CreateCrawler与 S Amazon DK 或命令行工具配合使用

    /// <summary>
    /// Create an AWS Glue crawler.
    /// </summary>
    /// <param name="crawlerName">The name for the crawler.</param>
    /// <param name="crawlerDescription">A description of the crawler.</param>
    /// <param name="role">The AWS Identity and Access Management (IAM) role to
    /// be assumed by the crawler.</param>
    /// <param name="schedule">The schedule on which the crawler will be executed.</param>
    /// <param name="s3Path">The path to the Amazon Simple Storage Service (Amazon S3)
    /// bucket where the Python script has been stored.</param>
    /// <param name="dbName">The name to use for the database that will be
    /// created by the crawler.</param>
    /// <returns>A Boolean value indicating the success of the action.</returns>
    public async Task<bool> CreateCrawlerAsync(
        string crawlerName,
        string crawlerDescription,
        string role,
        string schedule,
        string s3Path,
        string dbName)
    {
        var s3Target = new S3Target
        {
            Path = s3Path,
        };

        var targetList = new List<S3Target>
        {
            s3Target,
        };

        var targets = new CrawlerTargets
        {
            S3Targets = targetList,
        };

        var crawlerRequest = new CreateCrawlerRequest
        {
            DatabaseName = dbName,
            Name = crawlerName,
            Description = crawlerDescription,
            Targets = targets,
            Role = role,
            Schedule = schedule,
        };

        var response = await _amazonGlue.CreateCrawlerAsync(crawlerRequest);
        return response.HttpStatusCode == System.Net.HttpStatusCode.OK;
    }

        Aws::Client::ClientConfiguration clientConfig;
        // Optional: Set to the AWS Region in which the bucket was created (overrides config file).
        // clientConfig.region = "us-east-1";

    Aws::Glue::GlueClient client(clientConfig);

        Aws::Glue::Model::S3Target s3Target;
        s3Target.SetPath("s3://crawler-public-us-east-1/flight/2016/csv");
        Aws::Glue::Model::CrawlerTargets crawlerTargets;
        crawlerTargets.AddS3Targets(s3Target);

        Aws::Glue::Model::CreateCrawlerRequest request;
        request.SetTargets(crawlerTargets);
        request.SetName(CRAWLER_NAME);
        request.SetDatabaseName(CRAWLER_DATABASE_NAME);
        request.SetTablePrefix(CRAWLER_DATABASE_PREFIX);
        request.SetRole(roleArn);

        Aws::Glue::Model::CreateCrawlerOutcome outcome = client.CreateCrawler(request);

        if (outcome.IsSuccess()) {
            std::cout << "Successfully created the crawler." << std::endl;
        }
        else {
            std::cerr << "Error creating a crawler. " << outcome.GetError().GetMessage()
                      << std::endl;
            deleteAssets("", CRAWLER_DATABASE_NAME, "", bucketName, clientConfig);
            return false;
        }

import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.glue.GlueClient;
import software.amazon.awssdk.services.glue.model.CreateCrawlerRequest;
import software.amazon.awssdk.services.glue.model.CrawlerTargets;
import software.amazon.awssdk.services.glue.model.GlueException;
import software.amazon.awssdk.services.glue.model.S3Target;
import java.util.ArrayList;
import java.util.List;

/**
 * Before running this Java V2 code example, set up your development
 * environment, including your credentials.
 *
 * For more information, see the following documentation topic:
 *
 * https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/get-started.html
 */
public class CreateCrawler {
    public static void main(String[] args) {
        final String usage = """

                Usage:
                    <IAM> <s3Path> <cron> <dbName> <crawlerName>

                Where:
                    IAM - The ARN of the IAM role that has AWS Glue and S3 permissions.\s
                    s3Path - The Amazon Simple Storage Service (Amazon S3) target that contains data (for example, CSV data).
                    cron - A cron expression used to specify the schedule  (i.e., cron(15 12 * * ? *).
                    dbName - The database name.\s
                    crawlerName - The name of the crawler.\s
                """;

        if (args.length != 5) {
            System.out.println(usage);
            System.exit(1);
        }

        String iam = args[0];
        String s3Path = args[1];
        String cron = args[2];
        String dbName = args[3];
        String crawlerName = args[4];
        Region region = Region.US_EAST_1;
        GlueClient glueClient = GlueClient.builder()
                .region(region)
                .build();

        createGlueCrawler(glueClient, iam, s3Path, cron, dbName, crawlerName);
        glueClient.close();
    }

    public static void createGlueCrawler(GlueClient glueClient,
            String iam,
            String s3Path,
            String cron,
            String dbName,
            String crawlerName) {

        try {
            S3Target s3Target = S3Target.builder()
                    .path(s3Path)
                    .build();

            // Add the S3Target to a list.
            List<S3Target> targetList = new ArrayList<>();
            targetList.add(s3Target);

            CrawlerTargets targets = CrawlerTargets.builder()
                    .s3Targets(targetList)
                    .build();

            CreateCrawlerRequest crawlerRequest = CreateCrawlerRequest.builder()
                    .databaseName(dbName)
                    .name(crawlerName)
                    .description("Created by the AWS Glue Java API")
                    .targets(targets)
                    .role(iam)
                    .schedule(cron)
                    .build();

            glueClient.createCrawler(crawlerRequest);
            System.out.println(crawlerName + " was successfully created");

        } catch (GlueException e) {
            System.err.println(e.awsErrorDetails().errorMessage());
            System.exit(1);
        }
    }
}

const createCrawler = (name, role, dbName, tablePrefix, s3TargetPath) => {
  const client = new GlueClient({});

  const command = new CreateCrawlerCommand({
    Name: name,
    Role: role,
    DatabaseName: dbName,
    TablePrefix: tablePrefix,
    Targets: {
      S3Targets: [{ Path: s3TargetPath }],
    },
  });

  return client.send(command);
};

suspend fun createGlueCrawler(
    iam: String?,
    s3Path: String?,
    cron: String?,
    dbName: String?,
    crawlerName: String
) {
    val s3Target = S3Target {
        path = s3Path
    }

    // Add the S3Target to a list.
    val targetList = mutableListOf<S3Target>()
    targetList.add(s3Target)

    val targetOb = CrawlerTargets {
        s3Targets = targetList
    }

    val request = CreateCrawlerRequest {
        databaseName = dbName
        name = crawlerName
        description = "Created by the AWS Glue Kotlin API"
        targets = targetOb
        role = iam
        schedule = cron
    }

    GlueClient { region = "us-west-2" }.use { glueClient ->
        glueClient.createCrawler(request)
        println("$crawlerName was successfully created")
    }
}

        $crawlerName = "example-crawler-test-" . $uniqid;

        $role = $iamService->getRole("AWSGlueServiceRole-DocExample");

        $path = 's3://crawler-public-us-east-1/flight/2016/csv';
        $glueService->createCrawler($crawlerName, $role['Role']['Arn'], $databaseName, $path);

    public function createCrawler($crawlerName, $role, $databaseName, $path): Result
    {
        return $this->customWaiter(function () use ($crawlerName, $role, $databaseName, $path) {
            return $this->glueClient->createCrawler([
                'Name' => $crawlerName,
                'Role' => $role,
                'DatabaseName' => $databaseName,
                'Targets' => [
                    'S3Targets' =>
                        [[
                            'Path' => $path,
                        ]]
                ],
            ]);
        });
    }

class GlueWrapper:
    """Encapsulates AWS Glue actions."""

    def __init__(self, glue_client):
        """
        :param glue_client: A Boto3 Glue client.
        """
        self.glue_client = glue_client


    def create_crawler(self, name, role_arn, db_name, db_prefix, s3_target):
        """
        Creates a crawler that can crawl the specified target and populate a
        database in your AWS Glue Data Catalog with metadata that describes the data
        in the target.

        :param name: The name of the crawler.
        :param role_arn: The Amazon Resource Name (ARN) of an AWS Identity and Access
                         Management (IAM) role that grants permission to let AWS Glue
                         access the resources it needs.
        :param db_name: The name to give the database that is created by the crawler.
        :param db_prefix: The prefix to give any database tables that are created by
                          the crawler.
        :param s3_target: The URL to an S3 bucket that contains data that is
                          the target of the crawler.
        """
        try:
            self.glue_client.create_crawler(
                Name=name,
                Role=role_arn,
                DatabaseName=db_name,
                TablePrefix=db_prefix,
                Targets={"S3Targets": [{"Path": s3_target}]},
            )
        except ClientError as err:
            logger.error(
                "Couldn't create crawler. Here's why: %s: %s",
                err.response["Error"]["Code"],
                err.response["Error"]["Message"],
            )
            raise

# The `GlueWrapper` class serves as a wrapper around the AWS Glue API, providing a simplified interface for common operations.
# It encapsulates the functionality of the AWS SDK for Glue and provides methods for interacting with Glue crawlers, databases, tables, jobs, and S3 resources.
# The class initializes with a Glue client and a logger, allowing it to make API calls and log any errors or informational messages.
class GlueWrapper
  def initialize(glue_client, logger)
    @glue_client = glue_client
    @logger = logger
  end

  # Creates a new crawler with the specified configuration.
  #
  # @param name [String] The name of the crawler.
  # @param role_arn [String] The ARN of the IAM role to be used by the crawler.
  # @param db_name [String] The name of the database where the crawler stores its metadata.
  # @param db_prefix [String] The prefix to be added to the names of tables that the crawler creates.
  # @param s3_target [String] The S3 path that the crawler will crawl.
  # @return [void]
  def create_crawler(name, role_arn, db_name, db_prefix, s3_target)
    @glue_client.create_crawler(
      name: name,
      role: role_arn,
      database_name: db_name,
      targets: {
        s3_targets: [
          {
            path: s3_target
          }
        ]
      }
    )
  rescue Aws::Glue::Errors::GlueException => e
    @logger.error("Glue could not create crawler: \n#{e.message}")
    raise
  end

        let create_crawler = glue
            .create_crawler()
            .name(self.crawler())
            .database_name(self.database())
            .role(self.iam_role.expose_secret())
            .targets(
                CrawlerTargets::builder()
                    .s3_targets(S3Target::builder().path(CRAWLER_TARGET).build())
                    .build(),
            )
            .send()
            .await;

        match create_crawler {
            Err(err) => {
                let glue_err: aws_sdk_glue::Error = err.into();
                match glue_err {
                    aws_sdk_glue::Error::AlreadyExistsException(_) => {
                        info!("Using existing crawler");
                        Ok(())
                    }
                    _ => Err(GlueMvpError::GlueSdk(glue_err)),
                }
            }
            Ok(_) => Ok(()),
        }?;