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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188 | try:
from datetime import timedelta, datetime
from airflow import DAG
from airflow.operators.python_operator import PythonOperator
from datetime import datetime
from pandas.io.json import json_normalize
import pandas as pd
import json
import requests
import numpy as np
import psycopg2
from sqlalchemy import create_engine
except Exception as e:
print("Error {} ".format(e))
dRoW_api_end_url = "https://uat2.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/5fe47b29f964043fba328ca4?export_type=0",
headers={
"x-access-token": f"Bearer {token}",
"ICWPxAccessKey": "nd@201907ICWP_[1AG:4UdI){n=b~"
}
)
RISC_Data = json.loads(response.text)
Mapping= {
"A01 Date" : "a01_date",
}
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'
port = "5432"
conn_string = ('postgres://' +
dbUserName + ':' +
dbUserPassword +
'@' + host + ':' + port +
'/' + database)
db = create_engine(conn_string)
conn = db.connect()
with conn as conn:
df3=pd.read_sql("SELECT * FROM public.site_diary_activities_general_count_dc201911;",
conn,
parse_dates=["a01_date"])
df = pd.DataFrame()
_df = pd.DataFrame()
for x in RISC_Data:
df_nested_list = json_normalize(x['data'])
df2 = df_nested_list.reindex(columns=Mapping.keys())
if x['data']['A01 Date']is not None:
date = datetime.strptime(x['data']['A01 Date'], '%Y-%m-%dT%H:%M:%S.%f%z')
if x['data']['A01 Date'] is None:
date = datetime.strptime('2022-09-22T00:00:00.000Z', '%Y-%m-%dT%H:%M:%S.%f%z')
no_of_site_activities = df3.query('a01_date == @date')
if(len(no_of_site_activities['Count'])!= 0):
df2['no_of_site_activities'] = no_of_site_activities['Count'].iloc[0]
else:
df2['no_of_site_activities'] = 0
if (date < datetime.strptime('2022-10-01T00:00:00.000Z', '%Y-%m-%dT%H:%M:%S.%f%z')):
df2['complete_or_incomplete'] = 'complete'
else :
if x['Status'] == 'F : IOW Upload & Print SD' or x['Status'] == 'Z : SD Completed' or x['Status'] == 'H : IOW Upload & Print SD':
df2['complete_or_incomplete'] = 'complete'
else:
df2['complete_or_incomplete'] = 'incomplete'
if len(x['ApproveLogSummary']) > 0:
pmd_sign_date = [data for data in x['ApproveLogSummary'] if data.get('statusName')=="G : SRE Sign"]
contractor_sign_date = [data for data in x['ApproveLogSummary'] if data.get('statusName')=="E : Contractor Sign"]
supervisor_sign_date = [data for data in x['ApproveLogSummary'] if data.get('statusName')=="F : RE Sign"]
if len(pmd_sign_date) > 0 and ('to' in pmd_sign_date[len(pmd_sign_date)-1]):
pmd_receive_time = x['data']['Supervisor signature time']
pmd_sign_time = x['data']['PMD signature time']
df2['pmd_sign_time'] = x['data']['PMD signature time']
df2['Overdue_PMD']= (pmd_sign_time != None and pmd_sign_time != '' and (datetime.strptime(pmd_sign_time, '%Y-%m-%dT%H:%M:%S.%f%z') - datetime.strptime(pmd_receive_time, '%Y-%m-%dT%H:%M:%S.%f%z')).days > 7)
if (pmd_receive_time == '' or pmd_receive_time == ''):
df2['Overdue_PMD'] = None
else:
df2['pmd_sign_time'] = None
df2['Overdue_PMD'] = None
if len(contractor_sign_date) > 0 and ('to' in contractor_sign_date[len(contractor_sign_date)-1]):
cr_receive_time = contractor_sign_date[len(contractor_sign_date)-1]['from']
cr_sign_time = x['data']['Contractor signature time']
df2['cr_sign_time'] = x['data']['Contractor signature time']
df2['Overdue_CR']= (cr_sign_time != None and cr_receive_time != None and (datetime.strptime(cr_sign_time, '%Y-%m-%dT%H:%M:%S.%f%z') - datetime.strptime(cr_receive_time, '%Y-%m-%dT%H:%M:%S.%f%z')).days > 7)
if ( cr_sign_time == '' or cr_receive_time == ''):
df2['Overdue_CR']= None
else:
df2['cr_sign_time'] = None
df2['Overdue_CR'] = None
if len(supervisor_sign_date) > 0 and ('to' in supervisor_sign_date[len(supervisor_sign_date)-1]):
sup_receive_time = x['data']['Contractor signature time']
sup_sign_time = x['data']['Supervisor signature time']
df2['sup_sign_time'] = x['data']['Supervisor signature time']
df2['Overdue_SUP']= (sup_sign_time != None and sup_receive_time != None and (datetime.strptime(sup_sign_time, '%Y-%m-%dT%H:%M:%S.%f%z') - datetime.strptime(sup_receive_time, '%Y-%m-%dT%H:%M:%S.%f%z')).days > 7)
if (sup_sign_time == '' or sup_receive_time == ''):
df2['Overdue_SUP'] = None
else:
df2['sup_sign_time'] = None
df2['Overdue_SUP'] = None
df6 = df_nested_list[Mapping.keys()]
df4 = pd.DataFrame()
if len(x['data']["A04 Contractor's Management Team"]) > 0:
_df3 = df6.copy()
for c in x['data']["A04 Contractor's Management Team"]:
labourName = str(c['A04.1 Ctr Post'])
labourNum = 0
if ('A04.2 Ctr No.' in c) and not c['A04.2 Ctr No.'] is None:
labourNum = c['A04.2 Ctr No.']
else:
labourNum = 0
_df3['contractor_management_post_name'] = labourName
_df3['contractor_management_number'] = labourNum
df4 = df4.append(_df3)
df2.rename(columns=Mapping, inplace=True)
df4.rename(columns=Mapping, inplace=True)
df2.columns = df2.columns.str.replace(' ', '_').str.replace('.', '_').str.replace('(', '_').str.replace(')', '').str.replace('%', 'percent').str.replace('/', '_').str.replace('__', '_')
df4.columns = df4.columns.str.replace(' ', '_').str.replace('.', '_').str.replace('(', '_').str.replace(')', '').str.replace('%', 'percent').str.replace('/', '_').str.replace('__', '_')
df = df.append(df2)
_df = _df.append(df4)
df['a01_date']=df['a01_date'].apply(pd.to_datetime)
_df['a01_date']=_df['a01_date'].apply(pd.to_datetime)
df.to_sql('site_diary_general_dc201911', con=conn, if_exists='replace', index= False)
_df.to_sql('site_diary_general_contractor_management_dc201911', con=conn, if_exists='replace', index= False)
# */2 * * * * Execute every two minute
with DAG(
dag_id="dc201911_icwp_site_diary_general",
schedule_interval="20 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
|