Rumperuu/Cataloguer
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

finish processing tv series', add python linting

Browse source
This commit is contained in:
Ben Goldsworthy 2024-01-17 22:17:29 +01:00
parent cc6e4de409
commit 33e8270afe
7 changed files with 7498 additions and 2179 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
.gitignore vendored
View file

@ -6,3 +6,4 @@ node_modules/
public/ public/
logs/ logs/
.env .env
catalogue_venv/

35
data/tv-series/log.json
View file

@ -1,4 +1,39 @@
[ [
{
"id": 2371,
"origin_country": [
"GB"
],
"overview": "Bodies is an award-winning British television medical drama produced by Hat Trick Productions for the BBC. Created by Jed Mercurio, the series began in 2004 and is based on his book Bodies. In December 2009, The Times ranked Bodies in 9th place in its list of \"Shows of the Decade\". The Guardian has ranked the series among \"The Greatest Television Dramas of All-Time\".",
"poster_path": "/7sDRMbZC5zvbE4UMjm9cw7KSj9u.jpg",
"first_air_date": "2004-06-23",
"name": "Bodies",
"date_added": "2024-01-17"
},
{
"id": 80307,
"origin_country": [
"GB"
],
"overview": "A troubled war veteran is assigned to protect a controversial politician who may be the target of a terror plot.",
"poster_path": "/5DUJTrHTRLHLCKWriPhdusQogAv.jpg",
"first_air_date": "2018-08-26",
"name": "Bodyguard",
"date_added": "2024-01-17"
},
{
"id": 890,
"origin_country": [
"JP"
],
"original_language": "ja",
"original_name": "\u65b0\u4e16\u7d00\u30a8\u30f4\u30a1\u30f3\u30b2\u30ea\u30aa\u30f3",
"overview": "At the turn of the century, the Angels returned to Earth, seeking to wipe out humanity in an apocalyptic fury. Devastated, mankind's last remnants moved underground to wait for the day when the Angels would come back to finish the job. Fifteen years later, that day has come... but this time, humanity is ready to fight back with terrifying bio-mechanical weapons known as the Evangelions. Watch as Shinji, Rei, Asuka and the rest of the mysterious shadow agency Nerv battle to save earth from total annihilation.",
"poster_path": "/y2ah9t0navXyIvoHg1uIbIHO3tt.jpg",
"first_air_date": "1995-10-04",
"name": "Neon Genesis Evangelion",
"date_added": "2024-01-17"
},
{ {
"id": 2316, "id": 2316,
"name": "The Office", "name": "The Office",

9107
data/tv-series/wishlist.json
View file

File diff suppressed because it is too large Load diff

3
package.json
View file

@ -6,7 +6,8 @@
"build": "rm -rf ./public/ && snap run hugo --templateMetrics --templateMetricsHints", "build": "rm -rf ./public/ && snap run hugo --templateMetrics --templateMetricsHints",
"deploy": "rsync -rP ./public/ ovhvps:~/catalogue/content", "deploy": "rsync -rP ./public/ ovhvps:~/catalogue/content",
"lint:json": "jsonlint ./**/*.json -s", "lint:json": "jsonlint ./**/*.json -s",
"lint:json:fix": "npm run lint:json -- -i" "lint:json:fix": "npm run lint:json -- -i",
"lint:py": "pylint ./scripts/*.py"
}, },
"devDependencies": { "devDependencies": {
"jsonlint": "^1.6.3" "jsonlint": "^1.6.3"

13
requirements.txt Normal file
View file

@ -0,0 +1,13 @@
astroid==3.0.2
black==23.12.1
click==8.1.7
dill==0.3.7
isort==5.13.2
mccabe==0.7.0
mypy-extensions==1.0.0
packaging==23.2
pathspec==0.12.1
platformdirs==4.1.0
pylint==3.0.3
python-dotenv==1.0.0
tomlkit==0.12.3

311
scripts/add_item.py
View file

@ -9,19 +9,20 @@ import re
import requests import requests
from urllib.request import urlopen from urllib.request import urlopen
def setup_logger(name = __name__):
def setup_logger(name="add_item"):
logging.root.setLevel(logging.NOTSET) logging.root.setLevel(logging.NOTSET)
logger = logging.getLogger(name) logger = logging.getLogger(name)
c_handler = logging.StreamHandler() c_handler = logging.StreamHandler()
f_handler = logging.FileHandler('./logs/run.log') f_handler = logging.FileHandler("./logs/run.log")
c_handler.setLevel(logging.INFO) c_handler.setLevel(logging.INFO)
f_handler.setLevel(logging.ERROR) f_handler.setLevel(logging.ERROR)
c_format = logging.Formatter('%(name)s - %(levelname)s - %(message)s') c_format = logging.Formatter("%(name)s - %(levelname)s - %(message)s")
f_format = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s') f_format = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
c_handler.setFormatter(c_format) c_handler.setFormatter(c_format)
f_handler.setFormatter(f_format) f_handler.setFormatter(f_format)
@ -36,11 +37,13 @@ logger = setup_logger()
load_dotenv() load_dotenv()
TMDB_API_KEY = os.getenv('TMDB_API_KEY') TMDB_API_KEY = os.getenv("TMDB_API_KEY")
TVDB_API_KEY = os.getenv('TVDB_API_KEY') TVDB_API_KEY = os.getenv("TVDB_API_KEY")
if "" == TMDB_API_KEY: logger.error("TMDB API key not found") if "" == TMDB_API_KEY:
if "" == TVDB_API_KEY: logger.error("TVDB API key not found") logger.error("TMDB API key not found")
if "" == TVDB_API_KEY:
logger.error("TVDB API key not found")
def add_item_to_log(item_id, media_type, log): def add_item_to_log(item_id, media_type, log):
@ -50,38 +53,42 @@ def add_item_to_log(item_id, media_type, log):
item = import_by_id(item_id, media_type) item = import_by_id(item_id, media_type)
if log in ['log', 'current']: if log in ["log", "current"]:
# TODO - review this when moving from one log to another # TODO - review this when moving from one log to another
if media_type in ['books', 'tv-series', 'games']: if media_type in ["books", "tv-series", "games"]:
date_started = '' date_started = ""
while re.search('[0-9]{4}-[0-9]{2}-[0-9]{2}', date_started) is None: 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]: ") date_started = input("Enter date started [YYYY-MM-DD, t for today]: ")
if 't' == date_started: date_started = datetime.today().strftime('%Y-%m-%d') if "t" == date_started:
item['date_started'] = date_started date_started = datetime.today().strftime("%Y-%m-%d")
item["date_started"] = date_started
if 'log' == log: if "log" == log:
date_finished = '' date_finished = ""
while re.search('[0-9]{4}-[0-9]{2}-[0-9]{2}', date_finished) is None: while re.search("[0-9]{4}-[0-9]{2}-[0-9]{2}", date_finished) is None:
date_finished = input("Enter date finished [YYYY-MM-DD, t for today]: ") date_finished = input("Enter date finished [YYYY-MM-DD, t for today]: ")
if 't' == date_finished: date_finished = datetime.today().strftime('%Y-%m-%d') if "t" == date_finished:
item['date_finished'] = date_finished date_finished = datetime.today().strftime("%Y-%m-%d")
item["date_finished"] = date_finished
# TODO - do this automatically # TODO - do this automatically
is_repeat = '' is_repeat = ""
while is_repeat not in ['y', 'n']: while is_repeat not in ["y", "n"]:
is_repeat = input(f"Is this a repeat entry? [y/n]: ") is_repeat = input(f"Is this a repeat entry? [y/n]: ")
if 'y' == is_repeat: item['is_repeat'] = True if "y" == is_repeat:
item['added_by_id'] = item_id item["is_repeat"] = True
item["added_by_id"] = item_id
comments = input("Enter comments (optional): ") comments = input("Enter comments (optional): ")
if '' != comments: item['comments'] = comments if "" != comments:
item["comments"] = comments
# Validation step # Validation step
correct = '' correct = ""
print(f"{media_type} data to add:\n") print(f"{media_type} data to add:\n")
print(json.dumps(item, indent=4)) print(json.dumps(item, indent=4))
if 'y' != input("\nDoes this look correct? [y]: "): return if "y" != input("\nDoes this look correct? [y]: "):
return
# Save changes # Save changes
logger.info(f"Adding {media_type} to {log}…") logger.info(f"Adding {media_type} to {log}…")
@ -92,19 +99,19 @@ def add_item_to_log(item_id, media_type, log):
log_items.insert(0, item) log_items.insert(0, item)
with open(f"./data/{media_type}/{log}.json", "w") as log_file: with open(f"./data/{media_type}/{log}.json", "w") as log_file:
json.dump(log_items, log_file, indent=4) json.dump(log_items, log_file, indent=4)
logger.info(f"Added {media_type} {item_id} to {log}") logger.info(f"Added {media_type} {item_id} to {log}")
def import_by_id(import_id, media_type): def import_by_id(import_id, media_type):
if media_type in ['films', 'tv-series']: if media_type in ["films", "tv-series"]:
return import_from_imdb_by_id(import_id, media_type) return import_from_imdb_by_id(import_id, media_type)
elif media_type in ['tv-episodes']: elif media_type in ["tv-episodes"]:
return #import_from_tvdb_by_id(import_id, media_type) return # import_from_tvdb_by_id(import_id, media_type)
elif media_type in ['books']: elif media_type in ["books"]:
return import_from_openlibrary_by_id(import_id, media_type) return import_from_openlibrary_by_id(import_id, media_type)
@ -116,17 +123,15 @@ def import_from_imdb_by_id(imdb_id, media_type):
# Sending API request # Sending API request
response = requests.get( response = requests.get(
api_url, api_url,
params={ params={"external_source": "imdb_id"},
'external_source': 'imdb_id' headers={"Authorization": f"Bearer {TMDB_API_KEY}"},
},
headers={'Authorization': f"Bearer {TMDB_API_KEY}"}
) )
# Process the response # Process the response
if (200 == response.status_code): if 200 == response.status_code:
logger.info(response.status_code) logger.debug(response.status_code)
elif (429 == response.status_code): elif 429 == response.status_code:
time.sleep(2) time.sleep(2)
import_from_imdb_by_id(imdb_id, media_type) import_from_imdb_by_id(imdb_id, media_type)
return return
@ -134,9 +139,12 @@ def import_from_imdb_by_id(imdb_id, media_type):
else: else:
raise Exception(f"Error {response.status_code}: {response.text}") raise Exception(f"Error {response.status_code}: {response.text}")
if ('films' == media_type): results_key = 'movie_results' if "films" == media_type:
elif ('tv-episodes' == media_type): results_key = 'TODO' results_key = "movie_results"
elif ('tv-series' == media_type): results_key = 'tv_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] response_data = json.loads(response.text)[results_key]
@ -147,8 +155,7 @@ def import_from_imdb_by_id(imdb_id, media_type):
raise Exception(f"Returned no results for {imdb_id}") raise Exception(f"Returned no results for {imdb_id}")
elif 1 < len(response_data): elif 1 < len(response_data):
logger.warning(f"Returned more than one {media_type} for ID '{imdb_id}'") logger.warning(f"Returned more than one {media_type} for ID '{imdb_id}'\n")
print(f"Returned more than one {media_type} for ID '{imdb_id}':\n")
print(json.dumps(response_data, indent=4)) print(json.dumps(response_data, indent=4))
idx = input("\nEnter the index of the result to use: ") idx = input("\nEnter the index of the result to use: ")
try: try:
@ -167,16 +174,13 @@ def import_from_openlibrary_by_id(isbn, media_type):
api_url = f"https://openlibrary.org/isbn/{isbn}" api_url = f"https://openlibrary.org/isbn/{isbn}"
# Sending API request # Sending API request
response = requests.get( response = requests.get(api_url, headers={"accept": "application/json"})
api_url,
headers={'accept': 'application/json'}
)
# Process the response # Process the response
if (200 == response.status_code): if 200 == response.status_code:
logger.info(response.status_code) logger.debug(response.status_code)
elif (429 == response.status_code): elif 429 == response.status_code:
time.sleep(2) time.sleep(2)
import_from_openlibrary_by_id(isbn, media_type) import_from_openlibrary_by_id(isbn, media_type)
return return
@ -186,18 +190,18 @@ def import_from_openlibrary_by_id(isbn, media_type):
item = json.loads(response.text) item = json.loads(response.text)
for key in ['authors', 'works']: for key in ["authors", "works"]:
if key in item: if key in item:
for i, sub_item in enumerate(item[key]): for i, sub_item in enumerate(item[key]):
item[key][i] = import_from_openlibrary_by_ol_key(sub_item['key']) item[key][i] = import_from_openlibrary_by_ol_key(sub_item["key"])
if 'works' in item: if "works" in item:
if len(item['works']) > 1: if len(item["works"]) > 1:
raise Exception(f"Multiple works found for {isbn}") raise Exception(f"Multiple works found for {isbn}")
else: else:
item['work'] = item['works'][0] item["work"] = item["works"][0]
del item['works'] del item["works"]
# Modify the returned result to add additional data # Modify the returned result to add additional data
return cleanup_result(item, media_type) return cleanup_result(item, media_type)
