Example usage for org.apache.pdfbox.pdmodel PDResources getXObject

List of usage examples for org.apache.pdfbox.pdmodel PDResources getXObject

  1. HOME
  2. Java
  3. org.apache.pdfbox
  4. org.apache.pdfbox.pdmodel.*
  5. PDResources
  6. getXObject

Introduction

In this page you can find the example usage for org.apache.pdfbox.pdmodel PDResources getXObject.

Prototype

public PDXObject getXObject(COSName name) throws IOException

Source Link

Document

Returns the XObject resource with the given name, or null if none exists.

Usage

From source file:com.testautomationguru.utility.PDFUtil.java

License:Apache License

/**
* This method extracts all the embedded images of the pdf document
*///  w  ww.  ja  v a2 s  .c o  m
private List<String> extractimages(String file, int startPage, int endPage) {

    logger.info("file : " + file);
    logger.info("startPage : " + startPage);
    logger.info("endPage : " + endPage);

    ArrayList<String> imgNames = new ArrayList<String>();
    boolean bImageFound = false;
    try {

        this.createImageDestinationDirectory(file);
        String fileName = this.getFileName(file).replace(".pdf", "_resource");

        PDDocument document = PDDocument.load(new File(file));
        PDPageTree list = document.getPages();

        this.updateStartAndEndPages(file, startPage, endPage);

        int totalImages = 1;
        for (int iPage = this.startPage - 1; iPage < this.endPage; iPage++) {
            logger.info("Page No : " + (iPage + 1));
            PDResources pdResources = list.get(iPage).getResources();
            for (COSName c : pdResources.getXObjectNames()) {
                PDXObject o = pdResources.getXObject(c);
                if (o instanceof org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject) {
                    bImageFound = true;
                    String fname = this.imageDestinationPath + "/" + fileName + "_" + totalImages + ".png";
                    ImageIO.write(((org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject) o).getImage(),
                            "png", new File(fname));
                    imgNames.add(fname);
                    totalImages++;
                }
            }
        }
        document.close();
        if (bImageFound)
            logger.info("Images are saved @ " + this.imageDestinationPath);
        else
            logger.info("No images were found in the PDF");
    } catch (Exception e) {
        e.printStackTrace();
    }
    return imgNames;
}

From source file:org.apache.tika.parser.pdf.EnhancedPDF2XHTML.java

License:Apache License

private void extractImages(PDResources resources) throws SAXException, IOException {
    if (resources == null || config.getExtractInlineImages() == false) {
        return;/*from   w w  w.ja  v a 2 s  .  c o m*/
    }

    Iterable<COSName> cosIterable = resources.getXObjectNames();
    if (cosIterable == null) {
        return;
    }

    for (COSName name : cosIterable) {
        PDXObject object = resources.getXObject(name);
        if (object instanceof PDFormXObject) {
            extractImages(((PDFormXObject) object).getResources());
        } else if (object instanceof PDImageXObject) {
            PDImageXObject image = (PDImageXObject) object;

            Metadata metadata = new Metadata();
            String extension = "";

            if ("jpg".equalsIgnoreCase(image.getSuffix())) {
                metadata.set(Metadata.CONTENT_TYPE, "image/jpeg");
                extension = ".jpg";
            } else if ("tiff".equalsIgnoreCase(image.getSuffix())) {
                metadata.set(Metadata.CONTENT_TYPE, "image/tiff");
                extension = ".tif";
            } else if ("jpx".equalsIgnoreCase(image.getSuffix())) {
                metadata.set(Metadata.CONTENT_TYPE, "image/jpx");
                extension = ".jpx";
            } else if ("png".equalsIgnoreCase(image.getSuffix())) {
                metadata.set(Metadata.CONTENT_TYPE, "image/png");
                extension = ".png";
            }

            Integer imageNumber = processedInlineImages.get(name.getName());
            if (imageNumber == null) {
                imageNumber = inlineImageCounter++;
            }
            String fileName = "image" + imageNumber + extension;
            metadata.set(Metadata.RESOURCE_NAME_KEY, fileName);

            // Output the img tag
            AttributesImpl attr = new AttributesImpl();
            attr.addAttribute("", "src", "src", "CDATA", "embedded:" + fileName);
            attr.addAttribute("", "alt", "alt", "CDATA", fileName);
            handler.startElement("img", attr);
            handler.endElement("img");

            //Do we only want to process unique COSObject ids?
            //If so, have we already processed this one?
            if (config.getExtractUniqueInlineImagesOnly() == true) {
                String cosObjectId = name.getName();
                if (processedInlineImages.containsKey(cosObjectId)) {
                    continue;
                }
                processedInlineImages.put(cosObjectId, imageNumber);
            }

            metadata.set(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE,
                    TikaCoreProperties.EmbeddedResourceType.INLINE.toString());

