tika提取文件内容

最新推荐文章于 2025-03-19 17:22:40 发布

nddjava

最新推荐文章于 2025-03-19 17:22:40 发布

阅读量472

点赞数

文章标签： java 数据库开发语言

本文链接：https://blog.youkuaiyun.com/nddjava/article/details/128314363

版权

这篇博客介绍了如何利用Tika Java库来提取不同格式文件的内容，包括所需的Maven依赖和基本代码示例。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

引入mavenjar包（提取不通格式文件内容需要引入相关依赖的包）

 <!--tika-->
        <dependency>
            <groupId>org.apache.tika</groupId>
            <artifactId>tika-core</artifactId>
            <version>1.26</version>
        </dependency>
        <dependency>
            <groupId>org.apache.tika</groupId>
            <artifactId>tika-parsers</artifactId>
            <version>1.26</version>
        </dependency>
        <dependency>
            <groupId>org.apache.pdfbox</groupId>
            <artifactId>jbig2-imageio</artifactId>
            <version>3.0.1</version>
        </dependency>
        <dependency>
            <groupId>com.github.jai-imageio</groupId>
            <artifactId>jai-imageio-jpeg2000</artifactId>
            <version>1.3.0</version>
        </dependency>
        <dependency>
            <groupId>org.xerial</groupId>
            <artifactId>sqlite-jdbc</artifactId>
            <version>3.20.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi</artifactId>
            <version>4.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml</artifactId>
            <version>4.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml-schemas</artifactId>
            <version>4.0.0</version>
        </dependency>

代码



    public static void main(String[] args) {
        String filePath="D:\\tools\\nginx-1.18.0\\html\\index.html";
        Tika tika = new Tika();
        try {
            //System.out.println("---"+tika.parseToString(new File(filePath)));
            //推荐使用
            System.out.println("--1-"+new TikaController().fileToTxt(new File(filePath))+"---e1-");
            System.out.println("--2-"+new TikaController().tikaTool(new File(filePath))+"---e2-");
        }catch (Exception e) {
            e.printStackTrace();
        }

    }

    public String tikaTool(File f) throws IOException, TikaException {
        Tika tika = new Tika();
        Metadata metadata = new Metadata();
        metadata.set(Metadata.RESOURCE_NAME_KEY, f.getName());
        String str = tika.parseToString(new FileInputStream(f), metadata);
        for(String name : metadata.names()) {
            //System.out.println(name+":"+metadata.get(name));
        }
//return tika.parseToString(f);
        return str;
    }

    public String fileToTxt(File f) {
        Parser parser = new AutoDetectParser();
        InputStream is = null;
        try {
            Metadata metadata = new Metadata();
            metadata.set(Metadata.RESOURCE_NAME_KEY, f.getName());
            is = new FileInputStream(f);
            ContentHandler handler = new BodyContentHandler();
            ParseContext context = new ParseContext();
            context.set(Parser.class, parser);
            parser.parse(is, handler, metadata, context);
            for (String name : metadata.names()) {
                //System.out.println(name +":"+metadata.get(name));
            }
            return handler.toString();
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } catch (SAXException e) {
            e.printStackTrace();
        } catch (TikaException e) {
            e.printStackTrace();
        } finally {
            if (is != null) {
                try {
                    is.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
        return null;
    }