Java使用Apache Tika从PDF文件中提取文本

<dependency>
    <groupId>org.apache.tika</groupId>
    <artifactId>tika-core</artifactId>
    <version>2.4.1</version> <!-- 请根据最新版本调整 -->
</dependency>
<dependency>
    <groupId>org.apache.tika</groupId>
    <artifactId>tika-parsers</artifactId>
    <version>2.4.1</version> <!-- 同上 -->
</dependency>

import org.apache.tika.Tika;
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;

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

public class TikaExample {
    public static void main(String[] args) {
        try (FileInputStream input = new FileInputStream(new File("example.pdf"))) {
            // 创建 Tika 实例
            Tika tika = new Tika();
            
            // 获取文件的 MIME 类型
            String mimeType = tika.detect(input);
            System.out.println("Detected MIME type: " + mimeType);

            // 重置输入流位置
            input.getChannel().position(0);

            // 准备解析器
            BodyContentHandler handler = new BodyContentHandler(-1); // -1 表示不限制输出大小
            Metadata metadata = new Metadata();
            ParseContext context = new ParseContext();

            // 解析 PDF 并获取内容
            PDFParser parser = new PDFParser();
            parser.parse(input, handler, metadata, context);

            // 输出结果
            System.out.println("Extracted text:\n" + handler.toString());
            System.out.println("Metadata:");
            String[] metadataNames = metadata.names();
            for (String name : metadataNames) {
                System.out.println(name + ": " + metadata.get(name));
            }
        } catch (IOException | SAXException | TikaException e) {
            e.printStackTrace();
        }
    }
}