#!/usr/bin/env python3
"""Convert a PDF to an HTML presentation.
Each page is rendered as a PNG image (via pdftoppm). Supports external assets
mode for large files to avoid huge single-file HTML.
Requirements: poppler-utils (pdftoppm)
"""
import argparse
import base64
import glob
import os
import subprocess
import sys
import tempfile
from pathlib import Path
def get_page_count(pdf_path):
"""Get page count using pdfinfo if available."""
try:
result = subprocess.run(["pdfinfo", pdf_path], capture_output=True, text=True)
for line in result.stdout.splitlines():
if line.startswith("Pages:"):
return int(line.split(":")[1].strip())
except:
pass
return None
def convert(pdf_path: str, output_path: str | None = None, dpi: int = 150, external_assets=None):
pdf_path = str(Path(pdf_path).resolve())
if not Path(pdf_path).exists():
print(f"Error: {pdf_path} not found")
sys.exit(1)
if subprocess.run(["which", "pdftoppm"], capture_output=True).returncode != 0:
print("Error: pdftoppm not found. Install poppler-utils:")
print(" apt install poppler-utils # Debian/Ubuntu")
print(" brew install poppler # macOS")
sys.exit(1)
file_size_mb = os.path.getsize(pdf_path) / (1024 * 1024)
if file_size_mb > 150:
print(f"WARNING: PDF is {file_size_mb:.0f}MB — conversion may be slow and memory-intensive.")
page_count = get_page_count(pdf_path)
# Auto-detect external assets mode
if external_assets is None:
external_assets = file_size_mb > 20 or (page_count is not None and page_count > 50)
if external_assets:
print(f"Auto-enabling external assets mode (file: {file_size_mb:.1f}MB, pages: {page_count or 'unknown'})")
output = output_path or str(Path(pdf_path).with_suffix('.html'))
output_dir = Path(output).parent
if external_assets:
assets_dir = output_dir / "assets"
assets_dir.mkdir(parents=True, exist_ok=True)
with tempfile.TemporaryDirectory() as tmpdir:
prefix = os.path.join(tmpdir, "page")
result = subprocess.run(
["pdftoppm", "-png", "-r", str(dpi), pdf_path, prefix],
capture_output=True, text=True
)
if result.returncode != 0:
print(f"Error converting PDF: {result.stderr}")
sys.exit(1)
pages = sorted(glob.glob(f"{prefix}-*.png"))
if not pages:
print("Error: No pages rendered from PDF")
sys.exit(1)
slides_html = []
for i, page_path in enumerate(pages, 1):
with open(page_path, "rb") as f:
page_bytes = f.read()
if external_assets:
img_name = f"img-{i:03d}.png"
(assets_dir / img_name).write_bytes(page_bytes)
src = f"assets/{img_name}"
else:
b64 = base64.b64encode(page_bytes).decode()
src = f"data:image/png;base64,{b64}"
slides_html.append(
f''
f''
f'
'
f'