HTML转word_讯飞语记怎么变成word文档

依赖jar
poi-3.17.jar
poi-excelant-3.17.jar
poi-ooxml-3.17.jar
poi-ooxml-schemas-3.17.jar
jsoup-1.11.3.jar

/**
  * HTML转word
  *
  * @param noteName 导出文件名称
  * @paramre portDirName 文件路径
  * @param researchNoteInfo 文件的html
  * @return void
  * @author Solitary
  * @date 2019/1/11 9:21
  */
public static void htmlToWord(String noteName, String reportDirName, String researchNoteInfo) throws Exception {
     //拼一个标准的HTML格式文档
    Document document = Jsoup.parse(researchNoteInfo);
    FileUtils.fileIsExist(reportDirName);
    InputStream is = new ByteArrayInputStream(document.html().getBytes("GBK"));
    OutputStream os = new FileOutputStream(reportDirName+noteName);
    inputStreamToWord(is, os);
}
    
/**
 * 把is写入到对应的word输出流os中
 *
 * @param is
 * @param os
 * @throws IOException
 */
private static void inputStreamToWord(InputStream is, OutputStream os) throws IOException {
    POIFSFileSystem fs = new POIFSFileSystem();
    DirectoryNode root = fs.getRoot();
    root.createDocument("WordDocument", is);
    fs.writeFilesystem(os);
    os.close();
    is.close();
}

依赖jar
jacob.jar
jsoup-1.11.3.jar

/**
* 创建空白文档_写入html_处理空白文档image_复制空白文档至最终文档
* 
* @param imgs
* @param html
* @param localpath
*/
public static String getWord(String html, String localpath, long researchId) {
// 下载图片到本地 略
// 图片在文档中的键${name} - 值图片的绝对路径    imgMap.put("${ABC}", localpath + "\\ABC.png");
Map<String, String> imgMap = new HashMap<String, String>();
// 解析html_创建空白文档_html写入空白文档
Document document = Jsoup.parse(html);
for (Element element : document.body().select("body > *")) {
sysElementText(element, localpath, imgMap);
}
createWord(localpath, "blank");
File doc = new File(localpath + File.separator + "blank.doc");
FileWriter fw;
try {
fw = new FileWriter(doc);
fw.write(document.html(), 0, document.html().length());// 写入文件
fw.flush(); // 清空FileWriter缓冲区
fw.close();
} catch (IOException e) {
e.printStackTrace();
}
String complete = String.valueOf(researchId);
// 复制空白文档-粘贴到临时文档（相当于手动执行copy_paste）
MSOfficeGeneratorUtils officeUtils = new MSOfficeGeneratorUtils(false);
officeUtils.openDocument(localpath + File.separator + "blank.doc");
officeUtils.copy(); // 拷贝整篇文档
officeUtils.close();
officeUtils.createNewDocument();
officeUtils.paste(); // 粘贴整篇文档
// 将图片${image_name}替换为真实图片
for (Entry<String, String> entry : imgMap.entrySet())
officeUtils.replaceText2Image(entry.getKey(), entry.getValue());
officeUtils.setFont(true, false, false, "0,0,0", "20", "宋体"); // 设置字体,具体参数
officeUtils.saveAs(localpath + File.separator + complete + ".doc"); // 可生成UUID.doc文件，利用UUID防止同名
officeUtils.close(); // 关闭Office Word创建的文档
officeUtils.quit(); // 退出Office Word程序
imgMap.clear();
return complete;
}
/**
*  替换img标签为p标签
* 
* @param node 
* @param imgPath 本地图片存储路径
* @param imgMap key：${imgName} value:
*/
public static void sysElementText(Node node, String imgPath, Map<String, String> imgMap) {
if (node.childNodes().size() == 0) {
if (node.nodeName().equals("img")) {
String src = node.attr("src");
String fileName = src.substring(src.lastIndexOf("/") + 1, src.length());
Element element = new Element("p");
element.append("${"+fileName+"}");
element.attr("style", node.attr("style"));
node.replaceWith(element);
imgMap.put("${"+fileName+"}", imgPath + File.separator + fileName);
}
}
if (node.childNodes().size() > 0) {
List<Node> childNodes = node.childNodes();
for (Node node2 : childNodes) {
if (node2.nodeName().equals("img")) {
String src = node2.attr("src");
String fileName = src.substring(src.lastIndexOf("/") + 1, src.length());
Element element = new Element("p");
element.append("${"+fileName+"}");
element.attr("style", node2.attr("style"));
node2.replaceWith(element);
imgMap.put("${"+fileName+"}", imgPath + File.separator + fileName);
}
}
}
}
/**
* 创建word文档
* 
* @param localpath
* @param name
* @return
*/
public static void createWord(String localpath, String name) {
MSOfficeGeneratorUtils msOfficeUtils = new MSOfficeGeneratorUtils(false); // 整合过程设置为可见
msOfficeUtils.createNewDocument();
msOfficeUtils.saveAs(localpath + File.separator + name + ".doc");
msOfficeUtils.close();
msOfficeUtils.quit();
}

