goon/app/models/__init__.py
goon-foss 544de9c5ba feat(ingest): backfill brakujacej dlugosci scen
1 755 421 scen nie ma dlugosci ani na scenie, ani na zrodle, wiec wypadaja z
feedu: w SQL "duration_sec >= 60" nie jest prawda dla NULL, przez co scena o
nieznanej dlugosci znika tak samo jak dziesieciosekundowy smiec. Filtr zostaje,
bo odcina smieci, uzupelniamy dane.

Swiadomie waskie originy. Uniwersalny regex trafia w smieci: porntrex ma w HTML
"duration: 5" reklamy, mypornerleak dlugosc ciastka 720, a xhamster i porntrex
wypisuja dlugosci filmow z paska obok (naiwne dopasowanie dalo 198s zamiast 240s).
Zla dlugosc jest gorsza niz brak, bo dedup opiera sie na niej najmocniej.

- xvideos, xnxx: VideoObject LD-JSON, 5/5 na probce
- xhamster: videoEntity z kontrola zgodnosci id z URL-a
- porntrex pominiety: strona szczegolow nie podaje wlasnej dlugosci

Kolejka jak przy phashu (plan raz, mielenie paczkami, przezywa restart):
845 899 scen, 500 stron co 5 min, czyli ok. 6 dni. Plan powtarza sie co 24h,
zeby swieze sceny bez dlugosci tez trafialy do kolejki.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-20 12:10:22 +02:00

76 lines
2.2 KiB
Python

from app.models.base import Base
from app.models.blacklist import BlacklistedPerformer, BlacklistedStudio, BlacklistedTag
from app.models.bug_report import BugReport
from app.models.external_record import ExternalRecord
from app.models.favorite_movie import FavoriteMovie
from app.models.favorite_performer import FavoritePerformer
from app.models.favorite_scene import FavoriteScene
from app.models.favorite_studio import FavoriteStudio
from app.models.ingest_run import IngestRun
from app.models.merge_candidate import MergeCandidate
from app.models.movie import (
Movie,
MovieChapter,
MovieExternalRef,
MoviePerformer,
MovieTag,
)
from app.models.movie_playback_source import MoviePlaybackSource
from app.models.performer import Performer, PerformerAlias, PerformerExternalRef
from app.models.play_progress import MoviePlayProgress, ScenePlayProgress
from app.models.playback_event import PlaybackEvent
from app.models.playback_source import PlaybackSource
from app.models.duration_backfill_queue import DurationBackfillQueue
from app.models.phash_backfill_queue import PhashBackfillQueue
from app.models.phash_blacklist import PhashBlacklist
from app.models.saved_search import SavedSearch
from app.models.source_stats import SourceStats
from app.models.scene import (
Scene,
SceneExternalRef,
SceneFingerprint,
ScenePerformer,
SceneTag,
)
from app.models.source import Source
from app.models.studio import Studio, StudioAlias, StudioExternalRef
from app.models.tag import Tag
__all__ = [
"Base",
"BlacklistedPerformer",
"BlacklistedStudio",
"BlacklistedTag",
"BugReport",
"ExternalRecord",
"FavoriteMovie",
"FavoritePerformer",
"FavoriteScene",
"FavoriteStudio",
"IngestRun",
"MergeCandidate",
"Movie",
"MovieChapter",
"MovieExternalRef",
"MoviePerformer",
"MoviePlaybackSource",
"MovieTag",
"Performer",
"PerformerAlias",
"PerformerExternalRef",
"MoviePlayProgress",
"ScenePlayProgress",
"PlaybackSource",
"PhashBlacklist",
"SavedSearch",
"Scene",
"SceneExternalRef",
"SceneFingerprint",
"ScenePerformer",
"SceneTag",
"Source",
"Studio",
"StudioAlias",
"StudioExternalRef",
"Tag",
]