Anilist extractor added

modules/anime_etl/sources/anilist_async_client.py

@@ -0,0 +1,46 @@
+import httpx
+import asyncio
+from rate_limiter import ANILIST_RATE_LIMITER
+
+URL = "https://graphql.anilist.co"
+
+QUERY = """
+query ($search: String, $season: MediaSeason, $seasonYear: Int, $format: MediaFormat, $page: Int, $perPage: Int) {
+  Page(page: $page, perPage: $perPage) {
+    media(search: $search, type: ANIME, season: $season, seasonYear: $seasonYear, format: $format) {
+      id
+      title { romaji english native }
+      status
+      season
+      seasonYear
+      # seasonNumber
+      episodes
+      duration
+      popularity
+      averageScore
+      coverImage { extraLarge large }
+      genres
+      studios(isMain: true) { nodes { id name } }
+      nextAiringEpisode { episode }
+    }
+  }
+}
+"""
+
+CLIENT = httpx.AsyncClient(timeout=15.0)
+
+async def _post(payload: dict) -> dict:
+    for i in range(5):
+        await ANILIST_RATE_LIMITER.acquire()
+        try:
+            r = await CLIENT.post(URL, json=payload)
+            r.raise_for_status()
+            return r.json()
+        except Exception:
+            await asyncio.sleep(1 * 2**i)
+    raise RuntimeError("AniList unreachable")
+
+async def search_raw(filters: dict) -> list[dict]:
+    payload = {"query": QUERY, "variables": filters}
+    data = await _post(payload)
+    return data.get("data", {}).get("Page", {}).get("media") or []

modules/anime_etl/sources/anilist_source.py

@@ -0,0 +1,35 @@
+from mappers.anilist_filters import to_anilist_filters
+from sources.anilist_async_client import search_raw
+from normalizers.anilist_normalizer import normalize_media
+import asyncio
+import pprint
+
+
+class AniListSource:
+    async def search(self, local_filters: dict) -> list:
+        ani_filters = to_anilist_filters(local_filters)
+        raw_list = await search_raw(ani_filters)
+        return [normalize_media(r) for r in raw_list]
+
+
+async def _demo() -> None:
+    src = AniListSource()
+    filters = {
+        "query": "monogatari",
+        # "year": 2017,
+        # "season": "winter",
+        # "type": "tv",
+        # "limit": 5,
+    }
+    print("Запускаю поиск с фильтрами:", filters)
+    titles = await src.search(filters)
+    print("Найдено тайтлов:", len(titles))
+
+    for t in titles:
+        # t.title_names — dict[str, list[str]]
+        # en = (t.title_names.get("en") or [""])[0]
+        # print("-", en, "|", t.release_year, t.release_season)
+        pprint.pprint(t)
+
+if __name__ == "__main__":
+    asyncio.run(_demo())