Itext 读取pdf内容

引入jar

     
          com.itextpdf
          itextpdf
          5.5.13
      
      
      
          com.itextpdf
          itext-asian
          5.2.0
      

工具类：

import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.parser.PdfTextExtractor;

import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.io.Writer;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import java.util.logging.Level;
import java.util.logging.Logger;


public class PdfUtils {


  
  public static List extractTXTbyLine(String file) {
    List listArr = new ArrayList();
    try {
      PdfReader reader = new PdfReader(file);
      int pageNum = reader.getNumberOfPages(); // 获得页数
      for (int i = 1; i <= pageNum; i++) { // 只能从第1页开始读
        String textFromPageContent = PdfTextExtractor.getTextFromPage(reader, i);
        String[] splitArray = textFromPageContent.split("n");
        if (splitArray.length > 0) {
          listArr.addAll(Arrays.asList(splitArray));
        }
      }
    } catch (IOException ex) {
      Logger.getLogger(PdfUtils.class.getName()).log(Level.SEVERE, null, ex);
    }
    return listArr;
  }


  public static void main(String args[]) {
    String file = "F:\文档\test.pdf";
    long startTime = System.currentTimeMillis();
    List strings = extractTXTbyLine(file);
    for (String s : strings) {
      System.out.println(s);
    }
    long endTime = System.currentTimeMillis();
    System.out.println("读写所用时间为：" + (endTime - startTime) + "ms");
  }
}