from curl_cffi import requests as req
from bs4 import BeautifulSoup
import html2text

url = 'https://www.firecrawl.dev/'

# Fetch HTML content
response = req.get(url)
soup = BeautifulSoup(response.text, 'html.parser')

# Optional: Clean up unwanted tags
for tag in soup(['script', 'style', 'noscript', 'svg']):
    tag.decompose()

# Extract cleaned HTML
clean_html = str(soup)

# Convert to Markdown
markdown = html2text.html2text(clean_html)

# Output
print(markdown)