(CkPython) S3 Upload the Parts for a Multipart Upload

This example uploads a large file in parts. The multipart upload needs to have been first initiated prior to uploading the parts.

See http://docs.aws.amazon.com/AmazonS3/latest/API/mpUploadUploadPart.html for more information about uploading parts.

Chilkat Python Downloads install with pip pip3 install chilkat or download... Python Module for Windows, MacOS, Linux, Alpine Linux, Solaris

import sys
import chilkat

# In the 1st step for uploading a large file, the multipart upload was initiated
# as shown here: Initiate Multipart Upload

# Other S3 Multipart Upload Examples:
# Complete Multipart Upload
# Abort Multipart Upload
# List Parts

# When we initiated the multipart upload, we saved the XML response to a file.  This
# XML response contains the UploadId.  We'll begin by loading that XML and getting
# the Upload ID.

xmlInit = chilkat.CkXml()
success = xmlInit.LoadXmlFile("s3_multipart_uploads/initiate.xml")
if (success != True):
    print("Did not find the initiate.xml XML file.")
    sys.exit()

uploadId = xmlInit.getChildContent("UploadId")
print("UploadId = " + uploadId)

# When uploading parts, we need to keep an XML record of each part number
# and its corresponding ETag, which is received in the response for each part.
# There can be up to 10000 parts, numbered 1 to 10000.  
# After all parts have been uploaded, the final step will be to complete
# the multipart upload (see Complete Multipart Upload)

# In this example, the large file we want to upload is somethingBig.zip
fileToUploadPath = "s3_multipart_uploads/somethingBig.zip"

# The minimum allowed part size is 5MB (5242880 bytes).  The last part can be smaller because
# it will contain the remainder of the file.  (This minimum is enforced by the AWS service.)
# We'll use the minimum allowed part size for this example.
partSize = 5242880

# Let's use Chilkat's FileAccess API to examine the file to be uploaded.  We'll get the size
# of the file and find out how many parts will be needed, including the final "partial" part.
fac = chilkat.CkFileAccess()
fac.OpenForRead(fileToUploadPath)

# How many parts will there be if each part is 5242880 bytes?
numParts = fac.GetNumBlocks(partSize)
print("numParts = " + str(numParts))
fac.FileClose()

# Imagine that we may be running this for the 1st time, or maybe we already
# attempted to upload parts, and something failed. Maybe there was a network problem
# the resulted in not all parts getting uploaded.  We'll write this code so that if run again,
# it will upload whatever parts haven't yet been uploaded.

# We'll keep a partsList.xml file to record the parts that have already been successfully
# uploaded.  If this file does not yet exist, we'll create it..
partsListFile = "s3_multipart_uploads/partsList.xml"
partsListXml = chilkat.CkXml()
if (fac.FileExists(partsListFile) == True):
    partsListXml.LoadXmlFile(partsListFile)

# Make sure the top-level tag is "CompleteMultipartUpload"
partsListXml.put_Tag("CompleteMultipartUpload")

# --------------------------------------
# Before entering the loop to upload parts,
# setup the REST object with AWS authentication,
# and make the initial connection.
rest = chilkat.CkRest()

# Connect to the Amazon AWS REST server.
bTls = True
port = 443
bAutoReconnect = True
success = rest.Connect("s3.amazonaws.com",port,bTls,bAutoReconnect)

# ----------------------------------------------------------------------------
# Important: For buckets created in regions outside us-east-1,
# there are three important changes that need to be made.
# See Working with S3 Buckets in Non-us-east-1 Regions for the details.
# ----------------------------------------------------------------------------

# Provide AWS credentials for the REST call.
authAws = chilkat.CkAuthAws()
authAws.put_AccessKey("AWS_ACCESS_KEY")
authAws.put_SecretKey("AWS_SECRET_KEY")
authAws.put_ServiceName("s3")
success = rest.SetAuthAws(authAws)

# Set the bucket name via the HOST header.
# In this case, the bucket name is "chilkat100".
rest.put_Host("chilkat100.s3.amazonaws.com")
# --------------------------------------

partNumber = 1
sbPartNumber = chilkat.CkStringBuilder()

while (partNumber <= numParts) :
    print("---- " + str(partNumber) + " ----")

    # This cumbersome way of converting an integer to a string is because
    # Chilkat examples are written in a script that is converted to many programming languages.
    # At this time, the translator does not have integer-to-string code generation capability..
    sbPartNumber.Clear()
    sbPartNumber.AppendInt(partNumber)

    bPartAlreadyUploaded = False

    # If there are no children, then the XML is empty and no parts have yet been uploaded.
    numUploadedParts = partsListXml.get_NumChildren()
    if (numUploadedParts > 0):
        # If some parts have been uploaded, check to see if this particular part was already upload.
        # If so, then it can be skipped.

        # Position ourselves at the 1st record.
        # xRec0 is a CkXml
        xRec0 = partsListXml.GetChild(0)
        # foundRec is a CkXml
        foundRec = xRec0.FindNextRecord("PartNumber",sbPartNumber.getAsString())
        if (xRec0.get_LastMethodSuccess() == True):
            bPartAlreadyUploaded = True
            print("Part " + str(partNumber) + " was previously uploaded.")
            print(foundRec.getXml())

    # If this part was not already uploaded, we need to upload.
    # Also update the partsListXml and save as each part is successfully uploaded.
    if (bPartAlreadyUploaded == False):
        print("Uploading part " + str(partNumber) + " ...")

        # Setup the stream source for the large file to be uploaded..
        fileStream = chilkat.CkStream()
        fileStream.put_SourceFile(fileToUploadPath)
        # The Chilkat Stream API has features to make uploading a parts
        # of a file easy.  Indicate the part size by setting the SourceFilePartSize
        # property.
        fileStream.put_SourceFilePartSize(partSize)

        # Our HTTP start line to upload a part will look like this:
        # PUT /ObjectName?partNumber=PartNumber&uploadId=UploadId HTTP/1.1

        # Set the query params.  We'll need partNumber and uploadId.
        # Make sure the query params from previous iterations are clear.
        rest.ClearAllQueryParams()
        rest.AddQueryParam("partNumber",sbPartNumber.getAsString())
        rest.AddQueryParam("uploadId",uploadId)

        # Upload this particular file part.
        # Tell the fileStream which part is being uploaded.
        # Our partNumber is 1-based (the 1st part is at index 1), but the fileStream's SourceFilePart
        # property is 0-based.  Therefore we use partNumber-1.
        fileStream.put_SourceFilePart(partNumber - 1)

        # Because the SourceFilePart and SourceFilePartSize properties are set, the stream will 
        # will provide just that part of the file.  
        responseStr = rest.fullRequestStream("PUT","/somethingBig.zip",fileStream)
        if (rest.get_LastMethodSuccess() != True):
            print(rest.lastErrorText())
            sys.exit()

        if (rest.get_ResponseStatusCode() != 200):
            # Examine the request/response to see what happened.
            print("response status code = " + str(rest.get_ResponseStatusCode()))
            print("response status text = " + rest.responseStatusText())
            print("response header: " + rest.responseHeader())
            print("response body: " + responseStr)
            print("---")
            print("LastRequestStartLine: " + rest.lastRequestStartLine())
            print("LastRequestHeader: " + rest.lastRequestHeader())
            sys.exit()

        # OK, this part was uploaded..
        # The response will have a 0-length body.  The only information we need is the 
        # ETag response header field.
        etag = rest.responseHdrByName("ETag")
        # It should be present, but just in case there was no ETag header...
        if (rest.get_LastMethodSuccess() != True):
            print("No ETag response header found!")
            print("response header: " + rest.responseHeader())
            sys.exit()

        # We need to add record to the partsListXml.
        # The record will look like this:
        # &lt;Part>
        #   &lt;PartNumber>PartNumber&lt;/PartNumber>
        #   &lt;ETag>ETag&lt;/ETag>
        # &lt;/Part>
        # xPart is a CkXml
        xPart = partsListXml.NewChild("Part","")
        xPart.NewChildInt2("PartNumber",partNumber)
        xPart.NewChild2("ETag",etag)

        success = partsListXml.SaveXml(partsListFile)
        if (success != True):
            print(partsListXml.lastErrorText())
            sys.exit()

        print("-- Part " + str(partNumber) + " uploaded. ---------------------")

    partNumber = partNumber + 1

print("Finished.  All parts uploaded.")