@ -206,22 +210,19 @@ def import_from_openlibrary_by_id(isbn, media_type):
def import_from_openlibrary_by_ol_key(key): def import_from_openlibrary_by_ol_key(key):
"""Retrieves an item (author or work) from OpenLibrary using an OL key""" """Retrieves an item (author or work) from OpenLibrary using an OL key"""
_, mode, ol_id = key.split('/') _, mode, ol_id = key.split("/")
if mode in ['works', 'authors']: if mode in ["works", "authors"]:
api_url = f"https://openlibrary.org{key}" api_url = f"https://openlibrary.org{key}"
# Sending API request # Sending API request
response = requests.get( response = requests.get(api_url, headers={"accept": "application/json"})
api_url,
headers={'accept': 'application/json'}
)
# Process the response # Process the response
if (200 == response.status_code): if 200 == response.status_code:
logger.info(response.status_code) logger.debug(response.status_code)
elif (429 == response.status_code): elif 429 == response.status_code:
time.sleep(2) time.sleep(2)
import_from_openlibrary_by_ol_key(key) import_from_openlibrary_by_ol_key(key)
return return
@ -231,25 +232,21 @@ def import_from_openlibrary_by_ol_key(key):
item = json.loads(response.text) item = json.loads(response.text)
if 'authors' == mode: if "authors" == mode:
author = { author = {"id": ol_id, "name": item["name"]}
'id': ol_id,
'name': item['name']
}
if 'personal_name' in item: if "personal_name" in item:
if item['name'] != item['personal_name']: author['personal_name'] = item['personal_name'] if item["name"] != item["personal_name"]:
author["personal_name"] = item["personal_name"]
return author return author
elif 'works' == mode: elif "works" == mode:
work = { work = {"id": ol_id, "title": item["title"]}
'id': ol_id,
'title': item['title']
}
for key in ['first_publish_date', 'subjects']: for key in ["first_publish_date", "subjects"]:
if key in item: work[key] = item[key] if key in item:
work[key] = item[key]
return work return work
@ -261,47 +258,51 @@ def cleanup_result(item, media_type):
"""Process a film, TV series, TV episode or book returned by their respecitve APIs by removing unnecessary fields and adding others""" """Process a film, TV series, TV episode or book returned by their respecitve APIs by removing unnecessary fields and adding others"""
for field_name in [ for field_name in [
'adult', # TMDB "adult", # TMDB
'backdrop_path', # TMDB "backdrop_path", # TMDB
'copyright_date', # OpenLibrary "copyright_date", # OpenLibrary
'classifications', # OpenLibrary "classifications", # OpenLibrary
'created', # OpenLibrary "created", # OpenLibrary
'episode_type', # TMDB "episode_type", # TMDB
'first_sentence', # OpenLibrary "first_sentence", # OpenLibrary
'genre_ids', # TMDB "genre_ids", # TMDB
'identifiers', # OpenLibrary "identifiers", # OpenLibrary
'media_type', # TMDB "media_type", # TMDB
'last_modified', # OpenLibrary "last_modified", # OpenLibrary
'latest_revision', # OpenLibrary "latest_revision", # OpenLibrary
'lc_classifications', # OpenLibrary "lc_classifications", # OpenLibrary
'local_id', # OpenLibrary "local_id", # OpenLibrary
'ocaid', # OpenLibrary "ocaid", # OpenLibrary
'oclc_numbers', # OpenLibrary "oclc_numbers", # OpenLibrary
'popularity', # TMDB "popularity", # TMDB
'production_code', # TMDB "production_code", # TMDB
'revision', # OpenLibrary "revision", # OpenLibrary
'runtime', # TMDB "runtime", # TMDB
'source_records', # OpenLibrary "source_records", # OpenLibrary
'still_path', # TMDB "still_path", # TMDB
'type', # OpenLibrary "type", # OpenLibrary
'video', # TMDB "video", # TMDB
'vote_average', # TMDB "vote_average", # TMDB
'vote_count' # TMDB "vote_count", # TMDB
]: ]:
if field_name in item: del item[field_name] if field_name in item:
del item[field_name]
if media_type in ['films', 'tv-series']: if media_type in ["films", "tv-series"]:
title_key = 'name' if 'tv-series' == media_type else 'title' title_key = "name" if "tv-series" == media_type else "title"
if f"original_{title_key}" in item and 'original_language' in item: 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': if (
del item[f"original_{title_key}"], item['original_language'] item[f"original_{title_key}"] == item[title_key]
and item["original_language"] == "en"
):
del item[f"original_{title_key}"], item["original_language"]
if 'books' == media_type: if "books" == media_type:
_, _, item['id'] = item['key'].split('/') _, _, item["id"] = item["key"].split("/")
del item['key'] del item["key"]
for key in ['isbn_10', 'isbn_13']: for key in ["isbn_10", "isbn_13"]:
if key in item: if key in item:
if len(item[key]) > 1: if len(item[key]) > 1:
raise Exception("Multiple ISBN results") raise Exception("Multiple ISBN results")
@ -309,78 +310,84 @@ def cleanup_result(item, media_type):
else: else:
item[key] = item[key][0] item[key] = item[key][0]
if 'publish_places' in item: if "publish_places" in item:
if len(item['publish_places']) > 1: if len(item["publish_places"]) > 1:
raise Exception("Multiple publish_places") raise Exception("Multiple publish_places")
else: else:
item['published_in'] = item['publish_places'][0] item["published_in"] = item["publish_places"][0]
del item['publish_places'] del item["publish_places"]
if 'languages' in item: if "languages" in item:
item['languages'] = [lang['key'].split('/')[2] for lang in item['languages']] item["languages"] = [
lang["key"].split("/")[2] for lang in item["languages"]
]
if 'translation_of' in item: if "translation_of" in item:
if item['translation_of'] == item['work']['title']: if item["translation_of"] == item["work"]["title"]:
del item['translation_of'] del item["translation_of"]
else: else:
raise Exception(f"translation_of '{item['translation_of']}' is different to work title '{item['work']['title']}'") raise Exception(
f"translation_of '{item['translation_of']}' is different to work title '{item['work']['title']}'"
)
if 'translated_from' in item: if "translated_from" in item:
if len(item['translated_from']) > 1: if len(item["translated_from"]) > 1:
raise Exception("Multiple translated_from results") raise Exception("Multiple translated_from results")
else: else:
item['work']['original_language'] = item['translated_from'][0]['key'].split('/')[2] item["work"]["original_language"] = item["translated_from"][0][
del item['translated_from'] "key"
].split("/")[2]
del item["translated_from"]
if "date_added" not in item:
if 'date_added' not in item: item['date_added'] = datetime.today().strftime('%Y-%m-%d') item["date_added"] = datetime.today().strftime("%Y-%m-%d")
return item return item
def main(): def main():
media_type = '' media_type = ""
while media_type not in ['films', 'tv-episodes', 'tv-series', 'books']: while media_type not in ["films", "tv-episodes", "tv-series", "books"]:
media_type = input("Select media type [films|tv-episodes|tv-series|books]: ") media_type = input("Select media type [films|tv-episodes|tv-series|books]: ")
try: try:
if 'films' == media_type: if "films" == media_type:
log = '' log = ""
while log not in ['log', 'wishlist']: while log not in ["log", "wishlist"]:
log = input ("Enter log to update [log|wishlist]: ") log = input("Enter log to update [log|wishlist]: ")
imdb_id = '' imdb_id = ""
while re.search("tt[0-9]+", imdb_id) is None: while re.search("tt[0-9]+", imdb_id) is None:
imdb_id = input("Enter IMDB ID: ") imdb_id = input("Enter IMDB ID: ")
add_item_to_log(imdb_id, media_type, log) add_item_to_log(imdb_id, media_type, log)
elif 'books' == media_type: elif "books" == media_type:
log = '' log = ""
while log not in ['log', 'current', 'wishlist']: while log not in ["log", "current", "wishlist"]:
log = input ("Enter log to update [log|current|wishlist]: ") log = input("Enter log to update [log|current|wishlist]: ")
isbn = '' isbn = ""
while re.search("[0-9]+", isbn) is None: while re.search("[0-9]+", isbn) is None:
isbn = input("Enter ISBN: ") isbn = input("Enter ISBN: ")
add_item_to_log(isbn, media_type, log) add_item_to_log(isbn, media_type, log)
elif 'tv-episodes' == media_type: elif "tv-episodes" == media_type:
imdb_id = '' imdb_id = ""
while re.search("tt[0-9]+", imdb_id) is None: while re.search("tt[0-9]+", imdb_id) is None:
imdb_id = input("Enter IMDB ID: ") imdb_id = input("Enter IMDB ID: ")
add_item_to_log(imdb_id, media_type, 'log') add_item_to_log(imdb_id, media_type, "log")
elif 'tv-series' == media_type: elif "tv-series" == media_type:
log = '' log = ""
while log not in ['log', 'current', 'wishlist']: while log not in ["log", "current", "wishlist"]:
log = input ("Enter log to update [log|current|wishlist]: ") log = input("Enter log to update [log|current|wishlist]: ")
imdb_id = '' imdb_id = ""
while re.search("tt[0-9]+", imdb_id) is None: while re.search("tt[0-9]+", imdb_id) is None:
imdb_id = input("Enter IMDB ID: ") imdb_id = input("Enter IMDB ID: ")

