LLMScraper
Pricing
Pay per usage
Go to Store
LLMScraper
Find best scraper for your website and data you need.
0.0 (0)
Pricing
Pay per usage
0
Total users
1
Monthly users
1
Last modified
6 days ago
You can access the LLMScraper 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.
{ "openapi": "3.0.1", "info": { "version": "1.2", "x-build-id": "iMCbhjr668pRfq6xS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ohlava~llmscraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ohlava-llmscraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ohlava~llmscraper/runs": { "post": { "operationId": "runs-sync-ohlava-llmscraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ohlava~llmscraper/run-sync": { "post": { "operationId": "run-sync-ohlava-llmscraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "targetUrl", "extractionGoal", "claudeApiKey" ], "properties": { "targetUrl": { "title": "Target URL", "type": "string", "description": "The URL of the website you want to scrape" }, "extractionGoal": { "title": "Extraction Goal", "type": "string", "description": "Describe what data you want to extract from the website" }, "claudeApiKey": { "title": "Claude API Key", "type": "string", "description": "Your Anthropic Claude API key for AI-powered actor discovery and testing" }, "maxActorAttempts": { "title": "Max Actor Attempts", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of different actors to try", "default": 10 }, "maxRetriesPerActor": { "title": "Max Retries per Actor", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum number of retry attempts per actor", "default": 3 }, "maxTimeMinutes": { "title": "Max Time (minutes)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Maximum total execution time in minutes", "default": 30 }, "mcpUrl": { "title": "MCP Server URL", "type": "string", "description": "URL of the Apify MCP server for actor discovery", "default": "https://mcp.apify.com/sse?enableAddingActors=true" }, "modelName": { "title": "Claude Model", "enum": [ "claude-3-5-haiku-latest", "claude-3-5-sonnet-latest", "claude-3-opus-latest", "claude-3-haiku-20240307", "claude-3-sonnet-20240229", "claude-3-5-sonnet-20241022" ], "type": "string", "description": "Choose which Claude model to use for AI analysis", "default": "claude-3-5-haiku-latest" }, "debugMode": { "title": "Debug Mode", "type": "boolean", "description": "Enable detailed logging for debugging", "default": false }, "preferSpecificActors": { "title": "Prefer Specific Actors", "type": "boolean", "description": "Prioritize domain-specific actors over general-purpose ones", "default": true }, "minDataQualityScore": { "title": "Minimum Data Quality Score", "minimum": 0, "maximum": 100, "type": "integer", "description": "Minimum quality score (0-100) to accept results", "default": 70 }, "enableProxy": { "title": "Enable Proxy", "type": "boolean", "description": "Use proxy for scraping requests", "default": true } } }, "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 } } } } } } } } }}LLMScraper OpenAPI definition
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 LLMScraper 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:
