[feat/OPS-341] 벨로그 크롤러 생성 (#90)

* feat/OPS-341 : Velog 크롤러 생성

* fix : createDate,modifyDate 자동 적용되도록 설정

Author: taekkong

src/main/java/org/tuna/zoopzoop/backend/BackendApplication.java

@@ -2,8 +2,10 @@
 
 import org.springframework.boot.SpringApplication;
 import org.springframework.boot.autoconfigure.SpringBootApplication;
+import org.springframework.data.jpa.repository.config.EnableJpaAuditing;
 
 @SpringBootApplication
+@EnableJpaAuditing
 public class BackendApplication {
     public static void main(String[] args) {
         SpringApplication.run(BackendApplication.class, args);

src/main/java/org/tuna/zoopzoop/backend/domain/datasource/crawler/dto/SpecificSiteDto.java

@@ -9,4 +9,14 @@ public record SpecificSiteDto(
         String imageUrl, // 썸네일 이미지 url
         String source // 출처
 ) {
+    @Override
+    public String toString() {
+        return "SpecificSiteDto {\n" +
+                "  title='" + title + "',\n" +
+                "  dataCreatedDate=" + dataCreatedDate + ",\n" +
+                "  content='" + content + "',\n" +
+                "  imageUrl='" + imageUrl + "',\n" +
+                "  source='" + source + "'\n" +
+                "}";
+    }
 }

src/main/java/org/tuna/zoopzoop/backend/domain/datasource/crawler/service/SupportedDomain.java

@@ -2,7 +2,8 @@
 
 public enum SupportedDomain {
     NAVERNEWS("n.news.naver.com"),
-    NAVERBLOG("blog.naver.com");
+    NAVERBLOG("blog.naver.com"),
+    VELOG("velog.io");
 
     private final String domain;
 

src/main/java/org/tuna/zoopzoop/backend/domain/datasource/crawler/service/VelogCrawler.java

@@ -0,0 +1,62 @@
+package org.tuna.zoopzoop.backend.domain.datasource.crawler.service;
+
+import org.jsoup.nodes.Document;
+import org.springframework.stereotype.Component;
+import org.tuna.zoopzoop.backend.domain.datasource.crawler.dto.CrawlerResult;
+import org.tuna.zoopzoop.backend.domain.datasource.crawler.dto.SpecificSiteDto;
+
+import java.time.LocalDate;
+import java.time.format.DateTimeFormatter;
+
+@Component
+public class VelogCrawler implements Crawler{
+    private static final SupportedDomain DOMAIN = SupportedDomain.VELOG;
+    private static final DateTimeFormatter VELOG_FORMATTER = DateTimeFormatter.ofPattern("yyyy년 M월 d일");
+
+    @Override
+    public boolean supports(String domain) {
+        return domain.contains(DOMAIN.getDomain());
+    }
+
+    @Override
+    public CrawlerResult<?> extract(Document doc) {
+        // 제목
+        String title = doc.selectFirst("meta[property=og:title]").attr("content");
+
+        // 작성 날짜
+        String publishedAt = doc.selectFirst(
+                "div.information > span:not([class])"
+        ).text();
+
+        LocalDate dataCreatedDate = transLocalDate(publishedAt);
+
+        // 내용(ai한테 줘야함)
+        String content = doc.selectFirst("div.atom-one").text();
+
+        // 썸네일 이미지 url
+        String imageUrl = doc.selectFirst("meta[property=og:image]").attr("content");
+
+        // 출처
+        String source = doc.selectFirst("span.username > a").text();
+
+        return new CrawlerResult<>(
+                CrawlerResult.CrawlerType.SPECIFIC,
+                new SpecificSiteDto(title, dataCreatedDate, content, imageUrl, source)
+        );
+    }
+
+    @Override
+    public LocalDate transLocalDate(String rawDate) {
+
+        if(rawDate.contains("일 전")){
+            int daysAgo = Integer.parseInt(rawDate.split("일 전")[0].trim());
+            return LocalDate.now().minusDays(daysAgo);
+        }else if(rawDate.contains("방금 전")) {
+            return LocalDate.now();
+        }else if(rawDate.contains("시간 전")||rawDate.contains("분 전")){
+            return LocalDate.now();
+        }
+
+        return LocalDate.parse(rawDate, VELOG_FORMATTER);
+    }
+}

src/test/java/org/tuna/zoopzoop/backend/domain/datasource/crawler/service/VelogCrawlerTest.java

@@ -0,0 +1,25 @@
+package org.tuna.zoopzoop.backend.domain.datasource.crawler.service;
+
+import org.jsoup.Jsoup;
+import org.jsoup.nodes.Document;
+import org.junit.jupiter.api.Test;
+import org.tuna.zoopzoop.backend.domain.datasource.crawler.dto.CrawlerResult;
+
+import java.io.IOException;
+
+import static org.assertj.core.api.Assertions.assertThat;
+import static org.junit.jupiter.api.Assertions.*;
+
+class VelogCrawlerTest {
+
+    private final VelogCrawler velogCrawler = new VelogCrawler();
+
+    @Test
+    void testExtract() throws IOException {
+        Document doc = Jsoup.connect("https://velog.io/@hyeonnnnn/VampireSurvivorsClone-04.-PoolManager").get();
+        CrawlerResult<?> result = velogCrawler.extract(doc);
+        assertThat(result).isNotNull();
+
+        System.out.println(result);
+    }
+}