* @author chris
* @version 1.0,who use this example pls remain the declare
*/
public class FileExtracter{
public static void main(String[] args) {
ActiveXComponent component = new ActiveXComponent("Word.Application");
String inFile = "c://test.doc";
String tpFile = "c://temp.htm";
String otFile = "c://temp.xml";
boolean flag = false;
try {
component.setProperty("Visible", new Variant(false));
Object wordacc = component.getProperty("document.").toDispatch();
Object wordfile = Dispatch.invoke(wordacc,"Open", Dispatch.Method,
new Object[]{inFile,new Variant(false), new Variant(true)},
new int[1] ).toDispatch();
Dispatch.invoke(wordfile,"SaveAs", Dispatch.Method, new Object[]{tpFile,new Variant(8)}, new int[1]);
Variant f = new Variant(false);
Dispatch.call(wordfile, "Close", f);
flag = true;
} catch (Exception e) {
e.printStackTrace();
} finally {
component.invoke("Quit", new Variant[] {});
}
}
}
import java.io.*;
import org.textmining.text.extraction.WordExtractor;
/**
* <p>Title: word extraction</p>
* <p>Description: email:chris@matrix.org.cn</p>
* <p>Copyright: Matrix Copyright (c) 2003</p>
* <p>Company: Matrix.org.cn</p>
* @author chris
* @version 1.0,who use this example pls remain the declare
*/
public class PdfExtractor {
public PdfExtractor() {
}
public static void main(String args[]) throws Exception
{
FileInputStream in = new FileInputStream ("c://a.doc");
WordExtractor extractor = new WordExtractor();
String str = extractor.extractText(in);
System.out.println("the result length is"+str.length());
System.out.println("the result is"+str);
}
}