Oxylabs Realtime Scrape and Verify Usage

arazzo: 1.0.1
info:
  title: Oxylabs Realtime Scrape and Verify Usage
  summary: Run a synchronous Web Scraper API job and confirm the scrape against account usage statistics.
  description: >-
    Submits a scraping job to the Oxylabs Web Scraper API Realtime endpoint,
    which returns the rendered content synchronously, and then reads the
    account usage statistics so the caller can confirm the request was billed
    and inspect remaining capacity. The Realtime endpoint replaces the
    asynchronous submit-then-poll pattern because the single submitQuery
    operation returns results in the same response; the usage read closes the
    loop in place of a separate job-status poll. Every step spells out its
    request inline so the flow can be read and executed without opening the
    underlying OpenAPI description.
  version: 1.0.0
sourceDescriptions:
- name: queriesApi
  url: ../openapi/oxylabs-queries-api-openapi.yml
  type: openapi
- name: statsApi
  url: ../openapi/oxylabs-stats-api-openapi.yml
  type: openapi
workflows:
- workflowId: realtime-scrape-and-verify-usage
  summary: Scrape a target synchronously and verify usage was recorded.
  description: >-
    Submits a query-based or URL-based scrape to the Realtime server, captures
    the returned content, and then pulls usage statistics for a date range to
    confirm the consumption.
  inputs:
    type: object
    required:
    - source
    properties:
      source:
        type: string
        description: Target source identifier (e.g. google_search, amazon, universal).
      url:
        type: string
        description: Target URL for URL-based sources.
      query:
        type: string
        description: Search query for query-based sources.
      render:
        type: string
        description: Set to "html" to render JavaScript with a headless browser.
      geo_location:
        type: string
        description: Geo-targeting location string.
      from:
        type: string
        description: Usage window start date (YYYY-MM-DD).
      to:
        type: string
        description: Usage window end date (YYYY-MM-DD).
  steps:
  - stepId: scrapeTarget
    description: >-
      Submit the scrape to the Realtime server and receive the rendered
      content in the response.
    operationId: submitQuery
    requestBody:
      contentType: application/json
      payload:
        source: $inputs.source
        url: $inputs.url
        query: $inputs.query
        render: $inputs.render
        geo_location: $inputs.geo_location
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      content: $response.body#/results/0/content
      resultStatusCode: $response.body#/results/0/status_code
      resultUrl: $response.body#/results/0/url
  - stepId: verifyUsage
    description: >-
      Read usage statistics for the supplied date window to confirm the scrape
      was recorded against the account.
    operationId: getUsageStats
    parameters:
    - name: from
      in: query
      value: $inputs.from
    - name: to
      in: query
      value: $inputs.to
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      usage: $response.body
  outputs:
    content: $steps.scrapeTarget.outputs.content
    resultStatusCode: $steps.scrapeTarget.outputs.resultStatusCode
    usage: $steps.verifyUsage.outputs.usage