Estrai testo e immagini da PDF usando iText5

Question

Ho bisogno di aiuto per estrarre testo e immagini da un file PDF con mappature o riferimenti alle immagini nel testo estratto usando la libreria Java iText5. Se iText5 è lo strumento sbagliato per questo, ti prego di consigliarmi raccomandando un'altra libreria Java che faccia la stessa funzione.

Questo è finora quello che ho fatto

import java.io.IOException; 
import com.itextpdf.text.Document; 
import com.itextpdf.text.DocumentException; 
import com.itextpdf.text.pdf.PdfReader; 
import com.itextpdf.text.pdf.parser.PdfReaderContentParser; 
import com.itextpdf.text.pdf.parser.PdfTextExtractor; 
import com.itextpdf.text.Paragraph; 

public class Iconverter { 

    /** 
    * @param args 
    */ 
    static int PAGE_NUMBER; 


    /** The new document to which we've added a border rectangle. */ 
    public static final String RESULT = "/home/sarah/Java for Dummies 4th Edition/Img%s.%s"; 
    public static void main(String[] args) { 
     String docText = ""; 
     String pdfName = "/home/sarah/Java for Dummies 4th Edition.pdf"; 
     Document document = new Document(); 
     document.open(); 
     try { 
      PdfReader reader = new PdfReader(pdfName); 
      PAGE_NUMBER = reader.getNumberOfPages(); 
      for(int i = 1; i <=PAGE_NUMBER; i++){ 
       docText = PdfTextExtractor.getTextFromPage(reader, i); 
      } 
      extractImages(pdfName);  
      document.add(new Paragraph("..")); 
     } catch (Exception e) { 
      e.printStackTrace(); 
     } 
     document.close(); 
    } 
    /** 
    * Parses a PDF and extracts all the images. 
    * @param src the source PDF 
    * @param dest the resulting PDF 
    */ 
    public static void extractImages(String filename) throws IOException, DocumentException { 
     PdfReader reader = new PdfReader(filename); 
     PdfReaderContentParser parser = new PdfReaderContentParser(reader); 
     MyImageRenderListener listener = new MyImageRenderListener(RESULT); 
     for (int i = 1; i <= PAGE_NUMBER; i++) { 
      parser.processContent(i, listener); 
     } 
    } 
} 

import java.awt.image.BufferedImage; 
import java.io.FileOutputStream; 
import java.io.IOException; 

import javax.imageio.ImageIO; 

import com.itextpdf.text.pdf.PdfName; 
import com.itextpdf.text.pdf.parser.ImageRenderInfo; 
import com.itextpdf.text.pdf.parser.PdfImageObject; 
import com.itextpdf.text.pdf.parser.RenderListener; 
import com.itextpdf.text.pdf.parser.TextRenderInfo; 

public class MyImageRenderListener implements RenderListener { 

    /** The new document to which we've added a border rectangle. */ 
    protected String path = ""; 

    /** 
    * Creates a RenderListener that will look for images. 
    */ 
    public MyImageRenderListener(String path) { 
     this.path = path; 
    } 

    /** 
    * @see com.itextpdf.text.pdf.parser.RenderListener#beginTextBlock() 
    */ 
    public void beginTextBlock() { 
    } 

    /** 
    * @see com.itextpdf.text.pdf.parser.RenderListener#endTextBlock() 
    */ 
    public void endTextBlock() { 
    } 

    /** 
    * @see com.itextpdf.text.pdf.parser.RenderListener#renderImage(
    *  com.itextpdf.text.pdf.parser.ImageRenderInfo) 
    */ 
    public void renderImage(ImageRenderInfo renderInfo) { 
     try { 
      String filename; 
      FileOutputStream os; 
      PdfImageObject image = renderInfo.getImage(); 
      PdfName filter = (PdfName)image.get(PdfName.FILTER); 
      if (PdfName.DCTDECODE.equals(filter)) { 
       filename = String.format(path, renderInfo.getRef().getNumber(), "JPG"); 
       os = new FileOutputStream(filename); 
       os.write(image.getStreamBytes()); 
       os.flush(); 
       os.close(); 
      } 
      else if (PdfName.JPXDECODE.equals(filter)) { 
       filename = String.format(path, renderInfo.getRef().getNumber(), "jp2"); 
       os = new FileOutputStream(filename); 
       os.write(image.getStreamBytes()); 
       os.flush(); 
       os.close(); 
      } 
      else if (PdfName.JBIG2DECODE.equals(filter)) { 
       // ignore: filter not supported. 
      } 
      else { 
       BufferedImage awtimage = renderInfo.getImage().getBufferedImage(); 
       if (awtimage != null) { 
        filename = String.format(path, renderInfo.getRef().getNumber(), "png"); 
        ImageIO.write(awtimage, "png", new FileOutputStream(filename)); 
       } 
      } 
     } catch (IOException e) { 
      e.printStackTrace(); 
     } 
    } 

    /** 
    * @see com.itextpdf.text.pdf.parser.RenderListener#renderText(
    *  com.itextpdf.text.pdf.parser.TextRenderInfo) 
    */ 
    public void renderText(TextRenderInfo renderInfo) { 
    } 
} 

Answer 1

In alternativa a iText, Apache PDFBox può aiutare.

Date un'occhiata a queste classi:

org.apache.pdfbox.ExtractImages

org.apache.pdfbox.ExtractText