Java word转html、图片
1.下载aspose-words-20.12-jdk17-crack.jar
资源链接 https://download.csdn.net/download/qq_43601009/88466502
此jar包不包含在maven中心仓库中,所以下载手动下载并本地引入
2.将jar包放到项目中
建立src的同级目录lib,将下载好的jar包放到lib下
这里很多博客都写了在resources下创建lib,本人试过后会一直报错,放在src同级的lib可以正常运行。
3.将本地jar包以maven的方式引入
3.1
<!--引入本地jar包-->
<dependency>
<groupId>com.aspose</groupId>
<artifactId>aspose-words</artifactId>
<scope>system</scope>
<version>15.8.0</version>
<systemPath>${basedir}/lib/aspose-words-20.12-jdk17-crack.jar</systemPath>
</dependency>
3.2
<build>
<plugin>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-maven-plugin</artifactId>
<configuration>
<!-- maven打包时会将外部引入的jar包(比如在根目录下或resource文件下新加外部jar包)打包到项目jar -->
<includeSystemScope>true</includeSystemScope>
</configuration>
</plugin>
</build>
4.AsposeUtils
此工具可以word转图片、html,但是在转html时,可能会因为图片导致排版较乱的问题。
import com.aspose.words.Document;
import com.aspose.words.HtmlSaveOptions;
import com.aspose.words.ImageSaveOptions;
import com.aspose.words.SaveFormat;
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 {
//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> wordToImg(InputStream inputStream) throws Exception {
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>();
//这个重新生成新的图片是因为直接输出的图片底色为红色
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);
// 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 wordToPdf(String inPath, String outPath) {
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
//排版问题解决(word文档在编辑的时候是采用的多页编辑。页面效果是单页,可是在apose将word文档转为pdf后就变成了两页)
Document document = new Document();//新建一个空白pdf文档
document.removeAllChildren();
document.appendDocument(doc, ImportFormatMode.USE_DESTINATION_STYLES);//保留样式
//表格样式处理
TableCollection tables = document.getFirstSection().getBody().getTables();
for (Table table : tables) {
RowCollection rows = table.getRows();
table.setAllowAutoFit(false);
for (Row row : rows) {
CellCollection cells = row.getCells();
for (Cell cell : cells) {
CellFormat cellFormat = cell.getCellFormat();
cellFormat.setFitText(false);
cellFormat.setWrapText(true);
}
}
}
document.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;
}
public static boolean wordToHtml(InputStream is, String outPath) {
FileOutputStream os = null;
try {
HtmlSaveOptions opts = new HtmlSaveOptions(SaveFormat.HTML);
opts.setExportXhtmlTransitional(true);
opts.setExportImagesAsBase64(true);
opts.setExportPageSetup(true);
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(is); // Address是将要被转化的word文档
doc.save(os, opts);// 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;
}
}