Context.dev Web Scraping API

openapi: 3.1.0
info:
  title: Context Brand Intelligence Web Scraping API
  description: API for retrieving context data from any website
  version: 1.0.0
servers:
- url: https://api.context.dev/v1
tags:
- name: Web Scraping
paths:
  /web/scrape/html:
    get:
      summary: Scrape HTML
      description: Scrapes the given URL and returns the raw HTML content of the page.
      security:
      - bearerAuth: []
      tags:
      - Web Scraping
      x-mint:
        content: <Badge color="blue">1 Credit</Badge>
        title: Scrape HTML
        sidebarTitle: Scrape HTML
        description: Scrape the raw HTML from a URL
      parameters:
      - schema:
          type: string
          minLength: 1
          format: uri
          description: Full URL to scrape (must include http:// or https:// protocol)
        required: true
        description: Full URL to scrape (must include http:// or https:// protocol)
        name: url
        in: query
      - schema:
          type: object
          properties:
            shouldParse:
              anyOf:
              - type: boolean
              - type: string
                enum:
                - 'true'
                - 'false'
              default: true
              description: When true, PDF URLs are fetched and parsed. When false, PDF URLs are skipped and a 400 WEBSITE_ACCESS_ERROR is returned.
            start:
              type: integer
              minimum: 1
              description: First 1-based PDF page to parse. When omitted, parsing starts at the first page.
            end:
              type: integer
              minimum: 1
              description: Last 1-based PDF page to parse. When omitted, parsing ends at the last page. Must be greater than or equal to start when both are provided.
            ocr:
              anyOf:
              - type: boolean
              - type: string
                enum:
                - 'true'
                - 'false'
              default: false
              description: When true, detect and OCR images embedded in the selected PDF pages, inserting recognized text at each image's position in page reading order while preserving the PDF text layer. This is separate from automatic scanned-PDF OCR fallback.
          default:
            shouldParse: true
            ocr: false
          description: PDF parsing controls. Use start/end to limit text extraction and embedded-image detection/OCR to an inclusive 1-based page range.
        required: false
        description: PDF parsing controls. Use start/end to limit text extraction and embedded-image detection/OCR to an inclusive 1-based page range.
        name: pdf
        in: query
      - schema:
          anyOf:
          - type: boolean
          - type: string
            enum:
            - 'true'
            - 'false'
          default: false
          description: When true, iframes are rendered inline into the returned HTML.
        required: false
        description: When true, iframes are rendered inline into the returned HTML.
        name: includeFrames
        in: query
      - schema:
          anyOf:
          - type: boolean
          - type: string
            enum:
            - 'true'
            - 'false'
          default: false
          description: When true, return only the page's main content in the HTML response, excluding headers, footers, sidebars, and navigation when detectable.
        required: false
        description: When true, return only the page's main content in the HTML response, excluding headers, footers, sidebars, and navigation when detectable.
        name: useMainContentOnly
        in: query
      - schema:
          type:
          - array
          - 'null'
          items:
            type: string
            minLength: 1
            maxLength: 2048
          maxItems: 50
          description: 'CSS selectors. When provided, only matching subtrees (and their descendants) are kept and everything else is dropped. When omitted, the entire document is kept. Examples: "article.main", "#content", "[role=main]".'
        required: false
        description: 'CSS selectors. When provided, only matching subtrees (and their descendants) are kept and everything else is dropped. When omitted, the entire document is kept. Examples: "article.main", "#content", "[role=main]".'
        name: includeSelectors
        in: query
      - schema:
          type:
          - array
          - 'null'
          items:
            type: string
            minLength: 1
            maxLength: 2048
          maxItems: 50
          description: 'CSS selectors to remove from the result. Applied after includeSelectors. Exclusion takes precedence: an element matching both is removed. Examples: "nav", "footer", ".ad-banner", "[aria-hidden=true]".'
        required: false
        description: 'CSS selectors to remove from the result. Applied after includeSelectors. Exclusion takes precedence: an element matching both is removed. Examples: "nav", "footer", ".ad-banner", "[aria-hidden=true]".'
        name: excludeSelectors
        in: query
      - schema:
          type:
          - integer
          - 'null'
          minimum: 0
          maximum: 2592000000
          default: 86400000
          description: Return a cached result if a prior scrape for the same parameters exists and is younger than this many milliseconds. Defaults to 1 day (86400000 ms) when omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
        required: false
        description: Return a cached result if a prior scrape for the same parameters exists and is younger than this many milliseconds. Defaults to 1 day (86400000 ms) when omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
        name: maxAgeMs
        in: query
      - schema:
          type:
          - integer
          - 'null'
          minimum: 0
          maximum: 30000
          description: 'Optional browser wait time in milliseconds after initial page load. Min: 0. Max: 30000 (30 seconds).'
        required: false
        description: 'Optional browser wait time in milliseconds after initial page load. Min: 0. Max: 30000 (30 seconds).'
        name: waitForMs
        in: query
      - schema:
          anyOf:
          - type: boolean
          - type: string
            enum:
            - 'true'
            - 'false'
          default: false
          description: When true, waits briefly for CSS and transition animations to settle before extracting HTML. Defaults to false. This adds a bit of latency in exchange for more stable output on animated pages.
        required: false
        description: When true, waits briefly for CSS and transition animations to settle before extracting HTML. Defaults to false. This adds a bit of latency in exchange for more stable output on animated pages.
        name: settleAnimations
        in: query
      - schema:
          type: object
          additionalProperties:
            type: string
            maxLength: 8192
            pattern: ^[^\r\n]*$
          description: 'Optional outbound HTTP headers forwarded only to the target URL, sent as deep-object query params such as headers[X-Custom]=value. When provided, caching is bypassed: the result is neither read from nor written to cache.'
        required: false
        description: 'Optional outbound HTTP headers forwarded only to the target URL, sent as deep-object query params such as headers[X-Custom]=value. When provided, caching is bypassed: the result is neither read from nor written to cache.'
        name: headers
        in: query
      - schema:
          $ref: '#/components/schemas/BrowserCountryCode'
        required: false
        description: Two-letter ISO 3166-1 alpha-2 country code identifying a supported Context.dev residential proxy exit location. Must be one of Context.dev's supported countries. When provided, Context.dev fetches the target page from that country.
        name: country
        in: query
      - schema:
          $ref: '#/components/schemas/LenientTimeoutMS'
        required: false
        description: Optional timeout in milliseconds for the request. If the request takes longer than this value, it will be aborted with a 408 status code. Maximum allowed value is 300000ms (5 minutes).
        name: timeoutMS
        in: query
      - $ref: '#/components/parameters/RequestTags'
      responses:
        '200':
          description: Successful response
          headers:
            X-RateLimit-Limit:
              $ref: '#/components/headers/RateLimitLimit'
            X-RateLimit-Remaining:
              $ref: '#/components/headers/RateLimitRemaining'
            X-RateLimit-Reset:
              $ref: '#/components/headers/RateLimitReset'
          content:
            application/json:
              schema:
                type: object
                properties:
                  success:
                    type: boolean
                    enum:
                    - true
                    description: Indicates success
                  html:
                    type: string
                    description: The scraped content of the page. For normal pages this is the raw HTML. When the page is a sitemap or feed served behind an XSL stylesheet (which browsers render into HTML), this is the underlying XML instead — see the `type` field.
                  url:
                    type: string
                    description: The URL that was scraped
                  type:
                    type: string
                    enum:
                    - html
                    - xml
                    - json
                    - text
                    - csv
                    - markdown
                    - svg
                    - pdf
                    - docx
                    - doc
                    - xlsx
                    - xls
                    - pptx
                    - ppt
                    description: Detected content type of the returned `html` field. Sitemaps and feeds are surfaced as `xml`; ordinary pages are `html`. Excel workbooks are surfaced as `xlsx`/`xls` with the extracted sheets as HTML tables; PowerPoint presentations are surfaced as `pptx`/`ppt` with the extracted slides as HTML.
                  metadata:
                    $ref: '#/components/schemas/PageMetadata'
                  key_metadata:
                    $ref: '#/components/schemas/KeyMetadata'
                required:
                - success
                - html
                - url
                - type
                - metadata
        '400':
          description: Bad request - Invalid URL or failed to scrape
          headers:
            X-RateLimit-Limit:
              $ref: '#/components/headers/RateLimitLimit'
            X-RateLimit-Remaining:
              $ref: '#/components/headers/RateLimitRemaining'
            X-RateLimit-Reset:
              $ref: '#/components/headers/RateLimitReset'
          content:
            application/json:
              schema:
                type: object
                properties:
                  message:
                    type: string
                    description: Error message describing the issue
                  error_code:
                    type: string
                    enum:
                    - INPUT_VALIDATION_ERROR
                    - WEBSITE_ACCESS_ERROR
                    description: Error code indicating the type of error
                  key_metadata:
                    $ref: '#/components/schemas/KeyMetadata'
                required:
                - message
                - error_code
        '401':
          description: Unauthorized - Invalid or missing API key
          headers:
            X-RateLimit-Limit:
              $ref: '#/components/headers/RateLimitLimit'
            X-RateLimit-Remaining:
              $ref: '#/components/headers/RateLimitRemaining'
            X-RateLimit-Reset:
              $ref: '#/components/headers/RateLimitReset'
          content:
            application/json:
              schema:
                type: object
                properties:
                  message:
                    type: string
                    description: Error message
                  error_code:
                    type: string
                    enum:
                    - UNAUTHORIZED
                    description: Error code indicating unauthorized access
                  key_metadata:
                    $ref: '#/components/schemas/KeyMetadata'
        '403':
          description: Forbidden - Insufficient permissions or usage limit exceeded
          headers:
            X-RateLimit-Limit:
              $ref: '#/components/headers/RateLimitLimit'
            X-RateLimit-Remaining:
              $ref: '#/components/headers/RateLimitRemaining'
            X-RateLimit-Reset:
              $ref: '#/components/headers/RateLimitReset'
          content:
            application/json:
              schema:
                type: object
                properties:
                  message:
                    type: string
                    description: Error message
                  error_code:
                    type: string
                    enum:
                    - FORBIDDEN
                    - USAGE_EXCEEDED
                    - DISABLED
                    - INSUFFICIENT_PERMISSIONS
                    description: Error code indicating forbidden access
                  key_metadata:
                    $ref: '#/components/schemas/KeyMetadata'
        '404':
          description: Target page returned a 404
          headers:
            X-RateLimit-Limit:
              $ref: '#/components/headers/RateLimitLimit'
            X-RateLimit-Remaining:
              $ref: '#/components/headers/RateLimitRemaining'
            X-RateLimit-Reset:
              $ref: '#/components/headers/RateLimitReset'
          content:
            application/json:
              schema:
                type: object
                properties:
                  message:
                    type: string
                    description: Error message describing the issue
                  error_code:
                    type: string
                    enum:
                    - NOT_FOUND
                    description: Error code indicating the target page was not found
                  key_metadata:
                    $ref: '#/components/schemas/KeyMetadata'
                required:
                - message
                - error_code
        '408':
          description: Request timeout
          headers:
            X-RateLimit-Limit:
              $ref: '#/components/headers/RateLimitLimit'
            X-RateLimit-Remaining:
              $ref: '#/components/headers/RateLimitRemaining'
            X-RateLimit-Reset:
              $ref: '#/components/headers/RateLimitReset'
          content:
            application/json:
              schema:
                type: object
                properties:
                  message:
                    type: string
                    description: Timeout error message
                  error_code:
                    type: string
                    enum:
                    - REQUEST_TIMEOUT
                    description: Error code indicating request timeout
                  key_metadata:
                    $ref: '#/components/schemas/KeyMetadata'
        '415':
          description: Unsupported content type - the URL resolved to a content type that is not supported (e.g. an image, presentation, media, or archive). Supported types are HTML, XML, PDF, DOCX, DOC, XLSX, XLS, PPTX, PPT, and CSV.
          headers:
            X-RateLimit-Limit:
              $ref: '#/components/headers/RateLimitLimit'
            X-RateLimit-Remaining:
              $ref: '#/components/headers/RateLimitRemaining'
            X-RateLimit-Reset:
              $ref: '#/components/headers/RateLimitReset'
          content:
            application/json:
              schema:
                type: object
                properties:
                  message:
                    type: string
                    description: Error message describing the unsupported content type
                  error_code:
                    type: string
                    enum:
                    - UNSUPPORTED_CONTENT
                    description: Error code indicating an unsupported content type
                  key_metadata:
                    $ref: '#/components/schemas/KeyMetadata'
                required:
                - message
                - error_code
        '429':
          $ref: '#/components/responses/RateLimited'
        '500':
          description: Internal server error
          headers:
            X-RateLimit-Limit:
              $ref: '#/components/headers/RateLimitLimit'
            X-RateLimit-Remaining:
              $ref: '#/components/headers/RateLimitRemaining'
            X-RateLimit-Reset:
              $ref: '#/components/headers/RateLimitReset'
          content:
            application/json:
              schema:
                type: object
                properties:
                  message:
                    type: string
                    description: Error message
                  error_code:
                    type: string
                    enum:
                    - INTERNAL_ERROR
                    description: Error code indicating internal server error
                  key_metadata:
                    $ref: '#/components/schemas/KeyMetadata'
      x-codeSamples:
      - lang: JavaScript
        source: "import ContextDev from 'context.dev';\n\nconst client = new ContextDev({\n  apiKey: process.env['CONTEXT_DEV_API_KEY'], // This is the default and can be omitted\n});\n\nconst response = await client.web.webScrapeHTML({ url: 'https://example.com' });\n\nconsole.log(response.html);"
      - lang: Python
        source: "import os\nfrom context.dev import ContextDev\n\nclient = ContextDev(\n    api_key=os.environ.get(\"CONTEXT_DEV_API_KEY\"),  # This is the default and can be omitted\n)\nresponse = client.web.web_scrape_html(\n    url=\"https://example.com\",\n)\nprint(response.html)"
      - lang: Go
        source: "package main\n\nimport (\n\t\"context\"\n\t\"fmt\"\n\n\t\"github.com/context-dot-dev/context-go-sdk\"\n\t\"github.com/context-dot-dev/context-go-sdk/option\"\n)\n\nfunc main() {\n\tclient := contextdev.NewClient(\n\t\toption.WithAPIKey(\"My API Key\"),\n\t)\n\tresponse, err := client.Web.WebScrapeHTML(context.TODO(), contextdev.WebWebScrapeHTMLParams{\n\t\tURL: \"https://example.com\",\n\t})\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf(\"%+v\\n\", response.HTML)\n}\n"
      - lang: Ruby
        source: 'require "context_dev"


          context_dev = ContextDev::Client.new(api_key: "My API Key")


          response = context_dev.web.web_scrape_html(url: "https://example.com")


          puts(response)'
      - lang: PHP
        source: "<?php\n\nrequire_once dirname(__DIR__) . '/vendor/autoload.php';\n\nuse ContextDev\\Client;\nuse ContextDev\\Core\\Exceptions\\APIException;\n\n$client = new Client(apiKey: getenv('CONTEXT_DEV_API_KEY') ?: 'My API Key');\n\ntry {\n  $response = $client->web->webScrapeHTML(\n    url: 'https://example.com',\n    country: 'de',\n    excludeSelectors: ['x'],\n    headers: ['foo' => 'J!'],\n    includeFrames: 'true',\n    includeSelectors: ['x'],\n    maxAgeMs: 0,\n    pdf: ['end' => 1, 'ocr' => 'true', 'shouldParse' => 'true', 'start' => 1],\n    settleAnimations: 'true',\n    tags: ['production', 'team-alpha'],\n    timeoutMs: 1,\n    useMainContentOnly: 'true',\n    waitForMs: 0,\n  );\n\n  var_dump($response);\n} catch (APIException $e) {\n  echo $e->getMessage();\n}"
      - lang: CLI
        source: "context-dev web web-scrape-html \\\n  --api-key 'My API Key' \\\n  --url https://example.com"
  /web/scrape/markdown:
    get:
      summary: Scrape Markdown
      description: 'Scrapes the given URL into LLM usable Markdown. Inspect key_metadata on JSON responses from a recognized API key; use error_code to distinguish stable failure categories.


        ### Billing & errors


        | HTTP status | Billed? | Meaning |

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

        | 200 | Yes — 1 credit | Successful scrape, including a zero-length result when includeSelectors matched nothing |

        | 400 | No | Invalid input, skipped PDF, or the page could not be scraped |

        | 401 / 403 | No | Invalid/disabled key, insufficient permissions, or credits exhausted; inspect error_code |

        | 404 | No | Target page returned or fingerprinted as not found |

        | 408 | No | Request timed out |

        | 415 | No | Unsupported content type |

        | 429 | No | Per-minute rate limit exceeded; honor Retry-After |

        | 500 | No | Internal error |'
      security:
      - bearerAuth: []
      tags:
      - Web Scraping
      x-mint:
        content: <Badge color="blue">1 Credit</Badge>
        title: Scrape Markdown
        sidebarTitle: Scrape markdown
        description: Scrape the given URL into LLM usable Markdown
      parameters:
      - schema:
          type: string
          minLength: 1
          format: uri
          description: Full URL to scrape into LLM usable Markdown (must include http:// or https:// protocol)
        required: true
        description: Full URL to scrape into LLM usable Markdown (must include http:// or https:// protocol)
        name: url
        in: query
      - schema:
          anyOf:
          - type: boolean
          - type: string
            enum:
            - 'true'
            - 'false'
          default: true
          description: Preserve hyperlinks in Markdown output
        required: false
        description: Preserve hyperlinks in Markdown output
        name: includeLinks
        in: query
      - schema:
          anyOf:
          - type: boolean
          - type: string
            enum:
            - 'true'
            - 'false'
          default: false
          description: Include image references in Markdown output
        required: false
        description: Include image references in Markdown output
        name: includeImages
        in: query
      - schema:
          anyOf:
          - type: boolean
          - type: string
            enum:
            - 'true'
            - 'false'
          default: true
          description: Shorten base64-encoded image data in the Markdown output
        required: false
        description: Shorten base64-encoded image data in the Markdown output
        name: shortenBase64Images
        in: query
      - schema:
          anyOf:
          - type: boolean
          - type: string
            enum:
            - 'true'
            - 'false'
          default: false
          description: Extract only the main content of the page, excluding headers, footers, sidebars, and navigation
        required: false
        description: Extract only the main content of the page, excluding headers, footers, sidebars, and navigation
        name: useMainContentOnly
        in: query
      - schema:
          type: object
          properties:
            shouldParse:
              anyOf:
              - type: boolean
              - type: string
                enum:
                - 'true'
                - 'false'
              default: true
              description: When true, PDF URLs are fetched and parsed. When false, PDF URLs are skipped and a 400 WEBSITE_ACCESS_ERROR is returned.
            start:
              type: integer
              minimum: 1
              description: First 1-based PDF page to parse. When omitted, parsing starts at the first page.
            end:
              type: integer
              minimum: 1
              description: Last 1-based PDF page to parse. When omitted, parsing ends at the last page. Must be greater than or equal to start when both are provided.
            ocr:
              anyOf:
              - type: boolean
              - type: string
                enum:
                - 'true'
                - 'false'
              default: false
              description: When true, detect and OCR images embedded in the selected PDF pages, inserting recognized text at each image's position in page reading order while preserving the PDF text layer. This is separate from automatic scanned-PDF OCR fallback.
          default:
            shouldParse: true
            ocr: false
          description: PDF parsing controls. Use start/end to limit text extraction and embedded-image detection/OCR to an inclusive 1-based page range.
        required: false
        description: PDF parsing controls. Use start/end to limit text extraction and embedded-image detection/OCR to an inclusive 1-based page range.
        name: pdf
        in: query
      - schema:
          anyOf:
          - type: boolean
          - type: string
            enum:
            - 'true'
            - 'false'
          default: false
          description: When true, the contents of iframes are rendered to Markdown.
        required: false
        description: When true, the contents of iframes are rendered to Markdown.
        name: includeFrames
        in: query
      - schema:
          type:
          - array
          - 'null'
          items:
            type: string
            minLength: 1
            maxLength: 2048
          maxItems: 50
          description: 'CSS selectors. When provided, only matching HTML subtrees (and their descendants) are kept before conversion to Markdown. When omitted, the entire document is kept. Examples: "article.main", "#content", "[role=main]".'
        required: false
        description: 'CSS selectors. When provided, only matching HTML subtrees (and their descendants) are kept before conversion to Markdown. When omitted, the entire document is kept. Examples: "article.main", "#content", "[role=main]".'
        name: includeSelectors
        in: query
      - schema:
          type:
          - array
          - 'null'
          items:
            type: string
            minLength: 1
            maxLength: 2048
          maxItems: 50
          description: 'CSS selectors to remove before conversion to Markdown. Applied after includeSelectors. Exclusion takes precedence: an element matching both is removed. Examples: "nav", "footer", ".ad-banner", "[aria-hidden=true]".'
        required: false
        description: 'CSS selectors to remove before conversion to Markdown. Applied after includeSelectors. Exclusion takes precedence: an element matching both is removed. Examples: "nav", "footer", ".ad-banner", "[aria-hidden=true]".'
