-
Notifications
You must be signed in to change notification settings - Fork 0
/
lambda.py
91 lines (67 loc) · 2.48 KB
/
lambda.py
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
from datetime import datetime
import pandas as pd
import boto3
from io import StringIO
def handle_insert(record):
print("Handling Insert: ", record)
dict = {}
for key, value in record['dynamodb']['NewImage'].items():
for dt, col in value.items():
dict.update({key: col})
dff = pd.DataFrame([dict])
dff['EventType'] = record['eventName']
return dff
def handle_modify(record):
print("Handling Modify: ", record)
dict = {}
for key, value in record['dynamodb']['NewImage'].items():
for dt, col in value.items():
dict.update({key: col})
dff_insert = pd.DataFrame([dict])
dff_insert['EventType'] = "INSERT"
dict = {}
for key, value in record['dynamodb']['OldImage'].items():
for dt, col in value.items():
dict.update({key: col})
dff_remove = pd.DataFrame([dict])
dff_remove['EventType'] = "REMOVE"
return pd.concat([dff_insert, dff_remove], ignore_index=True)
def handle_remove(record):
print("Handle Remove: ", record)
dict = {}
for key, value in record['dynamodb']['OldImage'].items():
for dt, col in value.items():
dict.update({key: col})
dff = pd.DataFrame([dict])
dff['EventId'] = record['eventID']
dff['EventType'] = record['eventName']
return dff
def lambda_handler(event, context):
print(event)
df = pd.DataFrame()
for record in event['Records']:
table = record['eventSourceARN'].split("/")[1]
if record['eventName'] == "INSERT":
dff = handle_insert(record)
elif record['eventName'] == "MODIFY":
dff = handle_modify(record)
elif record['eventName'] == "REMOVE":
dff = handle_remove(record)
else:
continue
if dff is not None:
dff['created_at'] = record['dynamodb']['ApproximateCreationDateTime']
df = dff
if not df.empty:
all_columns = list(df)
df[all_columns] = df[all_columns].astype(str)
path = table + "_" + str(datetime.now()) + ".csv"
print(event)
csv_buffer = StringIO()
df.to_csv(csv_buffer,index=False)
s3 = boto3.client('s3')
bucketName = "project-de-datewithdata"
key = "staging/" + table + "/" + table + "_" + str(datetime.now()) + ".csv"
print(key)
s3.put_object(Bucket=bucketName, Key=key, Body=csv_buffer.getvalue(),)
print('Successfully processed %s records.' % str(len(event['Records'])))