Browserless Content To PDF

arazzo: 1.0.1
info:
  title: Browserless Content To PDF
  summary: Render a URL's HTML, then feed that exact HTML into the PDF engine to produce a self-contained PDF.
  description: >-
    A content-to-document pipeline. The workflow first renders the live page
    HTML via /chrome/content, then feeds that captured HTML string directly into
    /chrome/pdf as the html payload, so the resulting PDF is generated from the
    exact post-JavaScript HTML rather than re-fetching the live URL. This
    produces a deterministic, self-contained PDF that matches the captured
    content even if the source page later changes. Every step spells out its
    token query parameter and JSON request body inline so the flow can be read
    and executed without opening the underlying OpenAPI description.
  version: 1.0.0
sourceDescriptions:
- name: browserlessApi
  url: ../openapi/browserless-openapi.yml
  type: openapi
workflows:
- workflowId: content-to-pdf
  summary: Capture a page's rendered HTML and convert that exact HTML into a PDF.
  description: >-
    Renders the URL to HTML via /chrome/content, then passes the captured HTML
    string as the html payload to /chrome/pdf so the PDF is built from the
    snapshot rather than a fresh fetch.
  inputs:
    type: object
    required:
    - token
    - url
    properties:
      token:
        type: string
        description: The Browserless authorization token passed as a query parameter.
      url:
        type: string
        description: The URL of the page to render and convert to PDF.
  steps:
  - stepId: renderContent
    description: >-
      Render the URL to fully parsed HTML and return it as the html output for
      reuse in the PDF step.
    operationPath: '{$sourceDescriptions.browserlessApi.url}#/paths/~1chrome~1content/post'
    parameters:
    - name: token
      in: query
      value: $inputs.token
    requestBody:
      contentType: application/json
      payload:
        url: $inputs.url
        bestAttempt: true
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      html: $response.body
  - stepId: htmlToPdf
    description: >-
      Generate a PDF from the captured HTML string by supplying it as the html
      payload instead of a URL, producing a self-contained document.
    operationPath: '{$sourceDescriptions.browserlessApi.url}#/paths/~1chrome~1pdf/post'
    parameters:
    - name: token
      in: query
      value: $inputs.token
    requestBody:
      contentType: application/json
      payload:
        html: $steps.renderContent.outputs.html
        bestAttempt: true
        options:
          printBackground: true
          format: A4
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      pdf: $response.body
  outputs:
    html: $steps.renderContent.outputs.html
    pdf: $steps.htmlToPdf.outputs.pdf