基于JAVA的常用文件转换器（word 转 html,word 转 pdf,word 转 jpeg,word 转 png等等）

package com.zhengqing.demo; import cn.hutool.core.util.StrUtil; import cn.hutool.http.HttpUtil; import cn.hutool.json.JSON; import cn.hutool.json.JSONUtil; import lombok.AllArgsConstructor; import lombok.Data; import lombok.NoArgsConstructor; import lombok.extern.slf4j.Slf4j; import org.apache.poi.ss.usermodel.Cell; import org.apache.poi.ss.usermodel.Row; import org.apache.poi.ss.usermodel.Sheet; import org.apache.poi.ss.usermodel.Workbook; import org.apache.poi.xssf.usermodel.XSSFWorkbook; import org.jsoup.Jsoup; import org.jsoup.nodes.Document; import org.jsoup.nodes.Element; import org.jsoup.select.Elements; import java.io.*; import java.util.*; import java.util.regex.Matcher; import java.util.regex.Pattern; import java.util.stream.Collectors; /** * @description: todo * @author: azhou * @create: 2024/6/27 11:56 **/ @Slf4j public class AzhouTest { public static void main(String[] args) throws Exception { String path = "E:\\project\\file"; // 获取所有的需要操作的项目列表 List projectFileList = getProjectFileList(path, false); // 分两部进行，1：先把word转换为html coverWordToHtml(projectFileList, true); // 解析HTML，上传对应图片到阿里云，html章节提取变成文章内容，替换阿里云图片，将项目打包变成zip，zip上传百度网盘，获取分享链接 parseHtml(projectFileList, true); } public static void coverWordToHtml(String filePath, String name) { try { WordHandleTest.parseWord(filePath, name); } catch (Exception e) { e.printStackTrace(); } } public static boolean checkFolderExists(String directoryPath, String folderName) { File directory = new File(directoryPath); if (!directory.isDirectory()) { return false; } File[] files = directory.listFiles(); if (files != null) { for (File file : files) { if (file.isDirectory() && file.getName().equals(folderName)) { return true; } } } return false; } public static boolean checkTitle(String title) { return title.equals("论文.doc") || title.equals("论文.docx"); } public static void parseHtml(List fileEntities, Boolean printExcel) throws IOException { log.info("html解析开始，待解析项目总数：{}", fileEntities.size()); int i = 178; List errorList = new ArrayList<>(); for (FileEntity fileEntity : fileEntities) { String wordPath = fileEntity.getWordPath(); log.info("当前解析地址:{}", wordPath); if (StrUtil.isEmpty(wordPath)) { errorList.add(fileEntity); continue; } String htmlFilePath = wordPath.replaceAll(fileEntity.getArticleName(), "") + "\\html"; String projectName = fileEntity.getProjectName().replaceAll("^springboot\\d+", ""); boolean b = htmlToTxt(htmlFilePath, projectName, i); if (!b) { errorList.add(fileEntity); } else { i++; } } if (printExcel) { String outputPath = "errorHtml.xlsx"; exportToExcel(errorList, outputPath); } } public static void deleteTxt(String folderPath) { File folder = new File(folderPath); if (!folder.exists()) return; // 获取文件夹中的所有文件 File[] files = folder.listFiles(); // 遍历文件数组 for (File file : files) { // 检查文件是否为txt文件 if (file.isFile() && file.getName().endsWith(".txt")) { // 删除txt文件 boolean isDeleted = file.delete(); } } } public static boolean htmlToTxt(String htmlFilePath, String projectName, Integer projectId) throws IOException { // 删除之前的 deleteTxt(htmlFilePath); String htmlPath = htmlFilePath + "\\b.html"; File file = new File(htmlPath); if (!file.exists()) { return false; } // 上传图片 File imgFile = new File(htmlFilePath); List> imgMap = handleImg(imgFile); // 使用Jsoup解析HTML文件 Document doc = Jsoup.parse(file, "UTF-8"); String text1 = doc.text(); String result = extractTextBetweenKeywords(text1, "摘", "关"); String info = result.replaceFirst("要", "").replaceAll(" ", ""); List projectWordInfos = new ArrayList<>(); if (StrUtil.isNotEmpty(info)) { ProjectWordInfo projectWordInfo = new ProjectWordInfo(); projectWordInfo.setTitle("摘要"); projectWordInfo.setText(handleText(info)); projectWordInfos.add(projectWordInfo); } else { info = "暂无简介"; } // 获取所有的h1标签 Elements h1Elements = doc.select("h1"); // 遍历h1标签，获取两个相隔的h1标签之间的内容 for (int i = 0; i < h1Elements.size() - 1; i++) { Element currentH1 = h1Elements.get(i); String title = currentH1.text(); Element nextH1 = h1Elements.get(i + 1); // 获取当前h1标签和下一个h1标签之间的内容 Elements elements = currentH1.nextElementSiblings(); String content = elements.toString(); int i1 = content.indexOf(nextH1.toString()); if (i1 == -1) continue; content = content.substring(0, i1); if (StrUtil.isEmpty(title)) title = "未知" + i; String fileTitle = handleText(title); // 将内容添加到列表中 ProjectWordInfo projectWordInfo = new ProjectWordInfo(); // 进行图片地址替换 for (Map map : imgMap) { String key = map.get("key"); if (content.contains(key)) { content = content.replace(key, map.get("value")); } } content = content.replaceAll("'Times New Roman'", "宋体").replaceAll("'", ""); projectWordInfo.setHtmlContent(content); projectWordInfo.setTitle(fileTitle); projectWordInfo.setText(handleText(elements.text())); projectWordInfos.add(projectWordInfo); } String fileName = htmlFilePath + "\\详细信息.txt"; String content = JSONUtil.toJsonStr(projectWordInfos); writeToFile(fileName, content); ProjectInfo projectInfo = new ProjectInfo(projectName, info, content, projectId, 1); HttpUtil.post("http://localhost:8080/web/add", JSONUtil.toJsonStr(projectInfo)); handleSql(imgMap, projectInfo); return true; } @Data @AllArgsConstructor @NoArgsConstructor static class ProjectInfo { private String projectName; private String projectIntroduction; private String wordContent; private Integer id; private Integer hasThesis; } static String currentFileName = "project"; static int count = 1; public static void appendTextToFile(String contentToAppend) { String filePath = currentFileName + count + ".sql"; try { File file = new File(filePath); if (file.exists() && file.length() > 5 * 1024 * 1024) { count++; String newFileName = currentFileName + count + ".sql"; if (!new File(newFileName).exists()) { filePath =