lambdaでpdf変換をやってみた

import json

def handler(event, context):
    return {
        "statusCode": 200,
        "body": json.dumps(
            {
                "message": "hello world",
            }
        ),
    }

FROM public.ecr.aws/lambda/python:3.12
COPY app.py ${LAMBDA_TASK_ROOT}
CMD ["app.handler"]

$ docker build -t func1 .

ERROR: failed to solve: public.ecr.aws/lambda/python:3.12: failed to resolve source metadata for public.ecr.aws/lambda/python:3.12: error getting credentials - err: exec: "docker-credential-desktop.exe": executable file not found in $PATH, out: ``

$ docker run -d -p 9000:8080 func1

$ curl -d '{}' http://localhost:9000/2015-03-31/functions/function/invocations
{"statusCode": 200, "body": "{\"message\": \"hello world\"}"}

# Pull the base image with python 3.11 as a runtime for your Lambda
FROM public.ecr.aws/lambda/python:3.11

# Install OS packages
RUN yum -y install wget tar gzip zlib freetype-devel openssl
RUN yum -y install libxslt \
    gcc \
    ghostscript \
    lcms2-devel \
    libffi-devel \
    libjpeg-devel \
    libtiff-devel \
    libwebp-devel \
    make \
    openjpeg2-devel \
    sudo \
    tcl-devel \
    tk-devel \
    which \
    xorg-x11-server-Xvfb \
    zlib-devel \
    java \
    && yum clean all

RUN wget https://downloadarchive.documentfoundation.org/libreoffice/old/7.6.7.2/rpm/x86_64/LibreOffice_7.6.7.2_Linux_x86-64_rpm.tar.gz
RUN tar -xvzf LibreOffice_7.6.7.2_Linux_x86-64_rpm.tar.gz
RUN cd LibreOffice_7.6.7.2_Linux_x86-64_rpm/RPMS; yum -y localinstall *.rpm;
RUN yum -y install cairo

COPY app.py ${LAMBDA_TASK_ROOT}
CMD ["app.handler"]

import json
import subprocess
# import boto3 # type: ignore
import os
import urllib.parse

# s3 = boto3.resource('s3')
# output_bucket = "libreoffice-out"

def handler(event, context):
    # if 'Records' in event.keys():
    #     input_bucket = event['Records'][0]['s3']['bucket']['name']
    #     input_key = urllib.parse.unquote_plus(event['Records'][0]['s3']['object']['key'], encoding='utf-8')
    #     in_bucket = s3.Bucket(input_bucket)
    # else :
    #     return 'test finished'

    input_key = 'test.xlsx'
    print(input_key)
    # get S3 Object
    file_path = '/tmp/'+input_key
    # in_bucket.download_file(input_key, file_path)

    proc = subprocess.run("/opt/libreoffice7.6/program/soffice --headless --norestore --invisible --nodefault --nofirststartwizard --nolockcheck --nologo --convert-to pdf:writer_pdf_Export --outdir /tmp {}".format("/tmp/"+input_key), shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
    print('STDOUT: {}'.format(proc.stdout))
    print('STDERR: {}'.format(proc.stderr))

    key_list = input_key.split('.')
    pdf_path = "/tmp/"+input_key.replace(key_list[-1], 'pdf')

    # put S3 Object
    if os.path.exists(pdf_path):
        print('PDF: {}'.format(pdf_path.replace("/tmp/", "")))
        print('Size: {}'.format(os.path.getsize(pdf_path)))
        data = open(pdf_path, 'rb')
        # out_bucket = s3.Bucket(output_bucket)
        # out_bucket.put_object(Key=pdf_path.replace("/tmp/", ""),Body=data)
        data.close()
    else :
        print("The PDF file({}) cannot be found".format(pdf_path))

    return ''

$ docker build -t py-pdf:latest .

$ docker run --name app --volume ./src:/tmp  -p 8080:8080 py-pdf:latest

$ curl -XPOST "http://localhost:8080/2015-03-31/functions/function/invocations" -d '{}'

$ ls -l ./src/
total 300
drwxr-xr-x 2 root      root        4096 Oct 31 21:38 hsperfdata_root
-rw-r--r-- 1 root      root      212201 Oct 31 21:38 test.pdf
-rw-rw-r-- 1 hoge hoge  88757 Oct 31 20:42 test.xlsx