Scrape a web page

{
  "operationId": "scrape",
  "method": "post",
  "path": "/scrape",
  "summary": "Scrape a web page",
  "description": "Fetches a single URL and returns its content in the requested formats. By default returns clean main-content markdown. Use the `json` format with a `schema` to extract structured data, or request `html`, `links`, `summary`, or a `screenshot`. Handles JavaScript-rendered pages.",
  "parameters": [],
  "requestBody": {
    "required": true,
    "content": {
      "application/json": {
        "schema": {
          "type": "object",
          "required": [
            "url"
          ],
          "properties": {
            "url": {
              "type": "string",
              "format": "uri",
              "description": "The URL to scrape (must be a publicly reachable http(s) URL)."
            },
            "formats": {
              "type": "array",
              "description": "Output formats to return. Each entry is either a string preset or an object form. String presets: 'markdown' (default), 'summary', 'html', 'rawHtml', 'links', 'images'. Object forms include { type: 'json', schema, prompt } for structured extraction, { type: 'screenshot', fullPage, quality } for an image, and { type: 'changeTracking', modes } for diffs. Defaults to ['markdown'] when omitted.",
              "items": {
                "oneOf": [
                  {
                    "type": "string",
                    "enum": [
                      "markdown",
                      "summary",
                      "html",
                      "rawHtml",
                      "links",
                      "images"
                    ]
                  },
                  {
                    "type": "object",
                    "required": [
                      "type"
                    ],
                    "properties": {
                      "type": {
                        "type": "string",
                        "enum": [
                          "json",
                          "screenshot",
                          "changeTracking"
                        ]
                      },
                      "schema": {
                        "type": "object",
                        "description": "JSON schema describing the structured data to extract (for type 'json')."
                      },
                      "prompt": {
                        "type": "string",
                        "description": "Natural-language extraction prompt (for type 'json')."
                      },
                      "fullPage": {
                        "type": "boolean",
                        "description": "Capture the full scrollable page (for type 'screenshot')."
                      },
                      "modes": {
                        "type": "array",
                        "items": {
                          "type": "string",
                          "enum": [
                            "git-diff",
                            "json"
                          ]
                        },
                        "description": "Change-tracking modes (for type 'changeTracking')."
                      }
                    }
                  }
                ]
              }
            },
            "onlyMainContent": {
              "type": "boolean",
              "description": "Return only the main content of the page, excluding navs, headers, and footers.",
              "default": true
            },
            "includeTags": {
              "type": "array",
              "items": {
                "type": "string"
              },
              "description": "Only include content within these HTML tags / CSS selectors."
            },
            "excludeTags": {
              "type": "array",
              "items": {
                "type": "string"
              },
              "description": "Exclude content within these HTML tags / CSS selectors."
            },
            "maxAge": {
              "type": "integer",
              "description": "Return cached content up to this age in milliseconds (faster, cheaper). Default 172800000 (2 days).",
              "minimum": 0
            },
            "waitFor": {
              "type": "integer",
              "description": "Milliseconds to wait for the page to render before scraping.",
              "minimum": 0,
              "default": 0
            },
            "mobile": {
              "type": "boolean",
              "description": "Emulate a mobile device.",
              "default": false
            },
            "timeout": {
              "type": "integer",
              "description": "Request timeout in milliseconds (1000-300000). Default 60000.",
              "minimum": 1000,
              "maximum": 300000
            },
            "parsers": {
              "type": "array",
              "items": {},
              "description": "PDF parsing configuration."
            },
            "proxy": {
              "type": "string",
              "enum": [
                "basic",
                "enhanced",
                "auto"
              ],
              "description": "Proxy / anti-bot mode. 'auto' (default) escalates only on failure; 'enhanced' forces advanced anti-bot handling and costs more.",
              "default": "auto"
            },
            "location": {
              "type": "object",
              "description": "Geographic proxy location and language settings.",
              "properties": {
                "country": {
                  "type": "string",
                  "description": "ISO 3166-1 alpha-2 country code."
                },
                "languages": {
                  "type": "array",
                  "items": {
                    "type": "string"
                  }
                }
              }
            }
          }
        },
        "example": {
          "url": "https://example.com",
          "formats": [
            "markdown"
          ]
        }
      }
    }
  },
  "responses": [
    {
      "statusCode": "200",
      "description": "The scraped page content in the requested formats.",
      "content": {
        "application/json": {
          "schema": {
            "type": "object"
          }
        }
      }
    },
    {
      "statusCode": "400",
      "description": "Bad request — missing `url` or invalid parameter."
    },
    {
      "statusCode": "401",
      "description": "Unauthorized."
    },
    {
      "statusCode": "402",
      "description": "Insufficient balance."
    },
    {
      "statusCode": "429",
      "description": "Too many requests."
    },
    {
      "statusCode": "5XX",
      "description": "Upstream error."
    }
  ]
}