#!/usr/bin/env python3
import sys
import boto3
s3 = boto3.resource("s3")
bucket_name = sys.argv[1]
object_name = sys.argv[2]
try:
response = s3.Object(bucket_name,
object_name).put(Body=open(object_name, 'rb'))
print (response)
except Exception as error:
print (error)
That's my put_bucket function that puts objects into buckets but I need it done with little to no user input once I call the main program, basically automatic.
import sys
import boto3
ec2 = boto3.resource('ec2', region_name = 'eu-west-1')
s3 = boto3.resource('s3')
keyname = 'AlexBpem.pem'
user_data = '''#!/bin/bash
yum update -y
yum install httpd -y
systemctl enable httpd
systemctl start httpd'''
s3.create_bucket(Bucket='ec2-assignbuke2',CreateBucketConfiguration={'LocationConstraint': 'eu-west-1'})
sg = ec2.create_security_group(GroupName='MyWebServer', Description = 'WebServer', VpcId='vpc-0dea879f34afff60d')
instance = ec2.create_instances(
ImageId='ami-0fc970315c2d38f01',
MinCount=1,
MaxCount=1,
InstanceType='t2.nano',
KeyName = 'AlexBpem',
UserData = user_data,
SecurityGroupIds=[ sg.group_id ],
SubnetId = 'subnet-06add059500af7905'
)
for bucket_name in sys.argv[1:]:
try:
response = s3.create_bucket(Bucket=ec2-assignbuke2,
CreateBucketConfiguration={'LocationConstraint': 'eu-west-1'})
print (response)
except Exception as error:
print (error)
Is my main program, how would I go abouts using (def) functions within my code to make this call automatic.
To convert your inline 'upload to S3' code into a function, you can do this:
#!/usr/bin/env python3
import sys
import boto3
s3 = boto3.resource("s3")
def upload_to_s3(filename, bucket, key):
try:
response = s3.Object(bucket, key).put(Body=open(filename, 'rb'))
print (response)
return response
except Exception as error:
print (error)
To call this function, you can do this:
file = '/home/users/james/dogs/toto.png'
bkt = 'mybucket'
key = 'dogs/tot.png'
rsp = upload_to_s3(file, bkt, key)
Related
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 like to upload an image that is already on the web (say https://pbs.twimg.com/media/A9h_htACIAAaCf6.jpg:large).
Should I somehow download the image to the filesystem, and then upload it to S3 using boto as usual, then delete the image?
What would be ideal is if there is a way to get boto's key.set_contents_from_file or some other command that would accept a URL and nicely stream the image to S3 without having to explicitly download a file copy to my server.
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 = "test"
k.set_contents_from_file(url)
k.make_public()
return "Success?"
except Exception, e:
return e
Using set_contents_from_file, as above, I get a "string object has no attribute 'tell'" error. Using set_contents_from_filename with the url, I get a No such file or directory error . The boto storage documentation leaves off at uploading local files and does not mention uploading files stored remotely.
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)
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?
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)
Unfortunately, there really isn't any way to do this. At least not at the moment. We could add a method to boto, say set_contents_from_url, but that method would still have to download the file to the local machine and then upload it. It might still be a convenient method but it wouldn't save you anything.
In order to do what you really want to do, we would need to have some capability on the S3 service itself that would allow us to pass it the URL and have it store the URL to a bucket for us. That sounds like a pretty useful feature. You might want to post that to the S3 forums.
A simple 3-lines implementation that works on a lambda out-of-the-box:
import boto3
import requests
s3_object = boto3.resource('s3').Object(bucket_name, object_key)
with requests.get(url, stream=True) as r:
s3_object.put(Body=r.content)
The source for the .get part comes straight from the requests documentation
from io import BytesIO
def send_image_to_s3(url, name):
print("sending image")
bucket_name = 'XXX'
AWS_SECRET_ACCESS_KEY = "XXX"
AWS_ACCESS_KEY_ID = "XXX"
s3 = boto3.client('s3', aws_access_key_id=AWS_ACCESS_KEY_ID,
aws_secret_access_key=AWS_SECRET_ACCESS_KEY)
response = requests.get(url)
img = BytesIO(response.content)
file_name = f'path/{name}'
print('sending {}'.format(file_name))
r = s3.upload_fileobj(img, bucket_name, file_name)
s3_path = 'path/' + name
return s3_path
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')
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])
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
import boto
from boto.s3.key import Key
from boto.s3.connection import OrdinaryCallingFormat
from urllib import urlopen
def upload_images_s3(img_url):
try:
connection = boto.connect_s3('access_key', 'secret_key', calling_format=OrdinaryCallingFormat())
bucket = connection.get_bucket('boto-demo-1519388451')
file_obj = Key(bucket)
file_obj.key = img_url.split('/')[::-1][0]
fp = urlopen(img_url)
result = file_obj.set_contents_from_string(fp.read())
except Exception, e:
return e
Boto3 is installed but when I try to use the below function to upload an image to an S3 bucket I get global name 's3' is not defined error.
