{ "openapi": "3.0.1", "info": { "title": "Internet Archive Metadata Scraper — Bulk archive.org Export", "description": "Bulk-export item metadata from the Internet Archive (archive.org) by full-text query, collection, media type, creator, subject and date range. Extract identifier, title, creator, date, downloads, format, subject and more. Millions of items. No API key, no login.", "version": "1.0", "x-build-id": "DpIrPTmNsOBAspBOE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/logiover~internet-archive-metadata-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-logiover-internet-archive-metadata-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/logiover~internet-archive-metadata-scraper/runs": { "post": { "operationId": "runs-sync-logiover-internet-archive-metadata-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/logiover~internet-archive-metadata-scraper/run-sync": { "post": { "operationId": "run-sync-logiover-internet-archive-metadata-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Query (raw Lucene / full-text)", "type": "string", "description": "Raw archive.org Lucene query. If set, it is used directly and the structured filters below are ignored. Examples: `collection:nasa`, `grateful dead AND mediatype:audio`, `subject:\"machine learning\" AND date:[2015-01-01 TO 2020-12-31]`. Leave empty to build the query from the filters below.", "default": "" }, "collection": { "title": "Collection", "type": "string", "description": "Collection identifier to scrape (adds `collection:`). Popular collections: `nasa`, `librivoxaudio`, `prelinger` (films), `opensource_movies`, `gutenberg`, `internetarcade`, `etree` (live concerts), `metropolitanmuseumofart-gallery`. Browse collections at archive.org/details.", "default": "" }, "mediaType": { "title": "Media Type", "enum": [ "any", "texts", "audio", "movies", "image", "software", "web", "data", "collection" ], "type": "string", "description": "Restrict to one Internet Archive media type (adds `mediatype:`). `(any)` applies no media-type filter.", "default": "any" }, "creator": { "title": "Creator / Author", "type": "string", "description": "Filter by creator or author (adds `creator:`). Example: `NASA`, `Mark Twain`, `Grateful Dead`. Combined with the other filters using AND.", "default": "" }, "subject": { "title": "Subject / Topic", "type": "string", "description": "Filter by subject or topic tag (adds `subject:`). Example: `astronomy`, `jazz`, `world war ii`. Combined with the other filters using AND.", "default": "" }, "dateFrom": { "title": "Date From (YYYY-MM-DD)", "type": "string", "description": "Start of the item `date` range (inclusive). Applied as a Lucene range `date:[from TO to]`. Requires Date To as well. Example: `2010-01-01`.", "default": "" }, "dateTo": { "title": "Date To (YYYY-MM-DD)", "type": "string", "description": "End of the item `date` range (inclusive). Applied together with Date From as `date:[from TO to]`. Example: `2020-12-31`.", "default": "" }, "fields": { "title": "Metadata Fields", "type": "array", "description": "Which metadata fields to request per item. `identifier` is always included. Fewer fields = faster + lighter output.", "default": [ "identifier", "title", "creator", "date", "publicdate", "mediatype", "collection", "downloads", "item_size", "format", "language", "subject", "year", "description" ], "items": { "type": "string" } }, "sort": { "title": "Sort", "type": "string", "description": "Optional sort, e.g. `downloads desc`, `publicdate desc`, `date asc`, `week desc`. When set, the Actor uses the Advanced Search API (capped at ~10,000 results). When empty, it uses the Scrape API for unlimited bulk export (no sorting).", "default": "" }, "fetchFiles": { "title": "Fetch per-item file list (heavy)", "type": "boolean", "description": "Also fetch each item's full file list from the /metadata/ endpoint (adds fileCount + top file names + server). This makes ONE extra request per item and is much slower — leave OFF for fast bulk metadata export.", "default": false }, "maxItems": { "title": "Max Items", "minimum": 0, "type": "integer", "description": "Maximum number of items to export. The Scrape API can return millions of items across cursor pagination, so raise this for large bulk jobs. Set 0 for no cap (careful — some collections hold hundreds of thousands of items).", "default": 1000 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Proxy configuration. archive.org's public APIs are keyless and work over Apify's datacenter proxy; a fresh proxy IP is used on retries. Residential is not required.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }