{
  "openapi": "3.0.1",
  "info": {
    "title": "Internet Archive Scraper",
    "description": "Search archive.org via its public API and export flat rows.",
    "version": "0.2",
    "x-build-id": "frCAqgcyuUvJhcqMR"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/cordate_jebel~internet-archive-scraper/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-cordate_jebel-internet-archive-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": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/cordate_jebel~internet-archive-scraper/runs": {
      "post": {
        "operationId": "runs-sync-cordate_jebel-internet-archive-scraper",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/cordate_jebel~internet-archive-scraper/run-sync": {
      "post": {
        "operationId": "run-sync-cordate_jebel-internet-archive-scraper",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
          "mode": {
            "title": "Mode",
            "enum": [
              "search",
              "wayback"
            ],
            "type": "string",
            "description": "'search' = query the whole archive (books, film, audio, software, images). 'wayback' = list every archived snapshot of one URL from the Wayback Machine.",
            "default": "search"
          },
          "query": {
            "title": "Search query (mode = search)",
            "type": "string",
            "description": "archive.org advanced-search query, Lucene syntax. Examples: subject:\"machine learning\"  |  collection:nasa AND mediatype:image  |  creator:\"NASA\" AND date:[2000-01-01 TO 2010-12-31]"
          },
          "mediatype": {
            "title": "Media type filter (mode = search)",
            "enum": [
              "",
              "texts",
              "movies",
              "audio",
              "image",
              "software",
              "data",
              "web",
              "collection",
              "etree"
            ],
            "type": "string",
            "description": "Optional convenience filter ANDed into the query.",
            "default": ""
          },
          "sort": {
            "title": "Sort order (mode = search)",
            "enum": [
              "downloads desc",
              "week desc",
              "month desc",
              "date desc",
              "addeddate desc",
              "publicdate desc",
              "titleSorter asc",
              "avg_rating desc"
            ],
            "type": "string",
            "description": "How archive.org should order results before pagination.",
            "default": "downloads desc"
          },
          "startPage": {
            "title": "Start page (mode = search)",
            "minimum": 1,
            "type": "integer",
            "description": "First result page to fetch (100 items per page). Use to resume or skip ahead.",
            "default": 1
          },
          "fetchMetadata": {
            "title": "Fetch per-item metadata (mode = search)",
            "type": "boolean",
            "description": "For every result, also call /metadata/<id> to add description, subjects, license, file count and review count. Slower (one extra request per item).",
            "default": false
          },
          "waybackUrl": {
            "title": "URL (mode = wayback)",
            "type": "string",
            "description": "The URL whose archived snapshots you want, e.g. https://apify.com or example.com/pricing"
          },
          "waybackMatchType": {
            "title": "Match type (mode = wayback)",
            "enum": [
              "exact",
              "prefix",
              "host",
              "domain"
            ],
            "type": "string",
            "description": "exact = that URL only. prefix = URL and everything under its path. host = the whole hostname. domain = the domain and all sub-domains.",
            "default": "exact"
          },
          "waybackFrom": {
            "title": "From date (mode = wayback)",
            "type": "string",
            "description": "Earliest snapshot, as YYYY, YYYYMM or YYYYMMDD."
          },
          "waybackTo": {
            "title": "To date (mode = wayback)",
            "type": "string",
            "description": "Latest snapshot, as YYYY, YYYYMM or YYYYMMDD."
          },
          "waybackCollapse": {
            "title": "Collapse identical snapshots (mode = wayback)",
            "type": "boolean",
            "description": "Skip consecutive snapshots whose content digest is unchanged.",
            "default": true
          },
          "waybackOnlyOk": {
            "title": "Only HTTP 200 snapshots (mode = wayback)",
            "type": "boolean",
            "description": "Drop redirects, 404s and errors.",
            "default": true
          },
          "maxItems": {
            "title": "Max items",
            "minimum": 1,
            "maximum": 10000,
            "type": "integer",
            "description": "Stop after this many rows. archive.org caps search deep-pagination near 10000.",
            "default": 100
          }
        }
      },
      "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
                  }
                }
              },
              "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
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}