Java实现word转HTML

清疚 2023-06-18 13:57 42阅读 0赞

Java word转html主要是为了word的在线浏览。不过转换可用性不是很好。我们先开始开发吧

第一步：引用Maven

  1. <!-- Word转HTML start -->
  2.         <dependency>
  3.             <groupId>org.apache.poi</groupId>
  4.             <artifactId>poi-scratchpad</artifactId>
  5.             <version>3.14</version>
  6.         </dependency>
  8.         <dependency>
  9.             <groupId>org.apache.poi</groupId>
  10.             <artifactId>poi-ooxml</artifactId>
  11.             <version>3.14</version>
  12.         </dependency>
  14.         <dependency>
  15.             <groupId>fr.opensagres.xdocreport</groupId>
  16.             <artifactId>xdocreport</artifactId>
  17.             <version>1.0.6</version>
  18.         </dependency>
  20.         <dependency>
  21.             <groupId>org.apache.poi</groupId>
  22.             <artifactId>poi-ooxml-schemas</artifactId>
  23.             <version>3.14</version>
  24.         </dependency>
  26.         <dependency>
  27.             <groupId>org.apache.poi</groupId>
  28.             <artifactId>ooxml-schemas</artifactId>
  29.             <version>1.3</version>
  30.         </dependency>
  32.         <dependency>
  33.             <groupId>org.jsoup</groupId>
  34.             <artifactId>jsoup</artifactId>
  35.             <version>1.11.3</version>
  36.         </dependency>
  37.         <!-- Word转HTML end -->

第二步：java实现代码

原始版本；

  1. package com.mmxpw.mmw.file.view.word;
  3. import org.apache.poi.hwpf.HWPFDocument;
  4. import org.apache.poi.hwpf.converter.PicturesManager;
  5. import org.apache.poi.hwpf.converter.WordToHtmlConverter;
  6. import org.apache.poi.hwpf.usermodel.PictureType;
  7. import org.apache.poi.xwpf.converter.core.BasicURIResolver;
  8. import org.apache.poi.xwpf.converter.core.FileImageExtractor;
  9. import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter;
  10. import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;
  11. import org.apache.poi.xwpf.usermodel.XWPFDocument;
  12. import org.w3c.dom.Document;
  14. import javax.xml.parsers.DocumentBuilderFactory;
  15. import javax.xml.parsers.ParserConfigurationException;
  16. import javax.xml.transform.OutputKeys;
  17. import javax.xml.transform.Transformer;
  18. import javax.xml.transform.TransformerException;
  19. import javax.xml.transform.TransformerFactory;
  20. import javax.xml.transform.dom.DOMSource;
  21. import javax.xml.transform.stream.StreamResult;
  22. import java.io.*;
  24. public class WordToHtml {
  26.     /**
  27.      * 将word2003转换为html文件
  28.      *
  29.      * @param wordPath word文件路径
  30.      * @param wordName word文件名称无后缀
  31.      * @param suffix   word文件后缀
  32.      * @param htmlPath html存储地址
  33.      * @throws IOException
  34.      * @throws TransformerException
  35.      * @throws ParserConfigurationException
  36.      */
  37.     public static String Word2003ToHtml(String wordPath, String wordName, String suffix, String htmlPath)
  38.             throws IOException, TransformerException, ParserConfigurationException {
  39.         String htmlName = wordName + ".html";
  40.         final String imagePath = htmlPath + "image" + File.separator;
  41.         // 判断html文件是否存在
  42.         File htmlFile = new File(htmlPath + htmlName);
  43.         if (htmlFile.exists()) {
  44.             return htmlFile.getAbsolutePath();
  45.         }
  46.         // 原word文档
  47.         final String file = wordPath + File.separator + wordName + suffix;
  48.         InputStream input = new FileInputStream(new File(file));
  49.         HWPFDocument wordDocument = new HWPFDocument(input);
  50.         WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
  51.                 DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
  52.         // 设置图片存放的位置
  53.         wordToHtmlConverter.setPicturesManager(new PicturesManager() {
  54.             public String savePicture(byte[] content, PictureType pictureType, String suggestedName, float widthInches,
  55.                                       float heightInches) {
  56.                 File imgPath = new File(imagePath);
  57.                 if (!imgPath.exists()) {// 图片目录不存在则创建
  58.                     imgPath.mkdirs();
  59.                 }
  60.                 File file = new File(imagePath + suggestedName);
  61.                 try {
  62.                     OutputStream os = new FileOutputStream(file);
  63.                     os.write(content);
  64.                     os.close();
  65.                 } catch (FileNotFoundException e) {
  66.                     e.printStackTrace();
  67.                 } catch (IOException e) {
  68.                     e.printStackTrace();
  69.                 }
  70.                 // 图片在html文件上的路径 相对路径
  71.                 return "image/" + suggestedName;
  72.             }
  73.         });
  74.         // 解析word文档
  75.         wordToHtmlConverter.processDocument(wordDocument);
  76.         Document htmlDocument = wordToHtmlConverter.getDocument();
  77.         // 生成html文件上级文件夹
  78.         File folder = new File(htmlPath);
  79.         if (!folder.exists()) {
  80.             folder.mkdirs();
  81.         }
  82.         OutputStream outStream = new FileOutputStream(htmlFile);
  83.         DOMSource domSource = new DOMSource(htmlDocument);
  84.         StreamResult streamResult = new StreamResult(outStream);
  85.         TransformerFactory factory = TransformerFactory.newInstance();
  86.         Transformer serializer = factory.newTransformer();
  87.         serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
  88.         serializer.setOutputProperty(OutputKeys.INDENT, "yes");
  89.         serializer.setOutputProperty(OutputKeys.METHOD, "html");
  90.         serializer.transform(domSource, streamResult);
  91.         return htmlFile.getAbsolutePath();
  92.     }
  93.     /**
  94.      *
  95.      * 2007版本word转换成html
  96.      *
  97.      * @param wordPath  word文件路径
  98.      * @param wordName word文件名称无后缀
  99.      * @param suffix   word文件后缀
  100.      * @param htmlPath html存储地址
  101.      * @return
  102.      * @throws IOException
  103.      */
  104.     public static String Word2007ToHtml(String wordPath, String wordName, String suffix, String htmlPath)
  105.             throws IOException {
  106.         String htmlName = wordName + ".html";
  107.         String imagePath = htmlPath + "image" + File.separator;
  108.         // 判断html文件是否存在
  109.         File htmlFile = new File(htmlPath + htmlName);
  110.         if (htmlFile.exists()) {
  111.             return htmlFile.getAbsolutePath();
  112.         }
  113.         // word文件
  114.         File wordFile = new File(wordPath + File.separator + wordName + suffix);
  115.         // 1) 加载word文档生成 XWPFDocument对象
  116.         InputStream in = new FileInputStream(wordFile);
  117.         XWPFDocument document = new XWPFDocument(in);
  118.         // 2) 解析 XHTML配置 (这里设置IURIResolver来设置图片存放的目录)
  119.         File imgFolder = new File(imagePath);
  120.         XHTMLOptions options = XHTMLOptions.create();
  121.         options.setExtractor(new FileImageExtractor(imgFolder));
  122.         // html中图片的路径 相对路径
  123.         options.URIResolver(new BasicURIResolver("image"));
  124.         options.setIgnoreStylesIfUnused(false);
  125.         options.setFragment(true);
  126.         // 3) 将 XWPFDocument转换成XHTML
  127.         // 生成html文件上级文件夹
  128.         File folder = new File(htmlPath);
  129.         if (!folder.exists()) {
  130.             folder.mkdirs();
  131.         }
  132.         OutputStream out = new FileOutputStream(htmlFile);
  133.         XHTMLConverter.getInstance().convert(document, out, options);
  134.         return htmlFile.getAbsolutePath();
  135.     }
  137.     public static void main(String[] args) {
  138.         try {
  139.             //Word2003ToHtml("E:\\templates", "2019-11-26", ".doc", "E://templates/");
  140.             Word2007ToHtml("E:\\templates", "OnLineWord", ".doc", "E://templates/");
  141.         } catch (Exception e) {
  142.             e.printStackTrace();
  143.         }
  144.     }
  147. }

benr本人业务定制版本：

  1. package com.mmxpw.mmw.file.view.word;
  3. import org.apache.commons.fileupload.FileItem;
  4. import org.apache.poi.hwpf.HWPFDocument;
  5. import org.apache.poi.hwpf.converter.PicturesManager;
  6. import org.apache.poi.hwpf.converter.WordToHtmlConverter;
  7. import org.apache.poi.hwpf.usermodel.PictureType;
  8. import org.apache.poi.xwpf.converter.core.BasicURIResolver;
  9. import org.apache.poi.xwpf.converter.core.FileImageExtractor;
  10. import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter;
  11. import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;
  12. import org.apache.poi.xwpf.usermodel.XWPFDocument;
  13. import org.w3c.dom.Document;
  15. import javax.xml.parsers.DocumentBuilderFactory;
  16. import javax.xml.parsers.ParserConfigurationException;
  17. import javax.xml.transform.OutputKeys;
  18. import javax.xml.transform.Transformer;
  19. import javax.xml.transform.TransformerException;
  20. import javax.xml.transform.TransformerFactory;
  21. import javax.xml.transform.dom.DOMSource;
  22. import javax.xml.transform.stream.StreamResult;
  23. import java.io.*;
  24. import java.util.ArrayList;
  25. import java.util.List;
  27. /**
  28.  * @Class WordToHtmlNew
  29.  * @Version 1.0
  30.  * @Date 创建时间：2019-12-02 09:29
  31.  * @Direction 类说明   传入文件，自动识别2003版本或者07版本，然后解析成HTML，且自动解析里面的图片，然后对图片做本地化存储，然后返回HTML
  32.  */
  33. public class WordToHtmlNew {
  35.     public final static List<String> FILE_TYPE = new ArrayList<>() ;
  37.     static{
  38.         FILE_TYPE.add( "doc" ) ;
  39.         FILE_TYPE.add( "docx" ) ;
  40.     }
  42.     /***
  43.      * 文件格式处理
  44.      * @param fileItem
  45.      * @return
  46.      * @throws Exception
  47.      */
  48.     public static boolean fileTypeValidate( File fileItem ) throws Exception{
  49.         String[] namePix = fileItem.getName().split("\\u002E");
  50.         String suffix = namePix[namePix.length-1] ;
  51.         if( !FILE_TYPE.contains( suffix )  ){
  52.             throw new Exception( "您导入的文件格式错误，请导入word类型的文件." ) ;
  53.         }else{
  54.             return true ;
  55.         }
  56.     }
  58.     /****
  59.      * 判断文档的类型 本方法判断的是是否是新版
  60.      * @param fileItem
  61.      * @return
  62.      */
  63.     public static boolean isDocx( File fileItem ){
  64.         String[] namePix = fileItem.getName().split("\\u002E");
  65.         String suffix = namePix[namePix.length-1] ;
  66.         if( suffix.toLowerCase().equals( "docx" )){
  67.             return true ;
  68.         }else{
  69.             return false ;
  70.         }
  71.     }
  74.     /****
  75.      * 自动识别版本
  76.      * 自动生成word内部的图片
  77.      * 自动过滤其他的类型文件
  78.      * 自动添加不通模块的图片前缀
  79.      * @param file
  80.      * @param iamgePrefix  在file的同级创建文件夹-image 提取word内部图片前缀为传入值：prefix
  81.      * @param accessPath   html访问路径的url为：accessPath
  82.      * @return
  83.      */
  84.     public static String WordAutoToHtml( File file , String iamgePrefix , String accessPath ) throws Exception {
  85.         if( file == null ){
  86.             throw new Exception( "您传入的文件为空." ) ;
  87.         }else{
  88.             if( !file.exists() ){
  89.                 throw new Exception( "您传入的文件不存在." ) ;
  90.             }else{
  91.                 if ( fileTypeValidate( file ) ){
  92.                     //1.1 开始提取文件名称，文件路径
  93.                     String path = file.getParent() ;
  94.                     String fileName = file.getName() ;
  95.                     //切割文件名里面的信息
  96.                     String prefix = fileName.substring( 0 , fileName.lastIndexOf(".")  );
  97.                     String suffix = fileName.substring( fileName.lastIndexOf(".") + 1  );
  98.                     /*String[] namePix = fileName.split("\\u002E");
  99.                     String suffix = namePix[namePix.length-1] ;*/
  100.                     //1.2 开始做文件识别，然后指向去2007版本的docx 还是去2003版本的doc
  101.                     path = path + File.separator ;
  102.                     if( isDocx( file ) ){
  103.                         return Word2007ToHtml( file , path  , prefix  , path , iamgePrefix , accessPath  ) ;
  104.                     }else{
  105.                         return Word2003ToHtml( file , path , prefix , path , iamgePrefix , accessPath  ) ;
  106.                     }
  107.                 }
  108.             }
  109.         }
  110.         return null ;
  111.     }
  115.     /**
  116.      * 将word2003转换为html文件
  117.      *
  118.      * @param wordFile word文件
  119.      * @param wordPath word文件路径
  120.      * @param wordName word文件名称无后缀
  121.      * @param htmlPath html存储地址
  122.      * @param prefix   图片存储前缀
  123.      * @param accessPath  图片的相对路径访问地址
  124.      * @throws IOException
  125.      * @throws TransformerException
  126.      * @throws ParserConfigurationException
  127.      */
  128.     public static String Word2003ToHtml(File wordFile , String wordPath, String wordName, String htmlPath
  129.             ,final String prefix  ,final String accessPath)
  130.             throws IOException, TransformerException, ParserConfigurationException {
  131.         String htmlName = wordName + ".html";
  132.         //1.1 判断html文件是否存在
  133.         File htmlFile = new File(htmlPath  + htmlName);
  134.         if (htmlFile.exists()) {
  135.             return htmlFile.getAbsolutePath();
  136.         }
  137.         //1.2 原word文档 - 文件路径信息
  138.         //final String file = wordPath + File.separator + wordName  + "." + suffix;
  139.         //InputStream input = new FileInputStream( new File( wordFile ) );
  140.         InputStream input = new FileInputStream( wordFile );
  141.         //1.3 final String imagePath
  142.         final String imagePath = wordPath + "image" ;
  144.         HWPFDocument wordDocument = new HWPFDocument(input);
  145.         WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
  146.                 DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
  147.         // 设置图片存放的位置
  148.         wordToHtmlConverter.setPicturesManager(new PicturesManager() {
  149.             public String savePicture(byte[] content, PictureType pictureType, String suggestedName, float widthInches,
  150.                                       float heightInches) {
  151.                 File imgPath = new File(imagePath);
  152.                 if (!imgPath.exists()) {// 图片目录不存在则创建
  153.                     imgPath.mkdirs();
  154.                 }
  155.                 String imageFileName = prefix  + suggestedName ;
  156.                 File file = new File(imagePath + File.separator + imageFileName );
  157.                 try {
  158.                     OutputStream os = new FileOutputStream(file);
  159.                     os.write(content);
  160.                     os.close();
  161.                 } catch (FileNotFoundException e) {
  162.                     e.printStackTrace();
  163.                 } catch (IOException e) {
  164.                     e.printStackTrace();
  165.                 }
  166.                 // 图片在html文件上的路径 相对路径
  167.                 return accessPath + imageFileName;
  168.             }
  169.         });
  170.         // 解析word文档
  171.         wordToHtmlConverter.processDocument(wordDocument);
  172.         Document htmlDocument = wordToHtmlConverter.getDocument();
  173.         // 生成html文件上级文件夹
  174.         File folder = new File(htmlPath);
  175.         if (!folder.exists()) {
