关于使用itextpdf7提取pdf文件中指定关键字内容的坐标位置

参考文章和资料

老梁 - https://cloud.tencent.com/developer/article/1502408
微光•无单位 - https://blog.csdn.net/LvWeijie941/article/details/105248627/
官方api - https://api.itextpdf.com/iText7/java/7.0.5/

前言

具体版本为itexpdf7.0.4，使用Maven项目管理依赖
主要使用jar包： kernel-7.0.4.jar

转载请注明出处

配置

为所有Maven项目配置远程仓库m2/settings.xml

 
m2
    
        
            alimaven
            aliyun maven
            http://maven.aliyun.com/nexus/content/groups/public/
            central
        
    
  
    
       nexus 
        
            
                nexus
                local private nexus
                http://maven.oschina.net/content/groups/public/
                
                    true
                
                
                    false
                
            
        
        
        
            
            nexus
            local private nexus
            http://maven.oschina.net/content/groups/public/
            
                true
            
            
                false
            
            
        
    

 

具体项目通过pom.xml文件配置依赖(通过远程仓库自动在线下载依赖，即可无须手动下载jar包)

<dependencies>
	<dependency>
            <groupId>com.itextpdf</groupId>
            <artifactId>kernel</artifactId>
            <version>7.0.4</version>
	</dependency>
</dependencies>

具体运行代码

import com.itextpdf.kernel.geom.Rectangle;
import com.itextpdf.kernel.pdf.PdfDocument;
import com.itextpdf.kernel.pdf.PdfReader;
import com.itextpdf.kernel.pdf.canvas.parser.PdfDocumentContentParser;
import com.itextpdf.kernel.pdf.canvas.parser.listener.IPdfTextLocation;
import com.itextpdf.kernel.pdf.canvas.parser.listener.RegexBasedLocationExtractionStrategy;

import java.util.Collection;

public class test {
    public static void main(String args[]){
        String input = "target.pdf";
        //通过指定pdf文件名，指定关键字，和指定的pdf文件的待处理页数做参数
        getKeyWordsLocation(input, "presented", 46);
    }

    public static void getKeyWordsLocation(String input, String key, int pageNum){
        RegexBasedLocationExtractionStrategy strategy = new RegexBasedLocationExtractionStrategy(key);

        try{
        	//核心思路为对PdfDocument对象采用某种Strategy，这里使用RegexBasedLocationExtractionStrategy
            PdfReader pr = new PdfReader(input);
            PdfDocument pd = new PdfDocument(pr);
            PdfDocumentContentParser pdcp = new PdfDocumentContentParser(pd);

			//文本内容具体解析借助使用PdfDocumentContentParser类(实质使用PdfCanvasProcessor进行处理)， 对待处理页面装配合适策略
            RegexBasedLocationExtractionStrategy regexStrategy =
                    pdcp.processContent(pageNum, strategy);
			//获取处理结果
            Collection<IPdfTextLocation> resultantLocations = strategy.getResultantLocations();
            //自定义结果处理
            if (!resultantLocations.isEmpty()){
                for(IPdfTextLocation item: resultantLocations){
                    Rectangle boundRectangle = item.getRectangle();
                    System.out.println(item.getText());
                    System.out.println("["+key + "] location of x: " + boundRectangle.getX() + "  ,y: " + boundRectangle.getY());
                }
            }
            else {
                System.out.println("the result is null");
            }
            pr.close();
            pd.close();

        }catch (Exception e){
            System.err.println("read file failed!");
            e.printStackTrace();
        }
    }
}