Generative AI for suspicious transaction report compliance

import boto3
from bs4 import BeautifulSoup
import os
import re
import urllib.request

BUCKET_NAME = os.getenv('S3_BUCKET')

s3 = boto3.client('s3')

def get_receiving_entity_from_url(start_url):

response = urllib.request.urlopen(
urllib.request.Request(url=start_url, method='GET'),
timeout=5)

soup = BeautifulSoup(response.read(), 'html.parser')

# Extract page title
title = soup.title.string if soup.title else 'Untitled'

# Extract page content for specific HTML elements
content = ' '.join(p.get_text() for p in soup.find_all(['p', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6']))

content = re.sub(r'\s+', ' ', content).strip()

s3.put_object(Body=content, Bucket=BUCKET_NAME, Key=f"docs/{title}.txt")

return content

Replace the default generated code in lambda_function.py with the following code:

import json
from search-suspicious-party import *

def lambda_handler(event, context):

# apiPath should match the path specified in action group schema
if event['apiPath'] == '/get-receiving-entity-details':
# Extract the property from request data
start_url = get_named_property(event, 'start_url')

scraped_text = get_receiving_entity_from_url(start_url)

action_response = {
'actionGroup': event['actionGroup'],
'apiPath': event['apiPath'],
'httpMethod': event['httpMethod'],
'httpStatusCode': 200,
'responseBody': {
'application/json': {
'body': json.dumps({'scraped_text': scraped_text})
}
}
}

return {'response': action_response}

# Return an error if apiPath is not recognized
return {
'statusCode': 400,
'body': json.dumps({'error': 'Invalid API path'})
}

def get_named_property(event, name):
return next(
item for item in
event['requestBody']['content']['application/json']['properties']
if item['name'] == name
)['value']

import json
from search-suspicious-party import *

def lambda_handler(event, context):

# apiPath should match the path specified in action group schema
if event['apiPath'] == '/get-receiving-entity-details':
# Extract the property from request data
start_url = get_named_property(event, 'start_url')

scraped_text = get_receiving_entity_from_url(start_url)

action_response = {
'actionGroup': event['actionGroup'],
'apiPath': event['apiPath'],
'httpMethod': event['httpMethod'],
'httpStatusCode': 200,
'responseBody': {
'application/json': {
'body': json.dumps({'scraped_text': scraped_text})
}
}
}

return {'response': action_response}

# Return an error if apiPath is not recognized
return {
'statusCode': 400,
'body': json.dumps({'error': 'Invalid API path'})
}

def get_named_property(event, name):
return next(
item for item in
event['requestBody']['content']['application/json']['properties']
if item['name'] == name
)['value']

openapi: 3.0.0
info:
title: Gather suspicious receiving entity details from website
version: 1.0.0
paths:
/get-suspicious-entity-details:
post:
description: Get details about suspicious receiving entity from the URL
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/ScrapeRequest"
responses:
"200":
description: Suspicious entity details gathered successfully
components:
schemas:
ScrapeRequest:
type: object
properties:
start_url:
type: string
description: The URL to start scraping from
required:
- start_url