{ "openapi": "3.0.1", "info": { "title": "Wayback Machine Scraper API - Archived URLs & Website History", "description": "Search the Internet Archive Wayback Machine CDX index for archived URLs and website history. Filter captures by exact URL, prefix, host/domain, date, HTTP status, MIME type, and duplicate rule. Get timestamps, replay URLs, content hashes, status codes, sizes, and source evidence.", "version": "0.1", "x-build-id": "WmwGR3jCcIRzkdpd2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pink_comic~wayback-machine-archived-urls-website-history/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pink_comic-wayback-machine-archived-urls-website-history", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/pink_comic~wayback-machine-archived-urls-website-history/runs": { "post": { "operationId": "runs-sync-pink_comic-wayback-machine-archived-urls-website-history", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/pink_comic~wayback-machine-archived-urls-website-history/run-sync": { "post": { "operationId": "run-sync-pink_comic-wayback-machine-archived-urls-website-history", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "url": { "title": "URL or Domain", "minLength": 1, "maxLength": 2048, "type": "string", "description": "One URL or domain to search, such as example.org/, https://example.org/page, or example.org/blog. Ignored when URLs contains one or more targets.", "default": "example.org/" }, "urls": { "title": "URLs or Domains (Batch)", "maxItems": 20, "type": "array", "description": "Optional batch of up to 20 URL/domain targets. If supplied, this list takes precedence over URL. The total maxResults budget is split evenly across targets.", "items": { "type": "string" } }, "matchType": { "title": "URL Match Type", "enum": [ "exact", "prefix", "host", "domain" ], "type": "string", "description": "Exact searches one URL; prefix includes subpaths; host searches the same host; domain includes subdomains. Broad host/domain queries can be slower and hit the result bound.", "default": "exact" }, "fromDate": { "title": "Captured On or After", "pattern": "^$|^[0-9]{4}([0-9]{2}([0-9]{2}([0-9]{2}([0-9]{2}([0-9]{2})?)?)?)?)?$", "type": "string", "description": "Optional 4-14 digit timestamp prefix: YYYY, YYYYMM, YYYYMMDD, or full YYYYMMDDhhmmss." }, "toDate": { "title": "Captured On or Before", "pattern": "^$|^[0-9]{4}([0-9]{2}([0-9]{2}([0-9]{2}([0-9]{2}([0-9]{2})?)?)?)?)?$", "type": "string", "description": "Optional 4-14 digit ending timestamp prefix: YYYY, YYYYMM, YYYYMMDD, or full YYYYMMDDhhmmss." }, "statusCode": { "title": "Archived HTTP Status", "enum": [ "ALL", "200", "301", "302", "304", "400", "401", "403", "404", "410", "429", "500", "502", "503" ], "type": "string", "description": "Filter by the HTTP status recorded at capture time, or choose All. This is not the website's current status.", "default": "200" }, "mimeType": { "title": "Archived MIME Type", "pattern": "^$|^[A-Za-z0-9][A-Za-z0-9.+_-]*/[A-Za-z0-9][A-Za-z0-9.+_-]*$", "type": "string", "description": "Optional exact MIME filter such as text/html, application/pdf, image/jpeg, or application/json." }, "collapseBy": { "title": "Collapse Duplicate Captures", "enum": [ "NONE", "DIGEST", "URL", "MONTH", "DAY", "HOUR" ], "type": "string", "description": "Return every capture, unique content digests, one capture per archived URL, or one capture per month/day/hour bucket.", "default": "DIGEST" }, "sortDirection": { "title": "Capture Order", "enum": [ "latest", "earliest" ], "type": "string", "description": "Return the newest or oldest matching captures first. Latest uses the CDX negative-limit optimization for faster bounded queries.", "default": "latest" }, "maxResults": { "title": "Maximum Capture Records", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Total capture rows across all targets. For batch input, this budget is split evenly across targets so output remains bounded.", "default": 5 } } }, "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 } } } } } } } } } }