package com.kingdom.test;
import java.io.BufferedInputStream;
import java.io.BufferedOutputStream;
import java.io.ByteArrayOutputStream;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.List;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import jcifs.smb.SmbFile;
import jcifs.smb.SmbFileInputStream;
import jcifs.smb.SmbFileOutputStream;
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.xhtml.XHTMLConverter;
import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
public class WordToHtml {
public static void main(String[] args) throws Throwable {
String filename1 = "11.docx";
String filename = "22.doc";
final String path = "//192.168.12.142/kdum/2016/11/29/";
docToHTML(path,filename);
docxToHTML(path,filename1);
}
public static void docToHTML(String path, String filename){
InputStream input = null;
OutputStream output = null;
OutputStream imgoutput = null;
try{
final String resultfile =filename.substring(0, filename.lastIndexOf("."))+".html";
SmbFile sf = new SmbFile("smb:" + path+filename);
String imagepath = path+"word/media/";
SmbFile img = new SmbFile("smb:"+imagepath);
if(!img.exists()){
img.mkdirs();
}
input = new BufferedInputStream(new SmbFileInputStream(sf));
HWPFDocument wordDocument = new HWPFDocument(input);
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 "word/media/"+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 {
imgoutput = new BufferedOutputStream(new SmbFileOutputStream(new SmbFile("smb:"+imagepath+pic.suggestFullFileName()))) ;
//自定义图片存放路径
pic.writeImageContent(imgoutput);
} catch (FileNotFoundException e) {
e.printStackTrace();
}finally{
if(imgoutput!=null){
imgoutput.close();
}
}
}
}
org.w3c.dom.Document htmlDocument = wordToHtmlConverter.getDocument();
ByteArrayOutputStream outStream = new ByteArrayOutputStream();
DOMSource domSource = new DOMSource(htmlDocument);
StreamResult streamResult = new StreamResult(outStream);
TransformerFactory tf = TransformerFactory.newInstance();
Transformer serializer = tf.newTransformer();
serializer.setOutputProperty(OutputKeys.ENCODING, "GBK");
serializer.setOutputProperty(OutputKeys.INDENT, "yes");
serializer.setOutputProperty(OutputKeys.METHOD, "html");
serializer.transform(domSource, streamResult);
outStream.close();
String content = new String(outStream.toByteArray());
SmbFile remoteFile = new SmbFile("smb:" + path+resultfile);
if(remoteFile.exists()){
remoteFile.delete();
}
remoteFile.createNewFile();
//写内容
output = new BufferedOutputStream(new SmbFileOutputStream(remoteFile));
output.write(content.getBytes());
}catch(Exception e ){
e.printStackTrace();
}finally{
try {
if(output!=null){
output.close();
}
} catch (IOException e) {
e.printStackTrace();
}
}
}
public static void docxToHTML(String path,String filename){
InputStream input = null;
SmbFileInputStream smbinput = null;
OutputStream output = null;
SmbFileOutputStream smboutput = null;
try{
if(path==null||filename==null){
return ;
}
final String resultfile =filename.substring(0, filename.lastIndexOf("."))+".html";
SmbFile image = new SmbFile("smb:" + path);
SmbFile infile = new SmbFile("smb:" + path+filename);
SmbFile rf = new SmbFile("smb:" + path+resultfile);
smbinput = new SmbFileInputStream(infile);
smboutput = new SmbFileOutputStream(rf);
input = new BufferedInputStream(smbinput);
output = new BufferedOutputStream(smboutput);
XWPFDocument document = new XWPFDocument(input);
XHTMLOptions options = XHTMLOptions.create();
// .URIResolver(new BasicURIResolver("/"));
// XHTMLOptions options = XHTMLOptions.create().URIResolver(new SmbFileURIResolver(sf));
options.setExtractor(new SbmFileImageExtractor(image));
XHTMLConverter.getInstance().convert(document,output, options);
}catch(Exception e ){
e.printStackTrace();
}finally{
if(smboutput!=null){
try {
smboutput.close();
} catch (IOException e) {
e.printStackTrace();
}
}
if(smbinput!=null){
try {
smbinput.close();
} catch (IOException e) {
e.printStackTrace();
}
}
if(input!=null){
try {
input.close();
} catch (IOException e) {
e.printStackTrace();
}
}
if(output!=null){
try {
output.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
}
package com.kingdom.test;
import java.io.BufferedOutputStream;
import java.io.ByteArrayInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import jcifs.smb.SmbFile;
import jcifs.smb.SmbFileOutputStream;
import org.apache.commons.io.IOUtils;
import org.apache.poi.xwpf.converter.core.IImageExtractor;
public class SbmFileImageExtractor implements IImageExtractor{
private final SmbFile baseDir;
public SbmFileImageExtractor(SmbFile baseDir)
{
this.baseDir = baseDir;
}
@Override
public void extract(String imagePath, byte[] imageData) throws IOException {
SmbFile imageFile = new SmbFile(baseDir,imagePath);
SmbFile dir = new SmbFile(imageFile.getParent());
if(!dir.exists()){
dir.mkdirs();
}
System.out.println(imagePath);
InputStream in = null;
OutputStream out = null;
try
{
in = new ByteArrayInputStream(imageData);
out = new BufferedOutputStream(new SmbFileOutputStream(imageFile));
IOUtils.copy(in, out);
}
finally
{
if (in != null)
{
IOUtils.closeQuietly(in);
}
if (out != null)
{
IOUtils.closeQuietly(out);
}
}
}
}
所需jar包