Upload image available at public URL to S3 using boto

Question

I\'m working in a Python web environment and I can simply upload a file from the filesystem to S3 using boto\'s key.set_contents_from_filename(path/to/file). However, I\'d l

Answer 1

S3 doesn't support remote upload as of now it seems. You may use the below class for uploading an image to S3. The upload method here first tries to download the image and keeps it in memory for sometime until it gets uploaded. To be able to connect to S3 you will have to install AWS CLI using command pip install awscli, then enter few credentials using command aws configure:

import urllib3
import uuid
from pathlib import Path
from io import BytesIO
from errors import custom_exceptions as cex

BUCKET_NAME = "xxx.yyy.zzz"
POSTERS_BASE_PATH = "assets/wallcontent"
CLOUDFRONT_BASE_URL = "https://xxx.cloudfront.net/"


class S3(object):
    def __init__(self):
        self.client = boto3.client('s3')
        self.bucket_name = BUCKET_NAME
        self.posters_base_path = POSTERS_BASE_PATH

    def __download_image(self, url):
        manager = urllib3.PoolManager()
        try:
            res = manager.request('GET', url)
        except Exception:
            print("Could not download the image from URL: ", url)
            raise cex.ImageDownloadFailed
        return BytesIO(res.data)  # any file-like object that implements read()

    def upload_image(self, url):
        try:
            image_file = self.__download_image(url)
        except cex.ImageDownloadFailed:
            raise cex.ImageUploadFailed

        extension = Path(url).suffix
        id = uuid.uuid1().hex + extension
        final_path = self.posters_base_path + "/" + id
        try:
            self.client.upload_fileobj(image_file,
                                       self.bucket_name,
                                       final_path
                                       )
        except Exception:
            print("Image Upload Error for URL: ", url)
            raise cex.ImageUploadFailed

        return CLOUDFRONT_BASE_URL + id

Answer 2

For a 2017-relevant answer to this question which uses the official 'boto3' package (instead of the old 'boto' package from the original answer):

Python 3.5

If you're on a clean Python install, pip install both packages first:

pip install boto3

pip install requests

import boto3
import requests

# Uses the creds in ~/.aws/credentials
s3 = boto3.resource('s3')
bucket_name_to_upload_image_to = 'photos'
s3_image_filename = 'test_s3_image.png'
internet_image_url = 'https://docs.python.org/3.7/_static/py.png'


# Do this as a quick and easy check to make sure your S3 access is OK
for bucket in s3.buckets.all():
    if bucket.name == bucket_name_to_upload_image_to:
        print('Good to go. Found the bucket to upload the image into.')
        good_to_go = True

if not good_to_go:
    print('Not seeing your s3 bucket, might want to double check permissions in IAM')

# Given an Internet-accessible URL, download the image and upload it to S3,
# without needing to persist the image to disk locally
req_for_image = requests.get(internet_image_url, stream=True)
file_object_from_req = req_for_image.raw
req_data = file_object_from_req.read()

# Do the actual upload to s3
s3.Bucket(bucket_name_to_upload_image_to).put_object(Key=s3_image_filename, Body=req_data)

Answer 3

I have tried as following with boto3 and it works me:

import boto3;
import contextlib;
import requests;
from io import BytesIO;

s3 = boto3.resource('s3');
s3Client = boto3.client('s3')
for bucket in s3.buckets.all():
  print(bucket.name)


url = "@resource url";
with contextlib.closing(requests.get(url, stream=True, verify=False)) as response:
        # Set up file stream from response content.
        fp = BytesIO(response.content)
        # Upload data to S3
        s3Client.upload_fileobj(fp, 'aws-books', 'reviews_Electronics_5.json.gz')

Answer 4

Using the boto3 upload_fileobj method, you can stream a file to an S3 bucket, without saving to disk. Here is my function:

import boto3
import StringIO
import contextlib
import requests

def upload(url):
    # Get the service client
    s3 = boto3.client('s3')

    # Rember to se stream = True.
    with contextlib.closing(requests.get(url, stream=True, verify=False)) as response:
        # Set up file stream from response content.
        fp = StringIO.StringIO(response.content)
        # Upload data to S3
        s3.upload_fileobj(fp, 'my-bucket', 'my-dir/' + url.split('/')[-1])

Answer 5

Here is how I did it with requests, the key being to set stream=True when initially making the request, and uploading to s3 using the upload.fileobj() method:

import requests
import boto3

url = "https://upload.wikimedia.org/wikipedia/en/a/a9/Example.jpg"
r = requests.get(url, stream=True)

session = boto3.Session()
s3 = session.resource('s3')

bucket_name = 'your-bucket-name'
key = 'your-key-name' # key is the name of file on your bucket

bucket = s3.Bucket(bucket_name)
bucket.upload_fileobj(r.raw, key)

Answer 6

Ok, from @garnaat, it doesn't sound like S3 currently allows uploads by url. I managed to upload remote images to S3 by reading them into memory only. This works.

def upload(url):
    try:
        conn = boto.connect_s3(settings.AWS_ACCESS_KEY_ID, settings.AWS_SECRET_ACCESS_KEY)
        bucket_name = settings.AWS_STORAGE_BUCKET_NAME
        bucket = conn.get_bucket(bucket_name)
        k = Key(bucket)
        k.key = url.split('/')[::-1][0]    # In my situation, ids at the end are unique
        file_object = urllib2.urlopen(url)           # 'Like' a file object
        fp = StringIO.StringIO(file_object.read())   # Wrap object    
        k.set_contents_from_file(fp)
        return "Success"
    except Exception, e:
        return e

Also thanks to How can I create a GzipFile instance from the “file-like object” that urllib.urlopen() returns?