#!/usr/bin/env python3
import requests, re, json

url = "https://www.jinjiang.gov.cn/ztzl/lhzt/lyxx/sthj/"
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"}

r = requests.get(url, timeout=30, headers=headers)
html = r.text
print("LENGTH:", len(html))

# Links
links = re.findall(r'<a[^>]*href=["\']([^"\']+)["\']', html)
print("\n=== LINKS (first 30) ===")
for l in links[:30]:
    print(l)

# Titles
titles = re.findall(r'<a[^>]*>([^<]{5,80})</a>', html)
print("\n=== TITLES (first 20) ===")
for t in titles[:20]:
    print(t.strip())

# Pagination
pages = re.findall(r'page|index|list|Page|PageNo|pageno|pn=|pageNum|PageSize|pageCount', html, re.I)
print("\n=== PAGINATION HINTS ===")
print(pages[:20])

# Total
totals = re.findall(r'(?:共|total|records|条|页)[^<]{0,40}', html)
print("\n=== TOTAL HINTS ===")
for t in totals[:10]:
    print(t.strip())

# Look for AJAX/JS patterns
ajax = re.findall(r'ajax|fetch|XMLHttp|xhr|getJSON|\.load\(|dataType|type.*post|async', html, re.I)
print("\n=== AJAX HINTS ===")
print(ajax[:20])

# Form/input
inputs = re.findall(r'<input[^>]*>', html)
for i in inputs[:10]:
    print("INPUT:", i[:100])

# Scripts
scripts = re.findall(r'<script[^>]*src=["\']([^"\']+)["\']', html)
print("\n=== SCRIPTS ===")
for s in scripts[:15]:
    print(s)

# Search for data API
api = re.findall(r'api|service|Ajax|search|getList|getData|loadData|pageList', html, re.I)
print("\n=== API HINTS ===")
print(api[:20])