Extract Images from PDF with Apache Tika

Question

Apache Tika 1.6 has the ability to extract inline images from PDF documents. However, I\'ve been struggling to get it to work.

My use case is that I want some code t

Answer 1

Try the code bellow, ContentHandler turned has your xml content.

public ContentHandler convertPdf(byte[] content, String path, String filename)throws IOException, SAXException, TikaException{           

    Metadata metadata = new Metadata();
    ParseContext context = new ParseContext();
    ContentHandler handler =   new ToXMLContentHandler();
    PDFParser parser = new PDFParser(); 

    PDFParserConfig config = new PDFParserConfig();
    config.setExtractInlineImages(true);
    config.setExtractUniqueInlineImagesOnly(true);

    parser.setPDFParserConfig(config);


    EmbeddedDocumentExtractor embeddedDocumentExtractor = 
            new EmbeddedDocumentExtractor() {
        @Override
        public boolean shouldParseEmbedded(Metadata metadata) {
            return true;
        }
        @Override
        public void parseEmbedded(InputStream stream, ContentHandler handler, Metadata metadata, boolean outputHtml)
                throws SAXException, IOException {
            Path outputFile = new File(path+metadata.get(Metadata.RESOURCE_NAME_KEY)).toPath();
            Files.copy(stream, outputFile);
        }
    };

    context.set(PDFParser.class, parser);
    context.set(EmbeddedDocumentExtractor.class,embeddedDocumentExtractor );

    try (InputStream stream = new ByteArrayInputStream(content)) {
        parser.parse(stream, handler, metadata, context);
    }

    return handler;
}

Answer 2

It is possible to use an AutoDetectParser to extract images, without relying on PDFParser. This code works just as well for extracting images out from docx, pptx, etc.

Here I have a parseDocument() and a setPdfConfig() function which makes use of an AutoDetectParser.

1. I create an AutoDetectParser
2. Attach a EmbeddedDocumentExtractor onto a ParseContext.
3. Attach the AutoDetectParser onto the same ParseContext.
4. Attach a PDFParserConfig onto the same ParseContext.
5. Then give that ParseContext to AutoDetectParser.parse().

The images are saved to a folder in the same location as the source file, with the name <sourceFile>_/.

private static void setPdfConfig(ParseContext context) {
    PDFParserConfig pdfConfig = new PDFParserConfig();
    pdfConfig.setExtractInlineImages(true);
    pdfConfig.setExtractUniqueInlineImagesOnly(true);

    context.set(PDFParserConfig.class, pdfConfig);
}

private static String parseDocument(String path) {
    String xhtmlContents = "";

    AutoDetectParser parser = new AutoDetectParser();
    ContentHandler handler = new ToXMLContentHandler();
    Metadata metadata = new Metadata();
    ParseContext context = new ParseContext();
    EmbeddedDocumentExtractor embeddedDocumentExtractor = 
            new EmbeddedDocumentExtractor() {
        @Override
        public boolean shouldParseEmbedded(Metadata metadata) {
            return true;
        }
        @Override
        public void parseEmbedded(InputStream stream, ContentHandler handler, Metadata metadata, boolean outputHtml)
                throws SAXException, IOException {
            Path outputDir = new File(path + "_").toPath();
            Files.createDirectories(outputDir);

            Path outputPath = new File(outputDir.toString() + "/" + metadata.get(Metadata.RESOURCE_NAME_KEY)).toPath();
            Files.deleteIfExists(outputPath);
            Files.copy(stream, outputPath);
        }
    };

    context.set(EmbeddedDocumentExtractor.class, embeddedDocumentExtractor);
    context.set(AutoDetectParser.class, parser);

    setPdfConfig(context);

    try (InputStream stream = new FileInputStream(path)) {
        parser.parse(stream, handler, metadata, context);
        xhtmlContents = handler.toString();
    } catch (IOException e) {
        e.printStackTrace();
    } catch (SAXException | TikaException e) {
        e.printStackTrace();
    }

    return xhtmlContents;
}