I want to copy a file in s3 bucket using python.
Ex : I have bucket name = test. And in the bucket, I have 2 folders name "dump" & "input". Now I want to copy a file from local directory to S3 "dump" folder using python... Can anyone help me?
This question is related to
python
amazon-web-services
amazon-s3
boto
The answer is
Try this...
import boto
import boto.s3
import sys
from boto.s3.key import Key
AWS_ACCESS_KEY_ID = ''
AWS_SECRET_ACCESS_KEY = ''
bucket_name = AWS_ACCESS_KEY_ID.lower() + '-dump'
conn = boto.connect_s3(AWS_ACCESS_KEY_ID,
AWS_SECRET_ACCESS_KEY)
bucket = conn.create_bucket(bucket_name,
location=boto.s3.connection.Location.DEFAULT)
testfile = "replace this with an actual filename"
print 'Uploading %s to Amazon S3 bucket %s' % \
(testfile, bucket_name)
def percent_cb(complete, total):
sys.stdout.write('.')
sys.stdout.flush()
k = Key(bucket)
k.key = 'my test file'
k.set_contents_from_filename(testfile,
cb=percent_cb, num_cb=10)
[UPDATE] I am not a pythonist, so thanks for the heads up about the import statements. Also, I'd not recommend placing credentials inside your own source code. If you are running this inside AWS use IAM Credentials with Instance Profiles (http://docs.aws.amazon.com/IAM/latest/UserGuide/id_roles_use_switch-role-ec2_instance-profiles.html), and to keep the same behaviour in your Dev/Test environment, use something like Hologram from AdRoll (https://github.com/AdRoll/hologram)
This is a three liner. Just follow the instructions on the boto3 documentation.
import boto3
s3 = boto3.resource(service_name = 's3')
s3.meta.client.upload_file(Filename = 'C:/foo/bar/baz.filetype', Bucket = 'yourbucketname', Key = 'baz.filetype')
Some important arguments are:
Parameters:
str) -- The path to the file to upload.str) -- The name of the bucket to upload to.
str) -- The name of the that you want to assign to your file in your s3 bucket. This could be the same as the name of the file or a different name of your choice but the filetype should remain the same.
Note: I assume that you have saved your credentials in a ~\.aws folder as suggested in the best configuration practices in the boto3 documentation.
from boto3.s3.transfer import S3Transfer
import boto3
#have all the variables populated which are required below
client = boto3.client('s3', aws_access_key_id=access_key,aws_secret_access_key=secret_key)
transfer = S3Transfer(client)
transfer.upload_file(filepath, bucket_name, folder_name+"/"+filename)
This will also work:
import os
import boto
import boto.s3.connection
from boto.s3.key import Key
try:
conn = boto.s3.connect_to_region('us-east-1',
aws_access_key_id = 'AWS-Access-Key',
aws_secret_access_key = 'AWS-Secrete-Key',
# host = 's3-website-us-east-1.amazonaws.com',
# is_secure=True, # uncomment if you are not using ssl
calling_format = boto.s3.connection.OrdinaryCallingFormat(),
)
bucket = conn.get_bucket('YourBucketName')
key_name = 'FileToUpload'
path = 'images/holiday' #Directory Under which file should get upload
full_key_name = os.path.join(path, key_name)
k = bucket.new_key(full_key_name)
k.set_contents_from_filename(key_name)
except Exception,e:
print str(e)
print "error"
Upload file to s3 within a session with credentials.
