pdftextextractor.java

抽取pdf和word文本内容的源代码

package com.rsc.rs.util.xml;


import com.etymon.pj.Pdf;
import com.etymon.pj.exception.InvalidPdfObjectException;
import com.etymon.pj.exception.PjException;
import com.etymon.pj.object.PjArray;
import com.etymon.pj.object.PjObject;
import com.etymon.pj.object.PjPage;
import com.etymon.pj.object.PjStream;
import org.apache.log4j.Category;

import java.io.File;
import java.io.IOException;
import java.util.Vector;

/**
 * <p>
 * Attempts to extract text from a PDF file.
 * </p>
 * <p>
 * <a href="http://www.mail-archive.com/[e-mail]/msg00280.html">
 * Known limitations</a>
 * </p>
 *
 * @author <a href="mailto:[e-mail]">Kelvin Tan</a>
 * @version $Revision: 1.1 $
 */
public class PdfTextExtractor
{
    private static Category cat = Category.getInstance(PdfTextExtractor.class);

    public static void main(String[] args)
    {
        File f = new File("/usr/local/test.pdf");
        try
        {
            Pdf pdf = new Pdf(f.toString());
            int pagecount = pdf.getPageCount();
            cat.debug(f.toString() + "has " + pagecount + " pages.");
            for (int i = 1; i <= pagecount; i++)
            {
                System.out.println(getContent(pdf, i));
            }
        }
        catch (IOException ioe)
        {
            cat.error("IOException parsing PDF file:" + f.toString(), ioe);
        }
        catch (PjException pje)
        {
            cat.error("PjException parsing PDF file:" + f.toString(), pje);
        }
    }

    private static String getContent(Pdf pdf, int pageNo)
    {
        String content = null;
        PjStream stream = null;
        StringBuffer strbf = new StringBuffer();
        try
        {
            PjPage page = (PjPage) pdf.getObject(pdf.getPage(pageNo));
            PjObject pobj = (PjObject) pdf.resolve(page.getContents());
            if (pobj instanceof PjArray)
            {
                PjArray array = (PjArray) pobj;
                Vector vArray = array.getVector();
                int size = vArray.size();
                for (int j = 0; j < size; j++)
                {
                    stream = (PjStream) pdf.resolve((PjObject) vArray.get(j));
                    strbf.append(getStringFromPjStream(stream));
                }
                content = strbf.toString();
            }
            else
            {
                stream = (PjStream) pobj;
                content = getStringFromPjStream(stream);
            }
        }
        catch (InvalidPdfObjectException pdfe)
        {
            cat.error("Invalid PDF Object:" + pdfe, pdfe);
        }
        catch (Exception e)
        {
            cat.error("Exception in getContent() " + e, e);
        }
        return content;
    }

    private static String getStringFromPjStream(PjStream stream)
    {
        StringBuffer strbf = new StringBuffer();
        try
        {
            int start,end = 0;
            stream = stream.flateDecompress();
            String longString = stream.toString();
            int strlen = longString.length();
            int lastIndex = longString.lastIndexOf(')');
            while (lastIndex != -1 && end != lastIndex)
            {
                start = longString.indexOf('(', end);
                end = longString.indexOf(')', start);
                String text = longString.substring(start + 1, end);
                strbf.append(text);
            }
        }
        catch (InvalidPdfObjectException pdfe)
        {
            cat.error("InvalidObjectException:" + pdfe.getMessage(), pdfe);
        }
        return strbf.toString();
    }
}