207
scripts/process_logs.py
View file

@ -7,15 +7,18 @@ import time
from urllib.request import urlopen from urllib.request import urlopen
from add_item import cleanup_result, import_by_id, setup_logger from add_item import cleanup_result, import_by_id, setup_logger
logger = setup_logger(__name__) logger = setup_logger("process_logs")
load_dotenv() load_dotenv()
TMDB_API_KEY = os.getenv('TMDB_API_KEY') TMDB_API_KEY = os.getenv("TMDB_API_KEY")
TVDB_API_KEY = os.getenv('TVDB_API_KEY') TVDB_API_KEY = os.getenv("TVDB_API_KEY")
if "" == TMDB_API_KEY:
logger.warning("TMDB API key not found")
if "" == TVDB_API_KEY:
logger.warning("TVDB API key not found")
if "" == TMDB_API_KEY: logger.warning("TMDB API key not found")
if "" == TVDB_API_KEY: logger.warning("TVDB API key not found")
def process_log(media_type, log): def process_log(media_type, log):
"""Run through a log and call the appropriate API for each item found""" """Run through a log and call the appropriate API for each item found"""
@ -29,67 +32,78 @@ def process_log(media_type, log):
for i, item in enumerate(log_items): for i, item in enumerate(log_items):
try: try:
if 'id' not in item: if "id" not in item:
if 'films' == media_type: item_title = item['Title'] if "films" == media_type:
elif 'tv-episodes' == media_type: item_title = item['Episode Title'] item_title = item["Title"]
elif 'tv-series' == media_type: item_title = item['Show Title'] elif "tv-episodes" == media_type:
item_title = item["Episode Title"]
elif "tv-series" == media_type:
item_title = item["Show Title"]
logger.debug(f"Processing {item_title}…") logger.debug(f"Processing {item_title}…")
# Rename pre-existing fields # Rename pre-existing fields
if 'Date Added' in item: if "Date Added" in item:
log_item_values['date_added'] = item['Date Added'] log_item_values["date_added"] = item["Date Added"]
del item['Date Added'] del item["Date Added"]
if 'Date Watched' in item: if "Date Watched" in item:
log_item_values['date_finished'] = item['Date Watched'] log_item_values["date_finished"] = item["Date Watched"]
del item['Date Watched'] del item["Date Watched"]
if 'Rewatch' in item: if "Rewatch" in item:
log_item_values['is_repeat'] = item['Rewatch'] log_item_values["is_repeat"] = item["Rewatch"]
del item['Rewatch'] del item["Rewatch"]
if 'Comments' in item: if "Comments" in item:
log_item_values['comments'] = item['Comments'] log_item_values["comments"] = item["Comments"]
del item['Comments'] del item["Comments"]
if 'Series Title' in item: if "Series Title" in item:
log_item_values['series_title'] = item['Series Title'] log_item_values["series_title"] = item["Series Title"]
del item['Series Title'] del item["Series Title"]
if 'Episode Title' in item: if "Episode Title" in item:
log_item_values['name'] = item['Episode Title'] log_item_values["name"] = item["Episode Title"]
del item['Episode Title'] del item["Episode Title"]
if 'Episode Number' in item: if "Episode Number" in item:
if re.search("[0-9]+x[0-9]+", item['Episode Number']) is not None: if re.search("[0-9]+x[0-9]+", item["Episode Number"]) is not None:
season_no, _, episode_no = log_item_values['episode_number'].split("x") season_no, _, episode_no = log_item_values[
"episode_number"
].split("x")
elif re.search("S[0-9]+E[0-9]+", item['Episode Number']) is not None: elif (
season_no, _, episode_no = log_item_values['episode_number'].split("E") re.search("S[0-9]+E[0-9]+", item["Episode Number"]) is not None
):
season_no, _, episode_no = log_item_values[
"episode_number"
].split("E")
elif re.search("E[0-9]+", item['Episode Number']) is not None: elif re.search("E[0-9]+", item["Episode Number"]) is not None:
season_no = None season_no = None
episode_no = item['episode_number'][1:] episode_no = item["episode_number"][1:]
else: else:
logger.error(f"Invalid episode number format '{item['Episode Number']}'") logger.error(
