【tika】读取各个文件数据

首先我们到官网下载tika的jar包

1.将jar包引入到项目中:

接下来我们就可以进行数据的读取

1.读取普通本文

package cn.qblank.tika;

import java.io.File;

import org.apache.tika.Tika;
/**
 * 获取普通文本的数据
 * 使用Tika facade 类从文件中提取文本
 * @author evan_qb
 */
public class ReadText {
	public static void main(String[] args) throws Exception {
		File file = new File("D:/test/test.txt");
		Tika tika = new Tika();
		String content = tika.parseToString(file);
		content = new String(content.getBytes("ISO-8859-1"),"gbk");
		System.out.println("文件内容为:\n" + content);
	}
}

2.读取xml的数据

package cn.qblank.tika;

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

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;
/**
 * 读取xml文件
 * @author Administrator
 */
public class ReaderXML {
	public static void main(String[] args) throws Exception{
		  //检测文件类型
	      BodyContentHandler handler = new BodyContentHandler();
	      Metadata metadata = new Metadata();
	      FileInputStream inputstream = new FileInputStream(new File("d:/test/contact.xml"));
	      ParseContext pcontext = new ParseContext();
	      //转换为xml
	      XMLParser xmlparser = new XMLParser(); 
	      xmlparser.parse(inputstream, handler, metadata, pcontext);
	      System.out.println("XML文件内容:\n" + handler.toString());
	      System.out.println("元数据内容:");
	      String[] metadataNames = metadata.names();
	      for(String name : metadataNames) {
	         System.out.println(name + ": " + metadata.get(name));
	      }
	}
}

xml文件:

读取结果:

3.读取html

package cn.qblank.tika;

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

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;
/**
 * 获取HTML的数据
 * @author Administrator
 */
public class ReaderXHTML {
	public static void main(String[] args) throws Exception {
		//检测html文件
		BodyContentHandler handler = new BodyContentHandler();
	    Metadata metadata = new Metadata();
	    FileInputStream inputstream = new FileInputStream(new File("D:/test/test1.html"));
	    ParseContext pcontext = new ParseContext();
	    //转换为HTML
	    HtmlParser htmlparser = new HtmlParser();
	    htmlparser.parse(inputstream, handler, metadata,pcontext);
	    System.out.println("文档内容:\n" + handler.toString());
	    System.out.println("元数据:");
	    String[] metadataNames = metadata.names();
	    for(String name : metadataNames) {
	       System.out.println(name + ":   " + metadata.get(name));  
	    }
	}
	
}

html文件如下:

读取结果如下:

4.读取Excel文档:

package cn.qblank.tika;

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

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;

/**
 * tika入门:获取Excel文档的数据
 * @author evan_qb
 */
public class ReaderSheet {
	public static void main(String[] args) throws Exception {
		//检测文件类型
	    BodyContentHandler handler = new BodyContentHandler();
	    Metadata metadata = new Metadata();
	    FileInputStream inputstream = new FileInputStream(new File("d:/Writesheet.xlsx"));
	    ParseContext pcontext = new ParseContext();
	    //使用OOXMLParser转换器
	    OOXMLParser  msofficeparser = new OOXMLParser (); 
	    msofficeparser.parse(inputstream, handler, metadata,pcontext);
	    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) );
	    }
	}
}

Excel数据:

读取数据:

参考文件: http://www.yiibai.com/tika/tika_architecture.html