apache tika提取文件元数据

maven坐标

	<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-server</artifactId>
			<version>1.20</version>
	</dependency>

测试代码 

	@Test
	public void parseToPlainText() throws IOException, TikaException, org.xml.sax.SAXException {
		BodyContentHandler handler = new BodyContentHandler();
		File file=new File("C:/Users/yunxun/Desktop/开发总纲.doc");
        Metadata metadata = new Metadata();
		metadata.set(Metadata.RESOURCE_NAME_KEY, file.getName());
		ParseContext content = new ParseContext();
            //自动检测文件类型
		Parser parser = new AutoDetectParser();
		InputStream stream = new FileInputStream(file);
		content.set(Parser.class,parser);
		parser.parse(stream, handler, metadata, content);
//		System.out.println("数据内容:\n" + handler.toString());
		System.out.println("元数据:");
		String[] metadataNames = metadata.names();
		for (String name : metadataNames) {
			System.out.println(name + ": " + metadata.get(name));
		}
	}

结果: