fix(backend): Optimize populate_links script

backend/populate_links.py

@@ -15,55 +15,42 @@ def get_shows_from_api():
     """Fetch all shows with their permalinks from the API"""
     print("Fetching all shows from API...")
     url = f"{API_BASE}/shows.json"
-    params = {"artist": 1, "order_by": "showdate", "direction": "DESC"} # Get all, newest first
+    params = {"artist": 1, "order_by": "showdate", "direction": "DESC"} 
     
     all_shows = []
-    page = 1
-    while True:
-        params['page'] = page
-        print(f"  Fetching page {page}...", end="", flush=True)
-        try:
-            resp = requests.get(url, params=params)
-            resp.raise_for_status()
-            data = resp.json()
-            if not data or 'data' not in data:
-                print(" Done.")
-                break
     
-            chunk = data['data']
-            if not chunk:
-                print(" Done.")
-                break
+    # It seems the API might return ALL shows on page 1 if no limit is set. 
+    # We will try fetching page 1.
+    try:
+        print(f"  Fetching shows...", end="", flush=True)
+        resp = requests.get(url, params=params)
+        resp.raise_for_status()
+        data = resp.json()
         
-            all_shows.extend(chunk)
-            print(f" Got {len(chunk)} shows.")
-            page += 1
-            if page > 50: # Safety
-                break 
-        except Exception as e:
-            print(f" Error: {e}")
-            break
+        if data and 'data' in data:
+            all_shows = data['data']
+            print(f" Got {len(all_shows)} shows.")
+            return all_shows
+            
+    except Exception as e:
+        print(f" Error: {e}")
             
     return all_shows
 
-def scrape_links(permalink):
+def scrape_links(session_http, permalink):
     """Scrape Bandcamp and Nugs links from an El Goose show page"""
     if not permalink:
         return None, None
         
     url = f"{SITE_BASE}/setlists/{permalink}"
-    # Sometimes it might be at root? Try setlists/ first as per observation.
     
     try:
-        # print(f"  Scraping {url}...")
-        resp = requests.get(url, timeout=10)
+        resp = session_http.get(url, timeout=10)
         if resp.status_code == 404:
-             # Try root
              url = f"{SITE_BASE}/{permalink}"
-             resp = requests.get(url, timeout=10)
+             resp = session_http.get(url, timeout=10)
         
         if resp.status_code != 200:
-            print(f"  ❌ Failed to fetch {url}: {resp.status_code}")
             return None, None
             
         soup = BeautifulSoup(resp.text, 'html.parser')
@@ -71,10 +58,6 @@ def scrape_links(permalink):
         bandcamp = None
         nugs = None
         
-        # Look for links. 
-        # Usually they are in some container or just raw <a> tags
-        # Pattern matching for hrefs
-        
         for a in soup.find_all('a', href=True):
             href = a['href']
             
@@ -97,36 +80,48 @@ def scrape_links(permalink):
 def main():
     print("🔗 Starting Link Population Script...")
     
-    # 1. Fetch API data to get permalinks (since we didn't store them)
+    # 1. Fetch API data
     api_shows = get_shows_from_api()
     print(f"✓ Found {len(api_shows)} shows in API.")
     
-    # Create lookup map: Date -> Permalink
-    # Note: API date is "YYYY-MM-DD"
+    if not api_shows:
+        print("❌ No shows found in API. Exiting.")
+        return
+
     date_to_permalink = {s['showdate']: s['permalink'] for s in api_shows}
     
+    # Setup HTTP Session
+    http = requests.Session()
+    http.headers.update({
+        "User-Agent": "ElmegDemoBot/1.0 (+http://elmeg.xyz)"
+    })
+
     with Session(engine) as session:
         # 2. Get our DB shows
         db_shows = session.exec(select(Show)).all()
+        # Sort by date desc to update newest first
+        db_shows.sort(key=lambda x: x.date, reverse=True)
+        
         print(f"✓ Found {len(db_shows)} shows in DB to check.")
         
         updates = 0
+        checked = 0
         
         for show in db_shows:
+            checked += 1
             s_date = show.date.strftime("%Y-%m-%d")
             permalink = date_to_permalink.get(s_date)
             
             if not permalink:
-                # print(f"  ⚠️ No permalink found for {s_date}")
                 continue
             
-            # Skip if we already have both links (optional, but good for speed)
+            # Skip if we already have both
             if show.bandcamp_link and show.nugs_link:
-                continue
+                 continue
                 
-            print(f"Processing {s_date}...", end="", flush=True)
+            print(f"[{checked}/{len(db_shows)}] {s_date}...", end="", flush=True)
             
-            bc_link, nugs_link = scrape_links(permalink)
+            bc_link, nugs_link = scrape_links(http, permalink)
             
             updated = False
             if bc_link and bc_link != show.bandcamp_link:
@@ -143,19 +138,16 @@ def main():
                 session.add(show)
                 updates += 1
                 try:
-                    session.commit() # Commit frequently to save progress
+                    session.commit()
                     session.refresh(show)
                     print(" ✓")
                 except Exception as e:
                     print(f" ❌ Save error: {e}")
             else:
-                print(" (No new links)")
+                print(" -")
             
-            # Be nice to the server
-            if updated:
-                time.sleep(1) # Sleep only if we did work
-            else:
-                time.sleep(0.1) 
+            # Small delay
+            time.sleep(0.1)
 
     print(f"\n🎉 Done! Updated {updates} shows.")