{ "openapi": "3.0.1", "info": { "title": "Internet Archive Scraper", "description": "Search and scrape Internet Archive — 40M+ free books, movies, music, software, images, and Wayback Machine web archives. Filter by media type, date, and keyword. Export data as JSON, CSV, Excel, or XML. Great for public domain content, research, and bulk metadata downloads.", "version": "0.0", "x-build-id": "lobqYay2kfpLNlc54" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/defensible_mat~internet-archive-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-defensible_mat-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/defensible_mat~internet-archive-scraper/runs": { "post": { "operationId": "runs-sync-defensible_mat-internet-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/defensible_mat~internet-archive-scraper/run-sync": { "post": { "operationId": "run-sync-defensible_mat-internet-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "searchTerm" ], "properties": { "searchTerm": { "title": "Search query", "type": "string", "description": "Keyword(s) to search for, e.g. \"jazz 1950s\" or \"machine learning\". Supports full Internet Archive query syntax (AND, OR, field:value, etc)." }, "mediaTypes": { "title": "Media types", "type": "array", "description": "Restrict results to one or more Internet Archive media types. Leave empty to search across all types.", "items": { "type": "string", "enum": [ "texts", "movies", "audio", "software", "image", "web", "data", "collection", "etree" ], "enumTitles": [ "Texts / Books", "Movies & Video", "Audio & Music", "Software", "Images", "Web (Wayback)", "Data", "Collections", "Live Music (etree)" ] }, "default": [ "web", "movies", "image", "texts" ] }, "dateFrom": { "title": "Date from (optional)", "type": "string", "description": "Only include items published on or after this date. Format: YYYY-MM-DD." }, "dateTo": { "title": "Date to (optional)", "type": "string", "description": "Only include items published on or before this date. Format: YYYY-MM-DD." }, "sortBy": { "title": "Sort results by", "enum": [ "relevance", "dateDesc", "dateAsc", "downloadsDesc", "titleAsc" ], "type": "string", "description": "How to order the results returned by the Archive.org search API.", "default": "dateDesc" }, "maxItems": { "title": "Max items", "minimum": 0, "type": "integer", "description": "Maximum number of items to fetch. Leave at 0 for a reasonable default of 200.", "default": 100 }, "fetchFullMetadata": { "title": "Fetch full metadata per item", "type": "boolean", "description": "If enabled, makes one extra API call per item to archive.org/metadata/{identifier} to pull full details (all files, full description, licensing info, etc). Slower for large runs.", "default": true }, "outputFields": { "title": "Fields to include (search results)", "type": "array", "description": "Which metadata fields to request from the search API for each item. Leave default unless you need something specific.", "items": { "type": "string", "enum": [ "identifier", "title", "description", "mediatype", "creator", "date", "year", "publicdate", "downloads", "item_size", "subject", "language", "licenseurl", "collection", "publisher" ] }, "default": [ "identifier", "title", "description", "mediatype", "creator", "date", "downloads", "subject", "language", "licenseurl" ] } } }, "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 } } } } } } } } } }