Apache Nutch Database API

Query the CrawlDB and FetchDB

Operations 2

POST /db/crawldb Apache Nutch Query the CrawlDB #
GET /db/fetchdb Apache Nutch Get FetchDB Node Information #

Work with this as data

Every API 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 apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • 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.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/apache-nutch-database-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

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.

OpenAPI Specification

apache-nutch-database-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: Apache Nutch REST Admin Database API
  description: REST API for managing Apache Nutch crawl jobs, configurations, seed lists, database queries, and data readers.
  version: 1.0.0
  license:
    name: Apache 2.0
    identifier: Apache-2.0
  contact:
    name: Apache Nutch
    url: https://nutch.apache.org
servers:
- url: '{protocol}://localhost:{port}'
  description: Nutch REST server
  variables:
    protocol:
      default: http
      enum:
      - http
      - https
      description: The protocol used to access the Nutch server.
    port:
      default: '8081'
      description: The port the Nutch server listens on. Configurable via the --port command-line argument.
security:
- basicAuth: []
tags:
- name: Database
  description: Query the CrawlDB and FetchDB
paths:
  /db/crawldb:
    post:
      tags:
      - Database
      summary: Apache Nutch Query the CrawlDB
      description: 'Executes a query against the Nutch CrawlDB. The type field in the request body determines the operation: stats, dump, topN, or url. The stats and url types return JSON; dump and topN return binary octet-stream data.'
      operationId: readCrawlDb
      requestBody:
        required: true
        description: The database query parameters.
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/DbQuery'
      responses:
        '200':
          description: 'Query results. Content type varies by query type: application/json for stats and url queries; application/octet-stream for dump and topN queries.'
          content:
            application/json:
              schema:
                type: object
                description: CrawlDB query result (returned for stats and url query types).
            application/octet-stream:
              schema:
                type: string
                format: binary
                description: Binary data stream (returned for dump and topN query types).
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '500':
          $ref: '#/components/responses/InternalServerError'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /db/fetchdb:
    get:
      tags:
      - Database
      summary: Apache Nutch Get FetchDB Node Information
      description: Returns fetch node database entries for the specified index range. Both from and to default to 0; if to is 0 or exceeds the total number of entries, all entries from the starting index are returned.
      operationId: fetchDb
      parameters:
      - name: from
        in: query
        required: false
        description: Starting index (inclusive). Defaults to 0.
        schema:
          type: integer
          format: int32
          minimum: 0
          maximum: 2147483647
          default: 0
      - name: to
        in: query
        required: false
        description: Ending index (inclusive). Defaults to 0 (returns all).
        schema:
          type: integer
          format: int32
          minimum: 0
          maximum: 2147483647
          default: 0
      responses:
        '200':
          description: A JSON array of fetch node information objects.
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/FetchNodeDbInfo'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '500':
          $ref: '#/components/responses/InternalServerError'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  schemas:
    FetchNodeDbInfo:
      type: object
      description: Information about a fetched node in the FetchDB.
      required:
      - children
      properties:
        url:
          type: string
          description: The URL of the fetched node.
        status:
          type: integer
          format: int32
          minimum: 0
          maximum: 2147483647
          description: The HTTP status code of the fetch.
        numOfOutlinks:
          type: integer
          format: int32
          minimum: 0
          maximum: 2147483647
          description: The number of outgoing links discovered.
        children:
          type: array
          items:
            $ref: '#/components/schemas/ChildNode'
          description: The outgoing links from this node.
    DbQuery:
      type: object
      description: Parameters for a CrawlDB query.
      required:
      - crawlId
      - type
      properties:
        confId:
          type: string
          description: Configuration ID. Falls back to "default" if not provided.
        type:
          type: string
          description: The type of CrawlDB query to execute.
          enum:
          - stats
          - dump
          - topN
          - url
        args:
          type: object
          additionalProperties:
            type: string
          description: Additional arguments for the query.
        crawlId:
          type: string
          description: The crawl identifier.
      example:
        confId: default
        type: stats
        crawlId: crawl-01
        args: {}
    ChildNode:
      type: object
      description: A child (outlink) of a fetched node.
      properties:
        childUrl:
          type: string
          description: The URL of the child node.
        anchorText:
          type: string
          description: The anchor text of the link.
  responses:
    Unauthorized:
      description: Unauthorized. Basic authentication credentials are missing or invalid.
      content:
        application/json:
          schema:
            type: object
            properties:
              message:
                type: string
            example:
              message: Authentication required.
    BadRequest:
      description: Bad request. The request body is missing, malformed, or contains invalid parameters.
      content:
        text/plain:
          schema:
            type: string
          example: Nutch configuration cannot be empty!
    InternalServerError:
      description: An unexpected server error occurred.
      content:
        text/plain:
          schema:
            type: string
          example: Internal server error.
  securitySchemes:
    basicAuth:
      type: http
      scheme: basic
      description: HTTP Basic Authentication.