find_apisBrowse and filter every API in the catalog.
get_api_artifactsOne API's artifacts, grouped by type.
get_openapiThe primary OpenAPI for this API.
find_similar_apisAPIs that look like this one.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This API

curl "https://apis.io/api/v1/apis/datpaq-com:datpaq-com-web-scraping-api"

All apis

curl "https://apis.io/api/v1/apis?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

openapi: 3.2.0
info:
  title: Datpaq Com Web Scraping API
  version: 1.1.0
  contact:
    name: Datpaq Support
    url: https://datpaq.com
  license:
    name: Proprietary
  description: 'Operations tagged Web Scraping across 2 of this provider''s published API definitions: datpaq-com.yaml, datpaq-com-openapi.yaml. Each path carries the servers of the definition it was published in.'
servers:
- url: https://datpaq.com/api/v1
  description: Production
- url: https://staging.datpaq.com/api/v1
  description: Staging
security:
- ApiKeyHeader: []
- ApiKeyQuery: []
tags:
- name: Web Scraping
  description: Headless scrape, batch, crawl, and site-map extraction
paths:
  /web-scraping/scrape:
    post:
      tags:
      - Web Scraping
      operationId: webScrapingScrape
      summary: Synchronously scrape a public URL
      description: Returns page content in the requested formats. SSRF-guarded. Default format is markdown with Readability main-content extraction enabled.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - url
              properties:
                url:
                  type: string
                  format: uri
                  example: https://example.com/article
                formats:
                  type: array
                  items:
                    type: string
                    enum:
                    - markdown
                    - html
                    - rawHtml
                    - links
                    - images
                    - screenshot
                  default:
                  - markdown
                onlyMainContent:
                  type: boolean
                  default: true
                waitUntil:
                  type: string
                  enum:
                  - load
                  - domcontentloaded
                  - networkidle0
                  - networkidle2
                  default: domcontentloaded
                waitFor:
                  type: integer
                  minimum: 0
                  maximum: 10000
                  default: 0
                includeTags:
                  type: array
                  items:
                    type: string
                excludeTags:
                  type: array
                  items:
                    type: string
            example:
              url: https://example.com/article
              formats:
              - markdown
      responses:
        '200':
          description: Scraped page content
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GenericSuccess'
              example:
                success: true
                url: https://example.com/article
                title: Article Title
                text: Plain text content...
                excerpt: Summary...
                byline: null
                siteName: Example
                length: 1200
                content: <article>...</article>
                markdown: '# Article Title


