Add: crawl database script

This commit is contained in:
dx-tan 2024-01-03 11:07:58 +07:00
parent 8d76ae89aa
commit 7b8cfbb062

96
scripts/crawl_database.py Normal file
View File

@ -0,0 +1,96 @@
import csv
import psycopg2
import boto3
import os
from tqdm import tqdm
OUTPUT_NAME = "issue_7"
# 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
request_ids = [
'SAPe39e970592394b27a17d4a64c39f7ed0',
'SAP477a02a21faf41ecbd1a0bb21636e644',
'SAP459d58a7dba84e7195f5ad8f46fc1530',
'SAPa5aaa0e1ce8c4824a7b0ded2e550caec',
'SAP492c063db44049c6b1e44f59c531f8d8',
'SAP3d0bdd5cb4ce4291b0cb77d7de0a48e9',
'SAP7e2c673e49c441a991661d1227342131',
'SAPc26974bcac2649b28227981459a427aa',
'SAP25b12dde6b854c70b512ac79059ac1d4',
'SAP_20240102194138_bf4a3cc4e0304d0385126b6592c2632d',
'SAP_20240102214550_8389ec1b84a249738eed9d2152bf0922',
]
# 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()
# Generate the placeholder string for the IN statement
placeholders = ','.join(['%s'] * len(request_ids))
# Execute the SELECT query with the filter
query = f"SELECT * FROM fwd_api_subscriptionrequest WHERE request_id IN ({placeholders})"
cursor.execute(query, request_ids)
# 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
)
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)
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)