Upload shorts_rss_proxy.py with huggingface_hub

shorts_rss_proxy.py

@@ -0,0 +1,114 @@
+"""
+YouTube RSS Proxy - Fetches YouTube channel RSS feeds server-side
+Avoids CORS issues when client tries to fetch YouTube directly
+"""
+import requests as req
+from fastapi import Query
+from fastapi.responses import Response
+
+HEADERS = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"}
+
+YOUTUBE_CHANNELS = {
+    "baodantri7941": "UC_x5TKhOgd6GhYvv5z4I3jg",
+    "baosuckhoedoisongboyte": "UCBsY5fXTQLkF_JnH9kLkL4g",
+}
+
+def setup_rss_proxy(app):
+    """Add RSS proxy endpoints to the FastAPI app"""
+    
+    @app.get("/api/proxy/rss")
+    def proxy_rss(url: str = Query(...)):
+        """Proxy YouTube RSS feed to avoid CORS"""
+        try:
+            r = req.get(url, headers=HEADERS, timeout=15)
+            if r.status_code == 200:
+                return Response(
+                    content=r.content,
+                    media_type="application/xml",
+                    headers={"Access-Control-Allow-Origin": "*"}
+                )
+            return Response(status_code=r.status_code)
+        except Exception as e:
+            return Response(status_code=502, content=str(e))
+    
+    @app.get("/api/shorts/rss")
+    def shorts_via_rss():
+        """Get shorts from YouTube RSS feeds server-side"""
+        import xml.etree.ElementTree as ET
+        import html as html_lib
+        import re
+        
+        shorts = []
+        seen = set()
+        
+        for handle, channel_id in YOUTUBE_CHANNELS.items():
+            try:
+                rss_url = f"https://www.youtube.com/feeds/videos.xml?channel_id={channel_id}"
+                r = req.get(rss_url, headers=HEADERS, timeout=15)
+                if r.status_code != 200:
+                    continue
+                    
+                root = ET.fromstring(r.text)
+                ns = {
+                    'atom': 'http://www.w3.org/2005/Atom',
+                    'yt': 'http://www.youtube.com/xml/schemas/2015',
+                    'media': 'http://search.yahoo.com/mrss/'
+                }
+                
+                for entry in root.findall('atom:entry', ns)[:30]:
+                    title_el = entry.find('atom:title', ns)
+                    title = html_lib.unescape(title_el.text) if title_el is not None and title_el.text else ''
+                    
+                    link_el = entry.find('atom:link', ns)
+                    link = link_el.get('href', '') if link_el is not None else ''
+                    
+                    vid_el = entry.find('yt:videoId', ns)
+                    vid = vid_el.text if vid_el is not None else ''
+                    
+                    if not vid:
+                        m = re.search(r'(?:v=|shorts/)([A-Za-z0-9_-]{11})', link)
+                        if m:
+                            vid = m.group(1)
+                    
+                    if not vid or vid in seen:
+                        continue
+                    
+                    # Check if it's a short
+                    is_short = '#shorts' in title.lower() or '#short' in title.lower() or '/shorts/' in link
+                    
+                    if not is_short:
+                        desc_el = entry.find('media:description', ns)
+                        if desc_el is not None and desc_el.text:
+                            if '#shorts' in desc_el.text.lower():
+                                is_short = True
+                    
+                    if not is_short:
+                        continue
+                    
+                    seen.add(vid)
+                    
+                    # Get thumbnail
+                    thumb = f"https://i.ytimg.com/vi/{vid}/hqdefault.jpg"
+                    media_group = entry.find('media:group', ns)
+                    if media_group is not None:
+                        thumb_el = media_group.find('media:thumbnail', ns)
+                        if thumb_el is not None:
+                            thumb = thumb_el.get('url', thumb)
+                    
+                    shorts.append({
+                        'id': vid,
+                        'title': title.replace('#shorts', '').replace('#short', '').strip()[:120],
+                        'img': thumb,
+                        'link': f'https://www.youtube.com/shorts/{vid}',
+                        'channel': handle,
+                        'source': 'yt'
+                    })
+                    
+                    if len(shorts) >= 40:
+                        break
+                        
+            except Exception as e:
+                print(f"RSS error for {handle}: {e}")
+                continue
+        
+        return {"shorts": shorts, "count": len(shorts)}