SOAX Web Data API

openapi: 3.0.3
info:
  title: SOAX Web Data API
  description: >-
    The SOAX Web Data API enables extraction of fully rendered web content from any public URL. It handles JavaScript rendering, CAPTCHA bypass, anti-bot measures, and headless browser management automatically. Returns HTML, Markdown, screenshots, and XHR response data.
  version: '2'
  contact:
    name: SOAX Support
    url: https://helpcenter.soax.com/
  license:
    name: Proprietary
    url: https://soax.com/terms-of-service
servers:
  - url: https://scraping.soax.com
    description: SOAX Scraping API endpoint
security:
  - APIKeyHeader: []
tags:
  - name: Web Data
    description: Extract content from web pages
  - name: SERP Data
    description: Search engine result page extraction
  - name: Ecommerce Data
    description: E-commerce pricing and inventory data
paths:
  /v2/webdata/fetch-content:
    post:
      operationId: fetchWebContent
      summary: Fetch Web Content
      description: >-
        Fetch fully rendered content from any public web page. Handles JavaScript execution, CAPTCHA bypass, anti-bot circumvention, and headless browser management automatically. Returns HTML body, screenshots, XHR calls, or Markdown depending on response configuration.
      tags:
        - Web Data
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/FetchContentRequest'
            example:
              url: "https://www.example.com"
              proxy_settings:
                country: "us"
                type: 1
              response:
                body: true
                screenshot: false
                xhr: false
                markdown: false
      responses:
        '200':
          description: Successfully extracted web content
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/FetchContentResponse'
        '400':
          description: Invalid request parameters
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Invalid or missing API key
        '429':
          description: Rate limit exceeded
        '500':
          description: Internal server error or target site failure
  /v2/webdata/serp:
    post:
      operationId: fetchSerpData
      summary: Fetch SERP Data
      description: >-
        Extract search engine result page data from Google, Bing, and other search engines with geo-targeting. Returns structured search results, ads, and featured snippets.
      tags:
        - SERP Data
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SerpRequest'
      responses:
        '200':
          description: SERP data extracted successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SerpResponse'
        '400':
          description: Invalid request
        '401':
          description: Unauthorized
  /v2/webdata/ecommerce:
    post:
      operationId: fetchEcommerceData
      summary: Fetch Ecommerce Data
      description: >-
        Extract real-time pricing, product details, stock levels, and reviews from e-commerce sites including Amazon, eBay, and major retailer websites.
      tags:
        - Ecommerce Data
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/EcommerceRequest'
      responses:
        '200':
          description: Ecommerce data extracted successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EcommerceResponse'
        '400':
          description: Invalid request
        '401':
          description: Unauthorized
components:
  securitySchemes:
    APIKeyHeader:
      type: apiKey
      in: header
      name: X-SOAX-API-Secret
      description: SOAX API key from your dashboard Scraper APIs section
  schemas:
    FetchContentRequest:
      type: object
      required:
        - url
      properties:
        url:
          type: string
          format: uri
          description: The target URL to fetch content from
          example: "https://www.example.com"
        proxy_settings:
          type: object
          description: Proxy configuration for the request
          properties:
            country:
              type: string
              description: ISO 3166-1 alpha-2 country code for geo-targeting
              example: "us"
            type:
              type: integer
              description: Proxy type identifier (1=residential, 2=mobile, 3=datacenter)
              enum: [1, 2, 3]
              example: 1
            city:
              type: string
              description: Target city for geo-targeting
            region:
              type: string
              description: Target region/state for geo-targeting
            isp:
              type: string
              description: Target ISP for proxy selection
        response:
          type: object
          description: Configure what content to return in the response
          properties:
            body:
              type: boolean
              default: true
              description: Return the fully rendered HTML body
            screenshot:
              type: boolean
              default: false
              description: Return a PNG screenshot of the rendered page
            xhr:
              type: boolean
              default: false
              description: Return XHR/fetch background API responses captured during rendering
            markdown:
              type: boolean
              default: false
              description: Return a lightweight Markdown version of the page content
        session:
          type: object
          description: Session configuration for stateful browsing
          properties:
            sticky:
              type: boolean
              default: false
              description: Maintain the same IP across multiple requests
            session_id:
              type: string
              description: Session identifier for sticky sessions
    FetchContentResponse:
      type: object
      properties:
        status:
          type: integer
          description: HTTP status code of the fetched page
          example: 200
        url:
          type: string
          format: uri
          description: Final URL after redirects
        body:
          type: string
          description: Fully rendered HTML content of the page
        screenshot:
          type: string
          format: byte
          description: Base64-encoded PNG screenshot (if requested)
        xhr:
          type: array
          description: XHR/fetch calls captured during page rendering
          items:
            type: object
            properties:
              url:
                type: string
                description: URL of the XHR request
              method:
                type: string
                description: HTTP method
              status:
                type: integer
                description: Response status code
              body:
                type: string
                description: Response body
        markdown:
          type: string
          description: Markdown representation of the page content (if requested)
        metadata:
          type: object
          properties:
            title:
              type: string
              description: Page title
            description:
              type: string
              description: Meta description
            proxy_used:
              type: string
              description: The proxy IP used for the request
    SerpRequest:
      type: object
      required:
        - query
        - search_engine
      properties:
        query:
          type: string
          description: Search query string
          example: "best proxy providers 2026"
        search_engine:
          type: string
          enum: [google, bing, yahoo, yandex, baidu]
          description: Target search engine
          example: "google"
        country:
          type: string
          description: Country for localized search results
          example: "us"
        language:
          type: string
          description: Language code for search results
          example: "en"
        page:
          type: integer
          default: 1
          description: Result page number
        results_per_page:
          type: integer
          default: 10
          description: Number of results per page
    SerpResponse:
      type: object
      properties:
        query:
          type: string
          description: The search query
        total_results:
          type: integer
          description: Total number of results found
        organic_results:
          type: array
          items:
            type: object
            properties:
              position:
                type: integer
              title:
                type: string
              url:
                type: string
              snippet:
                type: string
        featured_snippet:
          type: object
          properties:
            title:
              type: string
            content:
              type: string
            url:
              type: string
        ads:
          type: array
          items:
            type: object
            properties:
              position:
                type: integer
              title:
                type: string
              url:
                type: string
              description:
                type: string
    EcommerceRequest:
      type: object
      required:
        - url
      properties:
        url:
          type: string
          format: uri
          description: URL of the product page to extract data from
        extract:
          type: array
          description: Data fields to extract
          items:
            type: string
            enum: [price, title, description, images, rating, reviews, stock, sku, seller]
        country:
          type: string
          description: Country for localized pricing
    EcommerceResponse:
      type: object
      properties:
        url:
          type: string
        title:
          type: string
        price:
          type: object
          properties:
            amount:
              type: number
            currency:
              type: string
            original_price:
              type: number
            discount_percentage:
              type: number
        stock:
          type: string
          enum: [in_stock, out_of_stock, limited]
        rating:
          type: number
          minimum: 0
          maximum: 5
        reviews_count:
          type: integer
        images:
          type: array
          items:
            type: string
            format: uri
    ErrorResponse:
      type: object
      properties:
        error:
          type: string
          description: Error code
        message:
          type: string
          description: Human-readable error description
        request_id:
          type: string
          description: Request identifier for support