Ruby
Amazon S3 List More than 1000 Objects in Bucket

S3 limits the size of the "List Objects" response to 1000 objects. To retrieve a listing of all of the objects in a bucket containing more than 1000 objects, we'll need to send several requests using continuation tokens.
Chilkat Ruby Downloads

Download Chilkat for Ruby
Ruby
require 'chilkat'

success = false

# This example assumes the Chilkat HTTP API to have been previously unlocked.
# See Global Unlock Sample for sample code.

http = Chilkat::CkHttp.new()

# Insert your access key here:
http.put_AwsAccessKey("AWS_ACCESS_KEY")

# Insert your secret key here:
http.put_AwsSecretKey("AWS_SECRET_KEY")

# For the example, we'll get a listing containing approx. 25 objects
# using continuation tokens with an artificially low max-keys set to 5.
# (You may omit the max-keys query parameter to get the default 1000 maximum
# number of keys per request.)

sbContinuationToken = Chilkat::CkStringBuilder.new()
bGetMore = true
sbUri = Chilkat::CkStringBuilder.new()
xml = Chilkat::CkXml.new()

dt = Chilkat::CkDateTime.new()
dtObj = Chilkat::CkDtObj.new()

while bGetMore == true

    # Make sure to set the "list-type" query param equal to "2".
    # This chooses the GET Bucket (List Objects) Version 2 of the method.

    # IMPORTANT: You must include the max-keys param to get a response with a continuation token.
    # S3 limits the number of objects in a single response to 1000. Therefore, your max-keys
    # can be up to 1000.  If, for example, you have 2000 objects and do not specify
    # max-keys, then the response will contain 1000 objects with no continuation token. 
    sbUri.SetString("chilkat100?list-type=2&max-keys=5")
    if (sbContinuationToken.get_Length() > 0)
        sbUri.Append("&continuation-token=")
        sbUri.Append(sbContinuationToken.getEncoded("url","utf-8"))
    end

    strXml = http.s3_ListBucketObjects(sbUri.getAsString())
    if (http.get_LastMethodSuccess() == false)
        print http.lastErrorText() + "\n";
        exit
    end

    print "Response status code = " + http.get_LastStatus().to_s() + "\n";

    success = xml.LoadXml(strXml)
    if (success == false)
        print xml.lastErrorText() + "\n";
        exit
    end

    # If the response status code was not 200, then the XML response is not a 
    # listing of objects, but instead contains error information.
    if (http.get_LastStatus() != 200)
        print xml.getXml() + "\n";
        print "Failed." + "\n";
        exit
    end

    # If this is not the final response, then we'll get an XML response that begins
    # like this.  (The IsTruncated child will be "true", and the NextContinuationToken
    # will have a value to be used in the next request.)
    # 	<?xml version="1.0" encoding="UTF-8" ?>
    # 	<ListBucketResult xmlns="http://s3.amazonaws.com/doc/2006-03-01/">
    # 	    <Name>chilkat100</Name>
    # 	    <Prefix />
    # 	    <NextContinuationToken>1Mlcx+W9OKsr8cxp3DP6r71wgsTUMj0vqlntWoaJKNbYdrauLdf40LsUdBeSYGFhzbGIHdcf5DSLcEBWbqG+1fW1UcQkUW1V4qgQONAKOwb8y8vOLJAQ8iQ==</NextContinuationToken>
    # 	    <KeyCount>5</KeyCount>
    # 	    <MaxKeys>5</MaxKeys>
    # 	    <IsTruncated>true</IsTruncated>
    # 	

    # Iterate over the bucket items in this chunk get information for each..
    numItems = xml.NumChildrenHavingTag("Contents")
    print "Number of bucket items = " + numItems.to_s() + "\n";

    i = 0
    while i < numItems
        xml.put_I(i)

        itemKey = xml.getChildContent("Contents[i]|Key")
        itemSizeDecimalStr = xml.getChildContent("Contents[i]|Size")
        lastModTimestamp = xml.getChildContent("Contents[i]|LastModified")

        dt.SetFromRfc822(lastModTimestamp)
        # Get a local date/time.
        bLocal = true
        dt.ToDtObj(bLocal,dtObj)

        print i.to_s() + ": " + itemKey + ", " + itemSizeDecimalStr + ", " + dtObj.get_Day().to_s() + "-" + dtObj.get_Month().to_s() + 
            "-" + dtObj.get_Year().to_s() + ":" + dtObj.get_Hour().to_s() + ":" + dtObj.get_Minute().to_s() + "\n";

        i = i + 1
    end

    # Check IsTruncated.
    bGetMore = false
    if (xml.ChildContentMatches("IsTruncated","true",true) == true)
        sbContinuationToken.SetString(xml.getChildContent("NextContinuationToken"))
        if (sbContinuationToken.get_Length() > 0)
            bGetMore = true
        end

    end

end

# The output of this example (when tested) was:

# Response status code = 200
# Number of bucket items = 5
# 0: Abc.ics, 1833, 25-5-2011:9:53
# 1: Corpse Bride film poster.jpg, 53481, 6-9-2016:13:32
# 2: chiliPepper.gif, 7718, 12-3-2017:12:18
# 3: chilkatdude.jpg, 35137, 20-5-2011:16:14
# 4: cloud.search/dfe/indexer/pscc/2016/3/28/id,x-2-15-0-25-87-0.json, 1238, 2-4-2016:12:0
# Response status code = 200
# Number of bucket items = 5
# 0: cloud.search/dfe/indexer/pscc/2016/3/28/idx-2-15-0-25-87-0.json, 1238, 2-4-2016:11:33
# 1: dude.gif, 6373, 25-5-2011:17:29
# 2: french.txt, 47, 12-3-2017:12:18
# 3: hamlet.xml, 279658, 2-5-2016:12:21
# 4: hamlet_play.xml, 279658, 20-3-2017:8:22
# Response status code = 200
# Number of bucket items = 5
# 0: images/sea_creatures/starfish123.jpg, 6229, 19-1-2017:10:45
# 1: images/sea_creatures/starfishåäö.jpg, 6229, 19-1-2017:12:7
# 2: new folder/, 0, 26-11-2014:12:36
# 3: new_starfish.jpg, 6229, 20-3-2017:8:22
# 4: pigs.xml, 2804, 20-3-2017:8:22
# Response status code = 200
# Number of bucket items = 5
# 0: somethingBig.zip, 13089458, 26-9-2016:9:29
# 1: starfish.jpg, 6229, 12-3-2017:12:18
# 2: starfish/, 0, 10-11-2014:10:7
# 3: starfish/starfish.jpg, 6229, 10-11-2014:10:8
# 4: starfish/starfish2.jpg, 6229, 19-11-2014:10:36
# Response status code = 200
# Number of bucket items = 5
# 0: starfish/starfish3.jpg, 6229, 24-11-2014:14:33
# 1: starfish2.jpg, 5987, 20-4-2012:12:6
# 2: starfish3.jpg, 5987, 11-4-2012:7:10
# 3: starfishA.jpg, 6229, 10-5-2016:8:44
# 4: starfishCust.jpg, 6229, 12-11-2014:18:25
# Response status code = 200
# Number of bucket items = 1
# 0: xyz.ics, 1833, 25-5-2011:8:52
# 
#