{ "openapi": "3.0.1", "info": { "title": "Wayback Machine Snapshot History & Archived Text Extractor", "description": "Pull the Wayback Machine's capture history for any URL, host, or domain with timestamps, status codes, MIME types, and optional archived page text.", "version": "2.0", "x-build-id": "IADcjvMrlQA9u17xO" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dataspryva~wayback-machine-snapshot-history-and-archived-text/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dataspryva-wayback-machine-snapshot-history-and-archived-text", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dataspryva~wayback-machine-snapshot-history-and-archived-text/runs": { "post": { "operationId": "runs-sync-dataspryva-wayback-machine-snapshot-history-and-archived-text", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dataspryva~wayback-machine-snapshot-history-and-archived-text/run-sync": { "post": { "operationId": "run-sync-dataspryva-wayback-machine-snapshot-history-and-archived-text", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Mode", "enum": [ "search", "timeline", "summary", "closest", "content" ], "type": "string", "description": "What to collect. 'search' returns every matching capture; 'timeline' returns one row per distinct content version; 'summary' returns archive coverage per target; 'closest' returns the nearest capture to a date; 'content' returns readable text from the archived page.", "default": "search" }, "url": { "title": "URL or domain (single target)", "type": "string", "description": "One URL, host, domain, or Wayback playback URL. Examples: 'apify.com', 'https://example.com/blog', 'https://web.archive.org/web/20240101000000/https://apify.com/'. Wildcards like 'example.com/*' and '*.example.com' are detected automatically." }, "urls": { "title": "URLs or domains (bulk)", "type": "array", "description": "One or more targets for batch collection. Each target is queried independently and the Max items budget is split across them.", "default": [], "items": { "type": "string" } }, "matchType": { "title": "URL match type", "enum": [ "exact", "prefix", "host", "domain" ], "type": "string", "description": "How the target is matched against the archive. 'exact' = that URL only; 'prefix' = the URL and every path beneath it; 'host' = every path on the same host; 'domain' = the host and all subdomains.", "default": "exact" }, "dateFrom": { "title": "From date", "type": "string", "description": "Earliest capture date, inclusive. Accepts YYYY, YYYY-MM, YYYY-MM-DD, or a full timestamp such as 2024-01-31T12:00:00." }, "dateTo": { "title": "To date", "type": "string", "description": "Latest capture date, inclusive. Uses the same formats as From date. A date without a time includes the whole day." }, "statusCodes": { "title": "Keep HTTP status codes", "type": "array", "description": "Only keep captures with these HTTP status codes, e.g. ['200','301']. Leave empty for all statuses. Values may also be comma-separated.", "default": [], "items": { "type": "string" } }, "excludeStatusCodes": { "title": "Exclude HTTP status codes", "type": "array", "description": "Drop captures with these HTTP status codes, e.g. ['404','500']. Leave empty to exclude nothing.", "default": [], "items": { "type": "string" } }, "mimeTypes": { "title": "Keep MIME types", "type": "array", "description": "Only keep captures with these MIME types, e.g. ['text/html','application/pdf']. Leave empty for all MIME types.", "default": [], "items": { "type": "string" } }, "excludeMimeTypes": { "title": "Exclude MIME types", "type": "array", "description": "Drop captures with these MIME types, e.g. ['image/png','video/mp4']. Leave empty to exclude nothing.", "default": [], "items": { "type": "string" } }, "collapseBy": { "title": "Collapse duplicates", "enum": [ "none", "digest", "urlkey", "monthly", "daily", "hourly" ], "type": "string", "description": "Deduplicate adjacent captures in 'search' mode. 'digest' keeps one record per distinct content fingerprint; 'urlkey' keeps one capture per URL; 'monthly', 'daily', and 'hourly' keep one capture per time bucket; 'none' returns every raw capture. 'timeline' and 'summary' always read raw captures so their counts and durations stay accurate.", "default": "digest" }, "sortDirection": { "title": "Which end of the archive", "enum": [ "earliest", "latest" ], "type": "string", "description": "Choose whether the limited result set comes from the oldest or newest captures. Search rows are emitted in chronological order; 'latest' reverses the final rows so the newest appears first.", "default": "earliest" }, "targetDate": { "title": "Target date", "type": "string", "description": "Date used by 'closest' and 'content' modes, and as the reference when a playback URL does not include a timestamp. Accepts YYYY, YYYY-MM, YYYY-MM-DD, or a full timestamp. Defaults to now when empty." }, "enrichWithContent": { "title": "Add archived text to search rows", "type": "boolean", "description": "In 'search' mode, fetch the archived HTML for the first Max content fetches rows and add its readable text and metadata. Off by default because it costs extra requests.", "default": false }, "maxContentFetch": { "title": "Max text fetches for search rows", "minimum": 0, "maximum": 500, "type": "integer", "description": "Cap on archived pages downloaded when 'Add archived text to search rows' is on. 0 disables enrichment. This setting is ignored by 'content' mode, which uses Max items instead.", "default": 10 }, "maxContentChars": { "title": "Max characters per archived page", "minimum": 1000, "maximum": 2000000, "type": "integer", "description": "Truncate extracted text at this many characters. The full word count and text hash are still recorded, and contentTruncated is set when clipping happens.", "default": 500000 }, "includeHeadings": { "title": "Include headings", "type": "boolean", "description": "Add the page's H1-H6 headings as structured records when archived text is extracted.", "default": true }, "maxItems": { "title": "Max items", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Hard cap on emitted records. For bulk search the budget is split evenly across targets. In 'summary' mode it is also the per-target capture scan budget, split between the oldest and newest ends. Up to 100,000 captures are supported through automatic resume-key pagination.", "default": 500 }, "detectChanges": { "title": "Annotate content changes", "type": "boolean", "description": "In 'search' mode, compare each capture with the previous capture of the same URL and add changed, changeType, previousTimestamp, and related fields.", "default": true } } }, "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 } } } } } } } } } }