Tika 简明教程

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.pdf.PDFParser;
import org.apache.tika.sax.BodyContentHandler;

import org.xml.sax.SAXException;

public class PdfParse {

   public static void main(final String[] args) throws IOException,TikaException {

      BodyContentHandler handler = new BodyContentHandler();
      Metadata metadata = new Metadata();
      FileInputStream inputstream = new FileInputStream(new File("Example.pdf"));
      ParseContext pcontext = new ParseContext();

      //parsing the document using PDF parser
      PDFParser pdfparser = new PDFParser();
      pdfparser.parse(inputstream, handler, metadata,pcontext);

      //getting the content of the document
      System.out.println("Contents of the PDF :" + handler.toString());

      //getting metadata of the document
      System.out.println("Metadata of the PDF:");
      String[] metadataNames = metadata.names();

      for(String name : metadataNames) {
         System.out.println(name+ " : " + metadata.get(name));
      }
   }
}

javac PdfParse.java
java PdfParse

Contents of the PDF:

Apache Tika is a framework for content type detection and content extraction
which was designed by Apache software foundation. It detects and extracts metadata
and structured text content from different types of documents such as spreadsheets,
text documents, images or PDFs including audio or video input formats to certain extent.

Metadata of the PDF:

dcterms:modified :     2014-09-28T12:31:16Z
meta:creation-date :     2014-09-28T12:31:16Z
meta:save-date :     2014-09-28T12:31:16Z
dc:creator :     Krishna Kasyap
pdf:PDFVersion :     1.5
Last-Modified :     2014-09-28T12:31:16Z
Author :     Krishna Kasyap
dcterms:created :     2014-09-28T12:31:16Z
date :     2014-09-28T12:31:16Z
modified :     2014-09-28T12:31:16Z
creator :     Krishna Kasyap
xmpTPg:NPages :     1
Creation-Date :     2014-09-28T12:31:16Z
pdf:encrypted :     false
meta:author :     Krishna Kasyap
created :     Sun Sep 28 05:31:16 PDT 2014
dc:format :     application/pdf; version = 1.5
producer :     Microsoft® Word 2013
Content-Type :     application/pdf
xmp:CreatorTool :     Microsoft® Word 2013
Last-Save-Date :     2014-09-28T12:31:16Z

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.odf.OpenDocumentParser;
import org.apache.tika.sax.BodyContentHandler;

import org.xml.sax.SAXException;

public class OpenDocumentParse {

   public static void main(final String[] args) throws IOException,SAXException, TikaException {

      //detecting the file type
      BodyContentHandler handler = new BodyContentHandler();
      Metadata metadata = new Metadata();
      FileInputStream inputstream = new FileInputStream(new File("example_open_document_presentation.odp"));
      ParseContext pcontext = new ParseContext();

      //Open Document Parser
      OpenDocumentParser openofficeparser = new OpenDocumentParser ();
      openofficeparser.parse(inputstream, handler, metadata,pcontext);
      System.out.println("Contents of the document:" + handler.toString());
      System.out.println("Metadata of the document:");
      String[] metadataNames = metadata.names();

      for(String name : metadataNames) {
         System.out.println(name + " :  " + metadata.get(name));
      }
   }
}

javac OpenDocumentParse.java
java OpenDocumentParse

Contents of the document:

Apache Tika
Apache Tika is a framework for content type detection and content extraction which was designed
by Apache software foundation. It detects and extracts metadata and structured text content from
different types of documents such as spreadsheets, text documents, images or PDFs including audio
or video input formats to certain extent.

Metadata of the document:

editing-cycles:   4
meta:creation-date:   2009-04-16T11:32:32.86
dcterms:modified:   2014-09-28T07:46:13.03
meta:save-date:   2014-09-28T07:46:13.03
Last-Modified:   2014-09-28T07:46:13.03
dcterms:created:   2009-04-16T11:32:32.86
date:   2014-09-28T07:46:13.03
modified:   2014-09-28T07:46:13.03
nbObject:   36
Edit-Time:   PT32M6S
Creation-Date:   2009-04-16T11:32:32.86
Object-Count:   36
meta:object-count:   36
generator:   OpenOffice/4.1.0$Win32 OpenOffice.org_project/410m18$Build-9764
Content-Type:   application/vnd.oasis.opendocument.presentation
Last-Save-Date:   2014-09-28T07:46:13.03

