Files
Aurora-Core/app/services/ingestion/series_ingestion.py
T
NixReaperandClaude Sonnet 5 fef914db36
CI / lint (push) Canceled after 0s
CI / typecheck (push) Canceled after 0s
CI / unit-tests (push) Canceled after 0s
CI / integration-tests (push) Canceled after 0s
CI / container-build (push) Canceled after 0s
CI / dependency-audit (push) Canceled after 0s
Add artwork self-hosting: local-disk download worker + storage
Section 10: every image API responses reference has pointed straight
at TMDb's CDN since day one -- Aurora never actually downloaded or
served artwork itself, despite storing dimensions/checksum/local_path
columns for exactly that. Closes the gap:

- is_primary was declared on the Artwork model but never actually set
  anywhere -- every row defaulted to False. Now the normalizer marks
  the one image each provider designates as *the* image for an entity
  (TMDb's poster_path/backdrop_path/profile_path) as primary,
  distinct from the dozens of alternates also ingested, including
  correctly marking an existing row primary (not inserting a
  duplicate) when that image already appears in the alternates list.
- app/services/artwork/: an ArtworkStorage interface with a
  LocalDiskStorage implementation (checksum-named files, single-host
  deployment via a Docker volume shared between api and worker -- see
  docs/architecture.md for the S3/R2 upgrade path), and a download
  pipeline with content-type validation, a size cap, and path-traversal
  protection.
- After movie/series/person ingestion succeeds, tasks.py cascades one
  download_artwork_task per primary artwork id via arq's ctx['redis']
  (same fan-out pattern as the season cascade) -- fire-and-forget, not
  tracked in ingestion_jobs, since a failed image cache is a
  known-safe fallback to the provider URL, not a user-facing failure.
- app/main.py serves MEDIA_ROOT at MEDIA_URL_PREFIX; local_path is
  preferred over original_url once set (already-existing fallback
  logic in app/services/common.py:artwork_url, now actually exercised).

Also fixes a real interaction bug this surfaced: every ingestion
pipeline deleted and recreated all of an entity's Artwork rows on each
re-sync, which would have silently wiped local_path/checksum on every
re-ingestion, forcing a full re-download every time and defeating the
point of caching locally at all. app/repositories/polymorphic.py's new
sync_artwork upserts by provider_asset_id (TMDb's stable per-image
path) instead, preserving downloaded copies across re-sync, and
replaces three near-identical delete+recreate helpers that used to
live separately in movie_ingestion.py, series_ingestion.py, and
person_ingestion.py.

Co-Authored-By: Claude Sonnet 5 <[email protected]>
2026-09-05 03:26:28 -05:00

412 lines
14 KiB
Python

"""Series/season/episode ingestion pipeline (section 15).
Mirrors `movie_ingestion.py`'s flow (fetch -> normalize -> match -> upsert
-> provenance) but split into two entry points because TMDb requires a
separate API call per season for episode data:
- `ingest_series` upserts the Series row and season *stubs* (number, title,
air date, poster — everything TMDb includes inline on `/tv/{id}`), but
not episodes.
- `ingest_season` fetches and upserts one season's full episode list. It
requires the series to have been ingested already (episodes attach to an
Aurora series_id that has to already exist).
"""
from __future__ import annotations
import uuid
from sqlalchemy import delete
from sqlalchemy.ext.asyncio import AsyncSession
from app.core.logging import get_logger
from app.models.company import SeriesCompany
from app.models.credit import Credit
from app.models.enums import CompanyType, MatchConfidence, SeriesStatus, VideoType
from app.models.genre import SeriesGenre
from app.models.keyword import SeriesKeyword
from app.models.tv import Series
from app.models.video import Video
from app.providers.base import MetadataProvider, ProviderNotFoundError
from app.repositories import polymorphic, tv_repository
from app.repositories import reference_repository as refs
from app.repositories.provider_repository import get_or_create_provider, upsert_provider_record
from app.services.metadata.matcher import match_entity
from app.services.metadata.normalizer import (
NormalizedSeries,
normalize_season,
normalize_series,
)
logger = get_logger(__name__)
_VIDEO_TYPES = {t.value for t in VideoType}
_LEADING_ARTICLES = ("the ", "a ", "an ")
def _sort_title(title: str) -> str:
lowered = title.lower()
for article in _LEADING_ARTICLES:
if lowered.startswith(article):
return title[len(article) :].strip()
return title
async def _replace_series_genres(session: AsyncSession, series_id: uuid.UUID, names: list[str]) -> None:
await session.execute(delete(SeriesGenre).where(SeriesGenre.series_id == series_id))
for name in names:
genre = await refs.get_or_create_genre(session, name)
session.add(SeriesGenre(series_id=series_id, genre_id=genre.id))
async def _replace_series_keywords(
session: AsyncSession, series_id: uuid.UUID, names: list[str]
) -> None:
await session.execute(delete(SeriesKeyword).where(SeriesKeyword.series_id == series_id))
for name in names:
keyword = await refs.get_or_create_keyword(session, name)
session.add(SeriesKeyword(series_id=series_id, keyword_id=keyword.id))
async def _replace_series_companies(
session: AsyncSession,
series_id: uuid.UUID,
provider_id: uuid.UUID,
networks,
companies,
) -> None:
await session.execute(delete(SeriesCompany).where(SeriesCompany.series_id == series_id))
for ref, company_type, role in (
*[(n, CompanyType.NETWORK, "network") for n in networks],
*[(c, CompanyType.PRODUCTION_COMPANY, "production") for c in companies],
):
country_code = None
if ref.country_code:
country = await refs.get_or_create_country(session, ref.country_code, ref.country_code)
country_code = country.code
company = await refs.get_or_create_company(
session,
provider_id=provider_id,
external_id=ref.external_id,
name=ref.name,
company_type=company_type,
country_code=country_code,
)
session.add(SeriesCompany(series_id=series_id, company_id=company.id, role=role))
async def _replace_series_credits(
session: AsyncSession,
series_id: uuid.UUID,
provider_id: uuid.UUID,
cast,
crew,
creators,
) -> None:
await session.execute(
delete(Credit).where(Credit.entity_type == "series", Credit.entity_id == series_id)
)
for order, ref in enumerate(cast):
person = await refs.get_or_create_person(
session, provider_id=provider_id, external_id=ref.external_id, name=ref.name, gender=ref.gender
)
session.add(
Credit(
person_id=person.id,
entity_type="series",
entity_id=series_id,
department="Acting",
character=ref.character,
billing_order=ref.billing_order if ref.billing_order is not None else order,
provider_id=provider_id,
)
)
for ref in (*crew, *creators):
person = await refs.get_or_create_person(
session, provider_id=provider_id, external_id=ref.external_id, name=ref.name, gender=ref.gender
)
session.add(
Credit(
person_id=person.id,
entity_type="series",
entity_id=series_id,
department=ref.department or "Crew",
job=ref.job,
provider_id=provider_id,
)
)
async def _replace_entity_videos(
session: AsyncSession, entity_type: str, entity_id: uuid.UUID, provider_id: uuid.UUID, videos
) -> None:
await session.execute(
delete(Video).where(Video.entity_type == entity_type, Video.entity_id == entity_id)
)
for v in videos:
video_type = v.video_type if v.video_type in _VIDEO_TYPES else "other"
session.add(
Video(
entity_type=entity_type,
entity_id=entity_id,
video_type=VideoType(video_type),
provider_id=provider_id,
provider_video_id=v.provider_video_id,
site=v.site,
url=v.url,
is_official=v.is_official,
published_at=v.published_at,
)
)
async def ingest_series(
session: AsyncSession,
provider: MetadataProvider,
external_id: str,
*,
ingestion_job_id: uuid.UUID | None = None,
) -> uuid.UUID:
"""Fetch, normalize, and upsert a series plus its season *stubs*
(without episodes — see `ingest_season`). Returns the Aurora series
UUID (new or existing)."""
tmdb_provider = await get_or_create_provider(session, provider.slug, provider.name)
aurora_id_existing, confidence = await match_entity(
session, provider_id=tmdb_provider.id, entity_type="series", external_id=external_id
)
raw = await provider.get_series(external_id)
normalized: NormalizedSeries = normalize_series(raw)
existing_series: Series | None = None
if aurora_id_existing is not None:
existing_series = await session.get(Series, aurora_id_existing)
if existing_series is None:
aurora_id_existing = None
series: Series
if existing_series is not None:
series = existing_series
else:
series = Series(title=normalized.title, sort_title=_sort_title(normalized.title))
session.add(series)
await session.flush()
series.title = normalized.title
series.original_title = normalized.original_title
series.sort_title = _sort_title(normalized.title)
series.overview = normalized.overview
series.tagline = normalized.tagline
series.status = SeriesStatus(normalized.status)
series.first_air_date = normalized.first_air_date
series.last_air_date = normalized.last_air_date
series.number_of_seasons = normalized.number_of_seasons
series.number_of_episodes = normalized.number_of_episodes
series.popularity = normalized.popularity
series.vote_average = normalized.vote_average
series.vote_count = normalized.vote_count
series.source_provider_id = tmdb_provider.id
if normalized.original_language:
language = await refs.get_or_create_language(
session, normalized.original_language, normalized.original_language.upper()
)
series.original_language_code = language.code
await session.flush()
await _replace_series_genres(session, series.id, normalized.genres)
await _replace_series_keywords(session, series.id, normalized.keywords)
await _replace_series_companies(
session, series.id, tmdb_provider.id, normalized.networks, normalized.companies
)
await _replace_series_credits(
session, series.id, tmdb_provider.id, normalized.cast, normalized.crew, normalized.creators
)
await polymorphic.sync_artwork(
session,
entity_type="series",
entity_id=series.id,
provider_id=tmdb_provider.id,
artwork_list=normalized.artwork,
)
await _replace_entity_videos(session, "series", series.id, tmdb_provider.id, normalized.videos)
for stub in normalized.seasons:
season = await tv_repository.get_or_create_season(session, series.id, stub.season_number)
season.title = stub.title
season.overview = stub.overview
season.air_date = stub.air_date
season.episode_count = stub.episode_count
await session.flush()
await polymorphic.sync_artwork(
session,
entity_type="season",
entity_id=season.id,
provider_id=tmdb_provider.id,
artwork_list=[stub.poster] if stub.poster else [],
)
await refs.link_external_id(
session,
entity_type="series",
entity_id=series.id,
provider_id=tmdb_provider.id,
external_id=external_id,
)
for slug, ext_id in normalized.external_ids.items():
ext_provider = await get_or_create_provider(session, slug, slug.upper())
await refs.link_external_id(
session,
entity_type="series",
entity_id=series.id,
provider_id=ext_provider.id,
external_id=ext_id,
)
await upsert_provider_record(
session,
provider_id=tmdb_provider.id,
entity_type="series",
external_id=external_id,
raw_data=raw,
aurora_entity_id=series.id,
match_confidence=confidence if aurora_id_existing else MatchConfidence.NEW,
ingestion_job_id=ingestion_job_id,
)
logger.info("series_ingested", series_id=str(series.id), external_id=external_id)
return series.id
async def _replace_episode_credits(
session: AsyncSession, episode_id: uuid.UUID, provider_id: uuid.UUID, guest_stars, crew
) -> None:
await session.execute(
delete(Credit).where(Credit.entity_type == "episode", Credit.entity_id == episode_id)
)
for ref in guest_stars:
person = await refs.get_or_create_person(
session, provider_id=provider_id, external_id=ref.external_id, name=ref.name, gender=ref.gender
)
session.add(
Credit(
person_id=person.id,
entity_type="episode",
entity_id=episode_id,
department="Acting",
character=ref.character,
billing_order=ref.billing_order,
is_guest=True,
provider_id=provider_id,
)
)
for ref in crew:
person = await refs.get_or_create_person(
session, provider_id=provider_id, external_id=ref.external_id, name=ref.name, gender=ref.gender
)
session.add(
Credit(
person_id=person.id,
entity_type="episode",
entity_id=episode_id,
department=ref.department or "Crew",
job=ref.job,
provider_id=provider_id,
)
)
async def ingest_season(
session: AsyncSession,
provider: MetadataProvider,
series_external_id: str,
season_number: int,
*,
ingestion_job_id: uuid.UUID | None = None,
) -> uuid.UUID:
"""Fetch, normalize, and upsert one season's full episode list. The
series must already be ingested (`ingest_series`) — episodes attach to
an Aurora series_id that has to exist first."""
tmdb_provider = await get_or_create_provider(session, provider.slug, provider.name)
series_id = await refs.find_entity_by_external_id(
session, tmdb_provider.id, "series", series_external_id
)
if series_id is None:
raise ProviderNotFoundError(
f"Cannot ingest season {season_number}: series tmdb:{series_external_id} has not "
"been ingested yet. Call POST /admin/ingest/series first."
)
raw = await provider.get_season(series_external_id, season_number)
normalized = normalize_season(raw)
season = await tv_repository.get_or_create_season(session, series_id, season_number)
season.title = normalized.title
season.overview = normalized.overview
season.air_date = normalized.air_date
season.episode_count = normalized.episode_count
await session.flush()
await polymorphic.sync_artwork(
session,
entity_type="season",
entity_id=season.id,
provider_id=tmdb_provider.id,
artwork_list=normalized.artwork,
)
for ep in normalized.episodes:
episode = await tv_repository.get_or_create_episode(
session,
series_id=series_id,
season_id=season.id,
season_number=season_number,
episode_number=ep.episode_number,
)
episode.title = ep.title
episode.overview = ep.overview
episode.air_date = ep.air_date
episode.runtime_minutes = ep.runtime_minutes
await session.flush()
await _replace_episode_credits(session, episode.id, tmdb_provider.id, ep.guest_stars, ep.crew)
await polymorphic.sync_artwork(
session,
entity_type="episode",
entity_id=episode.id,
provider_id=tmdb_provider.id,
artwork_list=ep.stills,
)
await refs.link_external_id(
session,
entity_type="episode",
entity_id=episode.id,
provider_id=tmdb_provider.id,
external_id=ep.external_id,
)
await upsert_provider_record(
session,
provider_id=tmdb_provider.id,
entity_type="season",
external_id=f"{series_external_id}:{season_number}",
raw_data=raw,
aurora_entity_id=season.id,
match_confidence=MatchConfidence.NEW,
ingestion_job_id=ingestion_job_id,
)
logger.info(
"season_ingested",
season_id=str(season.id),
series_external_id=series_external_id,
season_number=season_number,
)
return season.id