Bright Data Scrape API

openapi: 3.1.0
info:
  title: Bright Data Account Management Access Scrape API
  description: 'Programmatic management of Bright Data zones (proxy pools and product entitlements), IP

    allocations, access control (whitelists, blacklists, domain permissions), passwords, and

    billing/bandwidth reporting. Authentication uses a Bearer API token issued from the control panel.

    '
  version: '1.0'
  contact:
    name: Bright Data
    url: https://docs.brightdata.com
servers:
- url: https://api.brightdata.com
  description: Production
security:
- BearerAuth: []
tags:
- name: Scrape
  description: Trigger and monitor asynchronous scraping jobs.
paths:
  /datasets/v3/scrape:
    post:
      summary: Trigger a Web Scraper Job
      description: 'Trigger an asynchronous scraping job against a Bright Data dataset. Pass the `dataset_id` of

        the target collector and the per-record input payload as a JSON array. Returns a `snapshot_id`

        used to poll progress and download results.

        '
      operationId: triggerScrape
      tags:
      - Scrape
      parameters:
      - name: dataset_id
        in: query
        required: true
        schema:
          type: string
        description: Bright Data dataset identifier (e.g. `gd_l1viktl72bvl7bjuj0`).
      - name: include_errors
        in: query
        schema:
          type: boolean
      - name: notify
        in: query
        schema:
          type: string
          format: uri
        description: Webhook URL Bright Data calls when the snapshot completes.
      - name: format
        in: query
        schema:
          type: string
          enum:
          - json
          - ndjson
          - csv
          - jsonl
      - name: limit_per_input
        in: query
        schema:
          type: integer
      - name: limit_multiple_results
        in: query
        schema:
          type: integer
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: array
              items:
                type: object
                additionalProperties: true
      responses:
        '200':
          description: Job submitted.
          content:
            application/json:
              schema:
                type: object
                properties:
                  snapshot_id:
                    type: string
  /datasets/v3/progress/{snapshot_id}:
    parameters:
    - name: snapshot_id
      in: path
      required: true
      schema:
        type: string
    get:
      summary: Get Scrape Progress
      operationId: getScrapeProgress
      tags:
      - Scrape
      responses:
        '200':
          description: Progress.
          content:
            application/json:
              schema:
                type: object
                properties:
                  status:
                    type: string
                    enum:
                    - running
                    - ready
                    - failed
                    - building
                    - collecting
                    - cancelled
                  records:
                    type: integer
                  errors:
                    type: integer
  /datasets:
    get:
      summary: List Available Datasets
      operationId: listDatasets
      tags:
      - Scrape
      responses:
        '200':
          description: List of datasets the caller is entitled to query.
          content:
            application/json:
              schema:
                type: array
                items:
                  type: object
                  properties:
                    id:
                      type: string
                    name:
                      type: string
                    description:
                      type: string
components:
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer