Talend · Schema
PaginatedResources_CrawlerModel
This object represents a whole crawler but in a paginated context.
API ManagementData IntegrationData QualityETLOrchestrationPipelinesData Catalog
Properties
| Name | Type | Description |
|---|---|---|
| data | array | Contains the list of the crawlers |
| offset | integer | Pagination offset |
| limit | integer | Pagination limit |
| total | integer | Total number of crawlers |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/talend/json-schema/talend-paginated-resources-crawler-model-schema.json",
"title": "PaginatedResources_CrawlerModel",
"description": "This object represents a whole crawler but in a paginated context.",
"x-generated": "2026-11-04",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/talend-crawler-api-openapi.yml#/components/schemas/PaginatedResources_CrawlerModel",
"type": "object",
"required": [
"limit",
"offset",
"total"
],
"properties": {
"data": {
"type": "array",
"description": "Contains the list of the crawlers",
"items": {
"$ref": "#/$defs/CrawlerModel"
}
},
"offset": {
"type": "integer",
"format": "int32",
"description": "Pagination offset"
},
"limit": {
"type": "integer",
"format": "int32",
"description": "Pagination limit"
},
"total": {
"type": "integer",
"format": "int32",
"description": "Total number of crawlers"
}
},
"$defs": {
"CrawlerComplete": {
"type": "object",
"required": [
"connectionId",
"createdAt",
"createdBy",
"id",
"name",
"status"
],
"description": "This object represents a crawler in the complete version.",
"properties": {
"id": {
"type": "string",
"description": "The technical talend ID of the crawler"
},
"connectionId": {
"type": "string",
"description": "The technical talend ID of the connection"
},
"name": {
"type": "string",
"description": "Name of the crawler"
},
"description": {
"type": "string",
"description": "Description of the crawler"
},
"sharings": {
"type": "array",
"description": "Sharing policies",
"items": {
"$ref": "#/$defs/Sharing"
}
},
"status": {
"$ref": "#/$defs/Status"
},
"createdAt": {
"type": "string",
"format": "date-time",
"description": "The date when the crawler has been created"
},
"createdBy": {
"type": "string",
"description": "Technical ID of the talend user."
},
"crawledDatasets": {
"type": "array",
"description": "Names of the tables and views that we want to retrieve with the crawler.",
"items": {
"type": "string"
}
},
"updateAt": {
"type": "string",
"format": "date-time",
"description": "The date when the crawler has been updated"
},
"updatedBy": {
"type": "string",
"description": "Technical ID of the talend user."
},
"deletedAt": {
"type": "string",
"format": "date-time",
"description": "The date when the crawler has been deleted"
},
"deletedBy": {
"type": "string",
"description": "Technical ID of the talend user."
}
}
},
"CrawlerLight": {
"type": "object",
"required": [
"connectionId",
"id",
"name",
"runStatus"
],
"description": "This object represents a crawler in the light version (only contain the status).",
"properties": {
"id": {
"type": "string",
"description": "The technical talend ID of the crawler"
},
"name": {
"type": "string",
"description": "The name of the crawler"
},
"connectionId": {
"type": "string",
"description": "The technical talend ID of the connection"
},
"runStatus": {
"$ref": "#/$defs/RunStatus"
},
"deletedAt": {
"type": "string",
"format": "date-time",
"description": "The date when the crawler has been deleted"
}
}
},
"CrawlerModel": {
"description": "This object represents a whole crawler. It has two formats : either complete or light.",
"oneOf": [
{
"$ref": "#/$defs/CrawlerComplete"
},
{
"$ref": "#/$defs/CrawlerLight"
}
]
},
"RunStatus": {
"type": "string",
"description": "This object contains the different run status of the crawler."
},
"Sharing": {
"type": "object",
"required": [
"level",
"scimId",
"scimType"
],
"description": "This object indicate the sharing informations.",
"properties": {
"scimType": {
"type": "string",
"description": "indicate USER or GROUP",
"enum": [
"USER",
"GROUP"
]
},
"scimId": {
"type": "string",
"description": "the scim id of the USER or GROUP"
},
"level": {
"type": "string",
"description": "the level of the sharing",
"enum": [
"READER",
"WRITER",
"OWNER"
]
}
}
},
"Status": {
"type": "object",
"required": [
"nbDatasetsCreated",
"nbDatasetsFailed",
"nbDatasetsFinished",
"nbDatasetsToCrawl",
"nbSamplesFailed",
"runStatus"
],
"description": "This object contains informations about the crawler status",
"properties": {
"runStatus": {
"$ref": "#/$defs/RunStatus"
},
"runStartedAt": {
"type": "string",
"format": "date-time",
"description": "The date when the run has started"
},
"runBy": {
"type": "string",
"description": "Technical ID of the talend user."
},
"runFinishedAt": {
"type": "string",
"format": "date-time",
"description": "The date when the run has finished"
},
"failure": {
"type": "string"
},
"nbDatasetsToCrawl": {
"type": "integer",
"format": "int32",
"description": "Number of datasets to retrieve"
},
"nbDatasetsFinished": {
"type": "integer",
"format": "int32",
"description": "Number of datasets already retrieved"
},
"nbDatasetsCreated": {
"type": "integer",
"format": "int32",
"description": "Number of datasets tha has been created"
},
"nbDatasetsFailed": {
"type": "integer",
"format": "int32",
"description": "Number of datasets that has not been created"
},
"nbSamplesFailed": {
"type": "integer",
"format": "int32",
"description": "Number of samples that has not been created"
}
}
}
}
}
Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/talend-paginated-resources-crawler-model"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.