todpole3 · January 27, 2020 01:13
diff --git a/reproduce_boto3_character_encoding_bug.py b/reproduce_boto3_character_encoding_bug.py
 """
 Code adapted from
 https://github.com/aws-samples/mturk-code-samples/blob/master/Python/CreateHitSample.py

 Package version:
    boto3==1.10.45
    
 Usage:
    python3 reproduce_boto3_character_encoding_bug.py --aws_credentials /tmp/accessKeys.csv
 """

 import argparse
 import csv
 import boto3

 # Before connecting to MTurk, set up your AWS account and IAM settings as
 # described here:
 # https://blog.mturk.com/how-to-use-iam-to-control-api-access-to-your-mturk-account-76fe2c2e66e2
 #
 # Follow AWS best practices for setting up credentials here:
 # http://boto3.readthedocs.io/en/latest/guide/configuration.html

 # Use the Amazon Mechanical Turk Sandbox to publish test Human Intelligence
 # Tasks (HITs) without paying any money.  Sign up for a Sandbox account at
 # https://requestersandbox.mturk.com/ with the same credentials as your main
 # MTurk account.

 parser = argparse.ArgumentParser(description="HIT submissions")
 parser.add_argument("--aws_credentials", default=None, help="Path to AWS user credentials.")
 args = parser.parse_args()

 # By default, HITs are created in the free-to-use Sandbox
 create_hits_in_live = False

 environments = {
        "live": {
            "endpoint": "https://mturk-requester.us-east-1.amazonaws.com",
            "preview": "https://www.mturk.com/mturk/preview",
            "manage": "https://requester.mturk.com/mturk/manageHITs",
            "reward": "0.00"
        },
        "sandbox": {
            "endpoint": "https://mturk-requester-sandbox.us-east-1.amazonaws.com",
            "preview": "https://workersandbox.mturk.com/mturk/preview",
            "manage": "https://requestersandbox.mturk.com/mturk/manageHITs",
            "reward": "0.11"
        },
 }
 mturk_environment = environments["live"] if create_hits_in_live else environments["sandbox"]

 # use profile if one was passed as an arg, otherwise
 # Read user AWS credentials
 with open(args.aws_credentials) as f:
    reader = csv.DictReader(f)
    for row in reader:
        aws_access_key_id = row['Access key ID']
        aws_secret_access_key = row['Secret access key']
 session = boto3.Session(
    aws_access_key_id=aws_access_key_id,
    aws_secret_access_key=aws_secret_access_key)
 client = session.client(
    service_name='mturk',
    region_name='us-east-1',
    endpoint_url=mturk_environment['endpoint'],
 )

 # The question we ask the workers is contained in this file.
 question_sample = """
 <HTMLQuestion xmlns="http://mechanicalturk.amazonaws.com/AWSMechanicalTurkDataSchemas/2011-11-11/HTMLQuestion.xsd">
 <HTMLContent><![CDATA[
 <!-- YOUR HTML BEGINS -->
 <!DOCTYPE html>
 <html>
 <head>
 <meta http-equiv='Content-Type' content='text/html; charset=UTF-8'/>
 <script type='text/javascript' src='https://s3.amazonaws.com/mturk-public/externalHIT_v1.js'></script>
 </head>
 <body>
 <form name='mturk_form' method='post' id='mturk_form' action='https://www.mturk.com/mturk/externalSubmit'><input type='hidden' value='' name='assignmentId' id='assignmentId'/>
 <h2>Is this Tweet happy, angry, excited, scared, annoyed or upset? Type in one word to describe the main emotion in the message. If it is unclear, type in "unclear".</h2>
 <h3> Tweet: "I am really looking forward to the next Seahawks game!"</h3>
 <div>
  <input type='text' name='reported_emotion' placeholder='Type in your answer here'>
  👉
 </div>
 <p><input type='submit' id='submitButton' value='Submit' /></p></form>
 <script language='Javascript'>turkSetAssignmentID();</script>
 </body></html>
 <!-- YOUR HTML ENDS -->
 ]]>
 </HTMLContent>
 <FrameHeight>600</FrameHeight>
 </HTMLQuestion>
 """

 # Example of using qualification to restrict responses to Workers who have had
 # at least 80% of their assignments approved. See:
 # http://docs.aws.amazon.com/AWSMechTurk/latest/AWSMturkAPI/ApiReference_QualificationRequirementDataStructureArticle.html#ApiReference_QualificationType-IDs
 worker_requirements = [{
    'QualificationTypeId': '000000000000000000L0',
    'Comparator': 'GreaterThanOrEqualTo',
    'IntegerValues': [80],
    'RequiredToPreview': True,
 }]

 # Create the HIT
 response = client.create_hit(
    MaxAssignments=3,
    LifetimeInSeconds=600,
    AssignmentDurationInSeconds=600,
    Reward=mturk_environment['reward'],
    Title='Answer a simple question',
    Keywords='question, answer, research',
    Description='Answer a simple question. Created from mturk-code-samples.',
    Question=question_sample,
    QualificationRequirements=worker_requirements,
 )

 print("\nYou can work on the HIT groups here:")
 print(mturk_environment['preview'] + "?groupId={}".format((response['HIT']['HITGroupId'])))
	"""
	Code adapted from
	https://github.com/aws-samples/mturk-code-samples/blob/master/Python/CreateHitSample.py

