P_chandra_migrator/migrate_subscriptions.py

import sys
import requests
from dbfread import DBF
from datetime import date, datetime
import csv

import os
from dotenv import load_dotenv
load_dotenv(override=True)
host=os.getenv("HOST")
login_user = os.getenv("USER")
login_pass = os.getenv("PASS")
src_file_subs = os.getenv("FILE_ROOT")+os.getenv("SUBSCRIPTION_FILE")
print("Reading files: ", src_file_subs)

def read_dbf_file(file_path, columns):
    data = []
    try:
        # Open the .dbf file
        with DBF(file_path) as dbf:
            # Iterate over each record in the .dbf file
            for record in dbf:
                # Filter the record to include only the specified columns
                filtered_record = {column: record.get(column) for column in columns}
                
                # Clean up the ACNO field by removing spaces and keeping only numeric characters
                if filtered_record.get('ACNO'):
                    filtered_record['ACNO'] = ''.join(filter(str.isdigit, filtered_record['ACNO']))
                
                # Clean up the PHONE field by keeping only numeric characters
                if filtered_record.get('PHONE'):
                    filtered_record['PHONE'] = ''.join(filter(str.isdigit, filtered_record['PHONE']))
                
                # Check if NAME2 is empty
                if not filtered_record.get('NAME2'):
                    # If NAME2 is empty, check if PHONE has a value
                    if filtered_record.get('PHONE'):
                        filtered_record['NAME2'] = filtered_record['PHONE']
                    else:
                        # If both NAME2 and PHONE are empty, skip this record
                        continue
                
                # Check if PHONE length is not equal to 10
                if len(filtered_record.get('PHONE', '')) != 10:
                    continue
                
                # Merge [ADD1, ADD2, ADD3, PLACE, PIN] into one column "Address"
                address_components = [record.get(col, '') for col in ['ADD1', 'ADD2', 'ADD3', 'PLACE', 'PIN']]
                filtered_record['Address'] = '-'.join(filter(None, address_components))
                
                # Remove [ADD1, ADD2, ADD3, PLACE, PIN]
                for col in ['ADD1', 'ADD2', 'ADD3', 'PLACE', 'PIN']:
                    del filtered_record[col]
                
                data.append(filtered_record)
    except Exception as e:
        print("Error:", e)
    return data

def save_data_to_csv(data, file_path, columns):
    try:
        # Remove unnecessary columns from the fieldnames
        columns = [col for col in columns if col not in ["ADD1", "ADD2", "ADD3", "PLACE", "PIN", 'Address', 'NAME2']]
        
        # Remove unnecessary columns from each record in the data
        for record in data:
            for field in ["ADD1", "ADD2", "ADD3", "PLACE", "PIN", 'Address', 'NAME2']:
                if field in record:
                    del record[field]
        
        with open(file_path, 'w', newline='') as csv_file:
            writer = csv.DictWriter(csv_file, fieldnames=columns)
            writer.writeheader()
            writer.writerows(data)
        print(f"CSV saved to {file_path}")
    except Exception as e:
        print("Error saving CSV to file:", e)

def get_auth_token():
    url = host+"/auth/token/"
    print("Using URL: ", url)
    payload = {"phone_no": login_user, "password": login_pass}
    try:
        response = requests.post(url, data=payload)
        response.raise_for_status()
        return response.json().get('access')
    except requests.exceptions.RequestException as e:
        print("Error obtaining auth token:", e)
        return None

def send_data_to_api(data, token, batch_size=1000): 
    url = host+"/api/v1/migrateSubscriptions"
    print("Using URL: ", url)
    csv_file_path = 'batch.csv'
    headers = {'Authorization': f'Bearer {token}'}
    for i in range(0, len(data), batch_size):
        batch = data[i:i+batch_size]
        save_data_to_csv(batch, csv_file_path, batch[0].keys())
        try:
            # Send CSV file with data as multipart form-data
            files = {'file': open(csv_file_path, 'rb')}
            response = requests.post(url, files=files, headers=headers)
            
            # Check response status
            if response.status_code == 201:
                response_data = response.json()
                # Print the message
                print(f"Message from server: {response_data.get('message')}")
                print(f"Batch {i//batch_size + 1} sent successfully to the API")
            else:
                # Print the error message and response content
                print(f"Failed to send batch {i//batch_size + 1} to the API. Status code:", response.status_code)
                print("Response content:", response.content.decode('utf-8'))
        except Exception as e:
            # Print the general error message
            print("Error:", e)

if __name__ == "__main__":
    # Check if the file path is provided as a command-line argument
    # if len(sys.argv) < 2:
    #     print("Usage: python script.py DE2.DBF")
    # else:
        # Get the file path from the command-line arguments
        dbf_file_path = src_file_subs
        # Specify the columns to be extracted
        columns_to_extract = ["ACTP", "ACNO", "PHONE", "ADD1", "ADD2", "ADD3", "PLACE", "PIN"]
        # Call the function to read the .dbf file with specific columns
        dbf_data = read_dbf_file(dbf_file_path, columns_to_extract)
        # Obtain the authentication token
        token = get_auth_token()
        if token:
            # Send the data to the API in batches with authentication
            send_data_to_api(dbf_data, token)
        else:
            print("Failed to obtain auth token, cannot send data to API.")