Aller au contenu

integrations/robots/schema

Ce contenu n’est pas encore disponible dans votre langue.

type PolicyOptions = {
allow?: string | string[];
cleanParam?: string | string[];
crawlDelay?: number;
disallow?: string | string[];
userAgent?: | "*"
| "360Spider"
| "360Spider-Image"
| "360Spider-Video"
| "HaoSouSpider"
| "AdsBot-Google"
| "AdsBot-Google-Mobile"
| "AdsBot-Google-Mobile-Apps"
| "Googlebot"
| "Googlebot-Image"
| "Googlebot-Mobile"
| "Googlebot-News"
| "Googlebot-Video"
| "Mediapartners-Google"
| "adidxbot"
| "bingbot"
| "BingPreview"
| "MicrosoftPreview"
| "msnbot"
| "msnbot-media"
| "Applebot"
| "AppleNewsBot"
| "Baiduspider"
| "Baiduspider-image"
| "Baiduspider-mobile"
| "Baiduspider-news"
| "Baiduspider-video"
| "coccoc"
| "coccocbot-image"
| "coccocbot-web"
| "DuckDuckBot"
| "DuckDuckGo-Favicons-Bot"
| "facebookcatalog"
| "facebookexternalhit"
| "Facebot"
| "gooblog"
| "ichiro"
| "Sogou blog"
| "Sogou inst spider"
| "Sogou News Spider"
| "Sogou Orion spider"
| "Sogou spider2"
| "Sogou web spider"
| "Yandex"
| "YandexMobileBot"
| "Algolia Crawler"
| "BublupBot"
| "CCBot"
| "Cliqzbot"
| "Daumoa"
| "DeuSu"
| "EuripBot"
| "Exploratodo"
| "Feedly"
| "Findxbot"
| "istellabot"
| "JikeSpider"
| "Lycos"
| "Mail.Ru"
| "MojeekBot"
| "OrangeBot"
| "Pinterest"
| "Plukkie"
| "Qwantify"
| "Rambler"
| "SemanticScholarBot"
| "SeznamBot"
| "Sosospider"
| "Slurp"
| "Twitterbot"
| "WhatsApp"
| "yacybot"
| "YepBot"
| "Yeti"
| "YioopBot"
| "yoozBot"
| "YoudaoBot"
| (
| "*"
| "360Spider"
| "360Spider-Image"
| "360Spider-Video"
| "HaoSouSpider"
| "AdsBot-Google"
| "AdsBot-Google-Mobile"
| "AdsBot-Google-Mobile-Apps"
| "Googlebot"
| "Googlebot-Image"
| "Googlebot-Mobile"
| "Googlebot-News"
| "Googlebot-Video"
| "Mediapartners-Google"
| "adidxbot"
| "bingbot"
| "BingPreview"
| "MicrosoftPreview"
| "msnbot"
| "msnbot-media"
| "Applebot"
| "AppleNewsBot"
| "Baiduspider"
| "Baiduspider-image"
| "Baiduspider-mobile"
| "Baiduspider-news"
| "Baiduspider-video"
| "coccoc"
| "coccocbot-image"
| "coccocbot-web"
| "DuckDuckBot"
| "DuckDuckGo-Favicons-Bot"
| "facebookcatalog"
| "facebookexternalhit"
| "Facebot"
| "gooblog"
| "ichiro"
| "Sogou blog"
| "Sogou inst spider"
| "Sogou News Spider"
| "Sogou Orion spider"
| "Sogou spider2"
| "Sogou web spider"
| "Yandex"
| "YandexMobileBot"
| "Algolia Crawler"
| "BublupBot"
| "CCBot"
| "Cliqzbot"
| "Daumoa"
| "DeuSu"
| "EuripBot"
| "Exploratodo"
| "Feedly"
| "Findxbot"
| "istellabot"
| "JikeSpider"
| "Lycos"
| "Mail.Ru"
| "MojeekBot"
| "OrangeBot"
| "Pinterest"
| "Plukkie"
| "Qwantify"
| "Rambler"
| "SemanticScholarBot"
| "SeznamBot"
| "Sosospider"
| "Slurp"
| "Twitterbot"
| "WhatsApp"
| "yacybot"
| "YepBot"
| "Yeti"
| "YioopBot"
| "yoozBot"
| "YoudaoBot")[];
};

