100 lines
2.8 KiB
Python
100 lines
2.8 KiB
Python
import csv
|
|
import psycopg2
|
|
import boto3
|
|
import os
|
|
from tqdm import tqdm
|
|
from datetime import datetime, timedelta
|
|
import pytz
|
|
from django.utils import timezone
|
|
|
|
from dotenv import load_dotenv
|
|
|
|
load_dotenv("../.env_prod")
|
|
|
|
tz = pytz.timezone('Asia/Singapore')
|
|
|
|
OUTPUT_NAME = "0303-0327"
|
|
START_DATE = datetime(2024, 3, 3)
|
|
END_DATE = datetime(2024, 3, 27)
|
|
START_DATE = timezone.make_aware(START_DATE, tz)
|
|
END_DATE = timezone.make_aware(END_DATE, tz)
|
|
|
|
# Database connection details
|
|
db_host = os.environ.get('DB_HOST', "")
|
|
db_name = os.environ.get('DB_SCHEMA', "")
|
|
db_user = os.environ.get('DB_USER', "")
|
|
db_password = os.environ.get('DB_PASSWORD', "")
|
|
|
|
# S3 bucket details
|
|
s3_bucket_name = os.environ.get('S3_BUCKET_NAME', "")
|
|
s3_folder_prefix = 'sbt_invoice'
|
|
|
|
# S3 access credentials
|
|
access_key = os.environ.get('S3_ACCESS_KEY', "")
|
|
secret_key = os.environ.get('S3_SECRET_KEY', "")
|
|
|
|
# Request IDs for filtering
|
|
|
|
# Connect to the PostgreSQL database
|
|
conn = psycopg2.connect(
|
|
host=db_host,
|
|
database=db_name,
|
|
user=db_user,
|
|
password=db_password
|
|
)
|
|
|
|
# Create a cursor
|
|
cursor = conn.cursor()
|
|
|
|
|
|
# Execute the SELECT query with the filter
|
|
query = "SELECT * FROM fwd_api_subscriptionrequest WHERE created_at >= %s AND created_at <= %s"
|
|
cursor.execute(query, (START_DATE, END_DATE))
|
|
|
|
# Fetch the filtered data
|
|
data = cursor.fetchall()
|
|
|
|
# Define the CSV file path
|
|
csv_file_path = f'{OUTPUT_NAME}.csv'
|
|
|
|
# Write the data to the CSV file
|
|
with open(csv_file_path, 'w', newline='') as csv_file:
|
|
writer = csv.writer(csv_file)
|
|
writer.writerow([desc[0] for desc in cursor.description]) # Write column headers
|
|
writer.writerows(data) # Write the filtered data rows
|
|
|
|
# Close the cursor and database connection
|
|
cursor.close()
|
|
conn.close()
|
|
|
|
# # Download folders from S3
|
|
s3_client = boto3.client(
|
|
's3',
|
|
aws_access_key_id=access_key,
|
|
aws_secret_access_key=secret_key
|
|
)
|
|
|
|
request_ids = []
|
|
for rq in data:
|
|
rq_id = rq[3]
|
|
request_ids.append(rq_id)
|
|
|
|
for request_id in tqdm(request_ids):
|
|
folder_key = f"{s3_folder_prefix}/{request_id}/" # Assuming folder structure like: s3_bucket_name/s3_folder_prefix/request_id/
|
|
local_folder_path = f"{OUTPUT_NAME}/{request_id}/" # Path to the local folder to save the downloaded files
|
|
os.makedirs(OUTPUT_NAME, exist_ok=True)
|
|
if os.path.exists(local_folder_path):
|
|
continue
|
|
os.makedirs(local_folder_path, exist_ok=True)
|
|
|
|
|
|
# List objects in the S3 folder
|
|
response = s3_client.list_objects_v2(Bucket=s3_bucket_name, Prefix=folder_key)
|
|
objects = response.get('Contents', [])
|
|
|
|
for s3_object in objects:
|
|
object_key = s3_object['Key']
|
|
local_file_path = local_folder_path + object_key.split('/')[-1] # Extracting the file name from the object key
|
|
|
|
# Download the S3 object to the local file
|
|
s3_client.download_file(s3_bucket_name, object_key, local_file_path) |