#!/usr/bin/env python3
"""Analyze detail page of jingmen.gov.cn (Hanweb CMS)"""
import sys, re

html = sys.stdin.buffer.read().decode('utf-8', errors='replace')
print("Length:", len(html))

t = re.search(r'<title>([^<]+)</title>', html)
if t:
    print("Title:", t.group(1))

# Meta tags
for meta in re.findall(r'<meta[^>]+>', html, re.I):
    low = meta.lower()
    if any(k in low for k in ['pubdate','publishdate','column','source','author','date','description']):
        print("Meta:", meta.strip()[:150])

# Content containers  
for cls in ['content','article','zw','con','text','nr','detail','main','TRS_Editor','infoContent','bt_content','font','view','news']:
    pat = re.compile(r'<(div|p|section)[^>]*?class=[\"\'][^\"\']*' + cls + r'[^\"\']*[\"\'][^>]*>', re.I)
    for m in pat.finditer(html):
        print("Match: class containing", cls, "at", m.start())
        
# Show key sections
print("\n=== Before body ===")
idx = html.find('<body')
if idx > 0:
    print(html[idx:idx+2000])
PYEOF