Cataloguer/scripts/add_item.py

# Script to add a new item to the log

from datetime import datetime
from dotenv import load_dotenv
import json
import logging
import os
import re
import requests
from urllib.request import urlopen

logging.basicConfig(filename='./logs/run.log', encoding='utf-8', level=logging.DEBUG)

load_dotenv()

TMDB_API_KEY = os.getenv('TMDB_API_KEY')
TVDB_API_KEY = os.getenv('TVDB_API_KEY')
OPENLIBRARY_API_KEY = os.getenv('OPENLIBRARY_API_KEY')

if "" == TMDB_API_KEY: logging.error("TMDB API key not found")
if "" == TVDB_API_KEY: logging.error("TVDB API key not found")
if "" == OPENLIBRARY_API_KEY: logging.error("OpenLibrary API key not found")


def add_item_to_log(item_id, media_type, log):
    """Add a film, book, TV series or TV episode to a log"""
    logging.info(f"Processing {item_id}…")

    item = import_by_id(item_id, media_type)

    if log in ['log', 'current']:
        if 'log' == log:
            date_watched = ''
            while re.search('[0-9]{4}-[0-9]{2}-[0-9]{2}', date_watched) is None:
                date_watched = input("Enter date watched [YYYY-MM-DD, t for today]:")
                if 't' == date_watched: date_watched = datetime.today().strftime('%Y-%m-%d')
            item['date_watched'] = date_watched

        elif 'current' == log:
            date_started = ''
            while re.search('[0-9]{4}-[0-9]{2}-[0-9]{2}', date_started) is None:
                date_started = input("Enter date started [YYYY-MM-DD, t for today]:")
                if 't' == date_started: date_started = datetime.today().strftime('%Y-%m-%d')
            item['date_started'] = date_started

        is_rewatch = ''
        while is_rewatch not in ['y', 'n']:
            is_rewatch = input("Is this a rewatch? [y/n]:")
            if 'y' == is_rewatch: item['is_rewatch'] = True
        item['added_by_id'] = item_id

    comments = input("Enter comments (optional):")
    if '' != comments: item['comments'] = comments

    # Validation step
    correct = ''
    print(f"{media_type} data to add:\n")
    print(json.dumps(item, indent=4))
    if 'y' != input("\nDoes this look correct? [y]: "): return

    # Save changes
    logging.info(f"Adding {media_type} to {log}…")

    with open(f"./data/{media_type}/{log}.json", "r") as log_file:
        log_items = json.load(log_file)

    log_items.insert(0, item)

    with open(f"./data/{media_type}/{log}.json", "w") as log_file:
       json.dump(log_items, log_file, indent=4)

    logging.info(f"Added {media_type} {item_id} to {log}")


def import_by_id(import_id, media_type):
    if media_type in ['films', 'tv-series']:
        return import_from_imdb_by_id(import_id, media_type)
    elif media_type in ['tv-episodes']:
        return #import_from_tvdb_by_id(import_id, media_type)
    elif media_type in ['books']:
        return #import_from_openlibrary_by_id(import_id, media_type)


def import_from_imdb_by_id(imdb_id, media_type):
    """Retrieve a film, TV show or TV episode from TMDB using an IMDB ID"""

    api_url = f"https://api.themoviedb.org/3/find/{imdb_id}"

    # Sending API request
    response = requests.get(
        api_url,
        params={
            'external_source': 'imdb_id'
        },
        headers={'Authorization': f"Bearer {TMDB_API_KEY}"}
    )

    # Process the response
    if (200 == response.status_code):
        logging.info(response.status_code)
    elif (429 == response.status_code):
        time.sleep(2)
        import_from_imdb_by_id(imdb_id, media_type)
        return
    else:
        logging.error(response.text)

    if ('films' == media_type): results_key = 'movie_results'
    elif ('tv-episodes' == media_type): results_key = 'TODO'
    elif ('tv-series' == media_type): results_key = 'tv_results'

    response_data = json.loads(response.text)[results_key]

    if 1 == len(response_data):
        item = response_data[0]
    elif 0 == len(response_data):
        logging.error(f"Returned no results for {imdb_id}")
        return
    elif 1 < len(response_data):
        logging.warning(f"Returned more than one {media_type} for ID {imdb_id}")
        print(f"Returned more than one {media_type} for ID {imdb_id}:\n")
        print(json.dumps(response_data, indent=4))
        idx = input("\nEnter the index of the result to use: ")
        try:
            item = response_data[int(idx)]
        except:
            logging.error("Index invalid!")
            print("Index invalid!")

    # Modify the returned result to add additional data
    return cleanup_result(item)


def cleanup_result(item):
    """Process a film  or TV episode returned by the TMDB API by removing unnecessary fields and adding others"""

    for field_name in ['adult', 'backdrop_path', 'episode_type', 'genre_ids', 'media_type', 'origin_country', 'popularity', 'production_code', 'runtime', 'still_path', 'video', 'vote_average', 'vote_count']:
        if field_name in item: del item[field_name]

    # TODO - select automatically
    title_key = 'name'

    if f"original_{title_key}" in item and 'original_language' in item:
        if item[f"original_{title_key}"] == item[title_key] and item['original_language'] == 'en':
            del item[f"original_{title_key}"], item['original_language']

    if 'date_added' not in item: item['date_added'] = datetime.today().strftime('%Y-%m-%d')

    return item


def main():
    media_type = ''
    while media_type not in ['films', 'tv-episodes', 'tv-series', 'books']:
        media_type = input("Select media type [films|tv-episodes|tv-series|books]:")

        if 'films' == media_type:
            log = ''
            while log not in ['log', 'wishlist']:
                log = input ("Enter log to update [log|wishlist]:")

            imdb_id = ''
            while re.search("tt[0-9]+", imdb_id) is None:
                imdb_id = input("Enter IMDB ID:")

            add_item_to_log(imdb_id, media_type, log)

        elif 'books' == media_type:
            log = ''
            while log not in ['log', 'current', 'wishlist']:
                log = input ("Enter log to update [log|current|wishlist]:")

            isbn = ''
            while re.search("[0-9]+", isbn) is None:
                isbn = input("Enter ISBN:")

        elif 'tv-episodes' == media_type:
            imdb_id = ''
            while re.search("tt[0-9]+", imdb_id) is None:
                imdb_id = input("Enter IMDB ID:")

            add_item_to_log(imdb_id, media_type, 'log')

        elif 'tv-series' == media_type:
            log = ''
            while log not in ['log', 'current', 'wishlist']:
                log = input ("Enter log to update [log|current|wishlist]:")

            imdb_id = ''
            while re.search("tt[0-9]+", imdb_id) is None:
                imdb_id = input("Enter IMDB ID:")

            add_item_to_log(imdb_id, media_type, log)


if __name__ == "__main__":
    main()