Java - Extract Text and Images from PDF

One drawback of PDF file is that users can't directly extract the text or pictures in the document, which brings trouble for us to reuse the information that we find useful. This article demonstrates how to extract text and images from a PDF document by using Free Spire.PDF for Java.

Below is a screenshot of the sample PDF document.

Installing Spire.Pdf.jar

If you create a Maven project, you can easily import the jar in your application using the following configurations. For non-Maven projects, download the jar file from this link and add it as a dependency in your application. 

<repositories>
    <repository>
        <id>com.e-iceblue</id>
        <name>e-iceblue</name>
        <url>http://repo.e-iceblue.com/nexus/content/groups/public/</url>
    </repository>
</repositories>
<dependencies>
    <dependency>
        <groupId> e-iceblue </groupId>
        <artifactId>spire.pdf.free</artifactId>
        <version>2.6.3</version>
    </dependency>
</dependencies>

Example 1. Extract text

import java.io.FileWriter;
import java.io.IOException;

public class ExtractText {

    public static void main(String[] args) {

        //create a PdfDocument instance
        PdfDocument doc = new PdfDocument();

        //load a sample PDF file
        doc.loadFromFile("C:\\Users\\Administrator\\Desktop\\sample.pdf");

        //create a StringBuilder instance
        StringBuilder sb = new StringBuilder();

        //loop through PDF pages and extract text of each page
        PdfPageBase page;
        for (int i = 0; i < doc.getPages().getCount(); i++) {
            page = doc.getPages().get(i);
            sb.append(page.extractText(true));
        }
        FileWriter writer;
        try {
            //write text into a .txt file
            writer = new FileWriter("C:\\Users\\Administrator\\Desktop\\ExtractText.txt");
            writer.write(sb.toString());
            writer.flush();
        } catch (IOException e) {
            e.printStackTrace();
        }
        doc.close();
    }
}

Example 2. Extract images

import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.IOException;

public class ExtractImage {

    public static void main(String[] args) throws IOException {

        //create a PdfDocment object
        PdfDocument doc = new PdfDocument();

        //load a PDF file
        doc.loadFromFile("C:\\Users\\Administrator\\Desktop\\sample.pdf");

        //declare an int variable
        int index = 0;

        //loop through the pages
        for (int i = 0; i < doc.getPages().getCount(); i++) {

            //extract images from a particular page
            for (BufferedImage image : doc.getPages().get(i).extractImages()) {
               
                //specify the file path and name
                File output = new File("C:\\Users\\Administrator\\Desktop\\ExtractedImages\\" + String.format("Image_%d.png", index++));

                //save image as .png file
                ImageIO.write(image, "PNG", output);
            }
        }
    }
}