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.w3c.dom.Document;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.*;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import java.io.*;
import java.util.List;
public class WordToHtml {
public static void main(String[] args) throws IOException, ParserConfigurationException, TransformerException {
convert2Html("F:\\电脑桌面\\新建文件夹\\电商实操练习题1.doc","F:\\电脑桌面\\新建文件夹\\电商实操练习题1.html");
}
public static void writerFile(String context, String path) {
FileOutputStream fos = null;
BufferedWriter bw = null;
try {
File file = new File(path);
fos = new FileOutputStream(file);
bw = new BufferedWriter(new OutputStreamWriter(fos,"utf-8"));
bw.write(context);
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (UnsupportedEncodingException 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();
}
}
}
public static void convert2Html1(byte[] bytes, String outPutFile) throws Exception {
String picpath = outPutFile.replace(".html", "");//图片保存的绝对路径
final String picth = picpath.substring(picpath.lastIndexOf("/") + 1, picpath.length());//图片保存的文件夹名字
picpath = picpath + "/";//图片保存绝对的路径
File dir = new File(picpath);
if (!dir.exists()) {
dir.mkdirs();
}
System.out.println(picpath + "===" + picth);
//把fastdfs读取到的word文件字节数组转换为字节输入流对象
ByteArrayInputStream byteArrayInputStream = new ByteArrayInputStream(bytes);
HWPFDocument wordDocument = new HWPFDocument(byteArrayInputStream);
//WordToHtmlUtils.loadDoc(new FileInputStream(inputFile))
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) {
return picth + "/" + 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);
FileOutputStream fileout = new FileOutputStream(picpath + pic.suggestFullFileName());
pic.writeImageContent(fileout);
fileout.close();
}
}
Document htmlDocument = wordToHtmlConverter.getDocument();
ByteArrayOutputStream out = new ByteArrayOutputStream();
DOMSource domSource = new DOMSource(htmlDocument);
StreamResult streamResult = new StreamResult(out);
TransformerFactory tf = TransformerFactory.newInstance();
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();
writerFile(new String(out.toByteArray()), outPutFile);
}
public static void convert2Html(String fileName, String outPutFile) throws IOException, ParserConfigurationException, TransformerException {
String picpath = outPutFile.replace(".html", "");//图片保存的绝对路径
final String picth = picpath.substring(picpath.lastIndexOf("/") + 1, picpath.length());//图片保存的文件夹名字
picpath = picpath + "/";//图片保存绝对的路径
File dir = new File(picpath);
if (!dir.exists()) {
dir.mkdirs();
}
System.out.println(picpath + "===" + picth);
HWPFDocument wordDocument = new HWPFDocument(new FileInputStream(fileName));
//WordToHtmlUtils.loadDoc(new FileInputStream(inputFile))
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) {
return picth + "/" + 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);
FileOutputStream fileout = new FileOutputStream(picpath + pic.suggestFullFileName());
pic.writeImageContent(fileout);
fileout.close();
}
}
Document htmlDocument = wordToHtmlConverter.getDocument();
ByteArrayOutputStream out = new ByteArrayOutputStream();
DOMSource domSource = new DOMSource(htmlDocument);
StreamResult streamResult = new StreamResult(out);
TransformerFactory tf = TransformerFactory.newInstance();
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();
writerFile(new String(out.toByteArray()), outPutFile);
}
}