refactor: Crawler 성인 도서 오류 처리 (#115)

jisung-in · Jun 7, 2024 · b93856a · b93856a
1 parent b3bc7ff
commit b93856a
Show file tree

Hide file tree

Showing 5 changed files with 36 additions and 19 deletions.
diff --git a/.../jisungin/infra/crawler/CrawlingBook.java → ...m/jisungin/infra/crawler/CrawledBook.java b/.../jisungin/infra/crawler/CrawlingBook.java → ...m/jisungin/infra/crawler/CrawledBook.java
@@ -4,9 +4,12 @@
 import java.time.LocalDateTime;
 import lombok.Builder;
 import lombok.Getter;
+import lombok.NoArgsConstructor;
+import net.minidev.json.annotate.JsonIgnore;
 
 @Getter
-public class CrawlingBook {
+@NoArgsConstructor
+public class CrawledBook {
 
     private String title;
     private String content;
@@ -18,8 +21,8 @@ public class CrawlingBook {
     private LocalDateTime dateTime;
 
     @Builder
-    private CrawlingBook(String title, String content, String isbn, String publisher, String imageUrl, String thumbnail,
-                         String authors, LocalDateTime dateTime) {
+    private CrawledBook(String title, String content, String isbn, String publisher, String imageUrl, String thumbnail,
+                        String authors, LocalDateTime dateTime) {
         this.title = title;
         this.content = content;
         this.isbn = isbn;
@@ -30,9 +33,9 @@ private CrawlingBook(String title, String content, String isbn, String publisher
         this.dateTime = dateTime;
     }
 
-    public static CrawlingBook of(String title, String content, String isbn, String publisher, String imageUrl,
-                                  String thumbnail, String authors, LocalDateTime dateTime) {
-        return CrawlingBook.builder()
+    public static CrawledBook of(String title, String content, String isbn, String publisher, String imageUrl,
+                                 String thumbnail, String authors, LocalDateTime dateTime) {
+        return CrawledBook.builder()
                 .title(title)
                 .content(content)
                 .isbn(isbn)
@@ -57,6 +60,10 @@ public BookCreateServiceRequest toServiceRequest() {
                 .build();
     }
 
+    public boolean isBlankIsbn() {
+        return isbn == null || isbn.isBlank();
+    }
+
     private String[] convertAuthorsToArr(String authors) {
         return authors.split(" 저| 공저| 글| 편저| 원저| 기획|&")[0].split(",");
     }

diff --git a/src/main/java/com/jisungin/infra/crawler/Crawler.java b/src/main/java/com/jisungin/infra/crawler/Crawler.java
@@ -4,7 +4,7 @@
 
 public interface Crawler {
 
-    CrawlingBook crawlBook(String isbn);
-    Map<Long, CrawlingBook> crawlBestSellerBook();
+    CrawledBook crawlBook(String isbn);
+    Map<Long, CrawledBook> crawlBestSellerBook();
 
 }
diff --git a/src/main/java/com/jisungin/infra/crawler/Parser.java b/src/main/java/com/jisungin/infra/crawler/Parser.java
@@ -6,7 +6,7 @@
 public interface Parser {
 
     String parseIsbn(Document doc);
-    CrawlingBook parseBook(Document doc);
+    CrawledBook parseBook(Document doc);
     Map<Long, String> parseBestSellerBookId(Document doc);
 
 }
diff --git a/src/main/java/com/jisungin/infra/crawler/Yes24Crawler.java b/src/main/java/com/jisungin/infra/crawler/Yes24Crawler.java
@@ -5,8 +5,10 @@
 import java.util.concurrent.CompletableFuture;
 import java.util.concurrent.ConcurrentHashMap;
 import lombok.RequiredArgsConstructor;
+import lombok.extern.slf4j.Slf4j;
 import org.springframework.stereotype.Component;
 
+@Slf4j
 @Component
 @RequiredArgsConstructor
 public class Yes24Crawler implements Crawler {
@@ -15,26 +17,34 @@ public class Yes24Crawler implements Crawler {
     private final Parser parser;
 
     @Override
-    public CrawlingBook crawlBook(String isbn) {
+    public CrawledBook crawlBook(String isbn) {
         String bookId = parser.parseIsbn(fetcher.fetchIsbn(isbn));
 
         return parser.parseBook(fetcher.fetchBook(bookId));
     }
 
     @Override
-    public Map<Long, CrawlingBook> crawlBestSellerBook() {
-        Map<Long, String> bestSellerBookIds = parser.parseBestSellerBookId(fetcher.fetchBestSellerBookId());
-        Map<Long, CrawlingBook> bestSellerBooks = new ConcurrentHashMap<>();
+    public Map<Long, CrawledBook> crawlBestSellerBook() {
+        Map<Long, String> crawledBookIds = parser.parseBestSellerBookId(fetcher.fetchBestSellerBookId());
+        Map<Long, CrawledBook> crawledBookMap = new ConcurrentHashMap<>();
 
-        List<CompletableFuture<Void>> futures = bestSellerBookIds.entrySet().stream()
+        List<CompletableFuture<Void>> futures = crawledBookIds.entrySet().stream()
                 .map(entry -> CompletableFuture.supplyAsync(() -> parser.parseBook(fetcher.fetchBook(entry.getValue())))
-                        .thenAccept(crawlingBook -> bestSellerBooks.put(entry.getKey(), crawlingBook))
-                        .exceptionally(throwable -> null))
+                        .thenAccept(crawledBook -> {
+                            if (!crawledBook.isBlankIsbn()) {
+                                crawledBookMap.put(entry.getKey(), crawledBook);
+                            }
+                        })
+                        .exceptionally(throwable -> {
+                            log.warn("[WARN] 19세 이상 도서는 조회할 수 없습니다.");
+
+                            return null;
+                        }))
                 .toList();
 
         CompletableFuture.allOf(futures.toArray(CompletableFuture[]::new)).join();
 
-        return bestSellerBooks;
+        return crawledBookMap;
     }
 
 }
diff --git a/src/main/java/com/jisungin/infra/crawler/Yes24Parser.java b/src/main/java/com/jisungin/infra/crawler/Yes24Parser.java
@@ -35,7 +35,7 @@ public String parseIsbn(Document doc) {
     }
 
     @Override
-    public CrawlingBook parseBook(Document doc) {
+    public CrawledBook parseBook(Document doc) {
         String json = doc.select(bookJsonCss).html();
 
         String title = parseJsonToString(json, "$.name");
@@ -47,7 +47,7 @@ public CrawlingBook parseBook(Document doc) {
         String content = Jsoup.clean(doc.select(bookContentCss).text(), Safelist.none());
         LocalDateTime dateTime = parseDate(parseJsonToString(json, "$.workExample[0].datePublished"));
 
-        return CrawlingBook.of(title, content, isbn, publisher, imageUrl, thumbnail, authors, dateTime);
+        return CrawledBook.of(title, content, isbn, publisher, imageUrl, thumbnail, authors, dateTime);
     }
 
     @Override