@definisi/vidsrc-scraper 1.1.0 → 2.0.0

package/README.md

@@ -1,11 +1,20 @@
 # @definisi/vidsrc-scraper
 
-Extract HLS streaming URLs from VidSrc using TMDB ID. Zero dependencies, works on any platform.
+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
 ```
 
 ## Usage
@@ -13,42 +22,36 @@ npm install @definisi/vidsrc-scraper
 ```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: 15000,
-  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 | 30000 | Request timeout (ms) |
-| 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;
@@ -60,20 +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+ (uses native fetch)
+- Node.js 18+
+- Playwright
 
-## Playback
+## License
 
-```bash
-# VLC
-vlc "HLS_URL" --http-user-agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:121.0) Gecko/20100101 Firefox/121.0"
-
-# ffplay
-ffplay -user_agent "Mozilla/5.0" "HLS_URL"
-```
+MIT

package/dist/scraper.js

@@ -1,10 +1,23 @@
+import axios from 'axios';
+import https from 'https';
+const UA = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:121.0) Gecko/20100101 Firefox/121.0';
 const DEFAULT_OPTIONS = {
     timeout: 30000,
     cacheTtl: 900,
 };
-const UA = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:121.0) Gecko/20100101 Firefox/121.0';
-const CDN_DOMAINS = ['cloudnestra.com', 'quibblezoomfable.com'];
 const cache = new Map();
+function createClient(timeout) {
+    return axios.create({
+        httpsAgent: new https.Agent({ rejectUnauthorized: false }),
+        headers: {
+            'User-Agent': UA,
+            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+            'Accept-Language': 'en-US,en;q=0.5',
+            'Accept-Encoding': 'identity',
+        },
+        timeout,
+    });
+}
 function getCacheKey(tmdbId, type, season, episode) {
     return `${type}-${tmdbId}-${season || ''}-${episode || ''}`;
 }
@@ -20,84 +33,74 @@ 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-embed.ru/embed';
     if (type === 'tv') {
-        return `${base}/tv?tmdb=${tmdbId}&season=${season}&episode=${episode}`;
-    }
-    return `${base}/movie?tmdb=${tmdbId}`;
-}
-async function fetchWithHeaders(url, referer) {
-    const headers = {
-        'User-Agent': UA,
-        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
-        'Accept-Language': 'en-US,en;q=0.5',
-    };
-    if (referer) {
-        headers['Referer'] = referer;
-    }
-    const res = await fetch(url, { headers });
-    if (!res.ok)
-        throw new Error(`HTTP ${res.status}`);
-    return res.text();
-}
-async function resolveM3u8Domain(templateUrl) {
-    for (const domain of CDN_DOMAINS) {
-        const testUrl = templateUrl.replace(/\{v\d+\}/, domain);
-        try {
-            const res = await fetch(testUrl, {
-                method: 'HEAD',
-                headers: { 'User-Agent': UA },
-            });
-            if (res.ok)
-                return testUrl;
-        }
-        catch { }
+        return `${base}/tv/${tmdbId}/${season}/${episode}`;
     }
-    return null;
+    return `${base}/movie/${tmdbId}`;
 }
-function extractSubtitles(html) {
-    const subtitles = [];
-    const subMatches = html.matchAll(/https?:\/\/[^"'\s]+\.(?:vtt|srt)[^"'\s]*/g);
-    for (const match of subMatches) {
-        if (!subtitles.includes(match[0])) {
-            subtitles.push(match[0]);
-        }
-    }
-    return subtitles;
+function resolveM3u8Url(url) {
+    // Replace domain placeholders {v1} through {v5} with cloudnestra.com
+    return url
+        .split(' or ')[0]
+        .trim()
+        .replace(/\{v[1-5]\}/g, 'cloudnestra.com');
 }
 export async function scrapeVidsrc(tmdbId, type = 'movie', season = null, episode = null, options = {}) {
     const opts = { ...DEFAULT_OPTIONS, ...options };
     const cacheKey = getCacheKey(tmdbId, type, season, episode);
     const cached = getFromCache(cacheKey, opts.cacheTtl);
-    if (cached)
+    if (cached) {
         return cached;
+    }
+    const client = createClient(opts.timeout);
     let hlsUrl = null;
-    let subtitles = [];
+    const subtitles = [];
     try {
+        // Step 1: Get embed page
         const embedUrl = buildEmbedUrl(tmdbId, type, season, episode);
-        const embedHtml = await fetchWithHeaders(embedUrl);
-        const rcpMatch = embedHtml.match(/src="([^"]*\/rcp\/[^"]*)"/);
-        if (!rcpMatch)
-            throw new Error('RCP iframe not found');
+        const embedRes = await client.get(embedUrl);
+        // Step 2: Extract cloudnestra RCP iframe URL
+        const rcpMatch = embedRes.data.match(/src=["']((?:https?:)?\/\/[^"']*cloudnestra\.com\/rcp\/[^"']+)["']/i);
+        if (!rcpMatch) {
+            throw new Error('No RCP iframe found in embed page');
+        }
         let rcpUrl = rcpMatch[1];
         if (rcpUrl.startsWith('//'))
             rcpUrl = 'https:' + rcpUrl;
-        const rcpHtml = await fetchWithHeaders(rcpUrl, embedUrl);
-        const prorcpMatch = rcpHtml.match(/\/prorcp\/([a-zA-Z0-9=]+)/);
-        if (!prorcpMatch)
-            throw new Error('Prorcp hash not found');
-        const prorcpUrl = `https://cloudnestra.com/prorcp/${prorcpMatch[1]}`;
-        const prorcpHtml = await fetchWithHeaders(prorcpUrl, rcpUrl);
-        const fileMatch = prorcpHtml.match(/file:\s*["']([^"']+)["']/);
-        if (fileMatch) {
-            const fileUrls = fileMatch[1].split(' or ');
-            const templateUrl = fileUrls[0].trim();
-            hlsUrl = await resolveM3u8Domain(templateUrl);
+        // Step 3: Get RCP page
+        const rcpRes = await client.get(rcpUrl, {
+            headers: { Referer: embedUrl },
+        });
+        // Step 4: Extract prorcp hash from loadIframe function
+        const prorcpMatch = rcpRes.data.match(/\/prorcp\/([a-zA-Z0-9=+/]+)/);
+        if (!prorcpMatch) {
+            throw new Error('No prorcp hash found in RCP page');
+        }
+        const prorcpHash = prorcpMatch[1];
+        const rcpHost = new URL(rcpUrl).origin;
+        // Step 5: Get prorcp page
+        const prorcpUrl = `${rcpHost}/prorcp/${prorcpHash}`;
+        const prorcpRes = await client.get(prorcpUrl, {
+            headers: { Referer: rcpUrl },
+        });
+        // Step 6: Extract M3U8 file URL
+        const fileMatch = prorcpRes.data.match(/file:\s*["']([^"']+)["']/);
+        if (!fileMatch) {
+            throw new Error('No file URL found in prorcp page');
+        }
+        // Step 7: Resolve domain placeholders
+        hlsUrl = resolveM3u8Url(fileMatch[1]);
+        // Extract subtitles if present
+        const subMatches = prorcpRes.data.matchAll(/["'](https?:\/\/[^"']+\.(?:vtt|srt))["']/gi);
+        for (const match of subMatches) {
+            if (!subtitles.includes(match[1])) {
+                subtitles.push(match[1]);
+            }
         }
-        subtitles = extractSubtitles(prorcpHtml);
     }
     catch (error) {
-        console.error(`[ERROR] ${error.message}`);
+        console.error(`[vidsrc] ${error.message}`);
     }
     const result = {
         tmdbId,

package/dist/types.d.ts

@@ -1,5 +1,7 @@
 export interface ScrapeOptions {
+    /** Request timeout in ms (default: 30000) */
     timeout?: number;
+    /** Cache TTL in seconds (default: 900) */
     cacheTtl?: number;
 }
 export interface ScrapeResult {

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@definisi/vidsrc-scraper",
-  "version": "1.1.0",
-  "description": "Extract HLS streaming URLs from VidSrc (no browser required)",
+  "version": "2.0.0",
+  "description": "Extract HLS streaming URLs from VidSrc using axios",
   "type": "module",
   "main": "./dist/index.js",
   "types": "./dist/index.d.ts",
@@ -26,8 +26,8 @@
     "tmdb"
   ],
   "license": "MIT",
-  "engines": {
-    "node": ">=18.0.0"
+  "dependencies": {
+    "axios": "^1.6.0"
   },
   "devDependencies": {
     "@types/node": "^22.0.0",