URL to Markdown for AI & LLM (Clean Web Content) avatar

URL to Markdown for AI & LLM (Clean Web Content)

Pricing

$1.50 / 1,000 page converteds

Go to Apify Store
URL to Markdown for AI & LLM (Clean Web Content)

URL to Markdown for AI & LLM (Clean Web Content)

Convert any list of web pages into clean Markdown or plain text for LLMs, RAG, vector databases and AI agents. Removes navigation, ads and boilerplate; keeps headings, lists, tables and links. Returns title, author, date and word count.

Pricing

$1.50 / 1,000 page converteds

Rating

0.0

(0)

Developer

Proper Ecosystem Tools

Proper Ecosystem Tools

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

8 days ago

Last modified

Security

Limited permissions

Share

Feed the web to your AI. This Actor converts any list of URLs into clean Markdown (or plain text) with just the main content: no menus, cookie banners, ads, or footers. Ideal for LLM prompts, RAG pipelines, vector databases, and AI agents.

Features

  • Main-content extraction with trafilatura, a leading open-source boilerplate remover
  • Markdown keeps headings, lists, tables, and links; plain text is also available
  • Metadata: title, author, publish date, description, site name, language, main image
  • Word and character counts, plus an optional max length for token budgets
  • Fast HTTP fetching with no browser; honors robots.txt
  • Works great from LangChain, LlamaIndex, n8n, Make, and MCP clients

Input

FieldDescription
urlsDomains or full URLs, one per line.
outputFormatMarkdown keeps headings, lists, tables and links.
includeLinksKeep hyperlinks in Markdown output.
includeTablesKeep tables.
includeImagesKeep image references.
maxCharactersTruncate content longer than this.
concurrencyItems processed in parallel.
maxItemsStop after this many unique inputs.

Output (illustrative example)

{
"url": "https://www.example.com/blog/post",
"title": "Example Article Title",
"wordCount": 860,
"format": "markdown",
"content": "# Example Article Title\n\nThis is an example paragraph with a [link](https://www.example.com).\n\n## Section\n- point one\n- point two"
}

Pricing

Pay per event: page converted. Rows that fail with an error are free. Set a maximum charge per run to cap spend.

Use cases

  • Build RAG knowledge bases from docs and blogs
  • Give AI agents readable page content
  • Summarize or classify articles in bulk
  • Archive articles as Markdown

Works with the Apify API, schedules, webhooks, Make, Zapier, n8n, and AI agents via MCP.