[#27] Feat: 백준 문제 크롤링 및 DB 저장

build.gradle

@@ -38,6 +38,8 @@ dependencies {
 	testImplementation 'org.springframework.security:spring-security-test'
 	testRuntimeOnly 'org.junit.platform:junit-platform-launcher'
 	implementation 'org.springframework.boot:spring-boot-starter-webflux'
+	implementation 'org.jsoup:jsoup:1.15.3'
+	implementation group: 'com.googlecode.json-simple', name: 'json-simple', version: '1.1.1'
 
 	// Swagger API
 	implementation("org.springdoc:springdoc-openapi-starter-webmvc-ui:2.0.2")

src/main/java/com/sajang/devracebackend/domain/Problem.java

@@ -2,6 +2,7 @@
 
 import com.sajang.devracebackend.domain.common.BaseEntity;
 import jakarta.persistence.*;
+import lombok.Builder;
 import lombok.Getter;
 import lombok.NoArgsConstructor;
 
@@ -20,7 +21,7 @@ public class Problem extends BaseEntity implements Serializable {
     private Long id;
 
     @Column(name = "number", unique = true)
-    private Integer number;
+    private Integer number; //백준 문제번호
 
     private String title;
 
@@ -45,4 +46,18 @@ public class Problem extends BaseEntity implements Serializable {
     @Column(name = "sample_output")
     private String sampleOutput;  // 예제 출력
 
+
+    @Builder
+    public Problem(Long id, Integer number, String title, String content, String imageUrl, String problemInput, String problemOutput, String problemLimit, String sampleInput, String sampleOutput) {
+        this.id = id;
+        this.number = number;
+        this.title = title;
+        this.content = content;
+        this.imageUrl = imageUrl;
+        this.problemInput = problemInput;
+        this.problemOutput = problemOutput;
+        this.problemLimit = problemLimit;
+        this.sampleInput = sampleInput;
+        this.sampleOutput = sampleOutput;
+    }
 }

src/main/java/com/sajang/devracebackend/dto/problem/ProblemDto.java

@@ -0,0 +1,58 @@
+package com.sajang.devracebackend.dto.problem;
+
+import com.sajang.devracebackend.domain.Problem;
+import lombok.Builder;
+import lombok.Getter;
+import lombok.NoArgsConstructor;
+
+@Getter
+@NoArgsConstructor
+public class ProblemDto {
+
+    private String title;
+    private String content;
+    private String imageUrl;
+    private String problemInput;
+    private String problemOutput;
+    private String problemLimit;
+    private String sampleInput;
+    private String sampleOutput;
+    private Integer number;
+
+    @Builder
+    public ProblemDto(String imageUrl, String title, Integer number,String content, String problemInput, String problemOutput, String problemLimit, String sampleInput, String sampleOutput){
+        this.imageUrl = imageUrl;
+        this.title = title;
+        this.number = number;
+        this.content =content;
+        this.problemInput = problemInput;
+        this.problemOutput = problemOutput;
+        this.problemLimit = problemLimit;
+        this.sampleInput = sampleInput;
+        this.sampleOutput = sampleOutput;
+    }
+    public Problem toEntity(){
+        return Problem.builder()
+                .imageUrl(imageUrl)
+                .title(title)
+                .number(number)
+                .content(content)
+                .problemInput(problemInput)
+                .problemOutput(problemOutput)
+                .problemLimit(problemLimit)
+                .sampleInput(sampleInput)
+                .sampleOutput(sampleOutput)
+                .build();
+    }
+    public ProblemDto(Problem problem){
+        this.number = problem.getNumber();
+        this.imageUrl = problem.getImageUrl();
+        this.title = problem.getTitle();
+        this.content = problem.getContent();
+        this.problemInput = problem.getProblemInput();
+        this.problemOutput = problem.getProblemOutput();
+        this.problemLimit = problem.getProblemLimit();
+        this.sampleInput = problem.getSampleInput();
+        this.sampleOutput = problem.getSampleOutput();
+    }
+}

src/main/java/com/sajang/devracebackend/service/ProblemService.java

@@ -1,4 +1,7 @@
 package com.sajang.devracebackend.service;
 
