fix: 벨로그 크롤러 예외 처리 추가 (HTML 요소 없을 시 빈 문자열, 작성일 없을 시 기본값)

Author: taekkong

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

@@ -7,6 +7,12 @@
 import java.time.LocalDate;
 
 public interface Crawler {
+
+    // 작성 일자가 null일 경우 기본값 설정
+    // LocalDate.EPOCH(1970-01-01  - 시간이 없는 값 표현할 때 사용되는 관용적 기준점)
+    // 이 값이 사용되면 작성 일자가 없는 것으로 간주
+    LocalDate DEFAULT_DATE = LocalDate.EPOCH;
+
     boolean supports(String domain);
     CrawlerResult<?> extract(Document doc) throws IOException;
     LocalDate transLocalDate(String rawDate);

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

@@ -1,6 +1,7 @@
 package org.tuna.zoopzoop.backend.domain.datasource.crawler.service;
 
 import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
 import org.springframework.core.Ordered;
 import org.springframework.core.annotation.Order;
 import org.springframework.stereotype.Component;
@@ -22,25 +23,28 @@ public boolean supports(String domain) {
     }
 
     @Override
-    public CrawlerResult<?> extract(Document doc) {
+    public CrawlerResult<SpecificSiteDto> extract(Document doc) {
         // 제목
-        String title = doc.selectFirst("meta[property=og:title]").attr("content");
+        Element titleElement = doc.selectFirst("meta[property=og:title]");
+        String title = titleElement != null ? titleElement.attr("content") : "";
 
         // 작성 날짜
-        String publishedAt = doc.selectFirst(
-                "div.information > span:not([class])"
-        ).text();
+        Element publishedAtElement = doc.selectFirst("div.information > span:not([class])");
+        String publishedAt = publishedAtElement != null ? publishedAtElement.text() : "";
 
-        LocalDate dataCreatedDate = transLocalDate(publishedAt);
+        LocalDate dataCreatedDate = publishedAt.isBlank() ? DEFAULT_DATE : transLocalDate(publishedAt) ;
 
         // 내용(ai한테 줘야함)
-        String content = doc.selectFirst("div.atom-one").text();
+        Element contentElement = doc.selectFirst("div.atom-one");
+        String content = contentElement != null ? contentElement.text() : "";
 
         // 썸네일 이미지 url
-        String imageUrl = doc.selectFirst("meta[property=og:image]").attr("content");
+        Element imageUrlElement = doc.selectFirst("meta[property=og:image]");
+        String imageUrl = imageUrlElement != null ? imageUrlElement.attr("content") : "";
 
         // 출처
-        String source = doc.selectFirst("span.username > a").text();
+        Element sourceElement = doc.selectFirst("span.username > a");
+        String source = sourceElement != null ? sourceElement.text() : "";
 
         return new CrawlerResult<>(
                 CrawlerResult.CrawlerType.SPECIFIC,
@@ -60,7 +64,6 @@ public LocalDate transLocalDate(String rawDate) {
             return LocalDate.now().minusDays(1);
         }
 
-
         return LocalDate.parse(rawDate, VELOG_FORMATTER);
     }
 }

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

@@ -2,10 +2,13 @@
 
 import org.jsoup.Jsoup;
 import org.jsoup.nodes.Document;
+import org.junit.jupiter.api.DisplayName;
 import org.junit.jupiter.api.Test;
 import org.tuna.zoopzoop.backend.domain.datasource.crawler.dto.CrawlerResult;
+import org.tuna.zoopzoop.backend.domain.datasource.crawler.dto.SpecificSiteDto;
 
 import java.io.IOException;
+import java.time.LocalDate;
 
 import static org.assertj.core.api.AssertionsForClassTypes.assertThat;
 
@@ -14,11 +17,27 @@ class VelogCrawlerTest {
     private final VelogCrawler velogCrawler = new VelogCrawler();
 
     @Test
+    @DisplayName("Velog 크롤러 작동 테스트")
     void testExtract() throws IOException {
         Document doc = Jsoup.connect("https://velog.io/@imcute0703123/%EC%BA%A0%ED%8D%BC%EC%8A%A4%EC%8B%9C%EA%B7%B8%EB%84%90-2025-%EB%B0%B1%EC%84%9D%EC%97%B0%ED%99%94-1%EB%93%B1-%EB%B6%80%EC%8A%A4-%EB%9F%AC%EB%B8%8C%EB%9D%BC%EC%9D%B8-%EB%A7%A4%EC%B9%AD-%EC%84%9C%EB%B9%84%EC%8A%A4-%ED%9A%8C%EA%B3%A0%EB%A1%9D").get();
         CrawlerResult<?> result = velogCrawler.extract(doc);
         assertThat(result).isNotNull();
 
         System.out.println(result);
     }
+
+    @Test
+    @DisplayName("Velog 크롤러 예외처리 테스트")
+    void testExtractException() throws IOException {
+        String html = "<html><head></head><body></body></html>";
+        Document doc = Jsoup.parse(html);
+
+        SpecificSiteDto result = velogCrawler.extract(doc).data();
+
+        assertThat(result.title()).isEmpty();
+        assertThat(result.content()).isEmpty();
+        assertThat(result.imageUrl()).isEmpty();
+        assertThat(result.source()).isEmpty();
+        assertThat(result.dataCreatedDate()).isEqualTo(LocalDate.EPOCH);
+    }
 }