        name: excludeSelectors
        in: query
      - schema:
          type:
          - integer
          - 'null'
          minimum: 0
          maximum: 2592000000
          default: 86400000
          description: Return a cached result if a prior scrape for the same parameters exists and is younger than this many milliseconds. Defaults to 1 day (86400000 ms) when omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
        required: false
        description: Return a cached result if a prior scrape for the same parameters exists and is younger than this many milliseconds. Defaults to 1 day (86400000 ms) when omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
        name: maxAgeMs
        in: query
      - schema:
          type:
          - integer
          - 'null'
          minimum: 0
          maximum: 30000
          description: 'Optional browser wait time in milliseconds after initial page load before converting the page to Markdown. Min: 0. Max: 30000 (30 seconds).'
        required: false
        description: 'Optional browser wait time in milliseconds after initial page load before converting the page to Markdown. Min: 0. Max: 30000 (30 seconds).'
        name: waitForMs
        in: query
      - schema:
          anyOf:
          - type: boolean
          - type: string
            enum:
            - 'true'
            - 'false'
          default: false
          description: When true, waits briefly for CSS and transition animations to settle before converting to Markdown. Defaults to false. This adds a bit of latency in exchange for more stable output on animated pages.
        required: false
        description: When true, waits briefly for CSS and transition animations to settle before converting to Markdown. Defaults to false. This adds a bit of latency in exchange for more stable output on animated pages.
        name: settleAnimations
        in: query
      - schema:
          type: object
          additionalProperties:
            type: string
            maxLength: 8192
            pattern: ^[^\r\n]*$
          description: 'Optional outbound HTTP headers forwarded only to the target URL, sent as deep-object query params such as headers[X-Custom]=value. When provided, caching is bypassed: the result is neither read from nor written to cache.'
        required: false
        description: 'Optional outbound HTTP headers forwarded only to the target URL, sent as deep-object query params such as headers[X-Custom]=value. When provided, caching is bypassed: the result is neither read from nor written to cache.'
        name: headers
        in: query
      - schema:
          $ref: '#/components/schemas/BrowserCountryCode'
        required: false
        description: Two-letter ISO 3166-1 alpha-2 country code identifying a supported Context.dev residential proxy exit location. Must be one of Context.dev's supported countries. When provided, Context.dev fetches the target page from that country.
        name: country
        in: query
      - schema:
          $ref: '#/components/schemas/LenientTimeoutMS'
        required: false
        description: Optional timeout in milliseconds for the request. If the request takes longer than this value, it will be aborted with a 408 status code. Maximum allowed value is 300000ms (5 minutes).
        name: timeoutMS
        in: query
      - $ref: '#/components/parameters/RequestTags'
      responses:
        '200':
          description: Successful response
          headers:
            X-RateLimit-Limit:
              $ref: '#/components/headers/RateLimitLimit'
            X-RateLimit-Remaining:
              $ref: '#/components/headers/RateLimitRemaining'
            X-RateLimit-Reset:
              $ref: '#/components/headers/RateLimitReset'
          content:
            application/json:
              schema:
                type: object
                properties:
                  success:
                    type: boolean
                    enum:
                    - true
                    description: Indicates success
                  markdown:
                    type: string
                    description: Page content converted to GitHub Flavored Markdown
                  contentLength:
                    type: integer
                    minimum: 0
                    description: UTF-8 byte length of the returned Markdown. Use 0 to identify an empty result and compare small values against your workload's minimum useful-content threshold.
                  url:
                    type: string
                    description: The URL that was scraped
                  metadata:
                    $ref: '#/components/schemas/PageMetadata'
                  key_metadata:
                    $ref: '#/components/schemas/KeyMetadata'
                required:
                - success
                - markdown
                - contentLength
                - url
                - metadata
        '400':
          description: Bad request - Invalid URL or failed to scrape
          headers:
            X-RateLimit-Limit:
              $ref: '#/components/headers/RateLimitLimit'
            X-RateLimit-Remaining:
              $ref: '#/components/headers/RateLimitRemaining'
            X-RateLimit-Reset:
              $ref: '#/components/headers/RateLimitReset'
          content:
            application/json:
              schema:
                type: object
                properties:
                  message:
                    type: string
                    description: Error message describing the issue
                  error_code:
                    type: string
                    enum:
                    - INPUT_VALIDATION_ERROR
                    - WEBSITE_ACCESS_ERROR
                    description: Error code indicating the type of error
                  key_me

# --- truncated at 32 KB (138 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/contextdev/refs/heads/main/openapi/contextdev-web-scraping-api-openapi.yml