{ "openapi": "3.0.1", "info": { "title": "Internet Archive Scraper & API - archive.org Books & Media", "description": "Use this to search archive.org (Internet Archive): books, video, audio, software. Input: queries or item IDs, optional media type, collection, year filters. One result = one item: title, creator, year, media type, collections, license, downloads, URL, optional file links. $1.00 per 1,000 results.", "version": "1.0", "x-build-id": "dCbSf4f1jSVTDfcCr" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/rel8ble~internet-archive-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-rel8ble-internet-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/rel8ble~internet-archive-scraper/runs": { "post": { "operationId": "runs-sync-rel8ble-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/rel8ble~internet-archive-scraper/run-sync": { "post": { "operationId": "run-sync-rel8ble-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 queries", "type": "array", "description": "Optional. List of archive.org searches. Plain words must all match (\"apollo 11\" = apollo AND 11). Advanced syntax works: title:(moby dick), creator:\"Mark Twain\", subject:jazz, collection:gutenberg. Omit and set collection or mediaTypes to list a whole collection. Give queries, collection or identifiers.", "items": { "type": "string" } }, "searchIn": { "title": "Search in", "enum": [ "metadata", "title", "everything" ], "type": "string", "description": "Optional. Where plain words must match: \"metadata\" (default: title, subjects, creator; precise), \"title\" (title only) or \"everything\" (full text incl. descriptions and OCR; broad and noisy). field:value queries are used as written.", "default": "metadata" }, "mediaTypes": { "title": "Media types", "type": "array", "description": "Optional. Only these item types, list of: \"texts\", \"movies\", \"audio\", \"software\", \"image\", \"data\", \"web\", \"collection\", \"etree\" (live concerts). Omit for all types.", "items": { "type": "string", "enum": [ "texts", "movies", "audio", "software", "image", "data", "web", "collection", "etree" ], "enumTitles": [ "Texts (books, papers, magazines)", "Movies & video", "Audio & music", "Software", "Images", "Data sets", "Web crawls", "Collections", "Live music concerts (etree)" ] } }, "sortBy": { "title": "Sort by", "enum": [ "relevance", "downloads", "downloadsThisWeek", "newestUploads", "oldestUploads", "dateNewest", "dateOldest", "titleAZ", "rating" ], "type": "string", "description": "Optional. Result order: \"relevance\" (default), \"downloads\" (all time), \"downloadsThisWeek\", \"newestUploads\", \"oldestUploads\", \"dateNewest\", \"dateOldest\" (publication date), \"titleAZ\" or \"rating\".", "default": "relevance" }, "maxResults": { "title": "Max results per query", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Optional. Maximum items per query, integer 0-10000. Default 100; 0 = up to 10,000 (the API limit). You pay per item, so use 10-20 for a quick answer.", "default": 100 }, "collection": { "title": "Collection", "type": "string", "description": "Optional. Only items from this archive.org collection ID (from the collection URL), e.g. \"gutenberg\", \"prelinger\", \"nasa\". Several: comma-separated." }, "yearFrom": { "title": "Year from", "minimum": 0, "maximum": 2100, "type": "integer", "description": "Optional. Only items published in or after this year, integer 0-2100, e.g. 1950." }, "yearTo": { "title": "Year to", "minimum": 0, "maximum": 2100, "type": "integer", "description": "Optional. Only items published in or before this year, integer 0-2100, e.g. 1999." }, "language": { "title": "Language", "type": "string", "description": "Optional. Only items in this language as archive.org stores it: usually a 3-letter code (\"eng\", \"fre\", \"ger\", \"spa\") or a name (\"English\"). Several: comma-separated." }, "includeFiles": { "title": "Include file list and download links (slower)", "type": "boolean", "description": "Optional boolean. true = add every file in each item (PDF, EPUB, MP3, MP4...) with format, size, MD5 and direct download URL, plus the full description; one extra request per item. Default false.", "default": false }, "fileFormats": { "title": "Only these file formats", "type": "array", "description": "Optional, used with includeFiles. Keep only files whose format or extension matches, e.g. [\"pdf\", \"epub\", \"mp3\", \"h.264\"]. Omit for all files.", "items": { "type": "string" } }, "identifiers": { "title": "Item identifiers or URLs", "type": "array", "description": "Optional. Look up specific items instead of searching: list of archive.org identifiers (\"Apollo11Audio\") or item URLs (\"https://archive.org/details/Apollo11Audio\"). Always includes the file list.", "items": { "type": "string" } }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Optional, advanced. Number of parallel requests, integer 1-20. Default 10. Leave unset unless the run is very large.", "default": 10 }, "maxRequestRetries": { "title": "Max retries per request", "minimum": 0, "maximum": 20, "type": "integer", "description": "Optional, advanced. Retries per failed or blocked request, integer 0-20; each retry uses a new proxy session. Default 5. Leave unset.", "default": 5 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional, advanced. Apify Proxy settings object. Default {\"useApifyProxy\": false}: no proxy is needed for this public API. Leave unset.", "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 }, "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 } } } } } } } } } }