java 提取 pdf 中的表格-凯发线上登陆下载网址

    
        com.e-iceblue
        https://repo.e-iceblue.cn/repository/maven-public/
    


    
        e-iceblue
        spire.pdf
        4.12.1
    

import com.spire.pdf.*;
import com.spire.pdf.utilities.pdftable;
import com.spire.pdf.utilities.pdftableextractor;
import java.io.filewriter;
import java.io.ioexception;
public class extracttable {
    public static void main(string[] args)throws ioexception {
        //实例化pdfdocument类的对象
        pdfdocument pdf = new pdfdocument();
        //加载pdf文档
        pdf.loadfromfile("test.pdf");
        //创建stringbuilder类的实例
        stringbuilder builder = new stringbuilder();
        //创建pdftableextractor类的对象
        pdftableextractor extractor = new pdftableextractor(pdf);
        //遍历每一页
        for (int page = 0; page < pdf.getpages().getcount(); page  )
        {
            //提取页面中的表格存入pdftable[]数组
            pdftable[] tablelists = extractor.extracttable(page);
            if (tablelists != null && tablelists.length > 0)
            {
                //遍历表格
                for (pdftable table : tablelists)
                {
                    int row = table.getrowcount();//获取表格行
                    int column = table.getcolumncount();//获取表格列
                    for (int i = 0; i < row; i  )
                    {
                        for (int j = 0; j < column; j  )
                        {
                            //获取表格中的文本内容
                            string text = table.gettext(i, j);
                            //将获取的text写入stringbuilder容器
                            builder.append(text " ");
                        }
                        builder.append("\r\n");
                    }
                }
            }
        }
        //保存为txt文档
        filewriter filewriter = new filewriter("extractedtable.txt");
        filewriter.write(builder.tostring());
        filewriter.flush();
        filewriter.close();
    }
}