{ "openapi": "3.0.1", "info": { "title": "Wayback Machine Scraper: Snapshots, History & Old URLs", "description": "Get the Wayback Machine history of any URL or domain from archive.org's official CDX API: first and last capture, last working copy, status changes, content versions, every snapshot, and all historical URLs of a domain (for SEO recovery and due diligence).", "version": "0.1", "x-build-id": "qcGtZl2pUM3u9axxc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/latamdatatools~wayback-machine-history/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-latamdatatools-wayback-machine-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/latamdatatools~wayback-machine-history/runs": { "post": { "operationId": "runs-sync-latamdatatools-wayback-machine-history", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/latamdatatools~wayback-machine-history/run-sync": { "post": { "operationId": "run-sync-latamdatatools-wayback-machine-history", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "What to get", "enum": [ "summary", "snapshots", "domainUrls" ], "type": "string", "description": "History summary: one row per URL with first and last capture, last working capture, status changes, number of versions and captures per year. Snapshots: every capture of each URL. Historical URLs of a domain: every URL the Wayback Machine ever saw on the domain.", "default": "summary" }, "urls": { "title": "URLs or domains", "type": "array", "description": "One per line: a page URL (example.com/pricing) or a domain (example.com). http/https does not matter: the Wayback index ignores it.", "items": { "type": "string" } }, "datasetId": { "title": "Dataset (from another Actor run)", "type": "string", "description": "Optional: read the URLs from an Apify dataset (field set in \"URL field\")." }, "csvUrl": { "title": "CSV file URL", "type": "string", "description": "Optional: public CSV with a header row (or one URL per line). Google Sheets links work if shared as \"Anyone with the link\"." }, "urlField": { "title": "URL field", "type": "string", "description": "Field / column with the URL or domain.", "default": "url" }, "from": { "title": "From date", "type": "string", "description": "Optional: YYYY, YYYY-MM or YYYY-MM-DD." }, "to": { "title": "To date", "type": "string", "description": "Optional: YYYY, YYYY-MM or YYYY-MM-DD." }, "statusCodes": { "title": "HTTP status filter", "type": "array", "description": "Optional: keep only captures with these statuses, e.g. 200, 3xx. Prefix with ! to exclude: !404.", "items": { "type": "string" } }, "mimeTypes": { "title": "MIME type filter", "type": "array", "description": "Optional: e.g. text/html (only pages), application/pdf. * works as a wildcard: image/*.", "items": { "type": "string" } }, "collapse": { "title": "Snapshots: collapse", "enum": [ "none", "contentChange", "day", "month", "year" ], "type": "string", "description": "Snapshots mode only. Content changes = skip consecutive captures with identical content (the most useful to see when a page changed).", "default": "none" }, "domainMatch": { "title": "Historical URLs: scope", "enum": [ "domain", "host", "prefix" ], "type": "string", "description": "Historical URLs mode only. Domain = the domain and all subdomains; Host = only that exact host; Prefix = only URLs that start with the given URL (e.g. example.com/blog/).", "default": "domain" }, "skipUrlsWithParameters": { "title": "Historical URLs: skip URLs with ?parameters", "type": "boolean", "description": "Historical URLs mode only. On: leave out URLs with a query string (tracking parameters, session IDs, search pages), which are usually noise. Turn off to keep them (e.g. old ?p=123 links).", "default": true }, "maxResultsPerUrl": { "title": "Max results per URL / domain", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Snapshots or historical URLs returned per input (not used in summary mode).", "default": 1000 }, "maxUrls": { "title": "Max URLs / domains per run", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Inputs beyond this number are ignored.", "default": 1000 }, "onlyNewSinceLastRun": { "title": "Only new since the last run", "type": "boolean", "description": "Snapshots and historical URLs modes: remember what was already returned (named key-value store \"wayback-history-state\") and only return new captures / newly seen URLs. Good for scheduled runs.", "default": false }, "delayBetweenRequestsMs": { "title": "Delay between requests to archive.org (ms)", "minimum": 2000, "maximum": 30000, "type": "integer", "description": "archive.org is a non-profit with rate limits. Requests are sent one at a time with this delay; on HTTP 429 the Actor waits and, if it repeats, stops cleanly.", "default": 4000 } } }, "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 } } } } } } } } } }