File size: 1,422 Bytes
2976b80
 
3d44584
2976b80
 
 
 
 
4d1489a
3d44584
2976b80
 
 
 
 
 
 
262720b
 
2976b80
4d1489a
2976b80
262720b
2976b80
262720b
 
4d1489a
 
 
bdf7117
 
 
 
 
262720b
2976b80
 
bdf7117
2976b80
 
 
 
 
 
 
3d44584
4d1489a
2976b80
 
3d44584
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
# 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'):
    tts = gTTS(text=text, lang=lang)
    tts.save("output.mp3")
    return "output.mp3"

def process_url(url):
    text = get_text_from_webpage(url)
    lang = detect(text)
    audio_file = text_to_speech(text, lang)
    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...")
    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, 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