Upload 3 files

Dockerfile

@@ -1,25 +1,44 @@
-# Use the official Microsoft Playwright image. It has ALL complex system dependencies pre-installed!
-FROM mcr.microsoft.com/playwright/python:v1.40.0-jammy
+# Use a robust, official Python image
+FROM python:3.10-slim
 
+# 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)
 RUN useradd -m -u 1000 user
 USER user
 ENV HOME=/home/user \
-    PATH=/home/user/.local/bin:$PATH \
-    PYTHONUNBUFFERED=1
+    PATH=/home/user/.local/bin:$PATH
 
 WORKDIR $HOME/app
 
-# Install our python requirements
+# Copy and install requirements
 COPY --chown=user requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Download the Chromium portable browser incredibly fast without apt-get!
-RUN playwright install chromium
-
-# Copy our backend script into the container
+# Copy application code
 COPY --chown=user app.py .
 
+# Standard HF Port
 EXPOSE 7860
 
-# Start Gradio background daemon
+# Start command
 CMD ["python", "app.py"]

app.py

@@ -2,77 +2,102 @@ import gradio as gr
 import threading
 import time
 import schedule
-from playwright.sync_api import sync_playwright
 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
 
 URL = "https://streamer1-gvbgwaea2w2qmwgjey7ksg.streamlit.app/"
-logs = ["Service started. Waiting for next schedule..."]
+logs = ["System initialized. Waiting for first run..."]
 
 def add_log(message):
     timestamp = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')
-    logs.append(f"[{timestamp}] {message}")
-    if len(logs) > 30:
-         logs.pop(0)
+    log_entry = f"[{timestamp}] {message}"
+    print(log_entry) # Also print to container logs
+    logs.append(log_entry)
+    if len(logs) > 50:
+        logs.pop(0)
 
 def visit_and_scroll():
-    add_log(f"Started keeping alive {URL}...")
+    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:
-        with sync_playwright() as p:
-            # Playwright handles headless browsers inside Docker flawlessly
-            browser = p.chromium.launch(headless=True, args=['--no-sandbox', '--disable-dev-shm-usage'])
-            page = browser.new_page()
-            
-            # Open the Streamlit app
-            page.goto(URL, wait_until='networkidle')
-            time.sleep(8)
-            
-            total_height = page.evaluate("document.body.scrollHeight")
-            add_log("Scrolling down naturally...")
-            current_scroll = 0
-            while current_scroll < total_height:
-                scroll_step = random.randint(100, 500)
-                current_scroll += scroll_step
-                page.evaluate(f"window.scrollTo(0, {current_scroll});")
-                time.sleep(random.uniform(0.3, 1.2))
-                new_height = page.evaluate("document.body.scrollHeight")
-                if new_height > total_height:
-                    total_height = new_height
-                    
-            add_log("Scrolling up naturally...")
-            while current_scroll > 0:
-                scroll_step = random.randint(100, 500)
-                current_scroll -= scroll_step
-                if current_scroll < 0:
-                     current_scroll = 0
-                page.evaluate(f"window.scrollTo(0, {current_scroll});")
-                time.sleep(random.uniform(0.3, 1.2))
-                
-            add_log("Done navigating! Closing Playwright browser...")
-            browser.close()
-            
+        # 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")
+
+        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.")
+        
     except Exception as e:
-         add_log(f"Error occurred: {e}")
+        add_log(f"CRITICAL ERROR: {str(e)}")
+    finally:
+        if driver:
+            driver.quit()
 
-def run_schedule():
+def run_scheduler():
+    # Run immediately on startup
     visit_and_scroll()
+    
     schedule.every(1).hours.do(visit_and_scroll)
     while True:
         schedule.run_pending()
-        time.sleep(60)
+        time.sleep(30)
 
-# Start background thread
-thread = threading.Thread(target=run_schedule, daemon=True)
-thread.start()
+# Start the background thread
+threading.Thread(target=run_scheduler, daemon=True).start()
 
 def get_logs():
-    return "\n".join(logs)
+    return "\n".join(reversed(logs))
 
-with gr.Blocks() as demo:
-    gr.Markdown("# 🤖 Playwright Keep-Alive Status")
-    output = gr.Textbox(label="Live System Logs", lines=15, value=get_logs(), interactive=False)
-    refresh_btn = gr.Button("Refresh Logs")
-    refresh_btn.click(fn=get_logs, outputs=output)
+# Build the Gradio UI
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# 🚀 Streamlit Keep-Alive Bot")
+    gr.Markdown(f"Targeting: `{URL}`")
+    
+    with gr.Row():
+        status_box = gr.Textbox(
+            label="Live Activity Logs (Newest First)", 
+            value=get_logs, 
+            every=5, # Auto-refresh every 5 seconds
+            lines=20,
+            interactive=False
+        )
+    
+    refresh_btn = gr.Button("Manual Refresh")
+    refresh_btn.click(fn=get_logs, outputs=status_box)
 
-demo.launch(server_name="0.0.0.0", server_port=7860)
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860)

requirements.txt

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