arazzo: 1.0.1
info:
  title: Hyperbrowser Batch Scrape and Retrieve
  summary: Start a batch scrape over many URLs, poll status, then fetch all results.
  description: >-
    Scrapes many URLs in a single asynchronous job. The workflow submits a batch
    scrape over a list of URLs, polls the lightweight batch status endpoint until
    the job reaches a terminal state, and then fetches the full batch record
    containing every scraped page plus batching counters. 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: scrapeApi
  url: ../openapi/hyperbrowser-scrape-api-openapi.yml
  type: openapi
workflows:
- workflowId: batch-scrape-and-retrieve
  summary: Scrape a list of URLs in one batch job and return all page content.
  description: >-
    Submits a batch scrape job, waits for completion by polling status, and
    pulls every scraped page once the batch finishes.
  inputs:
    type: object
    required:
    - apiKey
    - urls
    properties:
      apiKey:
        type: string
        description: Hyperbrowser account API key sent in the x-api-key header.
      urls:
        type: array
        description: The list of URLs to scrape in the batch.
        items:
          type: string
  steps:
  - stepId: startBatch
    description: >-
      Submit a batch scrape job for the supplied URLs and capture the returned
      jobId used to track and retrieve results.
    operationId: post-api-scrape-batch
    parameters:
    - name: x-api-key
      in: header
      value: $inputs.apiKey
    requestBody:
      contentType: application/json
      payload:
        urls: $inputs.urls
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      jobId: $response.body#/jobId
  - stepId: pollStatus
    description: >-
      Poll the batch scrape job status. The status moves through pending and
      running before reaching completed, failed, or stopped; loop back while
      still in progress and branch out on a terminal state.
    operationId: get-api-scrape-batch-id-status
    parameters:
    - name: x-api-key
      in: header
      value: $inputs.apiKey
    - name: id
      in: path
      value: $steps.startBatch.outputs.jobId
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      status: $response.body#/status
    onSuccess:
    - name: batchComplete
      type: goto
      stepId: getResults
      criteria:
      - context: $response.body
        condition: $.status == "completed"
        type: jsonpath
    - name: batchRunning
      type: goto
      stepId: pollStatus
      criteria:
      - context: $response.body
        condition: $.status == "pending" || $.status == "running"
        type: jsonpath
  - stepId: getResults
    description: >-
      Fetch the completed batch scrape job to return every scraped page and the
      total page count.
    operationId: get-api-scrape-batch-id
    parameters:
    - name: x-api-key
      in: header
      value: $inputs.apiKey
    - name: id
      in: path
      value: $steps.startBatch.outputs.jobId
    successCriteria:
    - condition: $statusCode == 200
    - context: $response.body
      condition: $.status == "completed"
      type: jsonpath
    outputs:
      status: $response.body#/status
      pages: $response.body#/data
      totalScrapedPages: $response.body#/totalScrapedPages
  outputs:
    jobId: $steps.startBatch.outputs.jobId
    pages: $steps.getResults.outputs.pages
    totalScrapedPages: $steps.getResults.outputs.totalScrapedPages