@definisi/vidsrc-scraper 1.0.1 → 1.0.3

package/README.md

@@ -1,11 +1,19 @@
 # @definisi/vidsrc-scraper
 
-Extract HLS streaming URLs from VidSrc using TMDB ID.
+Extract HLS streaming URLs from VidSrc using Playwright.
 
-## Install
+## ⚠️ Important Notice
+
+VidSrc currently uses Cloudflare Turnstile CAPTCHA protection. This means:
+
+1. **Headless mode doesn't work** - The scraper must run with a visible browser (`headless: false`)
+2. **Manual CAPTCHA solving may be required** - You may need to complete the Turnstile challenge manually
+3. **Automation is limited** - Fully automated scraping is currently not possible due to bot detection
+
+## Installation
 
 ```bash
-npm install @definisi/vidsrc-scraper
+npm install @definisi/vidsrc-scraper playwright
 npx playwright install firefox
 ```
 
@@ -14,44 +22,36 @@ npx playwright install firefox
 ```typescript
 import { scrapeVidsrc } from '@definisi/vidsrc-scraper';
 
-// Movie
-const movie = await scrapeVidsrc('27205');
-
-// TV Show
-const tv = await scrapeVidsrc('1396', 'tv', '1', '1');
-
-// With options
+// Scrape a movie by TMDB ID
 const result = await scrapeVidsrc('27205', 'movie', null, null, {
-  timeout: 30000,
-  headless: true,
-  cacheTtl: 600,
+  timeout: 120000,
+  headless: false,  // Must be false for Turnstile
 });
-```
-
-## API
 
-### scrapeVidsrc(tmdbId, type?, season?, episode?, options?)
+if (result.success) {
+  console.log('HLS URL:', result.hlsUrl);
+  console.log('Subtitles:', result.subtitles);
+}
 
-| Parameter | Type | Default | Description |
-|-----------|------|---------|-------------|
-| tmdbId | string | - | TMDB ID |
-| type | 'movie' \| 'tv' | 'movie' | Content type |
-| season | string \| null | null | Season number (TV only) |
-| episode | string \| null | null | Episode number (TV only) |
-| options | ScrapeOptions | {} | Optional config |
+// Scrape a TV episode
+const tvResult = await scrapeVidsrc('1399', 'tv', '1', '1', {
+  timeout: 120000,
+  headless: false,
+});
+```
 
-### ScrapeOptions
+## Options
 
 | Option | Type | Default | Description |
 |--------|------|---------|-------------|
-| timeout | number | 60000 | Page load timeout (ms) |
-| headless | boolean | true | Run browser headless |
-| cacheTtl | number | 900 | Cache TTL (seconds) |
+| timeout | number | 120000 | Total timeout in milliseconds |
+| cacheTtl | number | 900 | Cache time-to-live in seconds |
+| headless | boolean | false | Run browser in headless mode (not recommended) |
 
-### ScrapeResult
+## Result Type
 
