WordAnalysis.py

import urllib
import boto3
import requests

print('Loading function')

s3 = boto3.client('s3')
# someday i will need to learn how to use AWS
s3_resource = boto3.resource('s3')


def lambda_handler(event, context):
    # Get the object from the event
    bucket = event['Records'][0]['s3']['bucket']['name']
    key = urllib.unquote_plus(event['Records'][0]['s3']['object']['key']).decode('utf8')
    destbucket = 'lambda-vinod-dest'

    thousand_words_url = 'https://gist.githubusercontent.com/deekayen/4148741/raw/01c6252ccc5b5fb307c1bb899c95989a8a284616/1-1000.txt'
    thousand_words = requests.get(thousand_words_url).content.split()
    try:
        response = s3.get_object(Bucket=bucket, Key=key)
        content = response['Body'].read()

        # how many words
        word_list = content.split()
        print('Word count: {}'.format(len(word_list)))

        # sentiment analysis
        r = requests.post('http://text-processing.com/api/sentiment/',
                          data={'text': content})
        print(r.text)

        # Remove any words not in the top 1000 and save to new bucket
        fixed_content = ' '.join([word for word in content.split() if word.lower() in thousand_words])
        s3_resource.Bucket(destbucket).put_object(Key='dest'+key, Body=fixed_content)
        return
    except Exception as e:
        print(e)
        print('Error getting object {} from bucket {}. Make sure they exist and your bucket is in the same region as this function.'.format(key, bucket))
        raise e