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.microsoft.ooxml.OOXMLParser;
import org.apache.tika.sax.BodyContentHandler;

import org.xml.sax.SAXException;

public class MSExcelParse {

   public static void main(final String[] args) throws IOException, TikaException {

      //detecting the file type
      BodyContentHandler handler = new BodyContentHandler();
      Metadata metadata = new Metadata();
      FileInputStream inputstream = new FileInputStream(new File("example_msExcel.xlsx"));
      ParseContext pcontext = new ParseContext();

      //OOXml parser
      OOXMLParser  msofficeparser = new OOXMLParser ();
      msofficeparser.parse(inputstream, handler, metadata,pcontext);
      System.out.println("Contents of the document:" + handler.toString());
      System.out.println("Metadata of the document:");
      String[] metadataNames = metadata.names();

      for(String name : metadataNames) {
         System.out.println(name + ": " + metadata.get(name));
      }
   }
}

javac MSExcelParse.java
java MSExcelParse

Contents of the document:

Sheet1
Name	Age	Designation		Salary
Ramu	50	Manager			50,000
Raheem	40	Assistant manager	40,000
Robert	30	Superviser		30,000
sita	25	Clerk			25,000
sameer	25	Section in-charge	20,000

Metadata of the document:

meta:creation-date:    2006-09-16T00:00:00Z
dcterms:modified:    2014-09-28T15:18:41Z
meta:save-date:    2014-09-28T15:18:41Z
Application-Name:    Microsoft Excel
extended-properties:Company:
dcterms:created:    2006-09-16T00:00:00Z
Last-Modified:    2014-09-28T15:18:41Z
Application-Version:    15.0300
date:    2014-09-28T15:18:41Z
publisher:
modified:    2014-09-28T15:18:41Z
Creation-Date:    2006-09-16T00:00:00Z
extended-properties:AppVersion:    15.0300
protected:    false
dc:publisher:
extended-properties:Application:    Microsoft Excel
Content-Type:    application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
Last-Save-Date:    2014-09-28T15:18:41Z

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.sax.BodyContentHandler;
import org.apache.tika.parser.txt.TXTParser;

import org.xml.sax.SAXException;

public class TextParser {

   public static void main(final String[] args) throws IOException,SAXException, TikaException {

      //detecting the file type
      BodyContentHandler handler = new BodyContentHandler();
      Metadata metadata = new Metadata();
      FileInputStream inputstream = new FileInputStream(new File("example.txt"));
      ParseContext pcontext=new ParseContext();

      //Text document parser
      TXTParser  TexTParser = new TXTParser();
      TexTParser.parse(inputstream, handler, metadata,pcontext);
      System.out.println("Contents of the document:" + handler.toString());
      System.out.println("Metadata of the document:");
      String[] metadataNames = metadata.names();

      for(String name : metadataNames) {
         System.out.println(name + " : " + metadata.get(name));
      }
   }
}

javac TextParser.java
java TextParser

Contents of the document:

At tutorialspoint.com, we strive hard to provide quality tutorials for self-learning
purpose in the domains of Academics, Information Technology, Management and Computer
Programming Languages.
The endeavour started by Mohtashim, an AMU alumni, who is the founder and the managing
director of Tutorials Point (I) Pvt. Ltd. He came up with the website tutorialspoint.com
in year 2006 with the help of handpicked freelancers, with an array of tutorials for
computer programming languages.

Metadata of the document:

Content-Encoding:   windows-1252
Content-Type:   text/plain; charset = windows-1252

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.html.HtmlParser;
import org.apache.tika.sax.BodyContentHandler;

import org.xml.sax.SAXException;

public class HtmlParse {

   public static void main(final String[] args) throws IOException,SAXException, TikaException {

      //detecting the file type
      BodyContentHandler handler = new BodyContentHandler();
      Metadata metadata = new Metadata();
      FileInputStream inputstream = new FileInputStream(new File("example.html"));
      ParseContext pcontext = new ParseContext();

      //Html parser
      HtmlParser htmlparser = new HtmlParser();
      htmlparser.parse(inputstream, handler, metadata,pcontext);
      System.out.println("Contents of the document:" + handler.toString());
      System.out.println("Metadata of the document:");
      String[] metadataNames = metadata.names();

      for(String name : metadataNames) {
         System.out.println(name + ":   " + metadata.get(name));
      }
   }
}

javac HtmlParse.java
java HtmlParse

Contents of the document:

	Name	                     Salary	    age
	Ramesh Raman	             50000	    20
	Shabbir Hussein	             70000          25
	Umesh Raman	             50000	    30
	Somesh	                     50000	    35

Metadata of the document:

title:   HTML Table Header
Content-Encoding:   windows-1252
Content-Type:   text/html; charset = windows-1252
dc:title:   HTML Table Header

