import duckdb def get_full_schema(): conn = duckdb.connect() conn.execute("INSTALL httpfs; LOAD httpfs;") conn.execute("SET s3_region='sgp1';") conn.execute("SET s3_endpoint='sgp1.digitaloceanspaces.com';") conn.execute("SET s3_url_style='path';") rows = conn.execute("DESCRIBE SELECT * FROM read_parquet('s3://nearle/parquet/deliveries/*.parquet')").fetchall() cols = [row[0] for row in rows] print(", ".join(cols)) if __name__ == "__main__": get_full_schema()