Upload 3 files

Dockerfile

@@ -1,44 +1,26 @@
-# Use a robust, official Python image
-FROM python:3.10-slim
+# Official Microsoft Playwright image - pre-compiled and lightning-fast!
+FROM mcr.microsoft.com/playwright/python:v1.40.0-jammy
 
-# Set environment variables for non-interactive installs
-ENV DEBIAN_FRONTEND=noninteractive
-ENV PYTHONUNBUFFERED=1
-
-# Install essential system dependencies for Chrome/Selenium
-RUN apt-get update && apt-get install -y \
-    wget \
-    gnupg \
-    unzip \
-    curl \
-    --no-install-recommends \
-    && rm -rf /var/lib/apt/lists/*
-
-# Add Google Chrome Repository and Install Chrome
-RUN wget -q -O - https://dl.google.com/linux/linux_signing_key.pub | gpg --dearmor -o /usr/share/keyrings/google-chrome.gpg \
-    && echo "deb [arch=amd64 signed-by=/usr/share/keyrings/google-chrome.gpg] http://dl.google.com/linux/chrome/deb/ stable main" > /etc/apt/sources.list.d/google-chrome.list \
-    && apt-get update \
-    && apt-get install -y google-chrome-stable \
-    --no-install-recommends \
-    && rm -rf /var/lib/apt/lists/*
-
-# Set up user for Hugging Face (UID 1000 is required)
+# Hugging Face UID 1000 is required for proper permissions
 RUN useradd -m -u 1000 user
 USER user
 ENV HOME=/home/user \
-    PATH=/home/user/.local/bin:$PATH
+    PATH=/home/user/.local/bin:$PATH \
+    PYTHONUNBUFFERED=1
 
 WORKDIR $HOME/app
 
-# Copy and install requirements
+# Only copy requirements first to cache layers (fast builds!)
 COPY --chown=user requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Copy application code
+# Playwright images have Chrome pre-baked. Just install the executable.
+RUN playwright install chromium
+
+# Copy our logic
 COPY --chown=user app.py .
 
-# Standard HF Port
 EXPOSE 7860
 
-# Start command
+# Starting the Gradio dashboard and background task
 CMD ["python", "app.py"]

app.py

@@ -4,18 +4,15 @@ import time
 import schedule
 import random
 import datetime
-from selenium import webdriver
-from selenium.webdriver.chrome.options import Options
-from selenium.webdriver.chrome.service import Service
-from webdriver_manager.chrome import ChromeDriverManager
+from playwright.sync_api import sync_playwright
 
 URL = "https://streamer1-gvbgwaea2w2qmwgjey7ksg.streamlit.app/"
-logs = ["System initialized. Waiting for first run..."]
+logs = ["System initialized. Waiting for build to finalize..."]
 
 def add_log(message):
-    timestamp = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+    timestamp = datetime.datetime.now().strftime('%H:%M:%S')
     log_entry = f"[{timestamp}] {message}"
-    print(log_entry) # Also print to container logs
+    print(log_entry)
     logs.append(log_entry)
     if len(logs) > 50:
         logs.pop(0)
@@ -23,76 +20,59 @@ def add_log(message):
 def visit_and_scroll():
     add_log(f"Starting keep-alive visit to: {URL}")
     
-    options = Options()
-    options.add_argument("--headless=new")
-    options.add_argument("--no-sandbox")
-    options.add_argument("--disable-dev-shm-usage")
-    options.add_argument("--disable-gpu")
-    options.add_argument("--window-size=1920,1080")
-    # Add a real-looking user agent to prevent blocks
-    options.add_argument("user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36")
-
-    driver = None
     try:
-        # Use webdriver-manager to handle the driver automatically
-        service = Service(ChromeDriverManager().install())
-        driver = webdriver.Chrome(service=service, options=options)
-        
-        driver.get(URL)
-        add_log("Page loaded. Waiting 10s for Streamlit hydration...")
-        time.sleep(10)
-        
-        # Natural scrolling logic
-        total_height = driver.execute_script("return document.body.scrollHeight")
-        add_log(f"Page height detected: {total_height}px. Beginning scroll...")
-        
-        current_scroll = 0
-        while current_scroll < total_height:
-            step = random.randint(200, 600)
-            current_scroll += step
-            driver.execute_script(f"window.scrollTo(0, {current_scroll});")
-            time.sleep(random.uniform(0.5, 1.5))
-            # Update height in case of lazy loading
-            total_height = driver.execute_script("return document.body.scrollHeight")
+        with sync_playwright() as p:
+            # Playwright is built specifically for containers and is very stable
+            browser = p.chromium.launch(headless=True, args=['--no-sandbox', '--disable-dev-shm-usage'])
+            context = browser.new_context(user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36")
+            page = context.new_page()
+            
+            # Go to site
+            page.goto(URL, wait_until='networkidle', timeout=60000)
+            add_log("Page loaded. Waiting 10s for Streamlit setup...")
+            time.sleep(10)
+            
+            # Smart scrolling logic
+            for i in range(1, 6):
+                scroll_y = i * 800
+                page.evaluate(f"window.scrollTo(0, {scroll_y});")
+                add_log(f"Scrolled to {scroll_y}px...")
+                time.sleep(random.uniform(1.0, 2.5))
 
-        add_log("Reached bottom. Scrolling back to top...")
-        driver.execute_script("window.scrollTo({top: 0, behavior: 'smooth'});")
-        time.sleep(3)
-        
-        add_log("Visit completed successfully.")
-        
+            # Back to top
+            page.evaluate("window.scrollTo(0, 0);")
+            add_log("Visit completed. Closing browser.")
+            browser.close()
+            
     except Exception as e:
         add_log(f"CRITICAL ERROR: {str(e)}")
-    finally:
-        if driver:
-            driver.quit()
 
 def run_scheduler():
-    # Run immediately on startup
+    # Immediate first run
     visit_and_scroll()
     
     schedule.every(1).hours.do(visit_and_scroll)
     while True:
         schedule.run_pending()
-        time.sleep(30)
+        time.sleep(60)
 
-# Start the background thread
+# Background Thread
 threading.Thread(target=run_scheduler, daemon=True).start()
 
 def get_logs():
     return "\n".join(reversed(logs))
 
-# Build the Gradio UI
+# Gradio Interface
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 🚀 Streamlit Keep-Alive Bot")
+    gr.Markdown("# 🚀 Streamlit Keep-Alive Cloud Console")
     gr.Markdown(f"Targeting: `{URL}`")
     
     with gr.Row():
         status_box = gr.Textbox(
-            label="Live Activity Logs (Newest First)", 
+            label="Live logs (Newest First)", 
             value=get_logs, 
-            every=5, # Auto-refresh every 5 seconds
-            lines=20,
+            every=5, # Refresh every 5s automatically 
+            lines=15,
             interactive=False
         )
     

requirements.txt

@@ -1,4 +1,3 @@
-selenium
+playwright
 schedule
 gradio
-webdriver-manager