CrawlGraph Backlinks API

openapi: 3.2.0
info:
  title: CrawlGraph Backlinks API
  description: Free backlink intelligence powered by Common Crawl's hyperlink graph.
  version: 1.2.2
tags:
- name: Backlinks
paths:
  /api/v1/backlinks:
    post:
      tags:
      - Backlinks
      summary: Look up referring domains for a target domain
      description: 'Public-API backlink lookup.


        Validates ``domain`` and ``release_id`` (400 ``validation_error`` on

        failure), charges one call against the caller''s monthly

        ``backlinks`` quota (429 ``quota_exceeded`` on overflow), then runs

        the same DuckDB query the internal route uses and returns the

        sliced results.'
      operationId: v1_lookup_backlinks_api_v1_backlinks_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/V1BacklinksBody'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/V1BacklinksResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
components:
  schemas:
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    V1BacklinkItem:
      properties:
        linking_domain:
          type: string
          title: Linking Domain
        num_hosts:
          type: integer
          title: Num Hosts
        tld:
          type: string
          title: Tld
        cg_authority:
          anyOf:
          - type: integer
          - type: 'null'
          title: Cg Authority
        cg_rank:
          anyOf:
          - type: integer
          - type: 'null'
          title: Cg Rank
      type: object
      required:
      - linking_domain
      - num_hosts
      - tld
      title: V1BacklinkItem
      description: 'One referring-domain row in the response.


        ``tld`` is the last label of ``linking_domain`` (no leading dot).

        ``cg_authority`` is a 0..100 log-rank percentile from the Common

        Crawl harmonic-centrality ranking (higher = more authoritative).

        ``cg_rank`` is the raw PageRank position across the whole graph

        (1 = top-ranked domain on the web). Both are NULL for domains

        that don''t appear in the ranks file.'
    V1BacklinksResponse:
      properties:
        domain:
          type: string
          title: Domain
        release_id:
          type: string
          title: Release Id
        release_label:
          type: string
          title: Release Label
        total_linking_domains:
          type: integer
          title: Total Linking Domains
          description: Number of distinct linking domains retrieved before the `limit` slice was applied.
        returned:
          type: integer
          title: Returned
          description: Number of rows actually included in `results`.
        cg_authority:
          anyOf:
          - type: integer
          - type: 'null'
          title: Cg Authority
          description: 0..100 log-rank percentile for the queried `domain`. NULL when the domain is missing from the ranks file.
        cg_rank:
          anyOf:
          - type: integer
          - type: 'null'
          title: Cg Rank
          description: Raw PageRank position of the queried `domain` (1 = top). NULL when the domain is missing from the ranks file.
        results:
          items:
            $ref: '#/components/schemas/V1BacklinkItem'
          type: array
          title: Results
      type: object
      required:
      - domain
      - release_id
      - release_label
      - total_linking_domains
      - returned
      - results
      title: V1BacklinksResponse
      description: Top-level response body for ``POST /api/v1/backlinks``.
    V1BacklinksBody:
      properties:
        domain:
          type: string
          maxLength: 255
          minLength: 1
          title: Domain
          description: Target domain to look up backlinks for, e.g. 'example.com'.
        release_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Release Id
          description: Common Crawl release id. Defaults to the latest release.
        limit:
          type: integer
          maximum: 10000.0
          minimum: 1.0
          title: Limit
          description: Max number of result rows to return (1..10000).
          default: 1000
        sort:
          type: string
          enum:
          - authority
          - hosts
          title: Sort
          description: Result ordering. 'authority' (default) sorts by cg_authority DESC then num_hosts DESC. 'hosts' preserves the legacy num_hosts DESC ordering.
          default: authority
      type: object
      required:
      - domain
      title: V1BacklinksBody
      description: Request body for ``POST /api/v1/backlinks``.
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError