new deep_translator

import os
import re
import textwrap
from deep_translator import GoogleTranslator

folder_path = r"c:\\download\\myprotein\\extracted\\"
translator = GoogleTranslator(source='auto', target='ro')
tags_to_translate = [
    r'(<title>)(.*?)(<\/title>)',
    r'(<meta name="description" content=")(.*?)("\/>)',
    r'(<div class="sc-jKDlA-D hSgfYV sc-glENfF hIVUeB">)(.*?)(<\/div>)',
    r'(<p>)(.*?)(<\/p>)',
    r'(<h4 class="sc-jMKfon fhunKk">)(.*?)(<\/h4>)',
    r'(<h2">)(.*?)(<\/h2>)'
    # ... alte tag-uri, structurate similar
]

def translate_in_parts(text, translator, max_length=4800):
    parts = textwrap.wrap(text, max_length, break_long_words=False)
    translated = ''
    for part in parts:
        if part:
            translated += translator.translate(part)
    return translated

for filename in os.listdir(folder_path):
    if filename.endswith((".html", ".htm")):
        with open(os.path.join(folder_path, filename), 'r', encoding='utf-8') as file:
            html_content = file.read()

        for tag in tags_to_translate:
            matches = re.finditer(tag, html_content, re.DOTALL)

            for match in matches:
                full_match = match.group(0)
                tag_start = match.group(1)
                tag_content = match.group(2)
                tag_end = match.group(3)

                # Traducem conținutul tag-ului în fragmente
                translated_content = translate_in_parts(tag_content, translator)
                translated_tag = f"{tag_start}{translated_content}{tag_end}"

                html_content = html_content.replace(full_match, translated_tag)

        new_filename = f"{filename.split('.')[0]}_ro.html"
        translated_folder_path = os.path.join(folder_path, 'translated')
        if not os.path.exists(translated_folder_path):
            os.mkdir(translated_folder_path)

        with open(os.path.join(translated_folder_path, new_filename), 'w', encoding='utf-8') as file:
            file.write(html_content)