itextpdf获取PDFXY----spire.pdf获取XY_itextpdf根据坐标获取pdf内容

本文章记录itextpdf5.3.2获取PDF对应坐标XY，以及spire3.11.6获取pdf对应XY样例代码----------------------

本文记录得两个jar包分别是：itextpdf

 <dependency>
      <groupId>com.itextpdf</groupId>
      <artifactId>itextpdf</artifactId>
      <version>5.3.2</version>
</dependency>

import com.itextpdf.awt.geom.Rectangle2D;
import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.parser.PdfReaderContentParser;
import java.io.IOException;
import java.util.List;
import java.util.Map;
public class pdfTest {
 
    public static void main(String[] args) {
        try {
            PdfReader reader = new PdfReader("C:\\Users\\T440P\\Desktop\\DHF文档.pdf");
            //新建一个PDF解析对象
            PdfReaderContentParser parser = new PdfReaderContentParser(reader);
                //包含了PDF页面的信息，作为处理的对象
//PdfStamper stamper = new PdfStamper(reader, new FileOutputStream("d:/test.pdf"));
            for (int i=1; i<reader.getNumberOfPages(); i++){
                //新建一个ImageRenderListener对象，该对象实现了RenderListener接口，作为处理PDF的主要类
                TestRenderListener listener = new TestRenderListener();
                //解析PDF，并处理里面的文字
                parser.processContent(i, listener);
                //获取文字的矩形边框
                List<Rectangle2D.Float> rectText = listener.rectText;
                List<String> textList = listener.textList;
                List<Float> listY = listener.listY;
                List<Map<String, Rectangle2D.Float>> list_text = listener.rows_text_rect;
                for(int k = 0;k < list_text.size();k++){
                    Map<String,Rectangle2D.Float> map = list_text.get(k);
                    System.out.println(">>>map"+map);
                }
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
 
}

 
 
import com.itextpdf.awt.geom.Rectangle2D;
import com.itextpdf.awt.geom.RectangularShape;
import com.itextpdf.text.pdf.parser.ImageRenderInfo;
import com.itextpdf.text.pdf.parser.RenderListener;
import com.itextpdf.text.pdf.parser.TextRenderInfo;
 
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
public class TestRenderListener implements RenderListener {
    //用来存放文字的矩形
    List<Rectangle2D.Float> rectText = new ArrayList<Rectangle2D.Float>();
    //用来存放文字
    List<String> textList = new ArrayList<String>();
    //用来存放文字的y坐标
    List<Float> listY = new ArrayList<Float>();
    //用来存放每一行文字的坐标位置
    List<Map<String,Rectangle2D.Float>> rows_text_rect = new ArrayList<>();
    //PDF文件的路径
    protected String filepath = null;
    public TestRenderListener() {
    }
 
    //step 2,遇到"BT"执行
    @Override
    public void beginTextBlock() {
        // TODO Auto-generated method stub
    }
 
    //step 3
    /**
     * 文字主要处理方法
     */
    @Override
    public void renderText(TextRenderInfo renderInfo) {
        //获取文字的下面的矩形
        //Rectangle2D.Float rectBase = renderInfo.getBaseline().getBoundingRectange();
 
 
        String text = renderInfo.getText();
        if(text.length() > 0){
            RectangularShape rectBase = renderInfo.getBaseline().getBoundingRectange();
//            获取文字下面的矩形
            Rectangle2D.Float rectAscen = renderInfo.getAscentLine().getBoundingRectange();
//            计算出文字的边框矩形
            float leftX = (float) rectBase.getMinX();
            float leftY = (float) rectBase.getMinY()-1;
            float rightX = (float) rectAscen.getMaxX();
            float rightY = (float) rectAscen.getMaxY()+1;
 
            Rectangle2D.Float rect = new Rectangle2D.Float(leftX, leftY, rightX - leftX, rightY - leftY);
 
            System.out.println("text:"+text+"--x:"+rect.x + "--y:"+rect.y + "--width:"+rect.width + "--height:"+rect.height);
 
            if(listY.contains(rect.y)){
                int index = listY.indexOf(rect.y);
                float tempx = rect.x > rectText.get(index).x ? rectText.get(index).x : rect.x;
                rectText.set(index,new Rectangle2D.Float(tempx,rect.y,rect.width + rectText.get(index).width,rect.height));
                textList.set(index,textList.get(index) + text);
            }else{
                rectText.add(rect);
                textList.add(text);
                listY.add(rect.y);
            }
 
            Map<String,Rectangle2D.Float> map = new HashMap<>();
            map.put(text,rect);
            rows_text_rect.add(map);
        }
    }
    //step 4(最后执行的，只执行一次)，遇到“ET”执行
    @Override
    public void endTextBlock() {
        // TODO Auto-generated method stub
    }
 
    //step 1(图片处理方法)
    @Override
    public void renderImage(ImageRenderInfo renderInfo) {
        System.out.println(renderInfo.getStartPoint().length());
        System.out.println("测试");
    }
}

=====================================分隔符===============================

 spire能解决coredraw，AUTOCAD转出得PDF,CAD图纸转出得PDF。无法读取字眼以及对应XY

spire:

<repositories>
        <repository>
            <id>com.e-iceblue</id>
            <url>http://repo.e-iceblue.cn/repository/maven-public/</url>
        </repository>
 </repositories>
<dependencies>
    <dependency>
        <groupId> e-iceblue </groupId>
        <artifactId>spire.pdf</artifactId>
        <version>3.11.6</version>
    </dependency>
</dependencies>

public class pdfTest {   
    public static void main(String[] args) throws Exception {
        List<Map<String, Rectangle2D.Float>> list_text = getCroeXYForString("C:\\Users\\T440P\\Desktop\\test.pdf", 0);
 
        for(int k = 0;k < list_text.size();k++) {
            //需要匹配位置的String
            Map<String, Rectangle2D.Float> siteMap = list_text.get(k);
            System.out.println(">>>map"+siteMap);
 
        }
    }
 
    public static List<Map<String,Rectangle2D.Float>> getCroeXYForString(String filePath,int i) throws Exception {
        PdfDocument pdf = new PdfDocument(filePath);
        List<Map<String,Rectangle2D.Float>> mapList=new ArrayList<>();
        //遍历PDF文档中每页
        PdfPageBase page;
        page = pdf.getPages().get(i);
        double height = page.getSize().getHeight();
        //调用extractText()方法提取文本
        String s = page.extractText(true);
        System.out.println(">>>>page.extractText"+s);
        PdfTextFindCollection allText = page.findAllText();
        PdfTextFind[] findss = allText.getFinds();
 
        for(PdfTextFind find : findss) {
            //计算出文字的边框矩形
            float leftX = (float) find.getBounds().getMinX();
            float leftY = (float) (height-find.getBounds().getMinY())-1;
            float rightX = (float) find.getBounds().getMaxX();
            float rightY = (float) (height-find.getBounds().getMaxY())+1;
            Rectangle2D.Float rect = new Rectangle2D.Float(leftX, leftY, rightX - leftX, rightY - leftY);
            System.out.println(find.getMatchText());
            Map<String,Rectangle2D.Float> xyMap=new HashMap<>();
            String str = find.getMatchText();
//            String unicode = stringToUnicode(str);
//            System.out.println("字符串转unicode结果：" + unicode);
            xyMap.put(str,rect);
            mapList.add(xyMap);
        }
        pdf.close();
        return mapList;
    }
}