WebCrawlerConfigurationProperty Struct
Provides the configuration information required for Amazon Kendra Web Crawler.
| Source | |
|---|---|
| Type last changed |
Example
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import { aws_kendra as kendra } from 'aws-cdk-lib';
const webCrawlerConfigurationProperty: kendra.CfnDataSource.WebCrawlerConfigurationProperty = {
urls: {
seedUrlConfiguration: {
seedUrls: ['seedUrls'],
// the properties below are optional
webCrawlerMode: 'webCrawlerMode',
},
siteMapsConfiguration: {
siteMaps: ['siteMaps'],
},
},
// the properties below are optional
authenticationConfiguration: {
basicAuthentication: [{
credentials: 'credentials',
host: 'host',
port: 123,
}],
},
crawlDepth: 123,
maxContentSizePerPageInMegaBytes: 123,
maxLinksPerPage: 123,
maxUrlsPerMinuteCrawlRate: 123,
proxyConfiguration: {
host: 'host',
port: 123,
// the properties below are optional
credentials: 'credentials',
},
urlExclusionPatterns: ['urlExclusionPatterns'],
urlInclusionPatterns: ['urlInclusionPatterns'],
};
# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk import aws_kendra as kendra
web_crawler_configuration_property = kendra.CfnDataSource.WebCrawlerConfigurationProperty(
urls=kendra.CfnDataSource.WebCrawlerUrlsProperty(
seed_url_configuration=kendra.CfnDataSource.WebCrawlerSeedUrlConfigurationProperty(
seed_urls=["seedUrls"],
# the properties below are optional
web_crawler_mode="webCrawlerMode"
),
site_maps_configuration=kendra.CfnDataSource.WebCrawlerSiteMapsConfigurationProperty(
site_maps=["siteMaps"]
)
),
# the properties below are optional
authentication_configuration=kendra.CfnDataSource.WebCrawlerAuthenticationConfigurationProperty(
basic_authentication=[kendra.CfnDataSource.WebCrawlerBasicAuthenticationProperty(
credentials="credentials",
host="host",
port=123
)]
),
crawl_depth=123,
max_content_size_per_page_in_mega_bytes=123,
max_links_per_page=123,
max_urls_per_minute_crawl_rate=123,
proxy_configuration=kendra.CfnDataSource.ProxyConfigurationProperty(
host="host",
port=123,
# the properties below are optional
credentials="credentials"
),
url_exclusion_patterns=["urlExclusionPatterns"],
url_inclusion_patterns=["urlInclusionPatterns"]
)
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import software.amazon.awscdk.services.kendra.*;
WebCrawlerConfigurationProperty webCrawlerConfigurationProperty = WebCrawlerConfigurationProperty.builder()
.urls(WebCrawlerUrlsProperty.builder()
.seedUrlConfiguration(WebCrawlerSeedUrlConfigurationProperty.builder()
.seedUrls(List.of("seedUrls"))
// the properties below are optional
.webCrawlerMode("webCrawlerMode")
.build())
.siteMapsConfiguration(WebCrawlerSiteMapsConfigurationProperty.builder()
.siteMaps(List.of("siteMaps"))
.build())
.build())
// the properties below are optional
.authenticationConfiguration(WebCrawlerAuthenticationConfigurationProperty.builder()
.basicAuthentication(List.of(WebCrawlerBasicAuthenticationProperty.builder()
.credentials("credentials")
.host("host")
.port(123)
.build()))
.build())
.crawlDepth(123)
.maxContentSizePerPageInMegaBytes(123)
.maxLinksPerPage(123)
.maxUrlsPerMinuteCrawlRate(123)
.proxyConfiguration(ProxyConfigurationProperty.builder()
.host("host")
.port(123)
// the properties below are optional
.credentials("credentials")
.build())
.urlExclusionPatterns(List.of("urlExclusionPatterns"))
.urlInclusionPatterns(List.of("urlInclusionPatterns"))
.build();
// Install: dotnet add package Amazon.CDK.Lib
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
using Amazon.CDK.AWS.Kendra;
var webCrawlerConfigurationProperty = new WebCrawlerConfigurationProperty {
Urls = new WebCrawlerUrlsProperty {
SeedUrlConfiguration = new WebCrawlerSeedUrlConfigurationProperty {
SeedUrls = new [] { "seedUrls" },
// the properties below are optional
WebCrawlerMode = "webCrawlerMode"
},
SiteMapsConfiguration = new WebCrawlerSiteMapsConfigurationProperty {
SiteMaps = new [] { "siteMaps" }
}
},
// the properties below are optional
AuthenticationConfiguration = new WebCrawlerAuthenticationConfigurationProperty {
BasicAuthentication = new [] { new WebCrawlerBasicAuthenticationProperty {
Credentials = "credentials",
Host = "host",
Port = 123
} }
},
CrawlDepth = 123,
MaxContentSizePerPageInMegaBytes = 123,
MaxLinksPerPage = 123,
MaxUrlsPerMinuteCrawlRate = 123,
ProxyConfiguration = new ProxyConfigurationProperty {
Host = "host",
Port = 123,
// the properties below are optional
Credentials = "credentials"
},
UrlExclusionPatterns = new [] { "urlExclusionPatterns" },
UrlInclusionPatterns = new [] { "urlInclusionPatterns" }
};
// Install: go get github.com/aws/aws-cdk-go/awscdk/v2
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import "github.com/aws/aws-cdk-go/awscdk"
webCrawlerConfigurationProperty := &WebCrawlerConfigurationProperty{
Urls: &WebCrawlerUrlsProperty{
SeedUrlConfiguration: &WebCrawlerSeedUrlConfigurationProperty{
SeedUrls: []*string{
jsii.String("seedUrls"),
