{ "openapi": "3.0.1", "info": { "title": "Wayback Machine CDX Scraper", "description": "Query the Internet Archive Wayback Machine CDX Server API at scale: every URL a domain ever had captured, filtered by status code, MIME type, and date range, with correct resumeKey pagination and a stable validated schema. Keyless, no API key required.", "version": "0.0", "x-build-id": "JhpXcMBJMwNSYCSBr" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/devilscrapes~wayback-machine-cdx-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-devilscrapes-wayback-machine-cdx-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/devilscrapes~wayback-machine-cdx-scraper/runs": { "post": { "operationId": "runs-sync-devilscrapes-wayback-machine-cdx-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/devilscrapes~wayback-machine-cdx-scraper/run-sync": { "post": { "operationId": "run-sync-devilscrapes-wayback-machine-cdx-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "url" ], "properties": { "url": { "title": "URL, host, or domain", "minLength": 1, "maxLength": 500, "type": "string", "description": "Target URL, host, or domain to look up in the Wayback Machine CDX index, e.g. \"stripe.com\" or \"https://stripe.com/pricing\"." }, "matchType": { "title": "Match type", "enum": [ "exact", "prefix", "host", "domain" ], "type": "string", "description": "How the URL is matched: an exact URL, a URL prefix, an exact host, or the whole domain (every subdomain and path — the \"recover my whole site's history\" default).", "default": "domain" }, "dateFrom": { "title": "Date from", "pattern": "^\\d{4,14}$", "type": "string", "description": "Start of the capture date range, digits only (YYYY through YYYYMMDDhhmmss, partial allowed). Leave blank for no lower bound." }, "dateTo": { "title": "Date to", "pattern": "^\\d{4,14}$", "type": "string", "description": "End of the capture date range, digits only (YYYY through YYYYMMDDhhmmss, partial allowed). Leave blank for no upper bound." }, "filters": { "title": "Filters", "type": "array", "description": "Repeatable CDX filter expressions, e.g. \"statuscode:200\", \"!statuscode:404\", \"mimetype:text/html\".", "items": { "type": "string", "pattern": "^!?[a-z]+:.+$" }, "default": [] }, "collapse": { "title": "Collapse", "pattern": "^[a-z]+(:\\d+)?$", "type": "string", "description": "CDX collapse expression to de-duplicate adjacent rows sharing a field, e.g. \"urlkey\" or \"timestamp:8\". Leave blank to disable." }, "pageSize": { "title": "Page size", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Rows requested per CDX page (the API's \"limit\" parameter).", "default": 1000 }, "maxResults": { "title": "Max results", "minimum": 1, "maximum": 200000, "type": "integer", "description": "Hard cap on total rows fetched across all pages — protects spend and compute.", "default": 10000 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "web.archive.org is keyless and not known to fingerprint clients at reasonable volumes — proxy is off by default. Switch it on if you hit IP-range throttling on very large pulls.", "default": { "useApifyProxy": 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 } } } } } } } } } }