  176.             folder.mkdirs();
  177.         }
  178.         OutputStream outStream = new FileOutputStream(htmlFile);
  179.         DOMSource domSource = new DOMSource(htmlDocument);
  180.         StreamResult streamResult = new StreamResult(outStream);
  181.         TransformerFactory factory = TransformerFactory.newInstance();
  182.         Transformer serializer = factory.newTransformer();
  183.         serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
  184.         serializer.setOutputProperty(OutputKeys.INDENT, "yes");
  185.         serializer.setOutputProperty(OutputKeys.METHOD, "html");
  186.         serializer.transform(domSource, streamResult);
  187.         return htmlFile.getAbsolutePath();
  188.     }
  190.     /**
  191.      * 2007版本word转换成html
  192.      *
  193.      * @param wordPath  word文件路径
  194.      * @param wordName word文件名称无后缀
  195.      * @param suffix   word文件后缀
  196.      * @param htmlPath html存储地址
  197.      * @param prefix   图片存储前缀
  198.      * @param accessPath  图片的相对路径访问地址
  199.      * @return
  200.      * @throws IOException
  201.      */
  202.     public static String Word2007ToHtml( File wordFile , String wordPath, String wordName, String htmlPath
  203.             ,final String prefix ,final String accessPath)
  204.             throws IOException, TransformerException, ParserConfigurationException {
  205.         String htmlName = wordName + ".html";
  206.         //1.1) 拼接HTML文件地址、判断html文件是否存在
  207.         File htmlFile = new File(htmlPath + htmlName);
  208.         if (htmlFile.exists()) {
  209.             return htmlFile.getAbsolutePath();
  210.         }
  211.         // word文件
  212.         //File wordFile = new File(wordPath + File.separator + wordName + suffix);
  213.         //1.2) 加载word文档生成 XWPFDocument对象
  214.         InputStream in = new FileInputStream( wordFile );
  215.         XWPFDocument document = new XWPFDocument( in );
  216.         //1.3) 解析 XHTML配置 (这里设置IURIResolver来设置图片存放的目录)
  217.         final String imagePath = wordPath + "image" ;
  218.         File imgFolder = new File( imagePath );
  219.         XHTMLOptions options = XHTMLOptions.create();
  220.         options.setExtractor(new FileImageExtractor(imgFolder));
  221.         // html中图片的路径 相对路径
  222.         options.URIResolver( new BasicURIResolver( accessPath ) );
  223.         options.setIgnoreStylesIfUnused(false);
  224.         options.setFragment(true);
  225.         //1.4) 将 XWPFDocument转换成XHTML
  226.         // 生成html文件上级文件夹
  227.         File folder = new File(htmlPath);
  228.         if (!folder.exists()) {
  229.             folder.mkdirs();
  230.         }
  231.         OutputStream out = new FileOutputStream(htmlFile);
  232.         XHTMLConverter.getInstance().convert(document, out, options);
  233.         return htmlFile.getAbsolutePath();
  234.     }
  236.     public static void main(String[] args) {
  237.         try {
  238.             //Word2003ToHtml("E:\\templates", "2019-11-26", ".doc", "E://templates/");
  239.             WordAutoToHtml( new File("E:\\templates\\OnLineWord.doc") , "image_" , "image/");
  240.             //WordAutoToHtml( new File("E:\\templates\\OnLineWord.docx") , "image_" , "image/");
  241.         } catch (Exception e) {
  242.             e.printStackTrace();
  243.         }
  244.     }
  247. }

第三步：使用结果

2007版本：Word文档样式

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3lleGlhb21vZGVtbw_size_16_color_FFFFFF_t_70

实际转换结果为：图片的居中，字体等信息自动换行效果不理想。

watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3lleGlhb21vZGVtbw_size_16_color_FFFFFF_t_70 1

2003版本的Word文档也有上述问题，大家使用此技术时请注意此问题。

参考来源：Java实现word转HTML

发表评论

表情：
评论列表 （有 0 条评论，42人围观）

还没有评论，来说两句吧...

相关阅读