            EmbeddedDocumentExtractor extractor = getEmbeddedDocumentExtractor();
            if (extractor.shouldParseEmbedded(metadata)) {
                try {
                    extractor.parseEmbedded(image.getCOSStream().getFilteredStream(),
                            new EmbeddedContentHandler(handler), metadata, false);
                } catch (IOException e) {
                    // could not extract this image, so just skip it...
                }
            }
        }
    }
}

From source file:org.apache.tika.parser.pdf.PDF2XHTMLPureJava.java

License:Apache License

private void extractImages(PDResources resources, Set<COSBase> seenThisPage) throws SAXException, IOException {
    if (resources == null || config.getExtractInlineImages() == false) {
        return;/*from  w w  w  .  j  a  v a 2 s . c  om*/
    }

    for (COSName name : resources.getXObjectNames()) {

        PDXObject object = null;
        try {
            object = resources.getXObject(name);
        } catch (MissingImageReaderException e) {
            EmbeddedDocumentUtil.recordException(e, metadata);
            continue;
        } catch (IOException e) {
            EmbeddedDocumentUtil.recordEmbeddedStreamException(e, metadata);
            continue;
        }

        if (object == null) {
            continue;
        }
        COSStream cosStream = object.getCOSObject();
        if (seenThisPage.contains(cosStream)) {
            //avoid infinite recursion TIKA-1742
            continue;
        }
        seenThisPage.add(cosStream);

        if (object instanceof PDFormXObject) {
            extractImages(((PDFormXObject) object).getResources(), seenThisPage);
        } else if (object instanceof PDImageXObject) {

            PDImageXObject image = (PDImageXObject) object;

            Metadata embeddedMetadata = new Metadata();
            String extension = image.getSuffix();

            //TODO remove this next block when upgrading to PDFBox 2.0.5.
            //See: https://issues.apache.org/jira/browse/PDFBOX-3634
            if (extension == null) {
                extension = getJBIG2Suffix(image);
            }

            if (extension == null || extension.equals("png")) {
                embeddedMetadata.set(Metadata.CONTENT_TYPE, "image/png");
                extension = "png";
            } else if (extension.equals("jpg")) {
                embeddedMetadata.set(Metadata.CONTENT_TYPE, "image/jpeg");
            } else if (extension.equals("tiff")) {
                embeddedMetadata.set(Metadata.CONTENT_TYPE, "image/tiff");
                extension = "tif";
            } else if (extension.equals("jpx")) {
                embeddedMetadata.set(Metadata.CONTENT_TYPE, "image/jp2");
            } else if (extension.equals("jb2")) {
                embeddedMetadata.set(Metadata.CONTENT_TYPE, "image/x-jbig2");
            } else {
                //TODO: determine if we need to add more image types
                //                    throw new RuntimeException("EXTEN:" + extension);
            }
            Integer imageNumber = processedInlineImages.get(cosStream);
            if (imageNumber == null) {
                imageNumber = inlineImageCounter++;
            }
            String fileName = "image" + imageNumber + "." + extension;
            embeddedMetadata.set(Metadata.RESOURCE_NAME_KEY, fileName);

            // Output the img tag
            AttributesImpl attr = new AttributesImpl();
            attr.addAttribute("", "src", "src", "CDATA", "embedded:" + fileName);
            attr.addAttribute("", "alt", "alt", "CDATA", fileName);
            xhtml.startElement("img", attr);
            xhtml.endElement("img");

            //Do we only want to process unique COSObject ids?
            //If so, have we already processed this one?
            if (config.getExtractUniqueInlineImagesOnly() == true) {
                if (processedInlineImages.containsKey(cosStream)) {
                    continue;
                }
                processedInlineImages.put(cosStream, imageNumber);
            }

            embeddedMetadata.set(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE,
                    TikaCoreProperties.EmbeddedResourceType.INLINE.toString());

            if (embeddedDocumentExtractor.shouldParseEmbedded(embeddedMetadata)) {
                ByteArrayOutputStream buffer = new ByteArrayOutputStream();
                try {
                    //TODO: handle image.getMetadata()?
                    try {
                        writeToBuffer(image, extension, buffer);
                    } catch (IOException e) {
                        EmbeddedDocumentUtil.recordEmbeddedStreamException(e, metadata);
                        continue;
                    }
                    try (InputStream embeddedIs = TikaInputStream.get(buffer.toByteArray())) {
                        embeddedDocumentExtractor.parseEmbedded(embeddedIs, new EmbeddedContentHandler(xhtml),
                                embeddedMetadata, false);
                    }
                } catch (IOException e) {
                    handleCatchableIOE(e);
                }
            }
        }
    }
}

