PDF to Text Java Examples

This page contains various examples of using the PDF to Text API in Java. The examples are complete and fully functional. Read more about how to convert PDF to Text in Java.

Basic examples
Spring examples

Basic examples

PDF file to text file

import com.pdfcrowd.*;
import java.io.*;

public class ApiTest {
    public static void main(String[] args) throws IOException, Pdfcrowd.Error {
        try {
            // create the API client instance
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d");

            // run the conversion and write the result to a file
            client.convertFileToFile("/path/to/invoice.pdf", "invoice.txt");
        }
        catch(Pdfcrowd.Error why) {
            System.err.println("Pdfcrowd Error: " + why);
            throw why;
        }
        catch(IOException why) {
            System.err.println("IO Error: " + why);
            throw why;
        }
    }
}

PDF file to in-memory text

import com.pdfcrowd.*;
import java.io.*;

public class ApiTest {
    public static void main(String[] args) throws Pdfcrowd.Error {
        try {
            // create the API client instance
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d");

            // run the conversion and store the result into the "txt" variable
            byte[] txt = client.convertFile("/path/to/invoice.pdf");

            // at this point the "txt" variable contains TXT raw data and
            // can be sent in an HTTP response, saved to a file, etc.
        }
        catch(Pdfcrowd.Error why) {
            System.err.println("Pdfcrowd Error: " + why);
            throw why;
        }
    }
}

PDF file to text stream

import com.pdfcrowd.*;
import java.io.*;

public class ApiTest {
    public static void main(String[] args) throws IOException, Pdfcrowd.Error {
        try {
            // create the API client instance
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d");

            // create an output stream for the conversion result
            FileOutputStream outputStream = new FileOutputStream("invoice.txt");

            // run the conversion and write the result into the output stream
            client.convertFileToStream("/path/to/invoice.pdf", outputStream);

            // close the output stream
            outputStream.close();
        }
        catch(Pdfcrowd.Error why) {
            System.err.println("Pdfcrowd Error: " + why);
            throw why;
        }
        catch(IOException why) {
            System.err.println("IO Error: " + why);
            throw why;
        }
    }
}

PDF url to text file

import com.pdfcrowd.*;
import java.io.*;

public class ApiTest {
    public static void main(String[] args) throws IOException, Pdfcrowd.Error {
        try {
            // create the API client instance
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d");

            // run the conversion and write the result to a file
            client.convertUrlToFile("https://pdfcrowd.com/static/pdf/apisamples/invoice.pdf", "invoice.txt");
        }
        catch(Pdfcrowd.Error why) {
            System.err.println("Pdfcrowd Error: " + why);
            throw why;
        }
        catch(IOException why) {
            System.err.println("IO Error: " + why);
            throw why;
        }
    }
}

PDF url to in-memory text

import com.pdfcrowd.*;
import java.io.*;

public class ApiTest {
    public static void main(String[] args) throws Pdfcrowd.Error {
        try {
            // create the API client instance
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d");

            // run the conversion and store the result into the "txt" variable
            byte[] txt = client.convertUrl("https://pdfcrowd.com/static/pdf/apisamples/invoice.pdf");

            // at this point the "txt" variable contains TXT raw data and
            // can be sent in an HTTP response, saved to a file, etc.
        }
        catch(Pdfcrowd.Error why) {
            System.err.println("Pdfcrowd Error: " + why);
            throw why;
        }
    }
}

PDF url to text stream

import com.pdfcrowd.*;
import java.io.*;

public class ApiTest {
    public static void main(String[] args) throws IOException, Pdfcrowd.Error {
        try {
            // create the API client instance
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d");

            // create an output stream for the conversion result
            FileOutputStream outputStream = new FileOutputStream("invoice.txt");

            // run the conversion and write the result into the output stream
            client.convertUrlToStream("https://pdfcrowd.com/static/pdf/apisamples/invoice.pdf", outputStream);

            // close the output stream
            outputStream.close();
        }
        catch(Pdfcrowd.Error why) {
            System.err.println("Pdfcrowd Error: " + why);
            throw why;
        }
        catch(IOException why) {
            System.err.println("IO Error: " + why);
            throw why;
        }
    }
}

In-memory PDF to text file

import com.pdfcrowd.*;
import java.io.*;
import java.nio.file.Files;
import java.nio.file.Paths;

public class ApiTest {
    public static void main(String[] args) throws IOException, Pdfcrowd.Error {
        try {
            // create the API client instance
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d");

