import sys, io, re, ssl, json, urllib.request
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
ctx = ssl.create_default_context(); ctx.check_hostname=False; ctx.verify_mode=ssl.CERT_NONE
BASE='https://www.jangsu.go.kr/index.jangsu?menuCd='
def fetch(cd, tries=3):
    for i in range(tries):
        try:
            return urllib.request.urlopen(urllib.request.Request(BASE+cd, headers={'User-Agent':'Mozilla/5.0'}), context=ctx, timeout=40).read().decode('utf-8','replace')
        except Exception as e:
            if i==tries-1: raise

# 대분류/중분류 라벨 — location nav(현재 위치) 또는 breadcrumb에서
def labels(cd):
    h=fetch(cd)
    # breadcrumb: class="location" 안의 텍스트들
    loc=re.search(r'class="(?:location|path|breadcrumb)[^"]*"(.*?)</(?:ul|div|nav)>', h, re.S)
    crumbs=[]
    if loc:
        crumbs=[re.sub(r'<[^>]+>','',x).strip() for x in re.findall(r'<(?:li|a|span)[^>]*>(.*?)</(?:li|a|span)>', loc.group(1))]
        crumbs=[c for c in crumbs if c and c not in ('홈','HOME','home')]
    # title
    t=re.search(r'<title>([^<|]+)', h)
    return crumbs, (t.group(1).strip() if t else '')

print('=== 누락 대분류 라벨 (108/107/303 등) ===')
for d in ['107','108','303','116','401','404','405']:
    try:
        cr,ti = labels(d+'000000000')
        print(f'  대{d}: title={ti!r} crumbs={cr[:3]}')
    except Exception as e:
        print(f'  대{d}: ERR {e}')
# 중분류 라벨도 location에서 확인 (108001 등)
print('=== 108 중분류 라벨 표본 ===')
for cd in ['108001001000','108002009000','108006008000']:
    cr,ti=labels(cd); print(f'  {cd}: title={ti!r} crumbs={cr}')