Defined in: studiocms/packages/studiocms/src/integrations/robots/schema.ts:265^

optional allow: string | string[];

[ At least one or more allow or disallow entries per rule ] Allows indexing site sections or individual pages.

policy:[{allow:["/"]}]

Path-based URL matching, refer to SYNTAX^ via Google.

optional cleanParam: string | string[];

[ Optional ] Indicates to the robot that the page URL contains parameters (like UTM tags) that should be ignored when indexing it.

Terminal window
# for URLs like:
www.example2.com/index.php?page=1&sid=2564126ebdec301c607e5df
www.example2.com/index.php?page=1&sid=974017dcd170d6c4a5d76ae
policy:[
{
cleanParam: [
"sid /index.php",
]
}
]

For additional examples, please consult Yandex’s SYNTAX^ guide.

optional crawlDelay: number;

[ Optional ] Specifies the minimum interval (in seconds) for the search robot to wait after loading one page, before starting to load another.

policy:[{crawlDelay:5}]

About the Crawl-delay^ directive.

optional disallow: string | string[];

[ At least one or more disallow or allow entries per rule ] Prohibits indexing site sections or individual pages.

policy:[
{
disallow:[
"/admin",
"/uploads/1989-08-21/*.jpg$"
]
}
]

Path-based URL matching, refer to SYNTAX^ via Google.

optional userAgent:
| "*"
| "360Spider"
| "360Spider-Image"
| "360Spider-Video"
| "HaoSouSpider"
| "AdsBot-Google"
| "AdsBot-Google-Mobile"
| "AdsBot-Google-Mobile-Apps"
| "Googlebot"
| "Googlebot-Image"
| "Googlebot-Mobile"
| "Googlebot-News"
| "Googlebot-Video"
| "Mediapartners-Google"
| "adidxbot"
| "bingbot"
| "BingPreview"
| "MicrosoftPreview"
| "msnbot"
| "msnbot-media"
| "Applebot"
| "AppleNewsBot"
| "Baiduspider"
| "Baiduspider-image"
| "Baiduspider-mobile"
| "Baiduspider-news"
| "Baiduspider-video"
| "coccoc"
| "coccocbot-image"
| "coccocbot-web"
| "DuckDuckBot"
| "DuckDuckGo-Favicons-Bot"
| "facebookcatalog"
| "facebookexternalhit"
| "Facebot"
| "gooblog"
| "ichiro"
| "Sogou blog"
| "Sogou inst spider"
| "Sogou News Spider"
| "Sogou Orion spider"
| "Sogou spider2"
| "Sogou web spider"
| "Yandex"
| "YandexMobileBot"
| "Algolia Crawler"
| "BublupBot"
| "CCBot"
| "Cliqzbot"
| "Daumoa"
| "DeuSu"
| "EuripBot"
| "Exploratodo"
| "Feedly"
| "Findxbot"
| "istellabot"
| "JikeSpider"
| "Lycos"
| "Mail.Ru"
| "MojeekBot"
| "OrangeBot"
| "Pinterest"
| "Plukkie"
| "Qwantify"
| "Rambler"
| "SemanticScholarBot"
| "SeznamBot"
| "Sosospider"
| "Slurp"
| "Twitterbot"
| "WhatsApp"
| "yacybot"
| "YepBot"
| "Yeti"
| "YioopBot"
| "yoozBot"
| "YoudaoBot"
| (
| "*"
| "360Spider"
| "360Spider-Image"
| "360Spider-Video"
| "HaoSouSpider"
| "AdsBot-Google"
| "AdsBot-Google-Mobile"
| "AdsBot-Google-Mobile-Apps"
| "Googlebot"
| "Googlebot-Image"
| "Googlebot-Mobile"
| "Googlebot-News"
| "Googlebot-Video"
| "Mediapartners-Google"
| "adidxbot"
| "bingbot"
| "BingPreview"
| "MicrosoftPreview"
| "msnbot"
| "msnbot-media"
| "Applebot"
| "AppleNewsBot"
| "Baiduspider"
| "Baiduspider-image"
| "Baiduspider-mobile"
| "Baiduspider-news"
| "Baiduspider-video"
| "coccoc"
| "coccocbot-image"
| "coccocbot-web"
| "DuckDuckBot"
| "DuckDuckGo-Favicons-Bot"
| "facebookcatalog"
| "facebookexternalhit"
| "Facebot"
| "gooblog"
| "ichiro"
| "Sogou blog"
| "Sogou inst spider"
| "Sogou News Spider"
| "Sogou Orion spider"
| "Sogou spider2"
| "Sogou web spider"
| "Yandex"
| "YandexMobileBot"
| "Algolia Crawler"
| "BublupBot"
| "CCBot"
| "Cliqzbot"
| "Daumoa"
| "DeuSu"
| "EuripBot"
| "Exploratodo"
| "Feedly"
| "Findxbot"
| "istellabot"
| "JikeSpider"
| "Lycos"
| "Mail.Ru"
| "MojeekBot"
| "OrangeBot"
| "Pinterest"
| "Plukkie"
| "Qwantify"
| "Rambler"
| "SemanticScholarBot"
| "SeznamBot"
| "Sosospider"
| "Slurp"
| "Twitterbot"
| "WhatsApp"
| "yacybot"
| "YepBot"
| "Yeti"
| "YioopBot"
| "yoozBot"
| "YoudaoBot")[];

[ Required ] Indicates the robot to which the rules listed in robots.txt apply.

policy:[
{
userAgent: [
'Googlebot',
'Applebot',
'Baiduspider',
'bingbot'
],
// crawling rule(s) for above bots
}
]

Verified bots, refer to DITIG^ or Cloudflare Radar^.


type RobotsConfig = {
host?: string | boolean;
policy?: {
allow?: string | string[];
cleanParam?: string | string[];
crawlDelay?: number;
disallow?: string | string[];
userAgent?: | "*"
| "360Spider"
| "360Spider-Image"
| "360Spider-Video"
| "HaoSouSpider"
| "AdsBot-Google"
| "AdsBot-Google-Mobile"
| "AdsBot-Google-Mobile-Apps"
| "Googlebot"
| "Googlebot-Image"
| "Googlebot-Mobile"
| "Googlebot-News"
| "Googlebot-Video"
| "Mediapartners-Google"
| "adidxbot"
| "bingbot"
| "BingPreview"
| "MicrosoftPreview"
| "msnbot"
| "msnbot-media"
| "Applebot"
| "AppleNewsBot"
| "Baiduspider"
| "Baiduspider-image"
| "Baiduspider-mobile"
| "Baiduspider-news"
| "Baiduspider-video"
| "coccoc"
| "coccocbot-image"
| "coccocbot-web"
| "DuckDuckBot"
| "DuckDuckGo-Favicons-Bot"
| "facebookcatalog"
| "facebookexternalhit"
| "Facebot"
| "gooblog"
| "ichiro"
| "Sogou blog"
| "Sogou inst spider"
| "Sogou News Spider"
| "Sogou Orion spider"
| "Sogou spider2"
| "Sogou web spider"
| "Yandex"
| "YandexMobileBot"
| "Algolia Crawler"
| "BublupBot"
| "CCBot"
| "Cliqzbot"
| "Daumoa"
| "DeuSu"
| "EuripBot"
| "Exploratodo"
| "Feedly"
| "Findxbot"
| "istellabot"
| "JikeSpider"
| "Lycos"
| "Mail.Ru"
| "MojeekBot"
| "OrangeBot"
| "Pinterest"
| "Plukkie"
| "Qwantify"
| "Rambler"
| "SemanticScholarBot"
| "SeznamBot"
| "Sosospider"
| "Slurp"
| "Twitterbot"
| "WhatsApp"
| "yacybot"
| "YepBot"
| "Yeti"
| "YioopBot"
| "yoozBot"
| "YoudaoBot"
| (
| "*"
| "360Spider"
| "360Spider-Image"
| "360Spider-Video"
| "HaoSouSpider"
| "AdsBot-Google"
| "AdsBot-Google-Mobile"
| "AdsBot-Google-Mobile-Apps"
| "Googlebot"
| "Googlebot-Image"
| "Googlebot-Mobile"
| "Googlebot-News"
| "Googlebot-Video"
| "Mediapartners-Google"
| "adidxbot"
| "bingbot"
| "BingPreview"
| "MicrosoftPreview"
| "msnbot"
| "msnbot-media"
| "Applebot"
| "AppleNewsBot"
| "Baiduspider"
| "Baiduspider-image"
| "Baiduspider-mobile"
| "Baiduspider-news"
| "Baiduspider-video"
| "coccoc"
| "coccocbot-image"
| "coccocbot-web"
| "DuckDuckBot"
| "DuckDuckGo-Favicons-Bot"
| "facebookcatalog"
| "facebookexternalhit"
| "Facebot"
| "gooblog"
| "ichiro"
| "Sogou blog"
| "Sogou inst spider"
| "Sogou News Spider"
| "Sogou Orion spider"
| "Sogou spider2"
| "Sogou web spider"
| "Yandex"
| "YandexMobileBot"
| "Algolia Crawler"
| "BublupBot"
| "CCBot"
| "Cliqzbot"
| "Daumoa"
| "DeuSu"
| "EuripBot"
| "Exploratodo"
| "Feedly"
| "Findxbot"
| "istellabot"
| "JikeSpider"
| "Lycos"
| "Mail.Ru"
| "MojeekBot"
| "OrangeBot"
| "Pinterest"
| "Plukkie"
| "Qwantify"
| "Rambler"
| "SemanticScholarBot"
| "SeznamBot"
| "Sosospider"
| "Slurp"
| "Twitterbot"
| "WhatsApp"
| "yacybot"
| "YepBot"
| "Yeti"
| "YioopBot"
| "yoozBot"
| "YoudaoBot")[];
}[];
sitemap?: string | boolean | string[];
};

