{ "openapi": "3.0.1", "info": { "title": "Wayback Machine Scraper – Snapshots and History", "description": "Wayback Machine snapshots for any URL or domain with no 10,000-row cap, at $2 per 1,000. Closest capture to a date, a one-row domain history, and archived text when you ask.", "version": "0.1", "x-build-id": "UvfhpKFcBmYe5yLhI" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/martinvarelaa~wayback-machine-snapshots/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-martinvarelaa-wayback-machine-snapshots", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/martinvarelaa~wayback-machine-snapshots/runs": { "post": { "operationId": "runs-sync-martinvarelaa-wayback-machine-snapshots", "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/martinvarelaa~wayback-machine-snapshots/run-sync": { "post": { "operationId": "run-sync-martinvarelaa-wayback-machine-snapshots", "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": "Mode", "enum": [ "list-snapshots", "closest-snapshot", "domain-summary" ], "type": "string", "description": "List snapshots, the capture closest to a date, or one history row per domain.", "default": "list-snapshots" }, "targets": { "title": "URLs or domains", "type": "array", "description": "One URL or domain per line, for example https://example.com or example.com/pricing.", "items": { "type": "string" } }, "matchType": { "title": "Match type", "enum": [ "exact", "prefix", "host", "domain" ], "type": "string", "description": "Exact URL is the reliable default. Domain-wide lists often time out at archive.org; use Domain history summary for a whole site.", "default": "exact" }, "from": { "title": "From", "type": "string", "description": "First day to include. YYYY, YYYY-MM, or YYYY-MM-DD. Example: 2015-01-01." }, "to": { "title": "To", "type": "string", "description": "Last day to include. YYYY, YYYY-MM, or YYYY-MM-DD. Example: 2015-12-31." }, "closestTo": { "title": "Date for the closest snapshot", "type": "string", "description": "Used in closest mode. Example: 2015-01-01." }, "collapse": { "title": "Collapse duplicates", "enum": [ "none", "digest", "day", "month", "year" ], "type": "string", "description": "Year keeps the default run short. Digest keeps a row only when the archived content changed.", "default": "year" }, "statusFilter": { "title": "HTTP status", "enum": [ "any", "200", "3xx", "4xx" ], "type": "string", "description": "200 keeps successful captures. 3xx and 4xx use the CDX status prefix.", "default": "200" }, "mimeFilter": { "title": "MIME type", "type": "string", "description": "Example: text/html. Leave empty to keep every MIME type.", "default": "text/html" }, "maxSnapshots": { "title": "Maximum snapshots", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Stop after this many snapshot rows. There is no hidden 10,000 cap.", "default": 10 }, "fetchContent": { "title": "Fetch archived page content", "type": "boolean", "description": "Download the archived page and return text, Markdown, or HTML. Charged per downloaded page.", "default": false }, "contentFormat": { "title": "Content format", "enum": [ "text", "markdown", "html" ], "type": "string", "description": "Used only when Fetch archived page content is on.", "default": "text" }, "maxContentPages": { "title": "Maximum pages to download", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Cap on archived pages downloaded in the run, even if Maximum snapshots is higher.", "default": 10 }, "onlyChanged": { "title": "Only rows where the content changed", "type": "boolean", "description": "Keep the first capture of each URL and later captures whose content digest changed.", "default": false }, "includeSnapshots": { "title": "Also list snapshots", "type": "boolean", "description": "In domain history mode, also return snapshot rows. Those rows are charged separately.", "default": false }, "sinceLastRun": { "title": "Only snapshots since the previous run", "type": "boolean", "description": "On a daily schedule, continue after the last snapshot already returned for the same targets and filters.", "default": 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 } } } } } } } } } }