In this program, You will see the complete example of extract content and metadata from pdf file by using TIKA PDFParser.

Sample File

Complete Example

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.pdf.PDFParser;
import org.apache.tika.sax.BodyContentHandler;

import org.xml.sax.SAXException;

public class TikaPDFParserExample {

   public static void main(final String[] args) throws IOException,TikaException, SAXException {

      BodyContentHandler handler = new BodyContentHandler();
      Metadata metadata = new Metadata();
      FileInputStream inputstream = new FileInputStream(new File("D:\\Leraning Material\\Blogs Data\\Bharti Ticket Original.pdf"));
      ParseContext pcontext = new ParseContext();

      //document parsing using PDF parser
      PDFParser pdfparser = new PDFParser();
      pdfparser.parse(inputstream, handler, metadata,pcontext);

      //extract content of the document
      System.out.println("Contents of the PDF File :" + handler.toString());

      //get metadata of the document
      System.out.println("Metadata of the PDF File:");
      String[] metadataNames = metadata.names();

      for(String name : metadataNames) {
         System.out.println(name+ " : " + metadata.get(name));
      }
   }
}

Output

Contents of the PDF File :
TEXT-FILE.txt
You are in FacingIssuesOnIT.

Learn from Others Experience.

Page 1


Metadata of the PDF File:
date : 2019-11-22T23:49:59Z
pdf:unmappedUnicodeCharsPerPage : 0
pdf:PDFVersion : 1.7
pdf:docinfo:title : TEXT-FILE.txt - Notepad
access_permission:modify_annotations : true
access_permission:can_print_degraded : true
dc:creator : Saurabh Gupta
dcterms:created : 2019-11-22T23:49:59Z
Last-Modified : 2019-11-22T23:49:59Z
dcterms:modified : 2019-11-22T23:49:59Z
dc:format : application/pdf; version=1.7
title : TEXT-FILE.txt - Notepad
Last-Save-Date : 2019-11-22T23:49:59Z
access_permission:fill_in_form : true
pdf:docinfo:modified : 2019-11-22T23:49:59Z
meta:save-date : 2019-11-22T23:49:59Z
pdf:encrypted : false
dc:title : TEXT-FILE.txt - Notepad
modified : 2019-11-22T23:49:59Z
Content-Type : application/pdf
pdf:docinfo:creator : Saurabh Gupta
creator : Saurabh Gupta
meta:author : Saurabh Gupta
meta:creation-date : 2019-11-22T23:49:59Z
created : 2019-11-22T23:49:59Z
access_permission:extract_for_accessibility : true
access_permission:assemble_document : true
xmpTPg:NPages : 1
Creation-Date : 2019-11-22T23:49:59Z
pdf:charsPerPage : 76
access_permission:extract_content : true
access_permission:can_print : true
Author : Saurabh Gupta
producer : Microsoft: Print To PDF
access_permission:can_modify : true
pdf:docinfo:producer : Microsoft: Print To PDF
pdf:docinfo:created : 2019-11-22T23:49:59Z