Compare commits

...

5 commits

6 changed files with 290 additions and 85 deletions

View file

@ -1,46 +1,4 @@
[
{
"publishers": [
"PAN MACMILLAN"
],
"physical_format": "paperback",
"title": "Permanent Record",
"covers": [
10118259
],
"isbn_13": "9781529035667",
"full_title": "Permanent Record",
"isbn_10": "152903566X",
"publish_date": "Sep 14, 2019",
"authors": [
{
"id": "OL7618561A",
"name": "Edward Snowden"
}
],
"work": {
"id": "OL20080323W",
"title": "Permanent Record",
"subjects": [
"Snowden, edward j., 1983-",
"Government information",
"Whistle blowing",
"Leaks (Disclosure of information)",
"Officials and employees",
"United States",
"United States. National Security Agency",
"Biography",
"nyt:combined-print-and-e-book-nonfiction=2019-10-06",
"New York Times bestseller",
"New York Times reviewed",
"Electronic surveillance"
]
},
"ol_id": "OL28181327M",
"date_added": "2019-09-14",
"date_started": "2024-02-20",
"added_by_id": "9781529035667"
},
{
"publishers": [
"O'Reilly Media"

View file

@ -1,4 +1,47 @@
[
{
"publishers": [
"PAN MACMILLAN"
],
"physical_format": "paperback",
"title": "Permanent Record",
"covers": [
10118259
],
"isbn_13": "9781529035667",
"full_title": "Permanent Record",
"isbn_10": "152903566X",
"publish_date": "Sep 14, 2019",
"authors": [
{
"id": "OL7618561A",
"name": "Edward Snowden"
}
],
"work": {
"id": "OL20080323W",
"title": "Permanent Record",
"subjects": [
"Snowden, edward j., 1983-",
"Government information",
"Whistle blowing",
"Leaks (Disclosure of information)",
"Officials and employees",
"United States",
"United States. National Security Agency",
"Biography",
"nyt:combined-print-and-e-book-nonfiction=2019-10-06",
"New York Times bestseller",
"New York Times reviewed",
"Electronic surveillance"
]
},
"ol_id": "OL28181327M",
"date_added": "2019-09-14",
"date_started": "2024-02-20",
"date_finished": "2024-03-11",
"added_by_id": "9781529035667"
},
{
"description": {
"type": "/type/text",

View file

@ -1,10 +1,34 @@
[
{
"ol_id": "OL23279299W",
"title": "Soldier box",
"authors": [
{
"ol_id": "OL8830255A",
"name": "Joe Glenton"
}
],
"subjects": [
"Afghan War, 2001-",
"Desertions",
"Military deserters",
"Biography",
"Conscientious objectors",
"Soldiers",
"Political activity",
"British Participation",
"Personal narratives",
"Afghan war, 2001-2021"
],
"date_added": "2024-03-06"
},
{
"ol_id": "OL25856221W",
"title": "Johnny Viable",
"subjects": [
"Art"
]
],
"date_added": "2024-02-25"
},
{
"ol_id": "OL27719403W",
@ -14,7 +38,8 @@
"Ecology",
"Forest ecology",
"Wald\u00f6kosystem"
]
],
"date_added": "2024-02-15"
},
{
"ol_id": "OL25815646W",
@ -30,7 +55,8 @@
"Sens et sensations",
"Physiologie",
"nyt:paperback-nonfiction=2023-09-17"
]
],
"date_added": "2024-02-15"
},
{
"ol_id": "OL21164374W",

