from flask import Flask, request, jsonify
import requests
from bs4 import BeautifulSoup

app = Flask(__name__)

def text_to_speech(msg, voice):
    # Start a session
    session = requests.Session()

    # Get the initial page to retrieve CSRF token and initial cookies
    initial_url = "https://texttospeech.online/home/tryme"
    response = session.get(initial_url)

    # Parse the response to extract the CSRF token
    soup = BeautifulSoup(response.text, 'html.parser')
    csrf_token = soup.find('input', {'name': 'csrf_test_name'})['value']

    # Define payload with dynamic CSRF token
    payload = {
        "csrf_test_name": csrf_token,
        "front_tryme_language": "en-IN",  # Assuming the language is fixed
        "front_tryme_voice": voice,
        "front_tryme_text": msg
    }

    # Define headers
    headers = {
        "Accept": "*/*",
        "Accept-Encoding": "gzip, deflate, br, zstd",
        "Accept-Language": "en-US,en;q=0.9",
        "Connection": "keep-alive",
        "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
        "Host": "texttospeech.online",
        "Origin": "https://texttospeech.online",
        "Referer": "https://texttospeech.online/",
        "Sec-Ch_Ua": '"Not/A)Brand";v="8", "Chromium";v="126", "Microsoft Edge";v="126"',
        "Sec-Ch_Ua-Mobile": "?0",
        "Sec-Ch_Ua-Platform": '"Windows"',
        "Sec-Fetch-Dest": "empty",
        "Sec-Fetch-Mode": "cors",
        "Sec-Fetch-Site": "same-origin",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36 Edg/126.0.0.0",
        "X-Requested-With": "XMLHttpRequest"
    }

    # Make the POST request with the session
    post_url = "https://texttospeech.online/home/tryme_action/"
    response = session.post(post_url, headers=headers, data=payload)

    # Parse the JSON response
    response_data = response.json()

    if response_data["result"]:
        tts_uri = response_data["tts_uri"]
        return tts_uri
    else:
        return None

@app.route('/text_to_speech', methods=['POST'])
def api_text_to_speech():
    # Extract parameters from URL query
    url_msg = request.args.get('msg')
    url_voice = request.args.get('voice')

    # Extract parameters from JSON body
    json_data = request.json
    body_msg = json_data.get('msg') if json_data else None
    body_voice = json_data.get('voice') if json_data else None

    # Prioritize URL parameters over JSON body parameters
    msg = url_msg if url_msg else body_msg
    voice = url_voice if url_voice else body_voice

    if not msg or not voice:
        return jsonify({"error": "Please provide both 'msg' and 'voice' parameters."}), 400

    tts_uri = text_to_speech(msg, voice)
    if tts_uri:
        return jsonify({"tts_uri": tts_uri})
    else:
        return jsonify({"error": "Failed to generate text-to-speech audio."}), 500

if __name__ == '__main__':
    app.run(debug=True, port=7860, host="0.0.0.0")