Java 将word文档转成html内容，输出到富文本

使用Java 将word文档转成html内容，输出到富文本

上传word文档解析到富文本

将word解析成html工具类

import com.common.utils.DateUtil;
import com.common.utils.RandomUtil;import org.apache.commons.fileupload.FileItem;
import org.apache.commons.fileupload.FileItemFactory;
import org.apache.commons.fileupload.disk.DiskFileItemFactory;
import org.apache.commons.io.FileUtils;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.usermodel.PictureType;
import org.apache.poi.xwpf.converter.core.BasicURIResolver;
import org.apache.poi.xwpf.converter.core.FileImageExtractor;
import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter;
import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.web.multipart.MultipartFile;
import org.springframework.web.multipart.commons.CommonsMultipartFile;
import org.w3c.dom.Document;import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import java.io.*;/*** @date * @description*/
public class WordToHtmlUtil {private static final Logger logger = LoggerFactory.getLogger(WordToHtmlUtil.class);/*** 上传Word文档，返回解析后的Html*/public static String docToHtmlText(MultipartFile file) throws Exception {//使用字符数组流获取解析的内容ByteArrayOutputStream baos = new ByteArrayOutputStream();OutputStream outStream = new BufferedOutputStream(baos);try {//将上传的文件传入Document转换HWPFDocument wordDocument = new HWPFDocument(file.getInputStream());Document document = DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument();WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(document);//将读取到的图片上传并添加链接地址wordToHtmlConverter.setPicturesManager((imageStream, pictureType, name, width, height) -> {try {//首先要判断图片是否能识别if (pictureType.equals(PictureType.UNKNOWN)) {return "[不能识别的图片]";}//此处上传到自己的文件服务器 todoString qiNiuName = "";//文件名boolean upload = FileUtil.upload(new        FileInputStream(fileImage), qiNiuName);   return "上传后的图片地址";} catch (Exception e) {logger.info("upload exception", e);}return "[图片上传失败]";});// word文档转Html文档wordToHtmlConverter.processDocument(wordDocument);Document htmlDocument = wordToHtmlConverter.getDocument();DOMSource domSource = new DOMSource(htmlDocument);StreamResult streamResult = new StreamResult(outStream);TransformerFactory factory = TransformerFactory.newInstance();Transformer serializer = factory.newTransformer();serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");serializer.setOutputProperty(OutputKeys.INDENT, "yes");serializer.setOutputProperty(OutputKeys.METHOD, "html");serializer.transform(domSource, streamResult);String content = baos.toString();logger.info("docToHtmlText--->{}", content);return content;} catch (Exception e) {logger.error("docToHtmlText 异常", e);throw new AppRuntimeException(e);} finally {baos.close();outStream.close();}}/*** 上传docx文档，返回解析后的Html*/public static String docxToHtmlText(MultipartFile file) throws Exception {ByteArrayOutputStream htmlStream = new ByteArrayOutputStream();try {// 将上传的文件传入Document转换XWPFDocument docxDocument = new XWPFDocument(file.getInputStream());XHTMLOptions options = XHTMLOptions.create();// 设置图片存储路径String path = System.getProperty("java.io.tmpdir");String firstImagePathStr = path + "/" + System.currentTimeMillis();options.setExtractor(new FileImageExtractor(new File(firstImagePathStr)));options.URIResolver(new BasicURIResolver(firstImagePathStr));// 转换htmldocxDocument.createNumbering();XHTMLConverter.getInstance().convert(docxDocument, htmlStream, options);String htmlStr = htmlStream.toString();String middleImageDirStr = "/word/media";String imageDirStr = firstImagePathStr + middleImageDirStr;File imageDir = new File(imageDirStr);String[] imageList = imageDir.list();if (imageList != null) {for (int i = 0; i < imageList.length; i++) {try {String oneImagePathStr = imageDirStr + "/" + imageList[i];File fileImage = new File(oneImagePathStr);if (fileImage.exists()) {String name = fileImage.getName();String suffix = name.substring(name.indexOf("."), name.length()).toLowerCase();//此处上传到自己的文件服务器 todoString qiNiuName = "";//文件名boolean upload = FileUtil.upload(new FileInputStream(fileImage), qiNiuName);   if (!upload) {continue;} else {//修改文档中的图片信息htmlStr = htmlStr.replace(oneImagePathStr, "上传后的图片地址");}}} catch (Exception e) {logger.info("upload docxToHtmlText exception", e);}}}//删除图片路径File firstImagePath = new File(firstImagePathStr);FileUtils.deleteDirectory(firstImagePath);return htmlStr;} catch (Exception e) {logger.error("docxToHtmlText 解析异常", e);throw new AppRuntimeException(e);} finally {if (htmlStream != null) {htmlStream.close();}}}/*    public static void main(String[] args) {try {String content = docxToHtmlText(getMulFileByPath("C:\\Users\\Administrator\\Desktop\\hah.docx"));System.out.println(content);} catch (Exception e) {e.printStackTrace();}}*//*** 获取MultipartFile文件** @param picPath* @return*/private static MultipartFile getMulFileByPath(String picPath) {FileItem fileItem = createFileItem(picPath);MultipartFile mfile = new CommonsMultipartFile(fileItem);return mfile;}private static FileItem createFileItem(String filePath) {FileItemFactory factory = new DiskFileItemFactory(16, null);String textFieldName = "textField";int num = filePath.lastIndexOf(".");String extFile = filePath.substring(num);FileItem item = factory.createItem(textFieldName, "text/plain", true,"MyFileName" + extFile);File newfile = new File(filePath);int bytesRead = 0;byte[] buffer = new byte[8192];try {FileInputStream fis = new FileInputStream(newfile);OutputStream os = item.getOutputStream();while ((bytesRead = fis.read(buffer, 0, 8192))!= -1) {os.write(buffer, 0, bytesRead);}os.close();fis.close();} catch (IOException e) {e.printStackTrace();}return item;}}

