Ad-hoc download trailers for movies in given directories

adhoc-trailers.py

#!/volume1/@appstore/python3/bin/python3

import logging
import os
import subprocess
from os import listdir
from os.path import isfile, join
from xml.dom import minidom
import locale

import requests  # not standard

TMDB_API_KEY = "YOUR_TMDB_API_KEY"
LANG = ['en', 'fr', 'jp']
LOC = "en_US.utf8"
EXTRAS = {
    # Map the Type from TMDB API to the sub-folder
    # You can remove the ones you don't want
    "Trailer": "Trailers",
    "Featurette": "Featurettes",
    "Behind the Scenes": "Behind The Scenes",
    "Deleted Scene": "Deleted Scenes",
    "Clip": "Scenes",
    "Interview": "Interviews"
}

DIRECTORIES = (
    '/volume1/WD_Red_02/Media/Movies',
    '/volume1/WD_Red_02/Media/Movies_JP',
    '/volume1/WD_Red_02/Media/Films',
    '/volume2/WD_Red_01/Media/Anime_Movies',
    '/volume2/WD_Red_01/Media/Movies',
    '/volume2/WD_Red_01/Media/Movies_JP',
    '/volume2/WD_Red_01/Media/Movies_Music',
    '/volume2/WD_Red_01/Media/Films'
)

locale.setlocale(locale.LC_ALL, LOC)

FORMAT = '%(asctime)-15s %(levelname)-8s %(message)s'
logging.basicConfig(format=FORMAT)
logger = logging.getLogger('adhoc-trailer')
logger.setLevel('DEBUG')

def get_immediate_subdirectories(a_dir):
    return [name for name in os.listdir(a_dir)
            if os.path.isdir(os.path.join(a_dir, name))]

for root in DIRECTORIES:
    for directory in get_immediate_subdirectories(root):
        title = directory
        tmdbId = ''
        full_directory = join(root, directory)
        for file in [f for f in listdir(full_directory) if isfile(join(full_directory, f))]:
            if tmdbId:
                break
            if file.endswith('.nfo') and not file.endswith('.orig.nfo'):
                nfo_path = join(full_directory, file)
                try:
                    mydoc = minidom.parse(nfo_path)
                except:
                    continue
                if mydoc:
                    items = mydoc.getElementsByTagName('movie')
                    if items:
                        movie = items[0]
                        tmdbIdNode = movie.getElementsByTagName('tmdbId')
                        if tmdbIdNode:
                            tmdbId = tmdbIdNode[0].firstChild.data
                        else:
                            uniqueidRoot = movie.getElementsByTagName('uniqueid')
                            if uniqueidRoot:
                                for uniqueidNode in uniqueidRoot:
                                    if uniqueidNode.attributes['type'].value == 'tmdb':
                                        tmdbId = uniqueidNode.firstChild.data
        if tmdbId:
            logger.debug('%s --> %s' % (title, tmdbId))
            for lang in LANG:
                url = 'https://api.themoviedb.org/3/movie/%s/videos?api_key=%s&language=%s' % (tmdbId, TMDB_API_KEY, lang)
                videos = requests.get(url).json()
                if not videos:
                    logger.error('%s --> FAILED getting the %s videos' % (title, lang))
                    continue
                if 'results' not in videos:
                    if 'status_message' in videos:
                        logger.error('%s --> %s: %s' % (title, lang, videos['status_message']))
                    else:
                        logger.error('%s --> %s: no results' % (title, lang))
                    continue
                if videos['results']:
                    for video in videos['results']:
                        if 'type' in video and video['type'] in EXTRAS and 'name' in video and 'key' in video and 'site' in video and video['site'] == 'YouTube':
                            plex_folder = EXTRAS[video['type']]
                            plex_folder_path = join(full_directory, plex_folder)
                            if not os.path.isdir(plex_folder_path):
                                os.mkdir(plex_folder_path)
                            output_filename = video['name'].replace("/", "", 100)
                            #output_filename = video['name'].translate ({ord(c): " " for c in "!@#$%^&*()[]{};:,./<>?\|`~-=_+"})
                            if not any(fname.startswith(output_filename) for fname in os.listdir(plex_folder_path)):
                                logger.info('Downloading %s %s %s %s' % (title, plex_folder, lang, output_filename))
                                output_filepath = '%s.%%(ext)s' % join(plex_folder_path, output_filename)
                                youtube_output = subprocess.run(['youtube-dl', video['key'], '--output', output_filepath, '--all-subs'])
                                if youtube_output.returncode == 0:
                                    logger.info('%s --> %s / (%s) %s' % (title, plex_folder, lang, output_filename))
                                else:
                                    logger.error('%s --> %s / (%s) %s !!! YOUTUBE-DL ERROR !!!' % (title, plex_folder, lang, output_filename))
                            else:
                                logger.debug('%s --> %s / (%s) %s ALREADY EXISTS' % (title, plex_folder, lang, output_filename))
                else:
                    logger.warning('%s --> %s: no results' % (title, lang))
        else:
            logger.warning('%s --> !!! TMDB ID NOT FOUND !!!' % directory)