doc转html并图片转base64
package com.lly.demo.util;
//
// Source code recreated from a .class file by IntelliJ IDEA
// (powered by FernFlower decompiler)
//
import com.lly.demo.bean.DocUser;
import com.spire.doc.FileFormat;
import org.apache.commons.codec.binary.Base64;
import org.apache.commons.lang3.StringUtils;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.usermodel.Picture;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.w3c.dom.Document;
import javax.xml.parsers.DocumentBuilderFactory;
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.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.util.Iterator;
import java.util.List;
import static java.lang.System.out;
//word转html
public class docTohtml {
public static void main(String[] args) throws Exception {
docxToHtml();
}
public Boolean docTohtml(DocUser docUser) throws Exception {
String sourceFileName = docUser.getDocname();
String targetFileName = docUser.getHtmlname();
String imagePathStr = "D:/doc2htmltest/image/";
Boolean secORfiled=true;
HWPFDocument wordDocument = null;
File file=new File(sourceFileName);
FileInputStream fileInputStream = new FileInputStream(sourceFileName);
String docxtodocSourceFileName = docUser.getDocname().substring(0,docUser.getDocname().length()-5)+".doc";
try {
if(StringUtils.isNotBlank(sourceFileName)&&StringUtils.isNotBlank(targetFileName)){
if(sourceFileName.endsWith(".doc")){
if(file.exists()){
out.println("aaaaa11111");
wordDocument = new HWPFDocument(fileInputStream);
out.println("aaaaa");
if (wordDocument != null) {
WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
wordToHtmlConverter.setPicturesManager((a, b, suggestedName, d, e) -> {
// convertFileToBase64()
out.println(suggestedName);
//返回图片路径
//return "image" + File.separator + suggestedName;
//返回图片base64值
return "data:image/"+b.getExtension().toLowerCase()+";base64,"+new String(Base64.encodeBase64(a));
});
wordToHtmlConverter.processDocument(wordDocument);
List pics = wordDocument.getPicturesTable().getAllPictures();
out.println(pics);
Iterator var8 = pics.iterator();
//转换图片
imgToBase64 imgToBase64pl=new imgToBase64();
int i=1;
while(var8.hasNext()) {
Picture pic = (Picture)var8.next();
//下载图片
// pic.writeImageContent(new FileOutputStream(imagePathStr + pic.suggestFullFileName()));
//System.out.println("第"+i++ +":"+imgToBase64pl.convertFileToBase64(imagePathStr + pic.suggestFullFileName()));
}
Document htmlDocument = wordToHtmlConverter.getDocument();
//生成空文档
DOMSource domSource = new DOMSource(htmlDocument);
//获取路径下html
StreamResult streamResult = new StreamResult(new File(targetFileName));
//设置html文件规范
TransformerFactory tf = TransformerFactory.newInstance();
Transformer serializer = tf.newTransformer();
serializer.setOutputProperty("encoding", "utf-8");
serializer.setOutputProperty("indent", "yes");
serializer.setOutputProperty("method", "html");
serializer.transform(domSource, streamResult);
}else {
out.println("请检查文件类型或后缀是否正确！");
secORfiled=false;
}
}else{
out.println("文件不存在");
secORfiled=false;
}
}else if(sourceFileName.endsWith("docx")){
System.out.println("上传文件为docx类型");
secORfiled=false;
}else{
out.println("上传文件为其他类型文件");
secORfiled=false;
}
}else{
secORfiled=false;
}
} catch (IOException e) {
e.printStackTrace();
secORfiled=false;
}finally {
fileInputStream.close();
return secORfiled;
}
}
public static void docxToHtml() throws Exception {
//D:\zpdtolly\工作总结文档\zpd使用文档\v4\用户使用手册\客户端使用手册
String sourceFileName = "D:\\zpdtolly\\工作总结文档\\zpd使用文档\\uos+ql飞腾\\uos+麒麟飞腾使用手册-网络版.doc";
String targetFileName = "D:\\zpdtolly\\工作总结文档\\zpd使用文档\\uos+ql飞腾\\uos+麒麟飞腾使用手册-网络版.html";
String imagePathStr = "D:/doc2htmltest/image/";
HWPFDocument wordDocument = new HWPFDocument(new FileInputStream(sourceFileName));
WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
wordToHtmlConverter.setPicturesManager((a, b, suggestedName, d, e) -> {
// convertFileToBase64()
out.println(suggestedName);
//返回图片路径
//return "image" + File.separator + suggestedName;
//返回图片base64值
return "data:image/"+b.getExtension().toLowerCase()+";base64,"+new String(Base64.encodeBase64(a));
});
wordToHtmlConverter.processDocument(wordDocument);
List pics = wordDocument.getPicturesTable().getAllPictures();
out.println(pics);
Iterator var8 = pics.iterator();
//转换图片
imgToBase64 imgToBase64pl=new imgToBase64();
int i=1;
while(var8.hasNext()) {
Picture pic = (Picture)var8.next();
//下载图片
// pic.writeImageContent(new FileOutputStream(imagePathStr + pic.suggestFullFileName()));
//System.out.println("第"+i++ +":"+imgToBase64pl.convertFileToBase64(imagePathStr + pic.suggestFullFileName()));
}
Document htmlDocument = wordToHtmlConverter.getDocument();
//生成空文档
DOMSource domSource = new DOMSource(htmlDocument);
//获取路径下html
StreamResult streamResult = new StreamResult(new File(targetFileName));
//设置html文件规范
TransformerFactory tf = TransformerFactory.newInstance();
Transformer serializer = tf.newTransformer();
serializer.setOutputProperty("encoding", "utf-8");
serializer.setOutputProperty("indent", "yes");
serializer.setOutputProperty("method", "html");
serializer.transform(domSource, streamResult);
out.println("doc转换完毕！"+streamResult.getSystemId());
}
}
依赖：
4.0.0 com.example demo 0.0.1-SNAPSHOT demo demo 1.8 UTF-8 UTF-8 2.3.7.RELEASE org.springframework.boot spring-boot-starter-web org.projectlombok lombok 1.16.10 io.springfox springfox-swagger2 2.9.2 io.springfox springfox-swagger-ui 2.9.2 org.springframework.boot spring-boot-starter-test test org.junit.vintage junit-vintage-engine org.apache.poi poi 3.14 org.apache.poi poi-examples 3.14 org.apache.poi poi-excelant 3.14 org.apache.poi poi-scratchpad 3.14 org.apache.poi poi-ooxml 3.14 org.apache.poi ooxml-schemas 1.3 org.apache.pdfbox pdfbox 2.0.9 fr.opensagres.xdocreport xdocreport 1.0.6 org.apache.xmlbeans xmlbeans 2.6.0 org.projectlombok lombok 1.16.10 org.springframework.boot spring-boot-dependencies ${spring-boot.version} pom import org.apache.maven.plugins maven-compiler-plugin 3.8.1 1.8 1.8 UTF-8 org.springframework.boot spring-boot-maven-plugin 2.3.7.RELEASE com.lly.demo.DemoApplication repackage repackage
导航样式：