keno-cctv.ru 2026

import requests
from urllib.parse import urljoin, urlparse
import re

def check_site_language_and_content(url):
try:
response = requests.get(url, timeout=10)
response.raise_for_status()
content_type = response.headers.get('content-type', '')
if 'text/html' not in content_type:
return None, None, "Non-HTML content"
content = response.text
# detect language via meta or html tag
lang_match = re.search(r']+lang=["\']?([a-z]{2})', content, re.IGNORECASE)
lang = lang_match.group(1).lower() if lang_match else None
if not lang:
# fallback: check common words
if re.search(r'\b(?:и|в|на|не|что|как)\b', content):
lang = 'ru'
elif re.search(r'\b(?:the|and|or|in|on|at)\b', content):
lang = 'en'
title_match = re.search(r'', content, re.IGNORECASE | re.DOTALL)
title = title_match.group(1).strip() if title_match else ''
return lang, title, content[:500]
except Exception as e:
return None, None, str(e)

lang, title, snippet = check_site_language_and_content('LINK1)
(lang, title, snippet[:200])

Telegram: https://t.me/+W5ms_rHT8lRlOWY5