java tika pdf_TIKA - 提取PDF

以下是从PDF中提取内容和元数据的程序。

importjava.io.File;importjava.io.FileInputStream;importjava.io.IOException;importorg.apache.tika.exception.TikaException;importorg.apache.tika.metadata.Metadata;importorg.apache.tika.parser.ParseContext;importorg.apache.tika.parser.pdf.PDFParser;importorg.apache.tika.sax.BodyContentHandler;importorg.xml.sax.SAXException;publicclassPdfParse{publicstaticvoidmain(finalString[]args)throwsIOException,TikaException{BodyContentHandlerhandler=newBodyContentHandler();Metadatametadata=newMetadata();FileInputStreaminputstream=newFileInputStream(newFile("Example.pdf"));ParseContextpcontext=newParseContext();//parsing the document using PDF parserPDFParserpdfparser=newPDFParser();pdfparser.parse(inputstream,handler,metadata,pcontext);//getting the content of the documentSystem.out.println("Contents of the PDF :"+handler.toString());//getting metadata of the documentSystem.out.println("Metada