#!/usr/bin/env python3
"""
Simple Markdown to PDF Converter
Converts updated Markdown files to HTML then PDF with Mermaid support
"""
import sys
import os
import asyncio
import subprocess
from pathlib import Path
def install_playwright():
"""Install playwright if needed"""
try:
import playwright
return True
except ImportError:
print("Installing playwright...")
try:
subprocess.check_call([sys.executable, "-m", "pip", "install", "playwright"])
subprocess.check_call([sys.executable, "-m", "playwright", "install", "chromium"])
return True
except Exception as e:
print(f"Failed to install playwright: {e}")
return False
def install_markdown():
"""Install markdown if needed"""
try:
import markdown
return True
except ImportError:
print("Installing markdown...")
try:
subprocess.check_call([sys.executable, "-m", "pip", "install", "markdown"])
return True
except Exception as e:
print(f"Failed to install markdown: {e}")
return False
def convert_markdown_to_html(md_file, html_file):
"""Convert Markdown to HTML with Mermaid support"""
try:
import markdown
# Read markdown content
with open(md_file, 'r', encoding='utf-8') as f:
md_content = f.read()
# Basic markdown conversion
md = markdown.Markdown(extensions=['extra', 'codehilite', 'toc'])
html_content = md.convert(md_content)
# Create full HTML document with Mermaid support
full_html = f"""
{Path(md_file).stem}
{html_content}
"""
# Write HTML file
with open(html_file, 'w', encoding='utf-8') as f:
f.write(full_html)
print(f" ā
Converted {md_file} to HTML")
return True
except Exception as e:
print(f" ā Error converting {md_file}: {e}")
return False
async def convert_html_to_pdf(html_file, pdf_file):
"""Convert HTML to PDF using Playwright"""
try:
from playwright.async_api import async_playwright
async with async_playwright() as p:
browser = await p.chromium.launch()
page = await browser.new_page()
# Load HTML file
file_path = Path(html_file).resolve()
await page.goto(f"file://{file_path}")
# Wait for content to load and Mermaid to process
await page.wait_for_timeout(3000)
# Check for Mermaid diagrams and wait for them to render
try:
# First check if there are mermaid divs
mermaid_count = await page.evaluate("document.querySelectorAll('.mermaid').length")
if mermaid_count > 0:
print(f" š Found {mermaid_count} Mermaid diagram(s), waiting for rendering...")
# Wait for SVG elements to appear
await page.wait_for_selector('svg[id^="mermaid"], .mermaid svg', timeout=10000)
print(f" ā
Mermaid diagrams rendered successfully")
else:
print(f" ā¹ļø No Mermaid diagrams detected")
except Exception as e:
print(f" ā ļø Mermaid rendering timeout or error: {e}")
# Generate PDF
await page.pdf(
path=pdf_file,
format='A4',
margin={
'top': '0.75in',
'right': '0.75in',
'bottom': '0.75in',
'left': '0.75in'
},
print_background=True,
prefer_css_page_size=True,
display_header_footer=False
)
await browser.close()
print(f" ā
Generated PDF: {pdf_file}")
return True
except Exception as e:
print(f" ā Error generating PDF: {e}")
return False
def main():
"""Main conversion process"""
if not install_playwright() or not install_markdown():
print("ā Could not install required dependencies")
return False
files = [
"executive-brief-enhanced-final",
"research-proposal-enhanced-final",
"architectural-vision-enhanced-final"
]
print("š Converting updated Markdown files to PDF...")
print("=" * 60)
success_count = 0
for file_base in files:
md_file = f"{file_base}.md"
html_file = f"{file_base}.html"
pdf_file = f"{file_base}.pdf"
if os.path.exists(md_file):
print(f"\nš Processing {md_file}...")
# Convert MD to HTML
if convert_markdown_to_html(md_file, html_file):
# Convert HTML to PDF
if asyncio.run(convert_html_to_pdf(html_file, pdf_file)):
success_count += 1
size_kb = os.path.getsize(pdf_file) / 1024
print(f" š PDF size: {size_kb:.1f} KB")
else:
print(f"ā ļø {md_file} not found")
print("\n" + "=" * 60)
print(f"šÆ Conversion complete!")
print(f"ā
Successfully converted {success_count}/{len(files)} files")
print(f"š Your updated Markdown edits are now in PDF format!")
return success_count > 0
if __name__ == "__main__":
main()