How to use

PDFParser

in

org.apache.tika.parser.pdf

 public class PDFReader{
  public static void main(String args[]) {
    PDFTextStripper pdfStripper = null;
    PDDocument pdDoc = null;
    COSDocument cosDoc = null;
    File file = new File("C:/my.pdf");
    try {
      PDFParser parser = new PDFParser(new FileInputStream(file));
      parser.parse();
      cosDoc = parser.getDocument();
      pdfStripper = new PDFTextStripper();
      pdDoc = new PDDocument(cosDoc);
      pdfStripper.setStartPage(1);
      pdfStripper.setEndPage(5);
      String parsedText = pdfStripper.getText(pdDoc);
      System.out.println(parsedText);
    } catch (IOException e) {
      // TODO Auto-generated catch block
      e.printStackTrace();
    } 
  }
}

    addMetadata(metadata, property, pdfBoxBaseline);
List<String> items = getXMPBagOrSeqList(dc, property.getName());
if (items == null) {
  if (pdfBoxBaseline != null && pdfBoxBaseline.length() > 0) {
    addMetadata(metadata, property, pdfBoxBaseline);
    addMetadata(metadata, property, item);
  addMetadata(metadata, property, pdfBoxBaseline);

private void addMetadata(Metadata metadata, String name, String value) {
  if (value != null) {
    metadata.add(name, decode(value));
  }
}

public static Metadata getMet(URL url) throws IOException, SAXException,
    TikaException {
  Metadata met = new Metadata();
  PDFParser parser = new PDFParser();
  parser.parse(url.openStream(), new BodyContentHandler(), met, new ParseContext());
  return met;
}

 public void parse(InputStream stream, ContentHandler handler,
   Metadata metadata, ParseContext context) throws IOException,
   SAXException, TikaException {
  TikaInputStream tis = TikaInputStream.get(stream, new TemporaryResources());
  File tmpFile = tis.getFile();

  GrobidRESTParser grobidParser = new GrobidRESTParser();
  grobidParser.parse(tmpFile.getAbsolutePath(), handler, metadata, context);

  PDFParser parser = new PDFParser();
  parser.parse(new FileInputStream(tmpFile), handler, metadata, context);
 }
}

PDFParser pps = new PDFParser(new FileInputStream(Filepath);

 File in = new File("somefile.pdf");
InputStream fin = new FileInputStream(in);
PDFParser parser = new PDFParser(fin);
parser.setTempDirectory(new File(tempDirectoryPath));
parser.parse();
PDDocument document = parser.getPDDocument();

  psStream = new FileInputStream(filename);
} catch (FileNotFoundException ffne) {
  try {
    PDFParser parser = new PDFParser(psStream);
    PrinterJob job1 = PrinterJob.getPrinterJob();
    job1.setPrintService(services[count]);
psStream.close();

 var PDFParser = require('pdf2json');
var pdfParser = new PDFParser();

pdfParser.on('pdfParser_dataReady', function(data) {
  var doc = data.PDFJS && data.PDFJS.pdfDocument && data.PDFJS.pdfDocument.numPages;
  console.log('Number of pages:', doc);
});
// pdfParser.on('pdfParser_dataError', _.bind(_onPFBinDataError, self));

pdfParser.loadPDF('test.pdf');

public void ReadPDF() throws Exception {
 URL TestURL = new URL("http://www.axmag.com/download/pdfurl-guide.pdf");
 BufferedInputStream TestFile = new BufferedInputStream(TestURL.openStream());
 PDFParser TestPDF = new PDFParser(TestFile);
 TestPDF.parse();
 String TestText = new PDFTextStripper().getText(TestPDF.getPDDocument());
 Assert.assertTrue(TestText.contains("Open the setting.xml, you can see it is like this"));
 }

private static void initParser(Fs fs) {
  if (parser == null) {
    PDFParser pdfParser = new PDFParser();
    DefaultParser defaultParser;
    if (fs.isPdfOcr()) {
      logger.debug("OCR is activated for PDF documents");
      if (ExternalParser.check("tesseract")) {
        pdfParser.setOcrStrategy("ocr_and_text");
      } else {
        logger.debug("But Tesseract is not installed so we won't run OCR.");
      }
      defaultParser = new DefaultParser();
    } else {
      logger.debug("OCR is disabled. Even though it's detected, it must be disabled explicitly");
      defaultParser = new DefaultParser(
          MediaTypeRegistry.getDefaultRegistry(),
          new ServiceLoader(),
          Collections.singletonList(TesseractOCRParser.class));
    }
    Parser PARSERS[] = new Parser[2];
    PARSERS[0] = defaultParser;
    PARSERS[1] = pdfParser;
    parser = new AutoDetectParser(PARSERS);
  }
}

try {
  TikaInputStream tstream = TikaInputStream.cast(stream);
  password = getPassword(metadata, context);
  MemoryUsageSetting memoryUsageSetting = MemoryUsageSetting.setupMainMemoryOnly();
  if (localConfig.getMaxMainMemoryBytes() >= 0) {
  extractMetadata(pdfDocument, metadata, context);
  AccessChecker checker = localConfig.getAccessChecker();
  checker.check(metadata);
  if (handler != null) {
    if (shouldHandleXFAOnly(pdfDocument, localConfig)) {
      handleXFAOnly(pdfDocument, handler, metadata, context);
    } else if (localConfig.getOcrStrategy().equals(PDFParserConfig.OCR_STRATEGY.OCR_ONLY)) {
      metadata.add("X-Parsed-By", TesseractOCRParser.class.toString());

