Premiers éléments de l'étude

lib/rebrickable/downloader.py

@@ -0,0 +1,47 @@
+"""Outils de téléchargement pour les fichiers fournis par Rebrickable."""
+
+from datetime import datetime, timedelta
+from pathlib import Path
+from typing import Iterable, List
+import gzip
+import shutil
+
+import requests
+
+
+REBRICKABLE_BASE_URL = "https://cdn.rebrickable.com/media/downloads/"
+CHUNK_SIZE = 8192
+CACHE_TTL = 7
+
+
+def build_rebrickable_url(file_name: str) -> str:
+    """Construit l'URL complète d'un fichier Rebrickable à partir de son nom."""
+    return f"{REBRICKABLE_BASE_URL}{file_name}"
+
+
+def download_rebrickable_file(file_name: str, destination_dir: Path) -> Path:
+    """Télécharge un fichier Rebrickable, le décompresse et supprime l'archive."""
+    target_path = destination_dir / file_name
+    destination_dir.mkdir(parents=True, exist_ok=True)
+    decompressed_path = target_path.with_suffix("")
+    if decompressed_path.exists():
+        cache_age = datetime.now() - datetime.fromtimestamp(decompressed_path.stat().st_mtime)
+        if cache_age <= timedelta(days=CACHE_TTL):
+            if target_path.exists():
+                target_path.unlink()
+            return decompressed_path
+    response = requests.get(build_rebrickable_url(file_name), stream=True)
+    response.raise_for_status()
+    with target_path.open("wb") as target_file:
+        for chunk in response.iter_content(chunk_size=CHUNK_SIZE):
+            target_file.write(chunk)
+    with gzip.open(target_path, "rb") as compressed_file:
+        with decompressed_path.open("wb") as decompressed_file:
+            shutil.copyfileobj(compressed_file, decompressed_file)
+    target_path.unlink()
+    return decompressed_path
+
+
+def download_rebrickable_files(file_names: Iterable[str], destination_dir: Path) -> List[Path]:
+    """Télécharge en série plusieurs fichiers compressés fournis par Rebrickable."""
+    return [download_rebrickable_file(file_name, destination_dir) for file_name in file_names]