Java 将word文档转成html内容，输出到富文本相关推荐

使用java将word文档docx，doc（包含图形，文本框）完美转换成所有格式图片（pdf，png，gif，jpeg等等）
使用java将word文档docx,doc(包含图形,文本框,图片等)完美转换成所有格式图片(pdf,png,gif,jpeg等等)下文中附带代码,效果图等思路使用到的包实现代码效果图: 思路 ...
java将WORD文档转换成pdf文件
总结对jacob和Itext学习总结.本文试验的是将WORD转换成PDF文件. 实现思路一.先将WORD文档转换成HMTL文件格式(参阅我的前一文<JAVA操作WORD文档). 二.用流读取H ...
java实现Word文档转换PDF文档
最近需要实现在java语言Word文档转成PDF文档的功能,做了一下调研,最后使用aspose-words实现了该功能. 注意,aspose-words 为商业软件,本文仅是使用方法的demo,使用的 ...
Java 将 Word 文档转换为 PDF 的完美工具
点击上方好好学java ,选择星标公众号重磅资讯.干货,第一时间送达今日推荐:为什么魂斗罗只有 128 KB却可以实现那么长的剧情?个人原创+1博客:点击前往,查看更多来源:https:/ ...
azw3转换为pdf_干货：如何Java 将 Word 文档转换为 PDF
在日常工作中,PDF格式良好的视觉阅读性和稳定性使其使用越来越广泛.因此我们常会遇到需要将成型的Word文档转换为PDF格式的情况.本文就将通过使用Java程序来演示如何将Word文档转换成PDF格式 ...
Java将Word文档转换为PDF的完美工具
引用至:https://mp.weixin.qq.com/s/JIgo3f98HufGJx23mgtvag Java 将 Word 文档转换为 PDF 的完美工具在日常工作中,PDF格式良好的视觉阅 ...
[摘]用Java生成Word文档
开发中隔三叉五的就要用到Word,经常被搞得不胜其烦,不过这次找到了不少好例子,干脆将他们都摘了过来,内容如下: 1. poi是apache的一个项目,不过就算用poi你可能都觉得很烦,不过不要紧,这 ...
Word处理控件Aspose.Words功能演示：用Java从Word文档中提取文本
Aspose.Words For .NET是一种高级Word文档处理API,用于执行各种文档管理和操作任务.API支持生成,修改,转换,呈现和打印文档,而无需在跨平台应用程序中直接使用Microsof ...
java实现word文档转pdf，并添加水印
前段时间,项目需要自动生成word文档,用WordFreeMarker生成word文档后,又要求生成的文档能在浏览器浏览,思来想去,把word文档转成pdf就好了,于是乎研究了一下. 将word文档转 ...

Java 将word文档转成html内容，输出到富文本

使用Java 将word文档转成html内容，输出到富文本

Java 将word文档转成html内容，输出到富文本相关推荐

最新文章

热门文章