{ "openapi": "3.0.1", "info": { "title": "Wayback Machine Scraper: Snapshots, History & Archived Pages", "description": "List every Internet Archive snapshot of a URL or a whole domain, find the closest capture to a date, track how a page changed over time, and download the archived HTML. Official CDX and availability APIs, no API key.", "version": "0.0", "x-build-id": "wZmclEeAd2oH9K3eo" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/winterlock~wayback-machine-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-winterlock-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/winterlock~wayback-machine-scraper/runs": { "post": { "operationId": "runs-sync-winterlock-wayback-machine-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/winterlock~wayback-machine-scraper/run-sync": { "post": { "operationId": "run-sync-winterlock-wayback-machine-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "mode" ], "properties": { "mode": { "title": "What to do", "enum": [ "snapshots", "availability", "pageHistory", "fetchSnapshot" ], "type": "string", "description": "List snapshots, find the closest capture to a date, track how a page changed, or download the archived content itself.", "default": "snapshots" }, "urls": { "title": "URLs", "type": "array", "description": "One per line. A full URL, or a bare hostname to cover a whole site when combined with a match type below.", "items": { "type": "string" } }, "matchType": { "title": "Match type", "enum": [ "exact", "prefix", "host", "domain" ], "type": "string", "description": "Exact matches that one URL. Prefix matches everything under a path. Host matches one hostname. Domain matches the hostname and all its subdomains.", "default": "exact" }, "fromDate": { "title": "From date", "type": "string", "description": "Earliest capture to include. A year (2015), a month (201503), a date (20150301) or a full timestamp all work." }, "toDate": { "title": "To date", "type": "string", "description": "Latest capture to include, in the same formats as From date." }, "newestFirst": { "title": "Newest captures first", "type": "boolean", "description": "For List snapshots and Page history. The archive is ordered oldest first, so a capped run returns a page's earliest captures; turn this on to take the most recent ones instead. Download archived content always takes the most recent capture in the date range you set.", "default": false }, "onlySuccessful": { "title": "Only successful captures", "type": "boolean", "description": "Skip captures the Archive recorded as redirects or errors, keeping only HTTP 200 responses.", "default": false }, "filters": { "title": "Extra filters (advanced)", "type": "array", "description": "Raw CDX filters, one per line, such as mimetype:text/html or !statuscode:404. A leading ! negates the match.", "items": { "type": "string" } }, "collapse": { "title": "Collapse (advanced)", "type": "array", "description": "Collapse consecutive rows sharing a field, one per line. digest keeps only captures where the content changed; timestamp:6 keeps one per month.", "items": { "type": "string" } }, "nearestTo": { "title": "Nearest to date", "type": "string", "description": "For Closest snapshot. The date to search around, such as 20200101. Leave empty for the most recent capture." }, "maxSnapshotsPerUrl": { "title": "Max snapshots per URL", "minimum": 1, "maximum": 20000, "type": "integer", "description": "For List snapshots and Page history. Popular pages hold tens of thousands of captures, so this is the main control on run size and cost.", "default": 500 }, "copiesPerUrl": { "title": "Archived copies to download per URL", "minimum": 1, "maximum": 100, "type": "integer", "description": "For Download archived content. 1 downloads the most recent capture in your date range; a higher number also downloads the captures before it, newest first. Each copy is one billed result.", "default": 1 }, "maxContentCharacters": { "title": "Max characters of archived content", "minimum": 500, "maximum": 1000000, "type": "integer", "description": "For Download archived content. Longer pages are cut off at this length and flagged as truncated.", "default": 200000 }, "maxItems": { "title": "Max items in total", "minimum": 1, "type": "integer", "description": "Stop the run after saving this many items. Leave empty for no limit." }, "maxConcurrency": { "title": "Max parallel requests", "minimum": 1, "maximum": 8, "type": "integer", "description": "The Internet Archive is a nonprofit running on donations. Please leave this low.", "default": 2 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Not needed for ordinary runs. Turn on Apify Proxy only if the Archive rate-limits a very long batch.", "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 }, "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 } } } } } } } } } }