Upload turbo.js

turbo.js

@@ -181,11 +181,64 @@ function extractMovieVoices(text) {
 }
 
 async function parseObrutEmbed(embedUrl, browser) {
-    // obrut.show uses Cloudflare - need Puppeteer with anti-detection
-    console.log('[turbo] parsing obrut embed with Puppeteer (Cloudflare bypass)');
+    // obrut.show uses Cloudflare - use Cloudflare Worker as proxy to bypass IP blocking
+    const WORKER_URL = 'https://proxy.recycleactor.workers.dev/turbo/proxy';
+    
+    console.log('[turbo] parsing obrut embed via Cloudflare Worker (bypass Cloudflare IP block)');
+    
+    // Try worker proxy first (parallel requests for better data coverage)
+    const BATCH_SIZE = 10;
+    const MAX_BATCHES = 5;
+    const mergedEntries = new Map();
+    const mergedVoices = new Map();
+
+    for (let batch = 0; batch < MAX_BATCHES; batch++) {
+        const promises = Array.from({ length: BATCH_SIZE }, () =>
+            fetchRaw(WORKER_URL + '?url=' + encodeURIComponent(embedUrl), {
+                'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 Chrome/120 Safari/537.36',
+                'accept': 'text/html'
+            }).then(html => {
+                console.log('[turbo] worker response len:', html.length, 'hasPlayer:', html.includes('new Player('));
+                const pm = html.match(/new\s+Player\s*\(\s*"([A-Za-z0-9+/=]{20,})"/);
+                if (!pm) return null;
+                const text = getCleanText(pm[1]);
+                return { entries: extractEntries(text), movieVoices: extractMovieVoices(text) };
+            }).catch(e => {
+                console.log('[turbo] worker request failed:', e.message);
+                return null;
+            })
+        );
+
+        const results = await Promise.all(promises);
+        
+        for (const r of results) {
+            if (!r) continue;
+            for (const e of r.entries) {
+                const key = e.voice + '|' + e.episode;
+                if (!mergedEntries.has(key)) mergedEntries.set(key, e);
+            }
+            for (const v of r.movieVoices) {
+                if (!mergedVoices.has(v.label)) mergedVoices.set(v.label, v);
+            }
+        }
+
+        const e = mergedEntries.size, v = mergedVoices.size;
+        console.log(`[turbo] batch ${batch + 1}: entries=${e} voices=${v}`);
+        if (v >= 5 || e >= 10) break;
+    }
+
+    const entries = Array.from(mergedEntries.values());
+    const movieVoices = Array.from(mergedVoices.values());
+    
+    if (entries.length > 0 || movieVoices.length > 0) {
+        console.log('[turbo] worker proxy success: entries=', entries.length, 'voices=', movieVoices.length);
+        return { entries, movieVoices };
+    }
+
+    // Fallback: try Puppeteer if worker failed
+    console.log('[turbo] worker proxy failed, trying Puppeteer fallback');
     const page = await browser.newPage();
     try {
-        // More realistic browser fingerprint
         await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36');
         await page.setExtraHTTPHeaders({ 
             'Accept-Language': 'ru-RU,ru;q=0.9,en;q=0.8',
@@ -216,7 +269,7 @@ async function parseObrutEmbed(embedUrl, browser) {
             }
         });
 
-        console.log('[turbo] navigating to obrut embed:', embedUrl.substring(0, 80));
+        console.log('[turbo] Puppeteer navigating to obrut embed:', embedUrl.substring(0, 80));
         
         await page.goto(embedUrl, {
             waitUntil: 'domcontentloaded',
@@ -244,74 +297,25 @@ async function parseObrutEmbed(embedUrl, browser) {
         console.log('[turbo] Puppeteer got HTML, len:', html.length, 'hasPlayer:', html.includes('new Player('));
         
         if (!html.includes('new Player(')) {
-            console.log('[turbo] no Player() found after Cloudflare bypass');
+            console.log('[turbo] Puppeteer: no Player() found');
             return null;
         }
 
         const pm = html.match(/new\s+Player\s*\(\s*"([A-Za-z0-9+/=]{20,})"/);
         if (!pm) {
-            console.log('[turbo] Player() found but no base64 data');
+            console.log('[turbo] Puppeteer: Player() found but no base64 data');
             return null;
         }
 
         const text = getCleanText(pm[1]);
-        const entries = extractEntries(text);
-        const movieVoices = extractMovieVoices(text);
-        console.log('[turbo] Puppeteer: entries=', entries.length, 'voices=', movieVoices.length);
+        const puppeteerEntries = extractEntries(text);
+        const puppeteerVoices = extractMovieVoices(text);
+        console.log('[turbo] Puppeteer: entries=', puppeteerEntries.length, 'voices=', puppeteerVoices.length);
         
-        if (entries.length === 0 && movieVoices.length === 0) {
-            console.log('[turbo] no data extracted, retrying with parallel requests...');
-            // Fallback to parallel HTTP if Puppeteer got Player but no data
-        } else {
-            return { entries, movieVoices };
-        }
+        return { entries: puppeteerEntries, movieVoices: puppeteerVoices };
     } finally {
         await page.close();
     }
-
-    // Fallback: parallel HTTP requests (may work after Puppeteer warmed up the session)
-    const BATCH_SIZE = 10;
-    const MAX_BATCHES = 5;
-    const mergedEntries = new Map();
-    const mergedVoices = new Map();
-
-    for (let batch = 0; batch < MAX_BATCHES; batch++) {
-        const promises = Array.from({ length: BATCH_SIZE }, () =>
-            fetchRaw(embedUrl, {
-                'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 Chrome/120 Safari/537.36',
-                'referer': 'https://kinojump.com/',
-                'accept': 'text/html'
-            }).then(html => {
-                const pm = html.match(/new\s+Player\s*\(\s*"([A-Za-z0-9+/=]{20,})"/);
-                if (!pm) return null;
-                const text = getCleanText(pm[1]);
-                return { entries: extractEntries(text), movieVoices: extractMovieVoices(text) };
-            }).catch(() => null)
-        );
-
-        const results = await Promise.all(promises);
-        
-        for (const r of results) {
-            if (!r) continue;
-            for (const e of r.entries) {
-                const key = e.voice + '|' + e.episode;
-                if (!mergedEntries.has(key)) mergedEntries.set(key, e);
-            }
-            for (const v of r.movieVoices) {
-                if (!mergedVoices.has(v.label)) mergedVoices.set(v.label, v);
-            }
-        }
-
-        const e = mergedEntries.size, v = mergedVoices.size;
-        console.log(`[turbo] batch ${batch + 1}: entries=${e} voices=${v}`);
-        if (v >= 5) break;
-    }
-
-    const entries = Array.from(mergedEntries.values());
-    const movieVoices = Array.from(mergedVoices.values());
-    
-    if (entries.length === 0 && movieVoices.length === 0) return null;
-    return { entries, movieVoices };
 }
 
 // ── Build serial structure ────────────────────────────────────────────────────