Document dom = loadDOM(document.getDocumentCatalog().getMetadata(), metadata, context);
extractMultilingualItems(metadata, TikaCoreProperties.TITLE, info.getTitle(), dcSchema);
addMetadata(metadata, PDF.DOC_INFO_TITLE, info.getTitle());
extractDublinCoreListItems(metadata, TikaCoreProperties.CREATOR, info.getAuthor(), dcSchema);
addMetadata(metadata, PDF.DOC_INFO_CREATOR, info.getAuthor());
extractDublinCoreListItems(metadata, TikaCoreProperties.CONTRIBUTOR, null, dcSchema);
addMetadata(metadata, TikaCoreProperties.CREATOR_TOOL, info.getCreator());
addMetadata(metadata, PDF.DOC_INFO_CREATOR_TOOL, info.getCreator());
addMetadata(metadata, Office.KEYWORDS, info.getKeywords());
addMetadata(metadata, PDF.DOC_INFO_KEY_WORDS, info.getKeywords());
addMetadata(metadata, PDF.DOC_INFO_PRODUCER, info.getProducer());
extractMultilingualItems(metadata, TikaCoreProperties.DESCRIPTION, null, dcSchema);
addMetadata(metadata, PDF.DOC_INFO_SUBJECT, info.getSubject());
addMetadata(metadata, TikaCoreProperties.SUBJECT, info.getKeywords());
addMetadata(metadata, TikaCoreProperties.SUBJECT, info.getSubject());
addMetadata(metadata, OfficeOpenXMLCore.SUBJECT, info.getSubject());
addMetadata(metadata, PDF.DOC_INFO_TRAPPED, info.getTrapped());
Calendar created = info.getCreationDate();
addMetadata(metadata, PDF.DOC_INFO_CREATED, created);
addMetadata(metadata, TikaCoreProperties.CREATED, created);
Calendar modified = info.getModificationDate();
addMetadata(metadata, TikaCoreProperties.MODIFIED, modified);
addMetadata(metadata, PDF.DOC_INFO_MODIFICATION_DATE, modified);
  String name = key.getName();

  @Override
  public List<Page> parse(InputStream fs, List<String> filterPatterns) throws Exception {
    List<Page> pages = new ArrayList<>();
    PageContentHandler handler = new PageContentHandler(filterPatterns);
    Metadata metadata = new Metadata();
    pdfParser.setSortByPosition(true);
    pdfParser.parse(fs, handler, metadata, new ParseContext());

    Map<Integer, List<String>> content =  handler.getImprovedContent();
    for (Integer i : content.keySet()) {
      Page page = new Page(i);
      for (String p : content.get(i)) {
        page.getParagraphs().add(p);
      }
      pages.add(page);
    }

    return pages;
  }
}

/**
 * Used when processing custom metadata entries, as PDFBox won't do
 * the conversion for us in the way it does for the standard ones
 */
private void addMetadata(Metadata metadata, String name, COSBase value) {
  if (value instanceof COSArray) {
    for (Object v : ((COSArray) value).toList()) {
      addMetadata(metadata, name, ((COSBase) v));
    }
  } else if (value instanceof COSString) {
    addMetadata(metadata, name, ((COSString) value).getString());
  }
  // Avoid calling COSDictionary#toString, since it can lead to infinite
  // recursion. See TIKA-1038 and PDFBOX-1835.
  else if (value != null && !(value instanceof COSDictionary)) {
    addMetadata(metadata, name, value.toString());
  }
}

 InputStream input = new FileInputStream(new File(resourceLocation));
ContentHandler textHandler = new BodyContentHandler();
Metadata metadata = new Metadata();
PDFParser parser = new PDFParser();
parser.parse(input, textHandler, metadata);
input.close();
out.println("Title: " + metadata.get("title"));
out.println("Author: " + metadata.get("Author"));
out.println("content: " + textHandler.toString());

PDFParser pps = new PDFParser(new FileInputStream(Filepath));

private void openPDFDoc(final File pdfFile) throws Exception {
   File originalPDF = pdfFile;
   PDFParser parser = new PDFParser(new BufferedInputStream(new FileInputStream(
       originalPDF)));
   parser.parse();
   PDDocument originialPdfDoc = parser.getPDDocument();
   boolean isOriginalDocEncrypted = originialPdfDoc.isEncrypted();
   if (isOriginalDocEncrypted) {
     originialPdfDoc.openProtection(new StandardDecryptionMaterial("password"));
   }
 }

  @Override
  protected Parser getParser() 
  {
    return new PDFParser();
  }
}

 import org.apache.tika.parser.pdf.PDFParser;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.sax.BodyContentHandler;
import org.xml.sax.ContentHandler;

public class URLReader {
  public static void main(String[] args) throws Exception {

    URL url = new URL("http://website.com/document.pdf");
    ContentHandler contenthandler = new BodyContentHandler();
    Metadata metadata = new Metadata();
    PDFParser pdfparser = new PDFParser();
    pdfparser.parse(is, contenthandler, metadata, new ParseContext());

    System.out.println(contenthandler.toString());
  }
}