from fp2_14 import get_product_prices
import h5py
import pandas as pd
import datetime
import sys
from datetime import datetime
import ntplib
import arrow

project_id = "fp-20230425"
subscription_name = "fp-subscription-NFL-zipcodes"
url = "https://www.sayweee.com/en/product/House-Foods-Firm-Tofu-/85175?trace_id=c93f3d1a-80a4-4e1a-8d41-a402ae43186f"

df_new = get_product_prices(project_id, subscription_name, url)

'''
# When using sys to call the 'get_product_prices' function

if __name__ == '__main__':
    # Check if the required command-line arguments are provided
    if len(sys.argv) < 4:
        print("Usage: python test_fp2_14.py project_id subscription_name url")
        sys.exit(1)

    project_id = sys.argv[1]
    subscription_name = sys.argv[2]
    url = sys.argv[3:]

    get_product_prices(project_id, subscription_name, url)
'''


# Now we have the new dataframe "df" recording the new price listed in weee's page
# Load such data in the existing HDF5 file
file_path = 'product1.h5'
with h5py.File(file_path, 'a') as file:
    # Load the existing dataframe 'df' from the HDF5 file
    # REPLACE KEY TO GET THE EXISTING DATAFRAME FOR EACH DIFFERENT PRODUCT
    df = pd.read_hdf(file, key='df')

    # Add timestamp to the new dataframe "df_new"
    # timestamp = datetime.now()
    '''
    To deal with the issue of inconsistent time when running a script on different systems, we can use 'ntplib' that
    provides time synchronization with a reliable time server.
    Also, to ensure that the local time is interpreted in the system's local time zone, we use 'arrow' which offers a
    sensible and human-friendly approach to format and convert the timestamps.
    '''
    # Fetch the time from an NTP server
    ntp_client = ntplib.NTPClient()
    response = ntp_client.request('pool.ntp.org')
    ntp_time = datetime.fromtimestamp(response.tx_time)
    timestamp = arrow.get(ntp_time).to('local')
    df_new['Timestamp'] = timestamp

    # Append 'df_new' to the existing df stored in the key
    df_update = df.append(df_new, ignore_index=True)

    # Save 'df2' to the HDF5 file with the key 'df'
    # REPLACE KEY FOR DIFFERENT PRODUCT
    df_update.to_hdf(file, key='df', mode='a')

print("Data appended and saved successfully.")