java 讀取PDF文件 工具類

package com.test;

import java.awt.Rectangle;
import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.encryption.InvalidPasswordException;
import org.apache.pdfbox.text.PDFTextStripperByArea;

public class PDFUtils {
	
	public static Map<String ,Object> readPdf(File file){
		Map<String ,Object> map=new HashMap<>();
		List<String> pdfLines=new ArrayList<>();
	try {
		PDDocument document = PDDocument.load(file);
		int pages = document.getNumberOfPages();
		//自己劃定區間，將文件內容全部包含在內
		Rectangle rectBase = new Rectangle(0, 0, 682, 800);
		for (int i = 0; i < pages; i++) {
			PDPage page = document.getPage(i);
			PDFTextStripperByArea stripper;
			stripper = new PDFTextStripperByArea();
			stripper.setSortByPosition(true);
			stripper.addRegion("base", rectBase);
			stripper.extractRegions(page);
			//獲取每一頁的數據信息
			String lines = stripper.getTextForRegion("base");
			pdfLines.add(lines);
		}
		
		map.put("ok", true);
		map.put("pdfLines", pdfLines);
	} catch (InvalidPasswordException e) {
		e.printStackTrace();
	} catch (IOException e) {
		e.printStackTrace();
	}finally {
		return map;
	}
	
	}
	
	public static void main(String[] args) {
		//File file = new File("resource/12345.pdf");
		File file = new File("d:/12345.pdf");
		Map<String, Object> readPdf = readPdf(file);
		if((boolean) readPdf.get("ok")){
			List<String> pdfLines = (List)readPdf.get("pdfLines");
			for (String object : pdfLines) {
				/**
				 * 將該頁信息進行切割
				 * 因爲在Linux上面使用\r容易出現問題(下標越界比較多)。小心使用
				 */
				//String[] line = object.split("\r\n");
				String[] line = object.split("\\n");
				for (String string : line) {
					System.out.println(string);
				}
			}
		}
	}
	
	
	
}

        jar包下載鏈接鏈接：https://pan.baidu.com/s/1GdEAtYGK0b9qgx_SvuegGA 密碼：evmt

        以及關於本地解析成功，但是Linux上面報錯，，可以參考系統\r\n問題