Question

我在研究论文中对参考论文进行排名，我从谷歌学者那里下载了这些论文，并将这些pdf文件转换为（.txt）。现在我想提取标题为Abstract的段落。我编写了代码，但问题是它提取整个文档。请仔细看看代码，并指导我。！

    PDFManager pdfManager = new PDFManager();
           pdfManager.setFilePath("D:\\paper.pdf");
           //System.out.println(pdfManager.ToText());

        PrintWriter outputfile = new PrintWriter("D:\\test.txt");
        outputfile.print(pdfManager.ToText());
        outputfile.close(); 


  try{

      FileInputStream fstream = new FileInputStream("D:\\test.txt");

      DataInputStream in = new DataInputStream(fstream);
      BufferedReader br = new BufferedReader(new InputStreamReader(in));
      String strLine;

      while ((strLine = br.readLine()) != null)   {

      System.out.println (strLine);
      }

      in.close();
        }catch (Exception e){
      System.err.println("Error: " + e.getMessage());
      }
      }
    }

这是我的pdfManager.class

package pdftext;

import java.io.File;
import java.io.IOException;
import org.apache.pdfbox.cos.COSDocument;
import org.apache.pdfbox.io.RandomAccessFile;
import org.apache.pdfbox.pdfparser.PDFParser;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;

public class PDFManager {

   private PDFParser parser;
   private PDFTextStripper pdfStripper;
   private PDDocument pdDoc ;
   private COSDocument cosDoc ;

   private String Text ;
   private String filePath;
   private File file;

    public PDFManager() {

    }
   public String ToText() throws IOException
   {
       this.pdfStripper = null;
       this.pdDoc = null;
       this.cosDoc = null;

       file = new File("D:\\information.pdf");
       parser = new PDFParser(new RandomAccessFile(file,"r")); // update for PDFBox V 2.0

       parser.parse();
       cosDoc = parser.getDocument();
       pdfStripper = new PDFTextStripper();
       pdDoc = new PDDocument(cosDoc);
       pdDoc.getNumberOfPages();
       pdfStripper.setStartPage(1);
       pdfStripper.setEndPage(10);

       // reading text from page 1 to 10
       // if you want to get text from full pdf file use this code
       // pdfStripper.setEndPage(pdDoc.getNumberOfPages());

       Text = pdfStripper.getText(pdDoc);
       return Text;
   }

    public void setFilePath(String filePath) {
        this.filePath = filePath;
    }

}

Answer 1

File fileName = new File("D:\\testa.txt");
    try {
        String startToken = "Abstract";
        String endToken = "1";

        boolean output = false;

        Scanner scan = new Scanner(fileName);
        while (scan.hasNextLine()) {
            String line = scan.nextLine();
            if (!output && line.indexOf(startToken) > -1) {
                output = true;
                line = line.substring(line.indexOf(startToken)+startToken.length());
            } else if (output && line.indexOf(endToken) > -1) {
                output = false;
                System.out.println(line.substring(0, line.indexOf(endToken)));
            }

            if (output) {
                System.out.println(line);
            }
        }
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    }
}

我终于设法使用扫描，开始令牌和结束令牌......！

从研究出版物中提取摘要（.txt）

1 个答案: