{ "openapi": "3.0.1", "info": { "title": "Wayback Page Extractor", "description": "Extract clean text, metadata, offline HTML and images from Wayback Machine (archive.org) snapshots for a list of URLs and a date range. JSON dataset + one ZIP per snapshot.", "version": "0.0", "x-build-id": "GMBfsSnVbbEPahq2Q" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/espmsftw~wayback-page-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-espmsftw-wayback-page-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/espmsftw~wayback-page-extractor/runs": { "post": { "operationId": "runs-sync-espmsftw-wayback-page-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/espmsftw~wayback-page-extractor/run-sync": { "post": { "operationId": "run-sync-espmsftw-wayback-page-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "type": "string", "description": "One URL per line." }, "fromDate": { "title": "From date", "type": "string", "description": "Earliest capture date, YYYY-MM-DD (YYYYMMDD also works). Empty = no lower limit." }, "toDate": { "title": "To date", "type": "string", "description": "Latest capture date, YYYY-MM-DD (YYYYMMDD also works). Empty = no upper limit." }, "matchType": { "title": "Match type", "enum": [ "exact", "prefix", "domain" ], "type": "string", "description": "exact (the URL as given), prefix (every URL under it) or domain (the whole domain).", "default": "exact" }, "collapse": { "title": "Collapse", "type": "string", "description": "CDX collapse parameter, e.g. timestamp:6 (one capture per month) or digest. Empty = timestamp:6 with a date range, urlkey without." }, "maxSnapshotsPerUrl": { "title": "Snapshots per URL", "minimum": 1, "maximum": 100, "type": "integer", "description": "How many captures to extract per URL (1–100): the most recent ones in the range.", "default": 1 }, "outputsText": { "title": "Text", "type": "boolean", "description": "Include the clean text (text.txt) in the ZIP and the dataset.", "default": true }, "outputsMetadata": { "title": "Metadata", "type": "boolean", "description": "Include title, description, Open Graph, canonical and charset.", "default": true }, "outputsHtml": { "title": "Offline HTML", "type": "boolean", "description": "Include the offline HTML (links and images rewritten) in the ZIP and the key-value store.", "default": false }, "outputsImages": { "title": "Images", "type": "boolean", "description": "Download the images referenced in the page into the ZIP.", "default": false }, "maxImagesPerPage": { "title": "Max images per page", "minimum": 1, "maximum": 100, "type": "integer", "description": "Image limit per capture (default 20, max 100).", "default": 20 }, "timeoutMs": { "title": "Timeout (ms)", "minimum": 1000, "maximum": 60000, "type": "integer", "description": "Per-request timeout to archive.org, in milliseconds. Timeouts are retried 3 times (2, 4 and 8 s).", "default": 30000 } } }, "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 } } } } } } } } } }