依赖jar
itext-2.1.7.jar
itext-rtf-2.1.7.jar

private static void html2WordIText(String html, String noteName, String reportDirName, long researchId) {
// 图片临时存放路径
String pwd = "tmp/researchNote";
Set<String> srcSet = ImageUtils.getImgStr(html);
for (String src : srcSet) {
String srcName = src.split("[/]")[src.split("[/]").length - 1];
ImageUtils.download(src, srcName, pwd + "/" + String.valueOf(researchId));
String newSrc = pwd + "/" + String.valueOf(researchId) + "/" + srcName;
html = html.replace(src, newSrc);
}
FileUtils.fileIsExist(reportDirName);
OutputStream out = null;
try {
out = new FileOutputStream(reportDirName + noteName);
Document document = new Document(PageSize.A4);
RtfWriter2.getInstance(document, out);
document.open();
Paragraph context = new Paragraph();
// Image img = Image.getInstance("D:\\图片\\2.jpg");
// img.setAbsolutePosition(0, 0);//
// document.add(img);
StyleSheet ss = new StyleSheet();
HashMap<String, String> interfaceProps = Maps.newHashMap();
interfaceProps.put("img_baseurl", "");
List htmlList = HTMLWorker.parseToList(new StringReader(html), ss, interfaceProps);
for (int i = 0; i < htmlList.size(); i++) {
com.lowagie.text.Element e = (com.lowagie.text.Element) htmlList.get(i);
context.add(e);
}
document.add(context);
document.close();
FileUtils.deletefile(pwd);
} catch (Exception e) {
} finally {
try {
if (out != null) {
out.close();
}
} catch (IOException e) {
}
}
}
ImageUtils.java :
public static Set<String> getImgStr(String htmlStr) {
Set<String> pics = new HashSet<String>();
String img = "";
Pattern pImage;
Matcher mImage;
String regEx_img = "<img.*src\\s*=\\s*(.*?)[^>]*?>";
pImage = Pattern.compile(regEx_img, Pattern.CASE_INSENSITIVE);
mImage = pImage.matcher(htmlStr);
while (mImage.find()) {
// 得到<img />数据
img = mImage.group();
// 匹配<img>中的src数据 
Matcher m = Pattern.compile("src\\s*=\\s*\"?(.*?)(\"|>|\\s+)").matcher(img);
while (m.find()) {
pics.add(m.group(1));
}
}
return pics;
}
/**
* 下载图片
* @param urlString  路径
* @param filename   保存的文件名
* @param savePath   保存路径
*/
public static void download(String urlString, String filename, String savePath) {
InputStream is = null;
OutputStream os = null;
try {
File researchFile = new File(savePath + File.separator + filename);
if (researchFile.exists()) {
return;
}
// 构造URL
URL url = new URL(urlString);
// 打开连接
URLConnection con = url.openConnection(new Proxy();
// 设置请求超时为5s
con.setConnectTimeout(5*1000);
con.setRequestProperty("User-Agent", "Mozilla/4.0 (compatible; MSIE 5.0; Windows NT; DigExt)"); 
// 输入流
is = con.getInputStream();
// 1K的数据缓冲
byte[] bs = new byte[1024 * 1024 * 3];
// 读取到的数据长度
int len;
// 输出的文件流
File sf=new File(savePath);
if(!sf.exists()){
sf.mkdirs();
}
os = new FileOutputStream(sf.getPath() + File.separator + filename);
// 开始读取
while ((len = is.read(bs)) != -1) {
os.write(bs, 0, len);
}
// 完毕，关闭所有链接
os.close();
is.close();
} catch (IOException e) {
e.printStackTrace();
} finally {
if (os != null) {
try {
os.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}