f"Invalid episode number format '{item['Episode Number']}'"
)
return return
log_item_values['season_number'] = season_no log_item_values["season_number"] = season_no
log_item_values['episode_number'] = episode_no log_item_values["episode_number"] = episode_no
del item['Episode Number'] del item["Episode Number"]
if 'IMDB ID' in item: if "IMDB ID" in item and item["IMDB ID"] != "":
log_items[i] = import_by_id(item['IMDB ID'], media_type) new_log_item = import_by_id(item["IMDB ID"], media_type)
else: else:
log_items[i] = import_by_details(item, item_title, media_type) new_log_item = import_by_details(item, item_title, media_type)
if log_items[i] is None: if new_log_item is None:
item['imdb_id'] = input(f"Enter IMDB ID for {item_title}: ") item["imdb_id"] = input(f"Enter IMDB ID for {item_title}: ")
if re.search("tt[0-9]+", item['imdb_id']) is not None: if re.search("tt[0-9]+", item["imdb_id"]) is not None:
log_items[i] = import_by_id(item['imdb_id'], media_type) log_items[i] = import_by_id(item["imdb_id"], media_type)
with open(f"./data/{media_type}/{log}.json", "w") as log_file: with open(f"./data/{media_type}/{log}.json", "w") as log_file:
json.dump(log_items, log_file, indent=4) json.dump(log_items, log_file, indent=4)
@ -97,7 +111,15 @@ def process_log(media_type, log):
else: else:
logger.warning(f"Skipped {item_title}") logger.warning(f"Skipped {item_title}")
if log_items[i] is not None: log_items[i] |= log_item_values else:
log_items[i] = new_log_item
if i % 15 == 0:
with open(f"./data/{media_type}/{log}.json", "w") as log_file:
json.dump(log_items, log_file, indent=4)
if log_items[i] is not None:
log_items[i] |= log_item_values
except KeyError: except KeyError:
print(json.dumps(item, indent=4)) print(json.dumps(item, indent=4))
@ -111,17 +133,17 @@ def process_log(media_type, log):
def import_by_details(item, item_title, media_type): def import_by_details(item, item_title, media_type):
"""Import an item when lacking a unique identifier""" """Import an item when lacking a unique identifier"""
if media_type in ['films', 'tv-series']: if media_type in ["films", "tv-series"]:
return import_from_tmdb_by_details(item, item_title, media_type) return import_from_tmdb_by_details(item, item_title, media_type)
elif media_type in ['tv-episodes']: elif media_type in ["tv-episodes"]:
return #import_from_tvdb_by_details(item, item_title, media_type) return # import_from_tvdb_by_details(item, item_title, media_type)
elif media_type in ['books']: elif media_type in ["books"]:
return #import_from_openlibrary_by_details(item, item_title, media_type) return # import_from_openlibrary_by_details(item, item_title, media_type)
elif media_type in ['games']: elif media_type in ["games"]:
return #import_from_igdb_by_details(item, item_title, media_type) return # import_from_igdb_by_details(item, item_title, media_type)
def import_from_tmdb_by_details(item, item_title, media_type): def import_from_tmdb_by_details(item, item_title, media_type):
@ -135,23 +157,23 @@ def import_from_tmdb_by_details(item, item_title, media_type):
response = requests.get( response = requests.get(
api_url, api_url,
params={ params={
'query': item_title, "query": item_title,
'include_adult': True, "include_adult": True,
'year': item['Release Year'] if 'Release Year' in item else None "year": item["Release Year"] if "Release Year" in item else None,
}, },
headers={'Authorization': f"Bearer {TMDB_API_KEY}"} headers={"Authorization": f"Bearer {TMDB_API_KEY}"},
) )
# Process the response # Process the response
if (200 == response.status_code): if 200 == response.status_code:
logger.info(response.status_code) logger.debug(response.status_code)
elif (429 == response.status_code): elif 429 == response.status_code:
time.sleep(2) time.sleep(2)
