fix(anime): 파이프라인 5건 수정 — 에피소드 정규식(v2/S01E), 릴리스 그룹 필터, 자막 보호, 배치 다운로드, 타임아웃

tools/anissia_client.py

@@ -110,11 +110,102 @@ class AnissiaClient:
         ]
 
     async def search_anime(self, keyword: str) -> list[AnimeInfo]:
-        """키워드로 전체 편성표에서 검색 (한글/일어 제목 매칭)."""
+        """키워드로 전체 편성표에서 검색 (한글/일어/영문 fuzzy 매칭)."""
+        import re as _re
+
         all_anime = await self.get_all_schedule()
         keyword_lower = keyword.lower()
-        return [
-            a for a in all_anime
-            if keyword_lower in a.subject.lower()
-            or keyword_lower in a.original_subject.lower()
-        ]
+        # 특수문자 제거 버전 (따옴표, 괄호 등)
+        keyword_norm = _re.sub(r'[^\w\s]', '', keyword_lower)
+
+        try:
+            from tools.title_matcher import japanese_to_romaji, title_similarity
+            use_romaji = True
+        except ImportError:
+            use_romaji = False
+
+        results = []
+        fuzzy_candidates = []
+
+        for a in all_anime:
+            subj_lower = a.subject.lower()
+            orig_lower = a.original_subject.lower()
+            # 특수문자 제거 버전
+            subj_norm = _re.sub(r'[^\w\s]', '', subj_lower)
+            orig_norm = _re.sub(r'[^\w\s]', '', orig_lower)
+
+            # 1차: substring 매칭 (원본 + 정규화)
+            if (keyword_lower in subj_lower or keyword_norm in subj_norm):
+                results.append(a)
+            elif (keyword_lower in orig_lower or keyword_norm in orig_norm):
+                results.append(a)
+            elif use_romaji:
+                romaji = japanese_to_romaji(a.original_subject).lower()
+                # 2차: romaji substring
+                if keyword_lower in romaji:
+                    results.append(a)
+                else:
+                    # 3차: 단어 단위 fuzzy — 검색어와 romaji 개별 단어 비교
+                    words = romaji.split()
+                    best_word_sim = max(
+                        (title_similarity(keyword, w) for w in words),
+                        default=0.0,
+                    )
+                    # 전체 문자열 유사도도 참고
+                    full_sim = title_similarity(keyword, romaji)
+                    best_sim = max(best_word_sim, full_sim)
+                    if best_sim >= 0.6:
+                        fuzzy_candidates.append((best_sim, a))
+
+        # exact 결과가 없을 때만 fuzzy 결과 사용
+        if not results and fuzzy_candidates:
+            fuzzy_candidates.sort(key=lambda x: x[0], reverse=True)
+            results = [a for _, a in fuzzy_candidates[:10]]
+
+        return results
+
+
+# ── CLI 진입점 ──
+if __name__ == "__main__":
+    import sys
+    import asyncio
+
+    client = AnissiaClient()
+    args = sys.argv[1:]
+
+    async def main():
+        if not args:
+            print("사용법: python tools/anissia_client.py [schedule|search|captions] [인자]")
+            return
+
+        if args[0] == "schedule":
+            # python tools/anissia_client.py schedule 3  (수요일)
+            week = int(args[1]) if len(args) > 1 else 0
+            anime_list = await client.get_schedule(week)
+            day = WEEK_NAMES.get(week, "?")
+            print(f"📺 {day}요일 편성표 ({len(anime_list)}개):")
+            for a in anime_list:
+                cap = f"자막 {a.caption_count}명" if a.caption_count else "자막 없음"
+                print(f"  {a.time} {a.subject} ({a.original_subject}) [{cap}]")
+
+        elif args[0] == "search" and len(args) > 1:
+            # python tools/anissia_client.py search "프리렌"
+            keyword = " ".join(args[1:])
+            results = await client.search_anime(keyword)
+            print(f"🔍 '{keyword}' 검색 결과 ({len(results)}개):")
+            for a in results:
+                print(f"  [{a.anime_no}] {a.subject} ({a.original_subject}) | {WEEK_NAMES.get(a.week, '?')} {a.time}")
+
+        elif args[0] == "captions" and len(args) > 1:
+            # python tools/anissia_client.py captions 12345
+            anime_no = int(args[1])
+            captions = await client.get_captions(anime_no)
+            print(f"📝 자막 목록 ({len(captions)}건):")
+            for c in captions:
+                print(f"  {c.episode}화 | {c.name} | {c.website} | {c.updated}")
+
+        else:
+            print("사용법: python tools/anissia_client.py [schedule|search|captions] [인자]")
+
+    asyncio.run(main())
+