mirror of
https://github.com/truewhile/MeBox.git
synced 2026-09-29 19:36:36 +08:00
8824638efb
Backend
- service/transcoder.go: encoder selector (software / nvenc / qsv /
vaapi) with proper hwaccel + scale_* filters per encoder; configurable
bitrate/preset/height/segment-seconds via transcoder.* config; new
Active() snapshot + ActiveJob struct for the Tasks panel; unit-tested
via buildFFmpegArgs(...).
- service/thetvdb.go: TheTVDB v4 provider — login() caches the JWT for
24h, SearchSeries() returns Match struct.
- service/fanart.go: Fanart.tv provider — high-res movie artwork keyed
by TMDb id; used to upgrade poster/backdrop after a successful match.
- service/scraper.go: provider chain reworked — anime → Bangumi, tv →
TheTVDB, default → TMDb, with optional Fanart upgrade post-match.
- service/discover.go: TMDb /trending/movie/day + /movie/popular for
the Discover rail.
- service/ai.go: OpenAI-compatible client. SmartSearch() turns a free-
form query into a structured SearchIntent JSON; Recommend() emits a
short list of titles given the user's history. Disabled when
ai.api_key is empty.
- service/nfo.go: per-movie .nfo writer (Kodi/Jellyfin schema) +
library-scope batch exporter.
- service/media.go: SoftDelete / Restore / Purge / ListRecycleBin
helpers backed by gorm Unscoped().
- service/service.go: container wires Fanart, TheTVDB, Discover, AI,
NFO; everything still tears down cleanly via Close().
- config: new transcoder.* section (encoder, preset, video_bitrate,
max_rate, buf_size, max_height, segment_seconds) with sensible
defaults.
Handlers / routes
- new files: discover.go, recycle.go, nfo.go, ai.go, tasks.go.
- registers GET /tasks, /discover/{trending,popular},
/ai/{status,search,recommend}; admin-only GET /recycle and
DELETE/POST /media/:id (soft delete / restore / purge); admin-only
POST /media/:id/nfo and /libraries/:id/nfo.
Frontend
- new pages: DiscoverPage, TasksPage, RecycleBinPage; SearchPage gains
an optional AI smart-search toggle that calls /api/ai/search.
- MediaDetailPage gains admin actions for 导出 NFO and 移至回收站.
- new api/ helpers: ai.ts, discover.ts, recycle.ts, tasks.ts.
- App.tsx routes /discover, /tasks, /recycle (last two admin-only).
- Layout sidebar groups now include Discover + Tasks + Recycle Bin.
Docker / config
- Dockerfile: adds intel-media-driver / libva-utils / mesa-va-gallium
so QSV + VAAPI work out of the box on Intel iGPUs.
- docker-compose.yml: documents devices + group_add + nvidia runtime
overrides for hardware transcoding.
Verified: go build, go vet, go test (incl. new TestBuildFFmpegArgs across
software / nvenc / qsv / vaapi encoder profiles); tsc -b && vite build
emits 22 route chunks plus the deferred hls chunk; main bundle 248 KB /
83 KB gzipped.
245 lines
6.5 KiB
Go
245 lines
6.5 KiB
Go
// Package service — scraper orchestrator.
|
|
//
|
|
// ScraperService takes a Media row and tries to enrich it with metadata
|
|
// from one or more providers. Selection is driven by the library type:
|
|
//
|
|
// library.type == "anime" -> Bangumi (fallback: TMDb)
|
|
// library.type == "tv" -> TheTVDB (fallback: TMDb)
|
|
// default -> TMDb
|
|
//
|
|
// After the primary match we optionally upgrade poster / backdrop with
|
|
// Fanart.tv when an API key is configured.
|
|
package service
|
|
|
|
import (
|
|
"context"
|
|
"path/filepath"
|
|
"regexp"
|
|
"strconv"
|
|
"strings"
|
|
"time"
|
|
|
|
"go.uber.org/zap"
|
|
|
|
"github.com/ShukeBta/MediaStationGo/internal/config"
|
|
"github.com/ShukeBta/MediaStationGo/internal/model"
|
|
"github.com/ShukeBta/MediaStationGo/internal/repository"
|
|
)
|
|
|
|
// ScraperService coordinates metadata enrichment across providers.
