Create server.js

server.js

@@ -0,0 +1,212 @@
+// server.js
+
+import express, { json } from "express";
+import cors from "cors";
+import puppeteer from 'puppeteer-extra';
+import StealthPlugin from 'puppeteer-extra-plugin-stealth';
+import { executablePath } from 'puppeteer';
+import fetch from 'node-fetch';
+import { JSDOM } from 'jsdom';
+
+// --- 1. 初始化 Puppeteer 和插件 ---
+puppeteer.use(StealthPlugin());
+const app = express();
+const PORT = process.env.PORT || 3000;
+app.use(cors());
+app.use(json());
+
+
+// --- 2. 优化后的辅助函数 ---
+
+/**
+ * [优化] 移除了对特定 sitekey 的检查，使其更通用和健壮。
+ * 现在它会等待任何 Turnstile 控件出现，而不是只寻找特定的那一个。
+ */
+async function handleTurnstile(page) {
+    try {
+        await page.waitForSelector('.cf-turnstile', { timeout: 5000 });
+        console.log('Turnstile detected - attempting generic bypass...');
+
+        await page.evaluate(() => {
+            if (typeof window.cftCallback === 'function') {
+                const mockToken = 'mock-token-' + Math.random().toString(36).substring(2);
+                window.cftCallback(mockToken);
+            }
+        });
+        console.log('Turnstile JS callback triggered.');
+        await page.waitForTimeout(2000);
+    } catch (error) {
+        if (error.name === 'TimeoutError') {
+            console.log('Turnstile not found on page, skipping bypass.');
+        } else {
+            console.warn('An error occurred during Turnstile handling:', error.message);
+        }
+    }
+}
+
+/**
+ * 您的参考代码中用于提取最终视频链接的函数，保持不变。
+ */
+async function getVideoAndSubtitles(finalUrl) {
+    try {
+        const response = await fetch(finalUrl);
+        if (!response.ok) {
+            throw new Error(`HTTP error! Status: ${response.status}`);
+        }
+        const html = await response.text();
+        const dom = new JSDOM(html);
+        const script = Array.from(dom.window.document.querySelectorAll('script')).find(s => s.textContent?.includes('new Playerjs'));
+        if (!script) return { videoFileUrl: null, subtitleSources: [] };
+
+        const fileMatch = script.textContent.match(/file:"(.*?m3u8.*?)"/);
+        const subtitlesMatch = script.textContent.match(/subtitle:"(.*?)"/);
+        
+        return {
+            videoFileUrl: fileMatch ? fileMatch[1] : null,
+            subtitleSources: subtitlesMatch ? subtitlesMatch[1].split(',').map(s => s.trim()).filter(Boolean) : []
+        };
+    } catch (error) {
+        console.error('Error in getVideoAndSubtitles:', error);
+        throw error;
+    }
+}
+
+
+// --- 3. 核心抓取逻辑 ---
+
+/**
+ * [重大重构]
+ * - 这是一个统一的抓取函数，支持电影和电视剧。
+ * - 它接收一个已经启动的 browser 实例，避免了每次请求都重复启动浏览器的巨大开销。
+ * - 使用了隔离的浏览器上下文 (Incognito Context) 来确保每个请求之间互不干扰。
+ */
+async function scrapeSource(browser, { type, id, season, episode }) {
+    let context = null;
+    console.log(`\nScraping for: type=${type}, id=${id}, s=${season}, e=${episode}`);
+
+    try {
+        // --- URL 构建 ---
+        let initialUrl;
+        const domain = "https://vidsrc.xyz"; // 您可以从一个列表中选择，这里以一个为例
+        if (type === 'tv') {
+            initialUrl = `${domain}/embed/tv?tmdb=${id}&season=${season}&episode=${episode}`;
+        } else { // 默认为 movie
+            initialUrl = `${domain}/embed/movie/${id}`;
+        }
+        console.log(`Initial URL: ${initialUrl}`);
+
+        // --- 浏览器操作 ---
+        context = await browser.createIncognitoBrowserContext();
+        const page = await context.newPage();
+        
+        // 设置通用的请求拦截，绕过 Turnstile 的 API 验证
+        await page.setRequestInterception(true);
+        page.on('request', (request) => {
+            if (request.url().includes('/rcp_verify')) {
