pdf 文本转换为 java 字符串

package org.bruce.toolkit.experiments;

import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.OutputStreamWriter;

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

/**
* @author Bruce Yang
* 将 pdf 文件中的字符解析为字符串中的字符~
*/
public class Pdf2Text {

/**
* @param args
* @throws Exception
*/
public static void main(String[] args) throws Exception {
//		System.out.println(parsePDF("/Users/user/Desktop/QT教程.pdf"));
System.out.println(parsePDF("/Users/user/Novels/pdf/《盗墓笔记》第一季：.第二部.怒海潜沙.pdf"));
}

/**
* @param filePath
* @return
* @throws Exception
*/
public static String parsePDF(String filePath) throws Exception {
File file = new File(filePath);
String context = "";
ByteArrayOutputStream out = new ByteArrayOutputStream();
OutputStreamWriter writer = new OutputStreamWriter(out);
PDDocument pdfdocument = null;

pdfdocument = PDDocument.load(file);
PDFTextStripper stripper = new PDFTextStripper();
stripper.writeText(pdfdocument, writer);
byte[] contents = out.toByteArray();
System.out.println(contents.length);
context = new String(contents);

writer.close();
if (pdfdocument != null) {
pdfdocument.close();
}
return context;
}
}