import boto3
session = boto3.Session(
aws_access_key_id='AWS_ACCESS_KEY_ID',
aws_secret_access_key='AWS_SECRET_ACCESS_KEY',
)
s3 = session.resource('s3')
# Filename - File to upload
# Bucket - Bucket to upload to (the top level directory under AWS S3)
# Key - S3 object name (can contain subdirectories). If not specified then file_name is used
s3.meta.client.upload_file(Filename='input_file_path', Bucket='bucket_name', Key='s3_output_key')
import boto
from boto.s3.key import Key
AWS_ACCESS_KEY_ID = ''
AWS_SECRET_ACCESS_KEY = ''
END_POINT = '' # eg. us-east-1
S3_HOST = '' # eg. s3.us-east-1.amazonaws.com
BUCKET_NAME = 'test'
FILENAME = 'upload.txt'
UPLOADED_FILENAME = 'dumps/upload.txt'
# include folders in file path. If it doesn't exist, it will be created
s3 = boto.s3.connect_to_region(END_POINT,
aws_access_key_id=AWS_ACCESS_KEY_ID,
aws_secret_access_key=AWS_SECRET_ACCESS_KEY,
host=S3_HOST)
bucket = s3.get_bucket(BUCKET_NAME)
k = Key(bucket)
k.key = UPLOADED_FILENAME
k.set_contents_from_filename(FILENAME)
Using boto3
import logging
import boto3
from botocore.exceptions import ClientError
def upload_file(file_name, bucket, object_name=None):
"""Upload a file to an S3 bucket
:param file_name: File to upload
:param bucket: Bucket to upload to
:param object_name: S3 object name. If not specified then file_name is used
:return: True if file was uploaded, else False
"""
# If S3 object_name was not specified, use file_name
if object_name is None:
object_name = file_name
# Upload the file
s3_client = boto3.client('s3')
try:
response = s3_client.upload_file(file_name, bucket, object_name)
except ClientError as e:
logging.error(e)
return False
return True
For more:- https://boto3.amazonaws.com/v1/documentation/api/latest/guide/s3-uploading-files.html
If you have the aws command line interface installed on your system you can make use of pythons subprocess library. For example:
import subprocess
def copy_file_to_s3(source: str, target: str, bucket: str):
subprocess.run(["aws", "s3" , "cp", source, f"s3://{bucket}/{target}"])
Similarly you can use that logics for all sort of AWS client operations like downloading or listing files etc. It is also possible to get return values. This way there is no need to import boto3. I guess its use is not intended that way but in practice I find it quite convenient that way. This way you also get the status of the upload displayed in your console - for example:
Completed 3.5 GiB/3.5 GiB (242.8 MiB/s) with 1 file(s) remaining
To modify the method to your wishes I recommend having a look into the subprocess reference as well as to the AWS Cli reference.
Note: This is a copy of my answer to a similar question.
You should mention the content type as well to omit the file accessing issue.
import os
image='fly.png'
s3_filestore_path = 'images/fly.png'
filename, file_extension = os.path.splitext(image)
content_type_dict={".png":"image/png",".html":"text/html",
".css":"text/css",".js":"application/javascript",
".jpg":"image/png",".gif":"image/gif",
".jpeg":"image/jpeg"}
content_type=content_type_dict[file_extension]
s3 = boto3.client('s3', config=boto3.session.Config(signature_version='s3v4'),
region_name='ap-south-1',
aws_access_key_id=S3_KEY,
aws_secret_access_key=S3_SECRET)
s3.put_object(Body=image, Bucket=S3_BUCKET, Key=s3_filestore_path, ContentType=content_type)
I have something that seems to me has a bit more order:
import boto3
from pprint import pprint
from botocore.exceptions import NoCredentialsError
class S3(object):
BUCKET = "test"
connection = None
def __init__(self):
try:
vars = get_s3_credentials("aws")
self.connection = boto3.resource('s3', 'aws_access_key_id',
'aws_secret_access_key')
except(Exception) as error:
print(error)
self.connection = None
def upload_file(self, file_to_upload_path, file_name):
