Internet Archive Search Scraper
Pricing
from $1.99 / 1,000 search results
Go to Apify Store
Internet Archive Search Scraper
Searches public Internet Archive items with filters, sorting, and API pagination.
Internet Archive Search Scraper
Pricing
from $1.99 / 1,000 search results
Searches public Internet Archive items with filters, sorting, and API pagination.
You can access the Internet Archive Search Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "2.0", "x-build-id": "iHqrH09HKHP5S2HFM" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/searchapi~internet-archive-search-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-searchapi-internet-archive-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/searchapi~internet-archive-search-scraper/runs": { "post": { "operationId": "runs-sync-searchapi-internet-archive-search-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/searchapi~internet-archive-search-scraper/run-sync": { "post": { "operationId": "run-sync-searchapi-internet-archive-search-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": [ "query" ], "properties": { "query": { "title": "Search query", "minLength": 1, "maxLength": 500, "type": "string", "description": "Words or Internet Archive Advanced Search syntax to search.", "default": "climate change" }, "mediaTypes": { "title": "Media types", "maxItems": 8, "uniqueItems": true, "type": "array", "description": "Optional Internet Archive media-type filters.", "items": { "type": "string", "enum": [ "texts", "movies", "audio", "software", "image", "data", "web", "etree" ] } }, "collections": { "title": "Collections", "maxItems": 20, "uniqueItems": true, "type": "array", "description": "Optional exact Internet Archive collection identifiers.", "items": { "type": "string", "minLength": 1, "maxLength": 200 } }, "creators": { "title": "Creators", "maxItems": 20, "uniqueItems": true, "type": "array", "description": "Optional exact creator names.", "items": { "type": "string", "minLength": 1, "maxLength": 200 } }, "languages": { "title": "Languages", "maxItems": 20, "uniqueItems": true, "type": "array", "description": "Optional exact language names or codes.", "items": { "type": "string", "minLength": 1, "maxLength": 80 } }, "yearFrom": { "title": "Year from", "minimum": 1000, "maximum": 3000, "type": "integer", "description": "Optional inclusive earliest item year." }, "yearTo": { "title": "Year to", "minimum": 1000, "maximum": 3000, "type": "integer", "description": "Optional inclusive latest item year." }, "sortBy": { "title": "Sort by", "enum": [ "relevance", "downloads", "date", "publicdate", "title" ], "type": "string", "description": "Native Internet Archive result ordering.", "default": "relevance" }, "sortDirection": { "title": "Sort direction", "enum": [ "asc", "desc" ], "type": "string", "description": "Direction for explicit sort fields; relevance uses the native order.", "default": "desc" }, "maxItems": { "title": "Maximum records", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Hard global result limit.", "default": 25 }, "maxPages": { "title": "Maximum pages", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum native API pages to request.", "default": 5 }, "rowsPerPage": { "title": "Rows per API page", "minimum": 1, "maximum": 200, "type": "integer", "description": "Number of candidates requested per native API page.", "default": 50 }, "maxRequestRetries": { "title": "Maximum request retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retries for temporary network, rate-limit, and server failures.", "default": 3 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Per-request timeout.", "default": 30 }, "useApifyProxy": { "title": "Use Apify Proxy", "type": "boolean", "description": "Route requests through an authorized Apify Proxy configuration.", "default": false }, "proxyGroups": { "title": "Apify Proxy groups", "maxItems": 10, "type": "array", "description": "Optional Apify Proxy groups.", "items": { "type": "string" } }, "proxyCountryCode": { "title": "Proxy country", "pattern": "^[A-Z]{2}$", "maxLength": 2, "type": "string", "description": "Optional two-letter proxy country code." }, "proxyUrls": { "title": "Custom proxy URLs", "maxItems": 20, "type": "array", "description": "Optional HTTP(S) proxy URLs. Credentials are never logged.", "items": { "type": "string" } } } }, "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 Internet Archive Search 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: