Tika解析pdf信息

Apache Tika是一个用于文件类型检测和文件内容，其中PDF解析器可以读取pdf内容

所用jar包：

        <dependency>
            <groupId>org.apache.tika</groupId>
            <artifactId>tika-core</artifactId>
            <version>1.20</version>
        </dependency>
        <dependency>
            <groupId>org.apache.tika</groupId>
            <artifactId>tika-parsers</artifactId>
            <version>1.16</version>
        </dependency>

　　

 

public static void main(String[] args) {
        File file =new File("D:\\101.pdf");
        BodyContentHandler handler=new BodyContentHandler();
        //元数据对象
        Metadata metadata=new Metadata();

        FileInputStream inputStream=new FileInputStream(file);

        ParseContext parseContext=new ParseContext();
        //
        PDFParser pdfParser=new PDFParser();

        pdfParser.parse(inputStream, handler, metadata, parseContext);
        System.out.println("文件属性信息：");
        for(String name: metadata.names()){
            System.out.println(name+":"+metadata.get(name));
        }
        System.out.println("pdf文件内容：");
        System.out.println(handler.toString());

    }