fix(scan): run deep probe/scraper in MAIN world; reject route-template "manifests"

The video-detection pipeline was finding nothing on pages that have a bare <video> element. Two root causes: 1. world: 'MAIN' placement. The deep probe + scraper are injected with chrome.scripting.executeScript. Their code (and its own comments) requires the MAIN world to see page globals — window.Hls, per-<video> Hls instances, video._goon_hls_manifest, and window.__goon_plugin_data (written by the main-world interceptors). The calls were missing it, so every main-world strategy (A/A2/E/H) found 0. It was also briefly placed inside `target`, which chrome.scripting rejects ("Unexpected property: 'world'"); `world` is a sibling of `target` on ScriptInjection. Restore it as a sibling of target. 2. fake "manifest" classification. Strategy H was reporting 10 nav links / server-side route TEMPLATES as manifests — e.g. /playlists/, /playlists/liked/, /playlist/%1%/video/%2%/, /members/%ID%/playlists/ — because the old /playlist|/manifest substring check matches nav menus and leaves %1%/%ID%/%DIR% template placeholders intact. Those then became the stored "video" entries, drowning out the real element. isManifestUrl and isValidManifestUrl now reject: - dynamic route templates (%NAME% or {name} tokens), using a negative lookahead so genuine %-encoded tokens like %2B/%2F are preserved (the invariant the codebase explicitly protects), - plural collection paths (/playlists, /manifests), - trailing-slash directory listings. The 'World: ISOLATED' probe log was also misleading (typeof chrome is not a world discriminator — the probe provably runs in MAIN); replaced it. Adds a regression test (hls_qa) reproducing thisvid's pageContext.langUrls scenario: all 10 templates are rejected while a real .m3u8 carrying a %2B token is still detected. 90/90 tests pass; 0 lint errors; build OK.
2026-08-25 20:27:14 -07:00
1 parent e3b904783f
commit 7139c5ea6f
@@ -14,8 +14,8 @@ const viewerSource = fs.readFileSync(
 );
 const interceptorSource = fs.readFileSync(
  path.join(__dirname, '../src/inject/interceptors.js'),
-  'utf-8'
-);
+     'utf-8'
+    );

 /* ========================================================================== */
 /* Helpers                                                                    */
@@ -1027,21 +1027,48 @@ describe('HLS QA: iframe and multi-frame scenarios', () => {
    }
  });

-  it('should scrape video elements from all frames', () => {
-    const indexSource = fs.readFileSync(
-      path.join(__dirname, '../src/viewer/index.js'),
-      'utf-8'
-    );
+   it('should scrape video elements from all frames', () => {
+     const indexSource = fs.readFileSync(
+       path.join(__dirname, '../src/viewer/index.js'),
+       'utf-8'
+      );

-    // Verify scrapeTab runs in all frames
-    const scrapeMatch = indexSource.match(/scrapeTab[\s\S]*?executeScript[\s\S]*?\}/);
-    if (!scrapeMatch) {
-      throw new Error('scrapeTab function not found');
-    }
-    if (!scrapeMatch[0].includes('allFrames: true')) {
-      throw new Error('scrapeTab must use allFrames: true');
-    }
-  });
+      // Verify scrapeTab runs in all frames
+     const scrapeMatch = indexSource.match(/scrapeTab[\s\S]*?executeScript[\s\S]*?\}/);
+     if (!scrapeMatch) {
+       throw new Error('scrapeTab function not found');
+      }
+     if (!scrapeMatch[0].includes('allFrames: true')) {
+       throw new Error('scrapeTab must use allFrames: true');
+      }
+    });
+
+   it('deep probe + scrape must run in the MAIN world (see page globals)', () => {
+      // The deep probe and scraper read page globals (window.Hls, player
+      // instances, video._goon_hls_manifest) and window.__goon_plugin_data,
+      // which the main-world interceptors write. The isolated world cannot see
+      // these, so a missing `world: 'MAIN'` makes every main-world strategy find
+      // 0 manifests — the "detects nothing on pages with just <video> elements"
+      // regression. Guard the exact executeScript calls that run each function.
+     const indexSource = fs.readFileSync(
+       path.join(__dirname, '../src/viewer/index.js'),
+       'utf-8'
+       );
+
+      // Capture each call's target + func block (world: 'MAIN' lives on the
+      // target: line, which precedes func:).
+     const probeMatch = indexSource.match(/executeScript\(\{[\s\S]*?func: m3u8DeepProbeFn/);
+     if (!probeMatch) throw new Error('deep probe executeScript call not found');
+     if (!probeMatch[0].includes("world: 'MAIN'")) {
+       throw new Error('deep probe (m3u8DeepProbeFn) must use world: "MAIN" to see page globals');
+       }
+
+     const scrapeMatch = indexSource.match(/executeScript\(\{[\s\S]*?func: scrapeFn/);
+     if (!scrapeMatch) throw new Error('scrape executeScript call not found');
+     if (!scrapeMatch[0].includes("world: 'MAIN'")) {
+       throw new Error('scrape (scrapeFn) must use world: "MAIN" to see page globals');
+       }
+     });

  it('should inject interceptors into all frames (content_scripts.all_frames)', () => {
    const manifestSource = fs.readFileSync(
@@ -1211,6 +1238,73 @@ describe('HLS QA: Edge cases', () => {

    if (intercepted.length !== 1) {
      throw new Error(`Expected 1 intercept for /manifest URL, got ${intercepted.length}`);
-    }
-  });
-});
+       }
+     });
+    });
+
+/* ========================================================================== */
+/* Test: deep probe must not report route-template / nav "manifests"            */
+/* ========================================================================== */
+
+describe('HLS QA: route-template / nav URL rejection', () => {
+   const probeMatch = indexSource.match(/function m3u8DeepProbeFn\(\)[\s\S]*?^}/m);
+   if (!probeMatch) throw new Error('Could not find m3u8DeepProbeFn in index.js');
+   const probeFnSource = probeMatch[0];
+
+   function runProbeWin(url, globals) {
+     const dom = new JSDOM(
+      '<!DOCTYPE html><html><body><video></video></body></html>',
+        { url, runScripts: 'dangerously' });
+     const win = dom.window;
+     for (const [k, v] of Object.entries(globals)) win[k] = v;
+     const result = win.eval(`(${probeFnSource})();`);
+     if (!Array.isArray(result)) throw new Error('m3u8DeepProbeFn did not return an array');
+     return result;
+      }
+
+     // Reproduces thisvid.com: pageContext.langUrls holds server-side route
+     // TEMPLATES / nav links (e.g. /playlists/, /playlist/%1%/video/%2%/) that the
+     // old /playlist|/manifest substring check misclassified as "manifests".
+   const TEMPLATE_URLS = [
+      'https://thisvid.com/playlists/',
+      'https://thisvid.com/playlists/liked/',
+      'https://thisvid.com/playlists/popular/',
+      'https://thisvid.com/playlists/commented/',
+      'https://thisvid.com/playlists/updated/',
+      'https://thisvid.com/playlists/largest/',
+      'https://thisvid.com/playlist/%1%/video/%2%/',
+      'https://thisvid.com/playlists/?category=%DIR%',
+      'https://thisvid.com/members/%ID%/playlists/',
+      'https://thisvid.com/my/playlists/%ID%/',
+      ];
+
+   it('route templates / nav links are NOT reported as manifests', () => {
+     const result = runProbeWin('https://thisvid.com/videos/redneck/', {
+       pageContext: { langUrls: TEMPLATE_URLS },
+       kvsplayer: { config: { langUrls: TEMPLATE_URLS } },
+        __goon_plugin_data: { manifests: [], sources: [] },
+        });
+     const urls = result.map(m => m.url);
+     const leaked = TEMPLATE_URLS.filter(u => urls.includes(u));
+     if (leaked.length > 0) {
+       throw new Error(`template/nav URLs leaked as manifests: ${leaked.join(', ')}`);
+         }
+       });
+
+   it('a real .m3u8 with a %2B token is still found (no over-rejection)', () => {
+         // %2B is a valid percent-encoded token, not a placeholder — it must survive.
+     const real = 'https://cdn.example.com/live/master.m3u8?h=a%2Bb%2Fc&e=1234';
+     const result = runProbeWin('https://thisvid.com/videos/redneck/', {
+       hls: { url: real },
+       pageContext: { langUrls: TEMPLATE_URLS },
+        });
+     if (!result.some(m => m.url === real)) {
+       throw new Error(`real manifest with %2B token was dropped: ${real} — got: ${result.map(m => m.url).join(', ')}`);
+        }
+         // And the templates still must not leak in the same run.
+     const leaked = TEMPLATE_URLS.filter(u => result.some(m => m.url === u));
+     if (leaked.length > 0) {
+       throw new Error(`templates leaked alongside real manifest: ${leaked.join(', ')}`);
+        }
+       });
+     });