com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of aws Show documentation
Show all versions of aws Show documentation
A Pulumi package for creating and managing Amazon Web Services (AWS) cloud resources.
// *** WARNING: this file was generated by pulumi-java-gen. ***
// *** Do not edit by hand unless you're certain you know what you are doing! ***
package com.pulumi.aws.kendra.inputs;
import com.pulumi.core.Output;
import com.pulumi.core.annotations.Import;
import com.pulumi.exceptions.MissingRequiredPropertyException;
import java.lang.String;
import java.util.List;
import java.util.Objects;
import java.util.Optional;
import javax.annotation.Nullable;
public final class DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs extends com.pulumi.resources.ResourceArgs {
public static final DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs Empty = new DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs();
/**
* The list of seed or starting point URLs of the websites you want to crawl. The list can include a maximum of `100` seed URLs. Array Members: Minimum number of `0` items. Maximum number of `100` items. Length Constraints: Minimum length of `1`. Maximum length of `2048`.
*
*/
@Import(name="seedUrls", required=true)
private Output> seedUrls;
/**
* @return The list of seed or starting point URLs of the websites you want to crawl. The list can include a maximum of `100` seed URLs. Array Members: Minimum number of `0` items. Maximum number of `100` items. Length Constraints: Minimum length of `1`. Maximum length of `2048`.
*
*/
public Output> seedUrls() {
return this.seedUrls;
}
/**
* The default mode is set to `HOST_ONLY`. You can choose one of the following modes:
* * `HOST_ONLY` – crawl only the website host names. For example, if the seed URL is `"abc.example.com"`, then only URLs with host name `"abc.example.com"` are crawled.
* * `SUBDOMAINS` – crawl the website host names with subdomains. For example, if the seed URL is `"abc.example.com"`, then `"a.abc.example.com"` and `"b.abc.example.com"` are also crawled.
* * `EVERYTHING` – crawl the website host names with subdomains and other domains that the webpages link to.
*
*/
@Import(name="webCrawlerMode")
private @Nullable Output webCrawlerMode;
/**
* @return The default mode is set to `HOST_ONLY`. You can choose one of the following modes:
* * `HOST_ONLY` – crawl only the website host names. For example, if the seed URL is `"abc.example.com"`, then only URLs with host name `"abc.example.com"` are crawled.
* * `SUBDOMAINS` – crawl the website host names with subdomains. For example, if the seed URL is `"abc.example.com"`, then `"a.abc.example.com"` and `"b.abc.example.com"` are also crawled.
* * `EVERYTHING` – crawl the website host names with subdomains and other domains that the webpages link to.
*
*/
public Optional
© 2015 - 2025 Weber Informatics LLC | Privacy Policy