fpox58wWoF3SNp6sK6jDfiAUGEHYJ9pjU=</Signature></License>";
ByteArrayInputStream inputStream = new ByteArrayInputStream(s.getBytes());
com.aspose.words.License license = new com.aspose.words.License();
license.setLicense(inputStream);
result = true;
} catch (Exception e) {
e.printStackTrace();
}
return result;
}
//outputStream转inputStream
public static ByteArrayInputStream parse(OutputStream out) throws Exception {
ByteArrayOutputStream baos = new ByteArrayOutputStream();
baos = (ByteArrayOutputStream) out;
ByteArrayInputStream swapStream = new ByteArrayInputStream(baos.toByteArray());
return swapStream;
}
/**
* word和txt文件 转换 图片
*
* @param inputStream
* @param
* @return
* @throws Exception
*/
public static List<BufferedImage> word2Img(InputStream inputStream) throws Exception {
if (!isWordLicense()) {
return null;
}
try {
Date start = new Date();
Document doc = new Document(inputStream);
ImageSaveOptions options = new ImageSaveOptions(SaveFormat.PNG);
options.setPrettyFormat(true);
options.setUseAntiAliasing(true);
options.setUseHighQualityRendering(true);
int pageCount = doc.getPageCount();
//生成前pageCount张,这可以限制输出长图时的页数(方法入参可以传值pageNum)
/*if (pageCount > pageNum) {
pageCount = pageNum;
}*/
List<BufferedImage> imageList = new ArrayList<BufferedImage>();
for (int i = 0; i < pageCount; i++) {
OutputStream output = new ByteArrayOutputStream();
options.setPageIndex(i);
doc.save(output, options);
ImageInputStream imageInputStream = javax.imageio.ImageIO.createImageInputStream(parse(output));
imageList.add(javax.imageio.ImageIO.read(imageInputStream));
}
List<BufferedImage> imageList2 = new ArrayList<BufferedImage>();
for (int j = 0; j < imageList.size(); j++) {
// 生成新图片
BufferedImage destImage = imageList.get(j);
int w1 = destImage.getWidth();
int h1 = destImage.getHeight();
destImage = new BufferedImage(w1, h1, BufferedImage.TYPE_INT_RGB);
Graphics2D g2 = (Graphics2D) destImage.getGraphics();
g2.setBackground(Color.LIGHT_GRAY);
g2.clearRect(0, 0, w1, h1);
g2.setPaint(Color.RED);
// 设置字体渲染质量
g2.setRenderingHint(RenderingHints.KEY_TEXT_ANTIALIASING, RenderingHints.VALUE_TEXT_ANTIALIAS_ON);
// 从图片中读取RGB
int[] ImageArrayOne = new int[w1 * h1];
ImageArrayOne = imageList.get(j).getRGB(0, 0, w1, h1, ImageArrayOne, 0, w1); // 逐行扫描图像中各个像素的RGB到数组中
destImage.setRGB(0, 0, w1, h1, ImageArrayOne, 0, w1); // 设置上半部分或左半部分的RGB
imageList2.add(destImage);
}
Date end = new Date();
long l = end.getTime() - start.getTime();
long hour = l / (1000 * 60 * 60);
long min = (l - hour * (1000 * 60 * 60)) / (1000 * 60);
long s = (l - hour * (1000 * 60 * 60) - min * 1000 * 60) / (1000);
long ss = (l - hour * (1000 * 60 * 60) - min * 1000 * 60 - s * 1000) / (1000 / 60);
System.out.println("word转图片时间:" + min + "分" + s + "秒" + ss + "毫秒");//hour+"小时"+
return imageList2;
} catch (Exception e) {
e.printStackTrace();
throw e;
}
}
/**
* 合并任数量的图片成一张图片
*
* @param isHorizontal true代表水平合并,fasle代表垂直合并
* @param imgs 待合并的图片数组
* @return
* @throws IOException
*/
public static BufferedImage mergeImage(boolean isHorizontal, List<BufferedImage> imgs) throws IOException {