Defined in: studiocms/packages/studiocms/src/integrations/robots/schema.ts:266^

optional host: string | boolean;
false

[ Optional ] Some crawlers(Yandex) support and only accept domain names.

integrations:[
robots({
host: siteUrl.replace(/^https?://|:\d+/g, "")
})
]

optional policy: {
allow?: string | string[];
cleanParam?: string | string[];
crawlDelay?: number;
disallow?: string | string[];
userAgent?: | "*"
| "360Spider"
| "360Spider-Image"
| "360Spider-Video"
| "HaoSouSpider"
| "AdsBot-Google"
| "AdsBot-Google-Mobile"
| "AdsBot-Google-Mobile-Apps"
| "Googlebot"
| "Googlebot-Image"
| "Googlebot-Mobile"
| "Googlebot-News"
| "Googlebot-Video"
| "Mediapartners-Google"
| "adidxbot"
| "bingbot"
| "BingPreview"
| "MicrosoftPreview"
| "msnbot"
| "msnbot-media"
| "Applebot"
| "AppleNewsBot"
| "Baiduspider"
| "Baiduspider-image"
| "Baiduspider-mobile"
| "Baiduspider-news"
| "Baiduspider-video"
| "coccoc"
| "coccocbot-image"
| "coccocbot-web"
| "DuckDuckBot"
| "DuckDuckGo-Favicons-Bot"
| "facebookcatalog"
| "facebookexternalhit"
| "Facebot"
| "gooblog"
| "ichiro"
| "Sogou blog"
| "Sogou inst spider"
| "Sogou News Spider"
| "Sogou Orion spider"
| "Sogou spider2"
| "Sogou web spider"
| "Yandex"
| "YandexMobileBot"
| "Algolia Crawler"
| "BublupBot"
| "CCBot"
| "Cliqzbot"
| "Daumoa"
| "DeuSu"
| "EuripBot"
| "Exploratodo"
| "Feedly"
| "Findxbot"
| "istellabot"
| "JikeSpider"
| "Lycos"
| "Mail.Ru"
| "MojeekBot"
| "OrangeBot"
| "Pinterest"
| "Plukkie"
| "Qwantify"
| "Rambler"
| "SemanticScholarBot"
| "SeznamBot"
| "Sosospider"
| "Slurp"
| "Twitterbot"
| "WhatsApp"
| "yacybot"
| "YepBot"
| "Yeti"
| "YioopBot"
| "yoozBot"
| "YoudaoBot"
| (
| "*"
| "360Spider"
| "360Spider-Image"
| "360Spider-Video"
| "HaoSouSpider"
| "AdsBot-Google"
| "AdsBot-Google-Mobile"
| "AdsBot-Google-Mobile-Apps"
| "Googlebot"
| "Googlebot-Image"
| "Googlebot-Mobile"
| "Googlebot-News"
| "Googlebot-Video"
| "Mediapartners-Google"
| "adidxbot"
| "bingbot"
| "BingPreview"
| "MicrosoftPreview"
| "msnbot"
| "msnbot-media"
| "Applebot"
| "AppleNewsBot"
| "Baiduspider"
| "Baiduspider-image"
| "Baiduspider-mobile"
| "Baiduspider-news"
| "Baiduspider-video"
| "coccoc"
| "coccocbot-image"
| "coccocbot-web"
| "DuckDuckBot"
| "DuckDuckGo-Favicons-Bot"
| "facebookcatalog"
| "facebookexternalhit"
| "Facebot"
| "gooblog"
| "ichiro"
| "Sogou blog"
| "Sogou inst spider"
| "Sogou News Spider"
| "Sogou Orion spider"
| "Sogou spider2"
| "Sogou web spider"
| "Yandex"
| "YandexMobileBot"
| "Algolia Crawler"
| "BublupBot"
| "CCBot"
| "Cliqzbot"
| "Daumoa"
| "DeuSu"
| "EuripBot"
| "Exploratodo"
| "Feedly"
| "Findxbot"
| "istellabot"
| "JikeSpider"
| "Lycos"
| "Mail.Ru"
| "MojeekBot"
| "OrangeBot"
| "Pinterest"
| "Plukkie"
| "Qwantify"
| "Rambler"
| "SemanticScholarBot"
| "SeznamBot"
| "Sosospider"
| "Slurp"
| "Twitterbot"
| "WhatsApp"
| "yacybot"
| "YepBot"
| "Yeti"
| "YioopBot"
| "yoozBot"
| "YoudaoBot")[];
}[];

[ Optional ] List of policy rules.

policy:[
{
userAgent: "*",
allow: "/"
}
]

For more help, refer to SYNTAX^ by Yandex.

optional sitemap: string | boolean | string[];

[ Optional, zero or more per file ] The location of a sitemap for this website.

sitemap: [
"https://example.com/sitemap.xml",
"https://www.example.com/sitemap.xml"
]

The value of the SITEMAP^ field is case-sensitive.


type SearchEngine =
| "360Spider"
| "360Spider-Image"
| "360Spider-Video"
| "HaoSouSpider"
| "AdsBot-Google"
| "AdsBot-Google-Mobile"
| "AdsBot-Google-Mobile-Apps"
| "Googlebot"
| "Googlebot-Image"
| "Googlebot-Mobile"
| "Googlebot-News"
| "Googlebot-Video"
| "Mediapartners-Google"
| "adidxbot"
| "bingbot"
| "BingPreview"
| "MicrosoftPreview"
| "msnbot"
| "msnbot-media"
| "Applebot"
| "AppleNewsBot"
| "Baiduspider"
| "Baiduspider-image"
| "Baiduspider-mobile"
| "Baiduspider-news"
| "Baiduspider-video"
| "coccoc"
| "coccocbot-image"
| "coccocbot-web"
| "DuckDuckBot"
| "DuckDuckGo-Favicons-Bot"
| "facebookcatalog"
| "facebookexternalhit"
| "Facebot"
| "gooblog"
| "ichiro"
| "Sogou blog"
| "Sogou inst spider"
| "Sogou News Spider"
| "Sogou Orion spider"
| "Sogou spider2"
| "Sogou web spider"
| "Yandex"
| "YandexMobileBot"
| "Algolia Crawler"
| "BublupBot"
| "CCBot"
| "Cliqzbot"
| "Daumoa"
| "DeuSu"
| "EuripBot"
| "Exploratodo"
| "Feedly"
| "Findxbot"
| "istellabot"
| "JikeSpider"
| "Lycos"
| "Mail.Ru"
| "MojeekBot"
| "OrangeBot"
| "Pinterest"
| "Plukkie"
| "Qwantify"
| "Rambler"
| "SemanticScholarBot"
| "SeznamBot"
| "Sosospider"
| "Slurp"
| "Twitterbot"
| "WhatsApp"
| "yacybot"
| "YepBot"
| "Yeti"
| "YioopBot"
| "yoozBot"
| "YoudaoBot";