	Package version:
	boto3==1.10.45

	Usage:
	python3 reproduce_boto3_character_encoding_bug.py --aws_credentials /tmp/accessKeys.csv
	"""

	import argparse
	import csv
	import boto3

	# Before connecting to MTurk, set up your AWS account and IAM settings as
	# described here:
	# https://blog.mturk.com/how-to-use-iam-to-control-api-access-to-your-mturk-account-76fe2c2e66e2
	#
	# Follow AWS best practices for setting up credentials here:
	# http://boto3.readthedocs.io/en/latest/guide/configuration.html

	# Use the Amazon Mechanical Turk Sandbox to publish test Human Intelligence
	# Tasks (HITs) without paying any money. Sign up for a Sandbox account at
	# https://requestersandbox.mturk.com/ with the same credentials as your main
	# MTurk account.

	parser = argparse.ArgumentParser(description="HIT submissions")
	parser.add_argument("--aws_credentials", default=None, help="Path to AWS user credentials.")
	args = parser.parse_args()

	# By default, HITs are created in the free-to-use Sandbox
	create_hits_in_live = False

	environments = {
	"live": {
	"endpoint": "https://mturk-requester.us-east-1.amazonaws.com",
	"preview": "https://www.mturk.com/mturk/preview",
	"manage": "https://requester.mturk.com/mturk/manageHITs",
	"reward": "0.00"
	},
	"sandbox": {
	"endpoint": "https://mturk-requester-sandbox.us-east-1.amazonaws.com",
	"preview": "https://workersandbox.mturk.com/mturk/preview",
	"manage": "https://requestersandbox.mturk.com/mturk/manageHITs",
	"reward": "0.11"
	},
	}
	mturk_environment = environments["live"] if create_hits_in_live else environments["sandbox"]

	# use profile if one was passed as an arg, otherwise
	# Read user AWS credentials
	with open(args.aws_credentials) as f:
	reader = csv.DictReader(f)
	for row in reader:
	aws_access_key_id = row['Access key ID']
	aws_secret_access_key = row['Secret access key']
	session = boto3.Session(
	aws_access_key_id=aws_access_key_id,
	aws_secret_access_key=aws_secret_access_key)
	client = session.client(
	service_name='mturk',
	region_name='us-east-1',
	endpoint_url=mturk_environment['endpoint'],
	)

	# The question we ask the workers is contained in this file.
	question_sample = """
	<HTMLQuestion xmlns="http://mechanicalturk.amazonaws.com/AWSMechanicalTurkDataSchemas/2011-11-11/HTMLQuestion.xsd">
	<HTMLContent><![CDATA[
	<!-- YOUR HTML BEGINS -->
	<!DOCTYPE html>
	<html>
	<head>
	<meta http-equiv='Content-Type' content='text/html; charset=UTF-8'/>
	<script type='text/javascript' src='https://s3.amazonaws.com/mturk-public/externalHIT_v1.js'></script>
	</head>
	<body>
	<form name='mturk_form' method='post' id='mturk_form' action='https://www.mturk.com/mturk/externalSubmit'><input type='hidden' value='' name='assignmentId' id='assignmentId'/>
	<h2>Is this Tweet happy, angry, excited, scared, annoyed or upset? Type in one word to describe the main emotion in the message. If it is unclear, type in "unclear".</h2>
	<h3> Tweet: "I am really looking forward to the next Seahawks game!"</h3>
	<div>
	<input type='text' name='reported_emotion' placeholder='Type in your answer here'>
	👉
	</div>
	<p><input type='submit' id='submitButton' value='Submit' /></p></form>
	<script language='Javascript'>turkSetAssignmentID();</script>
	</body></html>
	<!-- YOUR HTML ENDS -->
	]]>
	</HTMLContent>
	<FrameHeight>600</FrameHeight>
	</HTMLQuestion>
	"""

	# Example of using qualification to restrict responses to Workers who have had
	# at least 80% of their assignments approved. See:
	# http://docs.aws.amazon.com/AWSMechTurk/latest/AWSMturkAPI/ApiReference_QualificationRequirementDataStructureArticle.html#ApiReference_QualificationType-IDs
	worker_requirements = [{
	'QualificationTypeId': '000000000000000000L0',
	'Comparator': 'GreaterThanOrEqualTo',
	'IntegerValues': [80],
	'RequiredToPreview': True,
	}]

	# Create the HIT
	response = client.create_hit(
	MaxAssignments=3,
	LifetimeInSeconds=600,
	AssignmentDurationInSeconds=600,
	Reward=mturk_environment['reward'],
	Title='Answer a simple question',
	Keywords='question, answer, research',
	Description='Answer a simple question. Created from mturk-code-samples.',
	Question=question_sample,
	QualificationRequirements=worker_requirements,
	)

	print("\nYou can work on the HIT groups here:")
	print(mturk_environment['preview'] + "?groupId={}".format((response['HIT']['HITGroupId'])))