lambdaの中でcomprehend apiを呼び出す

detect_dominant_language.py

import json
import tempfile
import boto3
from uuid import uuid4

# Comprehend constant
REGION = 'us-west-2'


# Function for detecting the dominant language
def detect_dominant_language(text):
    comprehend = boto3.client('comprehend', region_name=REGION)
    response = comprehend.detect_dominant_language(Text=text)
    return response


# Function for detecting named entities
def detect_entities(text, language_code):
    comprehend = boto3.client('comprehend', region_name=REGION)
    response = comprehend.detect_entities(Text=text, LanguageCode=language_code)
    return response


# Function for detecting key phrases
def detect_key_phraes(text, language_code):
    comprehend = boto3.client('comprehend', region_name=REGION)
    response = comprehend.detect_key_phrases(Text=text, LanguageCode=language_code)
    return response


# Function for detecting sentiment
def detect_sentiment(text, language_code):
    comprehend = boto3.client('comprehend', region_name=REGION)
    response = comprehend.detect_sentiment(Text=text, LanguageCode=language_code)
    return response


def get_object_path(event):
    bucketName = event['Input']['detail']['requestParameters']['bucketName']
    objectKey  = event['Input']['detail']['requestParameters']['key']
    return bucketName, objectKey


def get_downloaded_file_path(bucketName, key):
    s3 = boto3.resource('s3')
    bucket = s3.Bucket(bucketName)
    obj = bucket.Object(key)
    
    tmpFilePath = '/tmp/'+str(uuid4())
    with open(tmpFilePath, 'wb') as fp:
        obj.download_fileobj(fp)
    
    return tmpFilePath


def lambda_handler(event, context):
    print(json.dumps(event))
    
    # text
    text = "Amazon Comprehend is a natural language processing (NLP) service that uses machine learning to find insights and relationships in text."
    
    bucketName, key = get_object_path(event)
    local_path = get_downloaded_file_path(bucketName, key)
    with open(local_path) as fp:
        text = fp.read()

    print(text)
    
    # language code
    language_code = 'en'

    # detecting the dominant language
    result = detect_dominant_language(text)
    print("Starting detecting the dominant language")
    print(json.dumps(result, sort_keys=True))
    print("End of detecting the dominant language\n")

    primary_language = max(result['Languages'], key=lambda elm: elm['Score'])
    print('Primary language detected.')
    print(json.dumps(primary_language))
    primary_language['Text'] = text
    
    return json.dumps(primary_language)
    
     

参考
https://dev.classmethod.jp/cloud/comprehend-operations-using-python-boto3-ja/