Files
MeBox/internal/service/scraper.go
T
Kiro 7bd6bcfb1b feat: downloads, RSS, subtitles, Bangumi, watcher, stats, profile, audit
Backend
  - service/bangumi.go: Bangumi (bgm.tv) scraper for anime libraries.
  - service/episode_parser.go: SxxExx / NxE / EPxx / 第NN集 parser with
    unit tests; consumed by the scanner for tv/anime libraries.
  - service/scraper.go: provider chain orchestrator picks Bangumi for
    anime libraries (TMDb fallback), TMDb for everything else; emits
    'no_match' rows so we don't retry forever; AnyEnabled() for the
    scanner kick.
  - service/scanner.go: writes season/episode numbers for tv/anime libs
    and reports a 'probed' counter alongside 'added'.
  - service/transcoder.go (existing): unchanged, stays per-media.
  - service/subtitle.go: discovers external subtitles next to the source
    file (.srt/.vtt/.ass/.ssa) and converts SRT/ASS to WebVTT on the fly.
  - service/qbittorrent.go: thread-safe qBittorrent v2 Web UI client
    (login / add / list / delete) with cookie-jar reuse.
  - service/downloads.go: persists download tasks, reads runtime
    qbittorrent.* settings, polls /torrents/info every 5 s and pushes
    the result to WS subscribers ('download' topic).
  - service/subscription.go: 10-minute RSS poller with regex filter,
    GUID dedup persisted in the settings table, and 'subscription' WS
    events on enqueue.
  - service/watcher.go: fsnotify watcher with 5 s coalescing debouncer
    that triggers per-library rescans on create/rename/remove.
  - service/stats.go: dashboard snapshot — totals, recently added,
    gopsutil-driven CPU/mem/disk readings.
  - service/profile.go: non-credential profile patch + admin role mutator.
  - service/audit.go: best-effort writer for the access_logs table.
  - service/service.go: container wires every new service; Boot() spins
    up watcher / downloads poller / subscription scheduler; Close()
    tears them down on graceful shutdown.

Handlers
  - new files: downloads.go, subscriptions.go, subtitles.go, series.go,
    stats.go, profile.go, util.go.
  - handler.go: registers PATCH /me, /libraries/:id/seasons,
    /media/:id/subtitles, /subtitles/:id, /downloads*, /subscriptions*,
    /stats, /admin/users/:id/role.
  - auth.go / media.go: write audit rows for login + library CRUD and
    refresh the watcher when libraries change.

Frontend
  - api: new helpers for downloads, subscriptions, profile, series, stats,
    subtitles; library helper gained scrape().
  - hooks/useWebSocket.ts: shared connection with 3 s reconnect.
  - components/GlobalEvents.tsx: surfaces scan / scrape / subscription
    completion as toasts (mounted at app root).
  - pages: Library now switches to a season-grouped layout for tv/anime
    libraries; Player attaches WebVTT <track> elements; new pages for
    Downloads (live torrent table), Subscriptions, Profile, Stats.
  - components/Layout.tsx + App.tsx: sidebar groups (媒体库 / 自动化 /
    账号 / 管理) and routes for the new pages; /stats and /admin remain
    admin-only.
  - types/index.ts: new types — Subscription, DownloadTask, QBitTorrent,
    Hardware, StatsSnapshot.

Verified: go build, go vet, go test (incl. ParseEpisode + srtToVTT +
stripASSTags) all pass; tsc -b && vite build emits 17 route chunks plus
the deferred hls chunk; main bundle 247 KB / 83 KB gzipped.
2026-05-14 16:07:49 +00:00

225 lines
6.3 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" -> TMDb (movies) — TV episodes inherit
// series metadata; episode-level scraping
// is left as a future step
// default -> TMDb
//
// The orchestrator publishes scrape progress events on the WS hub.
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
hub *Hub
}
// NewScraperService is the constructor.
func NewScraperService(
cfg *config.Config,
log *zap.Logger,
repo *repository.Container,
tmdb *TMDbProvider,
bangumi *BangumiProvider,
hub *Hub,
) *ScraperService {
return &ScraperService{
cfg: cfg, log: log, repo: repo,
tmdb: tmdb, bangumi: bangumi, 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)
// 1. Year first — bracketed years (1999) must survive the next step.
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], " ")
}
}
// 2. Drop everything inside brackets.
lower = bracketedTag.ReplaceAllString(lower, " ")
// 3. Drop episode markers (S01E02 / 1x02 / EP05 / 第03集).
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. The library's
// type decides which provider goes first; a fallback runs when the primary
// returns nothing.
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 {
// Mark explicitly so we don't retry forever.
_ = s.repo.DB.Model(&model.Media{}).Where("id = ?", m.ID).
Update("scrape_status", "no_match").Error
return nil
}
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
}
if kind == "anime" && s.bangumi != nil {
if m, err := s.bangumi.Search(ctx, query); err == nil && m != nil {
return m
}
s.log.Debug("bangumi miss, falling back to tmdb", zap.String("query", query))
}
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
}
return false
}