【记录】java 利用 poi 将word 转html

记录下利用poi 将word文件转为html文件，兼容doc及docx。

本地main方法运行成功，用到的jar包包括：

关于jar:之前在网上搜索的内容，未找到具体jar的版本，于是随意下的版本，出现了nosuchmethod或者ClassNoDefException异常，就是说白了jar冲突。。。然后在maven库http://mvnrepository.com/search?q=pdf上把所有的2015年的这几个jar下载了，我猜测同一年的应该不会有jar冲突。（xmlbeans不是2015的）。

代码大致如下:

import java.io.BufferedWriter;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStreamWriter;
import java.util.List;

import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerException;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;

import org.apache.commons.io.output.ByteArrayOutputStream;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.PicturesManager;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.usermodel.Picture;
import org.apache.poi.hwpf.usermodel.PictureType;
import org.apache.poi.xwpf.converter.core.FileImageExtractor;
import org.apache.poi.xwpf.converter.core.IURIResolver;
import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter;
import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.w3c.dom.Document;

public class PoiUtil {
   public static void main(String[] args) {
       try {
           wordToHtml("d:\\12345.docx", "d:\\", "123456.html");
           wordToHtml("d:\\123.doc", "d:\\", "123.html");
       } catch (Exception e) {
           e.printStackTrace();
       }
   }

   public static void wordToHtml(String wordPath, String htmlPath,
           String newFilename) throws Exception {
       convert2Html(wordPath, htmlPath, newFilename);
   }

   public static void writeFile(String content, String path) {
       FileOutputStream fos = null;
       BufferedWriter bw = null;
       try {
           File file = new File(path);
           fos = new FileOutputStream(file);
           bw = new BufferedWriter(new OutputStreamWriter(fos));
           bw.write(content);
       } catch (FileNotFoundException e) {
           e.printStackTrace();
       } catch (IOException e) {
           e.printStackTrace();
       } finally {
           try {
               if (bw != null)
                   bw.close();
               if (fos != null)
                   fos.close();
           } catch (IOException e) {
               e.printStackTrace();
           }
       }
   }

   /**
   * word转html，支持doc docx
   * @param fileName word文件名
   * @param outPutFilePath html存储路径
   * @param newFileName html名
   * @throws Exception
   */
   public static void convert2Html(String fileName, String outPutFilePath,
           String newFileName) throws Exception {

       String substring = fileName.substring(fileName.lastIndexOf(".") + 1);
       ByteArrayOutputStream out = new ByteArrayOutputStream();

       /**
       * word2007和word2003的构建方式不同，前者的构建方式是xml，后者的构建方式是dom树。
       * 文件的后缀也不同，前者后缀为.docx，后者后缀为.doc 相应的，apache.poi提供了不同的实现类。
       */
       if ("docx".equals(substring)) {
           InputStream inputStream = new FileInputStream(new File(fileName));
           XWPFDocument document = new XWPFDocument(inputStream);

           final String imageUrl = "";

           XHTMLOptions options = XHTMLOptions.create();

           options.setExtractor(new FileImageExtractor(new File(outPutFilePath
                   + imageUrl)));
           options.setIgnoreStylesIfUnused(false);
           options.setFragment(true);
           options.URIResolver(new IURIResolver() {
               @Override
               public String resolve(String uri) {
                   return imageUrl + uri;
               }
           });

           XHTMLConverter.getInstance().convert(document, out, options);
       } else {
           HWPFDocument wordDocument = new HWPFDocument(new FileInputStream(
                   fileName));
           WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
                   DocumentBuilderFactory.newInstance().newDocumentBuilder()
                           .newDocument());
           wordToHtmlConverter.setPicturesManager(new PicturesManager() {
               public String savePicture(byte[] content,
                       PictureType pictureType, String suggestedName,
                       float widthInches, float heightInches) {
                   return suggestedName;
               }
           });
           wordToHtmlConverter.processDocument(wordDocument);
           List pics = wordDocument.getPicturesTable().getAllPictures();
           if (pics != null) {
               for (int i = 0; i < pics.size(); i++) {
                   Picture pic = (Picture) pics.get(i);
                   try {
                       pic.writeImageContent(new FileOutputStream(
                               outPutFilePath + pic.suggestFullFileName()));
                   } catch (FileNotFoundException e) {
                       e.printStackTrace();
                   }
               }
           }
           Document htmlDocument = wordToHtmlConverter.getDocument();
           DOMSource domSource = new DOMSource(htmlDocument);
           StreamResult streamResult = new StreamResult(out);

           TransformerFactory tf = TransformerFactory.newInstance(); // 这个应该是转换成xml的
           Transformer serializer = tf.newTransformer();
           serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
           serializer.setOutputProperty(OutputKeys.INDENT, "yes");
           serializer.setOutputProperty(OutputKeys.METHOD, "html");
           serializer.transform(domSource, streamResult);
       }

       out.close();
       writeFile(new String(out.toByteArray()), outPutFilePath + newFileName);
   }

}

【记录】java 利用 poi 将word 转html

猜你喜欢