            // run the conversion and write the result to a file
            client.convertRawDataToFile(Files.readAllBytes(Paths.get("/path/to/hello_world.pdf")), "invoice.txt");
        }
        catch(Pdfcrowd.Error why) {
            System.err.println("Pdfcrowd Error: " + why);
            throw why;
        }
        catch(IOException why) {
            System.err.println("IO Error: " + why);
            throw why;
        }
    }
}

In-memory PDF to in-memory text

import com.pdfcrowd.*;
import java.io.*;
import java.nio.file.Files;
import java.nio.file.Paths;

public class ApiTest {
    public static void main(String[] args) throws IOException, Pdfcrowd.Error {
        try {
            // create the API client instance
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d");

            // run the conversion and store the result into the "txt" variable
            byte[] txt = client.convertRawData(Files.readAllBytes(Paths.get("/path/to/hello_world.pdf")));

            // at this point the "txt" variable contains TXT raw data and
            // can be sent in an HTTP response, saved to a file, etc.
        }
        catch(Pdfcrowd.Error why) {
            System.err.println("Pdfcrowd Error: " + why);
            throw why;
        }
        catch(IOException why) {
            System.err.println("IO Error: " + why);
            throw why;
        }
    }
}

In-memory PDF to text stream

import com.pdfcrowd.*;
import java.io.*;
import java.nio.file.Files;
import java.nio.file.Paths;

public class ApiTest {
    public static void main(String[] args) throws IOException, Pdfcrowd.Error {
        try {
            // create the API client instance
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d");

            // create an output stream for the conversion result
            FileOutputStream outputStream = new FileOutputStream("invoice.txt");

            // run the conversion and write the result into the output stream
            client.convertRawDataToStream(Files.readAllBytes(Paths.get("/path/to/hello_world.pdf")), outputStream);

            // close the output stream
            outputStream.close();
        }
        catch(Pdfcrowd.Error why) {
            System.err.println("Pdfcrowd Error: " + why);
            throw why;
        }
        catch(IOException why) {
            System.err.println("IO Error: " + why);
            throw why;
        }
    }
}

Get info about the current conversion

import com.pdfcrowd.*;
import java.io.*;

public class ApiTest {
    public static void main(String[] args) throws IOException, Pdfcrowd.Error {
        try {
            // create the API client instance
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d");

            // configure the conversion
            client.setDebugLog(true);
            client.setPageBreakMode("default");

            // run the conversion and write the result to a file
            client.convertFileToFile("/path/to/invoice.pdf", "invoice.txt");
            
            // print URL to the debug log
            System.out.println("Debug log url: " + client.getDebugLogUrl());
            
            // print the number of available conversion credits in your account
            System.out.println("Remaining credit count: " + client.getRemainingCreditCount());
            
            // print the number of credits consumed by the conversion
            System.out.println("Consumed credit count: " + client.getConsumedCreditCount());
            
            // print the unique ID of the conversion
            System.out.println("Job id: " + client.getJobId());
            
            // print the total number of pages in the output document
            System.out.println("Page count: " + client.getPageCount());
            
            // print the size of the output in bytes
            System.out.println("Output size: " + client.getOutputSize());
        }
        catch(Pdfcrowd.Error why) {
            System.err.println("Pdfcrowd Error: " + why);
            throw why;
        }
        catch(IOException why) {
            System.err.println("IO Error: " + why);
            throw why;
        }
    }
}

Spring examples

PDF file to text in Spring

import java.net.URLEncoder;
import java.io.UnsupportedEncodingException;
import org.springframework.stereotype.Controller;
import org.springframework.web.bind.annotation.PostMapping;
import org.springframework.http.ResponseEntity;
import org.springframework.http.HttpHeaders;
import org.springframework.http.HttpStatus;
import com.pdfcrowd.*;

@Controller
public class DemoController {
    // the recommended method is POST
    @PostMapping("/")
    public ResponseEntity<byte[]> convert() throws UnsupportedEncodingException {
        try {
            // create the API client instance
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d");

            // run the conversion and store the result into the "txt" variable
            byte[] txt = client.convertFile("/path/to/invoice.pdf");

            // set HTTP response headers
            HttpHeaders headers = new HttpHeaders();
            headers.add("Content-Type", "text/plain");
            headers.add("Cache-Control", "max-age=0");
            headers.add("Accept-Ranges", "none");
            headers.add("Content-Disposition", "attachment; filename*=UTF-8''" +
                        URLEncoder.encode("invoice.txt", "UTF-8").replace("+", "%20"));

            // send the result in the HTTP response
            return new ResponseEntity<>(txt, headers, HttpStatus.OK);
        }
        catch(Pdfcrowd.Error why) {
            // send the error in the HTTP response
            HttpHeaders headers = new HttpHeaders();
            headers.add("Content-Type", "text/plain");
            String msg = String.format("Pdfcrowd Error: %d - %s",
                                       why.getCode(), why.getMessage());
            return new ResponseEntity<>(msg.getBytes(), headers, HttpStatus.BAD_REQUEST);
        }
    }
}

PDF url to text in Spring

import java.net.URLEncoder;
import java.io.UnsupportedEncodingException;
import org.springframework.stereotype.Controller;
import org.springframework.web.bind.annotation.PostMapping;
import org.springframework.http.ResponseEntity;
import org.springframework.http.HttpHeaders;
import org.springframework.http.HttpStatus;
import com.pdfcrowd.*;

@Controller
public class DemoController {
    // the recommended method is POST
    @PostMapping("/")
    public ResponseEntity<byte[]> convert() throws UnsupportedEncodingException {
        try {
            // create the API client instance
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d");

            // run the conversion and store the result into the "txt" variable
            byte[] txt = client.convertUrl("https://pdfcrowd.com/static/pdf/apisamples/invoice.pdf");

            // set HTTP response headers
            HttpHeaders headers = new HttpHeaders();
            headers.add("Content-Type", "text/plain");
            headers.add("Cache-Control", "max-age=0");
            headers.add("Accept-Ranges", "none");
            headers.add("Content-Disposition", "attachment; filename*=UTF-8''" +
                        URLEncoder.encode("invoice.txt", "UTF-8").replace("+", "%20"));

            // send the result in the HTTP response
            return new ResponseEntity<>(txt, headers, HttpStatus.OK);
        }
        catch(Pdfcrowd.Error why) {
            // send the error in the HTTP response
            HttpHeaders headers = new HttpHeaders();
            headers.add("Content-Type", "text/plain");
            String msg = String.format("Pdfcrowd Error: %d - %s",
                                       why.getCode(), why.getMessage());
            return new ResponseEntity<>(msg.getBytes(), headers, HttpStatus.BAD_REQUEST);
        }
    }
}

In-memory PDF to text in Spring

import java.net.URLEncoder;
import java.io.UnsupportedEncodingException;
import org.springframework.stereotype.Controller;
import org.springframework.web.bind.annotation.PostMapping;
import org.springframework.http.ResponseEntity;
import org.springframework.http.HttpHeaders;
import org.springframework.http.HttpStatus;
import com.pdfcrowd.*;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.io.IOException;

@Controller
public class DemoController {
    // the recommended method is POST
    @PostMapping("/")
    public ResponseEntity<byte[]> convert() throws IOException, UnsupportedEncodingException {
        try {
            // create the API client instance
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d");

            // run the conversion and store the result into the "txt" variable
            byte[] txt = client.convertRawData(Files.readAllBytes(Paths.get("/path/to/hello_world.pdf")));

            // set HTTP response headers
            HttpHeaders headers = new HttpHeaders();
            headers.add("Content-Type", "text/plain");
            headers.add("Cache-Control", "max-age=0");
            headers.add("Accept-Ranges", "none");
            headers.add("Content-Disposition", "attachment; filename*=UTF-8''" +
                        URLEncoder.encode("invoice.txt", "UTF-8").replace("+", "%20"));

            // send the result in the HTTP response
            return new ResponseEntity<>(txt, headers, HttpStatus.OK);
        }
        catch(Pdfcrowd.Error why) {
            // send the error in the HTTP response
            HttpHeaders headers = new HttpHeaders();
            headers.add("Content-Type", "text/plain");
            String msg = String.format("Pdfcrowd Error: %d - %s",
                                       why.getCode(), why.getMessage());
            return new ResponseEntity<>(msg.getBytes(), headers, HttpStatus.BAD_REQUEST);
        }
    }
}