From source file:org.example.extractimagesfrompdfpages.ExtractImagesFromPDFPagesMain.java

public static void main(String[] args) {
    try {// w ww . ja  v a 2 s. c  om
        File thePDFFile = new File(args[0]);
        PDDocument document = PDDocument.load(thePDFFile);
        PDPageTree list = document.getPages();
        int i = 1;
        for (PDPage page : list) {
            Boolean alreadyCreatedFolderForThisPage = false;
            File thePDFFileDirectory = thePDFFile.getParentFile();
            File thePDFPageFolder = new File(thePDFFileDirectory.getAbsolutePath() + "/temp_images" + "/" + i);
            PDResources pdResources = page.getResources();
            int j = 1;
            for (COSName c : pdResources.getXObjectNames()) {
                PDXObject o = pdResources.getXObject(c);
                if (o instanceof org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject) {
                    if (alreadyCreatedFolderForThisPage == false) {
                        thePDFPageFolder.mkdirs();
                        alreadyCreatedFolderForThisPage = true;
                    }

                    File file = new File(thePDFPageFolder.getAbsolutePath() + "/" + j + ".png");
                    ImageIO.write(((org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject) o).getImage(),
                            "png", file);
                    System.out.println(thePDFPageFolder.getAbsolutePath() + "/" + j + ".png");

                    j++;
                }

            }
            i++;
        }
    } catch (IOException ex) {
        Logger.getLogger(ExtractImagesFromPDFPagesMain.class.getName()).log(Level.SEVERE, null, ex);
        throw new RuntimeException(ex);
    }

}

From source file:org.fit.pdfdom.PDFBoxTree.java

License:Open Source License

private void processFontResources(PDResources resources, FontTable table) throws IOException {
    String fontNotSupportedMessage = "Font: {} skipped because type '{}' is not supported.";

    for (COSName key : resources.getFontNames()) {
        PDFont font = resources.getFont(key);
        if (font instanceof PDTrueTypeFont) {
            table.addEntry(font.getName(), font.getFontDescriptor());
            log.debug("Font: " + font.getName() + " TTF");
        } else if (font instanceof PDType0Font) {
            PDCIDFont descendantFont = ((PDType0Font) font).getDescendantFont();
            if (descendantFont instanceof PDCIDFontType2)
                table.addEntry(font.getName(), descendantFont.getFontDescriptor());
            else//w w  w . j  a  v  a2s .c  o m
                log.warn(fontNotSupportedMessage, font.getName(), font.getClass().getSimpleName());
        } else if (font instanceof PDType1CFont)
            table.addEntry(font.getName(), font.getFontDescriptor());
        else
            log.warn(fontNotSupportedMessage, font.getName(), font.getClass().getSimpleName());
    }

    for (COSName name : resources.getXObjectNames()) {
        PDXObject xobject = resources.getXObject(name);
        if (xobject instanceof PDFormXObject) {
            PDFormXObject xObjectForm = (PDFormXObject) xobject;
            PDResources formResources = xObjectForm.getResources();
            if (formResources != null)
                processFontResources(formResources, table);
        }
    }

}

From source file:org.mabb.fontverter.pdf.PdfFontExtractor.java

License:Open Source License

private void extractFontResources(PDResources resources) throws IOException {
    for (COSName key : resources.getFontNames()) {
        PDFont font = resources.getFont(key);
        extractStrategy.extract(font);/*ww w. ja v  a  2 s .c om*/
    }

    for (COSName name : resources.getXObjectNames()) {
        PDXObject xobject = resources.getXObject(name);
        if (xobject instanceof PDFormXObject) {
            PDFormXObject xObjectForm = (PDFormXObject) xobject;
            PDResources formResources = xObjectForm.getResources();

            if (formResources != null)
                extractFontResources(formResources);
        }
    }
}

From source file:org.xwiki.test.misc.PDFTest.java

License:Open Source License

private Map<String, PDImageXObject> getImages(URL url) throws Exception {
    Map<String, PDImageXObject> results = new HashMap<>();

    PDDocument document = PDDocument.load(IOUtils.toByteArray(url));
    try {/*  w  ww. j  av a2  s  . c o m*/
        for (PDPage page : document.getDocumentCatalog().getPages()) {
            PDResources pdResources = page.getResources();
            for (COSName name : pdResources.getXObjectNames()) {
                if (pdResources.isImageXObject(name)) {
                    PDImageXObject pdxObjectImage = (PDImageXObject) pdResources.getXObject(name);
                    results.put(name.getName(), pdxObjectImage);
                }
            }
        }
    } finally {
        if (document != null) {
            document.close();
        }
    }

    return results;
}