Java PDF parser PDFBox

PDFBox

使用 command line 讀取文件
Usage: java org.pdfbox.ExtractText [OPTIONS] <PDF file> [Text File]
-password  <password>        Password to decrypt document
-encoding  <output encoding> (ISO-8859-1,UTF-16BE,UTF-16LE,...)
-console                     Send text to console instead of file
-html                        Output in HTML format instead of raw text
-sort                        Sort the text before writing
-startPage <number>          The first page to start extraction(1 based)
-endPage <number>            The last page to extract(inclusive)
<PDF file>                   The PDF document to use
[Text File]                  The file to write the text to

撰寫程式讀取 test.pdf 文件
//-- Main.java --
import org.pdfbox.pdmodel.PDDocument;
import org.pdfbox.util.PDFTextStripper;

public class Main {
public static void main(String[] args) throws Exception {
  PDDocument doc = PDDocument.load("test.pdf");
  PDFTextStripper stripper = new PDFTextStripper();
  System.out.println(stripper.getText(doc));
}
}

使用 command line 產生文件影像檔，但效果不好，中文字也產生不出來
Usage: java org.pdfbox.PDFToImage [OPTIONS] <PDF file>
-password  <password>          Password to decrypt document
-imageType <image type>        (BMP,bmp,jpg,JPG,wbmp,jpeg,png,PNG,JPEG,WBMP,GIF,gif)
-outputPrefix <output prefix>  Filename prefix for image files
-startPage <number>          The first page to start extraction(1 based)
-endPage <number>            The last page to extract(inclusive)
<PDF file>                   The PDF document to use

撰寫程式產生文件影像檔，參考 PDFToImage 的 source code，結果相同
//-- Main.java --
import java.awt.image.BufferedImage;
import java.io.File;
import java.util.Iterator;
import java.util.List;

import javax.imageio.IIOException;
import javax.imageio.IIOImage;
import javax.imageio.ImageIO;
import javax.imageio.ImageWriteParam;
import javax.imageio.ImageWriter;
import javax.imageio.stream.ImageOutputStream;

import org.pdfbox.pdmodel.PDDocument;
import org.pdfbox.pdmodel.PDPage;

public class Main {
public static void main(String[] args) throws Exception {
  PDDocument doc = PDDocument.load("test.pdf");
  List pages = doc.getDocumentCatalog().getAllPages();
  Iterator iter = pages.iterator();
  while (iter.hasNext()) {
    PDPage page = (PDPage) iter.next();
    BufferedImage image = page.convertToImage();
    File file = File.createTempFile("test_", ".jpg");
    System.out.println(file);
    ImageOutputStream output = ImageIO.createImageOutputStream(file);
    try {
      boolean foundWriter = false;
      Iterator writerIter = ImageIO.getImageWritersByFormatName("jpg");
      while (writerIter.hasNext() && !foundWriter) {

        try {
          ImageWriter imageWriter = (ImageWriter) writerIter.next();
          try {
            ImageWriteParam writerParams = imageWriter.getDefaultWriteParam();
            if (writerParams.canWriteCompressed()) {
              writerParams.setCompressionMode(ImageWriteParam.MODE_EXPLICIT);
              writerParams.setCompressionQuality(1.0f);
            }
            imageWriter.setOutput(output);
            imageWriter.write(null, new IIOImage(image, null, null), writerParams);
            foundWriter = true;
          } finally {
            imageWriter.dispose();
          }
        } catch (IIOException io) {
          io.printStackTrace();
        }
      }
    } finally {
      output.close();
    }
  } 
}
}