Connectors

Azure Blob Storage Connector - Get Data

Install packages

import os
os.system("pip install katonic[connectors]==1.6.2")

azure-blob-credentials.json

{
  "ACCOUNT_NAME": "accountname", 
  "ACCOUNT_KEY": "accountkey", 
  "CONTAINER_NAME": "container_data", 
  "BLOB_NAME": "driver_data.csv"
}

# Define all your configurations inside a JSON file.
import json

with open('azure-blob-credentials.json') as f:
    config = json.load(f)

Initializing the AzureBlobConnector with the provided credentials and configuration.

from katonic.connectors.python.azure_blob import AzureBlobConnector

df = AzureBlobConnector(
    account_name=config["ACCOUNT_NAME"],
    account_key=config["ACCOUNT_KEY"],
    container_name=config["CONTAINER_NAME"],
    blob_name=config["BLOB_NAME"],
    output="local",
    file_name="driver_data",
)

df.get_data()

>>> Connection instance to azure blob storage stablished Successfully.
>>> File saved to your 'local' file system with name 'azure_container_data_driver_data_2022_04_20_16_49_29.csv' Successfully.

BigQuery Connector - Get Data

Initializing the BigQueryConnector with the credentials in json file.

from katonic.connectors.python.bigquery import BigQueryConnector

CREDS = "big-query-credentials.json"
query = """
    SELECT Churn, AccountWeeks, ContractRenewal, DataPlan
    FROM `big-query-connect-364013.001.big-query-connect-364013`
    LIMIT 50
    """

df = BigQueryConnector(
    bigquery_credential_path=CREDS,
    query=query,
    file_name="driver_data",
)

df.get_data()

>>> Connection to bigquery stablished Successfully.
>>> File saved to your 'local' file system with name 'biquery_driver_data_2022_11_30_11_39_08.csv' Successfully.

DuckDB Connector - Get Data

Initializing the DuckDBConnector with the provided configuration.

from katonic.connectors.python.duckdb import DuckDBConnector

df = DuckDBConnector(
    database="sparkdb.duckdb",
    query="SELECT * FROM driver_stats_data",
    output="local",
    file_name="driver_data",
)

df.get_data()

>>> Connection to duckdb stablished Successfully.
>>> File saved to your 'local' file system with name 'duckdb_sparkdb_driver_data_2022_11_30_11_54_13.csv' Successfully.

MySQL Connector - Get Data

mysql-credentials.json

{
  "HOST": "localhost", 
  "PORT": 3306, 
  "DB_NAME": "dbname", 
  "USER": "localhost", 
  "PASSWORD": "password", 
  "TABLE_NAME": "driver_data"
}

# Define all your configurations inside a JSON file.
import json

with open('mysql-credentials.json') as f:
    config = json.load(f)

Initializing the MySQLConnector with the provided credentials and configuration.

from katonic.connectors.python.mysql import MySQLConnector

df = MySQLConnector(
    host=config["HOST"],
    port=config["PORT"],
    db_name=config["DB_NAME"],
    user=config["USER"],
    password=config["PASSWORD"],
    table_name=config["TABLE_NAME"],
    query="SELECT * FROM driver_stats_data",
    output="local",
    file_name="driver_data",
)

df.get_data()

>>> Connection to mysql stablished Successfully.
>>> File saved to your 'local' file system with name 'mysql_dbname_driver_data_2022_04_20_14_23_19.csv' Successfully.

PostgreSQL Connector - Get Data

postgresql-credentials.json

{
  "HOST": "localhost", 
  "PORT": 5432, 
  "DB_NAME": "dbname", 
  "USER": "postgres", 
  "PASSWORD": "postgres", 
  "TABLE_NAME": "driver_data", 
  "DB_SCHEMA": "public"
}

# Define all your configurations inside a JSON file.
import json

with open('postgresql-credentials.json') as f:
    config = json.load(f)

Initializing the PostgreSQLConnector with the provided credentials and configuration.

from katonic.connectors.python.postgres import PostgreSQLConnector

df = PostgreSQLConnector(
    host=config["HOST"],
    port=config["PORT"],
    db_name=config["DB_NAME"],
    user=config["USER"],
    password=config["PASSWORD"],
    db_schema=config["DB_SCHEMA"],
    table_name=config["TABLE_NAME"],
    query="SELECT * FROM driver_stats_data",
    output="local",
    file_name="driver_data",
)

df.get_data()

>>> Connection to postgres stablished Successfully.
>>> File saved to your 'local' file system with name 'postgres_public_dbname_driver_data_2022_04_20_12_09_25.csv' Successfully.

