#!/usr/bin/env python3
"""Convert a PDF to a self-contained HTML presentation.
Each page is rendered as a PNG image (via pdftoppm) and base64-embedded
into a single HTML file with slide navigation (arrows, swipe, click).
Requirements: poppler-utils (pdftoppm)
Usage: python3 convert-pdf.py input.pdf [output.html]
"""
import base64
import glob
import os
import subprocess
import sys
import tempfile
from pathlib import Path
def convert(pdf_path: str, output_path: str | None = None, dpi: int = 150):
pdf_path = str(Path(pdf_path).resolve())
if not Path(pdf_path).exists():
print(f"Error: {pdf_path} not found")
sys.exit(1)
# Check for pdftoppm
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)
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:
b64 = base64.b64encode(f.read()).decode()
slides_html.append(
f''
f''
f'
'
f'