Fixes issue with pornhub. Removes references.

src/background/background.js

@@ -227,6 +227,11 @@ async function injectFreshToken(url) {
 // re-query storage for a freshly-rotated token.
 function invalidateTokenCache() { tokenCache.clear(); }
 
+// CDN registrable domains whose referer we have already captured this SW
+// lifetime, so we do not re-query the tab for every segment of a stream.
+// Lost if the SW is killed; persistReferer's storage dedupe covers a fresh SW.
+const refererCapturedDomains = new Set();
+
 chrome.webRequest.onBeforeRequest.addListener(
   async (details) => {
     if (details.tabId < 0) return;
@@ -235,6 +240,28 @@ chrome.webRequest.onBeforeRequest.addListener(
     if (isVideoRequest(details.url)) {
       console.log('[goon-bg] webRequest: video request in tab', details.tabId, ':', details.url.substring(0, 180));
       await persistVideoRequest(details.tabId, details.url);
+       // Capture the provider referer for this CDN host from the source tab's
+       // URL: the browser sends the referring page's URL as the Referer for a
+       // cross-origin video request, and that IS the tab's URL. extraInfoSpec
+       // (reading the actual request headers) is rejected by some Chromium
+       // builds and fails the whole service worker, so we derive the referer
+       // from the tab instead. The `tabs` + host_permissions already allow it.
+      const host = hostOf(details.url);
+      const domain = host ? registrableDomain(host) : '';
+      if (domain && !refererCapturedDomains.has(domain)) {
+        try {
+          const tab = await chrome.tabs.get(details.tabId);
+          const ref = tab && tab.url;
+          if (ref) {
+            await persistReferer(host, ref);
+            refererCapturedDomains.add(domain);
+            console.log('[goon-bg] captured referer for', domain, '->', ref);
+          }
+        } catch {
+          // Tab may have closed mid-stream; a later request from a live tab
+          // re-captures. Best-effort.
+        }
+      }
       }
 
       // Also capture HLS manifest URLs (original logic)
@@ -258,7 +285,7 @@ chrome.webRequest.onBeforeRequest.addListener(
 );
 
 // Clean up stale PER-TAB entries when tabs are closed. NOTE: 'goon_referers' is
-// a host-keyed GLOBAL store — it must outlive its capture tab so a proxy fetch
+// a domain-keyed GLOBAL store — it must outlive its capture tab so a proxy fetch
 // for that host still finds its referer after the source tab is closed. It is
 // therefore NOT removed here (only the per-tab vr_requests_/wr_manifests_ keys
 // are). Stale referers are pruned opportunistically in persistReferer.
@@ -308,87 +335,74 @@ function hostOf(url) {
   try { return new URL(url).host.toLowerCase(); } catch { return ''; }
 }
 
-// Best-effort origin for a host when no referer was captured for it. Used only
-// as a fallback; a captured referer always wins.
-function originFromHost(host) {
-  return host ? 'https://' + host + '/' : '';
+// Registrable domain of a CDN host — the label a single provider's referer
+// applies to. A referer-protecting CDN serves manifests and segments from many
+// edge subdomains that share ONE
+// provider referer, so we key the referer store, the DNR rule, and proxy-host
+// matching on this domain rather than the exact subhost.
+//
+// Heuristic: the last two DNS labels. Correct for the overwhelmingly common
+// single-label public suffixes (.com, .net, .org, .io, ...). Known caveat:
+// multi-label public suffixes such as .co.uk / .com.au collapse to the public
+// suffix itself (foo.co.uk -> co.uk); that is an exotic edge case and no worse
+// than the exact-host behavior it replaces. A single-level host (no dot, or a
+// bare TLD) is returned unchanged.
+function registrableDomain(host) {
+  if (!host) return '';
+  const parts = host.split('.');
+  if (parts.length < 2) return host;
+  return parts.slice(-2).join('.');
 }
 
