generate_site.py

#!/usr/bin/env python3
"""
Static site generator for podcast episodes.
Reads episode metadata from local JSON files and generates a Hebrew RTL website.
"""

import json
import re
import shutil
from datetime import datetime
from html import escape
from pathlib import Path

AUDIO_BASE_URL = "https://rgw.rke2.hasadna.org.il/podcasts/"
METADATA_DIR = Path("metadata")
OUTPUT_DIR = Path("site")
TEMPLATES_DIR = Path("templates")


def parse_date(date_str: str) -> datetime:
    """Parse RFC 2822 date format."""
    # Example: "Fri, 29 Jun 2018 08:01:05 +0000"
    try:
        # Remove timezone for parsing
        date_str_clean = re.sub(r"\s*[+-]\d{4}$", "", date_str)
        return datetime.strptime(date_str_clean, "%a, %d %b %Y %H:%M:%S")
    except ValueError:
        return datetime.now()


def format_date_hebrew(dt: datetime) -> str:
    """Format date in Hebrew style."""
    months = [
        "ינואר", "פברואר", "מרץ", "אפריל", "מאי", "יוני",
        "יולי", "אוגוסט", "ספטמבר", "אוקטובר", "נובמבר", "דצמבר"
    ]
    return f"{dt.day} {months[dt.month - 1]} {dt.year}"


def load_template(name: str) -> str:
    """Load a template file."""
    return (TEMPLATES_DIR / name).read_text(encoding="utf-8")


def render_template(template: str, **kwargs) -> str:
    """Simple template rendering with {{variable}} placeholders."""
    result = template
    for key, value in kwargs.items():
        result = result.replace(f"{{{{{key}}}}}", str(value))
    return result


def load_episodes() -> list[dict]:
    """Load episode metadata from local JSON files."""
    episodes = []
    json_files = list(METADATA_DIR.glob("*.json"))
    print(f"Found {len(json_files)} episodes")

    for json_file in json_files:
        print(f"  Loading: {json_file.name}")
        try:
            metadata = json.loads(json_file.read_text(encoding="utf-8"))
            dt = parse_date(metadata.get("pubDate", ""))
            episodes.append({
                "guid": metadata.get("guid", json_file.stem),
                "title": metadata.get("title", "Untitled"),
                "description": metadata.get("description", ""),
                "date": dt,
                "date_formatted": format_date_hebrew(dt),
            })
        except Exception as e:
            print(f"    Error: {e}")

    return episodes


def generate_html(episodes: list[dict]) -> str:
    """Generate the HTML page."""
    # Sort episodes by date (newest first)
    episodes.sort(key=lambda e: e["date"], reverse=True)

    # Load templates
    index_template = load_template("index.html")
    episode_template = load_template("episode.html")

    # Render episodes
    episodes_html = ""
    for ep in episodes:
        mp3_url = AUDIO_BASE_URL + ep["guid"] + ".mp3"
        description = ep.get("description", "")
        # Clean HTML tags from description for preview
        description_text = re.sub(r"<[^>]+>", "", description)

        episodes_html += render_template(
            episode_template,
            guid=ep["guid"],
            title=escape(ep["title"]),
            date=ep["date_formatted"],
            description=escape(description_text),
            audio_url=escape(mp3_url),
        )

    # Render main page
    return render_template(
        index_template,
        episode_count=len(episodes),
        episodes=episodes_html,
    )


def main():
    print("Loading episodes...")
    episodes = load_episodes()

    print("Generating HTML...")
    html = generate_html(episodes)

    # Create output directory
    OUTPUT_DIR.mkdir(exist_ok=True)

    # Write HTML file
    output_file = OUTPUT_DIR / "index.html"
    output_file.write_text(html, encoding="utf-8")

    # Copy CSS file
    shutil.copy(TEMPLATES_DIR / "style.css", OUTPUT_DIR / "style.css")

    print(f"Done! Files saved to: {OUTPUT_DIR}/")


if __name__ == "__main__":
    main()