mahi424/html-to-pdf-via-lambda.py

## html-to-pdf-via-lambda.py
import subprocess
import os
import boto3
import json
import base64

# https://github.com/wkhtmltopdf/packaging/releases/download/0.12.6-4/wkhtmltox-0.12.6-4.amazonlinux2_lambda.zip
# add this as layer

region_name = 'ap-south-1'
s3 = boto3.client('s3')

def getEventBody(event):
    try:
        body = json.loads(event['body'])
        return body
    except json.JSONDecodeError as e:
        print('Bad Request: Invalid JSON', e)
        raise e

def getKeyFromEvent(event, key='html'):
    body = getEventBody(event)
    try:
        val = body.get(key)
        return val
    except Exception as e:
        print(e)
        raise e

def get_base64_of_pdf(pdf_file_path):
    try:
        with open(pdf_file_path, "rb") as pdf_file:
            pdf_content = pdf_file.read()
        base64_pdf = base64.b64encode(pdf_content).decode('utf-8')
        return base64_pdf
        print("PDF encoded in base64")
    except Exception as e:
        print(f"Failed to encode PDF in base64: {str(e)}")
        return {
            'statusCode': 500,
            'body': 'Failed to encode PDF'
        }

def uploadToS3(pdf_file_path, pdf_key, bucket_name):
    try:
        s3.upload_file(pdf_file_path, bucket_name, pdf_key, ExtraArgs={'ContentType': 'application/pdf'})
        print(f"PDF uploaded to: s3://{bucket_name}/{pdf_key}")
        # Constructing the S3 URL
        s3_url = f"https://{bucket_name}.s3.{region_name}.amazonaws.com/{pdf_key}"

        print(f"Object URL: {s3_url}")
        return s3_url
    except Exception as e:
        print("Error uploading PDF to S3:", str(e))
        raise e

def lambda_handler(event, context):
    html_data = getKeyFromEvent(event, "html")
    pdf_filename = getKeyFromEvent(event, "filename")
    path = getKeyFromEvent(event, "path")
    bucket = getKeyFromEvent(event, "bucket")
    return_base_64 = False

    try:
        return_base_64 = getKeyFromEvent(event, "return_base_64") == True
    except Exception as e:
        return_base_64 = False

    print(pdf_filename, path, bucket)

    html_file_path = "/tmp/input.html"
    pdf_file_path = "/tmp/output.pdf"

    try:
        with open(html_file_path, "w") as f:
            f.write(html_data)

        print('file written')
    except Exception as e:
        print(e)
        raise e

    # Convert HTML to PDF using wkhtmltopdf
    print('writing pdf')
    try:
        process = subprocess.Popen(["wkhtmltopdf", html_file_path, pdf_file_path], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
        stdout, stderr = process.communicate()
        if process.returncode != 0:
            print(f"Failed to convert HTML to PDF. Stdout: {stdout.decode()}, Stderr: {stderr.decode()}")
        else:
            print('pdf written')
    except Exception as e:
        print(e)
        print(f"Failed to convert HTML to PDF: {str(e)}")
    # try:
    #     subprocess.run(["wkhtmltopdf", html_file_path, pdf_file_path], check=True)
    #     print('pdf written')
    # except Exception as e:
    #     print(e)
    #     print(f"Failed to convert HTML to PDF: {str(e)}")
    # path = aadhaar_xml
    file_key = f'{path}/{pdf_filename}'
    try:
        s3_url = uploadToS3(pdf_file_path, file_key, bucket)
        print('s3_url', s3_url)
    except Exception as e:
        print(f"Failed to upload PDF to S3: {str(e)}")
        return {
            'statusCode': 500,
            'body': 'Failed to upload PDF to S3'
        }

    base_64 = ""

    if return_base_64:
        base_64 = get_base64_of_pdf(pdf_file_path)
    # s3_url = '123456'
    try:
        os.remove(html_file_path)
        os.remove(pdf_file_path)
    except Exception as e:
        print(e)
        raise e

    return {
        'statusCode': 200,
        'body': json.dumps({'s3_url': s3_url, 'base_64': base_64})
    }
	import subprocess
	import os
	import boto3
	import json
	import base64