Redshift Connector - Get Data

redshift-credentials.json

{
  "HOST": "localhost", 
  "PORT": 3306, 
  "DB_NAME": "dbname", 
  "USER": "localhost", 
  "PASSWORD": "password", 
  "TABLE_NAME": "driver_data"
}

# Define all your configurations inside a JSON file.
import json

with open('redshift-credentials.json') as f:
    config = json.load(f)

Initializing the RedshiftConnector with the provided credentials and configuration.

from katonic.connectors.python.redshift import RedshiftConnector

df = RedshiftConnector(
    host=config["HOST"],
    database=config["DB_NAME"],
    user=config["USER"],
    password=config["PASSWORD"],
    table_name=config["TABLE_NAME"],
    query="SELECT * FROM driver_stats_data",
    port=config["PORT"],
    output="local",
    file_name="driver_data",
)

df.get_data()

>>> Connection to Amazon redshift stablished Successfully.
>>> File saved to your 'local' file system with name 'redshift_sparkdb_driver_data_2022_04_20_06_51_49.csv' Successfully.

AWS S3 Connector - Get Data

aws-s3-credentials.json

{
  "AWS_ACCESS_KEY": "AWS_ACCESS_KEY", 
  "AWS_SECRET_KEY": "AWS_SECRET_KEY", 
  "AWS_SESSION_TOKEN": "AWS_SESSION_TOKEN", 
  "REGION_NAME": "REGION_NAME", 
  "PROFILE_NAME": "PROFILE_NAME",
  "BUCKET_NAME": "BUCKET_NAME",
  "OBJECT_NAME": "OBJECT_NAME"
}

# Define all your configurations inside a JSON file.
import json

with open('aws-s3-credentials.json') as f:
    config = json.load(f)

Initializing the AWSS3Connector with the provided credentials and configuration.

from katonic.connectors.python.s3 import AWSS3Connector

df = AWSS3Connector(
    aws_access_key=config["AWS_ACCESS_KEY"],
    aws_secret_key=config["AWS_SECRET_KEY"],
    aws_session_token=config["AWS_SESSION_TOKEN"],
    region_name=config["REGION_NAME"],
    profile_name=config["PROFILE_NAME"],
    bucket_name=config["BUCKET_NAME"],
    object_name=config["OBJECT_NAME"],
    output="local",
    file_name="driver_data",
)

df.get_data()

>>> Connection instance to aws s3 stablished Successfully.
>>> File saved to your 'local' file system with name 's3_driver_data_2022_04_20_06_51_49.csv' Successfully.

SAP HANA Connector - Get Data

sap-hana-credentials.json

{
  "HOST": "localhost", 
  "PORT": 3306, 
  "USER": "localhost", 
  "PASSWORD": "password", 
  "TABLE_NAME": "driver_data",
  "SCHEMA": "SCHEMA"

# Define all your configurations inside a JSON file.
import json

with open('sap-hana-credentials.json') as f:
    config = json.load(f)

Initializing the SAPHANAConnector with the provided credentials and configuration.

from katonic.connectors.python.sap_hana import SAPHANAConnector

df = SAPHANAConnector(
    host=config["HOST"],
    port=config["PORT"],
    user=config["USER"],
    password=config["PASSWORD"],
    table_name=config["TABLE_NAME"],
    schema=config["SCHEMA"],
    query="SELECT * FROM driver_stats_data",
    output="local",
    file_name="driver_data",
)

df.get_data()

>>> Connection to SAP HANA stablished Successfully.
>>> File saved to your 'local' file system with name 'sap_hana_TPCH_SH1_driver_data_2022_04_20_06_51_49.csv' Successfully.

SnowFlake Connector - Get Data

snowflake-credentials.json

{
  "USER": "username",
  "PASSWORD": "password",
  "ACCOUNT": "id.uae-north.azure",
  "DATABASE": "SNOWFLAKE_SAMPLE_DATA",
  "TABLE_NAME": "CUSTOMER",
  "SCHEMA": "TPCH_SF1",
  "WAREHOUSE": "COMPUTE_WH"
}

# Define all your configurations inside a JSON file.
import json

with open('snowflake-credentials.json') as f:
    config = json.load(f)

Initializing the SnowFlakeConnector with the provided credentials and configuration.

from katonic.connectors.python.snowflake import SnowFlakeConnector

df = SnowFlakeConnector(
    user=config["USER"],
    password=config["PASSWORD"],
    account=config["ACCOUNT"],
    database=config["DATABASE"],
    table_name=config["TABLE_NAME"],
    schema=config["SCHEMA"],
    warehouse=config["WAREHOUSE"],
    query="SELECT * FROM TPCH_SF1.CUSTOMER",
    output="local",
    file_name="driver_data",
)

df.get_data()

>>> Connection to snowflake stablished Successfully.
>>> File saved to your 'local' file system with name 'snowflake_TPCH_SF1_SNOWFLAKE_SAMPLE_DATA_driver_data_2022_04_20_08_46_38.csv' Successfully.