# LLM-Ready Web Scraper – RAG & Vertical Data Extraction (`conceivable_extension/llm-ready-web-scraper`) Actor 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. - **URL**: https://apify.com/conceivable\_extension/llm-ready-web-scraper.md - **Developed by:** [joseph fadero](https://apify.com/conceivable_extension) (community) - **Categories:** AI, Developer tools, Automation - **Stats:** 2 total users, 1 monthly users, 0.0% runs succeeded, 1 bookmarks - **User rating**: No ratings yet ## Pricing from $5.00 / 1,000 url crawleds This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## LLM-Ready Web Scraper – RAG Data Extraction with Vertical Processing **The affordable Firecrawl alternative. $0.005 per URL. No subscription.** Scrapes any public URL and returns clean, structured content optimised for LLMs and RAG pipelines — stripped of navigation, ads, cookie banners, and HTML boilerplate. ### What makes it different - **Vertical processing modes** — Legal, Medical, Property, E-commerce, Research, and News modes apply domain-specific extraction rules for better content quality - **RAG-ready chunking** — splits content into configurable token-sized chunks ready for embedding - **Token estimation** — every result includes estimated token count so you know your LLM context usage upfront - **Pay per URL** — $0.005/URL, no subscription ### Use cases - Feed RAG pipelines with fresh web content for Claude, GPT-4, or LlamaIndex - Build AI agents that need live web data - n8n/Make: scrape URLs from a spreadsheet → get clean markdown → send to your LLM - Research aggregation: scrape multiple sources → chunk → embed → search - Legal research: extract clean text from case law and statutes - Property analysis: extract listing descriptions for AI comparison ### Pricing | Event | Price | |---|---| | Run started | $0.05 | | URL crawled (no chunks) | $0.005 | | URL crawled (with chunking) | $0.008 | | URL failed | $0.001 | **100 URLs = $0.55 total. Firecrawl Hobby plan: $19/month for 500 URLs.** ### Input | Field | Default | Description | |---|---|---| | urls | required | Array of URLs to scrape | | outputFormat | markdown | markdown / plaintext / json | | vertical | general | general / legal / medical / property / ecommerce / research / news | | chunkContent | false | Split into RAG-sized chunks | | chunkTokenSize | 512 | Target tokens per chunk (128–4096) | | includeMetadata | true | Include title, author, dates, word/token count | | removeElements | [] | Extra CSS selectors to strip | | followLinks | false | Follow internal links from starting URLs | | maxDepth | 1 | Link follow depth (1–3) | | maxPagesPerUrl | 10 | Max pages per starting URL | ### Output fields - `url`, `sourceUrl`, `crawledAt` - `title`, `description`, `author`, `publishDate`, `language` - `wordCount`, `estimatedTokens` - `content` — clean text in chosen format - `vertical` — which extraction mode was applied - `chunks` — array of `{ index, content, tokenEstimate }` when chunking enabled - `status` — success / failed / partial - `chargedEvent` ### Example n8n workflow Apify node → this actor → Claude AI node → Google Sheets # Actor input Schema ## `urls` (type: `array`): List of URLs to scrape and convert to LLM-ready content. Supports any public web page. ## `outputFormat` (type: `string`): Format for the extracted content. Markdown is recommended for LLMs. ## `vertical` (type: `string`): Optimises extraction rules for the content type. General works for all pages. ## `chunkContent` (type: `boolean`): Split content into chunks suitable for embedding. Set chunk size with chunkTokenSize. ## `chunkTokenSize` (type: `integer`): Approximate token size per chunk when chunking is enabled. 512 is standard for most embedding models. ## `includeMetadata` (type: `boolean`): Include title, description, author, publish date, word count, and estimated token count in output. ## `removeElements` (type: `array`): CSS selectors for elements to strip from the page before extraction. Example: '.sidebar', '#comments' ## `followLinks` (type: `boolean`): If enabled, follows internal links from each starting URL and scrapes linked pages too. Use maxDepth to control depth. ## `maxDepth` (type: `integer`): How many levels of internal links to follow. Only used when followLinks is true. ## `maxPagesPerUrl` (type: `integer`): Maximum pages to scrape per starting URL when following links. ## `proxyConfiguration` (type: `object`): Proxy settings. Residential proxy recommended for protected sites. ## Actor input object example ```json { "urls": [ "https://example.com/article" ], "outputFormat": "markdown", "vertical": "general", "chunkContent": false, "chunkTokenSize": 512, "includeMetadata": true, "followLinks": false, "maxDepth": 1, "maxPagesPerUrl": 10 } ```` # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "urls": [ "https://example.com/article" ] }; // Run the Actor and wait for it to finish const run = await client.actor("conceivable_extension/llm-ready-web-scraper").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "urls": ["https://example.com/article"] } # Run the Actor and wait for it to finish run = client.actor("conceivable_extension/llm-ready-web-scraper").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "urls": [ "https://example.com/article" ] }' | apify call conceivable_extension/llm-ready-web-scraper --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=conceivable_extension/llm-ready-web-scraper", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "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 } } } } } } } } } } ```