feat: Paywall-Killer Tool (archive.is + PDF-Export)

backend/src/tools/paywallkiller/routes.js

@@ -0,0 +1,156 @@
+const express = require('express');
+const router = express.Router();
+const { authenticate } = require('../../middleware/auth');
+const https = require('https');
+const http = require('http');
+const path = require('path');
+const fs = require('fs');
+const crypto = require('crypto');
+
+// ── Hilfsfunktion: HTTP GET mit Follow-Redirect ────────────────────────────
+function fetchUrl(url, options = {}) {
+  return new Promise((resolve, reject) => {
+    const mod = url.startsWith('https') ? https : http;
+    const req = mod.get(url, {
+      headers: {
+        'User-Agent': 'Mozilla/5.0 (compatible; DickenDock/1.0)',
+        ...options.headers,
+      },
+      timeout: 10000,
+    }, (res) => {
+      // Redirects manuell folgen (max 5)
+      if ([301, 302, 303, 307, 308].includes(res.statusCode) && res.headers.location && (options.redirects || 0) < 5) {
+        const location = res.headers.location.startsWith('http')
+          ? res.headers.location
+          : new URL(res.headers.location, url).href;
+        res.resume();
+        return fetchUrl(location, { ...options, redirects: (options.redirects || 0) + 1 })
+          .then(resolve).catch(reject);
+      }
+      resolve({ statusCode: res.statusCode, url, finalUrl: url, headers: res.headers, res });
+    });
+    req.on('error', reject);
+    req.on('timeout', () => { req.destroy(); reject(new Error('Timeout')); });
+  });
+}
+
+// ── Prüfe ob archive.is-URL existiert (HEAD-ähnlich via GET + sofortiges Abbrechen) ──
+async function checkArchive(archiveUrl) {
+  try {
+    const result = await fetchUrl(archiveUrl);
+    result.res.destroy();
+    // archive.is gibt 200 zurück wenn Archiv existiert, 404 oder Redirect zu / wenn nicht
+    if (result.statusCode === 200) return true;
+    return false;
+  } catch {
+    return false;
+  }
+}
+
+// ── POST /api/tools/paywallkiller/check ───────────────────────────────────
+// Body: { url: "https://..." }
+// Response: { archiveUrl: "https://archive.is/...", type: "newest"|"oldest" }
+router.post('/check', authenticate, async (req, res) => {
+  const { url } = req.body;
+  if (!url || typeof url !== 'string') return res.status(400).json({ error: 'URL fehlt' });
+
+  let targetUrl = url.trim();
+  if (!targetUrl.startsWith('http')) targetUrl = 'https://' + targetUrl;
+
+  const newestUrl = `https://archive.is/newest/${targetUrl}`;
+  const oldestUrl = `https://archive.is/oldest/${targetUrl}`;
+
+  try {
+    const newestOk = await checkArchive(newestUrl);
+    if (newestOk) {
+      return res.json({ archiveUrl: newestUrl, type: 'newest' });
+    }
+    const oldestOk = await checkArchive(oldestUrl);
+    if (oldestOk) {
+      return res.json({ archiveUrl: oldestUrl, type: 'oldest' });
+    }
+    return res.status(404).json({ error: 'Kein Archiv für diese URL gefunden' });
+  } catch (err) {
+    return res.status(500).json({ error: 'Fehler beim Prüfen: ' + err.message });
+  }
+});
+
+// ── POST /api/tools/paywallkiller/pdf ─────────────────────────────────────
+// Body: { archiveUrl: "https://archive.is/..." }
+// Response: PDF als Download-Stream, Datei danach gelöscht
+router.post('/pdf', authenticate, async (req, res) => {
+  const { archiveUrl } = req.body;
+  if (!archiveUrl || typeof archiveUrl !== 'string') return res.status(400).json({ error: 'archiveUrl fehlt' });
+  if (!archiveUrl.startsWith('https://archive.is/')) return res.status(400).json({ error: 'Ungültige archive.is URL' });
+
+  let browser;
+  const tmpFile = path.join('/tmp', `pwk_${crypto.randomBytes(8).toString('hex')}.pdf`);
+
+  try {
+    let puppeteer, chromium;
+
+    // Versuche puppeteer-core + @sparticuz/chromium (Alpine-kompatibel)
+    try {
+      puppeteer = require('puppeteer-core');
+      chromium  = require('@sparticuz/chromium');
+    } catch {
+      // Fallback: normales puppeteer (falls installiert)
+      try {
+        puppeteer = require('puppeteer');
+        chromium  = null;
+      } catch {
+        return res.status(500).json({ error: 'PDF-Rendering nicht verfügbar – puppeteer nicht installiert' });
+      }
+    }
+
+    const launchOptions = chromium
+      ? {
+          args: [
+            ...chromium.args,
+            '--no-sandbox',
+            '--disable-setuid-sandbox',
+            '--disable-dev-shm-usage',
+          ],
+          defaultViewport: { width: 1280, height: 900 },
+          executablePath: process.env.CHROMIUM_PATH || await chromium.executablePath(),
+          headless: true,
+        }
+      : { headless: 'new', args: ['--no-sandbox', '--disable-setuid-sandbox'] };
+
+    browser = await puppeteer.launch(launchOptions);
+    const page = await browser.newPage();
+
+    await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36');
+    await page.goto(archiveUrl, { waitUntil: 'networkidle2', timeout: 30000 });
+
+    await page.pdf({
+      path: tmpFile,
+      format: 'A4',
+      printBackground: true,
+      margin: { top: '10mm', bottom: '10mm', left: '10mm', right: '10mm' },
+    });
+
+    await browser.close();
+    browser = null;
+
+    const filename = 'archiv_' + Date.now() + '.pdf';
+    res.setHeader('Content-Type', 'application/pdf');
+    res.setHeader('Content-Disposition', `attachment; filename="${filename}"`);
+
+    const stream = fs.createReadStream(tmpFile);
+    stream.pipe(res);
+    stream.on('end', () => {
+      fs.unlink(tmpFile, () => {});
+    });
+    stream.on('error', () => {
+      fs.unlink(tmpFile, () => {});
+    });
+
+  } catch (err) {
+    if (browser) try { await browser.close(); } catch {}
+    fs.unlink(tmpFile, () => {});
+    return res.status(500).json({ error: 'PDF-Erstellung fehlgeschlagen: ' + err.message });
+  }
+});
+
+module.exports = router;