{ "openapi": "3.0.1", "info": { "title": "Wayback Machine & Internet Archive Scraper – Snapshots, Search", "description": "Query the Wayback Machine's official JSON APIs: snapshot history (CDX) for any URL, the latest archived snapshot, and full-text search of archive.org items. No login, no scraping, no proxy.", "version": "0.2", "x-build-id": "lG0ZG1Jib9Z1yUM4k" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/rowfeed~wayback-internet-archive-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-rowfeed-wayback-internet-archive-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/rowfeed~wayback-internet-archive-scraper/runs": { "post": { "operationId": "runs-sync-rowfeed-wayback-internet-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/rowfeed~wayback-internet-archive-scraper/run-sync": { "post": { "operationId": "run-sync-rowfeed-wayback-internet-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "mode": { "title": "Mode", "enum": [ "snapshots", "latest", "search" ], "type": "string", "description": "snapshots = full CDX history per URL (one row per archived capture). latest = the most recent snapshot per URL (one row per URL). search = full-text search of archive.org items (books, audio, video, software, texts).", "default": "snapshots" }, "urls": { "title": "URLs", "type": "array", "description": "Domains or URLs to look up in the Wayback Machine. Used by the snapshots and latest modes. A malformed entry becomes an unbilled error row instead of stopping the run.", "default": [ "example.com", "apify.com" ], "items": { "type": "string" } }, "from": { "title": "From (snapshots mode)", "type": "string", "description": "Only include snapshots captured on or after this year or date, e.g. 2024 or 20240101. Leave blank for no lower bound." }, "to": { "title": "To (snapshots mode)", "type": "string", "description": "Only include snapshots captured on or before this year or date, e.g. 2026 or 20261231. Leave blank for no upper bound." }, "matchType": { "title": "Match type (snapshots mode)", "enum": [ "exact", "prefix", "host", "domain" ], "type": "string", "description": "exact = only this URL. prefix = this URL and everything under it. host = the whole hostname. domain = the hostname and its subdomains.", "default": "exact" }, "statusCode": { "title": "Status code filter (snapshots mode)", "type": "string", "description": "Only include snapshots with this HTTP status code, e.g. 200. Leave blank to include every status code.", "default": "200" }, "maxSnapshotsPerUrl": { "title": "Max snapshots per URL (snapshots mode)", "minimum": 1, "type": "integer", "description": "Stop after this many snapshot rows per URL. Each row is one `row` event ($0.50 per 1,000).", "default": 100 }, "collapse": { "title": "Collapse (snapshots mode)", "type": "string", "description": "Collapse consecutive snapshots that share the same value of this CDX field, e.g. digest (skip re-captures with identical content) or timestamp:8 (one per day). Leave blank for every capture.", "default": "digest" }, "query": { "title": "Search query (search mode)", "type": "string", "description": "Full-text search query against archive.org's item catalog (title, description, text).", "default": "climate data" }, "mediaType": { "title": "Media type filter (search mode)", "type": "string", "description": "Optional archive.org mediatype filter, e.g. texts, audio, movies, software, image, data. Leave blank for every media type." }, "maxResults": { "title": "Max results (search mode)", "minimum": 1, "type": "integer", "description": "Stop after this many search result rows. Each row is one `row` event ($0.50 per 1,000).", "default": 100 } } }, "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 } } }, "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 } } } } } } } } } }