Tfe

scripts/elhuyar_ahotsa.py

import urllib.request
import re
import ssl
import json
import sys
import subprocess

def get_csrf_token(url):
    """
    Fetches the given URL and extracts the CSRF middleware token.
    """
    try:
        # Create a default SSL context that does not verify certificates
        context = ssl._create_unverified_context()

        with urllib.request.urlopen(url, context=context) as response:
            html = response.read().decode('utf-8')
            # Use regex to find the csrfmiddlewaretoken
            match = re.search(r'<input[^>]*name="csrfmiddlewaretoken"[^>]*value="([^"]+)"', html)
            if match:
                return match.group(1)
            else:
                return "CSRF token not found."
    except Exception as e:
        return f"An error occurred: {e}"

def get_audio_path(post_url, text, token, target_url):
    """
    Makes a POST request to get an audio path.
    """
    try:
        # Prepare the data for the POST request
        post_data = {
            'csrfmiddlewaretoken': token,
            'language': 'eu',
            'voice': '29',
            'text': text
        }
        
        # Encode the data as X-WWW-Form-Urlencoded
        data = urllib.parse.urlencode(post_data).encode('utf-8')
        
        # create cookie header
        cookie = f"csrftoken={token}"
        # Create a request object
        req = urllib.request.Request(
            post_url, 
            data=data, 
            headers={
                'Cookie': cookie,
                'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
                'X-Requested-With': 'XMLHttpRequest',
                'Referer': target_url,
                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'
            }
        )
        
        # Create a default SSL context that does not verify certificates
        context = ssl._create_unverified_context()
        
        with urllib.request.urlopen(req, context=context) as response:
            # Read and print the response
            response_data = response.read().decode('utf-8')
            # Parse json result
            json_result = json.loads(response_data)
            # get the result audio_path
            return json_result.get('audio_path')
    except Exception as e:
        print(f"An error occurred during the POST request: {e}")
        return None

def play_audio(audio_url):
    """
    Plays the audio from the given URL using ffplay.
    """
    if not audio_url:
        print("No audio URL provided.")
        return
    try:
        # Construct the full URL if it's a relative path
        if not audio_url.startswith('http'):
            audio_url = f"https://ttsneuronala.elhuyar.eus{audio_url}"
        
        print(f"Playing audio from: {audio_url}")
        subprocess.run(['ffplay', '-nodisp', '-autoexit', audio_url], check=True, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
    except FileNotFoundError:
        print("ffplay not found. Please install ffmpeg.")
    except subprocess.CalledProcessError as e:
        print(f"An error occurred while trying to play the audio: {e}")
    except Exception as e:
        print(f"An unexpected error occurred: {e}")


if __name__ == "__main__":
    text = " ".join(sys.argv[1:])
    if not text:
        print("No text provided")
        sys.exit(1)
    
    target_url = "https://ttsneuronala.elhuyar.eus/es"
    token = get_csrf_token(target_url)

    if "CSRF token not found" in token or "An error occurred" in token:
        print(token)
    else:
        post_url = "https://ttsneuronala.elhuyar.eus/ajax/get_audio_from_box"
        audio_path = get_audio_path(post_url, text, token, target_url)
        if audio_path:
            play_audio(audio_path)