ETL in Python: Extract CSV, Transform Dict, Load JSON

import csv
import json
from pathlib import Path

def extract_csv(file_path):
    """Read CSV file and return list of row dictionaries."""
    with Path(file_path).open('r', newline='', encoding='utf-8') as f:
        reader = csv.DictReader(f)
        return list(reader)

def transform_dicts(rows):
    """Transform row dicts: strip whitespace and convert numeric fields."""
    for row in rows:
        for key, value in list(row.items()):
            if value is not None:
                row[key] = value.strip()
        if 'age' in row:
            row['age'] = int(row['age']) if row['age'].isdigit() else row['age']
        if 'salary' in row:
            row['salary'] = float(row['salary'])
    return rows

def load_json(data, output_path):
    """Write list of dicts to JSON file with indentation."""
    with Path(output_path).open('w', encoding='utf-8') as f:
        json.dump(data, f, indent=2)
    return output_path

if __name__ == "__main__":
    csv_file = "data.csv"  # sample: name,age,salary,city
    json_file = "output.json"

    # Create sample CSV for demonstration
    sample_csv = "name,age,salary,city\nAlice,30,75000.50,NYC\nBob,25,52000.00,LA\n"
    Path(csv_file).write_text(sample_csv, encoding='utf-8')

    extracted = extract_csv(csv_file)
    transformed = transform_dicts(extracted)
    load_json(transformed, json_file)

    print(f"Transformed {len(transformed)} records to {json_file}")
    print(json.dumps(transformed, indent=2))