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.xml.XMLParser;
import org.apache.tika.sax.BodyContentHandler;

import org.xml.sax.SAXException;

public class XmlParse {

   public static void main(final String[] args) throws IOException,SAXException, TikaException {

      //detecting the file type
      BodyContentHandler handler = new BodyContentHandler();
      Metadata metadata = new Metadata();
      FileInputStream inputstream = new FileInputStream(new File("pom.xml"));
      ParseContext pcontext = new ParseContext();

      //Xml parser
      XMLParser xmlparser = new XMLParser();
      xmlparser.parse(inputstream, handler, metadata, pcontext);
      System.out.println("Contents of the document:" + handler.toString());
      System.out.println("Metadata of the document:");
      String[] metadataNames = metadata.names();

      for(String name : metadataNames) {
         System.out.println(name + ": " + metadata.get(name));
      }
   }
}

javac XmlParse.java
java XmlParse

Contents of the document:

4.0.0
org.apache.tika
tika
1.6
org.apache.tika
tika-core
1.6
org.apache.tika
tika-parsers
1.6
src
maven-compiler-plugin
3.1
1.7
1.7

Metadata of the document:

Content-Type:   application/xml

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.asm.ClassParser;
import org.apache.tika.sax.BodyContentHandler;

import org.xml.sax.SAXException;

public class JavaClassParse {

   public static void main(final String[] args) throws IOException,SAXException, TikaException {

      //detecting the file type
      BodyContentHandler handler = new BodyContentHandler();
      Metadata metadata = new Metadata();
      FileInputStream inputstream = new FileInputStream(new File("Example.class"));
      ParseContext pcontext = new ParseContext();

      //Html parser
      ClassParser  ClassParser = new  ClassParser();
      ClassParser.parse(inputstream, handler, metadata,pcontext);
      System.out.println("Contents of the document:" + handler.toString());
      System.out.println("Metadata of the document:");
      String[] metadataNames = metadata.names();

      for(String name : metadataNames) {
         System.out.println(name + " :  " + metadata.get(name));
      }
   }
}

javac JavaClassParse.java
java JavaClassParse

Contents of the document:

package tutorialspoint.tika.examples;
public synchronized class Example {
   public void Example();
   public static void main(String[]);
}

Metadata of the document:

title: Example
resourceName: Example.class
dc:title: Example

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.sax.BodyContentHandler;
import org.apache.tika.parser.pkg.PackageParser;

import org.xml.sax.SAXException;

public class PackageParse {

   public static void main(final String[] args) throws IOException,SAXException, TikaException {

      //detecting the file type
      BodyContentHandler handler = new BodyContentHandler();
      Metadata metadata = new Metadata();
      FileInputStream inputstream = new FileInputStream(new File("Example.jar"));
      ParseContext pcontext = new ParseContext();

      //Package parser
      PackageParser packageparser = new PackageParser();
      packageparser.parse(inputstream, handler, metadata,pcontext);
      System.out.println("Contents of the document: " + handler.toString());
      System.out.println("Metadata of the document:");
      String[] metadataNames = metadata.names();

      for(String name : metadataNames) {
         System.out.println(name + ":   " + metadata.get(name));
      }
   }
}

javac PackageParse.java
java PackageParse

Contents of the document:

META-INF/MANIFEST.MF
tutorialspoint/tika/examples/Example.class

Metadata of the document:

Content-Type:   application/zip

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.jpeg.JpegParser;
import org.apache.tika.sax.BodyContentHandler;

import org.xml.sax.SAXException;

public class JpegParse {

   public static void main(final String[] args) throws IOException,SAXException, TikaException {

      //detecting the file type
      BodyContentHandler handler = new BodyContentHandler();
      Metadata metadata = new Metadata();
      FileInputStream inputstream = new FileInputStream(new File("boy.jpg"));
      ParseContext pcontext = new ParseContext();

      //Jpeg Parse
      JpegParser  JpegParser = new JpegParser();
      JpegParser.parse(inputstream, handler, metadata,pcontext);
      System.out.println("Contents of the document:" + handler.toString());
      System.out.println("Metadata of the document:");
      String[] metadataNames = metadata.names();

      for(String name : metadataNames) {
         System.out.println(name + ": " + metadata.get(name));
      }
   }
}

javac JpegParse.java
java JpegParse

Contents of the document:

Meta data of the document:

