{ "openapi": "3.0.1", "info": { "title": "Wayback Machine Scraper: Archived URLs, Snapshots & Page Text", "description": "Scrape the Internet Archive Wayback Machine via its official CDX API: every archived URL of a domain, snapshot history of any page (only content changes), first/last capture summary, and archived page text or Markdown. Date/status filters, alerts. $0.50 per 1,000 records.", "version": "1.0", "x-build-id": "sMfZpvCuHNhWPkx6z" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/manageable_gully~wayback-machine-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-manageable_gully-wayback-machine-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/manageable_gully~wayback-machine-scraper/runs": { "post": { "operationId": "runs-sync-manageable_gully-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/manageable_gully~wayback-machine-scraper/run-sync": { "post": { "operationId": "run-sync-manageable_gully-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", "required": [ "targets" ], "properties": { "mode": { "title": "What to get", "enum": [ "urls", "snapshots", "summary" ], "type": "string", "description": "urls = every unique archived URL of a domain or URL prefix with its first capture (find old/deleted pages, build redirect maps, SEO recovery). snapshots = every capture of the given pages over time (optionally only when the content changed). summary = one row per target: first and last capture, years archived, snapshot closest to a date.", "default": "urls" }, "targets": { "title": "Websites, domains or URLs", "type": "array", "description": "One per line: a domain (example.com), a URL (https://example.com/pricing), a URL prefix ending in * (example.com/blog/*), or a web.archive.org link.", "items": { "type": "string" } }, "matchType": { "title": "Match type", "enum": [ "auto", "exact", "prefix", "host", "domain" ], "type": "string", "description": "Auto: in 'urls' mode a bare domain means the whole domain incl. subdomains and a URL with a path means that prefix; in 'snapshots'/'summary' mode it means the exact URL. A trailing * always means prefix.", "default": "auto" }, "dateFrom": { "title": "Captured from", "type": "string", "description": "Only captures on/after this date: 2015, 2015-06, 2015-06-30, 20150630120000, or relative like '30 days' / '2 years'." }, "dateTo": { "title": "Captured to", "type": "string", "description": "Only captures on/before this date (same formats)." }, "statusCodes": { "title": "HTTP status codes", "type": "array", "description": "Keep only captures with these status codes, e.g. 200, 301, 404, or classes like 2xx / 3xx. Empty = all.", "items": { "type": "string" } }, "mimeTypes": { "title": "MIME types", "type": "array", "description": "Keep only these content types, e.g. text/html, application/pdf. Empty = all.", "items": { "type": "string" } }, "excludeAssets": { "title": "Skip images, CSS, JS & fonts", "type": "boolean", "description": "In 'urls' mode, skip URLs of static assets (images, CSS, JS, fonts, media, archives).", "default": true }, "urlFilter": { "title": "URL must match (regex)", "type": "string", "description": "Optional regular expression the full archived URL must match, e.g. .*/blog/.* or .*\\.pdf$" }, "collapse": { "title": "Snapshot frequency", "enum": [ "none", "hour", "day", "month", "year", "digest" ], "type": "string", "description": "Used in 'snapshots' mode. 'Only when content changed' skips captures identical to the previous one (same content hash).", "default": "none" }, "order": { "title": "Order", "enum": [ "oldest", "newest" ], "type": "string", "description": "Used in 'snapshots' mode.", "default": "oldest" }, "closestDate": { "title": "Snapshot closest to date", "type": "string", "description": "Used in 'summary' mode: also return the capture closest to this date (e.g. 2019-01-01)." }, "fetchContent": { "title": "Fetch archived page content", "type": "boolean", "description": "Download each archived HTML page (original, without the Wayback toolbar) and add title, meta description, canonical, H1, word count and the text/Markdown. Charged per page.", "default": false }, "contentFormat": { "title": "Content format", "enum": [ "text", "markdown", "html" ], "type": "string", "description": "Format of the 'content' field.", "default": "text" }, "maxContentChars": { "title": "Max content characters", "minimum": 0, "type": "integer", "description": "Truncate content to this many characters (0 = no limit).", "default": 20000 }, "maxContentPages": { "title": "Max pages with content", "minimum": 0, "type": "integer", "description": "Stop fetching content after this many pages (records are still saved).", "default": 100 }, "maxItemsPerTarget": { "title": "Max records per target", "minimum": 0, "type": "integer", "description": "0 = no limit (large domains can have millions of archived URLs).", "default": 1000 }, "maxItems": { "title": "Max records in total", "minimum": 0, "type": "integer", "description": "0 = no limit.", "default": 0 }, "onlyNew": { "title": "Only new (for schedules)", "type": "boolean", "description": "Remember what earlier runs returned and save only new archived URLs ('urls' mode) or new captures ('snapshots' mode). Use with a schedule to get alerts.", "default": false }, "stateKey": { "title": "Alert name", "type": "string", "description": "Separate memory for different scheduled tasks using Only new.", "default": "default" } } }, "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 } } } } } } } } } }