def read_from_s3(aws_env):
bucket_name = aws_env['bucketName']
s3_file_name = aws_env['objectName']
aws_region = aws_env['awsRegion']
s3 = AwsHelper().getResource('s3', aws_region)
obj = s3.Object(bucket_name, s3_file_name)
encoding = "utf-8"
try:
content = obj.get()['Body'].read()
except Exception as e:
print(e)
return
try:
encoding = chardet.detect(content)['encoding']
print("Trying to decode with {}".format(encoding))
content_decoded = content.decode(encoding)
return content_decoded
except UnicodeDecodeError as e:
print("Failing to decode with encoding {0}: {1}".format(encoding, e))
try:
print("Trying by removing the last character")
content_without_last_char = content[:-1].decode(encoding)
return content_without_last_char
except UnicodeDecodeError as e:
print("Failing to decode: {}".format(e))
print("Returning content in bytes")
return content
def convert_html_to_pdf(html_str, aws_env):
aws_region = aws_env['awsRegion']
output_bucket = aws_env['outputBucket']
output_file = aws_env['outputName']
output_content = BytesIO()
if html_str is None:
return {"status": -1, "errorMessage": "PDF is empty"}
print("Writing s3://%s/%s in %s" %
(output_bucket, output_file, aws_region))
s3 = AwsHelper().getResource('s3', aws_region)
s3_obj = s3.Object(output_bucket, output_file)
try:
pisa.CreatePDF(html_str, dest=output_content)
content = output_content.getvalue().decode("utf-8", errors="ignore")
s3_obj.put(Body=content)
except ValueError as e:
print(e)
return {"status": -1, "errorMessage": "PDF format not supported."}
return {"status": 1, "errorMessage": None}
def read_bytes_from_s3(bucketName, s3FileName, awsRegion=None):
s3 = AwsHelper().getResource('s3', awsRegion)
obj = s3.Object(bucketName, s3FileName)
content = obj.get()['Body'].read()
buffer = BytesIO(content)
return buffer