Saving a pymupdf fitz object to s3 as a pdf

Question

I am trying to crop a pdf and save it to s3 with same name using lambda. I am getting error on the data type being a fitz.fitz.page

import os
import json
import boto3
from urllib.parse import unquote_plus
import fitz, sys
from io import BytesIO

OUTPUT_BUCKET_NAME = os.environ["OUTPUT_BUCKET_NAME"]
OUTPUT_S3_PREFIX = os.environ["OUTPUT_S3_PREFIX"]
SNS_TOPIC_ARN = os.environ["SNS_TOPIC_ARN"]
SNS_ROLE_ARN = os.environ["SNS_ROLE_ARN"]


def lambda_handler(event, context):

    textract = boto3.client("textract")
    if event:
        file_obj = event["Records"][0]
        bucketname = str(file_obj["s3"]["bucket"]["name"])
        filename = unquote_plus(str(file_obj["s3"]["object"]["key"]))
        
        doc = fitz.open()
        s3 = boto3.resource('s3')
        obj = s3.Object(bucketname, filename)
        fs = obj.get()['Body'].read()
        pdf=fitz.open("pdf", stream=BytesIO(fs))
        #pdf.close()
        
        
        rect=fitz.Rect(0.0, 0.0, 595.0, 842.0)
        #page = pdf[0]
        page1 = doc.new_page(width = rect.width,  # new page with ...
                       height = rect.height)
        page1.show_pdf_page(rect, pdf, 0)  
        print(type(doc))
        print(type(page1))
        
        s3.Bucket(bucketname).put_object(Key=filename, Body=page1)

Answer 1

For some reason for me the doc.write() method didn't return a bytes object like stated above. Here's an additional way to create a new doc , convert to bytes using BytesIO , and then save it to s3 as a pdf :

import fitz
from io import BytesIO

client = boto3.client("s3")

# create new doc object
single_page = fitz.open()

# insert a page from original_pdf_doc
single_page.insert_pdf(
    original_pdf_doc, from_page=from_page_num, to_page=to_page_num
)

# Use BytesIO and .write() method to save to a bytes object
bytes_ = BytesIO(single_page.write())

# Upload the bytes object!
client.put_object(Body=bytes_, Bucket=bucket, Key=key)

Answer 2

This is happening because the page1 object is defined using fitz.fitz.page and the type expected by S3 put object is bytes.

In order to solve the issue, you can use the write function of the new PDF ( doc ) and get the output of it which is in bytes format that you could pass to S3 then.

# Save fil first.
new_bytes = doc.write()
s3.Bucket(bucketname).put_object(Key=filename, Body=new_bytes)