Internet Archive Metadata & File Exporter
Pricing
$1.00 / 1,000 results
Go to Apify Store
Internet Archive Metadata & File Exporter
Search Archive.org and export structured item metadata, file manifests, hashes, download links, and public reviews.
Internet Archive Metadata & File Exporter
Pricing
$1.00 / 1,000 results
Search Archive.org and export structured item metadata, file manifests, hashes, download links, and public reviews.
You can access the Internet Archive Metadata & File Exporter programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
![Internet Archive Scraper — Wayback + Search + Metadata [$1.5💰] avatar](https://images.apifyusercontent.com/Tkb7JVd6vvGNN4CCZI23E7wLy3CwGe-DUvxaTNiyBaA/rs:fill:76:76/cb:1/aHR0cHM6Ly9hcGlmeS1pbWFnZS11cGxvYWRzLXByb2QuczMudXMtZWFzdC0xLmFtYXpvbmF3cy5jb20vbmduOHZSRVNUa3NleVdFNnAtYWN0b3ItOUo5UmNFdGhDcEtYM3hEeDMtNUVQN1dMeVZUai1pbnRlcm5ldF9hcmNodmllLnBuZw.webp){kind=avatar}
{ "openapi": "3.0.1", "info": { "version": "0.0", "x-build-id": "zFuaGceEg6dW54xEc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/archive-scout-labs~internet-archive-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-archive-scout-labs-internet-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/archive-scout-labs~internet-archive-scraper/runs": { "post": { "operationId": "runs-sync-archive-scout-labs-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/archive-scout-labs~internet-archive-scraper/run-sync": { "post": { "operationId": "run-sync-archive-scout-labs-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", "required": [ "operation" ], "properties": { "operation": { "title": "Operation", "enum": [ "search", "itemDetails" ], "type": "string", "description": "Search the catalog, or fetch exact item identifiers.", "default": "search" }, "query": { "title": "Search query", "type": "string", "description": "Internet Archive Advanced Search query. Plain keywords work; advanced field queries such as title:(climate change) are also accepted.", "default": "public domain science" }, "mediaType": { "title": "Media type", "enum": [ "", "texts", "movies", "audio", "software", "image", "data", "collection", "web" ], "type": "string", "description": "Optional Internet Archive media-type filter.", "default": "" }, "collection": { "title": "Collection identifier", "type": "string", "description": "Optional exact collection identifier, for example opensource_movies." }, "language": { "title": "Language", "type": "string", "description": "Optional exact language value used by Internet Archive metadata, for example eng or English." }, "sortBy": { "title": "Sort results", "enum": [ "relevance", "downloads", "newest", "oldest", "title" ], "type": "string", "description": "Ordering for catalog search results.", "default": "relevance" }, "maxItems": { "title": "Maximum results", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of dataset items to return.", "default": 100 }, "identifiers": { "title": "Item identifiers", "maxItems": 1000, "uniqueItems": true, "type": "array", "description": "Exact archive.org item identifiers. Used when Operation is Fetch item details.", "items": { "type": "string" } }, "includeFiles": { "title": "Include file metadata", "type": "boolean", "description": "Include downloadable file names, formats, sizes, hashes, and direct download URLs.", "default": false }, "includeDerivedFiles": { "title": "Include derived files", "type": "boolean", "description": "Include files generated by Internet Archive in addition to original uploads.", "default": false }, "maxFilesPerItem": { "title": "Maximum files per item", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum file records embedded in each dataset item.", "default": 100 }, "includeReviews": { "title": "Include public reviews", "type": "boolean", "description": "Include public reviews returned in the item's metadata record.", "default": false }, "requestDelayMs": { "title": "Delay between detail requests (ms)", "minimum": 250, "maximum": 10000, "type": "integer", "description": "Polite delay between metadata requests. Internet Archive asks automated clients to respect rate limits.", "default": 500 } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Internet Archive Metadata & File Exporter from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: