{ "openapi": "3.0.1", "info": { "title": "Internet Archive Scraper — Search archive.org, Download Links", "description": "Search the Internet Archive by text, collection, media type, creator, subject, language and year, and export one row per item with downloads, size, rating, licence and links — plus a row per file with a direct download URL. No API key.", "version": "0.1", "x-build-id": "Bt54tqCzOFTzlP3SL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/chorelet~internet-archive-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-chorelet-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/chorelet~internet-archive-scraper/runs": { "post": { "operationId": "runs-sync-chorelet-internet-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/chorelet~internet-archive-scraper/run-sync": { "post": { "operationId": "run-sync-chorelet-internet-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "queries": { "title": "Search terms", "type": "array", "description": "Plain words or Lucene syntax, one search per line: `apollo 11`, `title:(\"public domain\")`. Leave empty to search by the filters below alone.", "items": { "type": "string" } }, "collections": { "title": "Collections", "type": "array", "description": "archive.org collection ids: `librivoxaudio`, `prelinger`, `nasa`, `opensource_movies`, `gutenberg`.", "items": { "type": "string" } }, "mediaTypes": { "title": "Media types", "type": "array", "description": "`texts`, `audio`, `movies`, `image`, `software`, `data`, `web`, `etree`, `collection`.", "items": { "type": "string" } }, "creators": { "title": "Creators", "type": "array", "description": "Author, band, studio or agency as the item credits it.", "items": { "type": "string" } }, "subjects": { "title": "Subjects", "type": "array", "description": "Subject tags as archive.org stores them.", "items": { "type": "string" } }, "languages": { "title": "Languages", "type": "array", "description": "`English`, `French`, `Spanish`…", "items": { "type": "string" } }, "yearFrom": { "title": "Year from", "type": "string", "description": "Year of the work itself, not of the upload." }, "yearTo": { "title": "Year to", "type": "string", "description": "Leave either end empty for an open range." }, "sortBy": { "title": "Sort by", "enum": [ "most downloaded", "newest", "oldest", "top rated", "title", "date of work" ], "type": "string", "description": "What comes first.", "default": "most downloaded" }, "includeFiles": { "title": "Add a row per file, with download links", "type": "boolean", "description": "Opens each item's file list and returns a direct download URL, format, size and duration for every file. One extra request per item.", "default": false }, "maxFilesPerItem": { "title": "Max files per item", "minimum": 0, "maximum": 1000, "type": "integer", "description": "0 = every file. Items can hold hundreds of derivatives.", "default": 10 }, "fileFormats": { "title": "Only these file formats", "type": "array", "description": "Partial matches against the format: `pdf`, `mp3`, `epub`, `mp4`. Empty keeps all of them.", "items": { "type": "string" } }, "originalFilesOnly": { "title": "Skip derivatives", "type": "boolean", "description": "Drops thumbnails, torrents, checksums and other generated files.", "default": true }, "maxResultsPerQuery": { "title": "Max items per search", "minimum": 1, "maximum": 10000, "type": "integer", "description": "archive.org serves at most 10,000 results for one search; narrow by year or collection to go deeper.", "default": 200 } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }