Sprint 002: Ingest duration & view count, FTS search, infinite scroll pagination, and transcript accordion

backend/fetcher.py

@@ -6,6 +6,7 @@ import logging
 import aiosqlite
 import httpx
 import xml.etree.ElementTree as ET
+import re
 from googleapiclient.discovery import build
 from googleapiclient.errors import HttpError
 from auth import get_credentials
@@ -65,6 +66,20 @@ async def _fetch_rss(client, channel_id):
         return []
 
 
+
+def parse_duration(duration_str: str) -> int:
+    """Parse ISO 8601 duration string (e.g., PT1H2M10S) to seconds."""
+    if not duration_str:
+        return 0
+    pattern = re.compile(r'PT(?:(\d+)H)?(?:(\d+)M)?(?:(\d+)S)?')
+    match = pattern.match(duration_str)
+    if not match:
+        return 0
+    hours = int(match.group(1)) if match.group(1) else 0
+    minutes = int(match.group(2)) if match.group(2) else 0
+    seconds = int(match.group(3)) if match.group(3) else 0
+    return hours * 3600 + minutes * 60 + seconds
+
 async def fetch_subscriptions():
     """Fetch latest videos from subscribed channels using RSS + YouTube Data API v3."""
     try:
@@ -144,16 +159,22 @@ async def fetch_subscriptions():
         for i in range(0, len(new_ids), 50):
             batch = new_ids[i:i+50]
             try:
-                resp = youtube.videos().list(part="snippet", id=",".join(batch)).execute()
+                resp = youtube.videos().list(part="snippet,contentDetails,statistics", id=",".join(batch)).execute()
                 for item in resp.get("items", []):
                     vid = item["id"]
                     snippet = item["snippet"]
                     cid, rss_title = rss_map.get(vid, (snippet.get("channelId", ""), snippet.get("title", "")))
 
+                    content_details = item.get("contentDetails", {})
+                    statistics = item.get("statistics", {})
+                    duration_str = content_details.get("duration", "")
+                    duration_secs = parse_duration(duration_str)
+                    view_count = int(statistics.get("viewCount", 0))
+
                     await db.execute("""
                         INSERT INTO videos
-                        (video_id, title, channel_name, channel_id, url, thumbnail_url, publish_date)
-                        VALUES (?, ?, ?, ?, ?, ?, ?)
+                        (video_id, title, channel_name, channel_id, url, thumbnail_url, publish_date, duration, view_count)
+                        VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)
                     """, (
                         vid,
                         html.unescape(snippet.get("title", rss_title)),
@@ -161,7 +182,9 @@ async def fetch_subscriptions():
                         snippet.get("channelId", cid),
                         f"https://www.youtube.com/watch?v={vid}",
                         snippet.get("thumbnails", {}).get("high", {}).get("url", ""),
-                        (snippet.get("publishTime") or "")[:10]
+                        (snippet.get("publishTime") or "")[:10],
+                        duration_secs,
+                        view_count
                     ))
                     new_count += 1
             except HttpError as e: