Move pipelines

pipeline/download/arcgis.py

@@ -0,0 +1,71 @@
+import zipfile
+import httpx
+import polars as pl
+from pathlib import Path
+from tqdm import tqdm
+
+URL = "https://www.arcgis.com/sharing/rest/content/items/077631e063eb4e1ab43575d01381ec33/data"
+
+BASE_DATA_PATH = Path("./data_sources")
+BASE_DATA_PATH.mkdir(exist_ok=True)
+DOWNLOAD_PATH = BASE_DATA_PATH / "arcgis_data.zip"
+EXTRACT_PATH = BASE_DATA_PATH / "arcgis_extracted"
+PARQUET_PATH = BASE_DATA_PATH / "arcgis_data.parquet"
+
+
+def download_with_progress(url: str, output_path: Path) -> None:
+    with httpx.stream(
+        "GET",
+        url,
+        follow_redirects=True,
+        timeout=httpx.Timeout(30.0, read=None),
+    ) as response:
+        response.raise_for_status()  # pyright: ignore[reportUnusedCallResult]
+        total = int(response.headers.get("content-length", 0))
+
+        with (
+            open(output_path, "wb") as f,
+            tqdm(
+                total=total,
+                unit="B",
+                unit_scale=True,
+                unit_divisor=1024,
+                desc="Downloading",
+            ) as pbar,
+        ):
+            for chunk in response.iter_bytes(chunk_size=8192):
+                f.write(chunk)
+                pbar.update(len(chunk))
+        return 
+   
+
+
+def extract_zip(zip_path: Path, extract_path: Path) -> None:
+    extract_path.mkdir(exist_ok=True)
+
+    with zipfile.ZipFile(zip_path, "r") as zf:
+        zf.extractall(extract_path)
+
+
+def convert_to_parquet(data_path: Path, parquet_path: Path) -> None:
+    df = pl.scan_csv(data_path / 'Data/NSPL_MAY_2025_UK.csv', try_parse_dates=True)
+    print(f"Columns: {df.columns}")
+    df.sink_parquet(parquet_path, compression="zstd")
+    print(f"Saved to {parquet_path}")
+
+
+def main() -> None:
+    if PARQUET_PATH.exists():
+        print(f"Parquet already exists at {PARQUET_PATH}, skipping")
+        return
+
+    if not DOWNLOAD_PATH.exists():
+        download_with_progress(URL, DOWNLOAD_PATH)
+    else:
+        print(f"File already exists at {DOWNLOAD_PATH}, skipping download")
+
+    extract_zip(DOWNLOAD_PATH, EXTRACT_PATH)
+    convert_to_parquet(EXTRACT_PATH, PARQUET_PATH)
+
+if __name__ == "__main__":
+    main()