ActiveXComponent app = new ActiveXComponent("Word.Application");
String inFile = "c:\\test.doc";
String tpFile = "c:\\temp.htm";
String otFile = "c:\\temp.xml";
boolean flag = false;
try {
app.setProperty("Visible", new Variant(false));
Object docs = app.getProperty("Documents").toDispatch();
Object doc = Dispatch.invoke(docs,"Open", Dispatch.Method, new Object[]{inFile,new Variant(false), new Variant(true)}, new int[1]).toDispatch();
Dispatch.invoke(doc,"SaveAs", Dispatch.Method, new Object[]{tpFile,new Variant(8)}, new int[1]);
Variant f = new Variant(false);
Dispatch.call(doc, "Close", f);
flag = true;
} catch (Exception e) {
e.printStackTrace();
} finally {
app.invoke("Quit", new Variant[] {});
}
}
}
2。用apache的poi来抽取word,excel。
poi是apache的一个项目,不过就算用poi你可能都觉得很烦,不过不要紧,这里提供了更加简单的一个接口给你:
下载经过封装后的poi包:http://www.matrix.org.cn/down_view.asp?id=14
下载之后,放到你的classpath就可以了,下面是如何使用它的一个例子:
import java.io.*;
import org.textmining.text.extraction.WordExtractor;
/**
* <p>Title: pdf 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);
}
}
3。pdfbox-用来抽取pdf文件
但是pdfbox对中文支持还不好,先下载pdfbox:http://www.matrix.org.cn/down_view.asp?id=12
下面是一个如何使用pdfbox抽取pdf文件的例子:
import org.pdfbox.pdmodel.PDDocument;
import org.pdfbox.pdfparser.PDFParser;
import java.io.*;
import org.pdfbox.util.PDFTextStripper;
import java.util.Date;
/**
* <p>Title: pdf 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 PdfExtracter{
public PdfExtracter(){
}
public String GetTextFromPdf(String filename) throws Exception
{
String temp=null;
PDDocument pdfdocument=null;
FileInputStream is=new FileInputStream(filename);
PDFParser parser = new PDFParser( is );
parser.parse();
pdfdocument = parser.getPDDocument();
ByteArrayOutputStream out = new ByteArrayOutputStream();
OutputStreamWriter writer = new OutputStreamWriter( out );
PDFTextStripper stripper = new PDFTextStripper();
stripper.writeText(pdfdocument.getDocument(), writer );
writer.close();
byte[] contents = out.toByteArray();