"""성평등가족부와 외교부의 lnb(좌측 메뉴)에서 active 상태 찾기."""
import sys, io, re
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')

import requests, urllib3
urllib3.disable_warnings()

s = requests.Session()
s.headers.update({
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0 Safari/537.36',
})

from bs4 import BeautifulSoup

samples = {
    '성평등가족부': 'https://www.mogef.go.kr/sp/geq/sp_geq_f001.do',
    '외교부': 'https://www.mofa.go.kr/www/wpge/m_3435/contents.do',
}

for site, url in samples.items():
    print(f'\n========== {site} ==========')
    r = s.get(url, verify=False, timeout=20)
    soup = BeautifulSoup(r.text, 'html.parser')

    # 1) lnb / sub_menu / left_menu에서 active/on/current 클래스
    for el in soup.find_all(['div', 'ul', 'nav']):
        cls = ' '.join(el.get('class', []))
        if re.search(r'lnb|sub_menu|left|gnb|sideMenu|side_menu|smb', cls, re.IGNORECASE):
            # active li
            actives = el.select('.on, .active, .current, .sel, [class*=active], [class*=current]')
            if actives:
                print(f'  [{cls}]:')
                for a in actives[:6]:
                    print(f'    "{a.get_text(" ", strip=True)[:100]}"  (class={" ".join(a.get("class", []))})')

    # 2) h2/h3 영역 주변 살펴보기
    h2s = soup.select('h2, h3')
    for h in h2s[:5]:
        print(f'  <{h.name}>: "{h.get_text(strip=True)[:60]}"  class={" ".join(h.get("class", []))}')

    # 3) 페이지 title에서 메뉴 추정 단서
    print(f'  title: {soup.title.get_text(" ", strip=True)[:150]}')

    # 4) meta name=description 등
    for m in soup.find_all('meta'):
        n = m.get('name', '')
        if n in ['description', 'keywords', 'subject']:
            print(f'  meta {n}: {m.get("content", "")[:100]}')