import_from_tmdb_by_details(item) import_from_tmdb_by_details(item)
else: else:
logger.error(response.text) logger.error(response.text)
response_data = json.loads(response.text)['results'] response_data = json.loads(response.text)["results"]
if 1 == len(response_data): if 1 == len(response_data):
return cleanup_result(response_data[0], media_type) return cleanup_result(response_data[0], media_type)
@ -160,18 +182,31 @@ def import_from_tmdb_by_details(item, item_title, media_type):
logger.warning(f"Returned no {media_type} for {item_title}") logger.warning(f"Returned no {media_type} for {item_title}")
elif 1 < len(response_data): elif 1 < len(response_data):
if 'films' == media_type: title_key = 'title' if "films" == media_type:
elif 'tv-series' == media_type: title_key = 'name' title_key = "title"
elif "tv-series" == media_type:
title_key = "name"
response_data = [result for result in response_data if result[title_key] == item_title] filtered_response_data = [
result for result in response_data if result[title_key] == item_title
]
if 1 == len(response_data): if 1 == len(filtered_response_data):
return cleanup_result(response_data[0], media_type) return cleanup_result(response_data[0], media_type)
else: else:
logger.warning(f"Returned more than one {media_type} for '{item_title}':\n") logger.warning(f"Returned more than one {media_type} for '{item_title}':\n")
print(json.dumps(response_data, indent=4)) print(
idx = input("\nEnter the index of the result to use: ") json.dumps(
filtered_response_data
if len(filtered_response_data) > 0
else response_data,
indent=4,
)
)
idx = input(
f"\nEnter the index of the result to use [0-{len(filtered_response_data if len(filtered_response_data) > 0 else response_data) - 1}]: "
)
if "" != idx: if "" != idx:
try: try:
@ -181,44 +216,44 @@ def import_from_tmdb_by_details(item, item_title, media_type):
logger.error("Index invalid!") logger.error("Index invalid!")
print("Index invalid!") print("Index invalid!")
item['IMDB ID'] = input(f"Enter IMDB ID for {item_title}: ") item["IMDB ID"] = input(f"Enter IMDB ID for {item_title}: ")
if '' != item['IMDB ID']: if "" != item["IMDB ID"]:
return import_by_id(item['IMDB ID'], media_type) return import_by_id(item["IMDB ID"], media_type)
else: else:
logger.warning(f"Skipped {item_title}") logger.warning(f"Skipped {item_title}")
return item return item
def main(): def main():
media_type = '' media_type = ""
while media_type not in ['films', 'tv-episodes', 'tv-series', 'books']: while media_type not in ["films", "tv-episodes", "tv-series", "books"]:
media_type = input("Select media type [films|tv-episodes|tv-series|books]: ") media_type = input("Select media type [films|tv-episodes|tv-series|books]: ")
try: try:
if 'films' == media_type: if "films" == media_type:
log = '' log = ""
while log not in ['log', 'wishlist']: while log not in ["log", "wishlist"]:
log = input ("Enter log to process [log|wishlist]:") log = input("Enter log to process [log|wishlist]: ")
process_log(media_type, log) process_log(media_type, log)
elif 'books' == media_type: elif "books" == media_type:
log = '' log = ""
while log not in ['log', 'current', 'wishlist']: while log not in ["log", "current", "wishlist"]:
log = input ("Enter log to process [log|current|wishlist]:") log = input("Enter log to process [log|current|wishlist]: ")
# TODO # TODO
elif 'tv-episodes' == media_type: elif "tv-episodes" == media_type:
process_log(media_type, 'log') process_log(media_type, "log")
# TODO # TODO
elif 'tv-series' == media_type: elif "tv-series" == media_type:
log = '' log = ""
while log not in ['log', 'current', 'wishlist']: while log not in ["log", "current", "wishlist"]:
log = input ("Enter log to process [log|current|wishlist]:") log = input("Enter log to process [log|current|wishlist]: ")
process_log(media_type, log) process_log(media_type, log)