URL to Markdown Converter

Paste any website URL and get the main content of the page as clean Markdown. ParseJet strips navigation, ads, cookie banners, and boilerplate — leaving just the article with headings, lists, tables, and links intact. Perfect for feeding web pages to LLMs, building knowledge bases, or migrating content.

Drop a file here or browse

PDF, DOCX, XLSX, images, audio, video, and more

Free — 3 requests/day, no signup. for 300 credits/month free.

How it works

Paste a URL

Drop in any public webpage link — an article, documentation page, blog post, or product page.

Main-content extraction

ParseJet fetches the page, identifies the main content, and removes navigation, sidebars, ads, and footers. What remains is converted to structured Markdown.

Copy or automate

Copy the Markdown output, or call the API to convert URLs to Markdown in bulk from your own code.

Key features

What makes this url to markdown stand out.

Boilerplate removal

Navigation menus, cookie banners, ads, share buttons, and footers are stripped automatically. You get the content, not the chrome around it.

Structure preserved

Headings, lists, tables, code blocks, and links in the page are mapped to proper Markdown syntax — not flattened into plain text.

Works on any page

News articles, documentation, blog posts, wikis, product pages — the extractor adapts to the page layout automatically.

LLM-ready output

Clean Markdown is the ideal input format for Claude, ChatGPT, and RAG pipelines: structured, compact, and free of HTML noise that wastes tokens.

Bulk conversion via API

Convert thousands of URLs to Markdown with a simple loop. One HTTP endpoint, no headless browser to run, no scraping infrastructure to maintain.

Metadata included

Each response includes the page title and source type alongside the Markdown text — useful for indexing and citations.

Use cases

Common scenarios where this tool saves you time.

LLM context from the web

Turn any web page into Markdown before passing it to Claude or ChatGPT. Structured Markdown gives the model cleaner context than raw HTML or copy-pasted text.

RAG and knowledge bases

Ingest documentation sites, help centers, and blogs into your vector database as clean Markdown documents with headings intact for better chunking.

AI agent web reading

Give your agent a reliable "read this URL" tool. One API call returns the page as Markdown — no scraping code, proxies, or HTML parsing in your agent loop.

Content migration and archiving

Save articles and docs as Markdown files for Obsidian, Notion, or a static site generator. The output is ready to commit to a Git repository.

Automate with the API

Use the same tool programmatically. Works with any language — just HTTP.

cURL

# Convert any URL to Markdown
curl -X POST https://api.parsejet.com/v1/parse/webpage \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com/article"}'

# Response: { "text": "# Article Title\n\nMain content as Markdown...", "title": "...", "source_type": "webpage" }

Python

import httpx

# Bulk: convert a list of URLs to Markdown files
urls = [
    "https://example.com/docs/getting-started",
    "https://example.com/docs/api-reference",
]

for url in urls:
    resp = httpx.post(
        "https://api.parsejet.com/v1/parse/webpage",
        headers={"Authorization": "Bearer YOUR_API_KEY"},
        json={"url": url},
    )
    data = resp.json()
    filename = url.rstrip("/").split("/")[-1] + ".md"
    with open(filename, "w", encoding="utf-8") as f:
        f.write(data["text"])
    print(f"Saved {filename}")

JavaScript

// Convert a URL to Markdown
const res = await fetch("https://api.parsejet.com/v1/parse/webpage", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ url: "https://example.com/article" }),
});
const { text, title } = await res.json();
console.log(text); // Clean Markdown of the page's main content

Want to automate this?

ParseJet API gives you the same parsing power via a single HTTP endpoint. No ffmpeg, no poppler, no tesseract — just one API call.

curl -X POST https://api.parsejet.com/v1/parse/auto/url \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com"}'

Read API Docs

Frequently asked questions

How do I convert a URL to Markdown?

Paste the URL in the tool above and click parse. ParseJet fetches the page, extracts the main content, and returns it as clean Markdown. For automation, POST the URL to /v1/parse/webpage.

Can I convert a whole website to Markdown?

The tool converts one page per request. To convert an entire website, loop over your URL list (from the sitemap, for example) and call the API for each page — see the Python example above for bulk conversion.

Does it remove ads and navigation?

Yes. ParseJet identifies the main content of the page and strips navigation menus, sidebars, ads, cookie banners, and footers automatically.

Is there a URL to Markdown API?

Yes. POST /v1/parse/webpage with a JSON body containing the URL. The response includes the Markdown text and page title. Free API keys include 300 requests per month.

Are links and images preserved?

Links in the content are converted to Markdown link syntax with their original URLs. Image references in the main content are preserved as Markdown image tags pointing to the source.

Is it free?

Yes. You get 3 free conversions per day with no signup. Create a free account for 300 credits per month. Paid plans start at $19/month for bulk conversion workloads.

Start extracting text for free

No signup required. Parse your first file in seconds.

View Pricing