1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132 | try:
from datetime import datetime, timezone, timedelta
from airflow import DAG
from airflow.operators.python_operator import PythonOperator
from airflow.operators.http_operator import SimpleHttpOperator
from airflow.hooks.base_hook import BaseHook
from datetime import datetime
from pandas.io.json import json_normalize
from airflow.operators.postgres_operator import PostgresOperator
# from pymongo import MongoClient
import pandas as pd
import json
import requests
import numpy as np
import re
import array
import psycopg2
from sqlalchemy import create_engine
import math
except Exception as e:
print("Error {} ".format(e))
dRoW_api_end_url = "https://drow.cloud"
def getDrowToken(**context):
response = requests.post(
url=f"{dRoW_api_end_url}/api/auth/authenticate",
data={
"username": "keexiansuen@drow.cloud",
"password": "c3UxMTk5a3ghIQ==",
}
).json()
context["ti"].xcom_push(key="token", value=response['token'])
def getdrowPSQLConnectionString():
host = 'drowdatewarehouse.crlwwhgepgi7.ap-east-1.rds.amazonaws.com'
# User name of the database server
dbUserName = 'dRowAdmin'
# Password for the database user
dbUserPassword = 'drowsuper'
# Name of the database
database = 'drowDateWareHouse'
# Character set
charSet = "utf8mb4"
port = "5432"
conn_string = ('postgres://' +
dbUserName + ':' +
dbUserPassword +
'@' + host + ':' + port +
'/' + database)
return conn_string
def getInspectionData(**context):
token = context.get("ti").xcom_pull(key="token")
# mongo_conn = BaseHook.get_connection("mongo_conn")
# mongo_uri = f"mongodb://{mongo_conn.host}:{mongo_conn.port}"
# mongo_client = MongoClient(mongo_uri)
# mongo_db = mongo_client[mongo_conn.schema]
# workflow_collection = mongo_db['workflows']
# workflow_records = mongo_db['workflowrecords']
itp_response = requests.get(
url=f"{dRoW_api_end_url}/api/module/document-export/airflow/workflow/6780da3a19a6ea5c197f5e8a?export_type=0",
headers={
"x-access-token": f"Bearer {token}",
"ICWPxAccessKey": "5WSD21ICWP_[1AG:4UdI){n=b~"
}
)
ITP_Data = json.loads(itp_response.text)
risc_response = requests.get(
url=f"{dRoW_api_end_url}/api/module/document-export/airflow/workflow/6732d16bf0fd5b8f573d79ef?export_type=0",
headers={
"x-access-token": f"Bearer {token}",
"ICWPxAccessKey": "5WSD21ICWP_[1AG:4UdI){n=b~"
}
)
RISC_Data = json.loads(risc_response.text)
conn_string = getdrowPSQLConnectionString()
db = create_engine(conn_string)
conn = db.connect()
with conn as conn:
itp_df = pd.DataFrame()
for x in ITP_Data:
print("Data ITP:", x)
df_nested_list = json_normalize(x['data'])
df_nested_list['ITP ID'] = x['_id']
itp_df = itp_df.append(df_nested_list)
# print("ITP Dataframe:", itp_df.columns)
df = pd.DataFrame()
for x in RISC_Data:
print("Data RISC:", x)
df_nested_list = json_normalize(x['data'])
df = df.append(df_nested_list)
# print("RISC Dataframe:", df.columns)
# print("ITP Status:", df['ITP Status'])
# print("ITP:", df['ITP Type'])
# Execute DAG 4 times every day
with DAG(
dag_id="hy202308_itp_dashboard",
schedule_interval="0 7,15 * * *",
default_args={
"owner": "airflow",
"retries": 1,
"retry_delay": timedelta(minutes=5),
"start_date": datetime(2023, 1, 17)
},
catchup=False) as f:
getDrowToken = PythonOperator(
task_id="getDrowToken",
python_callable=getDrowToken,
provide_context=True,
# op_kwargs={"name": "Dylan"}
)
getInspectionData = PythonOperator(
task_id="getInspectionData",
python_callable=getInspectionData,
provide_context=True,
op_kwargs={"name": "Dylan"},
)
getDrowToken >> getInspectionData
|