Java PdfReader類代碼示例

import com.itextpdf.text.pdf.PdfReader; //導入依賴的package包/類
private String getPdfContent(String pdfFile) {
	try {
		PdfReader reader = new PdfReader(pdfFile);
		StringBuffer sb = new StringBuffer();
		PdfReaderContentParser parser = new PdfReaderContentParser(reader);
		TextExtractionStrategy strategy;
		for (int i = 1; i <= reader.getNumberOfPages(); i++) {
			strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
			sb.append(strategy.getResultantText());
		}
		reader.close();
		return sb.toString();
	} catch (IOException e) {
		throw new IllegalArgumentException("Not able to read file " + pdfFile, e);
	}
}
 

import com.itextpdf.text.pdf.PdfReader; //導入依賴的package包/類
@Test
public void testWritePlainLetter() {

	try {
		PdfReader reader = new PdfReader("letters/" + voter.getNif() + ".pdf");
		String page = PdfTextExtractor.getTextFromPage(reader, 1);
		String[] lines = page.split("\n");
		String email = lines[1].split(":\t")[1];
		String password = lines[2].split(":\t")[1];
		assertEquals(voter.getEmail(), email);
		assertEquals(voter.getPassword(), password);

	} catch (IOException e) {
		System.err.println("Archivo no encontrado");
	}

}
 

import com.itextpdf.text.pdf.PdfReader; //導入依賴的package包/類
public static CropJob createCropJob(ClusterJob curClusterJob) throws IOException {
	File source = curClusterJob.getSource();
	if (source != null && source.exists()) {
		PdfReader reader = new PdfReader(source.getAbsolutePath());
		CropJob result = new CropJob(source, reader.getNumberOfPages(), reader.getInfo(),
				SimpleBookmark.getBookmark(reader));
		reader.close();
		result.setClusterCollection(curClusterJob.getClusterCollection());
		return result;
	}
	return null;
}
 

import com.itextpdf.text.pdf.PdfReader; //導入依賴的package包/類
/**
 * <a href="http://stackoverflow.com/questions/34394199/i-cant-rotate-my-page-from-existing-pdf">
 * I can't rotate my page from existing PDF
 * </a>
 * <p>
 * Switching between portrait and landscape like this obviously will cut off some parts of the page.
 * </p>
 */
@Test
public void testSwitchOrientation() throws DocumentException, IOException
{
    try (InputStream resourceStream = getClass().getResourceAsStream("/mkl/testarea/itext5/extract/n2013.00849449.pdf"))
    {
        PdfReader reader = new PdfReader(resourceStream);
        int n = reader.getNumberOfPages();
        PdfDictionary pageDict;
        for (int i = 1; i <= n; i++) {
            Rectangle rect = reader.getPageSize(i);
            Rectangle crop = reader.getCropBox(i);
            pageDict = reader.getPageN(i);
            pageDict.put(PdfName.MEDIABOX, new PdfArray(new float[] {rect.getBottom(), rect.getLeft(), rect.getTop(), rect.getRight()}));
            pageDict.put(PdfName.CROPBOX, new PdfArray(new float[] {crop.getBottom(), crop.getLeft(), crop.getTop(), crop.getRight()}));
        }
        PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(new File(RESULT_FOLDER, "n2013.00849449-switch.pdf")));
        stamper.close();
        reader.close();
    }
}
 

import com.itextpdf.text.pdf.PdfReader; //導入依賴的package包/類
/**
 * <a href="http://stackoverflow.com/questions/28991291/how-to-remove-whitespace-on-merge">
 * How To Remove Whitespace on Merge
 * </a>
 * <p>
 * Testing {@link PdfDenseMergeTool} using the OP's files.
 * </p>
 */
@Test
public void testMergeGrandizerFiles() throws DocumentException, IOException
{
    try (   InputStream docA = getClass().getResourceAsStream("Header.pdf");
            InputStream docB = getClass().getResourceAsStream("Body.pdf");
            InputStream docC = getClass().getResourceAsStream("Footer.pdf");    )
    {
        PdfDenseMergeTool tool = new PdfDenseMergeTool(PageSize.A4, 18, 18, 5);
        PdfReader readerA = new PdfReader(docA);
        PdfReader readerB = new PdfReader(docB);
        PdfReader readerC = new PdfReader(docC);
        try (FileOutputStream fos = new FileOutputStream(new File(RESULT_FOLDER, "GrandizerMerge.pdf")))
        {
            List<PdfReader> inputs = Arrays.asList(readerA, readerB, readerC);
            tool.merge(fos, inputs);
        }
        finally
        {
            readerA.close();
            readerB.close();
            readerC.close();
        }
    }