+                request.respond({ status: 200, contentType: 'application/json', body: '1' });
+            } else {
+                request.continue();
+            }
+        });
+
+        // 阶段 1: 访问初始页面
+        await page.goto(initialUrl, { waitUntil: 'networkidle2', timeout: 45000 });
+        await handleTurnstile(page);
+        
+        const firstIframeSrc = await page.evaluate(() => document.querySelector('#player_iframe')?.src);
+        if (!firstIframeSrc) throw new Error('First iframe (#player_iframe) not found');
+        console.log(`First iframe src: ${firstIframeSrc}`);
+
+        // 阶段 2: 访问第一个 Iframe
+        // [优化] 我们可以在同一个页面对象上导航，无需创建新页面
+        await page.goto(firstIframeSrc, { waitUntil: 'networkidle2', timeout: 45000 });
+        await handleTurnstile(page);
+
+        const finalIframeSrc = await page.evaluate(() => document.querySelector('iframe')?.src);
+        if (!finalIframeSrc) throw new Error('Final iframe source not found');
+        console.log(`Final iframe src: ${finalIframeSrc}`);
+
+        // 阶段 3: 提取数据
+        return await getVideoAndSubtitles(finalIframeSrc);
+
+    } catch (error) {
+        console.error('Full error during scraping process:', error.message);
+        throw error; // 将错误向上抛出，由 Express 路由统一处理
+    } finally {
+        if (context) {
+            await context.close(); // 关闭上下文，释放所有页面和资源，非常高效
+        }
+    }
+}
+
+
+// --- 4. Express 服务器和路由 ---
+
+let browser; // 全局浏览器实例
+
+app.get("/extract", async (req, res) => {
+    const type = req.query.type || 'movie';
+    const id = req.query.tmdb_id;
+    const season = req.query.season;
+    const episode = req.query.episode;
+
+    // --- 参数校验 ---
+    if (!id) {
+        return res.status(400).json({ success: false, error: "tmdb_id is required" });
+    }
+    if (type === 'tv' && (!season || !episode)) {
+        return res.status(400).json({ success: false, error: "season and episode are required for type 'tv'" });
+    }
+
+    try {
+        const result = await scrapeSource(browser, { type, id, season, episode });
+        
+        if (result && result.videoFileUrl) {
+            res.status(200).json({ success: true, result });
+        } else {
+            res.status(404).json({ success: false, error: "Could not find video stream from the source." });
+        }
+    } catch (error) {
+        res.status(500).json({ success: false, error: `An unexpected error occurred: ${error.message}` });
+    }
+});
+
+
+// --- 5. 服务器启动和优雅关停 ---
+
+(async () => {
+    try {
+        console.log("Launching a persistent browser instance...");
+        browser = await puppeteer.launch({
+            headless: true, // 在生产环境中建议设为 true
+            executablePath: executablePath(),
+            args: [
+                '--no-sandbox',
+                '--disable-setuid-sandbox',
+                '--disable-dev-shm-usage',
+                '--window-size=1200,800'
+            ],
+            defaultViewport: null
+        });
+        console.log("Browser launched successfully.");
+
+        app.listen(PORT, () => {
+            console.log(`🚀 Scraper server running at http://localhost:${PORT}`);
+        });
+    } catch (error) {
+        console.error("Failed to launch browser:", error);
+        process.exit(1);
+    }
+})();
+
+const gracefulShutdown = async () => {
+    console.log("\nShutting down gracefully...");
+    if (browser) {
+        await browser.close();
+        console.log("Browser instance closed.");
+    }
+    process.exit(0);
+};
+
+process.on('SIGINT', gracefulShutdown);
+process.on('SIGTERM', gracefulShutdown);