	# https://github.com/wkhtmltopdf/packaging/releases/download/0.12.6-4/wkhtmltox-0.12.6-4.amazonlinux2_lambda.zip
	# add this as layer

	region_name = 'ap-south-1'
	s3 = boto3.client('s3')

	def getEventBody(event):
	try:
	body = json.loads(event['body'])
	return body
	except json.JSONDecodeError as e:
	print('Bad Request: Invalid JSON', e)
	raise e

	def getKeyFromEvent(event, key='html'):
	body = getEventBody(event)
	try:
	val = body.get(key)
	return val
	except Exception as e:
	print(e)
	raise e

	def get_base64_of_pdf(pdf_file_path):
	try:
	with open(pdf_file_path, "rb") as pdf_file:
	pdf_content = pdf_file.read()
	base64_pdf = base64.b64encode(pdf_content).decode('utf-8')
	return base64_pdf
	print("PDF encoded in base64")
	except Exception as e:
	print(f"Failed to encode PDF in base64: {str(e)}")
	return {
	'statusCode': 500,
	'body': 'Failed to encode PDF'
	}

	def uploadToS3(pdf_file_path, pdf_key, bucket_name):
	try:
	s3.upload_file(pdf_file_path, bucket_name, pdf_key, ExtraArgs={'ContentType': 'application/pdf'})
	print(f"PDF uploaded to: s3://{bucket_name}/{pdf_key}")
	# Constructing the S3 URL
	s3_url = f"https://{bucket_name}.s3.{region_name}.amazonaws.com/{pdf_key}"

	print(f"Object URL: {s3_url}")
	return s3_url
	except Exception as e:
	print("Error uploading PDF to S3:", str(e))
	raise e

	def lambda_handler(event, context):
	html_data = getKeyFromEvent(event, "html")
	pdf_filename = getKeyFromEvent(event, "filename")
	path = getKeyFromEvent(event, "path")
	bucket = getKeyFromEvent(event, "bucket")
	return_base_64 = False

	try:
	return_base_64 = getKeyFromEvent(event, "return_base_64") == True
	except Exception as e:
	return_base_64 = False

	print(pdf_filename, path, bucket)

	html_file_path = "/tmp/input.html"
	pdf_file_path = "/tmp/output.pdf"

	try:
	with open(html_file_path, "w") as f:
	f.write(html_data)

	print('file written')
	except Exception as e:
	print(e)
	raise e

	# Convert HTML to PDF using wkhtmltopdf
	print('writing pdf')
	try:
	process = subprocess.Popen(["wkhtmltopdf", html_file_path, pdf_file_path], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
	stdout, stderr = process.communicate()
	if process.returncode != 0:
	print(f"Failed to convert HTML to PDF. Stdout: {stdout.decode()}, Stderr: {stderr.decode()}")
	else:
	print('pdf written')
	except Exception as e:
	print(e)
	print(f"Failed to convert HTML to PDF: {str(e)}")
	# try:
	# subprocess.run(["wkhtmltopdf", html_file_path, pdf_file_path], check=True)
	# print('pdf written')
	# except Exception as e:
	# print(e)
	# print(f"Failed to convert HTML to PDF: {str(e)}")
	# path = aadhaar_xml
	file_key = f'{path}/{pdf_filename}'
	try:
	s3_url = uploadToS3(pdf_file_path, file_key, bucket)
	print('s3_url', s3_url)
	except Exception as e:
	print(f"Failed to upload PDF to S3: {str(e)}")
	return {
	'statusCode': 500,
	'body': 'Failed to upload PDF to S3'
	}

	base_64 = ""

	if return_base_64:
	base_64 = get_base64_of_pdf(pdf_file_path)
	# s3_url = '123456'
	try:
	os.remove(html_file_path)
	os.remove(pdf_file_path)
	except Exception as e:
	print(e)
	raise e

	return {
	'statusCode': 200,
	'body': json.dumps({'s3_url': s3_url, 'base_64': base_64})
	}