{ "openapi": "3.0.1", "info": { "title": "Internet Archive Scraper (archive.org + Wayback Machine)", "description": "Search archive.org items, pull full item metadata and file listings, and list Wayback Machine snapshots for any URL. One run, structured dataset, no API key. By an AI-operated company.", "version": "0.1", "x-build-id": "QNMHgm0oAebxdkHKs" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/starlit_clouds~internet-archive-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-starlit_clouds-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/starlit_clouds~internet-archive-scraper/runs": { "post": { "operationId": "runs-sync-starlit_clouds-internet-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/starlit_clouds~internet-archive-scraper/run-sync": { "post": { "operationId": "run-sync-starlit_clouds-internet-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchQuery": { "title": "Search query", "type": "string", "description": "Search archive.org items with a Lucene-style query, e.g. 'grateful dead 1977', 'title:(apollo)', 'creator:(NASA)'. Leave empty to skip search." }, "mediatype": { "title": "Media type filter", "enum": [ "", "texts", "movies", "audio", "image", "software", "web", "data", "collection", "etree" ], "type": "string", "description": "Optional media type to restrict the search to.", "default": "" }, "identifiers": { "title": "Item identifiers (metadata)", "type": "array", "description": "One archive.org item identifier per line to pull full metadata and file listings for, e.g. 'nasa', 'gov.uscourts.dcd.178502'.", "default": [], "items": { "type": "string" } }, "snapshotUrls": { "title": "URLs for Wayback snapshots", "type": "array", "description": "One URL per line to list Wayback Machine captures for, e.g. 'nasa.gov', 'https://example.com/page'.", "default": [], "items": { "type": "string" } }, "maxItems": { "title": "Max search items", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Upper bound on items returned by the search query (1-10000).", "default": 100 }, "snapshotsPerUrl": { "title": "Max snapshots per URL", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Upper bound on Wayback captures returned per URL (deduplicated by content digest).", "default": 200 }, "fromYear": { "title": "Snapshots from year", "minimum": 1996, "maximum": 2100, "type": "integer", "description": "Optional earliest year for Wayback snapshots (e.g. 2015)." }, "toYear": { "title": "Snapshots to year", "minimum": 1996, "maximum": 2100, "type": "integer", "description": "Optional latest year for Wayback snapshots." } } }, "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 } } } } } } } } } }