Defined in: studiocms/packages/studiocms/src/integrations/robots/schema.ts:263^


type UserAgent =
| "*"
| "360Spider"
| "360Spider-Image"
| "360Spider-Video"
| "HaoSouSpider"
| "AdsBot-Google"
| "AdsBot-Google-Mobile"
| "AdsBot-Google-Mobile-Apps"
| "Googlebot"
| "Googlebot-Image"
| "Googlebot-Mobile"
| "Googlebot-News"
| "Googlebot-Video"
| "Mediapartners-Google"
| "adidxbot"
| "bingbot"
| "BingPreview"
| "MicrosoftPreview"
| "msnbot"
| "msnbot-media"
| "Applebot"
| "AppleNewsBot"
| "Baiduspider"
| "Baiduspider-image"
| "Baiduspider-mobile"
| "Baiduspider-news"
| "Baiduspider-video"
| "coccoc"
| "coccocbot-image"
| "coccocbot-web"
| "DuckDuckBot"
| "DuckDuckGo-Favicons-Bot"
| "facebookcatalog"
| "facebookexternalhit"
| "Facebot"
| "gooblog"
| "ichiro"
| "Sogou blog"
| "Sogou inst spider"
| "Sogou News Spider"
| "Sogou Orion spider"
| "Sogou spider2"
| "Sogou web spider"
| "Yandex"
| "YandexMobileBot"
| "Algolia Crawler"
| "BublupBot"
| "CCBot"
| "Cliqzbot"
| "Daumoa"
| "DeuSu"
| "EuripBot"
| "Exploratodo"
| "Feedly"
| "Findxbot"
| "istellabot"
| "JikeSpider"
| "Lycos"
| "Mail.Ru"
| "MojeekBot"
| "OrangeBot"
| "Pinterest"
| "Plukkie"
| "Qwantify"
| "Rambler"
| "SemanticScholarBot"
| "SeznamBot"
| "Sosospider"
| "Slurp"
| "Twitterbot"
| "WhatsApp"
| "yacybot"
| "YepBot"
| "Yeti"
| "YioopBot"
| "yoozBot"
| "YoudaoBot";

Defined in: studiocms/packages/studiocms/src/integrations/robots/schema.ts:264^

Schema for validating user agent strings in robots.txt rules.

Accepts either the wildcard ’*’ (representing all user agents) or a value from the SearchEngines schema.

SearchEngines for the list of supported search engine user agents.

const PolicyOptionsSchema: ZodObject<PolicyOptions>;

Defined in: studiocms/packages/studiocms/src/integrations/robots/schema.ts:134^


const RobotsTXTConfigSchema: ZodObject<RobotsConfig>;

Defined in: studiocms/packages/studiocms/src/integrations/robots/schema.ts:218^


const UserAgentSchema: ZodUnion<UserAgent>;

Defined in: studiocms/packages/studiocms/src/integrations/robots/schema.ts:132^

Schema for validating user agent strings in robots.txt rules.

Accepts either the wildcard ’*’ (representing all user agents) or a value from the SearchEngines schema.

SearchEngines for the list of supported search engine user agents.