Created
June 7, 2020 07:59
-
-
Save kntmr/c1fcb243859d7f979c8ec41439e8b792 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import json | |
import urllib.parse | |
import boto3 | |
import datetime | |
print('Loading function') | |
s3 = boto3.client('s3') | |
def read_input_text(bucket_name, input_key): | |
obj = s3.get_object(Bucket = bucket_name, Key = input_key) | |
body = obj['Body'].read().decode('utf-8') | |
return json.loads(body)['results']['transcripts'][0]['transcript'] | |
def translate_text(text): | |
translate = boto3.client('translate') | |
response = translate.translate_text( | |
Text = text, | |
SourceLanguageCode = 'en', | |
TargetLanguageCode = 'ja' | |
) | |
return response['TranslatedText'] | |
def upload_json(bucket_name, output_key, json_text): | |
resource_s3 = boto3.resource('s3') | |
obj = resource_s3.Object(bucket_name, output_key) | |
obj.put(Key = output_key, Body = json_text) | |
def lambda_handler(event, context): | |
bucket = event['Records'][0]['s3']['bucket']['name'] | |
input_key = urllib.parse.unquote_plus(event['Records'][0]['s3']['object']['key'], encoding='utf-8') | |
try: | |
input_text = read_input_text(bucket, input_key) | |
translated_text = translate_text(input_text) | |
output_key = datetime.datetime.now().strftime("%Y%m%d%H%M%S") + '_translated.json' | |
json_text = json.dumps({ | |
'input_text': input_text, | |
'translated_text': translated_text | |
}, ensure_ascii = False) | |
upload_json(bucket, output_key, json_text) | |
except Exception as e: | |
print(e) | |
raise e |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment