StartCrawler 搭配 a AWS SDK 或 CLI 使用

    /// <summary>
    /// Start an AWS Glue crawler.
    /// </summary>
    /// <param name="crawlerName">The name of the crawler.</param>
    /// <returns>A Boolean value indicating the success of the action.</returns>
    public async Task<bool> StartCrawlerAsync(string crawlerName)
    {
        var crawlerRequest = new StartCrawlerRequest
        {
            Name = crawlerName,
        };

        var response = await _amazonGlue.StartCrawlerAsync(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::StartCrawlerRequest request;
        request.SetName(CRAWLER_NAME);

        Aws::Glue::Model::StartCrawlerOutcome outcome = client.StartCrawler(request);


        if (outcome.IsSuccess() || (Aws::Glue::GlueErrors::CRAWLER_RUNNING ==
                                    outcome.GetError().GetErrorType())) {
            if (!outcome.IsSuccess()) {
                std::cout << "Crawler was already started." << std::endl;
            }
            else {
                std::cout << "Successfully started crawler." << std::endl;
            }

            std::cout << "This may take a while to run." << std::endl;

            Aws::Glue::Model::CrawlerState crawlerState = Aws::Glue::Model::CrawlerState::NOT_SET;
            int iterations = 0;
            while (Aws::Glue::Model::CrawlerState::READY != crawlerState) {
                std::this_thread::sleep_for(std::chrono::seconds(1));
                ++iterations;
                if ((iterations % 10) == 0) { // Log status every 10 seconds.
                    std::cout << "Crawler status " <<
                              Aws::Glue::Model::CrawlerStateMapper::GetNameForCrawlerState(
                                      crawlerState)
                              << ". After " << iterations
                              << " seconds elapsed."
                              << std::endl;
                }
                Aws::Glue::Model::GetCrawlerRequest getCrawlerRequest;
                getCrawlerRequest.SetName(CRAWLER_NAME);

                Aws::Glue::Model::GetCrawlerOutcome getCrawlerOutcome = client.GetCrawler(
                        getCrawlerRequest);

                if (getCrawlerOutcome.IsSuccess()) {
                    crawlerState = getCrawlerOutcome.GetResult().GetCrawler().GetState();
                }
                else {
                    std::cerr << "Error getting crawler.  "
                              << getCrawlerOutcome.GetError().GetMessage() << std::endl;
                    break;
                }
            }

            if (Aws::Glue::Model::CrawlerState::READY == crawlerState) {
                std::cout << "Crawler finished running after " << iterations
                          << " seconds."
                          << std::endl;
            }
        }
        else {
            std::cerr << "Error starting a crawler.  "
                      << outcome.GetError().GetMessage()
                      << std::endl;

            deleteAssets(CRAWLER_NAME, CRAWLER_DATABASE_NAME, "", bucketName,
                         clientConfig);
            return false;
        }

啟動爬蟲程式

以下 start-crawler 範例會啟動爬蟲程式。

aws glue start-crawler --name my-crawler

輸出：

None

如需詳細資訊，請參閱《AWS Glue 開發人員指南》中的定義爬蟲程式。

    /**
     * Starts a specific AWS Glue crawler.
     *
     * @param glueClient  the AWS Glue client to use for the crawler operation
     * @param crawlerName the name of the crawler to start
     * @throws GlueException if there is an error starting the crawler
     */
    public static void startSpecificCrawler(GlueClient glueClient, String crawlerName) {
        try {
            StartCrawlerRequest crawlerRequest = StartCrawlerRequest.builder()
                .name(crawlerName)
                .build();

            glueClient.startCrawler(crawlerRequest);
            System.out.println(crawlerName + " was successfully started!");

        } catch (GlueException e) {
            throw e;
        }
    }

const startCrawler = (name) => {
  const client = new GlueClient({});

  const command = new StartCrawlerCommand({
    Name: name,
  });

  return client.send(command);
};

suspend fun startSpecificCrawler(crawlerName: String?) {
    val request =
        StartCrawlerRequest {
            name = crawlerName
        }

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

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

        $databaseName = "doc-example-database-$uniqid";

        $glueService->startCrawler($crawlerName);

    public function startCrawler($crawlerName): Result
    {
        return $this->glueClient->startCrawler([
            'Name' => $crawlerName,
        ]);
    }

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

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


    def start_crawler(self, name):
        """
        Starts a crawler. The crawler crawls its configured target and creates
        metadata that describes the data it finds in the target data source.

        :param name: The name of the crawler to start.
        """
        try:
            self.glue_client.start_crawler(Name=name)
        except ClientError as err:
            logger.error(
                "Couldn't start crawler %s. Here's why: %s: %s",
                name,
                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

  # Starts a crawler with the specified name.
  #
  # @param name [String] The name of the crawler to start.
  # @return [void]
  def start_crawler(name)
    @glue_client.start_crawler(name: name)
  rescue Aws::Glue::Errors::ServiceError => e
    @logger.error("Glue could not start crawler #{name}: \n#{e.message}")
    raise
  end

        let start_crawler = glue.start_crawler().name(self.crawler()).send().await;

        match start_crawler {
            Ok(_) => Ok(()),
            Err(err) => {
                let glue_err: aws_sdk_glue::Error = err.into();
                match glue_err {
                    aws_sdk_glue::Error::CrawlerRunningException(_) => Ok(()),
                    _ => Err(GlueMvpError::GlueSdk(glue_err)),
                }
            }
        }?;