View file

@ -1,4 +1,101 @@
[
{
"belongs_to_collection": null,
"genres": [
{
"id": 878,
"name": "Science Fiction"
},
{
"id": 10749,
"name": "Romance"
},
{
"id": 35,
"name": "Comedy"
}
],
"imdb_id": "tt14230458",
"overview": "Brought back to life by an unorthodox scientist, a young woman runs off with a debauched lawyer on a whirlwind adventure across the continents. Free from the prejudices of her times, she grows steadfast in her purpose to stand for equality and liberation.",
"poster_path": "/kCGlIMHnOm8JPXq3rXM6c5wMxcT.jpg",
"production_countries": [
{
"iso_3166_1": "IE",
"name": "Ireland"
},
{
"iso_3166_1": "GB",
"name": "United Kingdom"
},
{
"iso_3166_1": "US",
"name": "United States of America"
}
],
"release_date": "2023-12-07",
"spoken_languages": [
{
"english_name": "English",
"iso_639_1": "en",
"name": "English"
},
{
"english_name": "French",
"iso_639_1": "fr",
"name": "Fran\u00e7ais"
},
{
"english_name": "Portuguese",
"iso_639_1": "pt",
"name": "Portugu\u00eas"
}
],
"title": "Poor Things",
"tmdb_id": 792307,
"date_added": "2024-03-12",
"date_finished": "2024-03-09",
"added_by_id": "792307"
},
{
"belongs_to_collection": {
"id": 726871,
"name": "Dune Collection",
"poster_path": "/wcVafar6Efk3YgFvh8oZQ4yHL6H.jpg",
"backdrop_path": "/ygVSGv86R0BTOKJIb8RQ1sFxs4q.jpg"
},
"genres": [
{
"id": 878,
"name": "Science Fiction"
},
{
"id": 12,
"name": "Adventure"
}
],
"imdb_id": "tt15239678",
"overview": "Follow the mythic journey of Paul Atreides as he unites with Chani and the Fremen while on a path of revenge against the conspirators who destroyed his family. Facing a choice between the love of his life and the fate of the known universe, Paul endeavors to prevent a terrible future only he can foresee.",
"poster_path": "/8b8R8l88Qje9dn9OE8PY05Nxl1X.jpg",
"production_countries": [
{
"iso_3166_1": "US",
"name": "United States of America"
}
],
"release_date": "2024-02-27",
"spoken_languages": [
{
"english_name": "English",
"iso_639_1": "en",
"name": "English"
}
],
"title": "Dune: Part Two",
"tmdb_id": 693134,
"date_added": "2024-03-12",
"date_finished": "2024-03-09",
"added_by_id": "693134"
},
{
"belongs_to_collection": null,
"genres": [

View file

@ -1,4 +1,35 @@
[
{
"belongs_to_collection": null,
"genres": [
{
"id": 99,
"name": "Documentary"
}
],
"imdb_id": "tt0318202",
"original_language": "fr",
"original_title": "\u00catre et avoir",
"overview": "The documentary's title translates as \"to be and to have\", the two auxiliary verbs in the French language. It is about a primary school in the commune of Saint-\u00c9tienne-sur-Usson, Puy-de-D\u00f4me, France, the population of which is just over 200. The school has one small class of mixed ages (from four to twelve years), with a dedicated teacher, Georges Lopez, who shows patience and respect for the children as we follow their story through a single school year.",
"poster_path": "/mqB5QPNCmbF8DgsZqmyGQAGktUE.jpg",
"production_countries": [
{
"iso_3166_1": "FR",
"name": "France"
}
],
"release_date": "2002-08-28",
"spoken_languages": [
{
"english_name": "French",
"iso_639_1": "fr",
"name": "Fran\u00e7ais"
}
],
"title": "To Be and to Have",
"tmdb_id": 5168,
"date_added": "2024-03-06"
},
{
"belongs_to_collection": null,
"genres": [

View file

@ -54,17 +54,28 @@ if "" == TMDB_API_KEY:
logger.error("TMDB API key not found")
def return_if_exists(item_id, media_type, log) -> dict | None:
def return_if_exists(item_id: str, media_type: str, log: str) -> dict | None:
"""Returns an item if it exists in the requested log"""
logger.info(f"Checking for '{item_id}' in '{log}'")
with open(f"./data/{media_type}/{log}.json", "r", encoding="utf-8") as log_file:
log_items = json.load(log_file)
id_key = "id"
if "books" == media_type:
if re.search("OL[0-9]+[MW]", item_id) is not None:
id_key = "ol_id"
elif re.search("[0-9]{13}", item_id) is not None:
id_key = "isbn_13"
elif re.search("[0-9]{10}", item_id) is not None:
id_key = "isbn_10"
else:
raise Exception("Invalid ID for book")
existing_items = [
log_item
for log_item in log_items
if "id" in log_item and log_item["id"] == item_id
if id_key in log_item and log_item[id_key] == item_id
]
if len(existing_items) > 0:
logger.info(f"Found item in '{log}'")
@ -72,18 +83,38 @@ def return_if_exists(item_id, media_type, log) -> dict | None:
logger.info(f"'{item_id}' not found in '{log}'")
def delete_existing(item_id, media_type, log) -> None:
def delete_existing(item_id: str, media_type: str, log: str) -> None:
"""Deletes an item from a log if it matches the ID"""
logger.info(f"Deleting '{item_id}' from '{log}'")
with open(f"./data/{media_type}/{log}.json", "r", encoding="utf-8") as log_file:
log_items = json.load(log_file)
id_key = "id"
if "books" == media_type:
if re.search("OL[0-9]+[MW]", item_id) is not None:
id_key = "ol_id"
elif re.search("[0-9]{13}", item_id) is not None:
id_key = "isbn_13"
elif re.search("[0-9]{10}", item_id) is not None:
id_key = "isbn_10"
else:
raise Exception("Invalid ID for book")
elif media_type in ["films", "tv-episodes"]:
if re.search("tt[0-9]+", item_id) is not None:
id_key = "isbn_id"
elif re.search("[0-9]+", item_id) is not None:
id_key = "tmdb_id"
else:
raise Exception("Invalid ID for film")
old_len = len(log_items)
log_items = [
log_item
for log_item in log_items
if "id" not in log_item or ("id" in log_item and log_item["id"] != item_id)
if id_key not in log_item
or (id_key in log_item and log_item[id_key] != item_id)
]
if len(log_items) < (old_len - 1):
raise Exception("More than one deletion made, discarding…")
@ -93,7 +124,9 @@ def delete_existing(item_id, media_type, log) -> None:
logger.info(f"'{item_id}' deleted from '{log}'")
def check_for_existing(item_id, media_type, log) -> dict[dict, str]:
def check_for_existing(
item_id, media_type, log
) -> tuple[dict[dict, str] | None, str | None]:
"""
Check for an existing item in the current log, and pull the
`date_added` etc. and mark it as a repeat if so.
@ -127,14 +160,14 @@ def check_for_existing(item_id, media_type, log) -> dict[dict, str]:
return None, None
def add_item_to_log(item_id, media_type, log) -> None:
def add_item_to_log(item_id: str, media_type: str, log: str) -> None:
"""Add a film, book, TV series or TV episode to a log"""
logger.info(f"Processing {item_id}")
item = None
item: dict | None = None
log_to_delete = None
if "tv-episodes" != media_type and ("books" != media_type and "wishlist" != log):
if media_type not in ["tv-episodes", "books"]:
item, log_to_delete = check_for_existing(item_id, media_type, log)
if item is None:
@ -142,10 +175,21 @@ def add_item_to_log(item_id, media_type, log) -> None:
if item is None:
raise Exception("No item found")
if "books" == media_type and "wishlist" != log:
item, log_to_delete = check_for_existing(item['work']['ol_id'], media_type, log)
if item is None:
item, log_to_delete = check_for_existing(item['ol_id'], media_type, log)
if "books" == media_type:
new_item, log_to_delete = check_for_existing(
item["work"]["ol_id"], media_type, log
)
if new_item is None:
new_item, log_to_delete = check_for_existing(item["ol_id"], media_type, log)
if new_item is None:
new_item, log_to_delete = check_for_existing(
item["isbn_13"], media_type, log
)
if new_item is None:
new_item, log_to_delete = check_for_existing(
item["isbn_10"], media_type, log
)
item = new_item if new_item is not None else item
if log in ["log", "current"]:
if "date_started" not in item and media_type in ["books", "tv-series", "games"]:
@ -202,7 +246,7 @@ def add_item_to_log(item_id, media_type, log) -> None:
delete_existing(item_id, media_type, log_to_delete)
def import_by_id(import_id, media_type, log) -> dict:
def import_by_id(import_id, media_type, log) -> dict | None:
"""Import from the appropriate API by unique ID"""
