{ "openapi": "3.0.1", "info": { "title": "Wayback Machine Scraper: Archived Snapshots & Pages", "description": "List Internet Archive Wayback Machine snapshots for URLs or whole domains (date range, status, MIME, collapse by change/day/URL), get the closest capture to a date, and optionally download archived page text or HTML. From $0.20 per 1,000 snapshots.", "version": "0.2", "x-build-id": "d5cqgjju2xFOiHrg8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tidyharvest~wayback-machine-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tidyharvest-wayback-machine-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/tidyharvest~wayback-machine-scraper/runs": { "post": { "operationId": "runs-sync-tidyharvest-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/tidyharvest~wayback-machine-scraper/run-sync": { "post": { "operationId": "run-sync-tidyharvest-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": [ "urls" ], "properties": { "urls": { "title": "URLs or domains", "type": "array", "description": "One per line: a page URL (`https://example.com/pricing`) or a domain (`example.com`). With *Match type* = prefix/host/domain, every archived URL under it is listed.", "items": { "type": "string" } }, "matchType": { "title": "Match type", "enum": [ "exact", "prefix", "host", "domain" ], "type": "string", "description": "Which archived URLs count as a match. Use *domain* with *Collapse = url* to list every page ever archived on a site (find deleted pages).", "default": "exact" }, "from": { "title": "From date", "type": "string", "description": "Only captures on or after this date: `YYYY`, `YYYY-MM` or `YYYY-MM-DD`." }, "to": { "title": "To date", "type": "string", "description": "Only captures on or before this date: `YYYY`, `YYYY-MM` or `YYYY-MM-DD`." }, "collapse": { "title": "Collapse (de-duplicate)", "enum": [ "none", "digest", "hour", "day", "month", "year", "url" ], "type": "string", "description": "Keep only the first capture per group. *Content changed* returns only captures whose content differs from the previous one: ideal for change history and price tracking.", "default": "none" }, "statusCodes": { "title": "HTTP status filter", "type": "array", "description": "Keep only captures with these original HTTP statuses, e.g. `200`, `301`, `404`, or `2xx`. Empty = all.", "items": { "type": "string" } }, "mimeType": { "title": "MIME type filter", "type": "string", "description": "Keep only this content type, e.g. `text/html`, `application/pdf`, `image/*`. Empty = all." }, "urlRegex": { "title": "URL regex filter", "type": "string", "description": "Keep only archived URLs matching this regular expression (whole URL), e.g. `.*/product/.*`. Useful with prefix/domain match." }, "newestFirst": { "title": "Newest first", "type": "boolean", "description": "Return the most recent captures first (with a cap, you get the latest N instead of the oldest N).", "default": false }, "closestTo": { "title": "Closest snapshot to date", "type": "string", "description": "Instead of listing, return the ONE capture of each URL closest to this date (`YYYY-MM-DD`). Uses the Wayback availability API." }, "fetchContent": { "title": "Fetch archived page content", "type": "boolean", "description": "Download the archived page for captures with status 200 (original bytes, no Wayback toolbar) and add `content`, `title`, `metaDescription`. Charged per page fetched.", "default": false }, "maxPagesFetched": { "title": "Max pages to fetch", "minimum": 0, "type": "integer", "description": "Cap on archived pages downloaded in the whole run (only with *Fetch content*).", "default": 10 }, "contentFormat": { "title": "Content format", "enum": [ "text", "html" ], "type": "string", "description": "Plain text (scripts/styles removed) or the raw archived HTML.", "default": "text" }, "maxContentChars": { "title": "Max characters per page", "minimum": 0, "type": "integer", "description": "Truncate each page's content to this many characters. 0 = no limit.", "default": 100000 }, "maxSnapshotsPerUrl": { "title": "Max snapshots per URL", "minimum": 0, "type": "integer", "description": "0 or empty = no limit." }, "maxItems": { "title": "Max snapshots in total", "minimum": 0, "type": "integer", "description": "Hard cap on results for the whole run (also caps your cost), shared fairly between your URLs: each gets an equal share and URLs with fewer captures pass the rest on. 0 = no limit.", "default": 1000 } } }, "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 } } } } } } } } } }