tesu_scraper_02

#Save our s3 word docs to the EC2 instance

bucket_name = 'name_of_s3_bucket' # replace with your bucket name
session = Session(aws_access_key_id=ACCESS_KEY,
                  aws_secret_access_key=SECRET_KEY)
s3 = session.resource('s3')

#for loop to loop through all files in the file_list and downlaod them to the EC2 instance.
for word_doc in file_list:
#word_doc is the name of our file, as a string.
    KEY = word_doc
    ec2_file_name = "../ec2docs/"+word_doc[5:]
    
    try:
        s3.Bucket(bucket_name).download_file(KEY, ec2_file_name)
    except botocore.exceptions.ClientError as e:
        if e.response['Error']['Code'] == "404":
            continue
            #print("The object does not exist.")
        else:
            raise