How to extract data from PDF files using Apache Tika? (31 of 285 technotes for 2015)

The Apache Tika™ toolkit detects and extracts metadata and text from over a thousand different file types (such as PPT, XLS, and PDF). All of these file types can be parsed through a single interface, making Tika useful for search engine indexing, content analysis, translation, and much more.

The code below shows a simple example as to how to use Apache Tika.

import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
 
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.sax.BodyContentHandler;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
 
public class Sample {
 
    public static void main(String[] args){
        InputStream is = null;
 
        try {
            is = new BufferedInputStream(new FileInputStream(new File("sample.pdf")));
 
            Parser parser = new AutoDetectParser();
            ContentHandler handler = new BodyContentHandler(System.out);
 
            Metadata metadata = new Metadata();
 
            parser.parse(is, handler, metadata, new ParseContext());
 
            for (String name : metadata.names()) {
                String value = metadata.get(name);
 
                if (value != null) {
                    System.out.println("Metadata Name:  " + name);
                    System.out.println("Metadata Value: " + value);
                }
            }
        } catch (IOException e) {
            e.printStackTrace();
        } catch (TikaException e) {
            e.printStackTrace();
        } catch (SAXException e) {
            e.printStackTrace();
        } finally {
            if (is != null) {
                try {
                    is.close();
                } catch(IOException e) {
                    e.printStackTrace();
                }
            }
        }
    }
}

<?xml version="1.0" ?>
<project
    xmlns="http://maven.apache.org/POM/4.0.0"
    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
    xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4.0.0.xsd">
 
    <modelVersion>4.0.0</modelVersion>
    <groupId>net.kinjouj.tika</groupId>
    <artifactId>kinjouj_tika</artifactId>
    <version>1.0</version>
    <name>kinjouj_tika</name>
 
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>2.3.2</version>
                <configuration>
                    <source>1.6</source>
                    <target>1.6</target>
                    <encoding>UTF-8</encoding>
                </configuration>
            </plugin>
            <plugin>
                <groupId>org.codehaus.mojo</groupId>
                <artifactId>exec-maven-plugin</artifactId>
                <version>1.2.1</version>
                 <configuration>
                     <mainClass>Sample</mainClass>
                 </configuration>
            </plugin>
        </plugins>
    </build>
 
    <dependencies>
        <dependency>
            <groupId>org.apache.tika</groupId>
            <artifactId>tika-core</artifactId>
            <version>1.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.tika</groupId>
            <artifactId>tika-parsers</artifactId>
            <version>1.1</version>
        </dependency>
    </dependencies>
</project>

https://gist.github.com/kinjouj/2507727