}
 

import com.itextpdf.text.pdf.PdfReader; //導入依賴的package包/類
/**
 * Update NDA file with visitor name and visitor signature.
 * 
 * @param destFile 
 * @param signatureImage signature file
 * @param visitorName
 * @return File
 */
public static File build(Path destFile, File signatureImage, String visitorName) {
	try {
		PdfReader pdfReader = new PdfReader(ndaUrl);
		PdfStamper pdfStamper = new PdfStamper(pdfReader,
				new FileOutputStream(destFile.toString()));
		Image image = createNDAImage(signatureImage, 0, 0);
		PdfContentByte over = pdfStamper.getOverContent(5);
		over.addImage(image);
		PdfContentByte pdfContentByte = pdfStamper.getOverContent(5);
		pdfContentByte.beginText();
		pdfContentByte.setFontAndSize(BaseFont.createFont
				(BaseFont.HELVETICA, 
						BaseFont.CP1257, 
						BaseFont.EMBEDDED
						)
				, 10); 
		pdfContentByte.setTextMatrix(112, 428); 
		pdfContentByte.showText(visitorName);
		pdfContentByte.setTextMatrix(89, 406);
		pdfContentByte.showText(new SimpleDateFormat("E, dd MMM yyyy").format(new Date()));
		pdfContentByte.endText();
		pdfStamper.close();
		return destFile.toFile();
	} catch (IOException | DocumentException | NumberFormatException e) {
		logger.error("Exception while generating NDA file. ",e);
		return null;
	}
}
 

import com.itextpdf.text.pdf.PdfReader; //導入依賴的package包/類
/**
 * <a href="http://stackoverflow.com/questions/35374110/how-do-i-use-itext-to-have-a-landscaped-pdf-on-half-of-a-a4-back-to-portrait-and">
 * How do i use iText to have a landscaped PDF on half of a A4 back to portrait and full size on A4
 * </a>
 * <p>
 * This sample shows how to rotate and enlarge the upper half of an A4 page to fit into a new A4 page.
 * </p>
 */
@Test
public void testRotateAndZoomUpperHalfPage() throws IOException, DocumentException
{
    try (   InputStream resource = getClass().getResourceAsStream("/mkl/testarea/itext5/extract/test.pdf");
            OutputStream result = new FileOutputStream(new File(RESULT_FOLDER, "test-upperHalf.pdf"))   )
    {
        PdfReader reader = new PdfReader(resource);
        Document document = new Document(PageSize.A4);
        PdfWriter writer = PdfWriter.getInstance(document, result);
        document.open();

        double sqrt2 = Math.sqrt(2);
        Rectangle pageSize = reader.getPageSize(1);
        PdfImportedPage importedPage = writer.getImportedPage(reader, 1);
        writer.getDirectContent().addTemplate(importedPage, 0, sqrt2, -sqrt2, 0, pageSize.getTop() * sqrt2, -pageSize.getLeft() * sqrt2);
        
        document.close();
    }
}
 

import com.itextpdf.text.pdf.PdfReader; //導入依賴的package包/類
/**
 * <a href="https://stackoverflow.com/questions/45027712/invalid-signature-when-signing-an-existing-sigrature-field-with-cosign-sapi">
 * Invalid signature when signing an existing sigrature field with CoSign SAPI
 * </a>
 * <br/>
 * <a href="https://www.dropbox.com/s/j6eme53lleaok13/test_signed.pdf?dl=0">
 * test_signed-1.pdf
 * </a>
 * <p>
 * Validation shows verification success while both Adobe and SD DSS fail.
 * Embedded certificates have issues (emailAddress RDN is typed PrintableString
 * which is wrong - specified is IA5String - and does not even make sense as
 * there is no '@' in PrintableString), but does this explain it?
 * </p>
 */
@Test
public void testVerifyTestSigned1() throws IOException, GeneralSecurityException
{
    System.out.println("\n\ntest_signed-1.pdf\n===================");
    
    try (   InputStream resource = getClass().getResourceAsStream("test_signed-1.pdf") )
    {
        PdfReader reader = new PdfReader(resource);
        AcroFields acroFields = reader.getAcroFields();

        List<String> names = acroFields.getSignatureNames();
        for (String name : names) {
           System.out.println("Signature name: " + name);
           System.out.println("Signature covers whole document: " + acroFields.signatureCoversWholeDocument(name));
           System.out.println("Document revision: " + acroFields.getRevision(name) + " of " + acroFields.getTotalRevisions());
           PdfPKCS7 pk = acroFields.verifySignature(name);
           System.out.println("Subject: " + CertificateInfo.getSubjectFields(pk.getSigningCertificate()));
           System.out.println("Document verifies: " + pk.verify());
        }
    }