if file_to_upload is None or file_name is None: return False
try:
pprint(file_to_upload)
file_name = "your-folder-inside-s3/{0}".format(file_name)
self.connection.Bucket(self.BUCKET).upload_file(file_to_upload_path,
file_name)
print("Upload Successful")
return True
except FileNotFoundError:
print("The file was not found")
return False
except NoCredentialsError:
print("Credentials not available")
return False
There're three important variables here, the BUCKET const, the file_to_upload and the file_name
BUCKET: is the name of your S3 bucket
file_to_upload_path: must be the path from file you want to upload
file_name: is the resulting file and path in your bucket (this is where you add folders or what ever)
There's many ways but you can reuse this code in another script like this
import S3
def some_function():
S3.S3().upload_file(path_to_file, final_file_name)
xmlstr = etree.tostring(listings, encoding='utf8', method='xml')
conn = boto.connect_s3(
aws_access_key_id = access_key,
aws_secret_access_key = secret_key,
# host = '<bucketName>.s3.amazonaws.com',
host = 'bycket.s3.amazonaws.com',
#is_secure=False, # uncomment if you are not using ssl
calling_format = boto.s3.connection.OrdinaryCallingFormat(),
)
conn.auth_region_name = 'us-west-1'
bucket = conn.get_bucket('resources', validate=False)
key= bucket.get_key('filename.txt')
key.set_contents_from_string("SAMPLE TEXT")
key.set_canned_acl('public-read')
import boto3
s3 = boto3.resource('s3')
BUCKET = "test"
s3.Bucket(BUCKET).upload_file("your/local/file", "dump/file")
No need to make it that complicated:
s3_connection = boto.connect_s3()
bucket = s3_connection.get_bucket('your bucket name')
key = boto.s3.key.Key(bucket, 'some_file.zip')
with open('some_file.zip') as f:
key.send_file(f)
For upload folder example as following code and S3 folder picture
import boto
import boto.s3
import boto.s3.connection
import os.path
import sys
# Fill in info on data to upload
# destination bucket name
bucket_name = 'willie20181121'
# source directory
sourceDir = '/home/willie/Desktop/x/' #Linux Path
# destination directory name (on s3)
destDir = '/test1/' #S3 Path
#max size in bytes before uploading in parts. between 1 and 5 GB recommended
MAX_SIZE = 20 * 1000 * 1000
#size of parts when uploading in parts
PART_SIZE = 6 * 1000 * 1000
access_key = 'MPBVAQ*******IT****'
secret_key = '11t63yDV***********HgUcgMOSN*****'
conn = boto.connect_s3(
aws_access_key_id = access_key,
aws_secret_access_key = secret_key,
host = '******.org.tw',
is_secure=False, # uncomment if you are not using ssl
calling_format = boto.s3.connection.OrdinaryCallingFormat(),
)
bucket = conn.create_bucket(bucket_name,
location=boto.s3.connection.Location.DEFAULT)
uploadFileNames = []
for (sourceDir, dirname, filename) in os.walk(sourceDir):
uploadFileNames.extend(filename)
break
def percent_cb(complete, total):
sys.stdout.write('.')
sys.stdout.flush()
for filename in uploadFileNames:
sourcepath = os.path.join(sourceDir + filename)
destpath = os.path.join(destDir, filename)
print ('Uploading %s to Amazon S3 bucket %s' % \
(sourcepath, bucket_name))
filesize = os.path.getsize(sourcepath)
if filesize > MAX_SIZE:
print ("multipart upload")
mp = bucket.initiate_multipart_upload(destpath)
fp = open(sourcepath,'rb')
fp_num = 0
while (fp.tell() < filesize):
fp_num += 1
print ("uploading part %i" %fp_num)
mp.upload_part_from_file(fp, fp_num, cb=percent_cb, num_cb=10, size=PART_SIZE)
mp.complete_upload()
else:
print ("singlepart upload")
k = boto.s3.key.Key(bucket)
k.key = destpath
k.set_contents_from_filename(sourcepath,
cb=percent_cb, num_cb=10)
PS: For more reference URL
I used this and it is very simple to implement
import tinys3
conn = tinys3.Connection('S3_ACCESS_KEY','S3_SECRET_KEY',tls=True)
f = open('some_file.zip','rb')
conn.upload('some_file.zip',f,'my_bucket')
Source: Stackoverflow.com