Inject custom requests.Session with browser User-Agent into YouTubeTranscriptApi

- Add requests import to summarizer.py
- Configure requests.Session with macOS Chrome User-Agent and English Accept-Language headers
- Initialize YouTubeTranscriptApi with custom http_client to bypass YouTube anti-scraping blocks on residential IPs

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

backend/summarizer.py

@@ -3,6 +3,7 @@ import asyncio
 import logging
 import httpx
 import aiosqlite
+import requests
 from youtube_transcript_api import YouTubeTranscriptApi
 from db import DB_PATH
 
@@ -32,7 +33,12 @@ Transcript:
 
 def download_transcript(video_id: str) -> str:
     try:
-        transcript_list = YouTubeTranscriptApi().list(video_id)
+        session = requests.Session()
+        session.headers.update({
+            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
+            "Accept-Language": "en-US,en;q=0.9"
+        })
+        transcript_list = YouTubeTranscriptApi(http_client=session).list(video_id)
 
         # Try to find manual transcripts in preferred languages
         try: