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;
}