 ```typescript
-{
+interface ScrapeResult {
   tmdbId: string;
   type: 'movie' | 'tv';
   season: string | null;
@@ -63,11 +63,27 @@ const result = await scrapeVidsrc('27205', 'movie', null, null, {
 }
 ```
 
-### clearCache()
+## Playback
+
+The HLS URLs require proper headers. Example with VLC:
+
+```bash
+vlc "HLS_URL" --http-user-agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:121.0) Gecko/20100101 Firefox/121.0"
+```
+
+## Limitations
 
-Clear the in-memory cache.
+- Requires Playwright and Firefox browser
+- Requires visible browser window (headless mode blocked by Turnstile)
+- May require manual CAPTCHA completion
+- Results are cached to reduce CAPTCHA occurrences
+- VidSrc may change their protection at any time
 
 ## Requirements
 
 - Node.js 18+
-- Playwright Firefox
+- Playwright
+
+## License
+
+MIT

package/dist/scraper.js

@@ -20,25 +20,28 @@ function setCache(key, data) {
     cache.set(key, { data, timestamp: Date.now() });
 }
 function buildEmbedUrl(tmdbId, type, season, episode) {
-    const base = 'https://vidsrcme.vidsrc.icu/embed';
+    const base = 'https://vidsrc.xyz/embed';
     if (type === 'tv') {
-        return `${base}/tv?tmdb=${tmdbId}&season=${season}&episode=${episode}&autoplay=1&ds_lang=en`;
+        return `${base}/tv/${tmdbId}/${season}/${episode}`;
     }
-    return `${base}/movie?tmdb=${tmdbId}&autoplay=1&ds_lang=en`;
+    return `${base}/movie/${tmdbId}`;
 }
 function isValidM3u8Url(url) {
     return url.includes('.m3u8') && !url.includes('{v') && !url.includes('{s');
 }
-async function setupResponseHandler(context, result) {
-    context.on('response', async (response) => {
-        const url = response.url();
-        if (isValidM3u8Url(url) && !result.hlsUrl) {
-            result.hlsUrl = url;
-        }
-        if (url.includes('.vtt') || url.includes('.srt')) {
-            result.subtitles.push(url);
+async function clickPlayButton(frame) {
+    const selectors = ['#pl_but', '#pl_but_background', '.play-btn'];
+    for (const sel of selectors) {
+        try {
+            const btn = await frame.$(sel);
+            if (btn) {
+                await btn.click();
+                return true;
+            }
         }
-    });
+        catch { }
+    }
+    return false;
 }
 export async function scrapeVidsrc(tmdbId, type = 'movie', season = null, episode = null, options = {}) {
     const opts = { ...DEFAULT_OPTIONS, ...options };
@@ -50,40 +53,52 @@ export async function scrapeVidsrc(tmdbId, type = 'movie', season = null, episod
     const browser = await firefox.launch({ headless: opts.headless });
     const context = await browser.newContext({
         userAgent: 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:121.0) Gecko/20100101 Firefox/121.0',
-        viewport: { width: 1920, height: 1080 },
+        viewport: { width: 1280, height: 720 },
     });
     const page = await context.newPage();
-    const responseData = { hlsUrl: null, subtitles: [] };
-    await setupResponseHandler(context, responseData);
+    let hlsUrl = null;
+    const subtitles = [];
+    // Capture network responses
+    context.on('response', (response) => {
+        const url = response.url();
+        if (isValidM3u8Url(url) && !hlsUrl) {
+            hlsUrl = url;
+        }
+        if ((url.includes('.vtt') || url.includes('.srt')) && !subtitles.includes(url)) {
+            subtitles.push(url);
+        }
+    });
     try {
         const embedUrl = buildEmbedUrl(tmdbId, type, season, episode);
-        await page.goto(embedUrl, { waitUntil: 'networkidle', timeout: opts.timeout });
+        await page.goto(embedUrl, { waitUntil: 'commit', timeout: opts.timeout });
         await page.waitForTimeout(3000);
-        for (const frame of page.frames()) {
-            const frameUrl = frame.url();
-            if (frameUrl.includes('cloudnestra.com/rcp/') || frameUrl.includes('/rcp/')) {
-                try {
-                    await frame.click('#pl_but, #pl_but_background, .play-btn', { timeout: 5000 });
-                    await page.waitForTimeout(5000);
-                }
-                catch {
-                    try {
-                        await frame.evaluate(() => {
-                            if (typeof window.loadIframe === 'function') {
-                                window.loadIframe(1);
-                            }
-                        });
-                        await page.waitForTimeout(5000);
+        // Poll for cloudnestra frame and play button (handles both movies and Turnstile-protected TV)
+        const maxWait = opts.timeout - 5000;
+        const startWait = Date.now();
+        while (Date.now() - startWait < maxWait && !hlsUrl) {
+            for (const frame of page.frames()) {
+                const frameUrl = frame.url();
+                if (frameUrl.includes('cloudnestra') || frameUrl.includes('/rcp/')) {
+                    const clicked = await clickPlayButton(frame);
+                    if (clicked) {
+                        // Wait for HLS after click
+                        const clickTime = Date.now();
+                        while (!hlsUrl && Date.now() - clickTime < 15000) {
+                            await page.waitForTimeout(500);
+                        }
                     }
-                    catch { }
+                    break;
                 }
-                break;
+            }
+            if (!hlsUrl) {
+                await page.waitForTimeout(1000);
             }
         }
-        await page.waitForTimeout(3000);
     }
     catch (error) {
-        console.error(`[ERROR] ${error.message}`);
+        if (!hlsUrl) {
+            console.error(`[vidsrc] ${error.message}`);
+        }
     }
     finally {
         await browser.close();
@@ -93,9 +108,9 @@ export async function scrapeVidsrc(tmdbId, type = 'movie', season = null, episod
         type,
         season,
         episode,
-        hlsUrl: responseData.hlsUrl,
-        subtitles: responseData.subtitles,
-        success: !!responseData.hlsUrl,
+        hlsUrl,
+        subtitles,
+        success: !!hlsUrl,
         timestamp: new Date().toISOString(),
     };
     if (result.success) {

package/dist/types.d.ts

@@ -1,7 +1,14 @@
 export interface ScrapeOptions {
+    /** Total timeout in ms (default: 60000) */
     timeout?: number;
-    headless?: boolean;
+    /** Cache TTL in seconds (default: 900) */
     cacheTtl?: number;
+    /**
+     * Run browser in headless mode (default: true)
+     * NOTE: VidSrc now uses Cloudflare Turnstile protection.
+     * Set to false to allow manual CAPTCHA solving in visible browser.
+     */
+    headless?: boolean;
 }
 export interface ScrapeResult {
     tmdbId: string;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@definisi/vidsrc-scraper",
-  "version": "1.0.1",
+  "version": "1.0.3",
   "description": "Extract HLS streaming URLs from VidSrc",
   "type": "module",
   "main": "./dist/index.js",