feat: add Rotten Tomatoes mirror site

Dockerfile

@@ -33,6 +33,6 @@ COPY control_server.py  /opt/control_server.py
 COPY site_runner.py     /opt/site_runner.py
 RUN chmod +x /opt/websyn_start.sh
 
-EXPOSE 8101 40000-40014
+EXPOSE 8101 40000-40015
 
 CMD ["/opt/websyn_start.sh"]

control_server.py

@@ -26,7 +26,7 @@
     'allrecipes', 'amazon', 'apple', 'arxiv', 'bbc_news', 'booking',
     'github', 'google_flights', 'google_map', 'google_search',
     'huggingface', 'wolfram_alpha', 'cambridge_dictionary',
-    'coursera', 'espn',
+    'coursera', 'espn', 'rotten_tomatoes',
 ]
 BASE_PORT = 40000
 WEBSYN_DIR = '/opt/WebSyn'

sites/rotten_tomatoes/_health.py

@@ -0,0 +1,3 @@
+"""Per-site health probe (optional, called by control_server)."""
+def health():
+    return {"ok": True, "site": "rotten_tomatoes"}

sites/rotten_tomatoes/download_people.py

@@ -0,0 +1,57 @@
+#!/usr/bin/env python3
+"""Download celebrity photos from RT celebrity pages."""
+import json, subprocess, os, re, sys
+
+PEOPLE_DIR = "static/images/people"
+os.makedirs(PEOPLE_DIR, exist_ok=True)
+
+sys.path.insert(0, '.')
+import seed_data
+
+total = len(seed_data.PERSONS)
+done = 0
+failed = []
+
+for p in seed_data.PERSONS:
+    slug = p['slug']
+    outpath = f"{PEOPLE_DIR}/{slug}.jpg"
+    if os.path.exists(outpath) and os.path.getsize(outpath) > 1000:
+        done += 1
+        continue
+
+    try:
+        result = subprocess.run(
+            ['curl', '-sL', '--connect-timeout', '5', '--max-time', '10',
+             f'https://www.rottentomatoes.com/celebrity/{slug}'],
+            capture_output=True, text=True, timeout=15
+        )
+        html = result.stdout
+
+        # Find celebrity headshot - look for celeb image patterns
+        # Pattern 1: ems-prd-assets/celebrities/ (base64: ZW1zLXByZC1hc3NldHMvY2VsZWJyaXRpZXMv)
+        # Pattern 2: prd-ems-assets/celebrities/ (base64: cHJkLWVtcy1hc3NldHMvY2VsZWJyaXRpZXMv)
+        celeb_urls = re.findall(r'https://resizing\.flixster\.com/[^"]+(?:Y2VsZWJyaXRpZXMv|Y2VsZWJyaXRpZX)[^"]*', html)
+
+        if celeb_urls:
+            photo_url = celeb_urls[-1]  # Last one is usually the main headshot
+            dl_result = subprocess.run(
+                ['curl', '-sL', '-o', outpath, '--connect-timeout', '5', '--max-time', '15', photo_url],
+                capture_output=True, timeout=20
+            )
+            if dl_result.returncode == 0 and os.path.exists(outpath) and os.path.getsize(outpath) > 1000:
+                done += 1
+            else:
+                failed.append(slug)
+                if os.path.exists(outpath):
+                    os.remove(outpath)
+        else:
+            failed.append(slug)
+    except Exception as e:
+        failed.append(slug)
+
+    if done % 20 == 0 and done > 0:
+        print(f"Downloaded {done}/{total}...", flush=True)
+
+print(f"Downloaded: {done}/{total}")
+if failed:
+    print(f"Failed ({len(failed)}): {', '.join(failed[:30])}")

sites/rotten_tomatoes/download_posters.py

@@ -0,0 +1,42 @@
+#!/usr/bin/env python3
+"""Download poster images from flixster CDN URLs."""
+import json, subprocess, os, sys
+
+POSTER_DIR = "static/images/posters"
+os.makedirs(POSTER_DIR, exist_ok=True)
+
+with open('scraped_data/movies.json') as f:
+    data = json.load(f)
+
+movies = data['movies']
+total = len([m for m in movies if m.get('poster_url')])
+done = 0
+failed = []
+
+for m in movies:
+    url = m.get('poster_url')
+    if not url:
+        continue
+    slug = m['slug']
+    outpath = f"{POSTER_DIR}/{slug}.jpg"
+    if os.path.exists(outpath) and os.path.getsize(outpath) > 1000:
+        done += 1
+        continue
+
+    result = subprocess.run(
+        ['curl', '-sL', '-o', outpath, '--connect-timeout', '10', '--max-time', '30', url],
+        capture_output=True, timeout=35
+    )
+
+    if result.returncode == 0 and os.path.exists(outpath) and os.path.getsize(outpath) > 1000:
+        done += 1
+        if done % 20 == 0:
+            print(f"Downloaded {done}/{total}...")
+    else:
+        failed.append(slug)
+        if os.path.exists(outpath):
+            os.remove(outpath)
+
+print(f"Downloaded: {done}/{total}")
+if failed:
+    print(f"Failed ({len(failed)}): {failed[:10]}...")

sites/rotten_tomatoes/requirements.txt

@@ -0,0 +1 @@
+Flask