{ "openapi": "3.0.1", "info": { "title": "Internet Archive Scraper", "description": "Searches the Internet Archive (archive.org) by keyword and returns structured items (title, creator, year, downloads, subjects, item URL); filter by media type and sort by downloads or upload date.", "version": "0.1", "x-build-id": "dZbgRXvIaL0QllzYn" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dami_studio~internet-archive-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dami_studio-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dami_studio~internet-archive-scraper/runs": { "post": { "operationId": "runs-sync-dami_studio-internet-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dami_studio~internet-archive-scraper/run-sync": { "post": { "operationId": "run-sync-dami_studio-internet-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "query": { "title": "Search query", "type": "string", "description": "Keywords to search the Internet Archive for (e.g. \"nasa apollo\", \"jazz\"). Supports Lucene operators used by archive.org, e.g. \"title:(grateful dead) AND year:[1977 TO 1980]\". Required." }, "mediaType": { "title": "Media type", "enum": [ "", "texts", "audio", "movies", "software", "image", "web", "data", "collection" ], "type": "string", "description": "Restrict results to one media type, or leave empty for any. texts = books/documents, audio = music/recordings, movies = video/film, software, image, web (archived sites), data, collection.", "default": "" }, "sort": { "title": "Sort by", "enum": [ "downloads", "date", "publicdate", "relevance" ], "type": "string", "description": "Order of results. downloads = most-downloaded first, date = newest item date first, publicdate = most recently added to archive.org first, relevance = the archive's default relevance ranking.", "default": "downloads" }, "maxItems": { "title": "Max items", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of unique items to return. The actor paginates 100 per request until this many items are collected or the result set is exhausted.", "default": 100 }, "notionConnector": { "title": "Notion connector (optional)", "type": "string", "description": "Optional. Write each item as a page into your Notion when the run finishes. Authorize a Notion connector once in Settings → API & Integrations → MCP connectors, then pick it here. Leave empty to skip (default) — results are always saved to the dataset regardless." }, "notionParentId": { "title": "Notion target data source ID", "type": "string", "description": "Optional. The Notion data source ID of the database to write into (only used if a Notion connector is set). Leave empty to create the pages privately in your workspace instead." }, "proxyConfiguration": { "title": "Proxy (optional)", "type": "object", "description": "OPTIONAL. The archive.org advancedsearch API is a public, no-auth, no-anti-bot JSON endpoint, so no proxy is needed and the default routes traffic directly (saving proxy credits). Only enable Apify Proxy if you hit IP rate limits at very high volume.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }