app.py

# app.py
# =============
# This is a complete app.py file for a web scraping and text-to-speech app using gTTS, BeautifulSoup, langdetect, and Gradio.

import requests
from bs4 import BeautifulSoup
from gtts import gTTS
import os
import gradio as gr
from langdetect import detect

def get_text_from_webpage(url):
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
    text = soup.get_text()
    return text

def text_to_speech(text, lang='en', slow=False, tld='com'):
    tts = gTTS(text=text, lang=lang, slow=slow, tld=tld)
    tts.save("output.mp3")
    return "output.mp3"

def process_url(url, lang, slow, tld):
    text = get_text_from_webpage(url)
    audio_file = text_to_speech(text, lang, slow, tld)
    return audio_file, text

# Create Gradio interface
with gr.Blocks() as demo:
    url_input = gr.Textbox(lines=1, placeholder="Enter the URL of the webpage...")
    lang_input = gr.Dropdown(choices=["en", "fr", "de", "es", "it", "ja", "ko", "zh-CN", "zh-TW", "ru"], label="Language", value="en")
    slow_checkbox = gr.Checkbox(label="Slow Speed")
    tld_input = gr.Dropdown(choices=["com", "co.uk", "fr", "de", "es", "it", "co.jp", "co.kr", "com.cn", "com.tw"], label="Accent", value="com")
    audio_output = gr.Audio(label="Generated Speech")
    text_output = gr.Textbox(lines=10, label="Extracted Text")
    greet_btn = gr.Button("Submit")
    greet_btn.click(fn=process_url, inputs=[url_input, lang_input, slow_checkbox, tld_input], outputs=[audio_output, text_output])

if __name__ == "__main__":
    demo.launch()

# Dependencies
# =============
# The following dependencies are required to run this app:
# - requests
# - beautifulsoup4
# - gtts
# - langdetect
# - gradio
#
# You can install these dependencies using pip:
# pip install requests beautifulsoup4 gtts langdetect gradio