{ "openapi": "3.0.1", "info": { "title": "Internet Archive Scraper - Books, Media & Wayback Snapshots", "description": "Search archive.org for books, movies, audio, software, and images, read full item metadata and file lists, and list Wayback Machine snapshots for any URL.", "version": "1.0", "x-build-id": "tZpRuHgdk2SW3z2lg" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/thirdwatch~internet-archive-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-thirdwatch-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/thirdwatch~internet-archive-scraper/runs": { "post": { "operationId": "runs-sync-thirdwatch-internet-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/thirdwatch~internet-archive-scraper/run-sync": { "post": { "operationId": "run-sync-thirdwatch-internet-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "mode" ], "properties": { "mode": { "title": "What to collect", "enum": [ "search", "item", "wayback" ], "type": "string", "description": "Search the archive, read metadata for known items, or list Wayback Machine snapshots for a URL.", "default": "search" }, "query": { "title": "Search query", "type": "string", "description": "Free text or an archive.org query such as creator:\"NASA\" AND subject:\"mars\". Used in search mode.", "default": "" }, "mediaTypes": { "title": "Media types", "type": "array", "description": "Restrict search results to these media types. Leave empty for everything.", "items": { "type": "string", "enum": [ "texts", "movies", "audio", "software", "image", "etree", "data", "web", "collection" ], "enumTitles": [ "Books and texts", "Movies and video", "Audio and music", "Software", "Images", "Live music archive", "Data", "Web archives", "Collections" ] }, "default": [] }, "collection": { "title": "Collection", "type": "string", "description": "Restrict search results to one archive.org collection, such as nasa or librivoxaudio.", "default": "" }, "creator": { "title": "Creator", "type": "string", "description": "Restrict search results to one creator, author, or uploader.", "default": "" }, "subject": { "title": "Subject", "type": "string", "description": "Restrict search results to one subject tag.", "default": "" }, "language": { "title": "Language", "type": "string", "description": "Restrict search results to one language, such as English or spa.", "default": "" }, "yearFrom": { "title": "Year from", "minimum": 1, "maximum": 2100, "type": "integer", "description": "Earliest publication year to include in search results." }, "yearTo": { "title": "Year to", "minimum": 1, "maximum": 2100, "type": "integer", "description": "Latest publication year to include in search results." }, "sort": { "title": "Sort search results by", "enum": [ "", "downloads desc", "downloads asc", "publicdate desc", "publicdate asc", "addeddate desc", "date desc", "item_size desc", "identifier asc" ], "type": "string", "description": "Order of returned search results.", "default": "" }, "identifiers": { "title": "Item identifiers", "type": "array", "description": "archive.org identifiers to read metadata and file lists for. Used in item mode.", "items": { "type": "string", "minLength": 1, "maxLength": 200, "pattern": "^[^/\\s]+$" }, "default": [] }, "maxFilesPerItem": { "title": "Maximum files per item", "minimum": 0, "maximum": 500, "type": "integer", "description": "How many files to list inside each item record in item mode.", "default": 50 }, "urls": { "title": "URLs for the Wayback Machine", "type": "array", "description": "URLs or domains to list archived snapshots for. Used in wayback mode.", "items": { "type": "string", "minLength": 3, "maxLength": 2000 }, "default": [] }, "waybackMatchType": { "title": "Wayback URL match", "enum": [ "exact", "prefix", "host", "domain" ], "type": "string", "description": "How broadly to match the URL when listing snapshots.", "default": "exact" }, "waybackCollapse": { "title": "Collapse duplicate snapshots", "enum": [ "", "timestamp:4", "timestamp:6", "timestamp:8", "digest" ], "type": "string", "description": "Keep one snapshot per period or per unique content instead of every capture.", "default": "timestamp:6" }, "waybackFrom": { "title": "Wayback from", "pattern": "^$|^[0-9]{4}([0-9]{2})?([0-9]{2})?$", "type": "string", "description": "Earliest capture date as YYYY, YYYYMM, or YYYYMMDD.", "default": "" }, "waybackTo": { "title": "Wayback to", "pattern": "^$|^[0-9]{4}([0-9]{2})?([0-9]{2})?$", "type": "string", "description": "Latest capture date as YYYY, YYYYMM, or YYYYMMDD.", "default": "" }, "waybackStatusCode": { "title": "Only this HTTP status", "pattern": "^$|^[1-5][0-9]{2}$", "type": "string", "description": "Keep only snapshots captured with this status code, such as 200.", "default": "" }, "maxResults": { "title": "Maximum results", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Upper bound on saved records. archive.org caps search paging at 10,000 results per query.", "default": 10 } } }, "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 } } } } } } } } } }