#!/usr/bin/env python3
"""Debug ningguo list parsing"""
import requests
from bs4 import BeautifulSoup
import re

headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'}
s = requests.Session()
s.headers.update(headers)

url = 'https://www.ningguo.gov.cn/XxgkContent/showList/383/22474/page_1.html'
r = s.get(url, timeout=60, verify=False)
if 'token_verified=true' in r.text:
    s.cookies.set('token_verified', 'true')
    r = s.get(url, timeout=60, verify=False)
r.encoding = 'utf-8'

soup = BeautifulSoup(r.text, 'html.parser')

# Find ALL uls and count li items
for i, ul in enumerate(soup.find_all('ul')):
    lis = ul.find_all('li', recursive=False)
    if len(lis) >= 3:
        a_count = sum(1 for li in lis if li.find('a', href=True))
        # Show every li's content
        print(f'UL #{i}: {len(lis)} li, {a_count} with links')
        for li in lis:
            a = li.find('a', href=True)
            href = a['href'] if a else 'N/A'
            txt = li.get_text(strip=True)[:100]
            print(f'  href={href} txt="{txt}"')
        print(f'---')

# Also try finding the specific section
print('\n=== Any div with list-ish class ===')
for div in soup.find_all('div'):
    cls = ' '.join(div.get('class', []))
    if any(kw in cls.lower() for kw in ['list', 'news', 'article', 'xxgk']):
        lis = div.find_all('li')
        if len(lis) >= 3:
            print(f'div.{cls}: {len(lis)} li')
            for li in lis[:3]:
                a = li.find('a', href=True)
                print(f'  <a href="{a["href"] if a else "N/A"}">{li.get_text(strip=True)[:60]}')