import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import org.w3c.tidy.Tidy;
public class HtmlToXml
{
public void tranceTo(String path,String encoding,String savePath){
Tidy tidy = new Tidy();
tidy.setXmlOut(true);
tidy.setQuoteNbsp(false);
tidy.setQuoteMarks(false);
tidy.setQuoteAmpersand(false);
tidy.setInputEncoding(encoding);//Encoding为你的输入文件的编码方式
tidy.setOutputEncoding("UTF-8");//设置输出文件的编码方式
try
{
FileInputStream in = new FileInputStream(new File(path));
FileOutputStream out = new FileOutputStream(new File(savePath+"temp.xml"));
tidy.parse(in, out);
}
catch (IOException e)
{
e.printStackTrace();
}
}
}