Is there something I'm missing?
import logging
import boto3
from botocore.exceptions import ClientError
import os
def upload_file(file_name, bucket, object_name=None):
if object_name is None:
object_name = os.path.basename(file_name)
s3_client = boto3.resource('s3')
try:
response = s3.client.upload_file(file_name, bucket,
object_name)
except ClientError as e:
logging.error(e)
return False
return True
upload = upload_file('test1.jpg','mybucket', 'test1.jpg')
This line:
response = s3.client.upload_file(file_name, bucket, object_name)
should be:
response = s3_client.upload_file(file_name, bucket, object_name)
I wrote a lambda function to download the csv file to s3 and created API Gateway
import os
import uuid
import boto3
from botocore.exceptions import ClientError
SECRET_KEY = os.environ["SECRET_KEY"]
ACCESS_KEY = os.environ["ACCESS_KEY"]
def lambda_handler(event, context):
# TODO implement
bucket = event['bucket']
object_name = '{}.csv'.format(uuid.uuid1())
file_name = event['filename']
s3_client = boto3.client('s3', aws_access_key_id=ACCESS_KEY, aws_secret_access_key=SECRET_KEY)
try:
response = s3_client.upload_file(file_name, bucket, object_name)
except ClientError as e:
logging.error(e)
return e
return True
When I run this code using the test event directly through the aws interface
test case
{
"bucket": "testcsvupload-drv-cvbx",
"filename": "file.csv",
"key3": "value3"
}
I got successful result. But then I trying using curl request fron linux console
curl -X POST https://tvomerrrcfa.execute-api.us-east-1.amazonaws.com/file_to_s3 -H "Content-Type: multipart/form-data" -F 'filename=#/home/y700/projects/start/file.csv'
I get an error
{"message": "Could not parse request body into json: Unexpected character (\'-\' (code 45)) in numeric value: expected digit (0-9) to follow minus sign, for valid numeric value\n at [Source: (byte[])\"--------------------------e6b7a9fa3c5b61d0\r\nContent-Disposition: form-data; name=\"filename\"; filename=\"file.csv\"\r\nContent-Type: application\/octet-stream\r\n\r\nname,surname,age\nTim,Bert,19\nHelen,Glad,23\n\r\n--------------------------e6b7a9fa3c5b61d0--\r\n\"; line: 1, column: 3]"}
file.csv
name,surname,age
Tim,Bert,19
Helen,Glad,23
What am I doing wrong? And why is json referenced in the error?
I have tried various attempts to estalish a connection to an S3 compatible service but I keep getting an error. The following code throws the error below. Any ideas?
import os
import boto
import boto.s3.connection
from boto.s3.key import Key
try:
conn = boto.s3.connect_to_region(region = 'nil',
aws_access_key_id = 'xx',
aws_secret_access_key = 'xx',
host = 'ds41s3-scs.xx.com',
calling_format = boto.s3.connection.OrdinaryCallingFormat(),
)
response = s3.list_buckets()
except Exception,e:
print str(e)
print "error"
The error:
TypeError: connect_to_region() missing 1 required positional argument: 'region_name'
Why is the region set to nil? The signature of connect_to_region is:
boto.s3.connect_to_region(region_name, **kw_params)
You are missing the mandatory argument: region_name
Go for latest version of AWS SDK for python (boto3) which supports latest features
import boto3
client = boto3.client('s3')
response = client.list_buckets()
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 like to upload an image that is already on the web (say https://pbs.twimg.com/media/A9h_htACIAAaCf6.jpg:large).
Should I somehow download the image to the filesystem, and then upload it to S3 using boto as usual, then delete the image?
What would be ideal is if there is a way to get boto's key.set_contents_from_file or some other command that would accept a URL and nicely stream the image to S3 without having to explicitly download a file copy to my server.
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 = "test"
k.set_contents_from_file(url)
k.make_public()
return "Success?"
except Exception, e:
return e
Using set_contents_from_file, as above, I get a "string object has no attribute 'tell'" error. Using set_contents_from_filename with the url, I get a No such file or directory error . The boto storage documentation leaves off at uploading local files and does not mention uploading files stored remotely.
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)
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?
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)
Unfortunately, there really isn't any way to do this. At least not at the moment. We could add a method to boto, say set_contents_from_url, but that method would still have to download the file to the local machine and then upload it. It might still be a convenient method but it wouldn't save you anything.
In order to do what you really want to do, we would need to have some capability on the S3 service itself that would allow us to pass it the URL and have it store the URL to a bucket for us. That sounds like a pretty useful feature. You might want to post that to the S3 forums.
A simple 3-lines implementation that works on a lambda out-of-the-box:
import boto3
import requests
s3_object = boto3.resource('s3').Object(bucket_name, object_key)
with requests.get(url, stream=True) as r:
s3_object.put(Body=r.content)
The source for the .get part comes straight from the requests documentation
from io import BytesIO
def send_image_to_s3(url, name):
print("sending image")
bucket_name = 'XXX'
AWS_SECRET_ACCESS_KEY = "XXX"
AWS_ACCESS_KEY_ID = "XXX"
s3 = boto3.client('s3', aws_access_key_id=AWS_ACCESS_KEY_ID,
aws_secret_access_key=AWS_SECRET_ACCESS_KEY)
response = requests.get(url)
img = BytesIO(response.content)
file_name = f'path/{name}'
print('sending {}'.format(file_name))
r = s3.upload_fileobj(img, bucket_name, file_name)
s3_path = 'path/' + name
return s3_path
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')
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])
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
import boto
from boto.s3.key import Key
from boto.s3.connection import OrdinaryCallingFormat
from urllib import urlopen
def upload_images_s3(img_url):
try:
connection = boto.connect_s3('access_key', 'secret_key', calling_format=OrdinaryCallingFormat())
bucket = connection.get_bucket('boto-demo-1519388451')
file_obj = Key(bucket)
file_obj.key = img_url.split('/')[::-1][0]
fp = urlopen(img_url)
result = file_obj.set_contents_from_string(fp.read())
except Exception, e:
return e