{ "openapi": "3.0.1", "info": { "title": "Wayback Machine URL Archive Scraper", "description": "Search and retrieve archived snapshots of any URL from Internet Archive's Wayback Machine. Supports date range filtering, deduplication, status code filtering, and optional HTML content fetching via CDX API. Ideal for web archive research, deleted content recovery, and SEO history analysis.", "version": "0.2", "x-build-id": "c5vFQYXF3UEke4Pxd" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gochujang~wayback-machine-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gochujang-wayback-machine-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/gochujang~wayback-machine-scraper/runs": { "post": { "operationId": "runs-sync-gochujang-wayback-machine-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/gochujang~wayback-machine-scraper/run-sync": { "post": { "operationId": "run-sync-gochujang-wayback-machine-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "URLs to archive search", "type": "array", "description": "List of URLs to search in the Wayback Machine CDX API.", "items": { "type": "string" }, "default": [ "https://example.com" ] }, "dateFrom": { "title": "Date From", "pattern": "^[0-9]{8}$", "type": "string", "description": "Start date for snapshot search in YYYYMMDD format (e.g. 20200101). Leave empty for no lower bound." }, "dateTo": { "title": "Date To", "pattern": "^[0-9]{8}$", "type": "string", "description": "End date for snapshot search in YYYYMMDD format (e.g. 20241231). Leave empty for no upper bound." }, "limit": { "title": "Max Snapshots Per URL", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of snapshots to return per URL.", "default": 100 }, "collapseBy": { "title": "Collapse / Deduplicate By", "enum": [ "", "digest", "timestamp:8", "timestamp:6" ], "type": "string", "description": "Deduplicate results by this field. 'digest' returns one snapshot per unique content hash; 'timestamp:8' collapses by day; 'timestamp:6' by month; empty string returns all.", "default": "digest" }, "statusFilter": { "title": "HTTP Status Code Filter", "type": "string", "description": "Filter by HTTP status code(s). Use '200' for OK only, '200,301' for multiple, or leave empty for all status codes.", "default": "200" }, "includeLatestOnly": { "title": "Latest Snapshot Only", "type": "boolean", "description": "If true, return only the most recent snapshot for each URL.", "default": false }, "fetchContent": { "title": "Fetch HTML Content", "type": "boolean", "description": "If true, fetch the full HTML content of each archived snapshot. Increases runtime and cost.", "default": 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 } } }, "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 } } } } } } } } } }