SnapAPI Scrape API

openapi: 3.1.0
info:
  title: SnapAPI - Screenshot & Web Data Analyze Scrape API
  version: 2.0.0
  description: 'Professional screenshot, PDF, video, scraping, content extraction, and AI analysis API. Convert any URL into structured data or visual captures with a single API call. Powered by headless Chromium.


    ## Authentication


    All API endpoints (except Auth and Health) require one of:

    - `X-Api-Key: sk_live_xxx` header (recommended for server-side)

    - `Authorization: Bearer sk_live_xxx` header

    - `?access_key=sk_live_xxx` query parameter (for GET endpoints)


    Dashboard endpoints use JWT Bearer tokens obtained from `/auth/login`.


    ## Rate Limits


    | Plan | Requests/month | Rate |

    |------|---------------|------|

    | Free | 100 | 10/min |

    | Starter | 5,000 | 60/min |

    | Pro | 50,000 | 300/min |


    Rate limit headers: `X-RateLimit-Limit`, `X-RateLimit-Remaining`, `X-RateLimit-Reset`'
  contact:
    email: support@snapapi.pics
    url: https://snapapi.pics
servers:
- url: https://api.snapapi.pics
  description: Production
security:
- ApiKeyAuth: []
tags:
- name: Scrape
  description: Web scraping — extract text, HTML, links, markdown, or metadata from any URL
paths:
  /v1/scrape:
    post:
      operationId: scrapeWebpage
      summary: Scrape Webpage
      description: Scrape content from any URL. Returns text, HTML, markdown, links, or metadata. Supports pagination for multi-page crawls, custom proxies, and resource blocking.
      tags:
      - Scrape
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ScrapeRequest'
            examples:
              text:
                summary: Scrape as plain text
                value:
                  url: https://example.com
                  type: text
              markdown:
                summary: Scrape as markdown (LLM-ready)
                value:
                  url: https://example.com
                  type: markdown
              links:
                summary: Extract all links
                value:
                  url: https://example.com
                  type: links
              metadata:
                summary: Extract page metadata
                value:
                  url: https://example.com
                  type: metadata
              multipage:
                summary: 3-page scrape
                value:
                  url: https://example.com/blog
                  type: text
                  pages: 3
                  waitMs: 500
      responses:
        '200':
          description: Content scraped successfully
          headers:
            X-Request-Id:
              $ref: '#/components/headers/X-Request-Id'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ScrapeResponse'
        '400':
          description: Validation error or invalid URL
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Invalid or missing API key
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '429':
          description: Rate limit or quota exceeded
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '500':
          description: Scrape failed (site unreachable or timeout)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
    get:
      operationId: scrapeWebpageGet
      summary: Scrape Webpage (GET)
      description: Simple GET version of the scrape endpoint using query parameters.
      tags:
      - Scrape
      parameters:
      - name: url
        in: query
        required: true
        schema:
          type: string
          format: uri
        description: URL to scrape
      - name: type
        in: query
        schema:
          type: string
          enum:
          - text
          - html
          - links
          default: text
      - name: pages
        in: query
        schema:
          type: integer
          default: 1
      - name: wait_ms
        in: query
        schema:
          type: integer
          default: 0
      - name: block_resources
        in: query
        schema:
          type: string
          enum:
          - 'true'
          - 'false'
      - name: locale
        in: query
        schema:
          type: string
      responses:
        '200':
          description: Content scraped
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ScrapeResponse'
        '400':
          description: Validation error
        '401':
          description: Invalid API key
components:
  schemas:
    Error:
      type: object
      properties:
        statusCode:
          type: integer
        error:
          type: string
        message:
          type: string
    ScrapeResponse:
      type: object
      properties:
        success:
          type: boolean
        results:
          type: array
          items:
            type: object
            properties:
              page:
                type: integer
              url:
                type: string
              data:
                type: string
                description: Scraped content (string or JSON string for links/metadata)
    ScrapeRequest:
      type: object
      required:
      - url
      properties:
        url:
          type: string
          format: uri
          description: URL to scrape
        type:
          type: string
          enum:
          - text
          - html
          - links
          - markdown
          - metadata
          default: text
          description: Output format
        pages:
          type: integer
          minimum: 1
          maximum: 10
          default: 1
          description: Number of paginated pages to scrape
        waitMs:
          type: integer
          minimum: 0
          maximum: 30000
          default: 0
          description: Wait time in ms after page load
        proxy:
          type: string
          description: Custom proxy URL (http://user:pass@host:port)
        premiumProxy:
          type: boolean
          description: Use managed residential proxy pool
        blockResources:
          type: boolean
          default: false
          description: Block images, media, and fonts
        locale:
          type: string
          maxLength: 20
          description: Browser locale (e.g. en-US)
  headers:
    X-Request-Id:
      schema:
        type: string
      description: Unique request identifier for debugging
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: x-api-key
      description: Your SnapAPI API key
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: JWT access token obtained from /auth/login or /auth/refresh