Created
March 10, 2023 05:38
-
-
Save harupy/cafc16f45a850dad203c11f5e58184fc to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import boto3 | |
import requests | |
import uuid | |
import tempfile | |
from pathlib import Path | |
import sys | |
with tempfile.TemporaryDirectory() as tmpdir: | |
# Create a 500MB file | |
print("Creating a large file") | |
path = Path(tmpdir) / uuid.uuid4().hex | |
with path.open("wb") as f: | |
f.seek(25 * 1024 * 1024 - 1) # 100MB | |
f.write(b"\0") | |
# Generate presigned URLs for each part of the file | |
s3 = boto3.client("s3") | |
bucket = sys.argv[1] | |
key = path.name | |
resp = s3.create_multipart_upload(Bucket=bucket, Key=key) | |
upload_id = resp["UploadId"] | |
chunk_size = 10 * 1024 * 1024 # 20MB = 5 parts | |
num_parts = path.stat().st_size // chunk_size + 1 | |
urls = [] | |
for i in range(num_parts): | |
part_number = i + 1 | |
print(f"generating presigned URL for part {part_number}") | |
presigned_url = s3.generate_presigned_url( | |
"upload_part", | |
Params={ | |
"Bucket": bucket, | |
"Key": key, | |
"PartNumber": part_number, | |
"UploadId": upload_id, | |
}, | |
ExpiresIn=3600, | |
HttpMethod="PUT", | |
) | |
urls.append(presigned_url) | |
# Upload each part | |
parts = [] | |
with path.open("rb") as f: | |
for i in range(num_parts): | |
part_number = i + 1 | |
print(f"uploading part {part_number}") | |
data = f.read(chunk_size) | |
resp = requests.put(urls[i], data=data) | |
resp.raise_for_status() | |
etag = resp.headers["ETag"] | |
print(etag) | |
parts.append({"PartNumber": part_number, "ETag": etag}) | |
# Generate presigned URL for CompleteMultipartUpload | |
presigned_url = s3.generate_presigned_url( | |
"complete_multipart_upload", | |
Params={ | |
"Bucket": bucket, | |
"Key": key, | |
"UploadId": upload_id, | |
}, | |
ExpiresIn=3600, | |
HttpMethod="POST", | |
) | |
xml = "".join( | |
[ | |
f"<Part><ETag>{part['ETag']}</ETag><PartNumber>{part['PartNumber']}</PartNumber></Part>" | |
for part in parts | |
] | |
) | |
xml = f'<CompleteMultipartUpload xmlns="http://s3.amazonaws.com/doc/2006-03-01/">{xml}</CompleteMultipartUpload>' | |
# print(xmltodict.unparse({"Parts": parts}, expand_iter="Part")) | |
r = requests.post(presigned_url, data=xml) | |
r.raise_for_status() | |
print("DONE") |
Author
harupy
commented
Mar 10, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment