A sample glue job

glue_job.yaml

AWSTemplateFormatVersion: "2010-09-09"
Description: "Create a glue job to process S3 Data events"
Parameters:
  LogBucket:
    Type: String
  GlueAssetsBucket:
    Type: String
  RawDBName:
    Type: String
  RawTableName:
    Type: String
  ConvertedTableName:
    Type: String
  ConvertedDBName:
    Type: String

Resources:
  GlueJobRole:
    Type: AWS::IAM::Role
    Properties:
      ManagedPolicyArns: 
          - "arn:aws:iam::aws:policy/service-role/AWSGlueServiceRole"
      AssumeRolePolicyDocument:
        Version: "2012-10-17"
        Statement:
          -
            Effect: "Allow"
            Principal:
              Service:
                - "glue.amazonaws.com"
            Action:
              - "sts:AssumeRole"
      Path: "/"
      Policies:
        -
          PolicyName: "inline"
          PolicyDocument:
            Version: "2012-10-17"
            Statement:
              -
                Effect: "Allow"
                Action: 
                  - "s3:ListAllMyBuckets"
                  - "s3:GetBucketLocation"
                Resource: "*"
              -
                Effect: "Allow"
                Action: 
                  - "s3:GetObject*"
                Resource: 
                  - !Sub |- 
                    arn:aws:s3:::${LogBucket}/AWSLogs/*
                  - !Sub |- 
                    arn:aws:s3:::${GlueAssetsBucket}/*
              - Effect: "Allow"
                Action:
                  - "s3:GetObject*"
                  - "s3:PutObject*"
                  - "s3:Delete*"
                Resource:
                  - !Sub |- 
                    arn:aws:s3:::${LogBucket}/converted2/*
                  - !Sub |- 
                    arn:aws:s3:::${LogBucket}/temp2/*

  MyJob:
    Type: AWS::Glue::Job
    Properties:
      Command:
        Name: glueetl
        ScriptLocation: !Sub "s3://${GlueAssetsBucket}/agsl/glue_scripts/sample_cloudtrail_s3_job.py"
      DefaultArguments:
        "--job-bookmark-option": "job-bookmark-enable"
        "--raw_database_name": !Sub "${RawDBName}"
        "--raw_table_name": !Sub "${RawTableName}"
        "--converted_database_name": !Sub "${ConvertedDBName}"
        "--converted_table_name": !Sub "${ConvertedTableName}"
        "--TempDir": !Sub "s3://${LogBucket}/temp2"
        "--s3_converted_target": !Sub "s3://${LogBucket}/converted2/s3_events_parquet/"
        "--s3_source_location": !Sub "s3://${LogBucket}/AWSLogs/${AWS::AccountId}/CloudTrail/"
        "--extra-py-files": !Sub "s3://${GlueAssetsBucket}/agsl/glue_scripts/athena_glue_converter_latest.zip"  
      ExecutionProperty:
        MaxConcurrentRuns: 2
      MaxRetries: 0
      Name: S3DataEventConverter
      Role: !Ref GlueJobRole

  MyJobTrigger:
    Type: AWS::Glue::Trigger
    Properties:
      Name: "S3DataEventConverterTrigger"
      Description: "Runs the S3 Data event converter every 4 hours"
      Type: SCHEDULED
      Schedule: cron(0 */4 * * ? *)
      Actions:
        - JobName: !Ref MyJob