{ "openapi": "3.0.1", "info": { "title": "Internet Archive Digital Library (archive.org) - Data Scraper", "description": "Extract record data from Internet Archive Digital Library (archive.org) via its official public JSON API. Search by search query, collection, format, media type and export 19 structured fields per record as JSON, CSV or Excel - reliable, with no fragile HTML scraping.", "version": "0.1", "x-build-id": "rhaXhqTPEqsY9idha" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gettingtechnicl~internet-archive/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gettingtechnicl-internet-archive", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/gettingtechnicl~internet-archive/runs": { "post": { "operationId": "runs-sync-gettingtechnicl-internet-archive", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/gettingtechnicl~internet-archive/run-sync": { "post": { "operationId": "run-sync-gettingtechnicl-internet-archive", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "search_q": { "title": "Search query", "type": "string", "description": "Search term used to filter results, for example a name, title, or keyword. The actor returns records matching this text. Leave blank to fetch a default sample." }, "collection": { "title": "Collection", "type": "string", "description": "Optional filter on 'collection' (for example 'podcasts_mirror_bobarchives'). Leave blank for no filter." }, "format": { "title": "Format", "type": "string", "description": "Optional filter on 'format' (for example 'Archive BitTorrent'). Leave blank for no filter." }, "mediatype": { "title": "Media type", "enum": [ "", "audio", "web", "texts", "data" ], "type": "string", "description": "Optional filter on 'mediatype' (for example 'audio'). Leave blank for no filter." }, "subject": { "title": "Subject", "type": "string", "description": "Optional filter on 'subject' (for example 'Podcast'). Leave blank for no filter." }, "year": { "title": "Year", "enum": [ "", "2022", "2008", "2013", "2009", "2006", "2020", "1977", "1732", "1993", "2019", "1966", "1972", "1956", "2021", "1973", "2002", "2023", "2010" ], "type": "string", "description": "Optional filter on 'year' (for example '2022'). Leave blank for no filter." }, "max_items": { "title": "Maximum results", "minimum": 1, "type": "integer", "description": "Maximum number of records to fetch and push to the dataset.", "default": 100 }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Optional Apify Proxy configuration. Leave unset to run without a proxy (default: no proxy, no extra traffic cost)." } } }, "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 } } } } } } } } } }