marcus-web/scripts/new_movie.py

#!/usr/bin/env python3
"""
Create a new movie post from an IMDB ID.

Usage:
    python scripts/new_movie.py tt1234567
    python scripts/new_movie.py tt1234567 --title "Custom Title"
    python scripts/new_movie.py https://www.imdb.com/title/tt1234567/

This fetches all metadata (title, year, runtime, director, poster) and creates
a ready-to-edit draft post.
"""

import argparse
import re
import subprocess
import sys
from datetime import datetime, timezone
from pathlib import Path

import requests

# Configuration
TMDB_API_KEY = "9e36fdcf70a4918e0dce327acc437dff"

# Paths
SCRIPT_DIR = Path(__file__).parent
PROJECT_ROOT = SCRIPT_DIR.parent
CONTENT_DIR = PROJECT_ROOT / "content" / "posts"
IMAGES_DIR = PROJECT_ROOT / "static" / "images" / "posters"


def extract_imdb_id(input_str):
    """Extract IMDB ID from URL or raw ID."""
    match = re.search(r'(tt\d+)', input_str)
    if match:
        return match.group(1)
    return None


def find_movie_by_imdb(imdb_id):
    """Find TMDB movie by IMDB ID."""
    url = f"https://api.themoviedb.org/3/find/{imdb_id}"
    params = {
        "api_key": TMDB_API_KEY,
        "external_source": "imdb_id"
    }
    resp = requests.get(url, params=params, timeout=10)
    resp.raise_for_status()
    data = resp.json()

    results = data.get("movie_results", [])
    if results:
        return results[0]
    return None


def get_movie_details(tmdb_id):
    """Get full movie details from TMDB."""
    url = f"https://api.themoviedb.org/3/movie/{tmdb_id}"
    params = {
        "api_key": TMDB_API_KEY,
        "append_to_response": "credits"
    }
    resp = requests.get(url, params=params, timeout=10)
    resp.raise_for_status()
    return resp.json()


def get_directors(credits):
    """Extract director names from credits."""
    crew = credits.get("crew", [])
    directors = [p["name"] for p in crew if p.get("job") == "Director"]
    return directors


def slugify(title):
    """Convert title to URL-friendly slug."""
    slug = title.lower()
    slug = re.sub(r"[^a-z0-9\s-]", "", slug)
    slug = re.sub(r"[\s_]+", "-", slug)
    slug = re.sub(r"-+", "-", slug)
    return slug.strip("-")


def download_poster(poster_path, filename):
    """Download and save poster. Returns local path."""
    if not poster_path:
        return ""

    # w500 = 500px wide, good for 200px display on retina
    url = f"https://image.tmdb.org/t/p/w500{poster_path}"
    resp = requests.get(url, timeout=10)
    resp.raise_for_status()

    IMAGES_DIR.mkdir(parents=True, exist_ok=True)
    filepath = IMAGES_DIR / filename
    filepath.write_bytes(resp.content)

    return f"/images/posters/{filename}"


def create_post(imdb_id, details, poster_path, custom_title=None):
    """Create the Hugo post with all metadata."""
    title = custom_title or details.get("title", "Untitled")
    slug = slugify(title)
    filename = f"{slug}.md"
    filepath = CONTENT_DIR / filename

    if filepath.exists():
        print(f"Post already exists: {filepath}")
        return None

    # Download poster
    poster_url = ""
    if details.get("poster_path"):
        poster_filename = f"{slug}.jpg"
        print(f"Downloading poster...")
        poster_url = download_poster(details["poster_path"], poster_filename)

    # Extract metadata
    release_date = details.get("release_date", "")
    year = int(release_date.split("-")[0]) if release_date else ""
    runtime = details.get("runtime", "")

    credits = details.get("credits", {})
    directors = get_directors(credits)
    director_str = directors[0] if len(directors) == 1 else directors if directors else ""

    genres = [g["name"] for g in details.get("genres", [])]

    now = datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")

    # Build frontmatter
    # Using manual formatting to control output
    genres_yaml = "\n".join(f"  - {g}" for g in genres) if genres else "[]"
    if isinstance(director_str, list):
        director_yaml = "\n".join(f"  - {d}" for d in director_str)
        director_yaml = f"\n{director_yaml}"
    else:
        director_yaml = f' "{director_str}"' if director_str else ' ""'

    content = f'''---
title: '{title}'
date: {now}
draft: true
series: "Frank's Couch"
summary: ""
imdb: "{imdb_id}"
poster: "{poster_url}"
year: {year}
runtime: {runtime}
director:{director_yaml}
genres:
{genres_yaml}
tags:
  - gucci
  - ghost theater
  - marcel
  - amc-south
  - amc-lakeline
  - anticipated
  - no-expectations
  - had pizza
---
{{{{< imdbposter >}}}}

| Date watched        |                   |
|---------------------|-------------------|
| Show Time           |                   |
| Theater             |                   |
| Theater Number      |                   |
| Pizza               |                   |
| Tickets             |                   |
| Letterboxd Rating   |                   |
| Crew                |                   |

{{{{< /imdbposter >}}}}

Write your review here...

'''

    filepath.write_text(content)
    return filepath


def main():
    parser = argparse.ArgumentParser(
        description="Create a new movie post from IMDB ID",
        epilog="Example: python scripts/new_movie.py tt1234567"
    )
    parser.add_argument("imdb", help="IMDB ID or URL (e.g., tt1234567)")
    parser.add_argument("--title", help="Custom title (default: from TMDB)")
    args = parser.parse_args()

    # Extract IMDB ID
    imdb_id = extract_imdb_id(args.imdb)
    if not imdb_id:
        print(f"Invalid IMDB ID: {args.imdb}")
        print("Expected format: tt1234567 or https://www.imdb.com/title/tt1234567/")
        sys.exit(1)

    print(f"Looking up {imdb_id}...")

    # Find on TMDB
    movie = find_movie_by_imdb(imdb_id)
    if not movie:
        print(f"Movie not found for IMDB ID: {imdb_id}")
        sys.exit(1)

    tmdb_id = movie["id"]
    print(f"Found: {movie.get('title')} ({movie.get('release_date', '')[:4]})")

    # Get full details
    print("Fetching details...")
    details = get_movie_details(tmdb_id)

    # Create post
    filepath = create_post(imdb_id, details, details.get("poster_path"), args.title)

    if filepath:
        print(f"\nCreated: {filepath.relative_to(PROJECT_ROOT)}")
        print(f"IMDB: https://www.imdb.com/title/{imdb_id}/")
        print(f"\nEdit your post, then run: ./scripts/build.sh")


if __name__ == "__main__":
    main()