Android将word(doc、docx)转换成html

package com.word; import java.io.BufferedReader; import java.io.BufferedWriter; import java.io.ByteArrayOutputStream; import java.io.File; import java.io.FileInputStream; import java.io.FileNotFoundException; import java.io.FileOutputStream; import java.io.FileReader; import java.io.IOException; import java.io.InputStream; import java.io.OutputStream; import java.io.OutputStreamWriter; import java.util.List; import org.w3c.dom.Document; import javax.xml.parsers.DocumentBuilderFactory; import javax.xml.parsers.ParserConfigurationException; import javax.xml.transform.OutputKeys; import javax.xml.transform.Transformer; import javax.xml.transform.TransformerConfigurationException; 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.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.FileURIResolver; import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter; import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions; import org.apache.poi.xwpf.usermodel.XWPFDocument; ; public class Word07 { /** * @param args */ public static void main(String[] args) { // TODO Auto-generated method stub try { File file = new File("e:\\test\\1.doc"); if (!file.exists()) { System.out.println("Sorry file does not exists!"); } else { if (file.getName().endsWith(".docx") || file.getName().endsWith(".DOCX")) { InputStream inputStream = new FileInputStream(file); XWPFDocument document = new XWPFDocument(inputStream); File imageFolderFile = new File("e://test"); XHTMLOptions options = XHTMLOptions.create().URIResolver( new FileURIResolver(imageFolderFile)); options.setExtractor(new FileImageExtractor(imageFolderFile)); options.setIgnoreStylesIfUnused(false); options.setFragment(true); File file2 = new File("e:\\test\\1.html"); OutputStream outputStream = new FileOutputStream(file2); XHTMLConverter.getInstance().convert(document, outputStream, options); BufferedReader bufferedReader = new BufferedReader(new FileReader("e:\\test\\1.html")); String string; while ((string = bufferedReader.readLine()) != null) { System.out.println(string); } bufferedReader.close(); } else if (file.getName().endsWith(".doc") || file.getName().endsWith(".DOC")) { InputStream inputStream = new FileInputStream(file); HWPFDocument document = new HWPFDocument(inputStream); WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(DocumentBuilderFactory .newInstance().newDocumentBuilder().newDocument()); wordToHtmlConverter.setPicturesManager(new PicturesManager() { @Override public String savePicture(byte[] content, PictureType pictureType, String suggestedName, float widthInches, float heightInches) { // TODO Auto-generated method stub return suggestedName; } }); wordToHtmlConverter.processDocument(document); List<Picture> pictures = document.getPicturesTable().getAllPictures(); if (pictures != null) { for (int i = 0; i < pictures.size(); i++) { Picture picture = (Picture) pictures.get(i); picture.writeImageContent(new FileOutputStream("e://test" + "/" + picture.suggestFullFileName())); } } Document htmlDocument = wordToHtmlConverter.getDocument(); ByteArrayOutputStream outputStream = new ByteArrayOutputStream(); DOMSource domSource = new DOMSource(htmlDocument); StreamResult streamResult = new StreamResult(outputStream); TransformerFactory transformerFactory = TransformerFactory.newInstance(); Transformer seralizer = transformerFactory.newTransformer(); seralizer.setOutputProperty(OutputKeys.ENCODING, "GB2312"); seralizer.setOutputProperty(OutputKeys.INDENT, "yes"); seralizer.setOutputProperty(OutputKeys.METHOD, "html"); seralizer.transform(domSource, streamResult); outputStream.close(); String content = new String(outputStream.toByteArray()); writeFile(content, "e:\\test\\1.html"); } } } catch (FileNotFoundException e) { // TODO Auto-generated catch block e.printStackTrace(); } catch (IOException e) { // TODO Auto-generated catch block e.printStackTrace(); } catch (ParserConfigurationException e) { // TODO Auto-generated catch block e.printStackTrace(); } catch (TransformerConfigurationException e) { // TODO Auto-generated catch block e.printStackTrace(); } catch (TransformerException e) { // TODO Auto-generated catch block e.printStackTrace(); } } private 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, "GB2312")); bw.write(content); } catch (FileNotFoundException fnfe) { fnfe.printStackTrace(); } catch (IOException ioe) { ioe.printStackTrace(); } finally { try { if (bw != null) bw.close(); if (fos != null) fos.close(); } catch (IOException ie) { } } } }