import com.spire.pdf.*;
import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
public class ExtractText {
  public static void main(String[]args) throws Exception {
    //加載測試文檔
    PdfDocument pdf = new PdfDocument("sample.pdf");
    //實例化StringBuilder類
    StringBuilder sb = new StringBuilder();
    //定義一個int型變量
    int index = 0;
    //遍歷PDF文檔中每頁
    PdfPageBase page;
    for (int i= 0; i<pdf.getPages().getCount();i++) {
      page = pdf.getPages().get(i);
      //調用extractText()方法提取文本
      sb.append(page.extractText(true));
      FileWriter writer;
      try {
        //將StringBuilder對象中的文本寫入到txt
        writer = new FileWriter("ExtractText.txt");
        writer.write(sb.toString());
        writer.flush();
      } catch (IOException e) {
        e.printStackTrace();
      }
      //調用extractImages方法獲取圖片
      for (BufferedImage image : page.extractImages()) {
          //指定輸出圖片名，指定圖片格式
          File output = new File(String.format("Image_%d.png", index++));
          ImageIO.write(image, "PNG", output);
      }
    }
    pdf.close();
  }
}