CrawlGraph Gap Analysis API

openapi: 3.2.0
info:
  title: CrawlGraph Gap Analysis API
  description: Free backlink intelligence powered by Common Crawl's hyperlink graph.
  version: 1.2.2
tags:
- name: Gap Analysis
paths:
  /api/v1/gap-analysis:
    post:
      tags:
      - Gap Analysis
      summary: Submit an async gap-analysis job
      description: 'Queue a gap-analysis job and return a poll URL.


        Validates the input domains, charges one call against the caller''s

        monthly ``gap`` quota (429 ``quota_exceeded`` on overflow), creates

        a row in ``export_jobs`` (``kind="gap"``), and schedules the worker

        via FastAPI''s ``BackgroundTasks``. The poll endpoint reads the same

        table and is owner-scoped.'
      operationId: v1_gap_submit_api_v1_gap_analysis_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/V1GapBody'
        required: true
      responses:
        '202':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/V1GapSubmitResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/gap-analysis/{job_id}:
    get:
      tags:
      - Gap Analysis
      summary: Poll a gap-analysis job
      description: 'Return the current status of a gap-analysis job.


        Owner-scoped - jobs that don''t exist or that belong to another user

        both return ``404 not_found`` (``get_job_for_user`` enforces the

        ownership check; we can''t distinguish the two cases, which is the

        point - never leak another user''s job ids).'
      operationId: v1_gap_poll_api_v1_gap_analysis__job_id__get
      parameters:
      - name: job_id
        in: path
        required: true
        schema:
          type: string
          title: Job Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/V1GapStatusResponse'
        '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
    V1GapBody:
      properties:
        my_domain:
          type: string
          maxLength: 255
          minLength: 1
          title: My Domain
          description: Your domain (the one you want to find gaps for).
        competitor_domains:
          items:
            type: string
          type: array
          maxItems: 5
          minItems: 1
          title: Competitor Domains
          description: 1..5 competitor domains. Linking domains that link to any of these but not to ``my_domain`` are returned as gaps.
      type: object
      required:
      - my_domain
      - competitor_domains
      title: V1GapBody
      description: Request body for ``POST /api/v1/gap-analysis``.
    V1GapResultGap:
      properties:
        linking_domain:
          type: string
          title: Linking Domain
          description: Domain that links to one or more competitors but not to ``my_domain``.
        found_on:
          items:
            type: string
          type: array
          title: Found On
          description: Subset of the request's ``competitor_domains`` that this linking_domain points at.
      type: object
      required:
      - linking_domain
      - found_on
      title: V1GapResultGap
      description: One gap row in a completed job's result.
    V1GapResultBody:
      properties:
        my_domain:
          type: string
          title: My Domain
        competitor_domains:
          items:
            type: string
          type: array
          title: Competitor Domains
        gaps:
          items:
            $ref: '#/components/schemas/V1GapResultGap'
          type: array
          title: Gaps
        total_gaps:
          type: integer
          title: Total Gaps
          description: '``len(gaps)`` - convenience for clients.'
        truncated:
          type: boolean
          title: Truncated
          description: True when the result was clipped to the export cap (25,000 gaps); more linking domains exist than were returned.
          default: false
      type: object
      required:
      - my_domain
      - competitor_domains
      - gaps
      - total_gaps
      title: V1GapResultBody
      description: The ``result`` object on a completed job.
    V1GapSubmitResponse:
      properties:
        job_id:
          type: string
          title: Job Id
        status:
          type: string
          title: Status
          description: Always ``"queued"`` on submit.
        poll_url:
          type: string
          title: Poll Url
          description: GET this URL to poll job status.
      type: object
      required:
      - job_id
      - status
      - poll_url
      title: V1GapSubmitResponse
      description: '``202`` response body when a job is queued.'
    V1GapStatusResponse:
      properties:
        job_id:
          type: string
          title: Job Id
        status:
          type: string
          title: Status
          description: One of "queued" | "running" | "completed" | "failed".
        progress_pct:
          anyOf:
          - type: integer
          - type: 'null'
          title: Progress Pct
          description: 0..100 progress hint while ``status == "running"``.
        started_at:
          anyOf:
          - type: string
          - type: 'null'
          title: Started At
          description: ISO 8601 timestamp; populated once the worker picks up the job.
        completed_at:
          anyOf:
          - type: string
          - type: 'null'
          title: Completed At
          description: ISO 8601 timestamp; populated when ``status == "completed"``.
        result:
          anyOf:
          - $ref: '#/components/schemas/V1GapResultBody'
          - type: 'null'
          description: Populated when ``status == "completed"``.
        error:
          anyOf:
          - type: object
          - type: 'null'
          title: Error
          description: 'Populated when ``status == "failed"``. Shape: ``{"code": "...", "message": "..."}``.'
      type: object
      required:
      - job_id
      - status
      title: V1GapStatusResponse
      description: '``GET /api/v1/gap-analysis/{job_id}`` response.


        Single model with optional fields rather than a discriminated union -

        consumers can branch on ``status`` and pick out the field set

        relevant to that state.'
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError