{
  "openapi": "3.0.1",
  "info": {
    "title": "AI Web Scraper: Any Page to Validated JSON, Plain English",
    "description": "AI web scraper: give URLs and say in plain English what to pull, and get one schema-validated JSON row per page. $0.004 per page, failed pages are free. LLM tokens are billed at cost through your own Apify account. No login.",
    "version": "0.0",
    "x-build-id": "rE1GofCHT1iLOeqyN"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/conserving_celerytop~ai-web-scraper/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-conserving_celerytop-ai-web-scraper",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/conserving_celerytop~ai-web-scraper/runs": {
      "post": {
        "operationId": "runs-sync-conserving_celerytop-ai-web-scraper",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/conserving_celerytop~ai-web-scraper/run-sync": {
      "post": {
        "operationId": "run-sync-conserving_celerytop-ai-web-scraper",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    }
  },
  "components": {
    "schemas": {
      "inputSchema": {
        "type": "object",
        "properties": {
          "startUrls": {
            "title": "Start URLs",
            "type": "array",
            "description": "Public pages to read. Each URL becomes one output row. No login pages.",
            "items": {
              "type": "object",
              "required": [
                "url"
              ],
              "properties": {
                "url": {
                  "type": "string",
                  "title": "URL of a web page",
                  "format": "uri"
                }
              }
            }
          },
          "listDatasetId": {
            "title": "Dataset with the list",
            "type": "string",
            "description": "Pick an Apify Dataset that holds your start URLs, one entry per item. They are added to the entries typed under Start URLs."
          },
          "listDatasetField": {
            "title": "Field in the dataset",
            "type": "string",
            "description": "Name of the dataset field that holds the entry. Leave empty to use the first text field it finds."
          },
          "listFileUrl": {
            "title": "List file URL",
            "type": "string",
            "description": "Web address of a .txt, .csv or .json file with your start URLs, one entry per line. A header row is skipped. Up to 10 MB."
          },
          "instructions": {
            "title": "Extraction request",
            "type": "string",
            "description": "Plain English: what should be pulled from each page."
          },
          "fields": {
            "title": "Fields",
            "type": "array",
            "description": "Optional list of fields to extract. Each entry: name, type (string, number, boolean, url, date, array) and an optional description. Every row is checked against the list; simple values are converted (\"$1,299\" becomes 1299). Rows that fail the check get status schema_invalid and are free. If set, 'Extraction request' is optional."
          },
          "jsonSchema": {
            "title": "JSON Schema (alternative to Fields)",
            "type": "object",
            "description": "Optional raw JSON Schema for the 'data' object. Use it instead of Fields, not together with it. Rows that fail the check get status schema_invalid and are free."
          },
          "outputSchema": {
            "title": "Output schema",
            "type": "object",
            "description": "Optional JSON Schema for the 'data' field. Rows that do not match it are retried once, then marked failed and not charged."
          },
          "maxPages": {
            "title": "Page limit",
            "minimum": 1,
            "maximum": 5000,
            "type": "integer",
            "description": "Maximum number of URLs processed in this run.",
            "default": 10
          },
          "model": {
            "title": "Model",
            "type": "string",
            "description": "OpenRouter model ID. Token cost is billed to your Apify account at OpenRouter's price.",
            "default": "google/gemini-2.5-flash-lite"
          },
          "useBrowserFallback": {
            "title": "Browser fallback",
            "type": "boolean",
            "description": "Open the page in headless Chromium when plain HTTP returns almost no text (JavaScript sites).",
            "default": true
          },
          "includePersonalData": {
            "title": "Personal data",
            "type": "boolean",
            "description": "Off by default: emails and phone numbers in results are replaced with [redacted]. Turn on only if you have a lawful basis.",
            "default": false
          },
          "openRouterApiKey": {
            "title": "OpenRouter API key",
            "type": "string",
            "description": "Optional. Leave empty to pay tokens through your Apify account. If set, tokens are billed to this key instead."
          }
        }
      },
      "runsResponseSchema": {
        "type": "object",
        "properties": {
          "data": {
            "type": "object",
            "properties": {
              "id": {
                "type": "string"
              },
              "actId": {
                "type": "string"
              },
              "userId": {
                "type": "string"
              },
              "startedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "finishedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "status": {
                "type": "string",
                "example": "READY"
              },
              "meta": {
                "type": "object",
                "properties": {
                  "origin": {
                    "type": "string",
                    "example": "API"
                  },
                  "userAgent": {
                    "type": "string"
                  }
                }
              },
              "stats": {
                "type": "object",
                "properties": {
                  "inputBodyLen": {
                    "type": "integer",
                    "example": 2000
                  },
                  "rebootCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "restartCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "resurrectCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "computeUnits": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "options": {
                "type": "object",
                "properties": {
                  "build": {
                    "type": "string",
                    "example": "latest"
                  },
                  "timeoutSecs": {
                    "type": "integer",
                    "example": 300
                  },
                  "memoryMbytes": {
                    "type": "integer",
                    "example": 1024
                  },
                  "diskMbytes": {
                    "type": "integer",
                    "example": 2048
                  }
                }
              },
              "buildId": {
                "type": "string"
              },
              "defaultKeyValueStoreId": {
                "type": "string"
              },
              "defaultDatasetId": {
                "type": "string"
              },
              "defaultRequestQueueId": {
                "type": "string"
              },
              "buildNumber": {
                "type": "string",
                "example": "1.0.0"
              },
              "containerUrl": {
                "type": "string"
              },
              "usage": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "integer",
                    "example": 1
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "usageTotalUsd": {
                "type": "number",
                "example": 0.00005
              },
              "usageUsd": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "number",
                    "example": 0.00005
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}