Oxylabs Web Scraper API

openapi: 3.0.3
info:
  title: Oxylabs Web Intelligence APIs
  description: >-
    Oxylabs provides web scraping and data extraction APIs including the
    Web Scraper API (Realtime and Push-Pull), the Dashboard API for usage
    and statistics, and the Residential Public API for sub-user and stats
    management.
  version: '1.0'
  contact:
    name: Oxylabs Developer Support
    url: https://developers.oxylabs.io/
servers:
  - url: https://realtime.oxylabs.io/v1
    description: Web Scraper API - Realtime
  - url: https://data.oxylabs.io/v1
    description: Web Scraper API - Push-Pull
  - url: https://api.oxylabs.io
    description: Dashboard API
  - url: https://residential-api.oxylabs.io/v2
    description: Residential Public API
security:
  - basicAuth: []
  - bearerAuth: []
paths:
  /queries:
    post:
      summary: Submit a scraping job
      description: >-
        Submit a job to the Web Scraper API. Use the Realtime server to
        receive results synchronously, or the Push-Pull server to receive
        results asynchronously via callback or polling.
      operationId: submitQuery
      security:
        - basicAuth: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ScrapeRequest'
      responses:
        '200':
          description: Scrape result (Realtime) or job acknowledgement (Push-Pull)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ScrapeResponse'
        '400':
          description: Bad request
        '401':
          description: Unauthorized
  /stats/v1/filters/instances:
    get:
      summary: List statistics filter instances
      operationId: listStatsFilters
      security:
        - bearerAuth: []
      responses:
        '200':
          description: List of available filter instances
  /stats/v1/usage:
    get:
      summary: Get usage statistics
      operationId: getUsageStats
      security:
        - bearerAuth: []
      parameters:
        - in: query
          name: from
          schema:
            type: string
            format: date
        - in: query
          name: to
          schema:
            type: string
            format: date
      responses:
        '200':
          description: Usage statistics
  /login:
    post:
      summary: Residential API login
      description: Exchange username and password (basic auth) for a bearer token.
      operationId: residentialLogin
      security:
        - basicAuth: []
      responses:
        '200':
          description: Auth token issued
          content:
            application/json:
              schema:
                type: object
                properties:
                  user_id:
                    type: integer
                  token:
                    type: string
  /users/{userId}/sub-users:
    parameters:
      - $ref: '#/components/parameters/UserId'
    get:
      summary: List sub-users
      operationId: listSubUsers
      security:
        - bearerAuth: []
      responses:
        '200':
          description: Sub-user list
    post:
      summary: Create a sub-user
      operationId: createSubUser
      security:
        - bearerAuth: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SubUser'
      responses:
        '201':
          description: Sub-user created
  /users/{userId}/sub-users/{subUserId}:
    parameters:
      - $ref: '#/components/parameters/UserId'
      - $ref: '#/components/parameters/SubUserId'
    get:
      summary: Get sub-user
      operationId: getSubUser
      security:
        - bearerAuth: []
      responses:
        '200':
          description: Sub-user record
    patch:
      summary: Update sub-user
      operationId: updateSubUser
      security:
        - bearerAuth: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SubUser'
      responses:
        '200':
          description: Updated
    delete:
      summary: Delete sub-user
      operationId: deleteSubUser
      security:
        - bearerAuth: []
      responses:
        '204':
          description: Deleted
  /users/{userId}/sub-users/{subUserId}/target-stats:
    parameters:
      - $ref: '#/components/parameters/UserId'
      - $ref: '#/components/parameters/SubUserId'
    get:
      summary: Get sub-user target statistics
      operationId: getSubUserTargetStats
      security:
        - bearerAuth: []
      responses:
        '200':
          description: Target statistics
  /users/{userId}/client-stats:
    parameters:
      - $ref: '#/components/parameters/UserId'
    get:
      summary: Get client statistics
      operationId: getClientStats
      security:
        - bearerAuth: []
      responses:
        '200':
          description: Client statistics
components:
  securitySchemes:
    basicAuth:
      type: http
      scheme: basic
    bearerAuth:
      type: http
      scheme: bearer
  parameters:
    UserId:
      in: path
      name: userId
      required: true
      schema:
        type: integer
    SubUserId:
      in: path
      name: subUserId
      required: true
      schema:
        type: integer
  schemas:
    ScrapeRequest:
      type: object
      required:
        - source
      properties:
        source:
          type: string
          description: Target source identifier (e.g., google_search, amazon, universal).
        url:
          type: string
          description: Target URL (used by URL-based sources).
        query:
          type: string
          description: Search query (used by query-based sources).
        render:
          type: string
          description: Set to "html" to render JavaScript with a headless browser.
          enum:
            - html
        parse:
          type: boolean
          description: Return structured parsed result for supported sources.
        geo_location:
          type: string
          description: Geo-targeting location string.
        locale:
          type: string
        user_agent_type:
          type: string
        callback_url:
          type: string
          format: uri
        browser_instructions:
          type: array
          items:
            type: object
        parsing_instructions:
          type: object
        context:
          type: array
          items:
            type: object
    ScrapeResponse:
      type: object
      properties:
        results:
          type: array
          items:
            type: object
            properties:
              content:
                type: string
              status_code:
                type: integer
              url:
                type: string
              created_at:
                type: string
                format: date-time
        job:
          type: object
          properties:
            id:
              type: string
            status:
              type: string
    SubUser:
      type: object
      properties:
        sub_user_name:
          type: string
        password:
          type: string
        traffic_limit:
          type: integer
        status:
          type: string