Crawlbase Storage API API

openapi: 3.0.3
info:
  title: Crawlbase Crawling API Storage API API
  description: 'Crawlbase (formerly ProxyCrawl) is a web crawling and scraping platform. A single REST host, https://api.crawlbase.com, exposes several products, all authenticated with a `token` query parameter: the Crawling API (fetch any URL through a rotating proxy network, optionally rendered in headless Chrome), the Scraper API (ready-made structured extractors for popular sites), the Cloud Storage API (retrieve/list/delete previously stored crawls), the Screenshots API (rendered page captures), and the Leads API (domain email discovery).

    Grounding note: paths, methods, and the token query-param auth model are confirmed from Crawlbase''s public documentation. Request query parameters are modeled from the documented parameter reference. Response bodies are largely raw upstream content (HTML, Markdown, JSON, or images) or, for the Scraper API, provider-specific JSON whose exact fields vary per scraper and are therefore modeled loosely rather than enumerated. Treat response schemas as illustrative.'
  version: '1.0'
  contact:
    name: Crawlbase
    url: https://crawlbase.com
servers:
- url: https://api.crawlbase.com
  description: Crawlbase API host (all products share this host)
security:
- tokenAuth: []
tags:
- name: Storage API
  description: Retrieve, list, and delete previously stored crawls.
paths:
  /storage:
    get:
      operationId: getStoredPage
      tags:
      - Storage API
      summary: Retrieve a stored page
      description: Returns a previously stored crawl by `rid` or by `url`. When queried by `url`, the most recent stored version is returned. Exactly one of `rid` or `url` is required.
      parameters:
      - name: rid
        in: query
        required: false
        description: The request id of a stored crawl.
        schema:
          type: string
      - name: url
        in: query
        required: false
        description: The URL-encoded target URL whose most recent stored version to return.
        schema:
          type: string
      - $ref: '#/components/parameters/Format'
      responses:
        '200':
          description: The stored page.
          content:
            text/html:
              schema:
                type: string
            application/json:
              schema:
                type: object
                additionalProperties: true
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          $ref: '#/components/responses/NotFound'
    delete:
      operationId: deleteStoredPage
      tags:
      - Storage API
      summary: Delete a stored page
      description: Deletes a single stored crawl identified by its `rid`.
      parameters:
      - name: rid
        in: query
        required: true
        description: The request id of the stored crawl to delete.
        schema:
          type: string
      responses:
        '200':
          description: Deletion confirmation.
          content:
            application/json:
              schema:
                type: object
                additionalProperties: true
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          $ref: '#/components/responses/NotFound'
  /storage/bulk:
    post:
      operationId: getStoredPagesBulk
      tags:
      - Storage API
      summary: Bulk retrieve stored pages
      description: Fetches up to 100 stored crawls in a single request by a list of request ids.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                rids:
                  type: array
                  items:
                    type: string
      responses:
        '200':
          description: A batch of stored pages.
          content:
            application/json:
              schema:
                type: object
                additionalProperties: true
        '401':
          $ref: '#/components/responses/Unauthorized'
  /storage/bulk_delete:
    post:
      operationId: deleteStoredPagesBulk
      tags:
      - Storage API
      summary: Bulk delete stored pages
      description: Deletes multiple stored crawls in a single request by a list of request ids.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                rids:
                  type: array
                  items:
                    type: string
      responses:
        '200':
          description: Deletion confirmation.
          content:
            application/json:
              schema:
                type: object
                additionalProperties: true
        '401':
          $ref: '#/components/responses/Unauthorized'
  /storage/rids:
    get:
      operationId: listStoredRids
      tags:
      - Storage API
      summary: List stored request ids
      description: Lists stored request ids with scroll-based pagination.
      parameters:
      - name: limit
        in: query
        required: false
        description: Maximum request ids to return per page (cap 10000).
        schema:
          type: integer
      - name: scroll
        in: query
        required: false
        description: Enable scroll pagination; the response returns a scroll_id to continue.
        schema:
          type: boolean
      responses:
        '200':
          description: A page of request ids.
          content:
            application/json:
              schema:
                type: object
                additionalProperties: true
        '401':
          $ref: '#/components/responses/Unauthorized'
  /storage/total_count:
    get:
      operationId: getStoredTotalCount
      tags:
      - Storage API
      summary: Total stored page count
      description: Returns the total number of pages currently in Cloud Storage.
      responses:
        '200':
          description: The total stored count.
          content:
            application/json:
              schema:
                type: object
                properties:
                  totalCount:
                    type: integer
        '401':
          $ref: '#/components/responses/Unauthorized'
components:
  parameters:
    Format:
      name: format
      in: query
      required: false
      description: Response format - html (default), json, or md (Markdown).
      schema:
        type: string
        enum:
        - html
        - json
        - md
        default: html
  responses:
    Unauthorized:
      description: Missing or invalid token.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    NotFound:
      description: The requested resource was not found.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  schemas:
    Error:
      type: object
      properties:
        pc_status:
          type: integer
        error:
          type: string
  securitySchemes:
    tokenAuth:
      type: apiKey
      in: query
      name: token
      description: 'Crawlbase authentication token passed as the `token` query parameter. Each account has two tokens: a Normal (TCP) token for static content and a JavaScript token for headless-Chrome rendering.'