WeebCentral and MangaPill are off by default, with an admin switch per source

Both are unofficial sites that mostly host unlicensed copies; MangaDex (official
API) stays on. Settings → Admin → Scraper → Hoster settings has a 'Use <source>'
switch. A switched-off source refuses new jobs, keeps queued jobs waiting and is
skipped by nightly update checks. Installations whose queue or history already
used a source keep it switched on, so upgrades don't stop a working queue.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

scraper/service.js

@@ -24,9 +24,13 @@ const DEFAULT_SOURCE_RATES = {
   mangadex: { ...FAST_RATE_SETTINGS },
   mangapill: { ...FAST_RATE_SETTINGS },
 };
+// Sources an admin must switch on first. WeebCentral and MangaPill mostly host unlicensed
+// copies; MangaDex has an official API and handles takedowns. Peers are always available.
+const DEFAULT_SOURCES_ENABLED = { weebcentral: false, mangadex: true, mangapill: false };
 const DEFAULT_SETTINGS = {
   ...FAST_RATE_SETTINGS,
   sourceRates: Object.fromEntries(Object.entries(DEFAULT_SOURCE_RATES).map(([source, rate]) => [source, { ...rate }])),
+  sourcesEnabled: { ...DEFAULT_SOURCES_ENABLED },
   autoUpdateEnabled: true, autoUpdateTime: '03:00',
 };
 
@@ -73,6 +77,15 @@ function validateSettings(input = {}, prior = DEFAULT_SETTINGS) {
     };
     next.sourceRates[source] = validateRateSettings(patch || {}, base, `sourceRates.${source}.`);
   }
+  if (input.sourcesEnabled !== undefined && (!input.sourcesEnabled || typeof input.sourcesEnabled !== 'object' || Array.isArray(input.sourcesEnabled))) {
+    throw new Error('sourcesEnabled must be an object');
+  }
+  next.sourcesEnabled = { ...DEFAULT_SOURCES_ENABLED, ...(prior.sourcesEnabled || {}) };
+  for (const [source, enabled] of Object.entries(input.sourcesEnabled || {})) {
+    if (!Object.hasOwn(DEFAULT_SOURCES_ENABLED, source)) throw new Error(`Unknown source: ${source}`);
+    if (typeof enabled !== 'boolean') throw new Error(`sourcesEnabled.${source} must be true or false`);
+    next.sourcesEnabled[source] = enabled;
+  }
   if (input.autoUpdateEnabled !== undefined) next.autoUpdateEnabled = !!input.autoUpdateEnabled;
   if (input.autoUpdateTime !== undefined) {
     const value = String(input.autoUpdateTime).trim();
@@ -86,6 +99,13 @@ function settingsForSource(settings, source) {
   return { ...settings, ...((settings.sourceRates || {})[source] || {}) };
 }
 
+// Installations from before the switch keep every source they already use: off-by-default
+// applies to new installations, it must not silently stop a working queue.
+function inheritedSourcesEnabled(saved) {
+  const used = new Set([...(saved.queue || []), ...(saved.history || [])].map(item => item && item.source));
+  return Object.fromEntries(Object.entries(DEFAULT_SOURCES_ENABLED).map(([source, enabled]) => [source, enabled || used.has(source)]));
+}
+
 function existingPolicy(value) {
   const policy = String(value || 'skip-any');
   if (!['skip-any', 'add-source'].includes(policy)) throw new Error('existingPolicy must be skip-any or add-source');
@@ -217,11 +237,13 @@ class ScraperService {
   async loadState() {
     if (await exists(this.stateFile)) {
       const saved = JSON.parse(await fs.readFile(this.stateFile, 'utf8'));
+      const savedSettings = saved.settings || {};
+      if (!savedSettings.sourcesEnabled) savedSettings.sourcesEnabled = inheritedSourcesEnabled(saved);
       return {
         version: 3, paused: false, status: 'idle', queue: [], history: [], publishedRevision: 0,
         currentIds: {}, sourcePaused: {},
         settings: DEFAULT_SETTINGS, ...saved,
-        settings: validateSettings(saved.settings || {}, DEFAULT_SETTINGS),
+        settings: validateSettings(savedSettings, DEFAULT_SETTINGS),
       };
     }
     const state = {
@@ -239,7 +261,7 @@ class ScraperService {
         status: completed.has(item.id) ? 'complete' : 'queued', order: index,
         added: legacy.created || new Date().toISOString(),
       }));
-      state.settings = validateSettings(legacy.settings || {}, DEFAULT_SETTINGS);
+      state.settings = validateSettings({ ...(legacy.settings || {}), sourcesEnabled: inheritedSourcesEnabled(state) }, DEFAULT_SETTINGS);
       state.migratedFrom = this.legacyStateFile;
     }
     return state;
@@ -401,7 +423,8 @@ class ScraperService {
     let queued = 0, skipped = 0;
     for (const manga of inventory.mangas) {
       if (!manga.autoUpdate) continue;
-      const supported = manga.sources.map(source => ({ source, found: this.resolveAdapter(source.url) })).filter(item => item.found);
+      const supported = manga.sources.map(source => ({ source, found: this.resolveAdapter(source.url) }))
+        .filter(item => item.found && this.sourceEnabled(item.found.adapter.id));
       if (!supported.length) { skipped++; continue; }
       const preferred = manga.meta?.['x-scraper']?.preferredSource;
       const selected = supported.find(item => item.found.adapter.id === preferred) || supported[0];
@@ -598,9 +621,16 @@ class ScraperService {
     };
   }
 
+  sourceEnabled(source) {
+    return !Object.hasOwn(DEFAULT_SOURCES_ENABLED, source) || this.state.settings.sourcesEnabled?.[source] === true;
+  }
+
   async enqueue(input) {
     const found = this.resolveAdapter(input.url);
     if (!found) throw new Error('No installed scraper adapter accepts this URL');
+    if (!this.sourceEnabled(found.adapter.id)) {
+      throw new Error(`${found.adapter.label || found.adapter.id} is switched off. An admin can switch it on under Settings → Admin → Scraper → Hoster settings.`);
+    }
     const workIdentity = normalizeWorkIdentity(input.workIdentity);
     if (input.workIdentity != null && !workIdentity) throw new Error('Invalid manga work identity');
     const scope = normalizeScope(input.scope || {});
@@ -902,7 +932,8 @@ class ScraperService {
             continue;
           }
           const source = found.adapter.id;
-          if (this.active.has(source) || this.state.sourcePaused[source]) continue;
+          // A switched-off source keeps its queued jobs; they wait until it is switched on again.
+          if (this.active.has(source) || this.state.sourcePaused[source] || !this.sourceEnabled(source)) continue;
           if (this.state.circuits[source]?.state === 'open') continue;
           if (item.libraryMangaId && [...this.active.values()].some(entry => {
             const activeItem = this.state.queue.find(candidate => candidate.id === entry.id);

scraper/test/scraper.test.js

@@ -426,6 +426,9 @@ test('daemon queue state is durable while paused', async t => {
   }));
   const service = await new ScraperService({ libraryRoot: path.join(temp, 'library'), dataRoot }).init();
   t.after(async () => { await service.close(); await fs.rm(temp, { recursive: true, force: true }); });
+  // WeebCentral is off on a fresh installation until an admin switches it on.
+  await assert.rejects(() => service.enqueue({ url: 'https://weebcentral.com/series/01ABCDEF/My-Series' }), /switched off/);
+  await service.updateSettings({ sourcesEnabled: { weebcentral: true } });
   const item = await service.enqueue({ url: 'https://weebcentral.com/series/01ABCDEF/My-Series' });
   assert.equal(item.status, 'queued');
   const scoped = await service.enqueue({ url: 'https://weebcentral.com/series/01ABCDEF/My-Series', scope: { mode: 'latest' } });
@@ -439,6 +442,30 @@ test('daemon queue state is durable while paused', async t => {
   assert.equal((await service.publicState()).queue.length, 0);
 });
 
+test('sources are off by default but existing installations keep the ones they use', async t => {
+  assert.deepEqual(validateSettings({}).sourcesEnabled, { weebcentral: false, mangadex: true, mangapill: false });
+  assert.throws(() => validateSettings({ sourcesEnabled: { weebcentral: 'yes' } }), /true or false/);
+  assert.throws(() => validateSettings({ sourcesEnabled: { other: true } }), /Unknown source/);
+  const temp = await fs.mkdtemp(path.join(os.tmpdir(), 'mcscraper-sources-'));
+  const dataRoot = path.join(temp, 'data');
+  await fs.mkdir(dataRoot, { recursive: true });
+  const { sourcesEnabled, ...older } = validateSettings({});
+  await fs.writeFile(path.join(dataRoot, 'queue.json'), JSON.stringify({
+    version: 3, paused: true, status: 'paused', settings: older, publishedRevision: 0,
+    queue: [{ id: 'A', title: 'A', url: 'https://weebcentral.com/series/AAA/A', source: 'weebcentral', status: 'queued', order: 0 }],
+    history: [],
+  }));
+  const service = await new ScraperService({ libraryRoot: path.join(temp, 'library'), dataRoot }).init();
+  t.after(async () => { await service.close(); await fs.rm(temp, { recursive: true, force: true }); });
+  assert.deepEqual(service.state.settings.sourcesEnabled, { weebcentral: true, mangadex: true, mangapill: false });
+  await assert.rejects(() => service.enqueue({ url: 'https://mangapill.com/manga/2/one-piece' }), /MangaPill is switched off/);
+  // Switching a source off keeps its jobs queued instead of failing them.
+  await service.updateSettings({ sourcesEnabled: { weebcentral: false } });
+  assert.equal(service.sourceEnabled('weebcentral'), false);
+  assert.equal(service.sourceEnabled('peer-abc'), true, 'peers have no switch');
+  assert.equal(service.state.queue[0].status, 'queued');
+});
+
 test('retry recovers stale downloading entries before work resumes', async t => {
   const temp = await fs.mkdtemp(path.join(os.tmpdir(), 'mcscraper-retry-'));
   const dataRoot = path.join(temp, 'data');