    System.out.println();
}
 

import com.itextpdf.text.pdf.PdfReader; //導入依賴的package包/類
@Test
public void testRemoveTransparentGraphicsTransparency() throws IOException, DocumentException
{
    try (   InputStream resource = getClass().getResourceAsStream("transparency.pdf");
            OutputStream result = new FileOutputStream(new File(RESULT_FOLDER, "transparency-noTransparency.pdf")))
    {
        PdfReader pdfReader = new PdfReader(resource);
        PdfStamper pdfStamper = new PdfStamper(pdfReader, result);
        PdfContentStreamEditor editor = new TransparentGraphicsRemover();

        for (int i = 1; i <= pdfReader.getNumberOfPages(); i++)
        {
            editor.editPage(pdfStamper, i);
        }
        
        pdfStamper.close();
    }
}
 

import com.itextpdf.text.pdf.PdfReader; //導入依賴的package包/類
public ImageInstance getImageByFile( PdfContentByte cb , File file ) throws IOException, BadElementException{
	Image image = null;
	ImageInstance instance = null;
	if( file.getName().toLowerCase().endsWith( ".pdf")){	
		PdfReader reader = new PdfReader( file.getAbsolutePath() );
		PdfImportedPage p = cb.getPdfWriter().getImportedPage(reader, 1);
		image = Image.getInstance(p);
		instance = new ImageInstance(image, reader);
	}else{
		image = Image.getInstance( file.getAbsolutePath() );
		instance = new ImageInstance(image, null);
	}
	
	instances.add(instance);
	

	return instance;
}
 

import com.itextpdf.text.pdf.PdfReader; //導入依賴的package包/類
/**
 * The <code>closePassedStream</code> method closes the stream passed.
 * 
 * @param reader {@link PdfReader}
 * @param document {@link Document}
 * @param contentByte {@link PdfContentByte}
 * @param writer {@link PdfWriter}
 * @param fileInputStream {@link FileInputStream}
 * @param fileOutputStream {@link FileOutputStream}
 * @throws IOException {@link} if unable to close input or output stream
 */
private static void closePassedStream(final PdfReader reader, final Document document,
		final PdfContentByte contentByte, final PdfWriter writer,
		final FileInputStream fileInputStream, final FileOutputStream fileOutputStream) throws IOException {
	if (null != reader) {
		reader.close();
	} 
	if (null != document) {
		document.close();
	}
	if (null != contentByte) {
		contentByte.closePath();
	}
	if (null != writer) {
		writer.close();
	}
	if (null != fileInputStream) {
		fileInputStream.close();
	}
	
	if (null != fileOutputStream) {
		fileOutputStream.flush();
		fileOutputStream.close();
	}
}
 

import com.itextpdf.text.pdf.PdfReader; //導入依賴的package包/類
void split(PdfReader reader, int page) throws IOException
{
    PdfImportedPage importedPage = writer.getImportedPage(reader, page);

    Rectangle pageSizeToImport = reader.getPageSize(page);
    Iterable<Rectangle> rectangles = determineSplitRectangles(reader, page);

    for (Rectangle rectangle : rectangles) {
        newPage(rectangle);
        PdfContentByte directContent = writer.getDirectContent();
        directContent.saveState();
        directContent.rectangle(rectangle.getLeft(), rectangle.getBottom(), rectangle.getWidth(), rectangle.getHeight());
        directContent.clip();
        directContent.newPath();

        writer.getDirectContent().addTemplate(importedPage, -pageSizeToImport.getLeft(), -pageSizeToImport.getBottom());

        directContent.restoreState();
    }
}
 

import com.itextpdf.text.pdf.PdfReader; //導入依賴的package包/類
public void merge(OutputStream outputStream, Iterable<PdfReader> inputs) throws DocumentException, IOException
{
    try
    {
        openDocument(outputStream);
        for (PdfReader reader: inputs)
        {
            merge(reader);
        }
    }
    finally
    {
        closeDocument();
    }
    
}
 

import com.itextpdf.text.pdf.PdfReader; //導入依賴的package包/類
void extract(String resource, int startPage, int endPage, boolean isV2) throws IOException, DocumentException, NoSuchFieldException, SecurityException
{
    String name = new File(resource).getName();
    String target = String.format(isV2 ? "%s-lines-v2-%%s.txt" : "%s-lines-%%s.txt", name);
    InputStream resourceStream = getClass().getResourceAsStream(resource);
    try
    {
        PdfReader reader = new PdfReader(resourceStream);
        System.out.printf("\nText by line in %s\n", name);

        for (int page = startPage; page < endPage; page++)
        {
            System.out.printf("\n   Page %s\n", page);

            String pageText = isV2 ? extractV2(reader, page) : extract(reader, page);
            Files.write(new File(RESULT_FOLDER, String.format(target, page)).toPath(), pageText.getBytes("UTF8"));
            System.out.println(pageText);
        }
    }
    finally
    {
        if (resourceStream != null)
            resourceStream.close();
    }
}
 

import com.itextpdf.text.pdf.PdfReader; //導入依賴的package包/類
<E extends TextExtractionStrategy> String extractAndStore(PdfReader reader, String format, Class<E> strategyClass, RenderFilter... filters) throws Exception
{
    StringBuilder builder = new StringBuilder();

    for (int page = 1; page <= reader.getNumberOfPages(); page++)
    {
        TextExtractionStrategy strategy = strategyClass.getConstructor().newInstance();
        if (filters != null && filters.length > 0)
        {
            strategy = new FilteredTextRenderListener(strategy, filters);
        }
        String pageText = extract(reader, page, strategy);
        Files.write(Paths.get(String.format(format, page)), pageText.getBytes("UTF8"));

        if (page > 1)
            builder.append("\n\n");
        builder.append(pageText);
    }

    return builder.toString();
}