                  Plain text content...'
                metadata:
                  timingMs: 3500
                  cached: false
                correlationId: req_abc123
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '429':
          $ref: '#/components/responses/RateLimited'
        default:
          $ref: '#/components/responses/ServiceUnavailable'
    servers:
    - url: https://datpaq.com/api/v1
      description: Production
    - url: https://staging.datpaq.com/api/v1
      description: Staging
  /web-scraping/batch/scrape:
    post:
      tags:
      - Web Scraping
      operationId: webScrapingBatchStart
      summary: Start an async batch scrape job
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - urls
              properties:
                urls:
                  type: array
                  items:
                    type: string
                    format: uri
                  minItems: 1
                  maxItems: 100
                formats:
                  type: array
                  items:
                    type: string
            example:
              urls:
              - https://a.example.com
              - https://b.example.com
              formats:
              - markdown
      responses:
        '202':
          description: Batch job accepted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GenericSuccess'
              example:
                id: batch_01HXYZ
                status: queued
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '429':
          $ref: '#/components/responses/RateLimited'
        default:
          $ref: '#/components/responses/ServiceUnavailable'
    servers:
    - url: https://datpaq.com/api/v1
      description: Production
    - url: https://staging.datpaq.com/api/v1
      description: Staging
  /web-scraping/batch/scrape/{id}:
    get:
      tags:
      - Web Scraping
      operationId: webScrapingBatchStatus
      summary: Poll an async batch scrape job
      parameters:
      - name: id
        in: path
        required: true
        schema:
          type: string
      - name: skip
        in: query
        required: false
        schema:
          type: integer
          minimum: 0
          default: 0
      responses:
        '200':
          description: Batch job status and results
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GenericSuccess'
              example:
                id: batch_01HXYZ
                status: completed
                completed: 2
                failed: 0
                results:
                - url: https://a.example.com
                  title: A
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          $ref: '#/components/responses/NotFound'
        '429':
          $ref: '#/components/responses/RateLimited'
        default:
          $ref: '#/components/responses/ServiceUnavailable'
    servers:
    - url: https://datpaq.com/api/v1
      description: Production
    - url: https://staging.datpaq.com/api/v1
      description: Staging
  /web-scraping/crawl:
    post:
      tags:
      - Web Scraping
      operationId: webScrapingCrawlStart
      summary: Start an async site crawl
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - url
              properties:
                url:
                  type: string
                  format: uri
                limit:
                  type: integer
                maxDepth:
                  type: integer
                includePaths:
                  type: array
                  items:
                    type: string
                excludePaths:
                  type: array
                  items:
                    type: string
            example:
              url: https://example.com
              limit: 25
              maxDepth: 2
      responses:
        '202':
          description: Crawl job accepted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GenericSuccess'
              example:
                id: crawl_01HXYZ
                status: queued
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '429':
          $ref: '#/components/responses/RateLimited'
        default:
          $ref: '#/components/responses/ServiceUnavailable'
    servers:
    - url: https://datpaq.com/api/v1
      description: Production
    - url: https://staging.datpaq.com/api/v1
      description: Staging
  /web-scraping/crawl/{id}:
    get:
      tags:
      - Web Scraping
      operationId: webScrapingCrawlStatus
      summary: Poll an async crawl job
      parameters:
      - name: id
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Crawl progress and page results
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GenericSuccess'
              example:
                id: crawl_01HXYZ
                status: completed
                pages: 12
                results:
                - url: https://example.com
                  title: Home
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          $ref: '#/components/responses/NotFound'
        '429':
          $ref: '#/components/responses/RateLimited'
        default:
          $ref: '#/components/responses/ServiceUnavailable'
    servers:
    - url: https://datpaq.com/api/v1
      description: Production
    - url: https://staging.datpaq.com/api/v1
      description: Staging
  /web-scraping/map:
    post:
      tags:
      - Web Scraping
      operationId: webScrapingMap
      summary: Discover links reachable from a URL
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - url
              properties:
                url:
                  type: string
                  format: uri
            example:
              url: https://example.com
      responses:
        '200':
          description: Discovered URL map
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GenericSuccess'
              example:
                url: https://example.com
                links:
                - https://example.com/about
                - https://example.com/docs
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '429':
          $ref: '#/components/responses/RateLimited'
        default:
          $ref: '#/components/responses/ServiceUnavailable'
    servers:
    - url: https://datpaq.com/api/v1
      description: Production
    - url: https://staging.datpaq.com/api/v1
      description: Staging
components:
  schemas:
    ErrorResponse:
      type: object
      properties:
        error:
          type: string
          description: Human-readable error message
          example: Invalid API key
        correlationId:
          type: string
          description: Request tracking identifier for support
          example: abc123-def456-789ghi
        service:
          type: string
          description: Service name that produced the error
          example: ip-geolocation
    GenericSuccess:
      type: object
      description: Standard success envelope. The data property structure varies by endpoint.
      properties:
        correlationId:
          type: string
          description: Request tracking identifier
          example: abc123-def456
        data:
          type: object
          description: Response payload (structure varies by endpoint)
        cached:
          type: boolean
          description: Whether the response was served from cache
          example: false
  responses:
    NotFound:
      description: Resource not found
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    BadRequest:
      description: Bad request — missing or invalid parameters
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    RateLimited:
      description: Rate limit exceeded — retry after the indicated period
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    ServiceUnavailable:
      description: Service temporarily unavailable
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    Unauthorized:
      description: Unauthorized — missing or invalid API key
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
  securitySchemes:
    ApiKeyHeader:
      type: apiKey
      in: header
      name: x-api-key
      description: API key passed via x-api-key request header
    ApiKeyQuery:
      type: apiKey
      in: query
      name: api_key
      description: API key passed as api_key query parameter
x-refined-from:
- datpaq-com.yaml
- datpaq-com-openapi.yaml