CreateCrawlerRequest ¶

class CreateCrawlerRequest(TypedDict, closed=True):
    name: "capo_glue.types.name_string.NameString"
    """<p>Name of the new crawler.</p>"""
    role: "capo_glue.types.role.Role"
    """<p>The IAM role or Amazon Resource Name (ARN) of an IAM role used by the new crawler to access customer resources.</p>"""
    database_name: NotRequired["capo_glue.types.database_name.DatabaseName"]
    """<p>The Glue database where results are written, such as: <code>arn:aws:daylight:us-east-1::database/sometable/*</code>.</p>"""
    description: NotRequired["capo_glue.types.description_string.DescriptionString"]
    """<p>A description of the new crawler.</p>"""
    targets: "capo_glue.types.crawler_targets.CrawlerTargets"
    """<p>A list of collection of targets to crawl.</p>"""
    schedule: NotRequired["capo_glue.types.cron_expression.CronExpression"]
    """<p>A <code>cron</code> expression used to specify the schedule (see <a href="https://docs.aws.amazon.com/glue/latest/dg/monitor-data-warehouse-schedule.html">Time-Based Schedules for Jobs and Crawlers</a>. For example, to run something every day at 12:15 UTC, you would specify: <code>cron(15 12 * * ? *)</code>.</p>"""
    classifiers: NotRequired["capo_glue.types.classifier_name_list.ClassifierNameList"]
    """<p>A list of custom classifiers that the user has registered. By default, all built-in classifiers are included in a crawl, but these custom classifiers always override the default classifiers for a given classification.</p>"""
    table_prefix: NotRequired["capo_glue.types.table_prefix.TablePrefix"]
    """<p>The table prefix used for catalog tables that are created.</p>"""
    schema_change_policy: NotRequired[
        "capo_glue.types.schema_change_policy.SchemaChangePolicy"
    ]
    """<p>The policy for the crawler's update and deletion behavior.</p>"""
    recrawl_policy: NotRequired["capo_glue.types.recrawl_policy.RecrawlPolicy"]
    """<p>A policy that specifies whether to crawl the entire dataset again, or to crawl only folders that were added since the last crawler run.</p>"""
    lineage_configuration: NotRequired[
        "capo_glue.types.lineage_configuration.LineageConfiguration"
    ]
    """<p>Specifies data lineage configuration settings for the crawler.</p>"""
    lake_formation_configuration: NotRequired[
        "capo_glue.types.lake_formation_configuration.LakeFormationConfiguration"
    ]
    """<p>Specifies Lake Formation configuration settings for the crawler.</p>"""
    configuration: NotRequired[
        "capo_glue.types.crawler_configuration.CrawlerConfiguration"
    ]
    """<p>Crawler configuration information. This versioned JSON string allows users to specify aspects of a crawler's behavior. For more information, see <a href="https://docs.aws.amazon.com/glue/latest/dg/crawler-configuration.html">Setting crawler configuration options</a>.</p>"""
    crawler_security_configuration: NotRequired[
        "capo_glue.types.crawler_security_configuration.CrawlerSecurityConfiguration"
    ]
    """<p>The name of the <code>SecurityConfiguration</code> structure to be used by this crawler.</p>"""
    tags: NotRequired["capo_glue.types.tags_map.TagsMap"]
    """<p>The tags to use with this crawler request. You may use tags to limit access to the crawler. For more information about tags in Glue, see <a href="https://docs.aws.amazon.com/glue/latest/dg/monitor-tags.html">Amazon Web Services Tags in Glue</a> in the developer guide.</p>"""
    catalog_id: NotRequired["capo_glue.types.catalog_id_string.CatalogIdString"]
    """<p>The ID of the Data Catalog in which to store the crawler's output. If none is supplied, the Amazon Web Services account ID is used by default.</p>"""