#!/usr/bin/env python3
import sys, re, subprocess, json
from bs4 import BeautifulSoup

url = "https://www.shucheng.gov.cn/site/tpl/5186?pid=7367495&id=7367498&organId=6596321"
headers = [
    "User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
    "Cookie: __jsluid_s=44466aca9d819cfbd85efd0d77815ac0",
]

cmd = ["curl", "-sL", "--max-time", "15"]
for h in headers:
    cmd.extend(["-H", h])
cmd.append(url)

result = subprocess.run(cmd, capture_output=True, text=True, timeout=30)
html = result.stdout
soup = BeautifulSoup(html, "html.parser")

# Extract all script content
for i, script in enumerate(soup.find_all("script")):
    content = script.string or ""
    if len(content) > 100:
        # Check for API URLs
        api_urls = re.findall(r'(https?://[^"\']*?api[^"\']*?)[\'"]', content)
        if api_urls:
            print(f"Script {i}: found APIs: {api_urls}")
        
        # Check for data arrays/objects
        if "data" in content.lower() or "url" in content.lower() or "list" in content.lower():
            print(f"\nScript {i} ({len(content)} chars):")
            lines = content.split("\n")
            relevant = [l for l in lines if any(k in l.lower() for k in ["url", "api", "page", "data", "list", "get", "load", "organid"])]
            for l in relevant[:20]:
                print(f"  {l.strip()[:120]}")

# Check for xzList or similar data
for script in soup.find_all("script"):
    content = script.string or ""
    if "var xzList" in content or "xzList" in content:
        print("\n\n=== xzList data ===")
        print(content[:1000])