Thordata Web Scraper API

openapi: 3.0.3
info:
  title: Thordata Web Scraper API - Tasks
  version: 1.0.0
  description: List, poll and download the results of Web Scraper API tasks launched via /builder or /video_builder.
  contact:
    name: Thordata Support
    email: support@thordata.com
    url: https://www.thordata.com/contact-us
  x-derived-from: https://raw.githubusercontent.com/Thordata/thordata-sdk-spec/main/v1.json
  x-derived-by: API Evangelist enrichment pipeline
  x-derived-on: '2026-08-11'
servers:
- url: https://openapi.thordata.com/api/web-scraper-api
  description: Web Scraper API task lifecycle
tags:
- name: Tasks
  description: Task lifecycle for the Web Scraper API
paths:
  /tasks-list:
    post:
      operationId: listScraperTasks
      tags:
      - Tasks
      summary: List scraper tasks
      security:
      - PublicToken: []
        PublicKey: []
      requestBody:
        required: true
        content:
          application/x-www-form-urlencoded:
            schema:
              type: object
              properties:
                page:
                  type: integer
                  description: 1-based page number
                size:
                  type: integer
                  description: Page size
      responses:
        '200':
          description: Paged task list. Response carries count and list.
          content:
            application/json:
              schema:
                type: object
                properties:
                  code:
                    type: integer
                  msg:
                    type: string
                  data:
                    type: object
                    properties:
                      count:
                        type: integer
                      list:
                        type: array
                        items:
                          type: object
        '400': &id001
          description: Bad Request - invalid parameters were passed. Not billed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Envelope'
        '401': &id002
          description: Unauthorized - authentication failed; check token validity. Not billed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Envelope'
        '403': &id003
          description: Forbidden - the target server refused to fulfill the request. Not billed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Envelope'
        '429': &id004
          description: Too Many Requests - request rate exceeded the API limit. Retryable with exponential backoff. Not billed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Envelope'
        '500': &id005
          description: Internal Server Error. Retryable with exponential backoff. Not billed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Envelope'
        '504': &id006
          description: Timeout Error - the proxy server timed out waiting for the upstream server. Not billed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Envelope'
  /tasks-status:
    post:
      operationId: getScraperTaskStatus
      tags:
      - Tasks
      summary: Get the status of one or more tasks
      security:
      - PublicToken: []
        PublicKey: []
      requestBody:
        required: true
        content:
          application/x-www-form-urlencoded:
            schema:
              type: object
              properties:
                tasks_ids:
                  type: string
                  description: One or more task ids
              required:
              - tasks_ids
      responses: &id007
        '200':
          description: Success. Billed only when the payload code is 200.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Envelope'
        '400': *id001
        '401': *id002
        '403': *id003
        '429': *id004
        '500': *id005
        '504': *id006
  /tasks-download:
    post:
      operationId: downloadScraperTaskResult
      tags:
      - Tasks
      summary: Download a completed task result
      security:
      - PublicToken: []
        PublicKey: []
      requestBody:
        required: true
        content:
          application/x-www-form-urlencoded:
            schema:
              type: object
              properties:
                tasks_id:
                  type: string
                type:
                  type: string
                  description: Result artifact to download
                  enum:
                  - json
                  - csv
                  - video
                  - subtitle
                  - audio
              required:
              - tasks_id
              - type
      responses: *id007
components:
  securitySchemes:
    PublicToken:
      type: apiKey
      in: header
      name: token
      description: Public token (THORDATA_PUBLIC_TOKEN) from the Thordata Dashboard.
    PublicKey:
      type: apiKey
      in: header
      name: key
      description: Public key (THORDATA_PUBLIC_KEY) from the Thordata Dashboard.
  schemas:
    Envelope:
      type: object
      description: Thordata JSON envelope. The effective status is the payload `code` when present and not 200, otherwise
        the HTTP status (v1.json errors.precedence).
      properties:
        code:
          type: integer
          description: Application status code. 200 success, 300 not collected (not billed).
        msg:
          type: string
          description: 'Human-readable message. Alternate field names: message, error, detail, description.'
        data:
          description: Result payload; shape varies by operation.