Tika读取文件内容

1.pom引入以下依赖，尽量版本使用下面的，poi-ooxml包可以引用，也可以不引用

        <!-- Tika -->
        <dependency>
            <groupId>org.apache.tika</groupId>
            <artifactId>tika-core</artifactId>
            <version>1.24.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.tika</groupId>
            <artifactId>tika-parsers</artifactId>
            <version>1.24.1</version>
        </dependency>

        <!--io常用工具类 -->
        <dependency>
            <groupId>commons-io</groupId>
            <artifactId>commons-io</artifactId>
            <version>2.5</version>
        </dependency>

        <!-- poi工具 -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml</artifactId>
            <version>4.1.2</version>
        </dependency>

2.工具类

package com.imooc;

import java.io.*;

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;

/**
 * 文本内容读取工具类
 * 目前测试支持格式：properties、bat、docx、pdf、txt、html、xlsx、pptx、ppt。其他暂没测试
 */
public class TikaUtil {

    /**
     * 读取文件内容
     * @param file  要读取的文件
     * @return
     * @throws Exception
     */
    public static String getBody(File file){
        if(file==null||!file.exists()){
            return null;
        }
        ContentHandler handler = null;
        Parser parser = new AutoDetectParser();
        InputStream input = null;
        try {
            input = new FileInputStream(file);
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
        Metadata meta = new Metadata();
        handler = new BodyContentHandler();
        try {
            parser.parse(input, handler, meta, new ParseContext());
        } catch (IOException e) {
            e.printStackTrace();
        } catch (SAXException e) {
            e.printStackTrace();
        } catch (TikaException e) {
            e.printStackTrace();
        }
        return handler.toString();
    }

    public static void main(String[] args) {
        String body = null;
        try {
            body = getBody(new File("文件路径"));
        } catch (Exception e) {
            e.printStackTrace();
        }
        System.out.println(body);
    }
}