+import com.sajang.devracebackend.dto.problem.ProblemDto;
+
 public interface ProblemService {
+    //ProblemDto crawlProblem(Integer problemNumber);
 }

src/main/java/com/sajang/devracebackend/service/impl/ProblemServiceImpl.java

@@ -1,13 +1,76 @@
 package com.sajang.devracebackend.service.impl;
 
+import com.sajang.devracebackend.domain.Problem;
+import com.sajang.devracebackend.dto.problem.ProblemDto;
 import com.sajang.devracebackend.repository.ProblemRepository;
 import com.sajang.devracebackend.service.ProblemService;
 import lombok.RequiredArgsConstructor;
+import org.json.simple.JSONObject;
 import org.springframework.stereotype.Service;
+import org.jsoup.Jsoup;
+import org.jsoup.nodes.Document;
+
+import org.jsoup.select.Elements;
+import org.springframework.transaction.annotation.Transactional;
+
+import java.io.IOException;
 
 @Service
 @RequiredArgsConstructor
 public class ProblemServiceImpl implements ProblemService {
 
     private final ProblemRepository problemRepository;
+
+    @Transactional
+    //@Override
+    public ProblemDto crawlProblem(Integer problemNumber) throws IOException{
+        String Url = "https://www.acmicpc.net/problem/" + problemNumber;
+        Document doc = Jsoup.connect(Url).get();
+
+        //#problem-body에 접근
+        Elements contents = doc.select("#problem-body");         //body에 접근
+        Elements contentHead = doc.select(".page-header h1");          //문제 title 추출을 위한 page-header에 접근
+        Elements sampleDataElement = doc.getElementsByClass("col-md-6");   //예제 문제쪽 요소에 따로 접근
+
+        int  Amount = sampleDataElement.size();        //예제 문제 개수 추출
+
+        JSONObject sampleInputJson = new JSONObject();
+        JSONObject sampleOutputJson = new JSONObject();
+        for(int i =1;i<=Amount/2;i++){
+            sampleInputJson.put("sampleInput"+i,contents.select(".col-md-6 #sample-input-"+i).text()); //예제객체 담기
+            sampleOutputJson.put("sampleOutput"+i,contents.select(".col-md-6 #sample-output-"+i).text()); //예제객체 담기
+        }
+
+        String sampleInput = sampleInputJson.toString(); //Json -> String
+        String sampleOutput = sampleOutputJson.toString(); //Json -> String
+
+        String problemTitle = contentHead.select("#problem_title").text();      //title 은 따로 접근. body가 아닌 header 부분
+        ProblemDto data = ProblemDto.builder()                                        //Builder를 이용해 ProblemDto 값으로 저장
+                .imageUrl(contents.select("p img").attr("abs:src"))
+                .number(problemNumber)
+                .title(problemTitle)
+                .content(contents.select("#problem_description").toString())
+                .problemInput(contents.select("#problem_input").toString())
+                .problemOutput(contents.select("#problem_output").toString())
+                .problemLimit(contents.select("#problem_limit").toString())
+                .sampleInput(sampleInput)
+                .sampleOutput(sampleOutput)
+                .build();
+
+        ProblemDto problemDto = new ProblemDto(
+                data.getImageUrl(),
+                data.getTitle(),
+                data.getNumber(),
+                data.getContent(),
+                data.getProblemInput(),
+                data.getProblemOutput(),
+                data.getProblemLimit(),
+                data.getSampleInput(),
+                data.getSampleOutput()
+        );
+
+        Problem problemEntity = problemRepository.save(problemDto.toEntity());
+
+        return new ProblemDto(problemEntity);
+    }
 }