解析pdf文档 (lucene3.5)

//今天根据课本写了个 解析pdf文档的小程序
 
 
 
import java.io.FileWriter;
import java.io.IOException;
import java.io.PrintWriter;

import org.pdfbox.pdmodel.PDDocument;
import org.pdfbox.util.PDFTextStripper;


public class ExtractorPDF {

	/**
	 * @param args
	 */
	public static String getText(String file) //throws Exception
	{String pdfFile=file;
	PDDocument document=null;
	String s=null;
	try {
		//装载文件
		document=PDDocument.load(pdfFile);
		//用PDFTextStripper来提取 文件
		PDFTextStripper stripper=new PDFTextStripper();
		s=stripper.getText(document);
		
	} catch (IOException e) {
		// TODO Auto-generated catch block
		e.printStackTrace();
	}
	finally {
		if (document!=null)
			try {
				document.close();
			} catch (IOException e) {
				// TODO Auto-generated catch block
				e.printStackTrace();
			}
		
		
	}
	return s;
	
	}
	
	public static void toTextFile(String file,String txt)
	{
		String pdfFile=file;
		PDDocument document=null;
		try {
			//加载文件
			document=PDDocument.load(pdfFile);
			//用PDFTextStripper提取文件
			PDFTextStripper stripper=new PDFTextStripper();
			PrintWriter pw=new PrintWriter(new FileWriter(txt));
			stripper.writeText(document, pw);
			pw.close();
			System.out.println("成功写入文本文件"+txt);
		} catch (IOException e) {
			// TODO Auto-generated catch block
			System.out.println("文本写入失败");
			e.printStackTrace();
		}
		finally
		{
			if(document!=null)
			{try {
				document.close();
			} catch (IOException e) {
				// TODO Auto-generated catch block
				e.printStackTrace();
			}}
				
		}
				
		
	}
	
	
	public static void main(String[] args) {
		// TODO Auto-generated method stub
		String s=getText("G:/学习资料/软件大赛学习资料/网上淘宝.pdf ");
		System.out.println(s);
		 toTextFile("G:/学习资料/软件大赛学习资料/网上淘宝.pdf ","G:/Lucene/PDF.txt");

	}

}

你可能感兴趣的:(解析pdf文档 (lucene3.5))