import requests
import pandas as pd
from io import StringIO

# -- 1. Configuration --
NCEI_API_TOKEN = 'YOUR_NCEI_API_TOKEN' # Get token from NCEI website
STATION_ID = 'GHCND:KOR00047122'
START_DATE = '2024-01-01'
END_DATE = '2024-01-31'
DATASET_ID = 'GHCND' # Global Historical Climatology Network Daily
DATA_TYPES = 'TMAX,TMIN,PRCP,AWND' # Max Temp, Min Temp, Precipitation, Avg Wind
OUTPUT_CSV = 'seoul_weather_2024_01.csv'

# -- 2. Construct API Request --
API_ENDPOINT = 'https://www.ncei.noaa.gov/cdo-web/api/v2/data'
headers = {'token': NCEI_API_TOKEN}
params = {
    'datasetid': DATASET_ID,
    'stationid': STATION_ID,
    'startdate': START_DATE,
    'enddate': END_DATE,
    'datatypeid': DATA_TYPES,
    'limit': 1000, # Max records per request
    'units': 'metric'
}

# -- 3. Fetch and Process Data --
print(f'Fetching data for {STATION_ID}...')
try:
    response = requests.get(API_ENDPOINT, headers=headers, params=params)
    response.raise_for_status() # Raise an exception for bad status codes
    
    data = response.json().get('results', [])
    
    if not data:
        print('No data found for the specified parameters.')
    else:
        # Pivot data for better readability
        df = pd.DataFrame(data)
        pivot_df = df.pivot_table(
            index='date', 
            columns='datatype', 
            values='value'
        ).reset_index()
        
        # Clean up date format
        pivot_df['date'] = pd.to_datetime(pivot_df['date']).dt.date
        
        # Save to CSV
        pivot_df.to_csv(OUTPUT_CSV, index=False)
        print(f'Successfully saved data to {OUTPUT_CSV}')
        print('\n--- Data Preview ---')
        print(pivot_df.head())

except requests.exceptions.HTTPError as e:
    print(f'API Request Error: {e}')
except Exception as e:
    print(f'An error occurred: {e}')