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
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147 | try:
import json
import logging
from datetime import datetime, timedelta
import numpy as np
import pandas as pd
import requests
from airflow import DAG
from airflow.operators.python_operator import PythonOperator
from pandas.io.json import json_normalize
from sqlalchemy import create_engine
except Exception as e:
print("Error {} ".format(e))
logger = logging.getLogger('airflow.task')
dRoW_api_end_url = "https://drow.cloud"
def getDrowToken(**context):
response = requests.post(
url=f"{dRoW_api_end_url}/api/auth/authenticate",
data={
"username": "icwp2@drow.cloud",
"password": "dGVzdDAxQHRlc3QuY29t"
}).json()
context["ti"].xcom_push(key="token", value=response['token'])
def getMongoDB(**context):
token = context.get("ti").xcom_pull(key="token")
response = requests.get(
url=f"{dRoW_api_end_url}/api/module/document-export/airflow/workflow/664ee0e3a02b18de5cb4e8a4?export_type=0",
headers={
"x-access-token": f"Bearer {token}",
"ICWPxAccessKey": "nd@201907ICWP_[1AG:4UdI){n=b~"
}
)
RISC_Data = json.loads(response.text)
Mapping= {
'Year':'year',
'Month':'month',
'Wage Information':'wage_information',
'Number of worker engaged on site on each calendar day':'number_of_worker_engaged_on_site_on_each_calendar_day',
}
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)
db = create_engine(conn_string)
conn = db.connect()
with conn as conn:
df = pd.DataFrame()
for x in RISC_Data:
df_nested_list = json_normalize(x['data'])
trade_list =[]
average = []
high = []
low = []
df2 = df_nested_list.reindex(columns=Mapping.keys())
df3 = pd.DataFrame()
for i in df2['Wage Information']:
for j in i:
for key, value in j.items():
if key == 'Trade':
trade_list.append(value)
elif key == 'Average':
average.append(value)
elif key == 'High':
high.append(value)
elif key == 'Low':
low.append(value)
df3['trade_list'] = pd.Series(trade_list)
df3['average'] = pd.Series(average)
df3['high'] = pd.Series(high)
df3['low']= pd.Series(low)
print(df2['Year'].values[0] + '-' + df2['Month'].values[0])
df3['date'] = datetime.strptime(df2['Year'].values[0].strip() + '-' + df2['Month'].values[0].strip(), '%Y-%B')
total_man_days = []
overtime_hours = []
for i in df2['Number of worker engaged on site on each calendar day']:
for idx, j in enumerate(i):
for key, value in j.items():
if key != 'Trade List':
if key == 'Total Man-days':
total_man_days.append(value)
elif key == 'Overtime (hours)':
overtime_hours.append(value)
else:
pass
df3['total_man_days'] = pd.Series(total_man_days)
df3['overtime_hours'] = pd.Series(overtime_hours)
df = df.append(df3)
df['total_man_days'].fillna(0,inplace=True)
df['overtime_hours'].fillna(0,inplace=True)
df.to_sql('labour_return_cv202308', con=conn, if_exists='replace', index= False)
# Execute the DAG at 3:00 PM UTC every day
with DAG(
dag_id="cv202308_labour_return",
schedule_interval="0 15 * * *",
default_args={
"owner": "airflow",
"retries": 1,
"retry_delay": timedelta(minutes=5),
"start_date": datetime(2023, 1, 17)
},
catchup=False) as f:
getMongoDB = PythonOperator(
task_id="getMongoDB",
python_callable=getMongoDB,
op_kwargs={"name": "Dylan"},
provide_context=True,
)
getDrowToken = PythonOperator(
task_id="getDrowToken",
python_callable=getDrowToken,
provide_context=True,
)
getDrowToken >> getMongoDB
|