update with docker

Dockerfile

@@ -0,0 +1,34 @@
+# Use an official Python runtime as a parent image
+FROM python:3.9-slim
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Copy the current directory contents into the container at /app
+COPY . /app
+
+# Install necessary dependencies including ffmpeg
+RUN apt-get update && apt-get install -y \
+    wget \
+    curl \
+    unzip \
+    git \
+    chromium \
+    chromium-driver \
+    ffmpeg \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install pip and the required Python packages
+RUN pip install --upgrade pip \
+    && pip install selenium requests gradio \
+    && pip install git+https://github.com/openai/whisper.git
+
+# Set environment variables for Selenium
+ENV CHROME_BIN=/usr/bin/chromium
+ENV CHROMEDRIVER_BIN=/usr/bin/chromedriver
+
+# Expose the port the app will run on
+EXPOSE 7860
+
+# Command to run the Gradio app
+CMD ["python", "app.py"]

app.py

@@ -71,4 +71,4 @@ with gr.Blocks() as interface:
 
 # Launch the app
 if __name__ == "__main__":
-    interface.launch(share=True)
+    interface.launch(server_name="0.0.0.0", server_port=7860)

download_video.py

@@ -1,4 +1,5 @@
 from selenium import webdriver
+from selenium.webdriver.chrome.service import Service
 from selenium.webdriver.common.by import By
 from selenium.webdriver.common.keys import Keys
 from selenium.webdriver.support.ui import WebDriverWait
@@ -15,25 +16,17 @@ def download_mp3_selenium(youtube_url):
     options.add_argument('--disable-gpu')  # Disable GPU to ensure it runs in cloud environments
     options.add_argument('--verbose')
     options.add_argument('--log-path=/tmp/chromedriver.log')
-    options.add_argument(
-    "user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.5615.49 Safari/537.36"
-    
-)
 
     log_contents = ""  # Initialize log_contents
-    driver = webdriver.Chrome(options=options)
 
-    try:
-        driver.get("https://www.google.com")
-        print("Page title was '{}'".format(driver.title))
-    except Exception as e:
-        print(e)
+    # Use the Service class to specify the path to the ChromeDriver binary
+    service = Service(executable_path="/usr/bin/chromedriver")
 
-    print(driver.capabilities['browserVersion'])
-    print(driver.capabilities['chrome']['chromedriverVersion'])
+    # Pass the service and options to the WebDriver
+    driver = webdriver.Chrome(service=service, options=options)
 
     # Set up WebDriverWait (with a timeout of 10 seconds)
-    wait = WebDriverWait(driver, 20)
+    wait = WebDriverWait(driver, 10)
 
     # Open the YouTube video page
     driver.get(youtube_url)

environment.yml

@@ -1,12 +0,0 @@
-name: yt-whisper-2
-channels:
-  - defaults
-  - conda-forge
-dependencies:
-  - python=3.9
-  - pip
-  - pip:
-      - selenium
-      - requests
-      - gradio
-      - openai-whisper @ git+https://github.com/openai/whisper.git

requirements.txt

@@ -1,12 +1,3 @@
-# numpy<2  # Pinning NumPy to a version below 2.0
-# gradio==3.39.0  # Downgrade Gradio to work with Pydantic v1
-# pytube==15.0.0
-# git+https://github.com/openai/whisper.git  # Install Whisper from GitHub
-# torch==2.0.1
-# pydantic==1.10  # Use Pydantic v1 to avoid the incompatibility
-# git+https://github.com/microsoft/playwright-python.git
-# BeautifulSoup4
-# requests
 selenium
 webdriver-manager
 requests