},
// the properties below are optional
WebCrawlerMode: jsii.String("webCrawlerMode"),
},
SiteMapsConfiguration: &WebCrawlerSiteMapsConfigurationProperty{
SiteMaps: []*string{
jsii.String("siteMaps"),
},
},
},
// the properties below are optional
AuthenticationConfiguration: &WebCrawlerAuthenticationConfigurationProperty{
BasicAuthentication: []interface{}{
&WebCrawlerBasicAuthenticationProperty{
Credentials: jsii.String("credentials"),
Host: jsii.String("host"),
Port: jsii.Number(123),
},
},
},
CrawlDepth: jsii.Number(123),
MaxContentSizePerPageInMegaBytes: jsii.Number(123),
MaxLinksPerPage: jsii.Number(123),
MaxUrlsPerMinuteCrawlRate: jsii.Number(123),
ProxyConfiguration: &ProxyConfigurationProperty{
Host: jsii.String("host"),
Port: jsii.Number(123),
// the properties below are optional
Credentials: jsii.String("credentials"),
},
UrlExclusionPatterns: []*string{
jsii.String("urlExclusionPatterns"),
},
UrlInclusionPatterns: []*string{
jsii.String("urlInclusionPatterns"),
},
}
Properties
authenticationConfigurationoptionalIResolvable | CfnDataSource.authentication_configurationoptionaltyping.Union[IResolvable, WebCrawlerAuthenticationConfigurationProperty]authenticationConfigurationoptionalIResolvableAuthenticationConfigurationoptionalIResolvableAuthenticationConfigurationoptionalinterface{} #notes
You can connect to websites using basic authentication of user name and password. You use a secret in AWS Secrets Manager to store your authentication credentials.
You must provide the website host name and port number. For example, the host name of https://a.example.com/page1.html is "a.example.com" and the port is 443, the standard port for HTTPS.
crawlDepthoptionalnumbercrawl_depthoptionalint | floatcrawlDepthoptionalNumberCrawlDepthoptionaldoubleCrawlDepthoptional*float64 #For example, the seed URL page is depth 1 and any hyperlinks on this page that are also crawled are depth 2.
maxContentSizePerPageInMegaBytesoptionalnumbermax_content_size_per_page_in_mega_bytesoptionalint | floatmaxContentSizePerPageInMegaBytesoptionalNumberMaxContentSizePerPageInMegaBytesoptionaldoubleMaxContentSizePerPageInMegaBytesoptional*float64 #Files larger than this size (in MB) are skipped/not crawled.
The default maximum size of a web page or attachment is set to 50 MB.
maxLinksPerPageoptionalnumbermax_links_per_pageoptionalint | floatmaxLinksPerPageoptionalNumberMaxLinksPerPageoptionaldoubleMaxLinksPerPageoptional*float64 #This number is per web page.
As a website’s web pages are crawled, any URLs the web pages link to are also crawled. URLs on a web page are crawled in order of appearance.
The default maximum links per page is 100.
maxUrlsPerMinuteCrawlRateoptionalnumbermax_urls_per_minute_crawl_rateoptionalint | floatmaxUrlsPerMinuteCrawlRateoptionalNumberMaxUrlsPerMinuteCrawlRateoptionaldoubleMaxUrlsPerMinuteCrawlRateoptional*float64 #A minimum of one URL is required.
The default maximum number of URLs crawled per website host per minute is 300.
proxyConfigurationoptionalIResolvable | CfnDataSource.proxy_configurationoptionaltyping.Union[IResolvable, ProxyConfigurationProperty]proxyConfigurationoptionalIResolvableProxyConfigurationoptionalIResolvableProxyConfigurationoptionalinterface{} #notes
You must provide the website host name and port number. For example, the host name of https://a.example.com/page1.html is "a.example.com" and the port is 443, the standard port for HTTPS.
Web proxy credentials are optional and you can use them to connect to a web proxy server that requires basic authentication. To store web proxy credentials, you use a secret in AWS Secrets Manager .
urlExclusionPatternsoptionalstring[]url_exclusion_patternsoptionaltyping.List[str]urlExclusionPatternsoptionalList<String>UrlExclusionPatternsoptionalstring[]UrlExclusionPatternsoptional*[]*string #notes
URLs that match the patterns are excluded from the index. URLs that don't match the patterns are included in the index. If a URL matches both an inclusion and exclusion pattern, the exclusion pattern takes precedence and the URL file isn't included in the index.
urlInclusionPatternsoptionalstring[]url_inclusion_patternsoptionaltyping.List[str]urlInclusionPatternsoptionalList<String>UrlInclusionPatternsoptionalstring[]UrlInclusionPatternsoptional*[]*string #notes
URLs that match the patterns are included in the index. URLs that don't match the patterns are excluded from the index. If a URL matches both an inclusion and exclusion pattern, the exclusion pattern takes precedence and the URL file isn't included in the index.
urlsIResolvable | CfnDataSource.urlstyping.Union[IResolvable, WebCrawlerUrlsProperty]urlsIResolvableUrlsIResolvableUrlsinterface{} required #notes
You can include website subdomains. You can list up to 100 seed URLs and up to three sitemap URLs.
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 webpages, or webpages that you have authorization to index.