import os
import pandas as pd
import re
import time

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By

options = Options()
options.binary_location = "C:\\SeleniumDrivers\\chrome-win64\\chrome.exe"
service = Service("C:\\SeleniumDrivers\\chromedriver-win64\\chromedriver.exe")
driver= webdriver.Chrome(service=service, options=options)

driver.set_window_position(0,0)
driver.set_window_size(1024,720)

driver.get("https://translate.google.com.mx/?sl=es&tl=en&op=translate")
time.sleep(5)

captions_dir= "files\\captions"
translations_dir= "files\\translations"
files_list= []

def get_files_list(captions_dir, files_list) -> list:
    for f in os.scandir(captions_dir):
        if f.is_dir():
            get_files_list(f.path, files_list)
        else:
            files_list.append(f.path)
    return files_list

file_paths= get_files_list(captions_dir, files_list)
print(file_paths)

for file_path in file_paths[0:1]:
    print("\nTraduciendo el archivo " + file_path)
    lines_df= pd.read_table(file_path)
    print(lines_df)

    regular_exp = re.compile('[0-9]{2}:[0-9]{2}.[0-9]{3} --> [0-9]{2}:[0-9]{2}.[0-9]{3}')

    textarea_element= driver.find_element(By.XPATH, "//*[@aria-label='Texto de origen']")

    for index, line in lines_df.iterrows():
        tmp_line= line["WEBVTT"]

        if not regular_exp.match(tmp_line):
            
            textarea_element.send_keys(tmp_line)
            time.sleep(4)

            transation_element= driver.find_element(By.XPATH, "/html/body/c-wiz/div/div[2]/c-wiz/div[2]/c-wiz/div[1]/div[2]/div[2]/c-wiz/div/div[6]/div/div[1]/span[1]/span")
            print(transation_element.text)

            line["WEBVTT"]= transation_element.text
            textarea_element.clear()

    print(lines_df)  
    
    translation_path= file_path.replace(captions_dir, translations_dir)
    os.makedirs(os.path.dirname(translation_path), exist_ok=True)
    lines_df.to_csv(translation_path, index=False)