Update app.py

app.py

@@ -1,6 +1,5 @@
 from flask import Flask, render_template, request, jsonify
 from playwright.sync_api import sync_playwright
-# REMOVED: from playwright_stealth import stealth_sync (Use manual function below instead)
 from concurrent.futures import ThreadPoolExecutor
 import time
 import os
@@ -10,7 +9,7 @@ app = Flask(__name__)
 
 # ---------------- CONFIGURATION ---------------- #
 SESSION_FILE = "instagram_session.json"
-MAX_WORKERS = 3
+MAX_WORKERS = 3 
 # ----------------------------------------------- #
 
 def identify_url_type(url):
@@ -21,36 +20,23 @@ def identify_url_type(url):
     if "instagram.com/" in url: return "PROFILE"
     return "UNKNOWN"
 
-# --- HELPER: MANUAL STEALTH MODE (Fixes ImportError) ---
+# --- HELPER: MANUAL STEALTH (The Magic Fix) ---
 def apply_stealth(page):
     """
-    Manually hides 'navigator.webdriver' and other bot flags 
-    so Instagram thinks this is a real browser.
+    Manually overrides browser variables to hide 'Headless' status.
+    This replaces the broken 'playwright-stealth' library.
     """
-    # 1. Hide the WebDriver flag
-    page.add_init_script("""
-        Object.defineProperty(navigator, 'webdriver', {
-            get: () => undefined
-        });
-    """)
-    # 2. Mock Chrome runtime
-    page.add_init_script("""
-        window.navigator.chrome = {
-            runtime: {}
-        };
-    """)
-    # 3. Mock Plugins (Bots usually have 0)
-    page.add_init_script("""
-        Object.defineProperty(navigator, 'plugins', {
-            get: () => [1, 2, 3, 4, 5]
-        });
-    """)
+    # 1. Hide WebDriver Flag
+    page.add_init_script("Object.defineProperty(navigator, 'webdriver', {get: () => undefined})")
+    
+    # 2. Mock Chrome Runtime
+    page.add_init_script("window.navigator.chrome = { runtime: {} };")
+    
+    # 3. Mock Plugins (Headless browsers have 0, Humans have many)
+    page.add_init_script("Object.defineProperty(navigator, 'plugins', {get: () => [1, 2, 3, 4, 5]})")
+    
     # 4. Mock Languages
-    page.add_init_script("""
-        Object.defineProperty(navigator, 'languages', {
-            get: () => ['en-US', 'en']
-        });
-    """)
+    page.add_init_script("Object.defineProperty(navigator, 'languages', {get: () => ['en-US', 'en']})")
 
 # --- HELPER: RECURSIVE SEARCH ---
 def find_username_in_json(obj):
@@ -72,37 +58,37 @@ def scrape_single_url(url):
     if not url or not url.strip(): return None
 
     with sync_playwright() as p:
-        # 1. LAUNCH BROWSER
+        # 1. LAUNCH BROWSER (Headless=True for Server)
         browser = p.chromium.launch(
             headless=True,
             args=[
-                "--disable-blink-features=AutomationControlled",
+                "--disable-blink-features=AutomationControlled", # Standard bot hide
                 "--no-sandbox",
                 "--disable-dev-shm-usage"
             ]
         )
         
-        # 2. CONFIGURE CONTEXT
+        # 2. CONFIGURE CONTEXT (Windows 10 Fingerprint)
         context_args = {
-            "user_agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
+            "user_agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36",
             "viewport": {"width": 1920, "height": 1080},
             "locale": "en-US",
             "timezone_id": "America/New_York"
         }
-
-        # Try to load session (if exists)
+        
+        # Load Session if available, else Guest
         if os.path.exists(SESSION_FILE):
             try:
                 context = browser.new_context(storage_state=SESSION_FILE, **context_args)
             except:
-                print("⚠️ Session corrupted. Guest mode.")
+                print("⚠️ Session Corrupt. Switching to Guest Mode.")
                 context = browser.new_context(**context_args)
         else:
             context = browser.new_context(**context_args)
         
         page = context.new_page()
         
-        # 3. APPLY MANUAL STEALTH (Replaces the library)
+        # 3. APPLY MANUAL STEALTH 
         apply_stealth(page)
 
         print(f"⚡ Processing: {url}")
@@ -128,7 +114,7 @@ def scrape_single_url(url):
             
             # Check Login Wall
             time.sleep(4)
-            if "Login" in page.title() or page.locator("input[name='username']").count() > 0:
+            if "Login" in page.title():
                 data["status"] = "Failed (Login Block)"
                 browser.close()
                 return data
@@ -190,7 +176,7 @@ def scrape_single_url(url):
                         match = re.search(r'\(@(.*?)\)', title) 
                         if match: data["author"] = match.group(1)
                     except: pass
-                
+
                 if not data["author"]:
                     try:
                         links = page.locator("a[href*='/reels/']").all()
@@ -246,7 +232,6 @@ def scrape_single_url(url):
         browser.close()
         return data
 
-# --- ROUTES ---
 @app.route('/')
 def home():
     return render_template('index.html')