Resolution Units: inch
Compression Type: Baseline
Data Precision: 8 bits
Number of Components: 3
tiff:ImageLength: 3000
Component 2: Cb component: Quantization table 1, Sampling factors 1 horiz/1 vert
Component 1: Y component: Quantization table 0, Sampling factors 2 horiz/2 vert
Image Height: 3000 pixels
X Resolution: 300 dots
Original Transmission Reference: 53616c7465645f5f2368da84ca932841b336ac1a49edb1a93fae938b8db2cb3ec9cc4dc28d7383f1
Image Width: 4000 pixels
IPTC-NAA record: 92 bytes binary data
Component 3: Cr component: Quantization table 1, Sampling factors 1 horiz/1 vert
tiff:BitsPerSample: 8
Application Record Version: 4
tiff:ImageWidth: 4000
Y Resolution: 300 dots

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.mp4.MP4Parser;
import org.apache.tika.sax.BodyContentHandler;

import org.xml.sax.SAXException;

public class Mp4Parse {

   public static void main(final String[] args) throws IOException,SAXException, TikaException {

      //detecting the file type
      BodyContentHandler handler = new BodyContentHandler();
      Metadata metadata = new Metadata();
      FileInputStream inputstream = new FileInputStream(new File("example.mp4"));
      ParseContext pcontext = new ParseContext();

      //Html parser
      MP4Parser MP4Parser = new MP4Parser();
      MP4Parser.parse(inputstream, handler, metadata,pcontext);
      System.out.println("Contents of the document:  :" + handler.toString());
      System.out.println("Metadata of the document:");
      String[] metadataNames = metadata.names();

      for(String name : metadataNames) {
         System.out.println(name + ": " + metadata.get(name));
      }
   }
}

javac Mp4Parse.java
java Mp4Parse

Contents of the document:

Metadata of the document:

dcterms:modified: 2014-01-06T12:10:27Z
meta:creation-date: 1904-01-01T00:00:00Z
meta:save-date: 2014-01-06T12:10:27Z
Last-Modified: 2014-01-06T12:10:27Z
dcterms:created: 1904-01-01T00:00:00Z
date: 2014-01-06T12:10:27Z
tiff:ImageLength: 360
modified: 2014-01-06T12:10:27Z
Creation-Date: 1904-01-01T00:00:00Z
tiff:ImageWidth: 640
Content-Type: video/mp4
Last-Save-Date: 2014-01-06T12:10:27Z

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.mp3.LyricsHandler;
import org.apache.tika.parser.mp3.Mp3Parser;
import org.apache.tika.sax.BodyContentHandler;

import org.xml.sax.SAXException;

public class Mp3Parse {

   public static void main(final String[] args) throws Exception, IOException, SAXException, TikaException {

      //detecting the file type
      BodyContentHandler handler = new BodyContentHandler();
      Metadata metadata = new Metadata();
      FileInputStream inputstream = new FileInputStream(new File("example.mp3"));
      ParseContext pcontext = new ParseContext();

      //Mp3 parser
      Mp3Parser  Mp3Parser = new  Mp3Parser();
      Mp3Parser.parse(inputstream, handler, metadata, pcontext);
      LyricsHandler lyrics = new LyricsHandler(inputstream,handler);

      while(lyrics.hasLyrics()) {
    	  System.out.println(lyrics.toString());
      }

      System.out.println("Contents of the document:" + handler.toString());
      System.out.println("Metadata of the document:");
      String[] metadataNames = metadata.names();

      for(String name : metadataNames) {
    	  System.out.println(name + ": " + metadata.get(name));
      }
   }
}

javac Mp3Parse.java
java Mp3Parse

Contents of the document:

Kanulanu Thaake
Arijit Singh
Manam (2014), track 01/06
2014
Soundtrack
30171.65
eng -
DRGM
Arijit Singh
Manam (2014), track 01/06
2014
Soundtrack
30171.65
eng -
DRGM

Metadata of the document:

xmpDM:releaseDate: 2014
xmpDM:duration: 30171.650390625
xmpDM:audioChannelType: Stereo
dc:creator: Arijit Singh
xmpDM:album: Manam (2014)
Author: Arijit Singh
xmpDM:artist: Arijit Singh
channels: 2
xmpDM:audioSampleRate: 44100
xmpDM:logComment: eng -
DRGM
xmpDM:trackNumber: 01/06
version: MPEG 3 Layer III Version 1
creator: Arijit Singh
xmpDM:composer: Music : Anoop Rubens | Lyrics : Vanamali
xmpDM:audioCompressor: MP3
title: Kanulanu Thaake
samplerate: 44100
meta:author: Arijit Singh
xmpDM:genre: Soundtrack
Content-Type: audio/mpeg
xmpDM:albumArtist: Manam (2014)
dc:title: Kanulanu Thaake