{ "openapi": "3.0.1", "info": { "title": "Wayback Snapshot Offline Export", "description": "Export supplied Wayback snapshots into selector-scoped text, image and provenance JSON plus sanitized offline HTML with bounded embedded images. No subpage crawling or interactive cloning.", "version": "0.1", "x-build-id": "ISqR3MLQNjb42Oq9z" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/automation-lab~wayback-snapshot-offline-export/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-automation-lab-wayback-snapshot-offline-export", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/automation-lab~wayback-snapshot-offline-export/runs": { "post": { "operationId": "runs-sync-automation-lab-wayback-snapshot-offline-export", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/automation-lab~wayback-snapshot-offline-export/run-sync": { "post": { "operationId": "run-sync-automation-lab-wayback-snapshot-offline-export", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Archived snapshot URLs", "type": "array", "description": "HTTPS web.archive.org/web/ URLs with a full 14-digit capture timestamp and an HTTP(S) original URL. Replay modifiers are normalized to raw id_ requests. Redirected capture timestamps are recorded. Duplicate normalized URLs are skipped; all URLs are validated even beyond the item limit. No live pages or URL-list files.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxItems": { "title": "Maximum snapshots", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Global maximum unique supplied snapshots attempted, in input order; default 10. Range 1–10000, no unlimited setting. Failed captures produce no charged result and fail the run after retaining successful partial exports.", "default": 10 }, "textSelector": { "title": "Text CSS selector", "type": "string", "description": "CSS selector for text extraction, default body. Matching trees are traversed once even when selectors overlap, with normalized whitespace; scripts, archive toolbar and style text are excluded. Empty matches fail that snapshot. Does not limit the offline HTML content.", "default": "body" }, "imageSelector": { "title": "Image CSS selector", "type": "string", "description": "CSS selector selecting img elements directly (for example article img); default img. Only selected src images are fetched and included in image metadata, subject to asset bounds. Other images, srcset, background images and remote resources are removed from offline HTML.", "default": "img" }, "metadataSelector": { "title": "Metadata CSS selector", "type": "string", "description": "CSS selector for metadata containers or title/meta elements directly, default head. Captures title and named/property/http-equiv meta entries inside the selection. Missing values remain null/empty; capture provenance is always recorded independently.", "default": "head" }, "maxImages": { "title": "Maximum image requests per snapshot", "minimum": 0, "maximum": 100, "type": "integer", "description": "Maximum distinct image fetches attempted per snapshot, including failures. Default 20, range 0–100. Zero disables image fetching. Duplicate successfully embedded images share bytes; omissions are recorded.", "default": 20 }, "maxAssetBytes": { "title": "Maximum bytes per image", "minimum": 1024, "maximum": 2097152, "type": "integer", "description": "Maximum downloaded bytes per raster image (PNG/JPEG/GIF/WebP). Default 1048576; range 1024–2097152. Larger or unsupported assets are omitted, not linked remotely.", "default": 1048576 }, "maxTotalAssetBytes": { "title": "Total image bytes per snapshot", "minimum": 1024, "maximum": 16777216, "type": "integer", "description": "Maximum aggregate downloaded validated raster bytes per snapshot, including assets omitted by the output budget. Default 8388608; range 1024–16777216. Independently, serialized data URLs are capped at 4 MiB across all occurrences, including duplicates; excess images are explicitly omitted. Source HTML and decoded text are capped at 2 MiB, markup at 10000 less-than characters, and final offline HTML at 16 MiB; complexity/decoding failures produce no charged result.", "default": 8388608 } } }, "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 } } } } } } } } } }