Files

127 lines
4.5 KiB
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""NFO reader — Curator's metadata source after ČSFD.
Jellyfin (configured to save metadata into the media folders) writes a Kodi-style
``.nfo`` next to each movie plus artwork. Curator only **reads** it — to drive the
miniDLNA genre tree and to fill the year/rating used by folder grouping. It never
writes NFO (Jellyfin owns that).
For a flat pool file ``Title (rok) [tmdbid].mkv`` the sidecar is
``Title (rok) [tmdbid].nfo``; a per-movie folder may instead hold ``movie.nfo``.
Both are found. Missing or unparsable NFO → ``None`` (the movie simply has no
genres until Jellyfin has scanned it).
"""
import xml.etree.ElementTree as ET
from dataclasses import dataclass, field
from pathlib import Path
@dataclass
class NfoData:
"""The bits of a movie ``.nfo`` Curator uses."""
title: str | None = None
year: str | None = None # four-digit string
genres: list[str] = field(default_factory=list)
countries: list[str] = field(default_factory=list)
rating: int | None = None # 0–100 (NFO 0–10 scaled up), or None
tmdb_id: int | None = None
csfd_url: str | None = None # ČSFD film URL, if the NFO carries a csfd id
def field_values(self, name: str) -> list[str]:
"""Values for a tag-schema source field (genres/countries/year/rating)."""
if name == "genres":
return list(self.genres)
if name == "countries":
return list(self.countries)
if name == "year":
return [self.year] if self.year else []
if name == "rating":
return [str(self.rating)] if self.rating is not None else []
return []
def find_nfo(video_path: Path) -> Path | None:
"""Locate the ``.nfo`` for a movie: sibling ``<stem>.nfo`` or ``movie.nfo``."""
video_path = Path(video_path)
sibling = video_path.with_suffix(".nfo")
if sibling.is_file():
return sibling
movie_nfo = video_path.parent / "movie.nfo"
if movie_nfo.is_file():
return movie_nfo
return None
def _texts(root: ET.Element, tag: str) -> list[str]:
return [e.text.strip() for e in root.findall(tag) if e.text and e.text.strip()]
def _parse_rating(root: ET.Element) -> int | None:
"""Read a 0–10 NFO rating and scale it to 0–100 (to match the old bands)."""
raw = root.findtext("rating")
if raw is None:
value = root.find("ratings/rating/value")
raw = value.text if value is not None else None
if not raw:
return None
try:
return round(float(raw.strip().replace(",", ".")) * 10)
except ValueError:
return None
def _parse_tmdb_id(root: ET.Element) -> int | None:
for uid in root.findall("uniqueid"):
if uid.get("type") == "tmdb" and uid.text and uid.text.strip().isdigit():
return int(uid.text.strip())
raw = root.findtext("tmdbid")
return int(raw.strip()) if raw and raw.strip().isdigit() else None
def _parse_csfd_url(root: ET.Element) -> str | None:
"""A ČSFD film URL from the NFO, if any.
Czech Kodi scrapers record ČSFD as ``<uniqueid type="csfd">`` (a bare id or a
full URL) or a legacy ``<csfdid>`` / ``<csfd>`` element. A bare id is expanded
to ``https://www.csfd.cz/film/<id>/``.
"""
candidates: list[str] = []
for uid in root.findall("uniqueid"):
if uid.get("type") == "csfd" and uid.text and uid.text.strip():
candidates.append(uid.text.strip())
for tag in ("csfdid", "csfd"):
raw = root.findtext(tag)
if raw and raw.strip():
candidates.append(raw.strip())
for value in candidates:
if value.isdigit():
return f"https://www.csfd.cz/film/{value}/"
if "csfd.cz" in value:
return value if value.startswith("http") else f"https://{value.lstrip('/')}"
return None
def read_nfo(video_path: Path) -> NfoData | None:
"""Read the movie's ``.nfo`` into :class:`NfoData`, or None if absent/broken."""
path = find_nfo(video_path)
if path is None:
return None
try:
root = ET.parse(path).getroot()
except ET.ParseError, OSError:
return None
year = root.findtext("year")
year = year.strip() if year and year.strip().isdigit() else None
title = root.findtext("title")
return NfoData(
title=title.strip() if title and title.strip() else None,
year=year,
genres=_texts(root, "genre"),
countries=_texts(root, "country"),
rating=_parse_rating(root),
tmdb_id=_parse_tmdb_id(root),
csfd_url=_parse_csfd_url(root),
)