#!/usr/bin/env python3
"""
Batch Markdown to PDF Converter with Mermaid Support
Processes all .md files in the current directory that don't have corresponding PDFs
"""
import sys
import os
import asyncio
import subprocess
from pathlib import Path
import glob
def install_dependencies():
"""Install required dependencies"""
try:
import playwright
import markdown
return True
except ImportError:
print("Installing required packages...")
try:
subprocess.check_call([sys.executable, "-m", "pip", "install", "playwright", "markdown"])
subprocess.check_call([sys.executable, "-m", "playwright", "install", "chromium"])
return True
except Exception as e:
print(f"Failed to install dependencies: {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 enhanced 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 initial content load
await page.wait_for_timeout(2000)
# Check for and wait for Mermaid diagrams
try:
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 (Mermaid renders as SVG)
await page.wait_for_selector('svg[id^="mermaid"], .mermaid svg', timeout=15000)
# Additional wait to ensure all diagrams are fully rendered
await page.wait_for_timeout(2000)
print(f" ā
All Mermaid diagrams rendered successfully")
else:
print(f" ā¹ļø No Mermaid diagrams detected")
except Exception as e:
print(f" ā ļø Mermaid rendering issue: {e}")
# Generate PDF with page break support
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 find_files_to_convert():
"""Find all .md files that don't have corresponding PDFs"""
md_files = glob.glob("*.md")
files_to_convert = []
for md_file in md_files:
base_name = Path(md_file).stem
pdf_file = f"{base_name}.pdf"
if not os.path.exists(pdf_file):
files_to_convert.append(base_name)
return files_to_convert
def main():
"""Main batch conversion process"""
if not install_dependencies():
print("ā Could not install required dependencies")
return False
files_to_convert = find_files_to_convert()
if not files_to_convert:
print("ā
All Markdown files already have corresponding PDFs!")
return True
print(f"š Batch converting {len(files_to_convert)} Markdown files to PDF with Mermaid diagrams...")
print("=" * 70)
print(f"Files to convert: {', '.join(files_to_convert)}")
print("=" * 70)
success_count = 0
for file_base in files_to_convert:
md_file = f"{file_base}.md"
html_file = f"{file_base}.html"
pdf_file = f"{file_base}.pdf"
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")
print("\n" + "=" * 70)
print(f"šÆ Batch conversion complete!")
print(f"ā
Successfully converted {success_count}/{len(files_to_convert)} files")
print(f"š All Markdown files now have PDF versions with:")
print(f" ā¢ Properly rendered Mermaid diagrams")
print(f" ā¢ Professional A4 formatting (0.75\" margins)")
print(f" ā¢ Print-optimized styling")
print(f" ā¢ Page break optimization")
return success_count > 0
if __name__ == "__main__":
main()