def execute(self, context):
mssql_hook = MsSqlHook(mssql_conn_id=self.mssql_conn_id, schema=self.database)
for rows in self._bq_get_data():
mssql_hook.insert_rows(self.mssql_table, rows, replace=self.replace)
def __init__(self, batch_size=20):
self.conn = MsSqlHook.get_connection(conn_id="mssql_test_db")
self.batch_size = batch_size
def get_hook(self):
if self.conn_type == 'mysql':
from airflow.providers.mysql.hooks.mysql import MySqlHook
return MySqlHook(mysql_conn_id=self.conn_id)
elif self.conn_type == 'google_cloud_platform':
from airflow.gcp.hooks.bigquery import BigQueryHook
return BigQueryHook(bigquery_conn_id=self.conn_id)
elif self.conn_type == 'postgres':
from airflow.providers.postgres.hooks.postgres import PostgresHook
return PostgresHook(postgres_conn_id=self.conn_id)
elif self.conn_type == 'pig_cli':
from airflow.providers.apache.pig.hooks.pig import PigCliHook
return PigCliHook(pig_cli_conn_id=self.conn_id)
elif self.conn_type == 'hive_cli':
from airflow.providers.apache.hive.hooks.hive import HiveCliHook
return HiveCliHook(hive_cli_conn_id=self.conn_id)
elif self.conn_type == 'presto':
from airflow.providers.presto.hooks.presto import PrestoHook
return PrestoHook(presto_conn_id=self.conn_id)
elif self.conn_type == 'hiveserver2':
from airflow.providers.apache.hive.hooks.hive import HiveServer2Hook
return HiveServer2Hook(hiveserver2_conn_id=self.conn_id)
elif self.conn_type == 'sqlite':
from airflow.providers.sqlite.hooks.sqlite import SqliteHook
return SqliteHook(sqlite_conn_id=self.conn_id)
elif self.conn_type == 'jdbc':
from airflow.hooks.jdbc_hook import JdbcHook
return JdbcHook(jdbc_conn_id=self.conn_id)
elif self.conn_type == 'mssql':
from airflow.providers.microsoft.mssql.hooks.mssql import MsSqlHook
return MsSqlHook(mssql_conn_id=self.conn_id)
elif self.conn_type == 'odbc':
from airflow.providers.odbc.hooks.odbc import OdbcHook
return OdbcHook(odbc_conn_id=self.conn_id)
elif self.conn_type == 'oracle':
from airflow.providers.oracle.hooks.oracle import OracleHook
return OracleHook(oracle_conn_id=self.conn_id)
elif self.conn_type == 'vertica':
from airflow.contrib.hooks.vertica_hook import VerticaHook
return VerticaHook(vertica_conn_id=self.conn_id)
elif self.conn_type == 'cloudant':
from airflow.contrib.hooks.cloudant_hook import CloudantHook
return CloudantHook(cloudant_conn_id=self.conn_id)
elif self.conn_type == 'jira':
from airflow.providers.jira.hooks.jira import JiraHook
return JiraHook(jira_conn_id=self.conn_id)
elif self.conn_type == 'redis':
from airflow.providers.redis.hooks.redis import RedisHook
return RedisHook(redis_conn_id=self.conn_id)
elif self.conn_type == 'wasb':
from airflow.providers.microsoft.azure.hooks.wasb import WasbHook
return WasbHook(wasb_conn_id=self.conn_id)
elif self.conn_type == 'docker':
from airflow.providers.docker.hooks.docker import DockerHook
return DockerHook(docker_conn_id=self.conn_id)
elif self.conn_type == 'azure_data_lake':
from airflow.providers.microsoft.azure.hooks.azure_data_lake import AzureDataLakeHook
return AzureDataLakeHook(azure_data_lake_conn_id=self.conn_id)
elif self.conn_type == 'azure_cosmos':
from airflow.providers.microsoft.azure.hooks.azure_cosmos import AzureCosmosDBHook
return AzureCosmosDBHook(azure_cosmos_conn_id=self.conn_id)
elif self.conn_type == 'cassandra':
from airflow.providers.apache.cassandra.hooks.cassandra import CassandraHook
return CassandraHook(cassandra_conn_id=self.conn_id)
elif self.conn_type == 'mongo':
from airflow.providers.mongo.hooks.mongo import MongoHook
return MongoHook(conn_id=self.conn_id)
elif self.conn_type == 'gcpcloudsql':
from airflow.gcp.hooks.cloud_sql import CloudSQLDatabaseHook
return CloudSQLDatabaseHook(gcp_cloudsql_conn_id=self.conn_id)
elif self.conn_type == 'grpc':
from airflow.contrib.hooks.grpc_hook import GrpcHook
return GrpcHook(grpc_conn_id=self.conn_id)
raise AirflowException("Unknown hook type {}".format(self.conn_type))
def extract(**kwargs):
conn = MsSqlHook.get_connection(conn_id="mssql_test_db")
hook = conn.get_hook()
df = hook.get_pandas_df(sql="SELECT top 5 * FROM dbo.drugs")
#do whatever you need on the df
print(df)