// 生成新图片
BufferedImage destImage = null;
// 计算新图片的长和高
int allw = 0, allh = 0, allwMax = 0, allhMax = 0;
// 获取总长、总宽、最长、最宽
for (int i = 0; i < imgs.size(); i++) {
BufferedImage img = imgs.get(i);
allw += img.getWidth();
if (imgs.size() != i + 1) {
allh += img.getHeight() + 5;
} else {
allh += img.getHeight();
}
if (img.getWidth() > allwMax) {
allwMax = img.getWidth();
}
if (img.getHeight() > allhMax) {
allhMax = img.getHeight();
}
}
// 创建新图片
if (isHorizontal) {
destImage = new BufferedImage(allw, allhMax, BufferedImage.TYPE_INT_RGB);
} else {
destImage = new BufferedImage(allwMax, allh, BufferedImage.TYPE_INT_RGB);
}
Graphics2D g2 = (Graphics2D) destImage.getGraphics();
g2.setBackground(Color.LIGHT_GRAY);
g2.clearRect(0, 0, allw, allh);
g2.setPaint(Color.RED);
// 合并所有子图片到新图片
int wx = 0, wy = 0;
for (int i = 0; i < imgs.size(); i++) {
BufferedImage img = imgs.get(i);
int w1 = img.getWidth();
int h1 = img.getHeight();
// 从图片中读取RGB
int[] ImageArrayOne = new int[w1 * h1];
ImageArrayOne = img.getRGB(0, 0, w1, h1, ImageArrayOne, 0, w1); // 逐行扫描图像中各个像素的RGB到数组中
if (isHorizontal) { // 水平方向合并
destImage.setRGB(wx, 0, w1, h1, ImageArrayOne, 0, w1); // 设置上半部分或左半部分的RGB
} else { // 垂直方向合并
destImage.setRGB(0, wy, w1, h1, ImageArrayOne, 0, w1); // 设置上半部分或左半部分的RGB
}
wx += w1;
wy += h1 + 5;
}
return destImage;
}
/**
* 当文档中含有中文字符时,该段代码的执行需要调用操作系统的本地字体库支持,否则所有中文字符都将乱码。
* <p>
* 该段代码如果想要在Linux服务器上完美运行,需要给Linux服务器安装中文字体库
* <p>
* 如何在Linux环境安装Windows字体库
* Java使用Spire.Pdf或Aspose-Words实现Word转换Pdf在Linux服务器上的中文乱码问题
* 解决: https://blog.csdn.net/neulily2005/article/details/106003527
*/
public static boolean word2Pdf(String inPath, String outPath) {
if (!isWordLicense()) {
return false;
}
FileOutputStream os = null;
try {
long old = System.currentTimeMillis();
File file = new File(outPath); // 新建一个空白pdf文档
os = new FileOutputStream(file);
Document doc = new Document(inPath); // Address是将要被转化的word文档
doc.save(os, SaveFormat.PDF);// 全面支持DOC, DOCX, OOXML, RTF HTML, OpenDocument, PDF,
// EPUB, XPS, SWF 相互转换
long now = System.currentTimeMillis();
System.out.println("pdf转换成功,共耗时:" + ((now - old) / 1000.0) + "秒"); // 转化用时
} catch (Exception e) {
e.printStackTrace();
return false;
} finally {
if (os != null) {
try {
os.flush();
os.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
return true;
}
/**
* @Description: pdf文件转换图片
*/
/*public static List<BufferedImage> pdf2img(InputStream inputStream) {
try {
PDDocument pdDocument;
pdDocument = PDDocument.load(inputStream);
PDFRenderer renderer = new PDFRenderer(pdDocument);
*//* dpi越大转换后越清晰,相对转换速度越慢 *//*
int pages = pdDocument.getNumberOfPages();
List<BufferedImage> imageList = new ArrayList<BufferedImage>();
for (int i = 0; i < pages; i++) {
BufferedImage image = renderer.renderImageWithDPI(i, 300);
imageList.add(image);
}
return imageList;
} catch (Exception e) {
e.printStackTrace();
} finally {
if (inputStream != null) {
try {
inputStream.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
return null;
}*/
}