Wayback Machine Snapshot History Scraper
Pricing
Pay per event
Go to Apify Store
Wayback Machine Snapshot History Scraper
Export Internet Archive Wayback Machine snapshot history with replay URLs, timestamps, status, MIME, digest, and size filters.
Wayback Machine Snapshot History Scraper
Pricing
Pay per event
Export Internet Archive Wayback Machine snapshot history with replay URLs, timestamps, status, MIME, digest, and size filters.
You can access the Wayback Machine Snapshot History Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
![Internet Archive Scraper — Wayback + Search + Metadata [$1.5💰] avatar](https://images.apifyusercontent.com/Tkb7JVd6vvGNN4CCZI23E7wLy3CwGe-DUvxaTNiyBaA/rs:fill:76:76/cb:1/aHR0cHM6Ly9hcGlmeS1pbWFnZS11cGxvYWRzLXByb2QuczMudXMtZWFzdC0xLmFtYXpvbmF3cy5jb20vbmduOHZSRVNUa3NleVdFNnAtYWN0b3ItOUo5UmNFdGhDcEtYM3hEeDMtNUVQN1dMeVZUai1pbnRlcm5ldF9hcmNodmllLnBuZw.webp){kind=avatar}
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "fqf0mYLhMGWEKgvys" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/automation-lab~wayback-machine-snapshot-history-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-automation-lab-wayback-machine-snapshot-history-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/automation-lab~wayback-machine-snapshot-history-scraper/runs": { "post": { "operationId": "runs-sync-automation-lab-wayback-machine-snapshot-history-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/automation-lab~wayback-machine-snapshot-history-scraper/run-sync": { "post": { "operationId": "run-sync-automation-lab-wayback-machine-snapshot-history-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "targets" ], "properties": { "targets": { "title": "Domains, URLs, or URL patterns", "minItems": 1, "maxItems": 100, "type": "array", "description": "One to 100 targets. Examples: nasa.gov, https://www.nasa.gov/history/, or nasa.gov/*.", "default": [ "nasa.gov" ], "items": { "type": "string" } }, "matchType": { "title": "Match type", "enum": [ "exact", "prefix", "host", "domain" ], "type": "string", "description": "Domain includes subdomains; host stays on one host; prefix finds URLs below a prefix; exact matches one URL.", "default": "domain" }, "from": { "title": "Captured from", "pattern": "^\\d{4}(?:\\d{2}(?:\\d{2}(?:\\d{2}(?:\\d{2}(?:\\d{2})?)?)?)?)?$", "type": "string", "description": "Optional UTC boundary using 4–14 digits, from YYYY to YYYYMMDDhhmmss." }, "to": { "title": "Captured to", "pattern": "^\\d{4}(?:\\d{2}(?:\\d{2}(?:\\d{2}(?:\\d{2}(?:\\d{2})?)?)?)?)?$", "type": "string", "description": "Optional inclusive UTC boundary using 4–14 digits, from YYYY to YYYYMMDDhhmmss." }, "statusCodes": { "title": "HTTP status filters", "type": "array", "description": "Exact status codes (200, 301) or classes (2.., 3..). All selected filters must match.", "default": [ "200" ], "items": { "type": "string" } }, "mimeTypes": { "title": "MIME type filters", "type": "array", "description": "CDX MIME types such as text/html, application/pdf, or image/*.", "default": [ "text/html" ], "items": { "type": "string" } }, "collapseByDigest": { "title": "Collapse identical content", "type": "boolean", "description": "Return only one capture for repeated records with the same Internet Archive digest.", "default": false }, "maxItems": { "title": "Maximum captures", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum dataset records across all targets.", "default": 20 }, "pageSize": { "title": "CDX page size", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Records requested per CDX page. Lower this if the archive rate-limits large queries.", "default": 500 }, "maxRetries": { "title": "Maximum retries", "minimum": 0, "maximum": 8, "type": "integer", "description": "Retries for timeouts, HTTP 429, and temporary 5xx responses.", "default": 4 } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Wayback Machine Snapshot History Scraper from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: