Read s3 files (PDF)

import boto3
import json

def read_ocr_from_s3(bucket_name, key_name):
    s3 = boto3.client('s3')
    response = s3.get_object(Bucket=bucket_name, Key=key_name)
    ocr_data = json.loads(response['Body'].read().decode('utf-8'))
    return ''.join([item["text"] for item in ocr_data])

import boto3

def read_s3_file(bucket_name, file_name):
    s3 = boto3.client('s3')
    try:
        response = s3.get_object(Bucket=bucket_name, Key=file_name)
        return response['Body'].read().decode('utf-8')
    except Exception as e:
        print(f"Error reading file from S3: {e}")
        return None