PDF to Text Java Examples

These examples demonstrate common PDF to Text API workflows in Java.

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 an API client instance.
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "demo");

            // Run the conversion and save 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 an API client instance.
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "demo");

            // Run the conversion and store the result in 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 an API client instance.
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "demo");

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

            // run the conversion and write the result to 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 an API client instance.
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "demo");

            // Run the conversion and save 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 an API client instance.
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "demo");

            // Run the conversion and store the result in 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 an API client instance.
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "demo");

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

            // run the conversion and write the result to 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 an API client instance.
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "demo");

            // Run the conversion and save 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 an API client instance.
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "demo");

            // Run the conversion and store the result in 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 an API client instance.
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "demo");

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

            // run the conversion and write the result to 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 an API client instance.
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "demo");

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

            // Run the conversion and save the result to a file.
            client.convertFileToFile("/path/to/invoice.pdf", "invoice.txt");
            
            // print URL pointing to the debug log for this request.
            System.out.println("Debug log url: " + client.getDebugLogUrl());
            
            // print number of conversion credits remaining in your account.
            System.out.println("Remaining credit count: " + client.getRemainingCreditCount());
            
            // print number of credits consumed for this conversion.
            System.out.println("Consumed credit count: " + client.getConsumedCreditCount());
            
            // print unique identifier assigned to this conversion job.
            System.out.println("Job id: " + client.getJobId());
            
            // print total number of pages in the output document.
            System.out.println("Page count: " + client.getPageCount());
            
            // print size of the output data 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 an API client instance.
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "demo");

            // Run the conversion and store the result in 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");
            return new ResponseEntity<>(why.toString().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 an API client instance.
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "demo");

            // Run the conversion and store the result in 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");
            return new ResponseEntity<>(why.toString().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 an API client instance.
            Pdfcrowd.PdfToTextClient client =
                new Pdfcrowd.PdfToTextClient("demo", "demo");

            // Run the conversion and store the result in 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");
            return new ResponseEntity<>(why.toString().getBytes(), headers, HttpStatus.BAD_REQUEST);
        }
    }
}