-// Read the `Referer` request header (the browser may title-case it; the
- // (onBeforeSendHeaders cannot read request headers in MV3 without a blocking API,
- // so we fall back to the page origin for hosts that send no referer).
-function readReferer(headers) {
-  if (!Array.isArray(headers)) return '';
-  for (const h of headers) {
-    if (h && h.name && h.name.toLowerCase() === 'referer') return h.value || '';
-   }
-  return '';
-}
 
 // How long a captured referer is trusted before it is pruned on the next
-// persist. Referers are short-lived session tokens; this keeps the per-host
-// global store from accumulating stale entries without tying cleanup to tab
-// close (a still-open source tab's referer must survive other tabs closing).
-const REFERER_TTL_MS = 30 * 60 * 1000;
+// persist. Kept long enough for the scan-now / watch-later flow (a user scans a
+// page, then opens the viewer much later) without tying cleanup to tab close (a
+// still-open source tab's referer must survive other tabs closing).
+const REFERER_TTL_MS = 7 * 24 * 60 * 60 * 1000;
 
-// Persist the captured referer per CDN host so the proxy can re-use it even
-// after this capture tab closes. Keyed by host so a proxy for that host can
-// look its referer up without knowing the source tab. Each entry is stamped
-// with a capture time; entries older than the TTL are pruned opportunistically
-// here (never on tab close).
+// Persist the captured referer per CDN registrable domain so the proxy can
+// re-use it even after the capture tab closes. Keyed by the host's registrable
+// domain so a single provider referer covers every edge subdomain (a CDN serves
+// manifests/segments from many subhosts that share one referer), and so a proxy
+// for any sibling subhost can look it up without knowing the source tab. Each
+// entry is stamped with a capture time; entries older than the TTL are pruned
+// opportunistically here (never on tab close).
 async function persistReferer(host, referer) {
-  if (!host || !referer) return;
+  const domain = registrableDomain(host);
+  if (!domain || !referer) return;
   try {
     const stored = await chrome.storage.local.get('goon_referers');
     const map = stored['goon_referers'] || {};
     const now = Date.now();
-    // Opportunistic per-host prune: drop entries older than the TTL.
+    // Opportunistic per-domain prune: drop entries older than the TTL.
     for (const [h, entry] of Object.entries(map)) {
-      if (h !== host && (!entry || !entry.at || now - entry.at > REFERER_TTL_MS)) {
+      if (h !== domain && (!entry || !entry.at || now - entry.at > REFERER_TTL_MS)) {
         delete map[h];
       }
     }
-    const current = map[host];
+    const current = map[domain];
     if (current && current.referer === referer) return;
-    map[host] = { referer, at: now };
+    map[domain] = { referer, at: now };
     await chrome.storage.local.set({ goon_referers: map });
       } catch (e) {
     console.warn('[goon-bg] persistReferer failed:', e && e.message ? e.message : e);
      }
  }
 
-// Look up the referer captured for a host. '' when none has been captured
-// (or the stored entry is malformed).
+// Look up the referer captured for a host's registrable domain. '' when none
+// has been captured (or the stored entry is malformed).
 async function getReferer(host) {
   if (!host) return '';
   try {
     const stored = await chrome.storage.local.get('goon_referers');
-    const entry = (stored['goon_referers'] || {})[host];
+    const entry = (stored['goon_referers'] || {})[registrableDomain(host)];
     return entry && entry.referer ? entry.referer : '';
       } catch {
     return '';
       }
  }
 
-// Capture the referer the real page sends for its video requests.
-chrome.webRequest.onBeforeSendHeaders.addListener(
-  async (details) => {
-    if (details.tabId < 0) return;
-    if (!isVideoRequest(details.url)) return;
-    const host = hostOf(details.url);
-    if (!host) return;
-    const referer = readReferer(details.requestHeaders);
-    if (referer) {
-      // The browser already built a referer from the source page — use it.
-      await persistReferer(host, referer);
-      } else {
-      // No referer was sent; assume the page's origin is the expected referer.
-      await persistReferer(host, originFromHost(host));
-      }
-   },
-{ urls: ['<all_urls>'] }
-);
-
 // Install (idempotently) a DNR rule that sets the captured referer for a given
 // CDN host. The value comes from capture (or a fallback origin), never a
 // hardcoded site. Scoped to the requested host so only proxy fetches for that
@@ -404,7 +418,8 @@ const refererRuleInstalled = new Map();
 const refererRuleLocks = new Map();
 
 async function ensureRefererRule(host, referer) {
-  if (!host || !referer) return;
+  const domain = registrableDomain(host);
+  if (!domain || !referer) return;
   const api = chrome.declarativeNetRequest;
   if (!api || typeof api.updateSessionRules !== 'function') {
     console.warn('[goon-bg] declarativeNetRequest unavailable; skipping referer rule');
@@ -413,10 +428,10 @@ async function ensureRefererRule(host, referer) {
 
    // Serialize per host so the idempotency check + updateSessionRules is atomic.
   const run = (async () => {
-    if (refererRuleInstalled.has(host) && refererRuleInstalled.get(host) === referer) {
+    if (refererRuleInstalled.has(domain) && refererRuleInstalled.get(domain) === referer) {
       return;
     }
-    const ruleId = refererRuleIdFor(host);
+    const ruleId = refererRuleIdFor(domain);
     try {
       // Remove only THIS host's own rule id, then add it back scoped to the host.
       await api.updateSessionRules({
@@ -435,17 +450,17 @@ async function ensureRefererRule(host, referer) {
           condition: {
             // Host + subdomains ONLY, so only proxy fetches for this host get the
             // rewritten referer; the source page's own requests keep theirs.
-            requestDomains: [host],
+            requestDomains: [domain],
           },
         }],
       });
-      refererRuleInstalled.set(host, referer);
-      console.log('[goon-bg] DNR referer rule installed for', host, '(' + ruleId + ')');
+      refererRuleInstalled.set(domain, referer);
+      console.log('[goon-bg] DNR referer rule installed for', domain, '(' + ruleId + ')');
     } catch (e) {
       console.warn('[goon-bg] ensureRefererRule failed:', e && e.message ? e.message : e);
     }
-  })().finally(() => { refererRuleLocks.set(host, null); });
-  refererRuleLocks.set(host, run);
+  })().finally(() => { refererRuleLocks.set(domain, null); });
+  refererRuleLocks.set(domain, run);
   return run;
 }
 
@@ -533,10 +548,13 @@ chrome.runtime.onMessage.addListener((message, _sender, sendResponse) => {
                 const proxyHost = hostOf(message.url);
                 if (proxyHost) {
                    // Prefer the provider's real referer captured from the live
-                   // tab; fall back to a viewer-supplied or host-derived origin.
+                   // tab (domain-aware), or the entry's scan-time referer the viewer sent.
+                    // With neither, install no rule: a self-origin referer is
+                    // guaranteed-wrong for hotlink protection, so we never fall
+                    // back to one (it would just 412).
                    const captured = await getReferer(proxyHost);
-                   const referer = captured || message.referer || originFromHost(proxyHost);
-                   await ensureRefererRule(proxyHost, referer);
+                   const referer = captured || message.referer || '';
+                   if (referer) await ensureRefererRule(proxyHost, referer);
                    }
                       // hls.js resolves sub-playslists/segments relative to the master
                       // and can DROP the token query, handing us a token-less
@@ -571,6 +589,24 @@ chrome.runtime.onMessage.addListener((message, _sender, sendResponse) => {
          return true;
          }
 
+    case 'GOON_GET_REFERERS': {
+        // Resolve the provider referer captured for each manifest host
+        // (domain-aware: one provider referer covers every edge subdomain).
+        // Used at scan time to bind the referer to a stored video entry so it
+        // survives the watch-later flow.
+       async function getReferers(message, sendResponse) {
+         const hosts = Array.isArray(message.hosts) ? message.hosts : [];
+         const referers = {};
+         for (const host of hosts) {
+           const r = await getReferer(host);
+           if (r) referers[host] = r;
+            }
+         sendResponse({ ok: true, referers });
+        }
+       getReferers(message, sendResponse);
+       return true;
+        }
+
     default:
       console.warn('[goon-plugin] Unknown message type:', message.type);
   }

src/viewer/index.js

@@ -1147,6 +1147,7 @@ async function scanVideos(tabsToScan) {
   }
 
   const items = [...seen.values()];
+  await attachReferers(items);
   const skipped = scrapeResults.filter(r => r === null).length;
 
   log('scanVideos complete: scanned=', tabResults.length, 'skipped=', skipped, 'unique items=', items.length);
@@ -1157,6 +1158,31 @@ async function scanVideos(tabsToScan) {
   return { items, scanned: tabResults.length, skipped };
 }
 
+/**
+ * Bind the provider referer the SW captured (domain-aware) to each item so it
+ * survives the watch-later flow and covers the sibling edge subdomains a segment
+ * may resolve to. Best-effort: playback still falls back to the SW's live store.
+ */
+async function attachReferers(items) {
+  const hostOf = (url) => { try { return new URL(url).host.toLowerCase(); } catch { return ''; } };
+  const hosts = [];
+  for (const it of items) {
+    const host = hostOf(it.hlsManifest || it.src || '');
+    if (host) hosts.push(host);
+    }
+  if (hosts.length === 0) return;
+  let referers = {};
+  try {
+    const resp = await chrome.runtime.sendMessage({ type: 'GOON_GET_REFERERS', hosts });
+    if (resp && resp.referers) referers = resp.referers;
+    } catch { /* referer is best-effort; the SW still resolves it at play time */ }
+  if (!Object.keys(referers).length) return;
+  for (const it of items) {
+    const host = hostOf(it.hlsManifest || it.src || '');
+    if (host && referers[host]) it.referer = referers[host];
+    }
+}
+
 /** Store video entries in chrome.storage.local. */
 async function storeVideos(items) {
   const stored = items.map(v => ({
@@ -1165,6 +1191,7 @@ async function storeVideos(items) {
     tab: v.tab,
     mediaType: v.mediaType || 'video',
     hlsManifest: v.hlsManifest || undefined,
+    referer: v.referer || undefined,
   }));
   await chrome.storage.local.set({
     [STORAGE_KEY]: stored,

src/viewer/schema.json

@@ -33,6 +33,11 @@
       "type": "string",
       "enum": ["direct", "hls"],
       "description": "Media delivery format. Defaults to 'direct' when omitted. Set to 'hls' for HTTP Live Streaming."
+    },
+    "referer": {
+      "type": ["string", "null"],
+      "format": "uri",
+      "description": "Provider Referer captured at scan time for the manifest's CDN; the proxy sends it so a referer-protecting CDN accepts sibling edge subdomains. Optional."
     }
   },
   "additionalProperties": false,

src/viewer/viewer.js

@@ -178,7 +178,7 @@ const panelsEl = document.getElementById('panels');
           // Route through the service worker to bypass the CDN's CORS/Referer
         // restrictions. The SW adds the required Referer and returns base64.
          console.log('[goon-viewer] Proxying via SW:', (url || '').substring(0, 120));
-        chrome.runtime.sendMessage({ type: 'GOON_PROXY_FETCH', url, referer: originForUrl(url) }, (resp) => {
+        chrome.runtime.sendMessage({ type: 'GOON_PROXY_FETCH', url, referer: refererForUrl(url) }, (resp) => {
           if (self._aborted) return;
           const lastErr = chrome.runtime.lastError;
           if (lastErr || !resp || !resp.ok) {
@@ -264,19 +264,34 @@ HlsLoader.canSupportLoader = function () { return true; };
  // hardcode a particular CDN.
  const PROXY_HOSTS_KEY = 'goon_proxy_hosts';
  const proxyHosts = new Set();
+ // Provider referers bound to a stored entry at scan time, keyed by the entry's
+ // manifest registrable domain. A single provider referer covers every edge
+ // subdomain, so a segment on a sibling subhost resolves to the same referer.
+ const refererByDomain = new Map();
  (async () => {
    try {
      const stored = await chrome.storage.local.get(PROXY_HOSTS_KEY);
      const hosts = stored[PROXY_HOSTS_KEY];
-     if (Array.isArray(hosts)) for (const h of hosts) proxyHosts.add(String(h).toLowerCase());
+     if (Array.isArray(hosts)) for (const h of hosts) proxyHosts.add(registrableDomainOf(String(h).toLowerCase()));
     } catch { /* ignore */ }
    })();
 
- // Origin for a URL's host — used as the Referer to request when a proxy fetch
- // is made for that host (the SW also captures the live referer per host).
- function originForUrl(url) {
-   if (!url) return '';
-   try { return new URL(url).origin + '/'; } catch { return ''; }
+ // Registrable domain of a CDN host — the label a single provider referer
+ // applies to (a referer-protecting CDN serves from many edge subdomains that
+ // share one referer). Last-two-labels heuristic; mirrors the SW's copy.
+ function registrableDomainOf(host) {
+   if (!host) return '';
+   const parts = host.split('.');
+   if (parts.length < 2) return host;
+   return parts.slice(-2).join('.');
+ }
+
+ // The provider referer to send for a proxied request: the referer bound to the
+ // entry at scan time (domain-keyed), or '' when none was captured. No self-origin
+ // fallback — a self-origin referer is guaranteed-wrong for hotlink protection.
+ function refererForUrl(url) {
+   const ref = refererByDomain.get(registrableDomainOf(hostOfUrl(url)));
+   return ref || '';
  }
 
  // Whether a given video URL should be proxied: its host is a known
@@ -284,7 +299,7 @@ HlsLoader.canSupportLoader = function () { return true; };
  function needsProxy(url) {
    if (!url || typeof url !== 'string') return false;
    const host = hostOfUrl(url);
-   return host ? proxyHosts.has(host) : false;
+   return host ? proxyHosts.has(registrableDomainOf(host)) : false;
  }
 
  // host of a URL (lowercased); '' when malformed.
@@ -1184,11 +1199,20 @@ async function init() {
       // Probe CORS on each video URL. Hosts that block extension-origin
       // requests are learned as referer-protected and persisted so the viewer
       // routes them through the service-worker proxy.
+     // Bind each entry's scan-time referer to its manifest's registrable
+     // domain, so the proxy sends it for every edge subdomain the provider
+     // serves from (segments often resolve to a sibling subhost).
+     for (const entry of videoUrls) {
+       const ref = entry && entry.referer;
+       if (!ref) continue;
+       const dom = registrableDomainOf(hostOfUrl(entry.src || entry.hlsManifest || ''));
+       if (dom) refererByDomain.set(dom, ref);
+       }
      const urlsToTest = videoUrls.map(v => v.src || v.hlsManifest || 'none').filter(u => u !== 'none' && typeof u === 'string');
      const blockedHosts = new Set();
      for (const url of [...new Set(urlsToTest)]) {
        const corsOk = await corsCheck(url);
-       if (!corsOk) blockedHosts.add(hostOfUrl(url));
+       if (!corsOk) blockedHosts.add(registrableDomainOf(hostOfUrl(url)));
         console.log('[goon-viewer] CORS', corsOk ? 'OK' : 'BLOCKED:', url.substring(0, 120));
         }
      if (blockedHosts.size > 0) {