fix: archive.is Prüfung via Redirect-Analyse statt Statuscode

backend/src/tools/paywallkiller/routes.js

@@ -7,49 +7,64 @@ const path = require('path');
 const fs = require('fs');
 const crypto = require('crypto');
 
-// ── Hilfsfunktion: HTTP GET mit Follow-Redirect ────────────────────────────
+// ── Hilfsfunktion: folgt Redirects, gibt finale URL zurück ───────────────
-function fetchUrl(url, options = {}) {
+function fetchFollowRedirects(url, redirectCount = 0) {
   return new Promise((resolve, reject) => {
+    if (redirectCount > 8) return reject(new Error('Zu viele Redirects'));
     const mod = url.startsWith('https') ? https : http;
     const req = mod.get(url, {
       headers: {
-        'User-Agent': 'Mozilla/5.0 (compatible; DickenDock/1.0)',
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
-        ...options.headers,
+        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+        'Accept-Language': 'de,en;q=0.5',
       },
-      timeout: 10000,
+      timeout: 12000,
     }, (res) => {
-      // Redirects manuell folgen (max 5)
+      if ([301, 302, 303, 307, 308].includes(res.statusCode) && res.headers.location) {
-      if ([301, 302, 303, 307, 308].includes(res.statusCode) && res.headers.location && (options.redirects || 0) < 5) {
+        let location = res.headers.location;
-        const location = res.headers.location.startsWith('http')
+        if (!location.startsWith('http')) {
-          ? res.headers.location
+          try {
-          : new URL(res.headers.location, url).href;
+            const base = new URL(url);
-        res.resume();
+            location = location.startsWith('/')
-        return fetchUrl(location, { ...options, redirects: (options.redirects || 0) + 1 })
+              ? `${base.protocol}//${base.host}${location}`
-          .then(resolve).catch(reject);
+              : `${base.protocol}//${base.host}/${location}`;
+          } catch { return reject(new Error('Ungültige Redirect-URL')); }
         }
-      resolve({ statusCode: res.statusCode, url, finalUrl: url, headers: res.headers, res });
+        res.resume();
+        return fetchFollowRedirects(location, redirectCount + 1).then(resolve).catch(reject);
+      }
+      res.resume();
+      resolve({ statusCode: res.statusCode, finalUrl: url });
     });
     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) ──
+// ── Prüfe ob archive.is einen Snapshot hat ────────────────────────────────
+// archive.is/newest/URL leitet auf archive.is/HASH weiter wenn ein Snapshot existiert.
+// Wenn kein Snapshot → Redirect zurück auf archive.is/ (Root) oder /newest/... bleibt stehen.
 async function checkArchive(archiveUrl) {
   try {
-    const result = await fetchUrl(archiveUrl);
+    const result = await fetchFollowRedirects(archiveUrl);
-    result.res.destroy();
+    const final = result.finalUrl;
-    // archive.is gibt 200 zurück wenn Archiv existiert, 404 oder Redirect zu / wenn nicht
+    // Kein Redirect = nichts gefunden (blieb auf gleicher URL)
-    if (result.statusCode === 200) return true;
+    if (final === archiveUrl) return { found: false };
-    return false;
+    // Snapshot-URL hat die Form https://archive.is/ABCDE (alphanumeric hash, 4-8 Zeichen)
+    if (/https?:\/\/archive\.(is|ph|today|fo|li|vn|md|gg)\/[a-zA-Z0-9]{4,10}$/.test(final)) {
+      return { found: true, resolvedUrl: final };
+    }
+    // archive.is Root oder Submit-Seite = kein Treffer
+    if (/archive\.[a-z]+\/?$/.test(final)) return { found: false };
+    if (final.includes('/submit')) return { found: false };
+    // Sonst: irgendwohin weitergeleitet → als Treffer werten
+    return { found: true, resolvedUrl: final };
   } catch {
-    return false;
+    return { found: 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' });
@@ -61,13 +76,13 @@ router.post('/check', authenticate, async (req, res) => {
   const oldestUrl = `https://archive.is/oldest/${targetUrl}`;
 
   try {
-    const newestOk = await checkArchive(newestUrl);
+    const newest = await checkArchive(newestUrl);
-    if (newestOk) {
+    if (newest.found) {
-      return res.json({ archiveUrl: newestUrl, type: 'newest' });
+      return res.json({ archiveUrl: newest.resolvedUrl || newestUrl, type: 'newest' });
     }
-    const oldestOk = await checkArchive(oldestUrl);
+    const oldest = await checkArchive(oldestUrl);
-    if (oldestOk) {
+    if (oldest.found) {
-      return res.json({ archiveUrl: oldestUrl, type: 'oldest' });
+      return res.json({ archiveUrl: oldest.resolvedUrl || oldestUrl, type: 'oldest' });
     }
     return res.status(404).json({ error: 'Kein Archiv für diese URL gefunden' });
   } catch (err) {
@@ -76,12 +91,12 @@ router.post('/check', authenticate, async (req, res) => {
 });
 
 // ── 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' });
+  if (!/^https?:\/\/archive\.(is|ph|today|fo|li|vn|md|gg)\//.test(archiveUrl)) {
+    return res.status(400).json({ error: 'Ungültige archive.is URL' });
+  }
 
   let browser;
   const tmpFile = path.join('/tmp', `pwk_${crypto.randomBytes(8).toString('hex')}.pdf`);
@@ -89,12 +104,10 @@ router.post('/pdf', authenticate, async (req, res) => {
   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;
@@ -105,12 +118,7 @@ router.post('/pdf', authenticate, async (req, res) => {
 
     const launchOptions = chromium
       ? {
-          args: [
+          args: [...chromium.args, '--no-sandbox', '--disable-setuid-sandbox', '--disable-dev-shm-usage'],
-            ...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,
@@ -119,32 +127,23 @@ router.post('/pdf', authenticate, async (req, res) => {
 
     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="${filename}"`);
+    res.setHeader('Content-Disposition', `attachment; filename="archiv_${Date.now()}.pdf"`);
-
     const stream = fs.createReadStream(tmpFile);
     stream.pipe(res);
-    stream.on('end', () => {
+    stream.on('end', () => fs.unlink(tmpFile, () => {}));
-      fs.unlink(tmpFile, () => {});
+    stream.on('error', () => fs.unlink(tmpFile, () => {}));
-    });
-    stream.on('error', () => {
-      fs.unlink(tmpFile, () => {});
-    });
 
   } catch (err) {
     if (browser) try { await browser.close(); } catch {}