html转Word(可批量转化但速度较慢,支持图片显示,图片在本地或网络都行)

package test; import org.apache.poi.poifs.filesystem.DirectoryEntry; import org.apache.poi.poifs.filesystem.DocumentEntry; import org.apache.poi.poifs.filesystem.POIFSFileSystem; import org.jsoup.Jsoup; import org.jsoup.nodes.Document; import org.jsoup.nodes.Element; import org.jsoup.select.Elements; import org.springframework.web.util.HtmlUtils; import java.io.*; import java.net.HttpURLConnection; import java.net.URL; import java.util.ArrayList; import java.util.HashMap; import java.util.List; import java.util.Map; import java.util.regex.Matcher; import java.util.regex.Pattern; public class HtmlToWord { static String savePath = "D:/Confluence";//文件保存位置 static String scanPath = "C:/Users/Administrator/Desktop/Confluence-space-export-094133-228.html/service/";//要扫描的文件所在文件夹 /** * 把输入流里面的内容以UTF-8编码当文本取出。 不考虑异常，直接抛出 * * @param ises * @return * @throws IOException */ private String getContent(InputStream... ises) throws IOException { if (ises != null) { StringBuilder result = new StringBuilder(); BufferedReader br; String line; for (InputStream is : ises) { br = new BufferedReader(new InputStreamReader(is, "UTF-8")); while ((line = br.readLine()) != null) { result.append(line); } } return result.toString(); } return null; } public static String writeWordFile(String content) { String path = savePath; Map<String, Object> param = new HashMap<String, Object>(); if (!"".equals(path)) { File fileDir = new File(path); if (!fileDir.exists()) { fileDir.mkdirs(); } content = HtmlUtils.htmlUnescape(content); HashMap<String, Object> imgsornm = getImgStr(content); List<HashMap<String, String>> imgs = (List<HashMap<String, String>>)imgsornm.get("list"); int count = 0; for (HashMap<String, String> img : imgs) { count++; //处理替换以“/>”结尾的img标签 content = content.replace(img.get("img"), "${imgReplace" + count + "}"); //处理替换以“>”结尾的img标签 content = content.replace(img.get("img1"), "${imgReplace" + count + "}"); Map<String, Object> header = new HashMap<String, Object>(); String imagePath = img.get("src"); String[] split = imagePath.split(":"); InputStream inputStream = null; if(split != null && split.length >3){ HttpURLConnection httpURLConnection = null; try { URL url = new URL(imagePath); httpURLConnection = (HttpURLConnection) url.openConnection();// 设置网络连接超时时间 httpURLConnection.setConnectTimeout(3000);// 设置应用程序要从网络连接读取数据 httpURLConnection.setDoInput(true); httpURLConnection.setRequestMethod("GET"); int responseCode = httpURLConnection.getResponseCode(); if (responseCode == 200) {// 从服务器返回一个输入流 inputStream = httpURLConnection.getInputStream(); } } catch (Exception e) { e.printStackTrace(); } } else { try { String imageispath = "C:/Users/Administrator/Desktop/Confluence-space-export-094133-228.html/service/" + imagePath; inputStream = new FileInputStream(imageispath); } catch (FileNotFoundException e1) { // TODO Auto-generated catch block e1.printStackTrace(); } } try { //如果没有宽高属性，默认设置为400*300 if (img.get("width") == null || img.get("height") == null) { header.put("width", 400); header.put("height", 300); } else { header.put("width", (int) (Double.parseDouble(img.get("width")))); header.put("height", (int) (Double.parseDouble(img.get("height")))); } header.put("type", "jpg"); header.put("content", OfficeUtil.inputStream2ByteArray(inputStream, true)); } catch (Exception e) { e.printStackTrace(); } param.put("${imgReplace" + count + "}", header); } try { // 生成doc格式的word文档，需要手动改为docx byte by[] = content.getBytes("UTF-8"); ByteArrayInputStream bais = new ByteArrayInputStream(by); POIFSFileSystem poifs = new POIFSFileSystem(); DirectoryEntry directory = poifs.getRoot(); DocumentEntry documentEntry = directory.createDocument("WordDocument", bais); FileOutputStream ostream = new FileOutputStream(savePath + "/temp.doc"); poifs.writeFilesystem(ostream); bais.close(); ostream.close(); JacobUtil.wordConveter(savePath + "/temp.doc"); // 临时文件（手动改好的docx文件） CustomXWPFDocument doc = OfficeUtil.generateWord(param, savePath + "/temp.docx"); //最终生成的带图片的word文件 System.out.println(); //处理h1标签作为文件名時的特殊字符 String namestr = (String)imgsornm.get("title"); String nm = RegExString(namestr);//去除文件名的特殊字符 FileOutputStream fopts = new FileOutputStream(savePath + "/"+ nm +".docx"); doc.write(fopts); fopts.close(); } catch (Exception e) { e.printStackTrace(); } } return "save is OK"; } //获取html中的图片元素信息 public static HashMap<String, Object> getImgStr(String htmlStr) { HashMap<String, Object> rnmap = new HashMap<String, Object>(); List<HashMap<String, String>> pics = new ArrayList<HashMap<String, String>>(); Document doc = Jsoup.parse(htmlStr); Elements imgs = doc.select("img"); //读取html中h1标签用来作为文件名开始------- Elements title = doc.select("h1"); String text = title.text(); HashMap<String, String> mapnm = new HashMap<String, String>(); rnmap.put("title", text); //读取html中h1标签用来作为文件名结束------- for (Element img : imgs) { System.out.println(img.attr("width").length()); HashMap<String, String> map = new HashMap<String, String>(); if (!"".equals(img.attr("width")) /*&& img.attr("width").length() >= 2*/) { map.put("width", img.attr("width").substring(0, img.attr("width").length())); } if (!"".equals(img.attr("height")) /*&& img.attr("height").length() >= 2*/) { map.put("height", img.attr("height").substring(0, img.attr("height").length())); } map.put("img", img.toString().substring(0, img.toString().length() - 1) + "/>"); map.put("img1", img.toString()); map.put("src", img.attr("src")); pics.add(map); }