Bright Data Web Scraper API

openapi: 3.0.3
info:
  title: Bright Data Platform Browser API Web Scraper API
  description: OpenAPI description of Bright Data's REST platform APIs served from https://api.brightdata.com - the Web Scraper API (dataset trigger, progress, snapshot), the synchronous scrape endpoint, the SERP API and Web Unlocker (both POST /request with a zone), account/zone management, and a Browser API session-metadata endpoint. Paths and methods are grounded in Bright Data's published API reference; request/response schemas are representative and modeled, not exhaustively reconciled. The Scraping Browser's Chrome DevTools Protocol WebSocket surface is described separately in asyncapi/brightdata-asyncapi.yml.
  termsOfService: https://brightdata.com/legal/tos
  contact:
    name: Bright Data Support
    url: https://brightdata.com/contact
  version: '3.0'
servers:
- url: https://api.brightdata.com
  description: Bright Data platform API base host.
security:
- bearerAuth: []
tags:
- name: Web Scraper
  description: Trigger dataset collections and retrieve snapshots.
paths:
  /datasets/v3/trigger:
    post:
      operationId: triggerCollection
      tags:
      - Web Scraper
      summary: Trigger an asynchronous Web Scraper collection.
      description: Starts an asynchronous collection for a pre-built scraper (dataset). Returns a snapshot_id used to poll progress and download results.
      parameters:
      - name: dataset_id
        in: query
        required: true
        description: Scraper / dataset identifier (e.g. gd_l1viktl72bvl7bjuj0).
        schema:
          type: string
      - name: format
        in: query
        required: false
        description: Output format.
        schema:
          type: string
          enum:
          - json
          - ndjson
          - jsonl
          - csv
      - name: include_errors
        in: query
        required: false
        schema:
          type: boolean
      - name: custom_output_fields
        in: query
        required: false
        description: Pipe- or comma-delimited list of fields to return.
        schema:
          type: string
      - name: notify
        in: query
        required: false
        description: Webhook URL notified when the snapshot is ready.
        schema:
          type: string
          format: uri
      requestBody:
        required: true
        description: Array of input objects for the scraper (commonly a url per item).
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ScraperInput'
            example:
            - url: https://www.airbnb.com/rooms/50122531
            - url: https://www.airbnb.com/rooms/50127677
      responses:
        '200':
          description: Collection triggered; snapshot identifier returned.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TriggerResponse'
        '401':
          $ref: '#/components/responses/Unauthorized'
  /datasets/v3/scrape:
    post:
      operationId: scrapeSynchronous
      tags:
      - Web Scraper
      summary: Synchronous Web Scraper collection.
      description: Runs a scraper synchronously and returns records in the response body (best for small, latency-sensitive jobs).
      parameters:
      - name: dataset_id
        in: query
        required: true
        schema:
          type: string
      - name: format
        in: query
        required: false
        schema:
          type: string
          enum:
          - json
          - ndjson
          - jsonl
          - csv
      - name: include_errors
        in: query
        required: false
        schema:
          type: boolean
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ScraperInput'
      responses:
        '200':
          description: Scraped records.
          content:
            application/json:
              schema:
                type: array
                items:
                  type: object
                  additionalProperties: true
        '401':
          $ref: '#/components/responses/Unauthorized'
  /datasets/v3/progress/{snapshot_id}:
    get:
      operationId: getSnapshotProgress
      tags:
      - Web Scraper
      summary: Monitor snapshot collection progress.
      parameters:
      - name: snapshot_id
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Snapshot progress status.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ProgressResponse'
        '401':
          $ref: '#/components/responses/Unauthorized'
  /datasets/v3/snapshot/{snapshot_id}:
    get:
      operationId: getSnapshotData
      tags:
      - Web Scraper
      summary: Download snapshot data.
      parameters:
      - name: snapshot_id
        in: path
        required: true
        schema:
          type: string
      - name: format
        in: query
        required: false
        schema:
          type: string
          enum:
          - json
          - ndjson
          - jsonl
          - csv
      responses:
        '200':
          description: Collected records for the snapshot.
          content:
            application/json:
              schema:
                type: array
                items:
                  type: object
                  additionalProperties: true
        '202':
          description: Snapshot not ready yet; still running.
        '401':
          $ref: '#/components/responses/Unauthorized'
components:
  responses:
    Unauthorized:
      description: Missing or invalid API token.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: string
  schemas:
    TriggerResponse:
      type: object
      description: Response of a trigger call. (Modeled.)
      properties:
        snapshot_id:
          type: string
          description: Identifier used to poll progress and download results.
    ScraperInput:
      type: array
      description: Array of input objects passed to a scraper. Most scrapers accept a `url` per item; some accept additional discovery parameters.
      items:
        type: object
        properties:
          url:
            type: string
            format: uri
        additionalProperties: true
    ProgressResponse:
      type: object
      description: Snapshot progress. (Modeled.)
      properties:
        snapshot_id:
          type: string
        status:
          type: string
          enum:
          - running
          - ready
          - failed
        dataset_id:
          type: string
        records:
          type: integer
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API key
      description: 'Bright Data API token from the control panel, sent as `Authorization: Bearer <API_KEY>`.'