1.配置依赖<dependency><groupId>e-iceblue</groupId><artifactId>spire.doc.free</artifactId><version>3.9.0</version></dependency><dependency><groupId>org.jsoup</groupId><artifactId>jsoup</artifactId><version>1.14.2</version></dependency><dependency><groupId>org.apache.httpcomponents</groupId><artifactId>httpclient</artifactId><version>4.5.13</version></dependency>因e-iceblue在阿里云maven仓库中找不到，需配置特定仓库<repository><id>com.e-iceblue</id><url>https://repo.e-/repository/maven-public/</url></repository>2.代码demoimport com.spire.doc.Document;import com.spire.doc.FileFormat;import com.spire.doc.Section;import mons.lang3.StringUtils;import org.apache.http.HttpEntity;import org.apache.http.client.config.RequestConfig;import org.apache.http.client.methods.CloseableHttpResponse;import org.apache.http.client.methods.HttpGet;import org.apache.http.impl.client.CloseableHttpClient;import org.apache.http.impl.client.HttpClients;import org.jsoup.Jsoup;import org.jsoup.nodes.Element;import org.jsoup.select.Elements;import javax.servlet.http.HttpServletRequest;import javax.servlet.http.HttpServletResponse;import java.io.*;import java.util.Base64;import java.util.HashMap;import java.util.Iterator;import java.util.Map;public class TestHtml2Doc {public static void main(String[] args) {long start = System.currentTimeMillis();String str="";try {//富文本内容在本地文件中，根据具体情况改成从数据库或网络中获取资源FileInputStream in=new FileInputStream("D:\\oo.txt");// size 为字串的长度 ，这里一次性读完int size=in.available();byte[] buffer=new byte[size];in.read(buffer);in.close();str=new String(buffer,"utf-8");} catch (IOException e) {e.printStackTrace();}org.jsoup.nodes.Document document = Jsoup.parse(str);Element body = document.body();// 获取body里面的所有子元素Elements links = body.children();try {for (Element link : links) {Elements img = link.select("img");String src = img.attr("src");if(StringUtils.isNotBlank(src) ) {// 处理图片 因有些图片资源带有防盗链，需加上RefererMap map=new HashMap() ;map.put("Referer","");String string=doGetHeader(src,map);img.attr("src","data:image/png;base64,"+string);System.out.println("src = " + src);System.out.println("Basestring = " + string);}}} catch (Exception e) {System.out.println("转换url图片报错了："+e.getMessage());}String html = document.html();//样式调整html=html.replace("class=\"ql-align-center\"","style=\"text-align:center\"").replace("<br></p>\n" +" <p>","<br></p>\n" +" <p>  ");//System.out.println("html = " + html);exportWord(html,"590");long end = System.currentTimeMillis();System.out.println("(end-start) = " + (end-start)/1000);}public static void exportWord( String content, String fileName) {try {HttpServletRequest request=null;HttpServletResponse response=null;//新建Document对象Document document = new Document();//添加sectionSection sec = document.addSection();ByteArrayOutputStream os = new ByteArrayOutputStream();//添加段落并写入HTML文本sec.addParagraph().appendHTML(content);document.saveToStream(os, FileFormat.Docx);InputStream input = new ByteArrayInputStream(os.toByteArray());//输出文件FileOutputStream no=new FileOutputStream("D:\\"+fileName+".docx");int len =-1;byte []by = new byte[1024];while((len = input.read(by))!=-1) {no.write(by,0,len);}no.flush();no.close();input.close();} catch (Exception e) {e.printStackTrace();}}/*** @Description HTTP header GET请求图片地址 返回base64* @param url 地址* @param*/public static String doGetHeader(String url, Map<String, String> headers) {CloseableHttpResponse response = null;try (CloseableHttpClient client = HttpClients.createDefault()){HttpGet httpGet = new HttpGet(url);Iterator<Map.Entry<String, String>> iterator = headers.entrySet().iterator();//设置header信息while(iterator.hasNext()) {Map.Entry<String, String> entry = iterator.next();httpGet.setHeader(entry.getKey(), entry.getValue());}RequestConfig config = RequestConfig.custom().setConnectTimeout(60000).setConnectionRequestTimeout(60000).setSocketTimeout(60000).build();httpGet.setConfig(config);response = client.execute(httpGet);HttpEntity entity = response.getEntity();ByteArrayOutputStream out = new ByteArrayOutputStream();entity.writeTo(out);// ByteArrayOutputStream编码成base64字符串String result = new String(Base64.getEncoder().encode(out.toByteArray()));return result;}catch(Exception e) {System.out.println("httpClient请求图片url报错 " + e.getMessage());;return null;}finally {try {if(response != null) {response.close();}}catch(Exception e) {System.out.println("关闭响应流报错："+e.getMessage());}}}}
如果觉得《java 富文本html 转 word(带图片处理》对你有帮助，请点赞、收藏，并留下你的观点哦！
