/** * Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved. * SPDX-License-Identifier: Apache-2.0. */ #pragma once #include #include #include #include namespace Aws { namespace Utils { namespace Json { class JsonValue; class JsonView; } // namespace Json } // namespace Utils namespace kendra { namespace Model { /** *

Provides the configuration information of the URLs to crawl.

You can * only crawl websites that use the secure communication protocol, Hypertext * Transfer Protocol Secure (HTTPS). If you receive an error when crawling a * website, it could be that the website is blocked from crawling.

When * selecting websites to index, you must adhere to the Amazon Acceptable Use Policy and all * other Amazon terms. Remember that you must only use Amazon Kendra Web Crawler to * index your own web pages, or web pages that you have authorization to index. *

See Also:

AWS API * Reference

*/ class Urls { public: AWS_KENDRA_API Urls(); AWS_KENDRA_API Urls(Aws::Utils::Json::JsonView jsonValue); AWS_KENDRA_API Urls& operator=(Aws::Utils::Json::JsonView jsonValue); AWS_KENDRA_API Aws::Utils::Json::JsonValue Jsonize() const; /** *

Configuration of the seed or starting point URLs of the websites you want to * crawl.

You can choose to crawl only the website host names, or the * website host names with subdomains, or the website host names with subdomains * and other domains that the web pages link to.

You can list up to 100 seed * URLs.

*/ inline const SeedUrlConfiguration& GetSeedUrlConfiguration() const{ return m_seedUrlConfiguration; } /** *

Configuration of the seed or starting point URLs of the websites you want to * crawl.

You can choose to crawl only the website host names, or the * website host names with subdomains, or the website host names with subdomains * and other domains that the web pages link to.

You can list up to 100 seed * URLs.

*/ inline bool SeedUrlConfigurationHasBeenSet() const { return m_seedUrlConfigurationHasBeenSet; } /** *

Configuration of the seed or starting point URLs of the websites you want to * crawl.

You can choose to crawl only the website host names, or the * website host names with subdomains, or the website host names with subdomains * and other domains that the web pages link to.

You can list up to 100 seed * URLs.

*/ inline void SetSeedUrlConfiguration(const SeedUrlConfiguration& value) { m_seedUrlConfigurationHasBeenSet = true; m_seedUrlConfiguration = value; } /** *

Configuration of the seed or starting point URLs of the websites you want to * crawl.

You can choose to crawl only the website host names, or the * website host names with subdomains, or the website host names with subdomains * and other domains that the web pages link to.

You can list up to 100 seed * URLs.

*/ inline void SetSeedUrlConfiguration(SeedUrlConfiguration&& value) { m_seedUrlConfigurationHasBeenSet = true; m_seedUrlConfiguration = std::move(value); } /** *

Configuration of the seed or starting point URLs of the websites you want to * crawl.

You can choose to crawl only the website host names, or the * website host names with subdomains, or the website host names with subdomains * and other domains that the web pages link to.

You can list up to 100 seed * URLs.

*/ inline Urls& WithSeedUrlConfiguration(const SeedUrlConfiguration& value) { SetSeedUrlConfiguration(value); return *this;} /** *

Configuration of the seed or starting point URLs of the websites you want to * crawl.

You can choose to crawl only the website host names, or the * website host names with subdomains, or the website host names with subdomains * and other domains that the web pages link to.

You can list up to 100 seed * URLs.

*/ inline Urls& WithSeedUrlConfiguration(SeedUrlConfiguration&& value) { SetSeedUrlConfiguration(std::move(value)); return *this;} /** *

Configuration of the sitemap URLs of the websites you want to crawl.

*

Only URLs belonging to the same website host names are crawled. You can list * up to three sitemap URLs.

*/ inline const SiteMapsConfiguration& GetSiteMapsConfiguration() const{ return m_siteMapsConfiguration; } /** *

Configuration of the sitemap URLs of the websites you want to crawl.

*

Only URLs belonging to the same website host names are crawled. You can list * up to three sitemap URLs.

*/ inline bool SiteMapsConfigurationHasBeenSet() const { return m_siteMapsConfigurationHasBeenSet; } /** *

Configuration of the sitemap URLs of the websites you want to crawl.

*

Only URLs belonging to the same website host names are crawled. You can list * up to three sitemap URLs.

*/ inline void SetSiteMapsConfiguration(const SiteMapsConfiguration& value) { m_siteMapsConfigurationHasBeenSet = true; m_siteMapsConfiguration = value; } /** *

Configuration of the sitemap URLs of the websites you want to crawl.

*

Only URLs belonging to the same website host names are crawled. You can list * up to three sitemap URLs.

*/ inline void SetSiteMapsConfiguration(SiteMapsConfiguration&& value) { m_siteMapsConfigurationHasBeenSet = true; m_siteMapsConfiguration = std::move(value); } /** *

Configuration of the sitemap URLs of the websites you want to crawl.

*

Only URLs belonging to the same website host names are crawled. You can list * up to three sitemap URLs.

*/ inline Urls& WithSiteMapsConfiguration(const SiteMapsConfiguration& value) { SetSiteMapsConfiguration(value); return *this;} /** *

Configuration of the sitemap URLs of the websites you want to crawl.

*

Only URLs belonging to the same website host names are crawled. You can list * up to three sitemap URLs.

*/ inline Urls& WithSiteMapsConfiguration(SiteMapsConfiguration&& value) { SetSiteMapsConfiguration(std::move(value)); return *this;} private: SeedUrlConfiguration m_seedUrlConfiguration; bool m_seedUrlConfigurationHasBeenSet = false; SiteMapsConfiguration m_siteMapsConfiguration; bool m_siteMapsConfigurationHasBeenSet = false; }; } // namespace Model } // namespace kendra } // namespace Aws