if media_type in ["films", "tv-series"]:
@ -230,8 +274,12 @@ def import_from_tmdb_by_external_id(external_id, media_type) -> dict:
response = requests.get(
api_url,
headers={"Authorization": f"Bearer {TMDB_API_KEY}"},
params={"external_source": "imdb_id" if re.search("tt[0-9]+", external_id) else "tvdb_id"},
timeout=15
params={
"external_source": (
"imdb_id" if re.search("tt[0-9]+", external_id) else "tvdb_id"
)
},
timeout=15,
)
# Process the response
@ -254,7 +302,7 @@ def import_from_tmdb_by_external_id(external_id, media_type) -> dict:
key = "movie_results"
response_data = json.loads(response.text)[key][0]
if response_data == None:
if response_data is None:
raise Exception(f"Nothing found for TVDB ID {external_id}!")
# Modify the returned result to add additional data
@ -289,7 +337,7 @@ def import_from_tmdb_by_id(tmdb_id, media_type) -> dict:
return cleanup_result(response_data, media_type)
def import_from_openlibrary_by_isbn(isbn, media_type) -> dict:
def import_from_openlibrary_by_isbn(isbn, media_type) -> dict | None:
"""Retrieve a film, TV show or TV episode from TMDB using an IMDB ID"""
logging.info(f"Importing '{isbn}'")
@ -337,18 +385,19 @@ def import_from_openlibrary_by_isbn(isbn, media_type) -> dict:
return cleanup_result(item, media_type)
def import_from_openlibrary_by_ol_key(key) -> dict:
def import_from_openlibrary_by_ol_key(key) -> dict | None:
"""Retrieves an item (author or work, NOT edition) from OpenLibrary using an OL key"""
if (len(key.split("/")) == 1):
if len(key.split("/")) == 1:
key = f"/works/{key}"
logger.info(f"Retrieving {key}")
_, mode, ol_id = key.split("/")
cached_authors = []
if "authors" == mode:
with open(
f"./scripts/caching/authors.json", "r", encoding="utf-8"
"./scripts/caching/authors.json", "r", encoding="utf-8"
) as authors_cache:
cached_authors = json.load(authors_cache)
@ -396,7 +445,7 @@ def import_from_openlibrary_by_ol_key(key) -> dict:
logger.info(f"Caching author '{author['name']}'")
cached_authors.append(author)
with open(
f"./scripts/caching/authors.json", "w", encoding="utf-8"
"./scripts/caching/authors.json", "w", encoding="utf-8"
) as authors_cache:
json.dump(cached_authors, authors_cache, indent=4)
logger.info(f"Author '{author['name']}' cached!")
@ -408,7 +457,9 @@ def import_from_openlibrary_by_ol_key(key) -> dict:
if "authors" in item:
for author in item["authors"]:
work["authors"].append(import_from_openlibrary_by_ol_key(author["author"]["key"]))
work["authors"].append(
import_from_openlibrary_by_ol_key(author["author"]["key"])
)
for result_key in ["first_publish_date", "subjects"]:
if result_key in item:
@ -487,8 +538,8 @@ def cleanup_result(item, media_type) -> dict:
del item[f"original_{title_key}"], item["original_language"]
if "tv-episodes" == media_type:
item['series'] = { 'tmdb_id': item['show_id'] }
del item['show_id']
item["series"] = {"tmdb_id": item["show_id"]}
del item["show_id"]
if "books" == media_type:
_, _, item["ol_id"] = item["key"].split("/")
@ -515,7 +566,7 @@ def cleanup_result(item, media_type) -> dict:
f"translation_of '{item['translation_of']}' \
is different to work title '{item['work']['title']}'"
)
if 'y' != input("Accept change? [y|n]: "):
if "y" != input("Accept change? [y|n]: "):
raise Exception(
f"translation_of '{item['translation_of']}' \
is different to work title '{item['work']['title']}'"
@ -546,8 +597,8 @@ def main() -> None:
try:
item_id = ""
if "films" == media_type:
log = ""
if "films" == media_type:
while log not in ["log", "wishlist"]:
log = input("Enter log to update [log|wishlist]: ")
@ -555,7 +606,6 @@ def main() -> None:
item_id = input("Enter TMDB ID: ")
elif "books" == media_type:
log = ""
while log not in ["log", "current", "wishlist"]:
log = input("Enter log to update [log|current|wishlist]: ")
@ -566,19 +616,19 @@ def main() -> None:
item_id = "".join(re.findall(r"\d+", input("Enter ISBN: ")))
elif "tv-episodes" == media_type:
log = "log"
while re.search("(tt)?[0-9]+", item_id) is None:
item_id = input("Enter TVDB or IMDB ID: ")
elif "tv-series" == media_type:
log = ""
while log not in ["log", "current", "wishlist"]:
log = input("Enter log to update [log|current|wishlist]: ")
while re.search("[0-9]+", item_id) is None:
item_id = input("Enter TMDB ID: ")
add_item_to_log(re.search("(OL|tt)?[0-9]+[WMA]?", item_id)[0], media_type, log)
item_id_parsed = re.search("(OL|tt)?[0-9]+[WMA]?", item_id)
if item_id_parsed is not None:
add_item_to_log(item_id_parsed[0], media_type, log)
except Exception:
logger.exception("Exception occurred")