{ "openapi": "3.0.1", "info": { "title": "LLM-Ready Web Scraper – RAG & Vertical Data Extraction", "description": "Scrapes any URL and returns clean LLM-ready content. Strips ads, nav, and boilerplate. Returns markdown, chunked text, token estimates, and metadata. Vertical modes for Legal, Medical, Property, E-commerce, Research, and News. Firecrawl alternative at $0.005 per URL.", "version": "1.0", "x-build-id": "mSO6S1SydcYYoBEdx" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/conceivable_extension~llm-ready-web-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-conceivable_extension-llm-ready-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/conceivable_extension~llm-ready-web-scraper/runs": { "post": { "operationId": "runs-sync-conceivable_extension-llm-ready-web-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/conceivable_extension~llm-ready-web-scraper/run-sync": { "post": { "operationId": "run-sync-conceivable_extension-llm-ready-web-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": [ "urls" ], "properties": { "urls": { "title": "URLs to Scrape", "minItems": 1, "type": "array", "description": "List of URLs to scrape and convert to LLM-ready content. Supports any public web page.", "items": { "type": "string" } }, "outputFormat": { "title": "Output Format", "enum": [ "markdown", "plaintext", "json" ], "type": "string", "description": "Format for the extracted content. Markdown is recommended for LLMs.", "default": "markdown" }, "vertical": { "title": "Content Vertical", "enum": [ "general", "legal", "medical", "property", "ecommerce", "research", "news" ], "type": "string", "description": "Optimises extraction rules for the content type. General works for all pages.", "default": "general" }, "chunkContent": { "title": "Chunk Content for RAG", "type": "boolean", "description": "Split content into chunks suitable for embedding. Set chunk size with chunkTokenSize.", "default": false }, "chunkTokenSize": { "title": "Chunk Token Size", "minimum": 128, "maximum": 4096, "type": "integer", "description": "Approximate token size per chunk when chunking is enabled. 512 is standard for most embedding models.", "default": 512 }, "includeMetadata": { "title": "Include Page Metadata", "type": "boolean", "description": "Include title, description, author, publish date, word count, and estimated token count in output.", "default": true }, "removeElements": { "title": "Additional Elements to Remove", "type": "array", "description": "CSS selectors for elements to strip from the page before extraction. Example: '.sidebar', '#comments'", "items": { "type": "string" } }, "followLinks": { "title": "Follow Internal Links", "type": "boolean", "description": "If enabled, follows internal links from each starting URL and scrapes linked pages too. Use maxDepth to control depth.", "default": false }, "maxDepth": { "title": "Max Link Depth", "minimum": 1, "maximum": 3, "type": "integer", "description": "How many levels of internal links to follow. Only used when followLinks is true.", "default": 1 }, "maxPagesPerUrl": { "title": "Max Pages Per Starting URL", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum pages to scrape per starting URL when following links.", "default": 10 }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings. Residential proxy recommended for protected sites." } } }, "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 } } } } } } } } } }