app.py

from flask import Flask, jsonify, render_template, request, Response, abort
import os
import urllib.parse
from hf_scrapper import download_and_cache_file, get_system_proxies
from indexer import indexer
from tvdb import fetch_and_cache_json
from dotenv import load_dotenv
import json
import re
from threading import Thread

load_dotenv()
INDEX_FILE = os.getenv("INDEX_FILE")
TOKEN = os.getenv("TOKEN")
REPO = os.getenv("REPO")
CACHE_DIR = os.getenv("CACHE_DIR")

# Ensure CACHE_DIR exists
if not os.path.exists(CACHE_DIR):
    os.makedirs(CACHE_DIR)

indexer()    

if not os.path.exists(INDEX_FILE):
    raise FileNotFoundError(f"{INDEX_FILE} not found. Please make sure the file exists.")

with open(INDEX_FILE, 'r') as f:
    file_structure = json.load(f)

def prefetch_metadata():
    for item in file_structure:
        if 'contents' in item:
            for sub_item in item['contents']:
                original_title = sub_item['path'].split('/')[-1]
                media_type = 'series' if item['path'].startswith('tv') else 'movie'
                title = original_title
                year = None
                
                match = re.search(r'\((\d{4})\)', original_title)
                if match:
                    year_str = match.group(1)
                    if year_str.isdigit() and len(year_str) == 4:
                        title = original_title[:match.start()].strip()
                        year = int(year_str)
                else:
                    parts = original_title.rsplit(' ', 1)
                    if len(parts) > 1 and parts[-1].isdigit() and len(parts[-1]) == 4:
                        title = parts[0].strip()
                        year = int(parts[-1])
                
                fetch_and_cache_json(original_title, title, media_type, year)

def start_prefetching():
    prefetch_metadata()

thread = Thread(target=start_prefetching)
thread.daemon = True
thread.start()

app = Flask(__name__)

def get_film_file_path(title):
    decoded_title = urllib.parse.unquote(title)
    normalized_title = decoded_title.split(' (')[0].strip()

    for item in file_structure:
        if item['path'].startswith('films'):
            for sub_item in item['contents']:
                sub_item_title = sub_item['path'].split('/')[-1]
                normalized_sub_item_title = sub_item_title.split(' (')[0].strip()

                if normalized_title == normalized_sub_item_title:
                    for file in sub_item['contents']:
                        if file['type'] == 'file':
                            return file['path']
    return None

def get_tv_show_seasons(title):
    seasons = []
    for item in file_structure:
        if item['path'].startswith('tv'):
            for sub_item in item['contents']:
                if sub_item['type'] == 'directory' and title in sub_item['path']:
                    for season in sub_item['contents']:
                        if season['type'] == 'directory':
                            episodes = [
                                {"title": episode['path'].split('/')[-1], "path": episode['path']}
                                for episode in season['contents'] if episode['type'] == 'file'
                            ]
                            seasons.append({
                                "season": season['path'].split('/')[-1],
                                "episodes": episodes
                            })
                    return seasons
    return []

def download_film_if_needed(file_path):
    cached_file_path = os.path.join(CACHE_DIR, file_path)
    if not os.path.exists(cached_file_path):
        file_url = f"https://huggingface.co/{REPO}/resolve/main/{file_path}"
        success = download_and_cache_file(file_url, TOKEN, cached_file_path, proxies=get_system_proxies())
        if not success:
            abort(404, description="File not found or failed to download.")
    return cached_file_path

@app.route('/')
def home():
    return render_template('index.html')

@app.route('/films')
def films():
    return render_template('films.html')

@app.route('/api/films')
def list_films():
    films = [item for item in file_structure if item['path'].startswith('films')]
    return jsonify([sub_item for film in films for sub_item in film['contents']])

@app.route('/tv')
def tv_shows():
    return render_template('tvshows.html')

@app.route('/api/tv')
def list_tv():
    tv_shows = [item for item in file_structure if item['path'].startswith('tv')]
    return jsonify([sub_item for show in tv_shows for sub_item in show['contents']])

@app.route('/api/film/<path:title>')
def film_page(title):
    title = urllib.parse.unquote(title)
    film_file_path = get_film_file_path(title)
    if not film_file_path:
        return jsonify({'error': 'Film not found'}), 404
    
    json_cache_path = os.path.join(CACHE_DIR, f"{urllib.parse.quote(title)}.json")
    if os.path.exists(json_cache_path):
        with open(json_cache_path, 'r') as f:
            metadata = json.load(f)
    else:
        return jsonify({'error': 'Metadata not found'}), 404
    
    cached_url = f"/cached_films/{urllib.parse.quote(title)}"
    return jsonify({
        'metadata': metadata,
        'cached_url': cached_url
    })

@app.route('/api/tv/<path:show_title>')
def tv_page(show_title):
    show_title = urllib.parse.unquote(show_title)
    seasons = get_tv_show_seasons(show_title)
    if not seasons:
        return jsonify({'error': 'TV show not found'}), 404
    
    json_cache_path = os.path.join(CACHE_DIR, f"{urllib.parse.quote(show_title)}.json")
    if os.path.exists(json_cache_path):
        with open(json_cache_path, 'r') as f:
            metadata = json.load(f)
    else:
        return jsonify({'error': 'Metadata not found'}), 404
    
    return jsonify({
        'metadata': metadata,
        'seasons': seasons
    })

@app.route('/get_metadata')
def get_metadata():
    title = request.args.get('title')
    if not title:
        return jsonify({'error': 'No title provided'}), 400
    
    json_cache_path = os.path.join(CACHE_DIR, f"{urllib.parse.quote(title)}.json")
    
    if os.path.exists(json_cache_path):
        with open(json_cache_path, 'r') as f:
            data = json.load(f)
        return jsonify(data)
    
    return jsonify({'error': 'Metadata not found'}), 404

@app.route('/api/cache_film/<path:title>')
def cache_film(title):
    title = urllib.parse.unquote(title)
    film_file_path = get_film_file_path(title)
    if not film_file_path:
        return jsonify({'error': 'Film not found'}), 404
    
    cached_file_path = os.path.join(CACHE_DIR, film_file_path)
    if not os.path.exists(cached_file_path):
        file_url = f"https://huggingface.co/{REPO}/resolve/main/{film_file_path}"
        success = download_and_cache_file(file_url, TOKEN, cached_file_path, proxies=get_system_proxies())
        if not success:
            return jsonify({'error': 'Failed to cache film'}), 500
    
    return jsonify({'success': True})

@app.route('/film/<path:title>')
def film_details(title):
    return render_template('film_details_page.html', title=title)

@app.route('/cached_films/<path:title>')
def serve_cached_film(title):
    cached_file_path = os.path.join(CACHE_DIR, urllib.parse.unquote(title))
    if not os.path.exists(cached_file_path):
        return jsonify({'error': 'Film not cached'}), 404
    
    def generate():
        with open(cached_file_path, 'rb') as f:
            while chunk := f.read(8192):
                yield chunk

    return Response(generate(), mimetype='video/mp4')

if __name__ == '__main__':
    app.run(debug=True, host="0.0.0.0", port=7860)