|
|
type ScraperService struct {
|
|
cfg *config.Config
|
|
log *zap.Logger
|
|
repo *repository.Container
|
|
tmdb *TMDbProvider
|
|
bangumi *BangumiProvider
|
|
thetvdb *TheTVDBProvider
|
|
fanart *FanartProvider
|
|
hub *Hub
|
|
}
|
|
|
|
// NewScraperService is the constructor.
|
|
func NewScraperService(
|
|
cfg *config.Config,
|
|
log *zap.Logger,
|
|
repo *repository.Container,
|
|
tmdb *TMDbProvider,
|
|
bangumi *BangumiProvider,
|
|
thetvdb *TheTVDBProvider,
|
|
fanart *FanartProvider,
|
|
hub *Hub,
|
|
) *ScraperService {
|
|
return &ScraperService{
|
|
cfg: cfg, log: log, repo: repo,
|
|
tmdb: tmdb, bangumi: bangumi, thetvdb: thetvdb, fanart: fanart, hub: hub,
|
|
}
|
|
}
|
|
|
|
// yearPattern extracts a 4-digit year (1900-2099).
|
|
var yearPattern = regexp.MustCompile(`(?:^|[^\d])(19\d{2}|20\d{2})(?:[^\d]|$)`)
|
|
|
|
// noiseTokens are stripped before search.
|
|
var noiseTokens = []string{
|
|
"1080p", "2160p", "4k", "720p", "480p",
|
|
"hdrip", "bluray", "blu-ray", "webrip", "web-dl", "web",
|
|
"x264", "x265", "h264", "h265", "hevc", "avc",
|
|
"hdr", "sdr", "dts", "ddp", "atmos", "aac", "ac3", "flac",
|
|
"remux", "extended", "uncut", "directors-cut", "directors_cut",
|
|
"hkfree", "yify", "rarbg", "ettv", "fgt",
|
|
}
|
|
|
|
// bracketedTag matches "[anything]" or "(anything)" segments.
|
|
var bracketedTag = regexp.MustCompile(`[\[\(][^\]\)]*[\]\)]`)
|
|
|
|
// CleanQuery converts a filename like "Inception.2010.1080p.BluRay.x264.mkv"
|
|
// into a TMDb-friendly title plus an optional year hint.
|
|
func CleanQuery(raw string) (title string, year int) {
|
|
name := strings.TrimSuffix(filepath.Base(raw), filepath.Ext(raw))
|
|
lower := strings.ToLower(name)
|
|
|
|
if m := yearPattern.FindStringSubmatch(lower); len(m) >= 2 {
|
|
if v, err := strconv.Atoi(m[1]); err == nil {
|
|
year = v
|
|
lower = strings.ReplaceAll(lower, m[1], " ")
|
|
}
|
|
}
|
|
|
|
lower = bracketedTag.ReplaceAllString(lower, " ")
|
|
|
|
lower = patSEnE.ReplaceAllString(lower, " ")
|
|
lower = patNxE.ReplaceAllString(lower, " ")
|
|
lower = patEP.ReplaceAllString(lower, " ")
|
|
lower = patCN.ReplaceAllString(lower, " ")
|
|
|
|
for _, t := range noiseTokens {
|
|
lower = strings.ReplaceAll(lower, t, " ")
|
|
}
|
|
for _, sep := range []string{".", "_", "-", "[", "]", "(", ")"} {
|
|
lower = strings.ReplaceAll(lower, sep, " ")
|
|
}
|
|
fields := strings.Fields(lower)
|
|
title = strings.Join(fields, " ")
|
|
return strings.TrimSpace(title), year
|
|
}
|
|
|
|
// EnrichOne runs the provider chain for a single media row.
|
|
func (s *ScraperService) EnrichOne(ctx context.Context, m *model.Media) error {
|
|
lib, err := s.repo.Library.FindByID(ctx, m.LibraryID)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
query := m.Title
|
|
if query == "" {
|
|
query, _ = CleanQuery(m.Path)
|
|
} else {
|
|
query, _ = CleanQuery(query)
|
|
}
|
|
year := m.Year
|
|
if year == 0 {
|
|
_, year = CleanQuery(filepath.Base(m.Path))
|
|
}
|
|
|
|
match := s.lookup(ctx, lib, query, year)
|
|
if match == nil {
|
|
_ = s.repo.DB.Model(&model.Media{}).Where("id = ?", m.ID).
|
|
Update("scrape_status", "no_match").Error
|
|
return nil
|
|
}
|
|
|
|
// Optional Fanart upgrade.
|
|
if s.fanart != nil && s.fanart.Enabled() && match.TMDbID > 0 {
|
|
if a, err := s.fanart.MovieArtwork(ctx, match.TMDbID); err == nil && a != nil {
|
|
if a.Poster != "" {
|
|
match.PosterURL = a.Poster
|
|
}
|
|
if a.Backdrop != "" {
|
|
match.BackdropURL = a.Backdrop
|
|
}
|
|
}
|
|
}
|
|
|
|
updates := map[string]any{
|
|
"title": match.Title,
|
|
"overview": match.Overview,
|
|
"poster_url": match.PosterURL,
|
|
"backdrop_url": match.BackdropURL,
|
|
"rating": match.Rating,
|
|
"year": match.Year,
|
|
"scrape_status": "matched",
|
|
}
|
|
if match.TMDbID > 0 {
|
|
updates["tmdb_id"] = match.TMDbID
|
|
}
|
|
if match.BangumiID > 0 {
|
|
updates["bangumi_id"] = match.BangumiID
|
|
}
|
|
if err := s.repo.DB.Model(&model.Media{}).Where("id = ?", m.ID).
|
|
Updates(updates).Error; err != nil {
|
|
return err
|
|
}
|
|
s.hub.Publish("scrape", map[string]any{
|
|
"media_id": m.ID,
|
|
"title": match.Title,
|
|
"tmdb_id": match.TMDbID,
|
|
"bangumi_id": match.BangumiID,
|
|
})
|
|
return nil
|
|
}
|
|
|
|
// lookup runs the provider chain. When the library is missing we fall
|
|
// back to TMDb only.
|
|
func (s *ScraperService) lookup(ctx context.Context, lib *model.Library, query string, year int) *Match {
|
|
kind := ""
|
|
if lib != nil {
|
|
kind = lib.Type
|
|
}
|
|
switch kind {
|
|
case "anime":
|
|
if s.bangumi != nil {
|
|
if m, err := s.bangumi.Search(ctx, query); err == nil && m != nil {
|
|
return m
|
|
}
|
|
}
|
|
case "tv":
|
|
if s.thetvdb != nil && s.thetvdb.Enabled() {
|
|
if m, err := s.thetvdb.SearchSeries(ctx, query); err == nil && m != nil {
|
|
return m
|
|
}
|
|
}
|
|
}
|
|
if s.tmdb != nil && s.tmdb.Enabled() {
|
|
if m, err := s.tmdb.SearchMovie(ctx, query, year); err == nil && m != nil {
|
|
return m
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// EnrichLibrary runs the provider chain for every "pending" media in a
|
|
// library. It throttles to 4 RPS and publishes a summary event when done.
|
|
func (s *ScraperService) EnrichLibrary(ctx context.Context, libraryID string) (int, error) {
|
|
var rows []model.Media
|
|
q := s.repo.DB.Where("scrape_status = ?", "pending")
|
|
if libraryID != "" {
|
|
q = q.Where("library_id = ?", libraryID)
|
|
}
|
|
if err := q.Find(&rows).Error; err != nil {
|
|
return 0, err
|
|
}
|
|
matched := 0
|
|
for i := range rows {
|
|
select {
|
|
case <-ctx.Done():
|
|
return matched, ctx.Err()
|
|
default:
|
|
}
|
|
if err := s.EnrichOne(ctx, &rows[i]); err != nil {
|
|
s.log.Warn("enrich failed", zap.String("media", rows[i].ID), zap.Error(err))
|
|
continue
|
|
}
|
|
matched++
|
|
time.Sleep(250 * time.Millisecond) // ~4 RPS
|
|
}
|
|
s.hub.Publish("scrape", map[string]any{
|
|
"library_id": libraryID,
|
|
"finished": true,
|
|
"matched": matched,
|
|
})
|
|
return matched, nil
|
|
}
|
|
|
|
// AnyEnabled reports whether at least one provider can run.
|
|
func (s *ScraperService) AnyEnabled() bool {
|
|
if s.tmdb != nil && s.tmdb.Enabled() {
|
|
return true
|
|
}
|
|
if s.bangumi != nil && s.bangumi.Enabled() {
|
|
return true
|
|
}
|
|
if s.thetvdb != nil && s.thetvdb.Enabled() {
|
|
return true
|
|
}
|
|
return false
|
|
}
|