Pricing

from $5.00 / 1,000 results

Try for free

Go to Apify Store

LLM Table Cleaner (HTML/CSV to Markdown) & llms.txt Auditor MCP

Try for free

Convert messy HTML tables and broken CSVs into compact LLM-ready Markdown & JSON. Audit and generate llms.txt for AI Agents.

Pricing

from $5.00 / 1,000 results

Rating

0.0

(0)

Developer

Thinh Le

Actor stats

Bookmarked

Total users

Monthly active users

2 days ago

Last modified

High-ROI B2B & AI Agent Use Cases

RAG & AI Agent Pipelines: Strip noisy HTML tags, inline CSS, scripts, and broken CSV delimiters before feeding tabular data into GPT-4o, Claude, or Gemini.
AEO & /llms.txt Compliance Auditing: Automatically verify whether client websites comply with the /llms.txt standard and generate a ready-to-deploy template.
Token Cost Optimization: Convert megabytes of raw HTML table markup into compact Markdown tables and normalized JSON arrays.

Transparent Pay-Per-Event (PPE) Pricing

Platform compute usage is included (Free for the first 5 seconds)—you only pay per processed item:

Volume	Event Price	Estimated Total Cost	Compute Overhead
100 Tables / Audits	$0.005 / item	$0.50	$0.00 (Included)
1,000 Tables / Audits	$0.005 / item	$5.00	$0.00 (Included)

Sample JSON Output

{
  "mode": "clean-table",
  "formatDetected": "html",
  "rowCount": 2,
  "columnCount": 2,
  "markdown": "| Company | Revenue |\n| --- | --- |\n| Acme AI | $12,500 |",
  "json": [{ "Company": "Acme AI", "Revenue": "$12,500" }],
  "stats": {
    "originalChars": 420,
    "cleanedChars": 62,
    "compressionPercent": 85,
    "estimatedTokensSaved": 89
  }
}

AI Agent & MCP Server Integration (Claude, Cursor, n8n, Make)

This Actor is natively compatible with the Apify Model Context Protocol (MCP) Server (https://mcp.apify.com).

Claude Desktop / Cursor / Windsurf: Add this Actor to your MCP configuration to allow autonomous AI Agents to query live structured data on demand.
n8n / Make / Zapier: Trigger this Actor on a daily or hourly cron schedule and pipe the clean JSON dataset directly into your CRM, PostgreSQL, Supabase, or Slack alerts.

Explore the Complete acer_quant_ai B2B Intelligence Suite

Build end-to-end automated pipelines by combining our pure-HTTP, ultra-low-cost (128MB RAM) MCP Actors:

E-Commerce & Retail Spy: Shopify Store & Product Catalog Spy | WooCommerce & WordPress JSON Spy
B2B Hiring & Salary Intelligence: Greenhouse Tech Jobs Spy | Ashby HQ AI Unicorn Jobs & Equity | Rippling v2 & Lever Salary Scraper
Healthcare, MedTech & Biotech Leads: US Doctors & Clinics NPI Registry v2.1 | openFDA 510(k) Devices & Drug NDC | NIH ClinicalTrials.gov v2 Biotech Contacts
SaaS, GovTech & PropTech: USASpending Federal Contract Winners | Atlassian Marketplace v3 SaaS Spy | WordPress Plugin Micro-PE Leads | VS Code Marketplace Trending DevTools | European Real Estate Listings
AI Data Utilities & AEO: LLM HTML/CSV Table Cleaner & llms.txt Auditor | Website AEO, Schema.org & AI Crawler Auditor

Website Content to Markdown for LLM Training

easyapi/website-content-to-markdown-for-llm-training

🚀 Transform web content into clean, LLM-ready Markdown! 📘 Scrape multiple pages, extract main content, and convert to Markdown format. Perfect for AI researchers, data scientists, and LLM developers. Fast, efficient, and customizable. Supercharge your AI training data today! 🌐📝🧠

EasyApi

338

5.0

(2)

Notion Page Scraper | Extract Wiki, Tables & Markdown

forlex/notion-page-scraper

Scrape public Notion pages, databases, and wikis into clean JSON, Markdown, or HTML. Fully reliable Playwright engine that succeeds where others fail. Perfect for AI/RAG, backups, and data extraction.

Forlex Lab

5.0

(1)

Website To Markdown

smart_api/website-to-markdown

Convert any webpage into clean, LLM-ready Markdown in seconds — perfect for AI training data, RAG pipelines, and content archiving.

SmartApi

5.0

(1)

Website Content Crawler — Markdown for LLM & RAG

brilliant_gum/web-content-crawler

Deep-crawl websites and extract LLM-ready Markdown with OG tags, JSON-LD, author, dates, token estimates, native RAG chunking, language filtering, content-hash dedup, and per-page error reporting. Enforced timeouts. Zero silent failures.

Yuliia Kulakova

Web to LLM Spanish — RAG-ready content extractor

fanciful_geode/web-to-llm-es

Crawls Spanish-language websites and extracts clean markdown content optimized for LLM RAG pipelines. Handles Spanish character encoding, removes boilerplate, and outputs structured chunks ready for embedding.

Ernesto de Armas

Doc2RAG AI - Documentation to LLM-Ready Markdown Converter

automation_studio/doc-to-rag-markdown-converter

Convert technical documentation websites (Stripe, Supabase, Next.js, Mintlify, Docusaurus) into clean, LLM-ready Markdown with preserved multi-language code blocks, tables, and RAG frontmatter. Exports JSON dataset, single llms-full.txt, and ZIP archive.

Automation Studio

HTML Table Extractor

benthepythondev/html-table-extractor

Extract structured rows from HTML tables on any web page.

Ben

LLM-Ready Web Scraper

devoted_helix/llm-web-scraper

Convert web pages to clean, LLM-friendly text. Perfect for RAG pipelines, AI chatbot training, and fine-tuning datasets. Removes ads,menus, and clutter automatically.

batuhan senavci

Inline HTML to Markdown & Text

grounded_goldeneye/inline-html-markdown-cleaner

Convert pasted HTML into Markdown and plain text, retaining headings, lists, code and tables. Remove scripts and hidden elements, optionally remove navigation and footer content. No browser or URL fetching.