{ "openapi": "3.0.1", "info": { "title": "Wayback Site Migration Audit & Archive Scraper", "description": "Export Wayback snapshots, find historical URLs missing after site migrations, or search Archive.org metadata. Structured JSON/CSV with no login, browser, or proxy.", "version": "0.1", "x-build-id": "RhP9RKQll0qqIIKPg" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/immense_insulator~internet-archive-data-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-immense_insulator-internet-archive-data-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/immense_insulator~internet-archive-data-extractor/runs": { "post": { "operationId": "runs-sync-immense_insulator-internet-archive-data-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/immense_insulator~internet-archive-data-extractor/run-sync": { "post": { "operationId": "run-sync-immense_insulator-internet-archive-data-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "mode": { "title": "Mode", "enum": [ "catalog", "snapshots", "migrationAudit", "items" ], "type": "string", "description": "catalog searches Archive.org items; snapshots returns CDX rows; migrationAudit finds archived HTML URLs absent from currentUrls or a current sitemap; items aliases catalog.", "default": "catalog" }, "query": { "title": "Catalog search query", "type": "string", "description": "Required in catalog/items mode. Internet Archive advanced-search query; plain text and clauses such as mediatype:texts are supported.", "default": "collection:opensource_movies" }, "url": { "title": "Wayback URL", "type": "string", "description": "A single http/https URL or CDX URL pattern for snapshots mode, for example https://example.com/*." }, "urls": { "title": "Wayback URLs", "maxItems": 100, "type": "array", "description": "Optional list of http/https URLs or CDX URL patterns. Combined with url, deduplicated, and limited to 100 entries.", "items": { "type": "string" } }, "currentUrls": { "title": "Current live URL inventory", "maxItems": 10000, "type": "array", "description": "migrationAudit only. Current absolute URLs; archived URLs absent from this inventory become review candidates. Combined with currentSitemapUrl.", "items": { "type": "string" } }, "currentSitemapUrl": { "title": "Current sitemap URL", "type": "string", "description": "migrationAudit only. Optional absolute sitemap or sitemap-index URL. At most 20 sitemap documents and 10,000 current URLs are read." }, "fromTimestamp": { "title": "Snapshots from", "pattern": "^[0-9]{1,14}$", "type": "string", "description": "Optional inclusive CDX timestamp prefix, from YYYY through YYYYMMDDhhmmss (digits only)." }, "toTimestamp": { "title": "Snapshots to", "pattern": "^[0-9]{1,14}$", "type": "string", "description": "Optional inclusive CDX timestamp prefix, from YYYY through YYYYMMDDhhmmss (digits only)." }, "statusCodes": { "title": "HTTP status filters", "maxItems": 20, "uniqueItems": true, "type": "array", "description": "Optional HTTP status codes to include, such as [200, 301]. Up to 20 values.", "items": { "type": "integer", "minimum": 100, "maximum": 599 } }, "mimeTypes": { "title": "MIME type filters", "maxItems": 20, "uniqueItems": true, "type": "array", "description": "Optional CDX MIME types to include, such as text/html or application/json. Up to 20 values.", "items": { "type": "string" } }, "collapse": { "title": "Collapse snapshots", "enum": [ "", "digest", "urlkey", "timestamp:4", "timestamp:6", "timestamp:8", "timestamp:10", "timestamp:12", "timestamp:14" ], "type": "string", "description": "Optional server-side CDX collapse. digest removes repeated content; urlkey groups canonical URLs; timestamp:N groups by timestamp prefix length.", "default": "" }, "mediaType": { "title": "Catalog media type", "enum": [ "", "texts", "movies", "audio", "software", "image", "web" ], "type": "string", "description": "Optional catalog mediatype filter.", "default": "" }, "yearFrom": { "title": "Catalog year from", "minimum": 1, "maximum": 2100, "type": "integer", "description": "Optional earliest catalog year (inclusive)." }, "yearTo": { "title": "Catalog year to", "minimum": 1, "maximum": 2100, "type": "integer", "description": "Optional latest catalog year (inclusive)." }, "sortBy": { "title": "Catalog sort order", "enum": [ "downloads desc", "date desc", "date asc", "titleSorter asc" ], "type": "string", "description": "Choose how matching catalog records are ordered before export.", "default": "downloads desc" }, "maxItems": { "title": "Maximum output items", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Global maximum dataset rows across all URLs or catalog pages. Hard limit: 10,000.", "default": 100 }, "includeMetadata": { "title": "Fetch full catalog metadata", "type": "boolean", "description": "Catalog mode only. Fetch each item's full metadata record.", "default": false }, "includeFiles": { "title": "Include catalog downloadable files", "type": "boolean", "description": "Catalog mode only. Include file names, formats, sizes, checksums, and download URLs. Enables full metadata.", "default": false }, "fileLimit": { "title": "Files per catalog item", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Catalog mode only. Maximum file entries returned for each item.", "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 } } } } } } } } } }