Does anyone know how I can read PDFs off of a S3 bucket using `pdfplumber`?

Question:

I’m trying to read PDF files that are stored in a S3 bucket, using a Python package called pdfplumber. I tried the following approaches, but none of them has worked.

Does anyone know how I can read PDFs off of a S3 bucket using pdfplumber?

######################################################################
## attempt 1: supplying S3 URL directly to pdfplumber.open() method ##
######################################################################

import pdfplumber

s3_url = "s3://example-s3-bucket/example.pdf"

with pdfplumber.open(s3_url) as pdf:
  pages = pdf.pages

## ERROR -- AttributeError: 'S3' object has no attribute 'seek'




#####################################################
## attempt 2: opening content using pre-signed URL ##
#####################################################

import pdfplumber
import boto3

s3 = boto3.client('s3')

pdf_url = s3.generate_presigned_url(
    'get_object',
    Params={'Bucket': 'example-s3-bucket', 'Key': 'example.pdf'},
    ExpiresIn=3600  # Set an expiration time for the URL if needed
)

with pdfplumber.open(pdf_url) as pdf:
  pages = pdf.pages

## ERROR -- OSError: [Errno 63] File name too long:




############################################################
## attempt 3: supplying bytes to pdfplumber.open() method ##
############################################################

import pdfplumber
import boto3

s3 = boto3.client('s3')

bucket_name = "example-s3-bucket"
file_key = "example.pdf"

response = s3.get_object(Bucket=bucket_name, Key=file_key)

file_bytes = response['Body'].read()

with pdfplumber.open(file_bytes) as pdf:
  pages = pdf.pages

## ERROR -- AttributeError: 'bytes' object has no attribute 'seek'
Asked By: Howard S

||

Answers:

The package repo owner (jsvine) responded with a solution:
https://github.com/jsvine/pdfplumber/discussions/1081

import pdfplumber
import boto3
import io

s3 = boto3.client('s3')

bucket_name = "example-s3-bucket"
file_key = "example.pdf"

response = s3.get_object(Bucket=bucket_name, Key=file_key)

file_bytes = response['Body'].read()

with pdfplumber.open(io.BytesIO(my_bytes)) as pdf:
  pages = pdf.pages
Answered By: Howard S